Gait Classification Based on Fuzzy Associative Memory
Gait classification is one of the hottest but most difficult subjects in computer vision. The paper describes a method for classifying the gaits of human bodies in video sequence and deals with classification of human gait types based on the notion that different gait types are actually different types of postures. Moment is independent on the location and the size of the silhouette, and hence a robust descriptor for gait classification. Silhouettes are extracted using the Background Subtraction. And according to the different sorts of movements, a set of standard image contours are made. Different behavior vectors based on spatio-temporal are acquired through Hidden Markov Models (HMM). A distance method is presented in order to get the similarity degree of silhouettes. We estimate this by comparing the incoming silhouettes to a database of silhouettes. Fuzzy Associative Memory (FAM) classifier is proposed to infer gait classification of a walker. Finally an evaluation of ten kinds of gaits involving walk, stand, faint, sit, run, bench, jump, crouch, wander and punch car are given high recognition rate achieved.
Gait Classification FAM HMM Moment Invariants Centroid
Jun Zhang Zhijing Liu Hong Zhou
School of Computer Science and Technology Xidian University No.2 South Taibai Road, Xian, 710071, Shannxi Province, CHINA
国际会议
2008 Sino-European Workshop on Intelligent Robots and Systems(SEIROS08)(第一届中欧智能系统及机器人国际学术研讨会)
重庆
英文
1-7
2008-12-11（万方平台首次上网日期，不代表论文的发表时间）