Scale Adaptation of Mean Shift Based on Graph Cuts Theory

摘要：

The classical Mean Shift can’t change the scale of tracking window in real time while tracking target is changing in size. This paper adopts graph cuts theory to the problem of scale adaptation for Mean Shift tracking. According to the result of Mean Shift iteration in every frame, implementing graph cuts using skin color Gaussian mixture model(GMM) in a small area around it, and updating tracking window size through the largest skin lump among the result of graph cuts. Experimental results clearly demonstrate that the method can reflect the real scale change of tracking target, avoid the interference of other objects in background, and has good usability and robustness. Besides it enriches manipulation method of Human Computer Interaction by controlling entertainment games.

关键词： Graph Cuts Mean Shift Scale-Adaptive Tracking

作者: ZhaoLing AN Guocheng Zhang Fengjun Wang Hongan Dai Guozhong

作者单位: Intelligence Engineering Lab,Institute of Software Chinese Academy of Sciences, 100190.China Intelligence Engineering Lab,Institute of Software Chinese Academy of Sciences,100190.China

会议类型: 国际会议

会议名称: 2011国际计算机辅助设计与图形学学术会议(CAD/Graphics 2011)

会议地点: 济南

会议语种:英文

页码: 1-4

在线出版日期: 2011-09-15（万方平台首次上网日期，不代表论文的发表时间）