9 January 2017 Accurate mask-based spatially regularized correlation filter for visual tracking
Author Affiliations +
Abstract
Recently, discriminative correlation filter (DCF)-based trackers have achieved extremely successful results in many competitions and benchmarks. These methods utilize a periodic assumption of the training samples to efficiently learn a classifier. However, this assumption will produce unwanted boundary effects, which severely degrade the tracking performance. Correlation filters with limited boundaries and spatially regularized DCFs were proposed to reduce boundary effects. However, their methods used the fixed mask or predesigned weights function, respectively, which was unsuitable for large appearance variation. We propose an accurate mask-based spatially regularized correlation filter for visual tracking. Our augmented objective can reduce the boundary effect even in large appearance variation. In our algorithm, the masking matrix is converted into the regularized function that acts on the correlation filter in frequency domain, which makes the algorithm fast convergence. Our online tracking algorithm performs favorably against state-of-the-art trackers on OTB-2015 Benchmark in terms of efficiency, accuracy, and robustness.
© 2017 SPIE and IS&T
Xiaodong Gu, Xiaodong Gu, Xinping Xu, Xinping Xu, } "Accurate mask-based spatially regularized correlation filter for visual tracking," Journal of Electronic Imaging 26(1), 013002 (9 January 2017). https://doi.org/10.1117/1.JEI.26.1.013002 . Submission: Received: 2 August 2016; Accepted: 13 December 2016
Received: 2 August 2016; Accepted: 13 December 2016; Published: 9 January 2017
JOURNAL ARTICLE
6 PAGES


SHARE
Back to Top