A Human Action Recognition Method Based on Tchebichef Moment Invariants and Temporal Templates

摘要：

In this paper, a new human action recognition method based on Tchebichef moment invariants and temporal templates is presented. We use the motion energy image (MEI) and motion history image (MHI) as the feature representation of the human action at first. Then the Tchebichef moment invariants extract the feature vectors of MEI and MHI. Tchebichef moment invariants perform better than Hu moment invariants and Zernike moment invariants. Finally cluster the actions and use the nearest neighbor algorithm to recognize each human action. The result of these experiments suggests that this method has a high recognition rate in in both noise-free and noisy condition. Therefore, the algorithm has a good robustness.

关键词： human action recognition Tchebichef moment invariants cluster MEI MHI

作者: Yanan Lu Yakang Li Yang Shen Fang Ding Xiaofeng Wang

作者单位: State key lab of software engineering Computer School of Wuhan University Wuhan, China Jicheng Hu and Songtao Ding State key lab of software engineering Computer School of Wuhan Universit

会议类型: 国际会议

会议名称: 2012 4th International Conference on Intelligent Human-Machine Systems and Cybernetics 第4届智能人机系统与控制论国际会议 IHMSC 2012

会议地点: 南昌

会议语种:英文

页码: 436-439

在线出版日期: 2012-08-26（万方平台首次上网日期，不代表论文的发表时间）