ARDOP: Robust and Discriminatory Approaches to People Observation


The automatic understanding of human activities in videos is of great interest because it allows the monitoring of environments based on the analysis of the interaction between individuals and their behaviors. In this way, new technologies to prevent accidents and to identify suspicious behavior can be developed, thus generating benefits for society. For human activities to be analyzed automatically, tasks such as detection, recognition, tracking and re-identification of individuals, as well as recognition of individual actions must be dealt with accurately and efficiently. These tasks comprise the subarea of ​​computer vision called people-watching, which deals with the analysis of images and videos containing humans. This project aimed at handling problems related to the observation of people by focusing on robust and discriminatory approaches so that the amount of non-accurate results is reduced and problems of higher level, such as recognition of activities, can be solved, thus allowing the development of applications for automatic monitoring of environments.


Contributions generated from this research…

  • Softwares

  • Publications

Sorry, no publications matched your criteria.