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

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 backgroun...