Graph mode-based contextual kernels for robust SVM tracking | |
Li, Xi ; Dick, Anthony ; Wang, Hanzi ; Shen, Chunh ; Van Den Hengel, Anton ; Wang HZ(王菡子) | |
2011 | |
关键词 | Image processing |
英文摘要 | Conference Name:2011 IEEE International Conference on Computer Vision, ICCV 2011. Conference Address: Barcelona, Spain. Time:November 6, 2011 - November 13, 2011.; TOYOTA; Google; Microsoft Research; SIEMENS; technicolor; Visual tracking has been typically solved as a binary classification problem. Most existing trackers only consider the pairwise interactions between samples, and thereby ignore the higher-order contextual interactions, which may lead to the sensitivity to complicated factors such as noises, outliers, background clutters and so on. In this paper, we propose a visual tracker based on support vector machines (SVMs), for which a novel graph mode-based contextual kernel is designed to effectively capture the higher-order contextual information from samples. To do so, we first create a visual graph whose similarity matrix is determined by a baseline visual kernel. Second, a set of high-order contexts are discovered in the visual graph. The problem of discovering these high-order contexts is solved by seeking modes of the visual graph. Each graph mode corresponds to a vertex community termed as a high-order context. Third, we construct a contextual kernel that effectively captures the interaction information between the high-order contexts. Finally, this contextual kernel is embedded into SVMs for robust tracking. Experimental results on challenging videos demonstrate the effectiveness and robustness of the proposed tracker. ? 2011 IEEE. |
语种 | 英语 |
出处 | http://dx.doi.org/10.1109/ICCV.2011.6126364 |
出版者 | Institute of Electrical and Electronics Engineers Inc. |
内容类型 | 其他 |
源URL | [http://dspace.xmu.edu.cn/handle/2288/87080] ![]() |
专题 | 信息技术-会议论文 |
推荐引用方式 GB/T 7714 | Li, Xi,Dick, Anthony,Wang, Hanzi,et al. Graph mode-based contextual kernels for robust SVM tracking. 2011-01-01. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论