Title :
Fight detection based on Hidden Markov Model
Author :
Dejian Liu ; Jinyong Wu ; Yike Wang ; Jun Wang ; Zhuo Gong
Author_Institution :
R&D Dept., AnKe Smart City Technol.(PRC) Co., Ltd., Shenzhen, China
Abstract :
This paper presents a novel approach to detect human fights based on Hidden Markov Model (HMM). We present two HMM models to the problem. The first one is Fight Model, the second is Ordinary Model. According to the motion analysis between people in the scene, features for human behavior have been proposed. Given the observation value of features in time sequence, the probability can be evaluated by two Models. The larger value means that the Model is the suitable one to describe what happens in the scene. Experimental result demonstrats that the method is robust and efficient in detecting human fight behaviors.
Keywords :
cognition; feature extraction; hidden Markov models; natural scenes; object recognition; probability; HMM model; feature extraction; fight model; hidden Markov model; human fight behavior detection; motion analysis; natural scene; ordinary model; probability; time sequence; Computational modeling; Hidden Markov models; Histograms; Humans; Optical sensors; Surveillance; Video sequences;
Conference_Titel :
Advanced Computational Intelligence (ICACI), 2012 IEEE Fifth International Conference on
Conference_Location :
Nanjing
Print_ISBN :
978-1-4673-1743-6
DOI :
10.1109/ICACI.2012.6463248