2016 |
Jordao, Artur; Sena, Jessica; Schwartz, William Robson A Late Fusion Approach to Combine Multiple Pedestrian Detectors Inproceedings IAPR International Conference on Pattern Recognition (ICPR), pp. 1-6, 2016. Links | BibTeX | Tags: DeepEyes, Featured Publication, GigaFrames, Pedestrian Detection @inproceedings{Correia:2016:ICPR, title = {A Late Fusion Approach to Combine Multiple Pedestrian Detectors}, author = {Artur Jordao and Jessica Sena and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/A-Late-Fusion-Approach-to-Combine-Multiple.pdf}, year = {2016}, date = {2016-12-13}, booktitle = {IAPR International Conference on Pattern Recognition (ICPR)}, pages = {1-6}, keywords = {DeepEyes, Featured Publication, GigaFrames, Pedestrian Detection}, pubstate = {published}, tppubtype = {inproceedings} } |
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} } |
Jordao, Artur The Good, the Fast and the Better Pedestrian Detector Masters Thesis Federal University of Minas Gerais, 2016. Resumo | 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. |
2015 |
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} } |
2014 |
de Melo, Victor Hugo Cunha Fast and Robust Optimization Approaches for Pedestrian Detection Masters Thesis Federal University of Minas Gerais, 2014. Resumo | 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} } |
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} } |
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} } |
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} } |
2011 |
Schwartz, William Robson; Davis, L S; Pedrini, H Local Response Context Applied to Pedestrian Detection Inproceedings Iberoamerican Congress on Pattern Recognition, pp. 181-188, 2011. Links | BibTeX | Tags: Partial Least Squares, Pedestrian Detection @inproceedings{Schwartz:2011:CIARP, title = {Local Response Context Applied to Pedestrian Detection}, author = {William Robson Schwartz and L S Davis and H Pedrini}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/2011-Local-Response-Context-Applied-to-Pedestrian-Detection.pdf}, year = {2011}, date = {2011-01-01}, booktitle = {Iberoamerican Congress on Pattern Recognition}, pages = {181-188}, keywords = {Partial Least Squares, Pedestrian Detection}, pubstate = {published}, tppubtype = {inproceedings} } |
2010 |
Gopalan, R; Schwartz, William Robson Detecting Humans under Partial Occlusions using Markov Logic Networks Inproceedings Performance Metrics for Intelligent Systems, 2010. Links | BibTeX | Tags: Markov Logic Networks, Pedestrian Detection @inproceedings{Gopalan:2010:PerMIS, title = {Detecting Humans under Partial Occlusions using Markov Logic Networks}, author = {R Gopalan and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/2010-Detecting-Humans-under-Partial-Occlusions-using-Markov-Logic-Networks-1.pdf}, year = {2010}, date = {2010-01-01}, booktitle = {Performance Metrics for Intelligent Systems}, keywords = {Markov Logic Networks, Pedestrian Detection}, pubstate = {published}, tppubtype = {inproceedings} } |
2009 |
Schwartz, William Robson; Kembhavi, A; Harwood, D; Davis, L S Human Detection Using Partial Least Squares Analysis Inproceedings IEEE International Conference on Computer Vision (ICCV), pp. 24-31, 2009, (oral presentation). Links | BibTeX | Tags: DetectorPLS, GLCM, HOG, Partial Least Squares, Pedestrian Detection, PLS NIPALS, VIP @inproceedings{Schwartz:2009:ICCV, title = {Human Detection Using Partial Least Squares Analysis}, author = {William Robson Schwartz and A Kembhavi and D Harwood and L S Davis}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/2009-Human-Detection-Using-Partial-Least-Squares-Analysis.pdf}, year = {2009}, date = {2009-01-01}, booktitle = {IEEE International Conference on Computer Vision (ICCV)}, pages = {24-31}, note = {oral presentation}, keywords = {DetectorPLS, GLCM, HOG, Partial Least Squares, Pedestrian Detection, PLS NIPALS, VIP}, pubstate = {published}, tppubtype = {inproceedings} } |
Schwartz, William Robson; Gopalan, R; Chellappa, R; Davis, L S Robust Human Detection under Occlusion by Integrating Face and Person Detectors Inproceedings International Conference on Biometrics, pp. 970-979, 2009. Links | BibTeX | Tags: Face Detection, Pedestrian Detection @inproceedings{Schwartz:2009:ICB, title = {Robust Human Detection under Occlusion by Integrating Face and Person Detectors}, author = {William Robson Schwartz and R Gopalan and R Chellappa and L S Davis}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/2009-Robust-Human-Detection-under-Occlusion-by-Integrating-Face-and-Person-Detectors.pdf}, year = {2009}, date = {2009-01-01}, booktitle = {International Conference on Biometrics}, volume = {5558}, pages = {970-979}, series = {Lecture Notes in Computer Science}, keywords = {Face Detection, Pedestrian Detection}, pubstate = {published}, tppubtype = {inproceedings} } |
2016 |
Artur Jordao; Jessica Sena; William Robson Schwartz A Late Fusion Approach to Combine Multiple Pedestrian Detectors Inproceedings IAPR International Conference on Pattern Recognition (ICPR), pp. 1-6, 2016. Links | BibTeX | Tags: DeepEyes, Featured Publication, GigaFrames, Pedestrian Detection @inproceedings{Correia:2016:ICPR, title = {A Late Fusion Approach to Combine Multiple Pedestrian Detectors}, author = {Artur Jordao and Jessica Sena and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/A-Late-Fusion-Approach-to-Combine-Multiple.pdf}, year = {2016}, date = {2016-12-13}, booktitle = {IAPR International Conference on Pattern Recognition (ICPR)}, pages = {1-6}, keywords = {DeepEyes, Featured Publication, GigaFrames, Pedestrian Detection}, pubstate = {published}, tppubtype = {inproceedings} } |
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} } |
Artur Jordao The Good, the Fast and the Better Pedestrian Detector Masters Thesis Federal University of Minas Gerais, 2016. Resumo | 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. |
2015 |
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} } |
2014 |
Victor Hugo Cunha de Melo Fast and Robust Optimization Approaches for Pedestrian Detection Masters Thesis Federal University of Minas Gerais, 2014. Resumo | 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} } |
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} } |
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} } |
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} } |
2011 |
William Robson Schwartz; L S Davis; H Pedrini Local Response Context Applied to Pedestrian Detection Inproceedings Iberoamerican Congress on Pattern Recognition, pp. 181-188, 2011. Links | BibTeX | Tags: Partial Least Squares, Pedestrian Detection @inproceedings{Schwartz:2011:CIARP, title = {Local Response Context Applied to Pedestrian Detection}, author = {William Robson Schwartz and L S Davis and H Pedrini}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/2011-Local-Response-Context-Applied-to-Pedestrian-Detection.pdf}, year = {2011}, date = {2011-01-01}, booktitle = {Iberoamerican Congress on Pattern Recognition}, pages = {181-188}, keywords = {Partial Least Squares, Pedestrian Detection}, pubstate = {published}, tppubtype = {inproceedings} } |
2010 |
R Gopalan; William Robson Schwartz Detecting Humans under Partial Occlusions using Markov Logic Networks Inproceedings Performance Metrics for Intelligent Systems, 2010. Links | BibTeX | Tags: Markov Logic Networks, Pedestrian Detection @inproceedings{Gopalan:2010:PerMIS, title = {Detecting Humans under Partial Occlusions using Markov Logic Networks}, author = {R Gopalan and William Robson Schwartz}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/2010-Detecting-Humans-under-Partial-Occlusions-using-Markov-Logic-Networks-1.pdf}, year = {2010}, date = {2010-01-01}, booktitle = {Performance Metrics for Intelligent Systems}, keywords = {Markov Logic Networks, Pedestrian Detection}, pubstate = {published}, tppubtype = {inproceedings} } |
2009 |
William Robson Schwartz; A Kembhavi; D Harwood; L S Davis Human Detection Using Partial Least Squares Analysis Inproceedings IEEE International Conference on Computer Vision (ICCV), pp. 24-31, 2009, (oral presentation). Links | BibTeX | Tags: DetectorPLS, GLCM, HOG, Partial Least Squares, Pedestrian Detection, PLS NIPALS, VIP @inproceedings{Schwartz:2009:ICCV, title = {Human Detection Using Partial Least Squares Analysis}, author = {William Robson Schwartz and A Kembhavi and D Harwood and L S Davis}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/2009-Human-Detection-Using-Partial-Least-Squares-Analysis.pdf}, year = {2009}, date = {2009-01-01}, booktitle = {IEEE International Conference on Computer Vision (ICCV)}, pages = {24-31}, note = {oral presentation}, keywords = {DetectorPLS, GLCM, HOG, Partial Least Squares, Pedestrian Detection, PLS NIPALS, VIP}, pubstate = {published}, tppubtype = {inproceedings} } |
William Robson Schwartz; R Gopalan; R Chellappa; L S Davis Robust Human Detection under Occlusion by Integrating Face and Person Detectors Inproceedings International Conference on Biometrics, pp. 970-979, 2009. Links | BibTeX | Tags: Face Detection, Pedestrian Detection @inproceedings{Schwartz:2009:ICB, title = {Robust Human Detection under Occlusion by Integrating Face and Person Detectors}, author = {William Robson Schwartz and R Gopalan and R Chellappa and L S Davis}, url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/2009-Robust-Human-Detection-under-Occlusion-by-Integrating-Face-and-Person-Detectors.pdf}, year = {2009}, date = {2009-01-01}, booktitle = {International Conference on Biometrics}, volume = {5558}, pages = {970-979}, series = {Lecture Notes in Computer Science}, keywords = {Face Detection, Pedestrian Detection}, pubstate = {published}, tppubtype = {inproceedings} } |