DocumentCode :
3004973
Title :
Trajectory parsing by cluster sampling in spatio-temporal graph
Author :
Xiaobai Liu ; Liang Lin ; Song-Chun Zhu ; Hai Jin
Author_Institution :
SCTS&CGCL, HUST, Wuhan, China
fYear :
2009
fDate :
20-25 June 2009
Firstpage :
739
Lastpage :
746
Abstract :
The objective of this paper is to parse object trajectories in surveillance video against occlusion, interruption, and background clutter. We present a spatio-temporal graph (ST-Graph) representation and a cluster sampling algorithm via deferred inference. An object trajectory in the ST-Graph is represented by a bundle of “motion primitives”, each of which consists of a small number of matched features (interesting patches) generated by adaptive feature pursuit and a tracking process. Each motion primitive is a graph vertex and has six bonds connecting to neighboring vertices. Based on the ST-Graph, we jointly solve three tasks: 1) spatial segmentation; 2) temporal correspondence and 3) object recognition, by flipping the labels of the motion primitives. We also adapt the scene geometric and statistical information as strong prior. Then the inference computation is formulated in a Markov chain and solved by an efficient cluster sampling. We apply the proposed approach to various challenging videos from a number of public datasets and show it outperform other state of the art methods.
Keywords :
Markov processes; graph theory; image segmentation; video surveillance; Markov chain; cluster sampling; graph vertex; motion primitive; object recognition; scene geometric information; spatial segmentation; spatio-temporal graph; statistical information; surveillance video; temporal correspondence; trajectory parsing; Context modeling; Inference algorithms; Joining processes; Layout; Object recognition; Sampling methods; Stochastic processes; Surveillance; Tracking; Trajectory;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on
Conference_Location :
Miami, FL
ISSN :
1063-6919
Print_ISBN :
978-1-4244-3992-8
Type :
conf
DOI :
10.1109/CVPR.2009.5206688
Filename :
5206688
Link To Document :
بازگشت