Abstract: This paper aimed to address the problem of modeling human behavior patterns captured in surveillance videos for the application of online normal behavior recognition and anomaly detection. From the perspective of cognitive psy- chology,a novel method was developed for automatic behavior modeling and online anomaly detection without the need for manual labeling of the training data set The work has been done with the hierarchical structure,following the rou- tine of "Video Representation-Semantic Behavior (Topic) Model-Behavior Classification":1) A compact and effective behavior representation method is developed based on spatial-temporal interest point detection. 2) The natural grouping of behavior patterns is determined through a novel clustering algorithm, topic hidden Markov model (THMM) built up- on the existing hidden Markov model ( HMM) and latent Dirichlet allocation (LDA) , which overcomes the current limi- tations in accuracy, robustness, and computational efficiency. I}he new model is a four-level hierarchical Bayesian model, in which each video is modeled as a Markov chain of behavior patterns where each behavior pattern is a distribution over some segments of the video. Each of these segments in the video can be modeled as a mixture of actions where each ac- lion is a distribution over spatial-temporal words. 3) An online anomaly measure is introduced to detect abnormal be- havior,whereas normal behavior is recognized by runtime accumulative visual evidence using likelihood ratio test (I_RT) method. Experimental results demonstrate the effectiveness and robustness of our approach using noisy and sparse data sets collected from a real surveillance scenario.

Key words: Computer vision, Topic model, Anomaly detection,13ag of motion word, l3chavior clustering