Online Appearance Model Learning and Generation for Adaptive Visual Tracking
Online Appearance Model Learning and Generation for Adaptive Visual Tracking
复制标题
自适应视觉跟踪的在线外观模型学习和生成
DOI：
10.1109/tcsvt.2011.2105598
复制
发表时间：
2011-02
影响因子：
8.4
通讯作者：
Qiao, Hong
中科院分区：
文献类型：
--
作者：
Wang, Peng;Qiao, Hong
近年来，人们提出了几种自适应视觉跟踪算法来捕捉目标的变化外观。然而，适应性也可能导致逐渐漂移的问题，特别是当目标外观急剧变化时。本文给出了目标模型在线学习的一些理论原理，并在此基础上提出了一种新的自适应跟踪算法，该算法能有效地科普目标外形的剧烈变化，并能抵抗渐进漂移。一旦目标在每帧中被定位，从目标观测采样的补丁首先被分类为前景和背景使用一个有效的分类器。然后通过吸收和剔除两个过程在线提取自适应的、纯的、时间连续的目标模型，只将可靠的、可分性高的特征吸收到新的目标模型中，而将可能导致背景模式混杂的“危险”特征剔除。为了尽量减少背景的影响，保持目标模型的时间连续性，设计了主导模型和连续模型两种协作模型。提出的目标模型的学习和生成机制，最后嵌入到一个自适应跟踪系统。实验结果表明，该算法在具有挑战性的条件下的鲁棒性能。
Several adaptive visual tracking algorithms have been recently proposed to capture the varying appearance of target. However, adaptability may also result in the problem of gradual drift, especially when the target appearance changes drastically. This paper gives some theoretical principles for online learning of target model, and then presents a novel adaptive tracking algorithm which is able to effectively cope with drastic variations in target appearance and resist gradual drift. Once target is localized in each frame, the patches sampled from target observation are first classified into foreground and background using an effective classifier. Then the adaptive, pure and time-continuous target model is extracted online through two processes: absorption process and rejection process, through which only the reliable features with high separability are absorbed in the new target model, while the “dangerous” features which may cause interfusion of background patterns are rejected. To minimize the influence of background and keep the temporal continuity of target model, two collaborative models dominant model and continuous model are designed. The proposed learning and generation mechanisms of target model are finally embedded in an adaptive tracking system. Experimental results demonstrate the robust performance of the proposed algorithm under challenging conditions.
登录
查看更多内容
DOI：
10.1109/cvpr.2005.242
发表时间：
2005-06
影响因子：
23.6
作者：
Zhimin Fan;Ying Wu;Ming Yang
通讯作者：
Zhimin Fan;Ying Wu;Ming Yang
影响因子：
10.6
作者：
Junqiu Wang;Y. Yagi
通讯作者：
Junqiu Wang;Y. Yagi
DOI：
10.1016/s0031-3203(00)00072-8
发表时间：
2001-06
期刊：
Pattern Recognit.
影响因子：
--
作者：
K. Shearer;K. D. Wong;S. Venkatesh
通讯作者：
K. Shearer;K. D. Wong;S. Venkatesh
DOI：
10.1109/cvpr.2004.267
发表时间：
2004-07
期刊：
Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004.
影响因子：
--
作者：
J. Ho;Kuang-chih Lee;Ming-Hsuan Yang;D. Kriegman
通讯作者：
J. Ho;Kuang-chih Lee;Ming-Hsuan Yang;D. Kriegman
影响因子：
10.6
作者：
C. Gentile;O. Camps;M. Sznaier
通讯作者：
C. Gentile;O. Camps;M. Sznaier