Deep Correlation Tracking with Backtracking

Yulong XU  Yang LI  Jiabao WANG  Zhuang MIAO  Hang LI  Yafei ZHANG  Gang TAO  

IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E100-A   No.7   pp.1601-1605
Publication Date: 2017/07/01
Online ISSN: 1745-1337
DOI: 10.1587/transfun.E100.A.1601
Type of Manuscript: LETTER
Category: Vision
visual tracking,  object backtracking,  correlation filter,  convolutional feature,  

Full Text: PDF>>
Buy this Article

Feature extractor is an important component of a tracker and the convolutional neural networks (CNNs) have demonstrated excellent performance in visual tracking. However, the CNN features cannot perform well under conditions of low illumination. To address this issue, we propose a novel deep correlation tracker with backtracking, which consists of target translation, backtracking and scale estimation. We employ four correlation filters, one with a histogram of oriented gradient (HOG) descriptor and the other three with the CNN features to estimate the translation. In particular, we propose a backtracking algorithm to reconfirm the translation location. Comprehensive experiments are performed on a large-scale challenging benchmark dataset. And the results show that the proposed algorithm outperforms state-of-the-art methods in accuracy and robustness.