Segmentation for robust tracking in the presence of severe occlusion
Segmentation for robust tracking in the presence of severe occlusion
复制标题
DOI：
10.1109/cvpr.2001.991001
复制
发表时间：
2001-12
影响因子：
10.6
通讯作者：
C. Gentile;O. Camps;M. Sznaier
中科院分区：
文献类型：
--
作者：
C. Gentile;O. Camps;M. Sznaier
跟踪图像序列中的对象可能会由于部分遮挡或混乱而失败。可以通过将对象作为一组“部分”来跟踪，使得不是所有这些部分都同时被遮挡，来增加对遮挡的鲁棒性。然而，这个想法的成功实施取决于找到一套合适的部件。在本文中，我们提出了一种新的分割，专门设计用于提高鲁棒性对遮挡跟踪的背景下。主要结果表明，跟踪的部分，从这种分割得到的跟踪部分通过传统的分割，跟踪整个目标。附加的结果包括部件的特征与跟踪误差之间的相关性的统计分析，以及识别表现出与跟踪误差的高度相关性的成本函数。
Tracking an object in a sequence of images can fail due to partial occlusion or clutter. Robustness to occlusion can be increased by tracking the object as a set of "parts" such that not all of these are occluded at the same time. However, successful implementation of this idea hinges upon finding a suitable set of parts. In this paper we propose a novel segmentation, specifically designed to improve robustness against occlusion in the context of tracking. The main result shows that tracking the parts resulting from this segmentation outperforms both tracking parts obtained through traditional segmentations, and tracking the entire target. Additional results include a statistical analysis of the correlation between features of a part and tracking error, and identifying a cost function that exhibits a high degree of correlation with the tracking error.