TY - JOUR
T1 - Correlation Filter Tracking via Distractor-aware Learning and Multi-Anchor Detection
AU - Chen, Guochun
AU - Pan, Gengzheng
AU - Zhou, Yongxin
AU - Kang, Wenxiong
AU - Hou, Junhui
AU - Deng, Feiqi
PY - 2020/12
Y1 - 2020/12
N2 - Correlation filter has demonstrated the power in object tracking, benefiting from its superior speed and competitive performance. However, existing correlation filter based trackers (CFTs) are fragile for some inherent defects caused by the boundary effect. To address this issue, we propose a novel correlation filter based tracking framework by integrating three highly collaborative components, including a fast target proposal module, a distractor-aware filter, and a correlation filter based refiner. Specifically, the target proposal aims at determining some target-like regions in contexts efficiently, which provides target-like patches to learn a distractor-aware filter and detect. Multi-region strategy enlarges space fields for learning and prediction. The filter learned from both target and distractors enhances its ability to identify background. Therefore, our method is capable of evaluating multiple candidates in wider context with less risk of drifting to distractors, namely multi-anchor detection. Besides, the proposed Proposal-Detect-Refine hierarchical searching process progressively achieves data alignment between testing and training samples, which benefits for reliable model prediction. A refiner is used to fine-tune positions after multi-anchor detection for lessening error accumulation and preventing model from drifting. Comprehensive experiments on five challenging datasets, i.e. OTB2013, OTB2015, VOT2017, VOT19, and TC128, demonstrate that the proposed method achieves superior performance against the state-of-the-art methods.
AB - Correlation filter has demonstrated the power in object tracking, benefiting from its superior speed and competitive performance. However, existing correlation filter based trackers (CFTs) are fragile for some inherent defects caused by the boundary effect. To address this issue, we propose a novel correlation filter based tracking framework by integrating three highly collaborative components, including a fast target proposal module, a distractor-aware filter, and a correlation filter based refiner. Specifically, the target proposal aims at determining some target-like regions in contexts efficiently, which provides target-like patches to learn a distractor-aware filter and detect. Multi-region strategy enlarges space fields for learning and prediction. The filter learned from both target and distractors enhances its ability to identify background. Therefore, our method is capable of evaluating multiple candidates in wider context with less risk of drifting to distractors, namely multi-anchor detection. Besides, the proposed Proposal-Detect-Refine hierarchical searching process progressively achieves data alignment between testing and training samples, which benefits for reliable model prediction. A refiner is used to fine-tune positions after multi-anchor detection for lessening error accumulation and preventing model from drifting. Comprehensive experiments on five challenging datasets, i.e. OTB2013, OTB2015, VOT2017, VOT19, and TC128, demonstrate that the proposed method achieves superior performance against the state-of-the-art methods.
KW - Correlation filter tracking
KW - online learning
KW - target proposal
UR - http://www.scopus.com/inward/record.url?scp=85077282619&partnerID=8YFLogxK
UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85077282619&origin=recordpage
U2 - 10.1109/TCSVT.2019.2961999
DO - 10.1109/TCSVT.2019.2961999
M3 - RGC 21 - Publication in refereed journal
SN - 1051-8215
VL - 30
SP - 4810
EP - 4822
JO - IEEE Transactions on Circuits and Systems for Video Technology
JF - IEEE Transactions on Circuits and Systems for Video Technology
IS - 12
ER -