Automatic Object Tracking Using Edge Orientation Histogram Based CamShift

摘要：

The automatic objects tracking in videos plays important roles in computer vision applications. In this paper, we propose an automatic object tracking method hybrid with GMM and edge orientation histogram based CamShift. GMM is applied to detect objects motion. Different moving objects are separated by connected component analysis. And CamShift is processed by using edge orientation histogram to track objects. We demonstrate the effectiveness and efficiency of this approach by experimenting on several video sequences.

关键词： object tracking gaussian mixture model edge orientation histogram CamShift

作者: Yang YANG Zhiliang WANG Dehui SUN Mengmeng ZHANG Nannan CHENG

作者单位: School of Information Engineering,University of Science and Technology Beijing College of Informatio School of Information Engineering,University of Science and Technology Beijing College of Mechanical and Electrical Engineering,North China University of Technology Beijing City,P College of Information Engineering,North China University of Technology

会议类型: 国际会议

会议名称: Third International Conference on Information and Computing(第三届信息与计算科学国际会议 ICIC 2010)

会议地点: 无锡

会议语种:英文

页码: 231-234

在线出版日期: 2010-06-04（万方平台首次上网日期，不代表论文的发表时间）