Papers by Keyword: Hierarchical Dirichlet Process

Paper TitlePage

Authors: Wen Qiu Zhu, Qian Qian Li, Jun Feng Man, Xiang Bing Wen
Abstract: For effectively solving human behavior recognition in video surveillance, a novel behavior recognition model is presented. New behaviors may be produced in the process of human motion, hierarchical Dirichlet process is used to cluster monitored feature data of human body to decide whether unknown behaviors occur or not. The infinite hidden Markov model is used to learn unknown behavior patterns with supervised method, and then update the knowledge base. When knowledge base reaches a certain scale, the system can analyze human behaviors with unsupervised method. The Viterbi decoding algorithm of HMM is adopted to analyze current behavior of the human motion. The simulation experiments show that this method has unique advantage over others.
Authors: Jun Feng Man, Hai Yu Lin, Qian Qian Li, Xiang Bing Wen
Abstract: The occlusion problem in crowded people environment makes human segmentation and tracking more difficult in video surveillance. Thus, a human segmentation method combing human model with body edge curve is presented. Because segmentation may result in serious defect and distortion, robust BP neural network model is adopted as tracking mode. For improving autonomous learning ability of BP network, Hierarchical Dirichlet Process (HDP) is used to decide whether new types of human body characteristic data is generated, which provides decision basis for BP network learning. The simulation experiments confirm that the method presented in this paper can effectively solve the problem of partial human body occlusion. Meanwhile, this method has unique advantage of simplicity and real-time over others.
Showing 1 to 2 of 2 Paper Titles