HECOL: Homography and epipolar-based consistent labeling for outdoor park surveillance
Computer Vision and Image Understanding
Machine Vision and Applications
Toward a sentient environment: real-time wide area multiple human tracking with identities
Machine Vision and Applications
Detecting motion patterns via direction maps with application to surveillance
Computer Vision and Image Understanding
Group interaction analysis in dynamic context
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics - Special issue on human computing
Abnormal crowd motion analysis
ROBIO'09 Proceedings of the 2009 international conference on Robotics and biomimetics
Understanding transit scenes: a survey on human behavior-recognition algorithms
IEEE Transactions on Intelligent Transportation Systems
Human activity analysis: A review
ACM Computing Surveys (CSUR)
Stochastic Representation and Recognition of High-Level Group Activities
International Journal of Computer Vision
| Hi-index | 0.00 |
We propose in this paper an approach for recognizinggroup of people behaviors using multiple cameras withoverlapping FOVs (Field Of View). In this context, Behaviorrecognition first relies on low level motion detection andframe to frame tracking which generate a graph of mobileobjects for each camera. Second, to take advantage of allcameras observing the same scene, a combination mechanismis performed to combine the graphs computed for eachcamera into a global one. This global graph is then used forlong term tracking of groups of people evolving in the scene.Finally, the result of the group tracking is used by a higherlevel module which recognizes predefined scenarios correspondingto specific group behaviors. This article focuseson the graphs combination mechanism and on the recognitionof group behaviors. At the end, results on these twoalgorithms are described.