文献类型：期刊文献

英文题名：Robust Scale Adaptive and Real-Time Visual Tracking with Correlation Filters

作者：Pi, Jiatian[1];Hu, Keli[2];Gu, Yuzhang[1];Qu, Lei[1];Li, Fengrong[1];Zhang, Xiaolin[1];Zhan, Yunlong[1]

机构：[1]SIMIT, Shanghai 200050, Peoples R China;[2]Shaoxing Univ, Shaoxing 312000, Peoples R China

年份：2016

卷号：E99D

期号：7

起止页码：1895

外文期刊名：IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS

收录：SCI-EXPANDED(收录号：WOS:000381562700016)、、EI(收录号：20162802572287)、Scopus(收录号：2-s2.0-84976904108)、WOS

基金：This work is partially sponsored by Shanghai Sailing Program (15YF1414500) and Public Welfare Technology Research Project in Zhejiang Province (2016C31082).

语种：英文

外文关键词：correlation filters; kernel methods; scale estimation; visual tracking

外文摘要：Visual tracking has been studied for several decades but continues to draw significant attention because of its critical role in many applications. Recent years have seen greater interest in the use of correlation filters in visual tracking systems, owing to their extremely compelling results in different competitions and benchmarks. However, there is still a need to improve the overall tracking capability to counter various tracking issues, including large scale variation, occlusion, and deformation. This paper presents an appealing tracker with robust scale estimation, which can handle the problem of fixed template size in Kernelized Correlation Filter (KCF) tracker with no significant decrease in the speed. We apply the discriminative correlation filter for scale estimation as an independent part after finding the optimal translation based on the KCF tracker. Compared to an exhaustive scale space search scheme, our approach provides improved performance while being computationally efficient. In order to reveal the effectiveness of our approach, we use benchmark sequences annotated with 11 attributes to evaluate how well the tracker handles different attributes. Numerous experiments demonstrate that the proposed algorithm performs favorably against several state-of-the-art algorithms. Appealing results both in accuracy and robustness are also achieved on all 51 benchmark sequences, which proves the efficiency of our tracker.