DocumentCode :
3408607
Title :
Tracking with local spatio-temporal motion patterns in extremely crowded scenes
Author :
Kratz, Louis ; Nishino, Ko
Author_Institution :
Dept. of Comput. Sci., Drexel Univ., Philadelphia, PA, USA
fYear :
2010
fDate :
13-18 June 2010
Firstpage :
693
Lastpage :
700
Abstract :
Tracking individuals in extremely crowded scenes is a challenging task, primarily due to the motion and appearance variability produced by the large number of people within the scene. The individual pedestrians, however, collectively form a crowd that exhibits a spatially and temporally structured pattern within the scene. In this paper, we extract this steady-state but dynamically evolving motion of the crowd and leverage it to track individuals in videos of the same scene. We capture the spatial and temporal variations in the crowd´s motion by training a collection of hidden Markov models on the motion patterns within the scene. Using these models, we predict the local spatio-temporal motion patterns that describe the pedestrian movement at each space-time location in the video. Based on these predictions, we hypothesize the target´s movement between frames as it travels through the local space-time volume. In addition, we robustly model the individual´s unique motion and appearance to discern them from surrounding pedestrians. The results show that we may track individuals in scenes that present extreme difficulty to previous techniques.
Keywords :
hidden Markov models; image motion analysis; video signal processing; extremely crowded scenes; hidden Markov models; individual pedestrians; local spatio-temporal motion patterns; pedestrian movement; space-time location; spatially structured pattern; temporally structured pattern; Cameras; Computer science; Hidden Markov models; Layout; Predictive models; Robustness; Steady-state; Surveillance; Target tracking; Videos;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on
Conference_Location :
San Francisco, CA
ISSN :
1063-6919
Print_ISBN :
978-1-4244-6984-0
Type :
conf
DOI :
10.1109/CVPR.2010.5540149
Filename :
5540149
Link To Document :
بازگشت