Learning spatially regularized similarity for robust visual tracking

Xiuzhuang Zhou

doi:10.1016/j.imavis.2016.11.016

2017-04-01

PRE

尚媛园 (Yuanyuan Shang) *

徐敏 (Min Xu)

丁

丁辉 (Hui Ding)

DOI：10.1016/j.imavis.2016.11.016

原文链接

原文求助

摘要

En 中文

Matching visual appearances of the target object over consecutive frames is a critical step in visual tracking. The accuracy performance of a practical tracking system highly depends on the similarity metric used for visual matching. Recent attempts to integrate discriminative metric learned by sequential visual data (instead of a predefined metric) in visual tracking have demonstrated more robust and accurate results. However, a global similarity metric is often suboptimal for visual matching when the target object experiences large appearance variation or occlusion. To address this issue, we propose in this paper a spatially weighted similarity fusion (SWSF) method for robust visual tracking. In our SWSF, a part-based model is employed as the object representation, and the local similarity metric and spatially regularized weights are jointly learned in a coherent process, such that the total matching accuracy between visual target and candidates can be effectively enhanced. Empirically, we evaluate our proposed tracker on various challenging sequences against several state-of-the-art methods, and the results demonstrate that our method can achieve competitive or better tracking performance in various challenging tracking scenarios. (C) 2016 Elsevier B.V. All rights reserved.

Keyword:

Visual tracking

Part-based representation

Metric learning

Local similarity

Spatially regularized