Human motion correction and representation method from motion camera

The Journal of Engineering

Tsung-Chih Hsiao²  Miaohui Zhang³  Hong-Bo Zhang⁴  Ying Lin⁵  Feng Guo⁵ 

[1] Department of Computer Science and Technology, Huaqiao University, Xiamen, People'Institute of Energy, Jiangxi Academy of Sciences, Jiangxi Province, People'School of Information Science and Engineering, Xiamen University, Xiamen, People'Xiamen Key Laboratory of Computer Vision and Pattern Recognition, Huaqiao University, Xiamen, People's Republic of China

关键词: motion objection detection;    computer vision;    motion feature descriptor;    motion descriptors;    optical flow;    motion camera;    motion estimation;    intelligent robot;    human motion representation;    human-computer interaction;    human motion correction;    motion difference histogram;   

DOI  :  10.1049/joe.2017.0159

学科分类：工程和技术（综合）

来源: IET

【 摘 要 】

Motion estimation is a basic issue for many computer vision tasks, such as human–computer interaction, motion objection detection and intelligent robot. In many practical scenes, the object movement goes with camera motion. Generally, motion descriptors directly based on optical flow are inaccurate and have low discrimination power. To this end, a novel motion correction method is proposed and a novel motion feature descriptor called the motion difference histogram (MDH) for recognising human action is proposed in this study. Motion estimation results are corrected by background motion estimation and MDH encodes the motion difference between the background and the objects. Experimental results on video shot with camera motion show that the proposed motion correction method is effective and the recognition accuracy of MDH is better than that of the state-of-the-art motion descriptor.

【 授权许可】

CC BY