Robust Object Tracking via Information Theoretic Measures | |
Wang, Weining; Li, Qi; Wang, Liang | |
发表期刊 | International Journal of Automation and Computing |
2020 | |
期号 | 17页码:1 |
摘要 | Object tracking is a very important topic in the field of computer vision. Many sophisticated appearance models have been proposed. Among them, the trackers based on holistic appearance information provide a compact notion of the tracked object and thus are robust to appearance variations under a small amount of noise. However, in practice, the tracked objects are often corrupted by complex noises (e.g., partial occlusions, illumination variations) so that the original appearance-based trackers become less effective. This paper presents a correntropy-based robust holistic tracking algorithm to deal with various noises. Then, a half-quadratic algorithm is carefully employed to minimize the correntropy-based objective function. Based on the proposed information theoretic algorithm, we design a simple and effective template update scheme for object tracking. Experimental results on publicly available videos demonstrate that the proposed tracker outperforms other popular tracking algorithms. |
关键词 | Object tracking, information theoretic measures, correntropy, template update, robust to complex noises |
收录类别 | EI |
语种 | 英语 |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/40312 |
专题 | 模式识别实验室 |
作者单位 | 中国科学院自动化研究所 |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Wang, Weining,Li, Qi,Wang, Liang. Robust Object Tracking via Information Theoretic Measures[J]. International Journal of Automation and Computing,2020(17):1. |
APA | Wang, Weining,Li, Qi,&Wang, Liang.(2020).Robust Object Tracking via Information Theoretic Measures.International Journal of Automation and Computing(17),1. |
MLA | Wang, Weining,et al."Robust Object Tracking via Information Theoretic Measures".International Journal of Automation and Computing .17(2020):1. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
IJAC2020.pdf(9045KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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