A fast long-term visual tracking algorithm based on deep learning

被引：0
作者：
Hou, Zhiqiang [1 ,2 ]
Ma, Jingyuan [1 ,2 ]
Han, Ruoxue [1 ,2 ]
Ma, Sugang [1 ,2 ]
Yu, Wangsheng [3 ]
Fan, Jiulun [1 ]
机构：
[1] School of Computer Science and Technology, Xi’an University of Posts and Telecommunications, Xi’an
[2] Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing, Xi’an University of Posts and Telecommunications, Xi’an
[3] College of Information and Navigation, Air Force Engineering University, Xi’an
来源：
Beijing Hangkong Hangtian Daxue Xuebao/Journal of Beijing University of Aeronautics and Astronautics | 2024年 / 50卷 / 08期
基金：
中国国家自然科学基金;
关键词：
deep learning; global re-detection; long-term visual tracking; regional spatial attention; second-order channel attention;
D O I：
10.13700/j.bh.1001-5965.2022.0645
中图分类号：
学科分类号：
摘要：
Current deep learning-based visual tracking algorithms have difficulty tracking the target accurately in real-time in complex long-term monitoring environments including target size change, occlusion, and out-of-view. To solve this problem, a fast long-term visual tracking algorithm is proposed, which consists of a fast short-term tracking algorithm and a fast global re-detection module. First, as a short-term tracking algorithm, the attention module of second-order channel and region spatial fusion is added to the base algorithm SiamRPN. Then, in order to make the improved short-term tracking algorithm have a fast long-term tracking ability, the global re-detection module based on template matching proposed in this paper is added to the algorithm, which uses a lightweight network and fast similarity judgment method to speed up the re-detection rate. The proposed algorithm is tested on five datasets (OTB100, LaSOT, UAV20L, VOT2018-LT, and VOT2020-LT). With an average tracking speed of 104 frames per second, the experimental findings demonstrate the algorithm's outstanding long-term tracking performance. © 2024 Beijing University of Aeronautics and Astronautics (BUAA). All rights reserved.
引用
收藏
页码：2391 / 2403
页数：12
相关论文
共 55 条
  • [1] LI X, ZHA Y F, ZHANG T Z, Et al., Survey of visual object tracking algorithms based on deep learning, Journal of Image and Graphics, 24, 12, pp. 2057-2080, (2019)
  • [2] LIU F, SUN Y N, WANG H J, Et al., Adaptive UAV target tracking algorithm based on residual learning, Journal of Beijing University of Aeronautics and Astronautics, 46, 10, pp. 1874-1882, (2020)
  • [3] ZHANG C, MA H D, FU H Y., Object tracking in surveillance videos using spatial-temporal correlation graph model, Journal of Beijing University of Aeronautics and Astronautics, 41, 4, pp. 713-720, (2015)
  • [4] LUKEZIC A, ZAJC L C, VOJIR T, Et al., FuCoLoT–A fully-correlational long-term tracker, Proceedings of the Asian Conference on Computer Vision, pp. 595-611, (2018)
  • [5] WANG X, HOU Z Q, YU W S, Et al., Robust visual tracking based on deep sparse learning, Journal of Beijing University of Aeronautics and Astronautics, 43, 12, pp. 2554-2563, (2017)
  • [6] PU L, FENG X X, HOU Z Q, Et al., Siamese network visual tracking algorithm based on cascaded attention mechanism, Journal of Beijing University of Aeronautics and Astronautics, 46, 12, pp. 2302-2310, (2020)
  • [7] LI B, YAN J, WU W, Et al., High performance visual tracking with Siamese region proposal network, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8971-8980, (2018)
  • [8] LI B, WU W, WANG Q, Et al., SiamRPN++: Evolution of Siamese visual tracking with very deep networks, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4277-4286, (2019)
  • [9] DANELLJAN M, BHAT G, KHAN F S, Et al., ATOM: Accurate tracking by overlap maximization, Proceedings of the IEEE/ CVF Conference on Computer Vision and Pattern Recognition, pp. 4655-4664, (2019)
  • [10] CHENG S Y, ZHONG B N, LI G R, Et al., Learning to filter: Siamese relation network for robust tracking, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4419-4429, (2021)
123456