Title :
Human Segmentation in Infrared Videos Using Markov Random Field
Author :
Wenjia Yang ; Xiaodan Xie ; Zhi Chai ; Yapeng Li
Author_Institution :
Beijing Inst. of Environ. Features, Beijing, China
Abstract :
This paper presents a Bayesian approach for human segmentation in infrared video sequences. To overcome the limitations of background modeling in dealing with pixel-wise processing, our background model is combined with clustering cue in a maximum a posterior probability (MAP)-MRF framework. This can not only enable us to exploit the spatial and temporal coherence to maintain the continuity of our segmentation, but also takes the interdependence of feature and segmentation field into consideration. Experimental results for several infrared video sequences are provided to demonstrate the effectiveness of the proposed approach.
Keywords :
Markov processes; image segmentation; image sequences; infrared imaging; maximum likelihood estimation; probability; video signal processing; Bayesian approach; MAP-MRF framework; Markov random field; background modeling limitations; clustering cue; human segmentation; infrared video sequences; maximum a posterior probability; pixel-wise processing; segmentation field; spatial coherence; temporal coherence; Adaptation models; Bayes methods; Biological system modeling; Clustering algorithms; Image segmentation; Markov random fields; Video sequences; background modeling; clustering; human segmentation; markov random field;
Conference_Titel :
Green Computing and Communications (GreenCom), 2013 IEEE and Internet of Things (iThings/CPSCom), IEEE International Conference on and IEEE Cyber, Physical and Social Computing
Conference_Location :
Beijing
DOI :
10.1109/GreenCom-iThings-CPSCom.2013.369
