Occlusion‐handling tracker based on discriminative correlation filters. Issue 13 (5th October 2020)

• Record Type: Journal Article
• Authors: Xie, Yue; Zhang, Hanling; Li, Lijun
• Is Part Of: IET image processing. Volume 14:Issue 13(2020)
• Page Start: 3054
• Page End: 3065
• Publication Date: 2020-10-05
• Subjects: image colour analysis -- image matching -- object detection -- object tracking -- filtering theory; computational efficiency -- DCF‐based methods -- model contamination -- model degradation -- Discriminative Correlation Filters framework -- online visual object tracking -- spatial–temporal regularized correlation filters -- partial occlusion -- complete occlusion -- block‐based methods -- Occlusion‐Handling Tracker -- VOT‐2016 datasets -- VOT‐2018 datasets; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2019.0651
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : Visual object tracking (VOT) based on discriminative correlation filters (DCF) has received great attention due to its higher computational efficiency and better robustness. However, DCF‐based methods suffer from the problem of model contamination. The tracker will drift into the background due to the uncertainties brought by shifting among peaks, which will further lead to the issues of model degradation. To deal with occlusions, a novel Occlusion‐Handling Tracker Based on Discriminative Correlation Filters (OHDCF) framework is proposed for online visual object tracking, where an occlusion‐handling strategy is integrated into the spatial–temporal regularized correlation filters (STRCF). The occlusion‐handling tracker follows a hybrid approach to handle partial occlusion and complete occlusion. Specifically, we first present a function to determine whether occlusion occurs. Then, the proposed filter uses block‐based and feature‐matching methods to determine whether an object is partially occluded or completely occluded. Following this, we use different methods to track the target. Extensive experiments have performed on OTB‐100, Temple‐Color‐128, VOT‐2016 and VOT‐2018 datasets, the results show that OHDCF achieves promising performance compared to other state‐of‐the‐art trackers. On VOT‐2018, OHDCF significantly outperforms STRCF from the challenge with a relative gain of 4.8 % in EAO and a gain of 4.6 % in Accuracy.