期刊
PATTERN RECOGNITION
卷 102, 期 -, 页码 -出版社
ELSEVIER SCI LTD
DOI: 10.1016/j.patcog.2019.107172
关键词
Visual object tracking; Discriminative correlation filters; Accelerated optimisation; Alternating direction method of multipliers
资金
- U.S. ARL
- U.S. Army Research Office
- U.K. MoD
- U.K. Engineering and Physical Sciences Research Council (EPSRC) [EP/R013616/1]
- EPSRC Programme Grant (FACER2VM) [EP/N007743/1]
- National Natural Science Foundation of China [61672265, U1836218, 61876072, 61902153]
- 111 Project of Ministry of Education of China [B12018]
Recent visual object tracking methods have witnessed a continuous improvement in the state-of-the-art with the development of efficient discriminative correlation filters (DCF) and robust deep neural network features. Despite the outstanding performance achieved by the above combination, existing advanced trackers suffer from the burden of high computational complexity of the deep feature extraction and online model learning. We propose an accelerated ADMM optimisation method obtained by adding a momentum to the optimisation sequence iterates, and by relaxing the impact of the error between DCF parameters and their norm. The proposed optimisation method is applied to an innovative formulation of the DCF design, which seeks the most discriminative spatially regularised feature channels. A further speed up is achieved by an adaptive initialisation of the filter optimisation process. The significantly increased convergence of the DCF filter is demonstrated by establishing the optimisation process equivalence with a continuous dynamical system for which the convergence properties can readily be derived. The experimental results obtained on several well-known benchmarking datasets demonstrate the efficiency and robustness of the proposed ACFT method, with a tracking accuracy comparable to the start-of-the-art trackers. (C) 2020 Elsevier Ltd. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据