Automation of Pedestrian Tracking in a Crowded Situation

Studies on microscopic pedestrian requires large amounts of trajectory data from real-world pedestrian crowds. Such data collection, if done manually, needs tremendous effort and is very time consuming. Though many studies have asserted the possibility of automating this task using video cameras, we found that only a few have demonstrated good performance in very crowded situations or from a top-angled view scene. This paper deals with tracking pedestrian crowd under heavy occlusions from an angular scene.

[1]  Dmitry Chetverikov,et al.  Tracking feature points: a new algorithm , 1998, Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170).

[2]  Philip Kelly.  Pedestrian detection and tracking using stereo vision techniques , 2008 .

[3]  Yael Moses,et al.  Homography based multiple camera detection and tracking of people in a dense crowd , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Alan F. Smeaton,et al.  Robust pedestrian detection and tracking in crowded scenes , 2009, Image Vis. Comput..

[5]  Dmitry Chetverikov,et al.  Motion Tracking of Dense Feature Point Sets , 1997 .

[6]  Mubarak Shah,et al.  Automated Multi-Camera Surveillance: Algorithms and Practice , 2008, The International Series in Video Computing.

[7]  Azriel Rosenfeld,et al.  Tracking Groups of People , 2000, Comput. Vis. Image Underst..

[8]  Osama Masoud,et al.  Robust pedestrian tracking using a model-based approach , 1997, Proceedings of Conference on Intelligent Transportation Systems.