Motion Detection Based on Temporal Difference Method and Optical Flow field

摘要：

A motion detection method based on temporal difference and optical flow field is proposed in this paper. Firstly, an absolute differential image is calculated from two consecutive gray images. The absolute differential image is filtered by low-pass filter and translation into binary image. Edge of moving object is indexed from row-coordinate and column-coordinate. Secondly, optical flow field is calculated from image sequences by Hrons algorithm. Thirdly, moving object area is found out by indexed edge and optical flow field above. Experimental results show that this method is suitable and effective.

关键词： Computer vision Motion detection Temporal difference method Optical flow field

作者: WEI Shuigen CHEN Zhen DONG Hua

作者单位: Lab of Computer Vision, School of Automation Nanchang Hangkong University Nanchang, Jiangxi, China, Key Laboratory of Nondestructive Test Ministry of Education Nanchang Hangkong University Nanchang, J

会议类型: 国际会议

会议名称: Second International Symposium on Electronic Commerce and Security(第二届电子商务与安全国际研究大会)(ISECS 2009)

会议地点: 南昌

会议语种:英文

页码: 741-744

在线出版日期: 2009-05-22（万方平台首次上网日期，不代表论文的发表时间）