Visual tracking via weakly supervised learning from multiple imperfect oracles

PATTERN RECOGNITION

卷:47

Article

Zhong, Bineng^1,6  Yao, Hongxun²  Chen, Sheng³  Ji, Rongrong⁴  Chin, Tat-Jun⁵  Wang, Hanzi⁶ 

[1] Huaqiao Univ, Dept Comp Sci & Engn, Fujian, Peoples R China

[2] Harbin Inst Technol, Dept Comp Sci & Engn, Harbin, Peoples R China

[3] Oregon State Univ, Corvallis, OR 97331 USA

[4] Columbia Univ, Dept Elect Engn, New York, NY 10027 USA

[5] Univ Adelaide, Sch Comp Sci, Adelaide, SA 5005, Australia

[6] Xiamen Univ, Sch Informat Sci & Technol, Xiamen 361005, Peoples R China

关键词: Visual tracking;    Weakly supervised learning;    Information fusion;    Online learning;    Adaptive appearance model;    Drift problem;    Online evaluation;   

DOI  :  10.1016/j.patcog.2013.10.002

来源: Elsevier

【 摘 要 】

Notwithstanding many years of progress, visual tracking is still a difficult but important problem. Since most top-performing tracking methods have their strengths and weaknesses and are suited for handling only a certain type of variation, one of the next challenges is to integrate all these methods and address the problem of long-term persistent tracking in ever-changing environments. Towards this goal, we consider visual tracking in a novel weakly supervised learning scenario where (possibly noisy) labels but no ground truth are provided by multiple imperfect oracles (i.e., different trackers). These trackers naturally have intrinsic diversity due to their different design strategies, and we propose a probabilistic method to simultaneously infer the most likely object position by considering the outputs of all trackers, and estimate the accuracy of each tracker. An online evaluation strategy of trackers and a heuristic training data selection scheme are adopted to make the inference more effective and efficient. Consequently, the proposed method can avoid the pitfalls of purely single tracking methods and get reliably labeled samples to incrementally update each tracker (if it is an appearance-adaptive tracker) to capture the appearance changes. Extensive experiments on challenging video sequences demonstrate the robustness and effectiveness of the proposed method. Crown Copyright (C) 2013 Published by Elsevier Ltd. All rights reserved.

【 授权许可】

Free