2016 |
Jordao, Artur; Schwartz, William Robson Oblique Random Forest based on Partial Least Squares Applied to Pedestrian Detection Inproceedings IEEE International Conference on Image Processing (ICIP), pp. 2931-2935, 2016. Links | BibTeX | Tags: DeepEyes, Pedestrian Detection, VER+ @inproceedings{Correia:2016:ICIP, title = {Oblique Random Forest based on Partial Least Squares Applied to Pedestrian Detection}, author = {Artur Jordao and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/OBLIQUE-RANDOM-FOREST-BASED-ON-PARTIAL-LEAST-SQUARES-APPLIED-TO.pdf}, year = {2016}, date = {2016-09-25}, booktitle = {IEEE International Conference on Image Processing (ICIP)}, pages = {2931-2935}, keywords = {DeepEyes, Pedestrian Detection, VER+}, pubstate = {published}, tppubtype = {inproceedings} } |
Goncalves, Gabriel Resende License Plate Recognition based on Temporal Redundancy Masters Thesis Federal University of Minas Gerais, 2016. Abstract | Links | BibTeX | Tags: Automatic License Plate Recognition, DeepEyes, GigaFrames @mastersthesis{Goncalves:2016:MSc, title = {License Plate Recognition based on Temporal Redundancy}, author = {Gabriel Resende Goncalves}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/03/dissertation_2016_Gabriel.pdf}, year = {2016}, date = {2016-08-26}, school = {Federal University of Minas Gerais}, abstract = {Recognition of vehicle license plates is an important task applied to a myriad of real scenarios. Most approaches in the literature first detect an on-track vehicle, locate the license plate, perform a segmentation of its characters and then recognize the characters using an Optical Character Recognition (OCR) approach. However, these approaches focus on performing these tasks using only a single frame of each vehicle in the video. Therefore, such techniques might have their recognition rates reduced due to noise present in that particular frame. On the other hand, in this work we propose an approach to automatically detect the vehicle on the road and identify (locate/recognize) its license plate based on temporal redundant information instead of selecting a single frame to perform the recognition. We also propose two post-processing steps that can be employed to improve the accuracy of the system by querying a license plate database (e.g., the Department of Motor Vehicles database containing a list of all issued license plates and car models). Experimental results demonstrate that it is possible to improve the vehicle recognition rate in 15.5 percentage points (p.p.) (an increase of 23.38%) of the baseline results, using our proposal temporal redundancy approach. Furthermore, additional 7.8 p.p. are achieved using the two post-processing approaches, leading to a final recognition rate of 89.6% on a dataset with 5,200 frame images of $300$ vehicles recorded at Federal University of Minas Gerais (UFMG). In addition, this work also proposes a novel benchmark, designed specifically to evaluate character segmentation techniques, composed of a dataset of 2,000 Brazilian license plates (resulting in 14,000 alphanumeric symbols) and an evaluation protocol considering a novel evaluation measure, the Jaccard-Centroid coefficient.}, keywords = {Automatic License Plate Recognition, DeepEyes, GigaFrames}, pubstate = {published}, tppubtype = {mastersthesis} } Recognition of vehicle license plates is an important task applied to a myriad of real scenarios. Most approaches in the literature first detect an on-track vehicle, locate the license plate, perform a segmentation of its characters and then recognize the characters using an Optical Character Recognition (OCR) approach. However, these approaches focus on performing these tasks using only a single frame of each vehicle in the video. Therefore, such techniques might have their recognition rates reduced due to noise present in that particular frame. On the other hand, in this work we propose an approach to automatically detect the vehicle on the road and identify (locate/recognize) its license plate based on temporal redundant information instead of selecting a single frame to perform the recognition. We also propose two post-processing steps that can be employed to improve the accuracy of the system by querying a license plate database (e.g., the Department of Motor Vehicles database containing a list of all issued license plates and car models). Experimental results demonstrate that it is possible to improve the vehicle recognition rate in 15.5 percentage points (p.p.) (an increase of 23.38%) of the baseline results, using our proposal temporal redundancy approach. Furthermore, additional 7.8 p.p. are achieved using the two post-processing approaches, leading to a final recognition rate of 89.6% on a dataset with 5,200 frame images of $300$ vehicles recorded at Federal University of Minas Gerais (UFMG). In addition, this work also proposes a novel benchmark, designed specifically to evaluate character segmentation techniques, composed of a dataset of 2,000 Brazilian license plates (resulting in 14,000 alphanumeric symbols) and an evaluation protocol considering a novel evaluation measure, the Jaccard-Centroid coefficient. |
Jordao, Artur The Good, the Fast and the Better Pedestrian Detector Masters Thesis Federal University of Minas Gerais, 2016. Abstract | Links | BibTeX | Tags: DeepEyes, DET, GigaFrames, Pedestrian Detection, VER+ @mastersthesis{Jordao:2016:MSc, title = {The Good, the Fast and the Better Pedestrian Detector}, author = {Artur Jordao}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/03/dissertation_2016_ArturJordao.pdf}, year = {2016}, date = {2016-06-24}, school = {Federal University of Minas Gerais}, abstract = {Pedestrian detection is a well-known problem in Computer Vision, mostly because of its direct applications in surveillance, transit safety and robotics. In the past decade, several efforts have been performed to improve the detection in terms of accuracy, speed and feature enhancement. In this work, we propose and analyze techniques focusing on these points. First, we develop an accurate oblique random forest (oRF) associated with Partial Least Squares (PLS). The method utilizes the PLS to find a decision surface, at each node of a decision tree, that better splits the samples presented to it, based on some purity criterion. To measure the advantages provided by PLS on the oRF, we compare the proposed method with the oRF based on SVM. Second, we evaluate and compare filtering approaches to reduce the search space and keep only potential regions of interest to be presented to detectors, speeding up the detection process. Experimental results demonstrate that the evaluated filters are able to discard a large number of detection windows without compromising the accuracy. Finally, we propose a novel approach to extract powerful features regarding the scene. The method combines results of distinct pedestrian detectors by reinforcing the human hypothesis, whereas suppressing a significant number of false positives due to the lack of spatial consensus when multiple detectors are considered. Our proposed approach, referred to as Spatial Consensus (SC), outperforms all previously published state-of-the-art pedestrian detection methods.}, keywords = {DeepEyes, DET, GigaFrames, Pedestrian Detection, VER+}, pubstate = {published}, tppubtype = {mastersthesis} } Pedestrian detection is a well-known problem in Computer Vision, mostly because of its direct applications in surveillance, transit safety and robotics. In the past decade, several efforts have been performed to improve the detection in terms of accuracy, speed and feature enhancement. In this work, we propose and analyze techniques focusing on these points. First, we develop an accurate oblique random forest (oRF) associated with Partial Least Squares (PLS). The method utilizes the PLS to find a decision surface, at each node of a decision tree, that better splits the samples presented to it, based on some purity criterion. To measure the advantages provided by PLS on the oRF, we compare the proposed method with the oRF based on SVM. Second, we evaluate and compare filtering approaches to reduce the search space and keep only potential regions of interest to be presented to detectors, speeding up the detection process. Experimental results demonstrate that the evaluated filters are able to discard a large number of detection windows without compromising the accuracy. Finally, we propose a novel approach to extract powerful features regarding the scene. The method combines results of distinct pedestrian detectors by reinforcing the human hypothesis, whereas suppressing a significant number of false positives due to the lack of spatial consensus when multiple detectors are considered. Our proposed approach, referred to as Spatial Consensus (SC), outperforms all previously published state-of-the-art pedestrian detection methods. |
Rodrigues, Marco Tulio Alves Detecção de Mudanças em Cenas Terrestres usando Imagens Aéreas PhD Thesis 2016. Abstract | Links | BibTeX | Tags: Change Detection @phdthesis{Rodrigues:2016:PhD, title = {Detecção de Mudanças em Cenas Terrestres usando Imagens Aéreas}, author = {Marco Tulio Alves Rodrigues}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/03/dissertation_2016_MarcoTulio.pdf}, year = {2016}, date = {2016-03-22}, abstract = {This study addresses the problem of change detection in landscapes using aerial images acquired at different times, important for many applications. The monitoring pipeline, for instance, the usual way to change detection is a task performed by human operators which evaluates a video of a monitoring camera and searches for changes in the scene from the comparison of image pairs. This procedure is prone to errors because it is a tedious task, therefore is a justification to automated method. Besides enabling the reduction of errors and speed up the monitoring process, a system automatic can be used as a filter to provide a set of key frames that should receive more attention from the operator. Thus, the system can help the operators on the decision making process regarding the actions to be performed. The basic procedure for detecting changes is to find a set of pixels or regions that are different in another test image. However, images acquired at different dates may be influenced by radiometric and registration factors. In other words, the influence of camera movement, lighting variation, and atmospheric variation must be minimized. One of the methods proposed extracts local descriptors in the image blocks and provides an estimate of change using a non-parametric model (KDE). Unlike background subtraction and remote sensing methods which are based on pixels and assume independence between them, the proposed approach not requires a complex learning phase and it is capable of detecting changes using only two images. The second method applies an image segmentation before make the matching of the similar regions. In the experiments, the proposed approaches are compared to techniques used in change detection. According to the results, the proposed approach based on non-parametric model outperforms other methods found in the literature, mainly due to the fact that the approach is more robust to lighting variation. The results also demonstrate that the approach is able to filter images that should be further analyzed by operators.}, keywords = {Change Detection}, pubstate = {published}, tppubtype = {phdthesis} } This study addresses the problem of change detection in landscapes using aerial images acquired at different times, important for many applications. The monitoring pipeline, for instance, the usual way to change detection is a task performed by human operators which evaluates a video of a monitoring camera and searches for changes in the scene from the comparison of image pairs. This procedure is prone to errors because it is a tedious task, therefore is a justification to automated method. Besides enabling the reduction of errors and speed up the monitoring process, a system automatic can be used as a filter to provide a set of key frames that should receive more attention from the operator. Thus, the system can help the operators on the decision making process regarding the actions to be performed. The basic procedure for detecting changes is to find a set of pixels or regions that are different in another test image. However, images acquired at different dates may be influenced by radiometric and registration factors. In other words, the influence of camera movement, lighting variation, and atmospheric variation must be minimized. One of the methods proposed extracts local descriptors in the image blocks and provides an estimate of change using a non-parametric model (KDE). Unlike background subtraction and remote sensing methods which are based on pixels and assume independence between them, the proposed approach not requires a complex learning phase and it is capable of detecting changes using only two images. The second method applies an image segmentation before make the matching of the similar regions. In the experiments, the proposed approaches are compared to techniques used in change detection. According to the results, the proposed approach based on non-parametric model outperforms other methods found in the literature, mainly due to the fact that the approach is more robust to lighting variation. The results also demonstrate that the approach is able to filter images that should be further analyzed by operators. |
dos Junior, Cassio Elias Santos; Kijak, Ewa; Gravier, Guillaume; Schwartz, William Robson Partial least squares for face hashing Journal Article Neurocomputing, 213 , pp. 34–47, 2016. Links | BibTeX | Tags: Face Identification, Face Recognition, Featured Publication, Partial Least Squares @article{Santos:2016:Neurocomputing, title = {Partial least squares for face hashing}, author = {Cassio Elias Santos dos Junior and Ewa Kijak and Guillaume Gravier and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/paper_2016_Neurocomputing_Santos.pdf}, year = {2016}, date = {2016-02-03}, journal = {Neurocomputing}, volume = {213}, pages = {34--47}, keywords = {Face Identification, Face Recognition, Featured Publication, Partial Least Squares}, pubstate = {published}, tppubtype = {article} } |
Junior, Antonio Carlos Nazare; Schwartz, William Robson A scalable and flexible framework for smart video surveillance Journal Article Computer Vision and Image Understanding, 144 (C), pp. 258–275, 2016. Links | BibTeX | Tags: Smart Surveillance, Smart Surveillance Framework, SSF, Surveillance Systems, VER+, Video Surveillance @article{Nazare:2016:CVIU, title = {A scalable and flexible framework for smart video surveillance}, author = {Antonio Carlos Nazare Junior and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/paper_2016_CVIU.pdf}, year = {2016}, date = {2016-01-01}, journal = {Computer Vision and Image Understanding}, volume = {144}, number = {C}, pages = {258--275}, keywords = {Smart Surveillance, Smart Surveillance Framework, SSF, Surveillance Systems, VER+, Video Surveillance}, pubstate = {published}, tppubtype = {article} } |
Rodrigues, Marco Tulio Alves; de Mesquita, Daniel Balbino; Nascimento, Erickson R; Schwartz, William Robson Change detection based on feature invariant to monotonic transforms and spatially constrained matching Journal Article Journal of Electronic Imaging, 25 (1), pp. 1-10, 2016. Links | BibTeX | Tags: Change Detection @article{Rodrigues:2016:JEI, title = {Change detection based on feature invariant to monotonic transforms and spatially constrained matching}, author = {Marco Tulio Alves Rodrigues and Daniel Balbino de Mesquita and Erickson R Nascimento and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/paper_2016_JEI.pdf}, year = {2016}, date = {2016-01-01}, journal = {Journal of Electronic Imaging}, volume = {25}, number = {1}, pages = {1-10}, keywords = {Change Detection}, pubstate = {published}, tppubtype = {article} } |
Dutra, Cristianne Rodrigues Santos Técnicas Otimizadas para Reidentificaçâo de Pessoas Masters Thesis Federal University of Minas Gerais, 2016. Links | BibTeX | Tags: DeepEyes, GigaFrames, Person Re-Identification, VER+ @mastersthesis{Dutra:2016:MSc, title = {Técnicas Otimizadas para Reidentificaçâo de Pessoas}, author = {Cristianne Rodrigues Santos Dutra}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/thesis_2016_Cristianne.pdf}, year = {2016}, date = {2016-01-01}, school = {Federal University of Minas Gerais}, keywords = {DeepEyes, GigaFrames, Person Re-Identification, VER+}, pubstate = {published}, tppubtype = {mastersthesis} } |
dos Jr., Cassio Santos E; Kijak, Ewa; Gravier, Guillaume; Schwartz, William Robson Partial least squares for face hashing Journal Article Neurocomputing, 213 , pp. 34-47, 2016. @article{Santos:2016:Neurocomputingb, title = {Partial least squares for face hashing}, author = {Cassio Santos E dos Jr. and Ewa Kijak and Guillaume Gravier and William Robson Schwartz}, url = {http://www.dcc.ufmg.br/~william/papers/paper_2016_Neurocomputing_Santos.pdf}, doi = {10.1016/j.neucom.2016.02.083}, year = {2016}, date = {2016-01-01}, journal = {Neurocomputing}, volume = {213}, pages = {34-47}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
2015 |
Colque, Rensso Victor Hugo Mora; Junior, Carlos Antonio Caetano; Schwartz, William Robson Histograms of Optical Flow Orientation and Magnitude to Detect Anomalous Events in Videos Inproceedings Conference on Graphics, Patterns and Images (SIBGRAPI), pp. 1-8, 2015. Links | BibTeX | Tags: Anomalous Event Detection, HOFM, SmartView @inproceedings{SIBGRAPI:2015:Colque, title = {Histograms of Optical Flow Orientation and Magnitude to Detect Anomalous Events in Videos}, author = {Rensso Victor Hugo Mora Colque and Carlos Antonio Caetano Junior and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/paper_camera_ready.pdf}, year = {2015}, date = {2015-08-25}, booktitle = {Conference on Graphics, Patterns and Images (SIBGRAPI)}, pages = {1-8}, keywords = {Anomalous Event Detection, HOFM, SmartView}, pubstate = {published}, tppubtype = {inproceedings} } |
dos Junior, Cassio Elias Santos Partial Least Squares for Face Hashing Masters Thesis Federal University of Minas Gerais, 2015. Abstract | Links | BibTeX | Tags: DeepEyes, Face Identification, Face Recognition, GigaFrames, Indexing Structure, Local Sensitive Hashing, Partial Least Squares, VER+ @mastersthesis{Santos:2015:MSc, title = {Partial Least Squares for Face Hashing}, author = {Cassio Elias Santos dos Junior}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/dissertation_2015_Cassio.pdf}, year = {2015}, date = {2015-08-24}, school = {Federal University of Minas Gerais}, abstract = {Face identification is an important research topic due to areas such as its application to surveillance, forensics and human-computer interaction. In the past few years, a myriad of methods for face identification has been proposed in the literature, with just a few among them focusing on scalability. In this work, we propose a simple but efficient approach for scalable face identification based on partial least squares (PLS) and random independent hash functions inspired by locality-sensitive hashing (LSH), resulting in the PLS for hashing (PLSH) approach. The original PLSH approach is further extended using feature selection to reduce the computational cost to evaluate the PLS-based hash functions, resulting in the state-of-the-art extended PLSH approach (ePLSH). The proposed approach is evaluated in the dataset FERET and in the dataset FRGCv1. The results show significant reduction in the number of subjects evaluated in the face identification (reduced to 0.3% of the gallery), providing averaged speedups up to 233 times compared to evaluating all subjects in the face gallery and 58 times compared to previous works in the literature.}, keywords = {DeepEyes, Face Identification, Face Recognition, GigaFrames, Indexing Structure, Local Sensitive Hashing, Partial Least Squares, VER+}, pubstate = {published}, tppubtype = {mastersthesis} } Face identification is an important research topic due to areas such as its application to surveillance, forensics and human-computer interaction. In the past few years, a myriad of methods for face identification has been proposed in the literature, with just a few among them focusing on scalability. In this work, we propose a simple but efficient approach for scalable face identification based on partial least squares (PLS) and random independent hash functions inspired by locality-sensitive hashing (LSH), resulting in the PLS for hashing (PLSH) approach. The original PLSH approach is further extended using feature selection to reduce the computational cost to evaluate the PLS-based hash functions, resulting in the state-of-the-art extended PLSH approach (ePLSH). The proposed approach is evaluated in the dataset FERET and in the dataset FRGCv1. The results show significant reduction in the number of subjects evaluated in the face identification (reduced to 0.3% of the gallery), providing averaged speedups up to 233 times compared to evaluating all subjects in the face gallery and 58 times compared to previous works in the literature. |
dos Junior, Cassio Elias Santos; Kijak, E; Gravier, G; Schwartz, William Robson Learning to Hash Faces Using Large Feature Vectors Inproceedings Content-Based Multimedia Indexing (CBMI), 13th International Workshop on, pp. 1–6, IEEE, 2015. Links | BibTeX | Tags: Face Identification, Face Recognition, GigaFrames, Indexing Structure, Locality Sensitive Hashing, Partial Least Squares, SmartView, VER+ @inproceedings{santos2015learning, title = {Learning to Hash Faces Using Large Feature Vectors}, author = {Cassio Elias Santos dos Junior and E Kijak and G Gravier and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/2015-Learning_to_Hash_Faces_Using_Large_Feature_Vectors.pdf}, year = {2015}, date = {2015-01-01}, booktitle = {Content-Based Multimedia Indexing (CBMI), 13th International Workshop on}, pages = {1--6}, publisher = {IEEE}, keywords = {Face Identification, Face Recognition, GigaFrames, Indexing Structure, Locality Sensitive Hashing, Partial Least Squares, SmartView, VER+}, pubstate = {published}, tppubtype = {inproceedings} } |
Hu, Shuowen; Choi, Jonghyun; Chan, Alex L; Schwartz, William Robson Thermal-to-visible Face Recognition using Partial Least Squares Journal Article Journal of the Optical Society of America A, 32 (3), pp. 431–442, 2015. Links | BibTeX | Tags: Face Recognition, Thermal Imaging, VER+ @article{Hu:2015:JOSAA, title = {Thermal-to-visible Face Recognition using Partial Least Squares}, author = {Shuowen Hu and Jonghyun Choi and Alex L Chan and William Robson Schwartz}, url = {http://dx.doi.org/10.1364/JOSAA.32.000431}, year = {2015}, date = {2015-01-01}, journal = {Journal of the Optical Society of America A}, volume = {32}, number = {3}, pages = {431--442}, publisher = {OSA}, keywords = {Face Recognition, Thermal Imaging, VER+}, pubstate = {published}, tppubtype = {article} } |
Prado, G L; Schwartz, William Robson; Pedrini, Helio A Verify-Correct Approach to Person Re-identification Based on Partial Least Squares Signatures Inproceedings International Conference on Biometrics, pp. 1-7, 2015. Links | BibTeX | Tags: Partial Least Squares, Person Re-Identification, SmartView, VER+ @inproceedings{Prado:2015:ICB, title = {A Verify-Correct Approach to Person Re-identification Based on Partial Least Squares Signatures}, author = {G L Prado and William Robson Schwartz and Helio Pedrini}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/paper_2015_ICB_Prado.pdf}, year = {2015}, date = {2015-01-01}, booktitle = {International Conference on Biometrics}, pages = {1-7}, series = {Lecture Notes in Computer Science}, keywords = {Partial Least Squares, Person Re-Identification, SmartView, VER+}, pubstate = {published}, tppubtype = {inproceedings} } |
de Carlos, Gerson Paulo; Pedrini, Helio; Schwartz, William Robson Classification schemes based on Partial Least Squares for face identification Journal Article Journal of Visual Communication and Image Representation, 32 , pp. 170 - 179, 2015, ISSN: 1047-3203. Links | BibTeX | Tags: Face Identification, Face Recognition, One-Against-All Classification Scheme, Partial Least Squares, VER+ @article{2015:JVCI:Carlos, title = {Classification schemes based on Partial Least Squares for face identification}, author = {Gerson Paulo de Carlos and Helio Pedrini and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/paper_2015_JVCI.pdf}, issn = {1047-3203}, year = {2015}, date = {2015-01-01}, journal = {Journal of Visual Communication and Image Representation}, volume = {32}, pages = {170 - 179}, keywords = {Face Identification, Face Recognition, One-Against-All Classification Scheme, Partial Least Squares, VER+}, pubstate = {published}, tppubtype = {article} } |
Rodrigues, Marco Tulio Alves; Balbino, Daniel; Nascimento, Erickson R; Schwartz, William Robson A Non-Parametric Approach to Detect Changes in Aerial Images Inproceedings 14th Iberoamerican Congress on Pattern Recognition (CIARP), pp. 1-8, 2015. Links | BibTeX | Tags: Change Detection @inproceedings{Rodrigues:2015:CIARP, title = {A Non-Parametric Approach to Detect Changes in Aerial Images}, author = {Marco Tulio Alves Rodrigues and Daniel Balbino and Erickson R Nascimento and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/paper_2015_CIARP_Rodrigues.pdf}, year = {2015}, date = {2015-01-01}, booktitle = {14th Iberoamerican Congress on Pattern Recognition (CIARP)}, pages = {1-8}, keywords = {Change Detection}, pubstate = {published}, tppubtype = {inproceedings} } |
Pinto, A; Pedrini, H; Schwartz, William Robson; A, Rocha Face Spoofing Detection Through Visual Codebooks of Spectral Temporal Cubes Journal Article Image Processing, IEEE Transactions on, 24 (12), pp. 4726-4740, 2015, ISSN: 1057-7149. Links | BibTeX | Tags: DET, GigaFrames, Spoofing Detection @article{TIP:2015:Pinto, title = {Face Spoofing Detection Through Visual Codebooks of Spectral Temporal Cubes}, author = {A Pinto and H Pedrini and William Robson Schwartz and Rocha A}, url = {http://dx.doi.org/10.1109/TIP.2015.2466088}, issn = {1057-7149}, year = {2015}, date = {2015-01-01}, journal = {Image Processing, IEEE Transactions on}, volume = {24}, number = {12}, pages = {4726-4740}, keywords = {DET, GigaFrames, Spoofing Detection}, pubstate = {published}, tppubtype = {article} } |
Jordao, Artur; de Melo, Victor Hugo Cunha; Schwartz, William Robson A Study of Filtering Approaches for Sliding Window Pedestrian Detection Inproceedings Workshop em Visao Computacional (WVC), pp. 1-8, 2015. Links | BibTeX | Tags: DET, Pedestrian Detection, SmartView @inproceedings{Correia:2015:WVC, title = {A Study of Filtering Approaches for Sliding Window Pedestrian Detection}, author = {Artur Jordao and Victor Hugo Cunha de Melo and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/paper_2015_WVC_Correia.pdf}, year = {2015}, date = {2015-01-01}, booktitle = {Workshop em Visao Computacional (WVC)}, pages = {1-8}, keywords = {DET, Pedestrian Detection, SmartView}, pubstate = {published}, tppubtype = {inproceedings} } |
Pessoa, Ramon F; Schwartz, William Robson; dos Santos, Jefersson A A Study on Low-Cost Representations for Image Feature Extraction on Mobile Devices Inproceedings 14th Iberoamerican Congress on Pattern Recognition (CIARP), pp. 1-8, 2015. Links | BibTeX | Tags: DET, Feature Extraction, GigaFrames @inproceedings{Pessoa:2015:CIARP, title = {A Study on Low-Cost Representations for Image Feature Extraction on Mobile Devices}, author = {Ramon F Pessoa and William Robson Schwartz and Jefersson A dos Santos}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/paper_2015_CIARP_Pessoa.pdf}, year = {2015}, date = {2015-01-01}, booktitle = {14th Iberoamerican Congress on Pattern Recognition (CIARP)}, pages = {1-8}, keywords = {DET, Feature Extraction, GigaFrames}, pubstate = {published}, tppubtype = {inproceedings} } |
dos Junior, Cassio Elias Santos; Gravier, Guillaume; Schwartz, William Robson SSIG and IRISA at Multimodal Person Discovery Inproceedings Working Notes Proceedings of the MediaEval 2015 Workshop, 2015. Links | BibTeX | Tags: Face Recognition, MediaEval, Multimodal Person Discovery, Person Discovery @inproceedings{Santos:2015:MediaEval, title = {SSIG and IRISA at Multimodal Person Discovery}, author = {Cassio Elias Santos dos Junior and Guillaume Gravier and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/paper_2015_MediaEval.pdf}, year = {2015}, date = {2015-01-01}, booktitle = {Working Notes Proceedings of the MediaEval 2015 Workshop}, keywords = {Face Recognition, MediaEval, Multimodal Person Discovery, Person Discovery}, pubstate = {published}, tppubtype = {inproceedings} } |
Peixoto, Sirlene; Gonçalves, Gabriel Resende; Camara-Chavez, Guillermo; Schwartz, William Robson; Gomes, David Menotti Brazilian License Plate Character Recognition using Deep Learning Inproceedings Workshop em Visao Computacional (WVC), pp. 1-5, 2015. Links | BibTeX | Tags: Automatic License Plate Recognition, Deep Learning @inproceedings{Peixoto:2015:WVC, title = {Brazilian License Plate Character Recognition using Deep Learning}, author = {Sirlene Peixoto and Gabriel Resende Gonçalves and Guillermo Camara-Chavez and William Robson Schwartz and David Menotti Gomes}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/paper_2015_WVC_Peixoto.pdf}, year = {2015}, date = {2015-01-01}, booktitle = {Workshop em Visao Computacional (WVC)}, pages = {1-5}, keywords = {Automatic License Plate Recognition, Deep Learning}, pubstate = {published}, tppubtype = {inproceedings} } |
de Prates, Raphael Felipe Carvalho; Schwartz, William Robson CBRA: Color-Based Ranking Aggregation for Person Re-Identification Inproceedings IEEE International Conference on Image Processing (ICIP), pp. 1-5, 2015. Links | BibTeX | Tags: CBRA, GigaFrames, Person Re-Identification, Ranking Aggregation, SmartView, VER+ @inproceedings{Prates:2015:ICB, title = {CBRA: Color-Based Ranking Aggregation for Person Re-Identification}, author = {Raphael Felipe Carvalho de Prates and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/paper_2015_ICIP_Prates.pdf}, year = {2015}, date = {2015-01-01}, booktitle = {IEEE International Conference on Image Processing (ICIP)}, pages = {1-5}, keywords = {CBRA, GigaFrames, Person Re-Identification, Ranking Aggregation, SmartView, VER+}, pubstate = {published}, tppubtype = {inproceedings} } |
de Prates, Raphael Felipe Carvalho; Schwartz, William Robson Appearance-Based Person Re-identification by Intra-Camera Discriminative Models and Rank Aggregation Inproceedings International Conference on Biometrics, pp. 1-8, 2015. Links | BibTeX | Tags: Person Re-Identification, SmartView @inproceedings{Prates:2015:ICBb, title = {Appearance-Based Person Re-identification by Intra-Camera Discriminative Models and Rank Aggregation}, author = {Raphael Felipe Carvalho de Prates and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/paper_2015_ICB_Prates.pdf}, year = {2015}, date = {2015-01-01}, booktitle = {International Conference on Biometrics}, pages = {1-8}, series = {Lecture Notes in Computer Science}, keywords = {Person Re-Identification, SmartView}, pubstate = {published}, tppubtype = {inproceedings} } |
Menotti, D; Chiachia, G; Pinto, A; Schwartz, William Robson; Pedrini, H; Falcao, Xavier A; Rocha, A Deep Representations for Iris, Face, and Fingerprint Spoofing Detection Journal Article Information Forensics and Security, IEEE Transactions on, 10 (4), pp. 864-879, 2015, ISSN: 1556-6013. Links | BibTeX | Tags: Deep Learning, DeepEyes, DET, SmartView, Spoofing Detection @article{Menotti:2015:TIFS, title = {Deep Representations for Iris, Face, and Fingerprint Spoofing Detection}, author = {D Menotti and G Chiachia and A Pinto and William Robson Schwartz and H Pedrini and Xavier A Falcao and A Rocha}, url = {http://dx.doi.org/10.1109/TIFS.2015.2398817}, issn = {1556-6013}, year = {2015}, date = {2015-01-01}, journal = {Information Forensics and Security, IEEE Transactions on}, volume = {10}, number = {4}, pages = {864-879}, keywords = {Deep Learning, DeepEyes, DET, SmartView, Spoofing Detection}, pubstate = {published}, tppubtype = {article} } |
Pinto, A; Schwartz, William Robson; Pedrini, H; Rocha, De Rezende A Using Visual Rhythms for Detecting Video-Based Facial Spoof Attacks Journal Article Information Forensics and Security, IEEE Transactions on, 10 (5), pp. 1025-1038, 2015, ISSN: 1556-6013. Links | BibTeX | Tags: DeepEyes, Spoofing Detection @article{Pinto:2015:TIFS, title = {Using Visual Rhythms for Detecting Video-Based Facial Spoof Attacks}, author = {A Pinto and William Robson Schwartz and H Pedrini and De Rezende A Rocha}, url = {http://dx.doi.org/10.1109/TIFS.2015.2395139}, issn = {1556-6013}, year = {2015}, date = {2015-01-01}, journal = {Information Forensics and Security, IEEE Transactions on}, volume = {10}, number = {5}, pages = {1025-1038}, keywords = {DeepEyes, Spoofing Detection}, pubstate = {published}, tppubtype = {article} } |
Kloss, Ricardo Barbosa; da Silva, Samira Santos; Cirne, Marcos Vinicius Mussel; Pedrini, Hélio; Schwartz, William Robson Partial Least Squares Image Clustering Inproceedings Conference on Graphics, Patterns and Images (SIBGRAPI), pp. 1-8, 2015. Links | BibTeX | Tags: Image Clustering, Image Grouping, Partial Least Squares, Video Summarization @inproceedings{Kloss:2015b, title = {Partial Least Squares Image Clustering}, author = {Ricardo Barbosa Kloss and Samira Santos da Silva and Marcos Vinicius Mussel Cirne and Hélio Pedrini and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/paper_camera_ready1.pdf}, year = {2015}, date = {2015-01-01}, booktitle = {Conference on Graphics, Patterns and Images (SIBGRAPI)}, pages = {1-8}, keywords = {Image Clustering, Image Grouping, Partial Least Squares, Video Summarization}, pubstate = {published}, tppubtype = {inproceedings} } |
2014 |
Colque, Rensso Victor Hugo Mora; Chavez, Guillermo Camara; Schwartz, William Robson Detection of groups of people in surveillance videos based on spatio-temporal clues Inproceedings 19th Iberoamerican Congress on Pattern Recognition (CIARP), pp. 948-955, Springer International Publishing, 2014. Links | BibTeX | Tags: Crowd Event Detection, DET, Group Detection, SmartView @inproceedings{crowdciarp2014, title = {Detection of groups of people in surveillance videos based on spatio-temporal clues}, author = {Rensso Victor Hugo Mora Colque and Guillermo Camara Chavez and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/2014-Detection-of-Groups-of-People-in-Surveillance-Videos-based-on-Spatio-Temporal-Clues.pdf}, year = {2014}, date = {2014-11-06}, booktitle = {19th Iberoamerican Congress on Pattern Recognition (CIARP)}, volume = {8827}, pages = {948-955}, publisher = {Springer International Publishing}, series = {Lecture Notes in Computer Science}, keywords = {Crowd Event Detection, DET, Group Detection, SmartView}, pubstate = {published}, tppubtype = {inproceedings} } |
Junior, Antonio Carlos Nazare A Scalable and Versatile Framework for Smart Video Surveillance Masters Thesis Federal University of Minas Gerais, 2014. Abstract | Links | BibTeX | Tags: ARDOP, Smart Surveillance, Surveillance Systems, VER+, Video Surveillance @mastersthesis{Nazare:2014:MSc, title = {A Scalable and Versatile Framework for Smart Video Surveillance}, author = {Antonio Carlos Nazare Junior}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/03/dissertation_2014_Antonio-1.pdf}, year = {2014}, date = {2014-09-05}, school = {Federal University of Minas Gerais}, abstract = {The availability of surveillance cameras placed in public locations has increased vastly in the last years, providing a safe environment for people at the cost of huge amount of visual data collected. Such data are mostly processed manually, a task which is labor intensive and prone to errors. Therefore, automatic approaches must be employed to enable the processing of the data, so that human operators only need to reason about selected portions. Focused on solving problems in the domain of visual surveillance, computer vision problems applied to this domain have been developed for several years aiming at finding accurate and efficient solutions, required to allow the execution of surveillance systems in real environments. The main goal of such systems is to analyze the scene focusing on the detection and recognition of suspicious activities performed by humans in the scene, so that the security staff can pay closer attention to these preselected activities. However these systems are rarely tackled in a scalable manner. Before developing a full surveillance system, several problems have to be solved first, for instance: background subtraction, person detection, tracking and re-identification, face recognition, and action recognition. Even though each of these problems have been researched in the past decades, they are hardly considered in a sequence. Each one is usually solved individually. However, in a real surveillance scenario, the aforementioned problems have to be solved in sequence considering only videos as the input. Aiming at the direction of evaluating approaches in more realistic scenarios, this work proposes a framework called Smart Surveillance Framework (SSF), to allow researchers to implement their solutions to the above problems as a sequence of processing modules that communicates through a shared memory. The SSF is a C++ library built to provide important features for a surveillance system, such as a automatic scene understanding, scalability, real-time operation, multi-sensor environment, usage of low cost standard components, runtime re-configuration, and communication control.}, keywords = {ARDOP, Smart Surveillance, Surveillance Systems, VER+, Video Surveillance}, pubstate = {published}, tppubtype = {mastersthesis} } The availability of surveillance cameras placed in public locations has increased vastly in the last years, providing a safe environment for people at the cost of huge amount of visual data collected. Such data are mostly processed manually, a task which is labor intensive and prone to errors. Therefore, automatic approaches must be employed to enable the processing of the data, so that human operators only need to reason about selected portions. Focused on solving problems in the domain of visual surveillance, computer vision problems applied to this domain have been developed for several years aiming at finding accurate and efficient solutions, required to allow the execution of surveillance systems in real environments. The main goal of such systems is to analyze the scene focusing on the detection and recognition of suspicious activities performed by humans in the scene, so that the security staff can pay closer attention to these preselected activities. However these systems are rarely tackled in a scalable manner. Before developing a full surveillance system, several problems have to be solved first, for instance: background subtraction, person detection, tracking and re-identification, face recognition, and action recognition. Even though each of these problems have been researched in the past decades, they are hardly considered in a sequence. Each one is usually solved individually. However, in a real surveillance scenario, the aforementioned problems have to be solved in sequence considering only videos as the input. Aiming at the direction of evaluating approaches in more realistic scenarios, this work proposes a framework called Smart Surveillance Framework (SSF), to allow researchers to implement their solutions to the above problems as a sequence of processing modules that communicates through a shared memory. The SSF is a C++ library built to provide important features for a surveillance system, such as a automatic scene understanding, scalability, real-time operation, multi-sensor environment, usage of low cost standard components, runtime re-configuration, and communication control. |
Sena, Jessica; Ferreira, Cesar Augusto Moura; dos Junior, Cassio Elias Santos; de Melo, Victor Hugo Cunha; Schwartz, William Robson Self-Organizing Traffic Lights: A Pedestrian Oriented Approach Miscellaneous Workshop of Undergraduate Works (WUW) in SIBGRAPI - Conference on Graphics, Patterns and Images, 2014, (1st place award). Links | BibTeX | Tags: DET, Self-Organizing Pedestrian Traffic Lights @misc{sibgrapi2014selfb, title = {Self-Organizing Traffic Lights: A Pedestrian Oriented Approach}, author = {Jessica Sena and Cesar Augusto Moura Ferreira and Cassio Elias Santos dos Junior and Victor Hugo Cunha de Melo and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/2014-SIBGRAPI-Self-Organizing-Traffic-Lights-A-Pedestrian-Oriented-Approach.pdf http://www.icex.ufmg.br/index.php/noticias/noticias-do-icex/80-noticias-do-icex/alunos-do-dcc-sao-premiados-no-sibgrapi-2014}, year = {2014}, date = {2014-08-29}, pages = {86-91}, howpublished = {Workshop of Undergraduate Works (WUW) in SIBGRAPI - Conference on Graphics, Patterns and Images}, note = {1st place award}, keywords = {DET, Self-Organizing Pedestrian Traffic Lights}, pubstate = {published}, tppubtype = {misc} } |
de Melo, Victor Hugo Cunha Fast and Robust Optimization Approaches for Pedestrian Detection Masters Thesis Federal University of Minas Gerais, 2014. Abstract | Links | BibTeX | Tags: ARDOP, Pedestrian Detection, SmartView @mastersthesis{Melo:2014:MSc, title = {Fast and Robust Optimization Approaches for Pedestrian Detection}, author = {Victor Hugo Cunha de Melo}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/dissertation_2014_Victor.pdf}, year = {2014}, date = {2014-02-28}, school = {Federal University of Minas Gerais}, abstract = {The large number of surveillance cameras available nowadays in strategic points of major cities provides a safe environment. However, the huge amount of data provided by the cameras prevents its manual processing, requiring the application of automated methods. Among such methods, pedestrian detection plays an important role in reducing the amount of data by locating only the regions of interest for further processing regarding activities being performed by agents in the scene. However, the currently available methods are unable to process such large amount of data in real time. Therefore, there is a need for the development of optimization techniques. Towards accomplishing the goal of reducing costs for pedestrian detection, we propose in this work two optimization approaches. The first approach consists of a cascade of rejection based on Partial Least Squares (PLS) combined with the propagation of latent variables through the stages. Our results show that the method reduces the computational cost by increasing the number of rejected background samples in earlier stages of the cascade. Our second approach proposes a novel optimization that performs a random filtering in the image to select a small number of detection windows, allowing a reduction in the computational cost. Our results show that accurate results can be achieved even when a large number of detection windows are discarded.}, keywords = {ARDOP, Pedestrian Detection, SmartView}, pubstate = {published}, tppubtype = {mastersthesis} } The large number of surveillance cameras available nowadays in strategic points of major cities provides a safe environment. However, the huge amount of data provided by the cameras prevents its manual processing, requiring the application of automated methods. Among such methods, pedestrian detection plays an important role in reducing the amount of data by locating only the regions of interest for further processing regarding activities being performed by agents in the scene. However, the currently available methods are unable to process such large amount of data in real time. Therefore, there is a need for the development of optimization techniques. Towards accomplishing the goal of reducing costs for pedestrian detection, we propose in this work two optimization approaches. The first approach consists of a cascade of rejection based on Partial Least Squares (PLS) combined with the propagation of latent variables through the stages. Our results show that the method reduces the computational cost by increasing the number of rejected background samples in earlier stages of the cascade. Our second approach proposes a novel optimization that performs a random filtering in the image to select a small number of detection windows, allowing a reduction in the computational cost. Our results show that accurate results can be achieved even when a large number of detection windows are discarded. |
de Melo, Victor Hugo Cunha; Leao, Samir Moreira Andrade; Menotti, D; Schwartz, William Robson An Optimized Sliding Window Approach to Pedestrian Detection Inproceedings IAPR International Conference on Pattern Recognition (ICPR), pp. 1-6, 2014. Links | BibTeX | Tags: DET, Pedestrian Detection, Random Filtering, SmartView @inproceedings{Melo:2014:ICPR, title = {An Optimized Sliding Window Approach to Pedestrian Detection}, author = {Victor Hugo Cunha de Melo and Samir Moreira Andrade Leao and D Menotti and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/2014-An-Optimized-Sliding-Window-Approach-to-Pedestrian-Detection.pdf}, year = {2014}, date = {2014-01-01}, booktitle = {IAPR International Conference on Pattern Recognition (ICPR)}, pages = {1-6}, keywords = {DET, Pedestrian Detection, Random Filtering, SmartView}, pubstate = {published}, tppubtype = {inproceedings} } |
Junior, Antonio Carlos Nazare; dos Junior, Cassio Elias Santos; Ferreira, Renato; Schwartz, William Robson Smart Surveillance Framework: A Versatile Tool for Video Analysis Inproceedings IEEE Winter Conference on Applications of Computer Vision, pp. 753–760, 2014. Links | BibTeX | Tags: ARDOP, Smart Surveillance, Smart Surveillance Framework, SmartView, SSF, Surveillance Systems, Video Surveillance @inproceedings{wacv2014smart, title = {Smart Surveillance Framework: A Versatile Tool for Video Analysis}, author = {Antonio Carlos Nazare Junior and Cassio Elias Santos dos Junior and Renato Ferreira and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/2014-Smart-Surveillance-Framework-A-Versatile-Tool-for-Video-Analysis.pdf}, year = {2014}, date = {2014-01-01}, booktitle = {IEEE Winter Conference on Applications of Computer Vision}, pages = {753--760}, keywords = {ARDOP, Smart Surveillance, Smart Surveillance Framework, SmartView, SSF, Surveillance Systems, Video Surveillance}, pubstate = {published}, tppubtype = {inproceedings} } |
dos Junior, Cassio Elias Santos; Schwartz, William Robson Extending Face Identification to Open-Set Face Recognition Inproceedings Conference on Graphics, Patterns and Images (SIBGRAPI), pp. 1-8, 2014. Links | BibTeX | Tags: ARDOP, Face Identification, Face Recognition, Open-Set Classification, SmartView @inproceedings{sibgrapi2014extending, title = {Extending Face Identification to Open-Set Face Recognition}, author = {Cassio Elias Santos dos Junior and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/2014-Extending-Face-Identification-to-Open-Set-Face-Recognition.pdf}, year = {2014}, date = {2014-01-01}, booktitle = {Conference on Graphics, Patterns and Images (SIBGRAPI)}, pages = {1-8}, keywords = {ARDOP, Face Identification, Face Recognition, Open-Set Classification, SmartView}, pubstate = {published}, tppubtype = {inproceedings} } |
Sena, Jessica; Ferreira, Cesar Augusto Moura; dos Junior, Cassio Elias Santos; de Melo, Victor Hugo Cunha; Schwartz, William Robson Self-Organizing Traffic Lights: A Pedestrian Oriented Approach Inproceedings X Workshop de Visão Computacional, pp. 1-6, 2014. Links | BibTeX | Tags: DET, Self-Organizing Pedestrian Traffic Lights @inproceedings{wvc2014self, title = {Self-Organizing Traffic Lights: A Pedestrian Oriented Approach}, author = {Jessica Sena and Cesar Augusto Moura Ferreira and Cassio Elias Santos dos Junior and Victor Hugo Cunha de Melo and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/2014-WVC-Self-Organizing-Traffic-Lights-A-Pedestrian-Oriented-Approach.pdf}, year = {2014}, date = {2014-01-01}, booktitle = {X Workshop de Visão Computacional}, pages = {1-6}, keywords = {DET, Self-Organizing Pedestrian Traffic Lights}, pubstate = {published}, tppubtype = {inproceedings} } |
Rodrigues, Marco Tulio Alves; Milen, L O; Nascimento, E R; Schwartz, William Robson Change detection based on features invariant to monotonic transforms and spatial constrained matching Inproceedings Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on, pp. 4334-4338, 2014. Links | BibTeX | Tags: Change Detection @inproceedings{rodrigues:2014:icassp, title = {Change detection based on features invariant to monotonic transforms and spatial constrained matching}, author = {Marco Tulio Alves Rodrigues and L O Milen and E R Nascimento and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/2014-CHANGE-DETECTION-BASED-ON-FEATURES-INVARIANT-TO-MONOTONIC-TRANSFORMS-AND-SPATIAL-CONSTRAINED-MATCHING.pdf}, year = {2014}, date = {2014-01-01}, booktitle = {Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on}, pages = {4334-4338}, keywords = {Change Detection}, pubstate = {published}, tppubtype = {inproceedings} } |
Schwartz, William Robson Computer Vision: A Reference Guide Book Chapter Ikeuchi, Katsushi (Ed.): Chapter Appearance-Based Human Detection, pp. 36–38, Springer US, 2014. Links | BibTeX | Tags: Pedestrian Detection @inbook{schwartz:2014:appearance, title = {Computer Vision: A Reference Guide}, author = {William Robson Schwartz}, editor = {Katsushi Ikeuchi}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/paper_submitted.pdf http://www.springer.com/us/book/9780387307718}, year = {2014}, date = {2014-01-01}, pages = {36--38}, publisher = {Springer US}, chapter = {Appearance-Based Human Detection}, keywords = {Pedestrian Detection}, pubstate = {published}, tppubtype = {inbook} } |
Junior, Antonio Carlos Nazare; Ferreira, Renato; Schwartz, William Robson Scalable Feature Extraction for Visual Surveillance Inproceedings Iberoamerican Congress on Pattern Recognition (CIARP), pp. 375-382, Springer International Publishing, 2014. Links | BibTeX | Tags: DET, Feature Extraction, Smart Surveillance, SmartView, Surveillance Systems, Video Surveillance @inproceedings{Nazare:2014:CIARP, title = {Scalable Feature Extraction for Visual Surveillance}, author = {Antonio Carlos Nazare Junior and Renato Ferreira and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/paper_2014_CIARP_Antonio.pdf}, year = {2014}, date = {2014-01-01}, booktitle = {Iberoamerican Congress on Pattern Recognition (CIARP)}, volume = {8827}, pages = {375-382}, publisher = {Springer International Publishing}, series = {Lecture Notes in Computer Science}, keywords = {DET, Feature Extraction, Smart Surveillance, SmartView, Surveillance Systems, Video Surveillance}, pubstate = {published}, tppubtype = {inproceedings} } |
Dutra, Cristianne Rodrigues Santos; Rocha, M C; Schwartz, William Robson Person Re-Identification Based on Weighted Indexing Structures Inproceedings Iberoamerican Congress on Pattern Recognition (CIARP), pp. 359-366, Springer International Publishing, 2014. Links | BibTeX | Tags: ARDOP, Indexing Structure, Inverted Lists, Person Re-Identification, SmartView @inproceedings{Dutra:2014:CIARP, title = {Person Re-Identification Based on Weighted Indexing Structures}, author = {Cristianne Rodrigues Santos Dutra and M C Rocha and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/paper_2014_CIARP_Dutra.pdf}, year = {2014}, date = {2014-01-01}, booktitle = {Iberoamerican Congress on Pattern Recognition (CIARP)}, volume = {8827}, pages = {359-366}, publisher = {Springer International Publishing}, series = {Lecture Notes in Computer Science}, keywords = {ARDOP, Indexing Structure, Inverted Lists, Person Re-Identification, SmartView}, pubstate = {published}, tppubtype = {inproceedings} } |
de Prates, Raphael Felipe Carvalho; Camara-Chavez, G; Schwartz, William Robson; Gomes, D M An Adaptive Vehicle License Plate Detection at Higher Matching Degree Inproceedings Iberoamerican Congress on Pattern Recognition (CIARP), pp. 454-461, Springer International Publishing, 2014. Links | BibTeX | Tags: Automatic License Plate Recognition, DET, License Plate Detection @inproceedings{Prates:2014:CIARP, title = {An Adaptive Vehicle License Plate Detection at Higher Matching Degree}, author = {Raphael Felipe Carvalho de Prates and G Camara-Chavez and William Robson Schwartz and D M Gomes}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/paper_2014_CIARP_Prates-1.pdf}, year = {2014}, date = {2014-01-01}, booktitle = {Iberoamerican Congress on Pattern Recognition (CIARP)}, volume = {8827}, pages = {454-461}, publisher = {Springer International Publishing}, series = {Lecture Notes in Computer Science}, keywords = {Automatic License Plate Recognition, DET, License Plate Detection}, pubstate = {published}, tppubtype = {inproceedings} } |
2013 |
Schwartz, William Robson; de Melo, Victor Hugo Cunha; Pedrini, H; Davis, L S A Data-Driven Detection Optimization Framework Journal Article Neurocomputing, 104 , pp. 35-49, 2013. Links | BibTeX | Tags: Partial Least Squares, Pedestrian Detection @article{Schwartz:2013:Neurocomputing, title = {A Data-Driven Detection Optimization Framework}, author = {William Robson Schwartz and Victor Hugo Cunha de Melo and H Pedrini and L S Davis}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/2013-A-Data-Driven-Detection-Optimization-Framework.pdf}, year = {2013}, date = {2013-01-01}, journal = {Neurocomputing}, volume = {104}, pages = {35-49}, keywords = {Partial Least Squares, Pedestrian Detection}, pubstate = {published}, tppubtype = {article} } |
Prado, Gabriel Lorencetti; Schwartz, William Robson; Pedrini, Helio Person Re-identification Using Partial Least Squares Appearance Modeling Incollection Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications, pp. 382–390, 2013. Links | BibTeX | Tags: ARDOP, Person Re-Identification @incollection{prado2013person, title = {Person Re-identification Using Partial Least Squares Appearance Modeling}, author = {Gabriel Lorencetti Prado and William Robson Schwartz and Helio Pedrini}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/2013-Person-Re-identification-Using-Partial-Least-Squares-Appearance-Modeling.pdf}, year = {2013}, date = {2013-01-01}, booktitle = {Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications}, pages = {382--390}, keywords = {ARDOP, Person Re-Identification}, pubstate = {published}, tppubtype = {incollection} } |
Carlos, G P; Pedrini, H; Schwartz, William Robson Fast and Scalable Enrollment for Face Identification based on Partial Least Squares Inproceedings IEEE International Conference on Automatic Face and Gesture Recognition, 2013. Links | BibTeX | Tags: ARDOP, Face Identification, Face Recognition, One-Against-Some Classification Scheme @inproceedings{Carlos:2013:FG, title = {Fast and Scalable Enrollment for Face Identification based on Partial Least Squares}, author = {G P Carlos and H Pedrini and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/paper_2013_FG.pdf}, year = {2013}, date = {2013-01-01}, booktitle = {IEEE International Conference on Automatic Face and Gesture Recognition}, keywords = {ARDOP, Face Identification, Face Recognition, One-Against-Some Classification Scheme}, pubstate = {published}, tppubtype = {inproceedings} } |
de Siqueira, F R; Schwartz, William Robson; Pedrini, H Multi-Scale Gray Level Co-Occurrence Matrices for Texture Description Journal Article Neurocomputing, pp. 1-10, 2013. Links | BibTeX | Tags: Feature Extraction, GLCM @article{Siqueira:2012:Neurocomputing, title = {Multi-Scale Gray Level Co-Occurrence Matrices for Texture Description}, author = {F R de Siqueira and William Robson Schwartz and H Pedrini}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/2013-Multi-Scale-Gray-Level-Co-Occurrence-Matrices-for-Texture-Description-1.pdf}, year = {2013}, date = {2013-01-01}, journal = {Neurocomputing}, pages = {1-10}, keywords = {Feature Extraction, GLCM}, pubstate = {published}, tppubtype = {article} } |
Chakka, M M; Anjos, A; Marcel, S; Tronci, R; Muntoni, D; Fadda, G; Pili, M; Sirena, N; Murgia, G; Ristori, M; Roli, F; Yan, J; Yi, D; Lei, Z; Zhang, Z; Li, S; Schwartz, William Robson; Rocha, A; Pedrini, H; Lorenzo-Navarro, J; Castrillon-Santana, M; Maatta, J Competition on Counter Measures to 2D Facial Spoofing Attacks Inproceedings International Joint Conference on Biometrics, 2013. Links | BibTeX | Tags: Spoofing Detection @inproceedings{Anjos:2011:IJCB, title = {Competition on Counter Measures to 2D Facial Spoofing Attacks}, author = {M M Chakka and A Anjos and S Marcel and R Tronci and D Muntoni and G Fadda and M Pili and N Sirena and G Murgia and M Ristori and F Roli and J Yan and D Yi and Z Lei and Z Zhang and S Li and William Robson Schwartz and A Rocha and H Pedrini and J Lorenzo-Navarro and M Castrillon-Santana and J Maatta}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/2011-Competition-on-Counter-Measures-to-2D-Facial-Spoofing-Attacks.pdf}, year = {2013}, date = {2013-01-01}, booktitle = {International Joint Conference on Biometrics}, keywords = {Spoofing Detection}, pubstate = {published}, tppubtype = {inproceedings} } |
de Lima, Vitor Cezar; Schwartz, William Robson; Pedrini, H 3D Searchless Fractal Video Encoding at Low Bit Rates Journal Article Journal of Mathematical Imaging and Vision, 45 (3), pp. 239-250, 2013. Links | BibTeX | Tags: Fractal Compression @article{Lima:2012:JMIV, title = {3D Searchless Fractal Video Encoding at Low Bit Rates}, author = {Vitor Cezar de Lima and William Robson Schwartz and H Pedrini}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/2013-3D-Searchless-Fractal-Video-Encoding-at-Low-Bit-Rates.pdf}, year = {2013}, date = {2013-01-01}, journal = {Journal of Mathematical Imaging and Vision}, volume = {45}, number = {3}, pages = {239-250}, keywords = {Fractal Compression}, pubstate = {published}, tppubtype = {article} } |
de Melo, Victor Hugo Cunha; Leao, Samir Moreira Andrade; Campos, M; Menotti, D; Schwartz, William Robson Fast Pedestrian Detection based on a Partial Least Squares Cascade Inproceedings IEEE International Conference on Image Processing, pp. 4146 - 4150, 2013. Links | BibTeX | Tags: ARDOP, Partial Least Squares, Pedestrian Detection, Rejection Cascade @inproceedings{Melo:2013:ICIPb, title = {Fast Pedestrian Detection based on a Partial Least Squares Cascade}, author = {Victor Hugo Cunha de Melo and Samir Moreira Andrade Leao and M Campos and D Menotti and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/2013-Fast-Pedestrian-Detection-based-on-a-Partial-Least-Squares-Cascade.pdf}, year = {2013}, date = {2013-01-01}, booktitle = {IEEE International Conference on Image Processing}, pages = {4146 - 4150}, keywords = {ARDOP, Partial Least Squares, Pedestrian Detection, Rejection Cascade}, pubstate = {published}, tppubtype = {inproceedings} } |
Dutra, Cristianne Rodrigues Santos; Souza, T; Alves, R; Schwartz, William Robson; Oliveira, L R Re-identifying People based on Indexing Structure and Manifold Appearance Modeling Inproceedings Conference on Graphics, Patterns and Images (SIBGRAPI), pp. 218-225, 2013. Links | BibTeX | Tags: ARDOP, Indexing Structure, Inverted Lists, Person Re-Identification, Riemannian Manifold @inproceedings{Dutra:2013:SIBGRAPIb, title = {Re-identifying People based on Indexing Structure and Manifold Appearance Modeling}, author = {Cristianne Rodrigues Santos Dutra and T Souza and R Alves and William Robson Schwartz and L R Oliveira}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/03/paper_2013_SIBGRAPI.pdf}, year = {2013}, date = {2013-01-01}, booktitle = {Conference on Graphics, Patterns and Images (SIBGRAPI)}, pages = {218-225}, keywords = {ARDOP, Indexing Structure, Inverted Lists, Person Re-Identification, Riemannian Manifold}, pubstate = {published}, tppubtype = {inproceedings} } |
de Prates, Raphael Felipe Carvalho; Camara-Chavez, G; Schwartz, William Robson; Menotti, D Brazilian License Plate Detection Using Histogram of Oriented Gradients and Sliding Windows Journal Article International Journal of Computer Science and Information Technology, 5 , pp. 39-52, 2013. Links | BibTeX | Tags: ARDOP, Automatic License Plate Recognition, HOG, License Plate Detection @article{Prates:2013:IJCSIT, title = {Brazilian License Plate Detection Using Histogram of Oriented Gradients and Sliding Windows}, author = {Raphael Felipe Carvalho de Prates and G Camara-Chavez and William Robson Schwartz and D Menotti}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/paper_2013_IJCSIT.pdf}, year = {2013}, date = {2013-01-01}, journal = {International Journal of Computer Science and Information Technology}, volume = {5}, pages = {39-52}, keywords = {ARDOP, Automatic License Plate Recognition, HOG, License Plate Detection}, pubstate = {published}, tppubtype = {article} } |
2012 |
Schwartz, William Robson Scalable People Re-Identification Based on a One-Against-Some Classification Scheme Inproceedings IEEE International Conference on Image Processing, 2012. Links | BibTeX | Tags: One-Against-All Classification Scheme, Person Re-Identification @inproceedings{Schwartz:2012:ICIP, title = {Scalable People Re-Identification Based on a One-Against-Some Classification Scheme}, author = {William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/2012-Scalable-People-Re-Identification-Based-on-a-One-Against-Some-Classification-Scheme.pdf}, year = {2012}, date = {2012-01-01}, booktitle = {IEEE International Conference on Image Processing}, keywords = {One-Against-All Classification Scheme, Person Re-Identification}, pubstate = {published}, tppubtype = {inproceedings} } |
Chiachia, Giovani; Pinto, Nicolas; Schwartz, William Robson; Rocha, Anderson; Falc~ao, Alexandre X; Cox, David D Person-Specific Subspace Analysis for Unconstrained Familiar Face Identification. Inproceedings BMVC, pp. 1–12, 2012. Links | BibTeX | Tags: Face Recognition, Face Verification, Partial Least Squares @inproceedings{chiachia2012person, title = {Person-Specific Subspace Analysis for Unconstrained Familiar Face Identification.}, author = {Giovani Chiachia and Nicolas Pinto and William Robson Schwartz and Anderson Rocha and Alexandre X Falc~ao and David D Cox}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/2012-Person-Specific-Subspace-Analysis-for-Unconstrained-Familiar-Face-Identification..pdf}, year = {2012}, date = {2012-01-01}, booktitle = {BMVC}, pages = {1--12}, keywords = {Face Recognition, Face Verification, Partial Least Squares}, pubstate = {published}, tppubtype = {inproceedings} } |
2016 |
Artur Jordao; William Robson Schwartz Oblique Random Forest based on Partial Least Squares Applied to Pedestrian Detection Inproceedings IEEE International Conference on Image Processing (ICIP), pp. 2931-2935, 2016. Links | BibTeX | Tags: DeepEyes, Pedestrian Detection, VER+ @inproceedings{Correia:2016:ICIP, title = {Oblique Random Forest based on Partial Least Squares Applied to Pedestrian Detection}, author = {Artur Jordao and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/OBLIQUE-RANDOM-FOREST-BASED-ON-PARTIAL-LEAST-SQUARES-APPLIED-TO.pdf}, year = {2016}, date = {2016-09-25}, booktitle = {IEEE International Conference on Image Processing (ICIP)}, pages = {2931-2935}, keywords = {DeepEyes, Pedestrian Detection, VER+}, pubstate = {published}, tppubtype = {inproceedings} } |
Gabriel Resende Goncalves License Plate Recognition based on Temporal Redundancy Masters Thesis Federal University of Minas Gerais, 2016. Abstract | Links | BibTeX | Tags: Automatic License Plate Recognition, DeepEyes, GigaFrames @mastersthesis{Goncalves:2016:MSc, title = {License Plate Recognition based on Temporal Redundancy}, author = {Gabriel Resende Goncalves}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/03/dissertation_2016_Gabriel.pdf}, year = {2016}, date = {2016-08-26}, school = {Federal University of Minas Gerais}, abstract = {Recognition of vehicle license plates is an important task applied to a myriad of real scenarios. Most approaches in the literature first detect an on-track vehicle, locate the license plate, perform a segmentation of its characters and then recognize the characters using an Optical Character Recognition (OCR) approach. However, these approaches focus on performing these tasks using only a single frame of each vehicle in the video. Therefore, such techniques might have their recognition rates reduced due to noise present in that particular frame. On the other hand, in this work we propose an approach to automatically detect the vehicle on the road and identify (locate/recognize) its license plate based on temporal redundant information instead of selecting a single frame to perform the recognition. We also propose two post-processing steps that can be employed to improve the accuracy of the system by querying a license plate database (e.g., the Department of Motor Vehicles database containing a list of all issued license plates and car models). Experimental results demonstrate that it is possible to improve the vehicle recognition rate in 15.5 percentage points (p.p.) (an increase of 23.38%) of the baseline results, using our proposal temporal redundancy approach. Furthermore, additional 7.8 p.p. are achieved using the two post-processing approaches, leading to a final recognition rate of 89.6% on a dataset with 5,200 frame images of $300$ vehicles recorded at Federal University of Minas Gerais (UFMG). In addition, this work also proposes a novel benchmark, designed specifically to evaluate character segmentation techniques, composed of a dataset of 2,000 Brazilian license plates (resulting in 14,000 alphanumeric symbols) and an evaluation protocol considering a novel evaluation measure, the Jaccard-Centroid coefficient.}, keywords = {Automatic License Plate Recognition, DeepEyes, GigaFrames}, pubstate = {published}, tppubtype = {mastersthesis} } Recognition of vehicle license plates is an important task applied to a myriad of real scenarios. Most approaches in the literature first detect an on-track vehicle, locate the license plate, perform a segmentation of its characters and then recognize the characters using an Optical Character Recognition (OCR) approach. However, these approaches focus on performing these tasks using only a single frame of each vehicle in the video. Therefore, such techniques might have their recognition rates reduced due to noise present in that particular frame. On the other hand, in this work we propose an approach to automatically detect the vehicle on the road and identify (locate/recognize) its license plate based on temporal redundant information instead of selecting a single frame to perform the recognition. We also propose two post-processing steps that can be employed to improve the accuracy of the system by querying a license plate database (e.g., the Department of Motor Vehicles database containing a list of all issued license plates and car models). Experimental results demonstrate that it is possible to improve the vehicle recognition rate in 15.5 percentage points (p.p.) (an increase of 23.38%) of the baseline results, using our proposal temporal redundancy approach. Furthermore, additional 7.8 p.p. are achieved using the two post-processing approaches, leading to a final recognition rate of 89.6% on a dataset with 5,200 frame images of $300$ vehicles recorded at Federal University of Minas Gerais (UFMG). In addition, this work also proposes a novel benchmark, designed specifically to evaluate character segmentation techniques, composed of a dataset of 2,000 Brazilian license plates (resulting in 14,000 alphanumeric symbols) and an evaluation protocol considering a novel evaluation measure, the Jaccard-Centroid coefficient. |
Artur Jordao The Good, the Fast and the Better Pedestrian Detector Masters Thesis Federal University of Minas Gerais, 2016. Abstract | Links | BibTeX | Tags: DeepEyes, DET, GigaFrames, Pedestrian Detection, VER+ @mastersthesis{Jordao:2016:MSc, title = {The Good, the Fast and the Better Pedestrian Detector}, author = {Artur Jordao}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/03/dissertation_2016_ArturJordao.pdf}, year = {2016}, date = {2016-06-24}, school = {Federal University of Minas Gerais}, abstract = {Pedestrian detection is a well-known problem in Computer Vision, mostly because of its direct applications in surveillance, transit safety and robotics. In the past decade, several efforts have been performed to improve the detection in terms of accuracy, speed and feature enhancement. In this work, we propose and analyze techniques focusing on these points. First, we develop an accurate oblique random forest (oRF) associated with Partial Least Squares (PLS). The method utilizes the PLS to find a decision surface, at each node of a decision tree, that better splits the samples presented to it, based on some purity criterion. To measure the advantages provided by PLS on the oRF, we compare the proposed method with the oRF based on SVM. Second, we evaluate and compare filtering approaches to reduce the search space and keep only potential regions of interest to be presented to detectors, speeding up the detection process. Experimental results demonstrate that the evaluated filters are able to discard a large number of detection windows without compromising the accuracy. Finally, we propose a novel approach to extract powerful features regarding the scene. The method combines results of distinct pedestrian detectors by reinforcing the human hypothesis, whereas suppressing a significant number of false positives due to the lack of spatial consensus when multiple detectors are considered. Our proposed approach, referred to as Spatial Consensus (SC), outperforms all previously published state-of-the-art pedestrian detection methods.}, keywords = {DeepEyes, DET, GigaFrames, Pedestrian Detection, VER+}, pubstate = {published}, tppubtype = {mastersthesis} } Pedestrian detection is a well-known problem in Computer Vision, mostly because of its direct applications in surveillance, transit safety and robotics. In the past decade, several efforts have been performed to improve the detection in terms of accuracy, speed and feature enhancement. In this work, we propose and analyze techniques focusing on these points. First, we develop an accurate oblique random forest (oRF) associated with Partial Least Squares (PLS). The method utilizes the PLS to find a decision surface, at each node of a decision tree, that better splits the samples presented to it, based on some purity criterion. To measure the advantages provided by PLS on the oRF, we compare the proposed method with the oRF based on SVM. Second, we evaluate and compare filtering approaches to reduce the search space and keep only potential regions of interest to be presented to detectors, speeding up the detection process. Experimental results demonstrate that the evaluated filters are able to discard a large number of detection windows without compromising the accuracy. Finally, we propose a novel approach to extract powerful features regarding the scene. The method combines results of distinct pedestrian detectors by reinforcing the human hypothesis, whereas suppressing a significant number of false positives due to the lack of spatial consensus when multiple detectors are considered. Our proposed approach, referred to as Spatial Consensus (SC), outperforms all previously published state-of-the-art pedestrian detection methods. |
Marco Tulio Alves Rodrigues Detecção de Mudanças em Cenas Terrestres usando Imagens Aéreas PhD Thesis 2016. Abstract | Links | BibTeX | Tags: Change Detection @phdthesis{Rodrigues:2016:PhD, title = {Detecção de Mudanças em Cenas Terrestres usando Imagens Aéreas}, author = {Marco Tulio Alves Rodrigues}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/03/dissertation_2016_MarcoTulio.pdf}, year = {2016}, date = {2016-03-22}, abstract = {This study addresses the problem of change detection in landscapes using aerial images acquired at different times, important for many applications. The monitoring pipeline, for instance, the usual way to change detection is a task performed by human operators which evaluates a video of a monitoring camera and searches for changes in the scene from the comparison of image pairs. This procedure is prone to errors because it is a tedious task, therefore is a justification to automated method. Besides enabling the reduction of errors and speed up the monitoring process, a system automatic can be used as a filter to provide a set of key frames that should receive more attention from the operator. Thus, the system can help the operators on the decision making process regarding the actions to be performed. The basic procedure for detecting changes is to find a set of pixels or regions that are different in another test image. However, images acquired at different dates may be influenced by radiometric and registration factors. In other words, the influence of camera movement, lighting variation, and atmospheric variation must be minimized. One of the methods proposed extracts local descriptors in the image blocks and provides an estimate of change using a non-parametric model (KDE). Unlike background subtraction and remote sensing methods which are based on pixels and assume independence between them, the proposed approach not requires a complex learning phase and it is capable of detecting changes using only two images. The second method applies an image segmentation before make the matching of the similar regions. In the experiments, the proposed approaches are compared to techniques used in change detection. According to the results, the proposed approach based on non-parametric model outperforms other methods found in the literature, mainly due to the fact that the approach is more robust to lighting variation. The results also demonstrate that the approach is able to filter images that should be further analyzed by operators.}, keywords = {Change Detection}, pubstate = {published}, tppubtype = {phdthesis} } This study addresses the problem of change detection in landscapes using aerial images acquired at different times, important for many applications. The monitoring pipeline, for instance, the usual way to change detection is a task performed by human operators which evaluates a video of a monitoring camera and searches for changes in the scene from the comparison of image pairs. This procedure is prone to errors because it is a tedious task, therefore is a justification to automated method. Besides enabling the reduction of errors and speed up the monitoring process, a system automatic can be used as a filter to provide a set of key frames that should receive more attention from the operator. Thus, the system can help the operators on the decision making process regarding the actions to be performed. The basic procedure for detecting changes is to find a set of pixels or regions that are different in another test image. However, images acquired at different dates may be influenced by radiometric and registration factors. In other words, the influence of camera movement, lighting variation, and atmospheric variation must be minimized. One of the methods proposed extracts local descriptors in the image blocks and provides an estimate of change using a non-parametric model (KDE). Unlike background subtraction and remote sensing methods which are based on pixels and assume independence between them, the proposed approach not requires a complex learning phase and it is capable of detecting changes using only two images. The second method applies an image segmentation before make the matching of the similar regions. In the experiments, the proposed approaches are compared to techniques used in change detection. According to the results, the proposed approach based on non-parametric model outperforms other methods found in the literature, mainly due to the fact that the approach is more robust to lighting variation. The results also demonstrate that the approach is able to filter images that should be further analyzed by operators. |
Cassio Elias Santos dos Junior; Ewa Kijak; Guillaume Gravier; William Robson Schwartz Partial least squares for face hashing Journal Article Neurocomputing, 213 , pp. 34–47, 2016. Links | BibTeX | Tags: Face Identification, Face Recognition, Featured Publication, Partial Least Squares @article{Santos:2016:Neurocomputing, title = {Partial least squares for face hashing}, author = {Cassio Elias Santos dos Junior and Ewa Kijak and Guillaume Gravier and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/paper_2016_Neurocomputing_Santos.pdf}, year = {2016}, date = {2016-02-03}, journal = {Neurocomputing}, volume = {213}, pages = {34--47}, keywords = {Face Identification, Face Recognition, Featured Publication, Partial Least Squares}, pubstate = {published}, tppubtype = {article} } |
Antonio Carlos Nazare Junior; William Robson Schwartz A scalable and flexible framework for smart video surveillance Journal Article Computer Vision and Image Understanding, 144 (C), pp. 258–275, 2016. Links | BibTeX | Tags: Smart Surveillance, Smart Surveillance Framework, SSF, Surveillance Systems, VER+, Video Surveillance @article{Nazare:2016:CVIU, title = {A scalable and flexible framework for smart video surveillance}, author = {Antonio Carlos Nazare Junior and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/paper_2016_CVIU.pdf}, year = {2016}, date = {2016-01-01}, journal = {Computer Vision and Image Understanding}, volume = {144}, number = {C}, pages = {258--275}, keywords = {Smart Surveillance, Smart Surveillance Framework, SSF, Surveillance Systems, VER+, Video Surveillance}, pubstate = {published}, tppubtype = {article} } |
Marco Tulio Alves Rodrigues; Daniel Balbino de Mesquita; Erickson R Nascimento; William Robson Schwartz Change detection based on feature invariant to monotonic transforms and spatially constrained matching Journal Article Journal of Electronic Imaging, 25 (1), pp. 1-10, 2016. Links | BibTeX | Tags: Change Detection @article{Rodrigues:2016:JEI, title = {Change detection based on feature invariant to monotonic transforms and spatially constrained matching}, author = {Marco Tulio Alves Rodrigues and Daniel Balbino de Mesquita and Erickson R Nascimento and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/paper_2016_JEI.pdf}, year = {2016}, date = {2016-01-01}, journal = {Journal of Electronic Imaging}, volume = {25}, number = {1}, pages = {1-10}, keywords = {Change Detection}, pubstate = {published}, tppubtype = {article} } |
Cristianne Rodrigues Santos Dutra Técnicas Otimizadas para Reidentificaçâo de Pessoas Masters Thesis Federal University of Minas Gerais, 2016. Links | BibTeX | Tags: DeepEyes, GigaFrames, Person Re-Identification, VER+ @mastersthesis{Dutra:2016:MSc, title = {Técnicas Otimizadas para Reidentificaçâo de Pessoas}, author = {Cristianne Rodrigues Santos Dutra}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/thesis_2016_Cristianne.pdf}, year = {2016}, date = {2016-01-01}, school = {Federal University of Minas Gerais}, keywords = {DeepEyes, GigaFrames, Person Re-Identification, VER+}, pubstate = {published}, tppubtype = {mastersthesis} } |
Cassio Santos E dos Jr.; Ewa Kijak; Guillaume Gravier; William Robson Schwartz Partial least squares for face hashing Journal Article Neurocomputing, 213 , pp. 34-47, 2016. @article{Santos:2016:Neurocomputingb, title = {Partial least squares for face hashing}, author = {Cassio Santos E dos Jr. and Ewa Kijak and Guillaume Gravier and William Robson Schwartz}, url = {http://www.dcc.ufmg.br/~william/papers/paper_2016_Neurocomputing_Santos.pdf}, doi = {10.1016/j.neucom.2016.02.083}, year = {2016}, date = {2016-01-01}, journal = {Neurocomputing}, volume = {213}, pages = {34-47}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
2015 |
Rensso Victor Hugo Mora Colque; Carlos Antonio Caetano Junior; William Robson Schwartz Histograms of Optical Flow Orientation and Magnitude to Detect Anomalous Events in Videos Inproceedings Conference on Graphics, Patterns and Images (SIBGRAPI), pp. 1-8, 2015. Links | BibTeX | Tags: Anomalous Event Detection, HOFM, SmartView @inproceedings{SIBGRAPI:2015:Colque, title = {Histograms of Optical Flow Orientation and Magnitude to Detect Anomalous Events in Videos}, author = {Rensso Victor Hugo Mora Colque and Carlos Antonio Caetano Junior and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/paper_camera_ready.pdf}, year = {2015}, date = {2015-08-25}, booktitle = {Conference on Graphics, Patterns and Images (SIBGRAPI)}, pages = {1-8}, keywords = {Anomalous Event Detection, HOFM, SmartView}, pubstate = {published}, tppubtype = {inproceedings} } |
Cassio Elias Santos dos Junior Partial Least Squares for Face Hashing Masters Thesis Federal University of Minas Gerais, 2015. Abstract | Links | BibTeX | Tags: DeepEyes, Face Identification, Face Recognition, GigaFrames, Indexing Structure, Local Sensitive Hashing, Partial Least Squares, VER+ @mastersthesis{Santos:2015:MSc, title = {Partial Least Squares for Face Hashing}, author = {Cassio Elias Santos dos Junior}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/dissertation_2015_Cassio.pdf}, year = {2015}, date = {2015-08-24}, school = {Federal University of Minas Gerais}, abstract = {Face identification is an important research topic due to areas such as its application to surveillance, forensics and human-computer interaction. In the past few years, a myriad of methods for face identification has been proposed in the literature, with just a few among them focusing on scalability. In this work, we propose a simple but efficient approach for scalable face identification based on partial least squares (PLS) and random independent hash functions inspired by locality-sensitive hashing (LSH), resulting in the PLS for hashing (PLSH) approach. The original PLSH approach is further extended using feature selection to reduce the computational cost to evaluate the PLS-based hash functions, resulting in the state-of-the-art extended PLSH approach (ePLSH). The proposed approach is evaluated in the dataset FERET and in the dataset FRGCv1. The results show significant reduction in the number of subjects evaluated in the face identification (reduced to 0.3% of the gallery), providing averaged speedups up to 233 times compared to evaluating all subjects in the face gallery and 58 times compared to previous works in the literature.}, keywords = {DeepEyes, Face Identification, Face Recognition, GigaFrames, Indexing Structure, Local Sensitive Hashing, Partial Least Squares, VER+}, pubstate = {published}, tppubtype = {mastersthesis} } Face identification is an important research topic due to areas such as its application to surveillance, forensics and human-computer interaction. In the past few years, a myriad of methods for face identification has been proposed in the literature, with just a few among them focusing on scalability. In this work, we propose a simple but efficient approach for scalable face identification based on partial least squares (PLS) and random independent hash functions inspired by locality-sensitive hashing (LSH), resulting in the PLS for hashing (PLSH) approach. The original PLSH approach is further extended using feature selection to reduce the computational cost to evaluate the PLS-based hash functions, resulting in the state-of-the-art extended PLSH approach (ePLSH). The proposed approach is evaluated in the dataset FERET and in the dataset FRGCv1. The results show significant reduction in the number of subjects evaluated in the face identification (reduced to 0.3% of the gallery), providing averaged speedups up to 233 times compared to evaluating all subjects in the face gallery and 58 times compared to previous works in the literature. |
Cassio Elias Santos dos Junior; E Kijak; G Gravier; William Robson Schwartz Learning to Hash Faces Using Large Feature Vectors Inproceedings Content-Based Multimedia Indexing (CBMI), 13th International Workshop on, pp. 1–6, IEEE, 2015. Links | BibTeX | Tags: Face Identification, Face Recognition, GigaFrames, Indexing Structure, Locality Sensitive Hashing, Partial Least Squares, SmartView, VER+ @inproceedings{santos2015learning, title = {Learning to Hash Faces Using Large Feature Vectors}, author = {Cassio Elias Santos dos Junior and E Kijak and G Gravier and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/2015-Learning_to_Hash_Faces_Using_Large_Feature_Vectors.pdf}, year = {2015}, date = {2015-01-01}, booktitle = {Content-Based Multimedia Indexing (CBMI), 13th International Workshop on}, pages = {1--6}, publisher = {IEEE}, keywords = {Face Identification, Face Recognition, GigaFrames, Indexing Structure, Locality Sensitive Hashing, Partial Least Squares, SmartView, VER+}, pubstate = {published}, tppubtype = {inproceedings} } |
Shuowen Hu; Jonghyun Choi; Alex L Chan; William Robson Schwartz Thermal-to-visible Face Recognition using Partial Least Squares Journal Article Journal of the Optical Society of America A, 32 (3), pp. 431–442, 2015. Links | BibTeX | Tags: Face Recognition, Thermal Imaging, VER+ @article{Hu:2015:JOSAA, title = {Thermal-to-visible Face Recognition using Partial Least Squares}, author = {Shuowen Hu and Jonghyun Choi and Alex L Chan and William Robson Schwartz}, url = {http://dx.doi.org/10.1364/JOSAA.32.000431}, year = {2015}, date = {2015-01-01}, journal = {Journal of the Optical Society of America A}, volume = {32}, number = {3}, pages = {431--442}, publisher = {OSA}, keywords = {Face Recognition, Thermal Imaging, VER+}, pubstate = {published}, tppubtype = {article} } |
G L Prado; William Robson Schwartz; Helio Pedrini A Verify-Correct Approach to Person Re-identification Based on Partial Least Squares Signatures Inproceedings International Conference on Biometrics, pp. 1-7, 2015. Links | BibTeX | Tags: Partial Least Squares, Person Re-Identification, SmartView, VER+ @inproceedings{Prado:2015:ICB, title = {A Verify-Correct Approach to Person Re-identification Based on Partial Least Squares Signatures}, author = {G L Prado and William Robson Schwartz and Helio Pedrini}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/paper_2015_ICB_Prado.pdf}, year = {2015}, date = {2015-01-01}, booktitle = {International Conference on Biometrics}, pages = {1-7}, series = {Lecture Notes in Computer Science}, keywords = {Partial Least Squares, Person Re-Identification, SmartView, VER+}, pubstate = {published}, tppubtype = {inproceedings} } |
Gerson Paulo de Carlos; Helio Pedrini; William Robson Schwartz Classification schemes based on Partial Least Squares for face identification Journal Article Journal of Visual Communication and Image Representation, 32 , pp. 170 - 179, 2015, ISSN: 1047-3203. Links | BibTeX | Tags: Face Identification, Face Recognition, One-Against-All Classification Scheme, Partial Least Squares, VER+ @article{2015:JVCI:Carlos, title = {Classification schemes based on Partial Least Squares for face identification}, author = {Gerson Paulo de Carlos and Helio Pedrini and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/paper_2015_JVCI.pdf}, issn = {1047-3203}, year = {2015}, date = {2015-01-01}, journal = {Journal of Visual Communication and Image Representation}, volume = {32}, pages = {170 - 179}, keywords = {Face Identification, Face Recognition, One-Against-All Classification Scheme, Partial Least Squares, VER+}, pubstate = {published}, tppubtype = {article} } |
Marco Tulio Alves Rodrigues; Daniel Balbino; Erickson R Nascimento; William Robson Schwartz A Non-Parametric Approach to Detect Changes in Aerial Images Inproceedings 14th Iberoamerican Congress on Pattern Recognition (CIARP), pp. 1-8, 2015. Links | BibTeX | Tags: Change Detection @inproceedings{Rodrigues:2015:CIARP, title = {A Non-Parametric Approach to Detect Changes in Aerial Images}, author = {Marco Tulio Alves Rodrigues and Daniel Balbino and Erickson R Nascimento and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/paper_2015_CIARP_Rodrigues.pdf}, year = {2015}, date = {2015-01-01}, booktitle = {14th Iberoamerican Congress on Pattern Recognition (CIARP)}, pages = {1-8}, keywords = {Change Detection}, pubstate = {published}, tppubtype = {inproceedings} } |
A Pinto; H Pedrini; William Robson Schwartz; Rocha A Face Spoofing Detection Through Visual Codebooks of Spectral Temporal Cubes Journal Article Image Processing, IEEE Transactions on, 24 (12), pp. 4726-4740, 2015, ISSN: 1057-7149. Links | BibTeX | Tags: DET, GigaFrames, Spoofing Detection @article{TIP:2015:Pinto, title = {Face Spoofing Detection Through Visual Codebooks of Spectral Temporal Cubes}, author = {A Pinto and H Pedrini and William Robson Schwartz and Rocha A}, url = {http://dx.doi.org/10.1109/TIP.2015.2466088}, issn = {1057-7149}, year = {2015}, date = {2015-01-01}, journal = {Image Processing, IEEE Transactions on}, volume = {24}, number = {12}, pages = {4726-4740}, keywords = {DET, GigaFrames, Spoofing Detection}, pubstate = {published}, tppubtype = {article} } |
Artur Jordao; Victor Hugo Cunha de Melo; William Robson Schwartz A Study of Filtering Approaches for Sliding Window Pedestrian Detection Inproceedings Workshop em Visao Computacional (WVC), pp. 1-8, 2015. Links | BibTeX | Tags: DET, Pedestrian Detection, SmartView @inproceedings{Correia:2015:WVC, title = {A Study of Filtering Approaches for Sliding Window Pedestrian Detection}, author = {Artur Jordao and Victor Hugo Cunha de Melo and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/paper_2015_WVC_Correia.pdf}, year = {2015}, date = {2015-01-01}, booktitle = {Workshop em Visao Computacional (WVC)}, pages = {1-8}, keywords = {DET, Pedestrian Detection, SmartView}, pubstate = {published}, tppubtype = {inproceedings} } |
Ramon F Pessoa; William Robson Schwartz; Jefersson A dos Santos A Study on Low-Cost Representations for Image Feature Extraction on Mobile Devices Inproceedings 14th Iberoamerican Congress on Pattern Recognition (CIARP), pp. 1-8, 2015. Links | BibTeX | Tags: DET, Feature Extraction, GigaFrames @inproceedings{Pessoa:2015:CIARP, title = {A Study on Low-Cost Representations for Image Feature Extraction on Mobile Devices}, author = {Ramon F Pessoa and William Robson Schwartz and Jefersson A dos Santos}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/paper_2015_CIARP_Pessoa.pdf}, year = {2015}, date = {2015-01-01}, booktitle = {14th Iberoamerican Congress on Pattern Recognition (CIARP)}, pages = {1-8}, keywords = {DET, Feature Extraction, GigaFrames}, pubstate = {published}, tppubtype = {inproceedings} } |
Cassio Elias Santos dos Junior; Guillaume Gravier; William Robson Schwartz SSIG and IRISA at Multimodal Person Discovery Inproceedings Working Notes Proceedings of the MediaEval 2015 Workshop, 2015. Links | BibTeX | Tags: Face Recognition, MediaEval, Multimodal Person Discovery, Person Discovery @inproceedings{Santos:2015:MediaEval, title = {SSIG and IRISA at Multimodal Person Discovery}, author = {Cassio Elias Santos dos Junior and Guillaume Gravier and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/paper_2015_MediaEval.pdf}, year = {2015}, date = {2015-01-01}, booktitle = {Working Notes Proceedings of the MediaEval 2015 Workshop}, keywords = {Face Recognition, MediaEval, Multimodal Person Discovery, Person Discovery}, pubstate = {published}, tppubtype = {inproceedings} } |
Sirlene Peixoto; Gabriel Resende Gonçalves; Guillermo Camara-Chavez; William Robson Schwartz; David Menotti Gomes Brazilian License Plate Character Recognition using Deep Learning Inproceedings Workshop em Visao Computacional (WVC), pp. 1-5, 2015. Links | BibTeX | Tags: Automatic License Plate Recognition, Deep Learning @inproceedings{Peixoto:2015:WVC, title = {Brazilian License Plate Character Recognition using Deep Learning}, author = {Sirlene Peixoto and Gabriel Resende Gonçalves and Guillermo Camara-Chavez and William Robson Schwartz and David Menotti Gomes}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/paper_2015_WVC_Peixoto.pdf}, year = {2015}, date = {2015-01-01}, booktitle = {Workshop em Visao Computacional (WVC)}, pages = {1-5}, keywords = {Automatic License Plate Recognition, Deep Learning}, pubstate = {published}, tppubtype = {inproceedings} } |
Raphael Felipe Carvalho de Prates; William Robson Schwartz CBRA: Color-Based Ranking Aggregation for Person Re-Identification Inproceedings IEEE International Conference on Image Processing (ICIP), pp. 1-5, 2015. Links | BibTeX | Tags: CBRA, GigaFrames, Person Re-Identification, Ranking Aggregation, SmartView, VER+ @inproceedings{Prates:2015:ICB, title = {CBRA: Color-Based Ranking Aggregation for Person Re-Identification}, author = {Raphael Felipe Carvalho de Prates and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/paper_2015_ICIP_Prates.pdf}, year = {2015}, date = {2015-01-01}, booktitle = {IEEE International Conference on Image Processing (ICIP)}, pages = {1-5}, keywords = {CBRA, GigaFrames, Person Re-Identification, Ranking Aggregation, SmartView, VER+}, pubstate = {published}, tppubtype = {inproceedings} } |
Raphael Felipe Carvalho de Prates; William Robson Schwartz Appearance-Based Person Re-identification by Intra-Camera Discriminative Models and Rank Aggregation Inproceedings International Conference on Biometrics, pp. 1-8, 2015. Links | BibTeX | Tags: Person Re-Identification, SmartView @inproceedings{Prates:2015:ICBb, title = {Appearance-Based Person Re-identification by Intra-Camera Discriminative Models and Rank Aggregation}, author = {Raphael Felipe Carvalho de Prates and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/paper_2015_ICB_Prates.pdf}, year = {2015}, date = {2015-01-01}, booktitle = {International Conference on Biometrics}, pages = {1-8}, series = {Lecture Notes in Computer Science}, keywords = {Person Re-Identification, SmartView}, pubstate = {published}, tppubtype = {inproceedings} } |
D Menotti; G Chiachia; A Pinto; William Robson Schwartz; H Pedrini; Xavier A Falcao; A Rocha Deep Representations for Iris, Face, and Fingerprint Spoofing Detection Journal Article Information Forensics and Security, IEEE Transactions on, 10 (4), pp. 864-879, 2015, ISSN: 1556-6013. Links | BibTeX | Tags: Deep Learning, DeepEyes, DET, SmartView, Spoofing Detection @article{Menotti:2015:TIFS, title = {Deep Representations for Iris, Face, and Fingerprint Spoofing Detection}, author = {D Menotti and G Chiachia and A Pinto and William Robson Schwartz and H Pedrini and Xavier A Falcao and A Rocha}, url = {http://dx.doi.org/10.1109/TIFS.2015.2398817}, issn = {1556-6013}, year = {2015}, date = {2015-01-01}, journal = {Information Forensics and Security, IEEE Transactions on}, volume = {10}, number = {4}, pages = {864-879}, keywords = {Deep Learning, DeepEyes, DET, SmartView, Spoofing Detection}, pubstate = {published}, tppubtype = {article} } |
A Pinto; William Robson Schwartz; H Pedrini; De Rezende A Rocha Using Visual Rhythms for Detecting Video-Based Facial Spoof Attacks Journal Article Information Forensics and Security, IEEE Transactions on, 10 (5), pp. 1025-1038, 2015, ISSN: 1556-6013. Links | BibTeX | Tags: DeepEyes, Spoofing Detection @article{Pinto:2015:TIFS, title = {Using Visual Rhythms for Detecting Video-Based Facial Spoof Attacks}, author = {A Pinto and William Robson Schwartz and H Pedrini and De Rezende A Rocha}, url = {http://dx.doi.org/10.1109/TIFS.2015.2395139}, issn = {1556-6013}, year = {2015}, date = {2015-01-01}, journal = {Information Forensics and Security, IEEE Transactions on}, volume = {10}, number = {5}, pages = {1025-1038}, keywords = {DeepEyes, Spoofing Detection}, pubstate = {published}, tppubtype = {article} } |
Ricardo Barbosa Kloss; Samira Santos da Silva; Marcos Vinicius Mussel Cirne; Hélio Pedrini; William Robson Schwartz Partial Least Squares Image Clustering Inproceedings Conference on Graphics, Patterns and Images (SIBGRAPI), pp. 1-8, 2015. Links | BibTeX | Tags: Image Clustering, Image Grouping, Partial Least Squares, Video Summarization @inproceedings{Kloss:2015b, title = {Partial Least Squares Image Clustering}, author = {Ricardo Barbosa Kloss and Samira Santos da Silva and Marcos Vinicius Mussel Cirne and Hélio Pedrini and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/paper_camera_ready1.pdf}, year = {2015}, date = {2015-01-01}, booktitle = {Conference on Graphics, Patterns and Images (SIBGRAPI)}, pages = {1-8}, keywords = {Image Clustering, Image Grouping, Partial Least Squares, Video Summarization}, pubstate = {published}, tppubtype = {inproceedings} } |
2014 |
Rensso Victor Hugo Mora Colque; Guillermo Camara Chavez; William Robson Schwartz Detection of groups of people in surveillance videos based on spatio-temporal clues Inproceedings 19th Iberoamerican Congress on Pattern Recognition (CIARP), pp. 948-955, Springer International Publishing, 2014. Links | BibTeX | Tags: Crowd Event Detection, DET, Group Detection, SmartView @inproceedings{crowdciarp2014, title = {Detection of groups of people in surveillance videos based on spatio-temporal clues}, author = {Rensso Victor Hugo Mora Colque and Guillermo Camara Chavez and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/2014-Detection-of-Groups-of-People-in-Surveillance-Videos-based-on-Spatio-Temporal-Clues.pdf}, year = {2014}, date = {2014-11-06}, booktitle = {19th Iberoamerican Congress on Pattern Recognition (CIARP)}, volume = {8827}, pages = {948-955}, publisher = {Springer International Publishing}, series = {Lecture Notes in Computer Science}, keywords = {Crowd Event Detection, DET, Group Detection, SmartView}, pubstate = {published}, tppubtype = {inproceedings} } |
Antonio Carlos Nazare Junior A Scalable and Versatile Framework for Smart Video Surveillance Masters Thesis Federal University of Minas Gerais, 2014. Abstract | Links | BibTeX | Tags: ARDOP, Smart Surveillance, Surveillance Systems, VER+, Video Surveillance @mastersthesis{Nazare:2014:MSc, title = {A Scalable and Versatile Framework for Smart Video Surveillance}, author = {Antonio Carlos Nazare Junior}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/03/dissertation_2014_Antonio-1.pdf}, year = {2014}, date = {2014-09-05}, school = {Federal University of Minas Gerais}, abstract = {The availability of surveillance cameras placed in public locations has increased vastly in the last years, providing a safe environment for people at the cost of huge amount of visual data collected. Such data are mostly processed manually, a task which is labor intensive and prone to errors. Therefore, automatic approaches must be employed to enable the processing of the data, so that human operators only need to reason about selected portions. Focused on solving problems in the domain of visual surveillance, computer vision problems applied to this domain have been developed for several years aiming at finding accurate and efficient solutions, required to allow the execution of surveillance systems in real environments. The main goal of such systems is to analyze the scene focusing on the detection and recognition of suspicious activities performed by humans in the scene, so that the security staff can pay closer attention to these preselected activities. However these systems are rarely tackled in a scalable manner. Before developing a full surveillance system, several problems have to be solved first, for instance: background subtraction, person detection, tracking and re-identification, face recognition, and action recognition. Even though each of these problems have been researched in the past decades, they are hardly considered in a sequence. Each one is usually solved individually. However, in a real surveillance scenario, the aforementioned problems have to be solved in sequence considering only videos as the input. Aiming at the direction of evaluating approaches in more realistic scenarios, this work proposes a framework called Smart Surveillance Framework (SSF), to allow researchers to implement their solutions to the above problems as a sequence of processing modules that communicates through a shared memory. The SSF is a C++ library built to provide important features for a surveillance system, such as a automatic scene understanding, scalability, real-time operation, multi-sensor environment, usage of low cost standard components, runtime re-configuration, and communication control.}, keywords = {ARDOP, Smart Surveillance, Surveillance Systems, VER+, Video Surveillance}, pubstate = {published}, tppubtype = {mastersthesis} } The availability of surveillance cameras placed in public locations has increased vastly in the last years, providing a safe environment for people at the cost of huge amount of visual data collected. Such data are mostly processed manually, a task which is labor intensive and prone to errors. Therefore, automatic approaches must be employed to enable the processing of the data, so that human operators only need to reason about selected portions. Focused on solving problems in the domain of visual surveillance, computer vision problems applied to this domain have been developed for several years aiming at finding accurate and efficient solutions, required to allow the execution of surveillance systems in real environments. The main goal of such systems is to analyze the scene focusing on the detection and recognition of suspicious activities performed by humans in the scene, so that the security staff can pay closer attention to these preselected activities. However these systems are rarely tackled in a scalable manner. Before developing a full surveillance system, several problems have to be solved first, for instance: background subtraction, person detection, tracking and re-identification, face recognition, and action recognition. Even though each of these problems have been researched in the past decades, they are hardly considered in a sequence. Each one is usually solved individually. However, in a real surveillance scenario, the aforementioned problems have to be solved in sequence considering only videos as the input. Aiming at the direction of evaluating approaches in more realistic scenarios, this work proposes a framework called Smart Surveillance Framework (SSF), to allow researchers to implement their solutions to the above problems as a sequence of processing modules that communicates through a shared memory. The SSF is a C++ library built to provide important features for a surveillance system, such as a automatic scene understanding, scalability, real-time operation, multi-sensor environment, usage of low cost standard components, runtime re-configuration, and communication control. |
Jessica Sena; Cesar Augusto Moura Ferreira; Cassio Elias Santos dos Junior; Victor Hugo Cunha de Melo; William Robson Schwartz Self-Organizing Traffic Lights: A Pedestrian Oriented Approach Miscellaneous Workshop of Undergraduate Works (WUW) in SIBGRAPI - Conference on Graphics, Patterns and Images, 2014, (1st place award). Links | BibTeX | Tags: DET, Self-Organizing Pedestrian Traffic Lights @misc{sibgrapi2014selfb, title = {Self-Organizing Traffic Lights: A Pedestrian Oriented Approach}, author = {Jessica Sena and Cesar Augusto Moura Ferreira and Cassio Elias Santos dos Junior and Victor Hugo Cunha de Melo and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/2014-SIBGRAPI-Self-Organizing-Traffic-Lights-A-Pedestrian-Oriented-Approach.pdf http://www.icex.ufmg.br/index.php/noticias/noticias-do-icex/80-noticias-do-icex/alunos-do-dcc-sao-premiados-no-sibgrapi-2014}, year = {2014}, date = {2014-08-29}, pages = {86-91}, howpublished = {Workshop of Undergraduate Works (WUW) in SIBGRAPI - Conference on Graphics, Patterns and Images}, note = {1st place award}, keywords = {DET, Self-Organizing Pedestrian Traffic Lights}, pubstate = {published}, tppubtype = {misc} } |
Victor Hugo Cunha de Melo Fast and Robust Optimization Approaches for Pedestrian Detection Masters Thesis Federal University of Minas Gerais, 2014. Abstract | Links | BibTeX | Tags: ARDOP, Pedestrian Detection, SmartView @mastersthesis{Melo:2014:MSc, title = {Fast and Robust Optimization Approaches for Pedestrian Detection}, author = {Victor Hugo Cunha de Melo}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/dissertation_2014_Victor.pdf}, year = {2014}, date = {2014-02-28}, school = {Federal University of Minas Gerais}, abstract = {The large number of surveillance cameras available nowadays in strategic points of major cities provides a safe environment. However, the huge amount of data provided by the cameras prevents its manual processing, requiring the application of automated methods. Among such methods, pedestrian detection plays an important role in reducing the amount of data by locating only the regions of interest for further processing regarding activities being performed by agents in the scene. However, the currently available methods are unable to process such large amount of data in real time. Therefore, there is a need for the development of optimization techniques. Towards accomplishing the goal of reducing costs for pedestrian detection, we propose in this work two optimization approaches. The first approach consists of a cascade of rejection based on Partial Least Squares (PLS) combined with the propagation of latent variables through the stages. Our results show that the method reduces the computational cost by increasing the number of rejected background samples in earlier stages of the cascade. Our second approach proposes a novel optimization that performs a random filtering in the image to select a small number of detection windows, allowing a reduction in the computational cost. Our results show that accurate results can be achieved even when a large number of detection windows are discarded.}, keywords = {ARDOP, Pedestrian Detection, SmartView}, pubstate = {published}, tppubtype = {mastersthesis} } The large number of surveillance cameras available nowadays in strategic points of major cities provides a safe environment. However, the huge amount of data provided by the cameras prevents its manual processing, requiring the application of automated methods. Among such methods, pedestrian detection plays an important role in reducing the amount of data by locating only the regions of interest for further processing regarding activities being performed by agents in the scene. However, the currently available methods are unable to process such large amount of data in real time. Therefore, there is a need for the development of optimization techniques. Towards accomplishing the goal of reducing costs for pedestrian detection, we propose in this work two optimization approaches. The first approach consists of a cascade of rejection based on Partial Least Squares (PLS) combined with the propagation of latent variables through the stages. Our results show that the method reduces the computational cost by increasing the number of rejected background samples in earlier stages of the cascade. Our second approach proposes a novel optimization that performs a random filtering in the image to select a small number of detection windows, allowing a reduction in the computational cost. Our results show that accurate results can be achieved even when a large number of detection windows are discarded. |
Victor Hugo Cunha de Melo; Samir Moreira Andrade Leao; D Menotti; William Robson Schwartz An Optimized Sliding Window Approach to Pedestrian Detection Inproceedings IAPR International Conference on Pattern Recognition (ICPR), pp. 1-6, 2014. Links | BibTeX | Tags: DET, Pedestrian Detection, Random Filtering, SmartView @inproceedings{Melo:2014:ICPR, title = {An Optimized Sliding Window Approach to Pedestrian Detection}, author = {Victor Hugo Cunha de Melo and Samir Moreira Andrade Leao and D Menotti and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/2014-An-Optimized-Sliding-Window-Approach-to-Pedestrian-Detection.pdf}, year = {2014}, date = {2014-01-01}, booktitle = {IAPR International Conference on Pattern Recognition (ICPR)}, pages = {1-6}, keywords = {DET, Pedestrian Detection, Random Filtering, SmartView}, pubstate = {published}, tppubtype = {inproceedings} } |
Antonio Carlos Nazare Junior; Cassio Elias Santos dos Junior; Renato Ferreira; William Robson Schwartz Smart Surveillance Framework: A Versatile Tool for Video Analysis Inproceedings IEEE Winter Conference on Applications of Computer Vision, pp. 753–760, 2014. Links | BibTeX | Tags: ARDOP, Smart Surveillance, Smart Surveillance Framework, SmartView, SSF, Surveillance Systems, Video Surveillance @inproceedings{wacv2014smart, title = {Smart Surveillance Framework: A Versatile Tool for Video Analysis}, author = {Antonio Carlos Nazare Junior and Cassio Elias Santos dos Junior and Renato Ferreira and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/2014-Smart-Surveillance-Framework-A-Versatile-Tool-for-Video-Analysis.pdf}, year = {2014}, date = {2014-01-01}, booktitle = {IEEE Winter Conference on Applications of Computer Vision}, pages = {753--760}, keywords = {ARDOP, Smart Surveillance, Smart Surveillance Framework, SmartView, SSF, Surveillance Systems, Video Surveillance}, pubstate = {published}, tppubtype = {inproceedings} } |
Cassio Elias Santos dos Junior; William Robson Schwartz Extending Face Identification to Open-Set Face Recognition Inproceedings Conference on Graphics, Patterns and Images (SIBGRAPI), pp. 1-8, 2014. Links | BibTeX | Tags: ARDOP, Face Identification, Face Recognition, Open-Set Classification, SmartView @inproceedings{sibgrapi2014extending, title = {Extending Face Identification to Open-Set Face Recognition}, author = {Cassio Elias Santos dos Junior and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/2014-Extending-Face-Identification-to-Open-Set-Face-Recognition.pdf}, year = {2014}, date = {2014-01-01}, booktitle = {Conference on Graphics, Patterns and Images (SIBGRAPI)}, pages = {1-8}, keywords = {ARDOP, Face Identification, Face Recognition, Open-Set Classification, SmartView}, pubstate = {published}, tppubtype = {inproceedings} } |
Jessica Sena; Cesar Augusto Moura Ferreira; Cassio Elias Santos dos Junior; Victor Hugo Cunha de Melo; William Robson Schwartz Self-Organizing Traffic Lights: A Pedestrian Oriented Approach Inproceedings X Workshop de Visão Computacional, pp. 1-6, 2014. Links | BibTeX | Tags: DET, Self-Organizing Pedestrian Traffic Lights @inproceedings{wvc2014self, title = {Self-Organizing Traffic Lights: A Pedestrian Oriented Approach}, author = {Jessica Sena and Cesar Augusto Moura Ferreira and Cassio Elias Santos dos Junior and Victor Hugo Cunha de Melo and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/2014-WVC-Self-Organizing-Traffic-Lights-A-Pedestrian-Oriented-Approach.pdf}, year = {2014}, date = {2014-01-01}, booktitle = {X Workshop de Visão Computacional}, pages = {1-6}, keywords = {DET, Self-Organizing Pedestrian Traffic Lights}, pubstate = {published}, tppubtype = {inproceedings} } |
Marco Tulio Alves Rodrigues; L O Milen; E R Nascimento; William Robson Schwartz Change detection based on features invariant to monotonic transforms and spatial constrained matching Inproceedings Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on, pp. 4334-4338, 2014. Links | BibTeX | Tags: Change Detection @inproceedings{rodrigues:2014:icassp, title = {Change detection based on features invariant to monotonic transforms and spatial constrained matching}, author = {Marco Tulio Alves Rodrigues and L O Milen and E R Nascimento and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/2014-CHANGE-DETECTION-BASED-ON-FEATURES-INVARIANT-TO-MONOTONIC-TRANSFORMS-AND-SPATIAL-CONSTRAINED-MATCHING.pdf}, year = {2014}, date = {2014-01-01}, booktitle = {Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on}, pages = {4334-4338}, keywords = {Change Detection}, pubstate = {published}, tppubtype = {inproceedings} } |
William Robson Schwartz Computer Vision: A Reference Guide Book Chapter Ikeuchi, Katsushi (Ed.): Chapter Appearance-Based Human Detection, pp. 36–38, Springer US, 2014. Links | BibTeX | Tags: Pedestrian Detection @inbook{schwartz:2014:appearance, title = {Computer Vision: A Reference Guide}, author = {William Robson Schwartz}, editor = {Katsushi Ikeuchi}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/paper_submitted.pdf http://www.springer.com/us/book/9780387307718}, year = {2014}, date = {2014-01-01}, pages = {36--38}, publisher = {Springer US}, chapter = {Appearance-Based Human Detection}, keywords = {Pedestrian Detection}, pubstate = {published}, tppubtype = {inbook} } |
Antonio Carlos Nazare Junior; Renato Ferreira; William Robson Schwartz Scalable Feature Extraction for Visual Surveillance Inproceedings Iberoamerican Congress on Pattern Recognition (CIARP), pp. 375-382, Springer International Publishing, 2014. Links | BibTeX | Tags: DET, Feature Extraction, Smart Surveillance, SmartView, Surveillance Systems, Video Surveillance @inproceedings{Nazare:2014:CIARP, title = {Scalable Feature Extraction for Visual Surveillance}, author = {Antonio Carlos Nazare Junior and Renato Ferreira and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/paper_2014_CIARP_Antonio.pdf}, year = {2014}, date = {2014-01-01}, booktitle = {Iberoamerican Congress on Pattern Recognition (CIARP)}, volume = {8827}, pages = {375-382}, publisher = {Springer International Publishing}, series = {Lecture Notes in Computer Science}, keywords = {DET, Feature Extraction, Smart Surveillance, SmartView, Surveillance Systems, Video Surveillance}, pubstate = {published}, tppubtype = {inproceedings} } |
Cristianne Rodrigues Santos Dutra; M C Rocha; William Robson Schwartz Person Re-Identification Based on Weighted Indexing Structures Inproceedings Iberoamerican Congress on Pattern Recognition (CIARP), pp. 359-366, Springer International Publishing, 2014. Links | BibTeX | Tags: ARDOP, Indexing Structure, Inverted Lists, Person Re-Identification, SmartView @inproceedings{Dutra:2014:CIARP, title = {Person Re-Identification Based on Weighted Indexing Structures}, author = {Cristianne Rodrigues Santos Dutra and M C Rocha and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/paper_2014_CIARP_Dutra.pdf}, year = {2014}, date = {2014-01-01}, booktitle = {Iberoamerican Congress on Pattern Recognition (CIARP)}, volume = {8827}, pages = {359-366}, publisher = {Springer International Publishing}, series = {Lecture Notes in Computer Science}, keywords = {ARDOP, Indexing Structure, Inverted Lists, Person Re-Identification, SmartView}, pubstate = {published}, tppubtype = {inproceedings} } |
Raphael Felipe Carvalho de Prates; G Camara-Chavez; William Robson Schwartz; D M Gomes An Adaptive Vehicle License Plate Detection at Higher Matching Degree Inproceedings Iberoamerican Congress on Pattern Recognition (CIARP), pp. 454-461, Springer International Publishing, 2014. Links | BibTeX | Tags: Automatic License Plate Recognition, DET, License Plate Detection @inproceedings{Prates:2014:CIARP, title = {An Adaptive Vehicle License Plate Detection at Higher Matching Degree}, author = {Raphael Felipe Carvalho de Prates and G Camara-Chavez and William Robson Schwartz and D M Gomes}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/paper_2014_CIARP_Prates-1.pdf}, year = {2014}, date = {2014-01-01}, booktitle = {Iberoamerican Congress on Pattern Recognition (CIARP)}, volume = {8827}, pages = {454-461}, publisher = {Springer International Publishing}, series = {Lecture Notes in Computer Science}, keywords = {Automatic License Plate Recognition, DET, License Plate Detection}, pubstate = {published}, tppubtype = {inproceedings} } |
2013 |
William Robson Schwartz; Victor Hugo Cunha de Melo; H Pedrini; L S Davis A Data-Driven Detection Optimization Framework Journal Article Neurocomputing, 104 , pp. 35-49, 2013. Links | BibTeX | Tags: Partial Least Squares, Pedestrian Detection @article{Schwartz:2013:Neurocomputing, title = {A Data-Driven Detection Optimization Framework}, author = {William Robson Schwartz and Victor Hugo Cunha de Melo and H Pedrini and L S Davis}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/2013-A-Data-Driven-Detection-Optimization-Framework.pdf}, year = {2013}, date = {2013-01-01}, journal = {Neurocomputing}, volume = {104}, pages = {35-49}, keywords = {Partial Least Squares, Pedestrian Detection}, pubstate = {published}, tppubtype = {article} } |
Gabriel Lorencetti Prado; William Robson Schwartz; Helio Pedrini Person Re-identification Using Partial Least Squares Appearance Modeling Incollection Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications, pp. 382–390, 2013. Links | BibTeX | Tags: ARDOP, Person Re-Identification @incollection{prado2013person, title = {Person Re-identification Using Partial Least Squares Appearance Modeling}, author = {Gabriel Lorencetti Prado and William Robson Schwartz and Helio Pedrini}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/2013-Person-Re-identification-Using-Partial-Least-Squares-Appearance-Modeling.pdf}, year = {2013}, date = {2013-01-01}, booktitle = {Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications}, pages = {382--390}, keywords = {ARDOP, Person Re-Identification}, pubstate = {published}, tppubtype = {incollection} } |
G P Carlos; H Pedrini; William Robson Schwartz Fast and Scalable Enrollment for Face Identification based on Partial Least Squares Inproceedings IEEE International Conference on Automatic Face and Gesture Recognition, 2013. Links | BibTeX | Tags: ARDOP, Face Identification, Face Recognition, One-Against-Some Classification Scheme @inproceedings{Carlos:2013:FG, title = {Fast and Scalable Enrollment for Face Identification based on Partial Least Squares}, author = {G P Carlos and H Pedrini and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/paper_2013_FG.pdf}, year = {2013}, date = {2013-01-01}, booktitle = {IEEE International Conference on Automatic Face and Gesture Recognition}, keywords = {ARDOP, Face Identification, Face Recognition, One-Against-Some Classification Scheme}, pubstate = {published}, tppubtype = {inproceedings} } |
F R de Siqueira; William Robson Schwartz; H Pedrini Multi-Scale Gray Level Co-Occurrence Matrices for Texture Description Journal Article Neurocomputing, pp. 1-10, 2013. Links | BibTeX | Tags: Feature Extraction, GLCM @article{Siqueira:2012:Neurocomputing, title = {Multi-Scale Gray Level Co-Occurrence Matrices for Texture Description}, author = {F R de Siqueira and William Robson Schwartz and H Pedrini}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/2013-Multi-Scale-Gray-Level-Co-Occurrence-Matrices-for-Texture-Description-1.pdf}, year = {2013}, date = {2013-01-01}, journal = {Neurocomputing}, pages = {1-10}, keywords = {Feature Extraction, GLCM}, pubstate = {published}, tppubtype = {article} } |
M M Chakka; A Anjos; S Marcel; R Tronci; D Muntoni; G Fadda; M Pili; N Sirena; G Murgia; M Ristori; F Roli; J Yan; D Yi; Z Lei; Z Zhang; S Li; William Robson Schwartz; A Rocha; H Pedrini; J Lorenzo-Navarro; M Castrillon-Santana; J Maatta Competition on Counter Measures to 2D Facial Spoofing Attacks Inproceedings International Joint Conference on Biometrics, 2013. Links | BibTeX | Tags: Spoofing Detection @inproceedings{Anjos:2011:IJCB, title = {Competition on Counter Measures to 2D Facial Spoofing Attacks}, author = {M M Chakka and A Anjos and S Marcel and R Tronci and D Muntoni and G Fadda and M Pili and N Sirena and G Murgia and M Ristori and F Roli and J Yan and D Yi and Z Lei and Z Zhang and S Li and William Robson Schwartz and A Rocha and H Pedrini and J Lorenzo-Navarro and M Castrillon-Santana and J Maatta}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/2011-Competition-on-Counter-Measures-to-2D-Facial-Spoofing-Attacks.pdf}, year = {2013}, date = {2013-01-01}, booktitle = {International Joint Conference on Biometrics}, keywords = {Spoofing Detection}, pubstate = {published}, tppubtype = {inproceedings} } |
Vitor Cezar de Lima; William Robson Schwartz; H Pedrini 3D Searchless Fractal Video Encoding at Low Bit Rates Journal Article Journal of Mathematical Imaging and Vision, 45 (3), pp. 239-250, 2013. Links | BibTeX | Tags: Fractal Compression @article{Lima:2012:JMIV, title = {3D Searchless Fractal Video Encoding at Low Bit Rates}, author = {Vitor Cezar de Lima and William Robson Schwartz and H Pedrini}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/2013-3D-Searchless-Fractal-Video-Encoding-at-Low-Bit-Rates.pdf}, year = {2013}, date = {2013-01-01}, journal = {Journal of Mathematical Imaging and Vision}, volume = {45}, number = {3}, pages = {239-250}, keywords = {Fractal Compression}, pubstate = {published}, tppubtype = {article} } |
Victor Hugo Cunha de Melo; Samir Moreira Andrade Leao; M Campos; D Menotti; William Robson Schwartz Fast Pedestrian Detection based on a Partial Least Squares Cascade Inproceedings IEEE International Conference on Image Processing, pp. 4146 - 4150, 2013. Links | BibTeX | Tags: ARDOP, Partial Least Squares, Pedestrian Detection, Rejection Cascade @inproceedings{Melo:2013:ICIPb, title = {Fast Pedestrian Detection based on a Partial Least Squares Cascade}, author = {Victor Hugo Cunha de Melo and Samir Moreira Andrade Leao and M Campos and D Menotti and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/2013-Fast-Pedestrian-Detection-based-on-a-Partial-Least-Squares-Cascade.pdf}, year = {2013}, date = {2013-01-01}, booktitle = {IEEE International Conference on Image Processing}, pages = {4146 - 4150}, keywords = {ARDOP, Partial Least Squares, Pedestrian Detection, Rejection Cascade}, pubstate = {published}, tppubtype = {inproceedings} } |
Cristianne Rodrigues Santos Dutra; T Souza; R Alves; William Robson Schwartz; L R Oliveira Re-identifying People based on Indexing Structure and Manifold Appearance Modeling Inproceedings Conference on Graphics, Patterns and Images (SIBGRAPI), pp. 218-225, 2013. Links | BibTeX | Tags: ARDOP, Indexing Structure, Inverted Lists, Person Re-Identification, Riemannian Manifold @inproceedings{Dutra:2013:SIBGRAPIb, title = {Re-identifying People based on Indexing Structure and Manifold Appearance Modeling}, author = {Cristianne Rodrigues Santos Dutra and T Souza and R Alves and William Robson Schwartz and L R Oliveira}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/03/paper_2013_SIBGRAPI.pdf}, year = {2013}, date = {2013-01-01}, booktitle = {Conference on Graphics, Patterns and Images (SIBGRAPI)}, pages = {218-225}, keywords = {ARDOP, Indexing Structure, Inverted Lists, Person Re-Identification, Riemannian Manifold}, pubstate = {published}, tppubtype = {inproceedings} } |
Raphael Felipe Carvalho de Prates; G Camara-Chavez; William Robson Schwartz; D Menotti Brazilian License Plate Detection Using Histogram of Oriented Gradients and Sliding Windows Journal Article International Journal of Computer Science and Information Technology, 5 , pp. 39-52, 2013. Links | BibTeX | Tags: ARDOP, Automatic License Plate Recognition, HOG, License Plate Detection @article{Prates:2013:IJCSIT, title = {Brazilian License Plate Detection Using Histogram of Oriented Gradients and Sliding Windows}, author = {Raphael Felipe Carvalho de Prates and G Camara-Chavez and William Robson Schwartz and D Menotti}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/paper_2013_IJCSIT.pdf}, year = {2013}, date = {2013-01-01}, journal = {International Journal of Computer Science and Information Technology}, volume = {5}, pages = {39-52}, keywords = {ARDOP, Automatic License Plate Recognition, HOG, License Plate Detection}, pubstate = {published}, tppubtype = {article} } |
2012 |
William Robson Schwartz Scalable People Re-Identification Based on a One-Against-Some Classification Scheme Inproceedings IEEE International Conference on Image Processing, 2012. Links | BibTeX | Tags: One-Against-All Classification Scheme, Person Re-Identification @inproceedings{Schwartz:2012:ICIP, title = {Scalable People Re-Identification Based on a One-Against-Some Classification Scheme}, author = {William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/2012-Scalable-People-Re-Identification-Based-on-a-One-Against-Some-Classification-Scheme.pdf}, year = {2012}, date = {2012-01-01}, booktitle = {IEEE International Conference on Image Processing}, keywords = {One-Against-All Classification Scheme, Person Re-Identification}, pubstate = {published}, tppubtype = {inproceedings} } |
Giovani Chiachia; Nicolas Pinto; William Robson Schwartz; Anderson Rocha; Alexandre X Falc~ao; David D Cox Person-Specific Subspace Analysis for Unconstrained Familiar Face Identification. Inproceedings BMVC, pp. 1–12, 2012. Links | BibTeX | Tags: Face Recognition, Face Verification, Partial Least Squares @inproceedings{chiachia2012person, title = {Person-Specific Subspace Analysis for Unconstrained Familiar Face Identification.}, author = {Giovani Chiachia and Nicolas Pinto and William Robson Schwartz and Anderson Rocha and Alexandre X Falc~ao and David D Cox}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/2012-Person-Specific-Subspace-Analysis-for-Unconstrained-Familiar-Face-Identification..pdf}, year = {2012}, date = {2012-01-01}, booktitle = {BMVC}, pages = {1--12}, keywords = {Face Recognition, Face Verification, Partial Least Squares}, pubstate = {published}, tppubtype = {inproceedings} } |