DocumentCode :
595448
Title :
Incorporating contextual knowledge to Dynamic Bayesian Networks for event recognition
Author :
Xiaoyang Wang ; Qiang Ji
Author_Institution :
Dept. of ECSE, Rensselaer Polytech. Inst., Troy, NY, USA
fYear :
2012
fDate :
11-15 Nov. 2012
Firstpage :
3378
Lastpage :
3381
Abstract :
This paper proposes a new Probabilistic Graphical Model (PGM) to incorporate the scene, event object interaction and the event temporal contexts into Dynamic Bayesian Networks (DBNs) for event recognition in surveillance videos. We first construct the event DBNs for modeling the events from their own appearance and kinematic observations, and then extend the DBN to incorporate the contexts for boosting event recognition performance. Unlike the existing context methods, our model incorporates various contexts into one unified model. Experiments on natural scene surveillance videos show that the contexts can effectively improve the event recognition performance even with great challenges like large intra-class variations and low image resolution.
Keywords :
belief networks; object recognition; video signal processing; video surveillance; DBN; PGM; contextual knowledge; dynamic Bayesian networks; event object interaction; event recognition performance; event temporal contexts; kinematic observations; probabilistic graphical model; unified model; video surveillance; Context; Context modeling; Hidden Markov models; Legged locomotion; Surveillance; Vehicles; Videos;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Pattern Recognition (ICPR), 2012 21st International Conference on
Conference_Location :
Tsukuba
ISSN :
1051-4651
Print_ISBN :
978-1-4673-2216-4
Type :
conf
Filename :
6460889
Link To Document :
بازگشت