Title | An adaptive template matching-based single object tracking algorithm with parallel acceleration |
Authors | Yan, Baicheng Xiao, Limin Zhang, Hang Xu, Daliang Ruan, Li Wang, Zhaokai Zhang, Yiyang |
Affiliation | Beihang Univ, Sch Comp Sci & Engn, XueYuan Rd 37, Beijing 100191, Peoples R China Sci & Technol Complex Syst Control & Intelligent, Beijing, Peoples R China Peking Univ, Sch Elect Engn & Comp Sci, 5 Yiheyuan Rd, Beijing 10087, Peoples R China |
Keywords | Visual object tracking Adaptive template update Parallel acceleration Deep learning Embedded platform |
Issue Date | 2019 |
Publisher | JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION |
Abstract | Existing template matching based visual object tracking algorithms usually require to manually update the template and have high execution cost on general embedded systems. To address these issues, an adaptive template matching-based single object tracking algorithm with parallel acceleration is proposed in this paper. In this algorithm, we propose an adaptive single object tracking algorithm framework to achieve template update online. Based on the Faster-RCNN model, we design a single object capture method to update the template. Meanwhile, we present a parallel strategy to accelerate the process of template matching. To evaluate the proposed algorithm, we use OTB benchmark to compare the performance with several state-of-the-art trackers on TX2 embedded platform. Experimental results show that the proposed method achieves a 5.9 times execution speed and 71.9% accuracy improvement over the comparison methods. (C) 2019 Published by Elsevier Inc. |
URI | http://hdl.handle.net/20.500.11897/553468 |
ISSN | 1047-3203 |
DOI | 10.1016/j.jvcir.2019.102603 |
Indexed | SCI(E) EI |
Appears in Collections: | 信息科学技术学院 |