Abstract | ||
---|---|---|
People naturally escape from a place when unexpected events happen. Based on this observation, efficient detection of crowd escape behavior in surveillance videos is a promising way to perform timely detection of anomalous situations. In this paper, we propose a Bayesian framework for escape detection by directly modeling crowd motion in both the presence and absence of escape events. Specifically, we introduce the concepts of potential destinations and divergent centers to characterize crowd motion in the above two cases respectively, and construct the corresponding class-conditional probability density functions of optical flow. Escape detection is finally performed based on the proposed Bayesian framework. Although only data associated with nonescape behavior are included in the training set, the density functions associated with the case of escape can also be adaptively updated using observed data. In addition, the identified divergent centers indicate possible locations at which the unexpected events occur. The performance of our proposed method is validated in a number of experiments on crowd escape detection in various scenarios. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/TCSVT.2013.2276151 | IEEE Transactions on Circuits and Systems for Video Technology |
Keywords | Field | DocType |
belief networks,escape events,data association,bayesian framework,crowd detection,divergent centers,crowd escape behavior detection,bayesian model,markov chain monte carlo,escape detection,escape,image sequences,crowd motion,object detection,surveillance videos,timely detection,optical flow,class-conditional probability density functions,divergent motion pattern,sensor fusion,probability,video surveillance | Object detection,Computer vision,Bayesian inference,Markov chain Monte Carlo,Computer science,Sensor fusion,Artificial intelligence,Unexpected events,Probability density function,Optical flow,Machine learning,Bayesian probability | Journal |
Volume | Issue | ISSN |
24 | 1 | 1051-8215 |
Citations | PageRank | References |
29 | 0.81 | 27 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Si Wu | 1 | 148 | 16.73 |
Hau-San Wong | 2 | 1008 | 86.89 |
Zhiwen Yu | 3 | 231 | 18.51 |