DocumentCode :
727071
Title :
A novel visual object tracking algorithm using multiple spatial context models and Bayesian Kalman filter
Author :
Wei, X.G. ; Shuai Zhang ; Chan, S.C.
Author_Institution :
Dept. Electr. & Electron. Eng., Univ. of Hong Kong, Hong Kong, China
fYear :
2015
fDate :
24-27 May 2015
Firstpage :
1034
Lastpage :
1037
Abstract :
Appearance modelling and tracking strategy are two fundamental problems in visual object tracking. In this paper, the appearance of the object is modeled by a spatial context based bag of multiple models (BMM). The BMM keeps multiple hypotheses and utilizes spatial information to perform tracking. Furthermore, a novel Bayesian Kalman filter is used as the tracking strategy to handle fast movement and acceleration of the tracked object. Experimental results show that our method can successfully handle complex scenarios with complicated background, long-term occlusion and fast movement.
Keywords :
Bayes methods; Kalman filters; computer vision; object tracking; BMM; Bayesian Kalman filter; appearance modelling strategy; appearance tracking strategy; computer vision; multiple spatial context models; spatial context based bag-of-multiple models; spatial information utilization; visual object tracking algorithm; Context; Context modeling; Kalman filters; Object tracking; Target tracking; Visualization; Bayesian Kalman filter; object tracking; spatio context model;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Circuits and Systems (ISCAS), 2015 IEEE International Symposium on
Conference_Location :
Lisbon
Type :
conf
DOI :
10.1109/ISCAS.2015.7168813
Filename :
7168813
Link To Document :
بازگشت