Robust Scale Adaptive and Real-Time Visual Tracking with Correlation Filters

Jiatian PI  Keli HU  Yuzhang GU  Lei QU  Fengrong LI  Xiaolin ZHANG  Yunlong ZHAN  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E99-D   No.7   pp.1895-1902
Publication Date: 2016/07/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2015EDP7459
Type of Manuscript: PAPER
Category: Image Recognition, Computer Vision
Keyword: 
correlation filters,  kernel methods,  scale estimation,  visual tracking,  

Full Text: PDF(2MB)>>
Buy this Article




Summary: 
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.