Human tracking and silhouette extraction for human-robot interaction systems

作     者：Ahn, Jung-Ho Choi, Cheolmin Kwak, Sooyeong Kim, Kilcheon Byun, Hyeran 

作者机构：Yonsei Univ Dept Comp Sci Seoul 120749 South Korea Kangnam Univ Div Comp & Media Engn Yongin South Korea Access Seoul Co Ltd Docviewer Grp Seoul South Korea 

出 版 物：《PATTERN ANALYSIS AND APPLICATIONS》 (模式分析与应用)

年 卷 期：2009年第12卷第2期

页      面：167-177页

核心收录：

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：MIC (Ministry of Information and Communication), Korea, ITRC (Information Technology Research Center) [IITA-2007-(C1090-0701-0046] KOSEF(Korea Science and Engineering Foundation) [R01-2007-000-11683-0] 

主　　题：Robot vision Human detection Tracking Silhouette extraction 

摘      要：In this study, we propose a new integrated computer vision system designed to track multiple human beings and extract their silhouette with a pan-tilt stereo camera, so that it can assist in gesture and gait recognition in the field of Human-Robot Interaction (HRI). The proposed system consists of three modules: detection, tracking and silhouette extraction. These modules are robust to camera movements, and they work interactively in near real-time. Detection was performed by camera ego-motion compensation and disparity segmentation. For tracking, we present an efficient mean shift-based tracking method in which the tracking objects are characterized as disparity weighted color histograms. The silhouette was obtained by two-step segmentation. A trimap was estimated in advance and then effectively incorporated into the graph-cut framework for fine segmentation. The proposed system was evaluated with respect to ground truth data, and it was shown to detect and track multiple people very well and also produce high-quality silhouettes.