Adaptive Region Proposal With Channel Regularization for Robust Object Tracking

• Published in: IEEE transactions on circuits and systems for video technology Vol. 31; no. 4; pp. 1268 - 1282
• Main Authors: Lu, Xiankai, Ma, Chao, Ni, Bingbing, Yang, Xiaokang
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.04.2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adaptive region proposals; Algorithms; channel regularization; Correlation; correlation filters; Estimation; Feature extraction; Object tracking; Occlusion; Proposals; Redundancy; Regularization; robust object tracking; Robustness (mathematics); Target detection; Target tracking; Tracking; Visualization
• ISSN: 1051-8215; 1558-2205
• DOI: 10.1109/TCSVT.2019.2944654

In this paper, we propose an adaptive region proposal scheme with feature channel regularization to facilitate robust object tracking. We consider tracking as a linear regression problem and an ensemble of correlation filters is trained on-line to distinguish the foreground target from the background. Further, we integrate adaptively learned region proposals into an enhanced two-stream tracking framework based on correlation filters. For the tracking stream, we learn two-stage cascade correlation filters on deep convolutional features to ensure competitive tracking performance. For the detection stream, we employ adaptive region proposals, which are effective in recovering target objects from tracking failures caused by heavy occlusion or out-of-view movement. In contrast to traditional tracking-by-detection methods using random samples or sliding windows, we perform target re-detection over adaptively learned region proposals. Since region proposals naturally take the objectness information into account, we show that the proposed adaptive region proposals can handle the challenging scale estimation problem as well. In addition, we observe the channel redundancy and noisy of feature representation, especially for the convolutional features. Thus, we apply a channel regularization to the correlation filter learning. Extensive experimental validations on OTB, VOT and UAV-123 datasets demonstrate that the proposed method performs favorably against state-of-the-art tracking algorithms.