VISUAL ANALYSIS OF CROWDED PEDESTRIAN SCENES

The tracking of individuals in cluttered scenes has been of much interest in Machine Vision research for more than a decade. A number of algorithms have been devised to track individuals and some of the algorithms have attempted the tracking of large groups of people. In this paper we discuss how to generate automatic maps of trends of movement in complex scenes, without the use of tracking. In the proposed approach a probability density function (PDF) for the occurrence and the local orientation is generated for a scene, using a conventional foreground detection algorithm. Then, connected components and main paths are identified by exploring the two PDFs. The performance of the algorithm is then evaluated estimating errors for new instances of pedestrian patterns in the scene.

[1]  W. Eric L. Grimson,et al.  Adaptive background mixture models for real-time tracking , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[2]  Tim J. Ellis,et al.  Learning semantic scene models from observing activity in visual surveillance , 2005, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[3]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[4]  Milan Sonka,et al.  Image Processing, Analysis and Machine Vision , 1993, Springer US.

[5]  Dirk Helbing,et al.  Simulating dynamical features of escape panic , 2000, Nature.

[6]  Lubos Buzna,et al.  Self-Organized Pedestrian Crowd Dynamics: Experiments, Simulations, and Design Solutions , 2005, Transp. Sci..

[7]  George Kollios,et al.  Extraction and clustering of motion trajectories in video , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[8]  W. Eric L. Grimson,et al.  Learning Patterns of Activity Using Real-Time Tracking , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Daniel Thalmann,et al.  Hierarchical Model for Real Time Simulation of Virtual Human Crowds , 2001, IEEE Trans. Vis. Comput. Graph..