A Method of Moving Object Tracking Based on Background Subtraction and Color Feature

摘要：

　　Background subtraction method is a tracking method only based on motion information.It cannot make a distinction between the foreground objects detected.The feature-based tracking methods need to select the appropriate prediction and search algorithm.But the algorithm complexity and amount of computation is large for the multi-target tracking.Therefore,this paper presents the method based on the combination of background subtraction and color feature.For improving the weak points of the traditional background subtraction method based on grayscale image,it is proposed to use the background subtraction based on RGB color difference.It improves the integrity of the foreground regions that makes better effect of the color feature matching.The experimental results show that in the multi-target tracking applications,the proposed method is simple and easy to implement.It can be used to track the targets with specific color feature and has high robustness.

关键词： background extraction background subtraction color histogram feature matching

作者: Liu Chun-yang Hou Dao-zheng Liu Chang-an

作者单位: School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, C School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, C

会议类型: 国际会议

会议名称: 2nd International Conference on Polymer Composities and Polymer Testing (2013第二届高分子复合材料与高分子测试国际会议暨先进工业技术与方案国际会议)(ISPCPT2013)

会议地点: 太原

会议语种:英文

页码: 488-491

在线出版日期: 2013-03-22（万方平台首次上网日期，不代表论文的发表时间）