Visual object tracking via online sparse instance learning |
| |
| Institution: | 1. Department of Electrical Engineering, School of Electronic Information, Wuhan University, Wuhan 430072, Hubei, PR China;2. School of International Software, Wuhan University, Wuhan 430072, Hubei, PR China;1. School of Computer Science and Technology, Harbin Institute of Technology, 150080 Harbin, China;2. Department of CSIE, National Dong Hwa University, Hualien 974, Taiwan;1. Key Laboratory of Virtual Geographic Environment, Ministry of Education, Nanjing Normal University, 1# WenYuan Road, Nanjing, Jiangsu 210023, PR China;2. Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application, 1# WenYuan Road, Nanjing, Jiangsu 210023, PR China;3. Key Laboratory of Police Geographic Information Technology, Ministry of Public Security, Nanjing Normal University, 1# WenYuan Road, Nanjing, Jiangsu 210023, PR China;1. Beijing Key Laboratory of Digital Media, School of Computer Science and Engineering, Beihang University, Beijing 100191, China;2. State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing 100191, China;1. School of Computer Engineering, Nanyang Technological University, 639798, Singapore;2. School of Information Technology, Jiangxi University of Finance and Economics, Nanchang 330032, Jiangxi, China |
| |
| Abstract: | Sparse representation has been attracting much more attention in visual tracking. However most sparse representation based trackers only focus on how to model the target appearance and do not consider the learning of sparse representation when the training samples are imprecise, and hence may drift or fail in the challenging scene. In this paper, we present a novel online tracking algorithm. The tracker integrates the online multiple instance learning into the recent sparse representation scheme. For tracking, the integrated sparse representation combining texture, intensity and local spatial information is proposed to model the target. This representation takes both occlusion and appearance change into account. Then, an efficient online learning approach is proposed to select the most distinguishable features to separate the target from the background samples. In addition, the sparse representation is dynamically updated online with respect to the current context. Both qualitative and quantitative evaluations on challenging benchmark video sequences demonstrate that the proposed tracking algorithm performs favorably against several state-of-the-art methods. |
| |
| Keywords: | Visual tracking Multiple instance learning Integrated sparse representation Tracking by detection Random projection Online learning Appearance variation Occlusion |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
