An optimized target tracing algorithm for intelligent robot

摘要：

In this paper we study on target tracing system for intelligent robot and propose an optimized algorithm to track the objects such as human body, which needs to detect the moving targets from the background in image sequence, and trace them by controlling theory and image processing. In the first stage, we detect the changing regions and background area through GMM (Gaussian Mixture Model)1. Based on the results of the first stage, we adopt Kalman filter algorithm united with Mean-Shift to keep track of the moving targets. At last, the experimental results show that our method is robust and efficient, it has theoretical significance and practical value.

关键词： track moveing targets GMM,Kalman filter MeanShift

作者: Wei Benjie Zhang Xiaokun Li Shan Teng Xuejian

作者单位: Center for Space Science and Applied Research Chinese Academy of Sciences,Brijing 100190,China Department of Computer Science,Beijing Electronic Science & Technology Institute,Beijing 100070,Chin

会议类型: 国际会议

会议名称: 2010 International Conference on Digital Manufacturing and Automation(2010 数字制造与自动化国际会议 ICDMA 2010)

会议地点: 长沙

会议语种:英文

页码: 214-218

在线出版日期: 2010-12-18（万方平台首次上网日期，不代表论文的发表时间）