Human Behavior Analysis Using Multiple 2D Features and Multicategory Support Vector Machine.
Hao-Cheng Mo, Jin-Jang Leou, Cheng-Shian Lin · 2009
In this study, a human behavior analysis system using multiple 2D (two-dimensional) features and a multicategory support vector machine is proposed. In the proposed system, three kinds of features, namely, human star skeleton, angles of six sticks in the star skeleton, and object motion vectors, are employed to train the human posture classifier and recognize human postures. Based on the recognized human postures, a backward search strategy is proposed to recognize human actions. Based on the experimental results obtained in this study, in terms of recall and precision rates, the proposed system has good performance and is superior to the comparison system. 1.