The Motion detection of Video Using Active Surface and Particle Swarm Optimation

摘要：

The segmentation of an image sequence into moving objects and estimation of object motion belong to one of the most important tasks in image sequence analysis. In this paper, the new motion detection methods of video based on active surface and particle swarm optimization is presented. Firstly, each frame of image sequence is separated into 2-D regions of motion activity by differentiating one frame from the other they produce, and motion detection problem is simplified into an interactive estimation of segmentation surface. Then image sequence analysis jointly over multiple frames is proposed with the improved motion model and parameter with particle swarm optimization. Finally, The effectiveness of proposal method is proved with simulation experiment. The results show that our proposal detected the boundary with enough accuracy.

关键词： Active Contour Particle Swarm Optimization, Motion Detection, Video Segmentation

作者: Ruiping Xu Huifang Li Qiong Wen

作者单位: School of Electronics and Information Northwestern Polytechnical University Xi an, China School of Electronics and Information Northwestern Polytechnical University Xi an,China

会议类型: 国际会议

会议名称: 2010 International Conference on Signal and Information Processing(2010年IEEE信号与信息处理国际会议 ICSIP2010)

会议地点: 长沙

会议语种:英文

页码: 708-711

在线出版日期: 2010-12-14（万方平台首次上网日期，不代表论文的发表时间）