Survey of Holistic Crowd Analysis Models

The behavior analysis techniques used in computer vision, are mostly targeting individual's behavior. The study on crowd analysis is more focused on counting individuals and devising a management plan for load balancing for vehicles and pedestrians. The recent advancements in vision based techniques have allowed the study of collective behavior of the crowd for valuable information. It targets the application areas where crowds are dense making it impossible to segment individuals separately due to severe occlusion. Since object detection and identification techniques only works in low density crowds, therefore, holistic crowd analysis techniques are considered for this study. Holistic approach does not attempt to separate out the crowd and rather consider it as a single entity. It studies the behavior of the crowd, instead of the individual's behavior. Recently available techniques for holistic crowd analysis are considered for this study. The working of these techniques is described and a comparative analysis is given to highlight their strengths and weaknesses.

[1]  Helbing,et al.  Social force model for pedestrian dynamics. , 1995, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[2]  J. Ferryman,et al.  PETS2009: Dataset and challenge , 2009, 2009 Twelfth IEEE International Workshop on Performance Evaluation of Tracking and Surveillance.

[3]  Sergio A. Velastin,et al.  Crowd analysis: a survey , 2008, Machine Vision and Applications.

[4]  Mubarak Shah,et al.  Abnormal crowd behavior detection using social force model , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Zhiwen Yu,et al.  A Bayesian Model for Crowd Escape Behavior Detection , 2014, IEEE Transactions on Circuits and Systems for Video Technology.

[6]  Xinyu Wu,et al.  Abnormal crowd behavior detection based on the energy model , 2011, 2011 IEEE International Conference on Information and Automation.

[7]  Shuang Wu,et al.  Abnormal crowd behavior detection based on local pressure model , 2012, Proceedings of The 2012 Asia Pacific Signal and Information Processing Association Annual Summit and Conference.

[8]  Yangsheng Xu,et al.  Crowd Energy and Feature Analysis , 2007, 2007 IEEE International Conference on Integration Technology.

[9]  Zhimin Zhang,et al.  Abnormal Crowd Behavior Detection Using Topological Methods , 2011, 2011 12th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing.

[10]  Serge P. Hoogendoorn,et al.  Capacity of doors during evacuation conditions , 2010 .

[11]  Mubarak Shah,et al.  A Lagrangian Particle Dynamics Approach for Crowd Flow Segmentation and Stability Analysis , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[12]  Soraia Raupp Musse,et al.  Crowd Analysis Using Computer Vision Techniques , 2010, IEEE Signal Processing Magazine.

[13]  Christian Bauckhage,et al.  Analyzing pedestrian behavior in crowds for automatic detection of congestions , 2011, 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops).

[14]  Ying Liu,et al.  Crowd density estimation based on image potential energy model , 2011, 2011 IEEE International Conference on Robotics and Biomimetics.

[15]  Sergio A. Velastin,et al.  Motion-based machine vision techniques for the management of large crowds , 1999, ICECS'99. Proceedings of ICECS '99. 6th IEEE International Conference on Electronics, Circuits and Systems (Cat. No.99EX357).