%0 Conference Proceedings
%4 sid.inpe.br/sibgrapi/2013/07.05.19.01
%2 sid.inpe.br/sibgrapi/2013/07.05.19.01.14
%@doi 10.1109/SIBGRAPI.2013.18
%T Change detection in human crowds
%D 2013
%A Almeida, Igor Rodrigues de,
%A Jung, Claudio Rosito,
%@affiliation Federal University of Rio Grande do Sul
%@affiliation Federal University of Rio Grande do Sul
%E Boyer, Kim,
%E Hirata, Nina,
%E Nedel, Luciana,
%E Silva, Claudio,
%B Conference on Graphics, Patterns and Images, 26 (SIBGRAPI)
%C Arequipa, Peru
%8 5-8 Aug. 2013
%I IEEE Computer Society
%J Los Alamitos
%S Proceedings
%K Crowd analysis, Unusual event detection, Video surveillance.
%X This paper presents a method to detect unusual behavior in human crowds based on histograms of velocities in world coordinates. A combination of background removal and optical flow is used to extract the global motion at each image frame, discarding small motion vectors due artifacts such as noise, non-stationary background pixels and compression issues. Using a calibrated camera, the global motion can be estimated, and it is used to build a 2D histogram containing information of speed and direction for all frames. Each frame is compared with a set of previous frames by using a histogram comparison metric, resulting in a similarity vector. This vector is then used to determine changes in the crowd behavior, also allowing a classification based on the nature of the change in time: short or long-term changes. The method was tested on publicly available datasets involving crowded scenarios.
%@language en
%3 PID2848451.pdf