首页 > 论文 > 激光与光电子学进展 > 57卷 > 22期(pp:221507--1)

目标跟踪中基于光流映射的模板更新算法

Template-Updating Algorithm Based on Optical Flow Mapping in Object Tracking

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

基于深层孪生网络的目标跟踪算法普遍缺乏目标模板在线更新方法,从而在某些复杂应用场景中适应能力较差。针对这一问题,提出一种基于光流映射的目标模板在线更新算法,该算法能够在保证实时性的前提下有效提高对复杂场景的适应能力。首先在跟踪过程中计算模板帧之间的光流信息;其次由光流映射和残差计算获取目标的运动变化信息。除此以外,还提出一种基于奇异值分解的由初始帧生成的修正项以修正目标位置偏差的方法。在OTB100和VOT2016数据集上对所提算法进行测试评估,结果显示,所提算法可以较好地优化新生成的目标模板,增强算法的鲁棒性,且与现有的跟踪算法相比,所提算法结果更佳。

Abstract

The tracking algorithm based on deep-level siamese network generally lacks the capability to update the target template online; hence, it exhibits poor adaptability in some complex application environments. Aiming to resolve this problem, a target template online-updating algorithm based on optical flow mapping is proposed herein. On the premise of ensuring real-time operation, the proposed algorithm can efficiently improve its adaptability in complex circumstances. First, the optical-flow information between the template frames is calculated in the tracking process. Then, the information of motion change is generated via optical flow mapping and residual calculation. Furthermore, based on singular value decomposition, a method that creates a correction term via the initial frame, which modifies the target-position deviation, is proposed herein. Finally, the proposed algorithm is tested on OTB100 and VOT2016 datasets. The results show that the proposed algorithm can optimize the new target template to enhance the robustness and can achieve the best results compared with existing tracking algorithms.

广告组1 - 空间光调制器+DMD
补充资料

中图分类号:TP391.4

DOI:10.3788/LOP57.221507

所属栏目:机器视觉

基金项目:国家自然科学基金、 天津大学自主创新基金;

收稿日期:2020-03-06

修改稿日期:2020-04-30

网络出版日期:2020-11-01

作者单位    点击查看

张静:天津大学电气自动化与信息工程学院, 天津 300072
郝志晖:天津大学电气自动化与信息工程学院, 天津 300072
刘婧:天津大学电气自动化与信息工程学院, 天津 300072

联系人作者:刘婧(jliu_tju@tju.edu.cn)

备注:国家自然科学基金、 天津大学自主创新基金;

【1】Chen Y F, Wu Y, Zhang W. Survey of target tracking algorithm based on siamese network structure [J]. Computer Engineering and Applications. 2020, 56(6): 10-18.
陈云芳, 吴懿, 张伟. 基于孪生网络结构的目标跟踪算法综述 [J]. 计算机工程与应用. 2020, 56(6): 10-18.
Chen Y F, Wu Y, Zhang W. Survey of target tracking algorithm based on siamese network structure [J]. Computer Engineering and Applications. 2020, 56(6): 10-18.
陈云芳, 吴懿, 张伟. 基于孪生网络结构的目标跟踪算法综述 [J]. 计算机工程与应用. 2020, 56(6): 10-18.

【2】Yilmaz A, Javed O, Shah M. Object tracking: a survey [J]. ACM Computing Surveys. 2006, 38(4): 13-58.

【3】Danelljan M, Robinson A, Shahbaz Khan F, et al. Beyond correlation filters: learning continuous convolution operators for visual tracking [M]. //Leibe B, Matas J, Sebe N, et al. Computer vision—ECCV 2016. Lecture notes in computer science. Cham: Springer. 2016, 9909: 472-488.

【4】Danelljan M, Bhat G, Khan F S, et al. ECO: efficient convolution operators for tracking . [C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 21-26, 2017, Honolulu, HI, USA. New York: IEEE. 2017, 6931-6939.

【5】Meng L, Li C X. Kernel correlation filtering algorithm based on a dual-feature model Journal of Image and Graphics[J]. 0, 2019(12): 2183-2199.
孟琭, 李诚新. 双特征模型核相关滤波目标跟踪算法 中国图象图形学报[J]. 0, 2019(12): 2183-2199.

【6】Danelljan M, H?ger G, Khan F S, et al. Learning spatially regularized correlation filters for visual tracking . [C]//2015 IEEE International Conference on Computer Vision (ICCV), December 7-13, 2015, Santiago, Chile. New York: IEEE. 2015, 4310-4318.

【7】Wang D W, Xu C X, Liu Y. Kernelized correlation filter for target tracking with multi-feature fusion [J]. Computer Engineering and Design. 2019, 40(12): 3463-3468.
王殿伟, 许春香, 刘颖. 基于多特征融合的核相关滤波目标跟踪算法 [J]. 计算机工程与设计. 2019, 40(12): 3463-3468.
Wang D W, Xu C X, Liu Y. Kernelized correlation filter for target tracking with multi-feature fusion [J]. Computer Engineering and Design. 2019, 40(12): 3463-3468.
王殿伟, 许春香, 刘颖. 基于多特征融合的核相关滤波目标跟踪算法 [J]. 计算机工程与设计. 2019, 40(12): 3463-3468.

【8】Danelljan M, H?ger G, Khan F S, et al. Adaptive decontamination of the training set: a unified formulation for discriminative visual tracking . [C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 27-30, 2016, Las Vegas, NV, USA. New York: IEEE. 2016, 1430-1438.

【9】Galoogahi H K, Fagg A, Lucey S. Learning background-aware correlation filters for visual tracking . [C]//2017 IEEE International Conference on Computer Vision (ICCV), October 22-29, 2017, Venice, Italy. New York: IEEE. 2017, 1144-1152.

【10】Wang K Y, Chen Z G, Fu Y. Target anti-occlusion algorithm based on correlation filter [J]. Laser & Optoelectronics Progress. 2019, 56(3): 030401.
王凯宇, 陈志国, 傅毅. 基于相关滤波器的目标抗遮挡算法 [J]. 激光与光电子学进展. 2019, 56(3): 030401.

【11】Yang Y G, Shang Z H. Object Tracking Algorithm Based on Correlation Filtering and Convolution Residuals Learning [J]. Laser & Optoelectronics Progress. 2020, 57(12): 121012.
杨亚光, 尚振宏. 相关滤波融合卷积残差学习的目标跟踪算法 [J]. 激光与光电子学进展. 2020, 57(12): 121012.

【12】Cheng Y, Li J Z, Zhu L N, et al. Correlation filter tracking algorithm based on model and scale updating [J]. Laser & Optoelectronics Progress. 2018, 55(12): 121015.
成悦, 李建增, 褚丽娜, 等. 基于模型与尺度更新的相关滤波跟踪算法 [J]. 激光与光电子学进展. 2018, 55(12): 121015.

【13】Yu Y Y, Shi Z L, Liu Y P. Foreground-aware based spatiotemporal correlation filter tracking algorithm [J]. Laser & Optoelectronics Progress. 2019, 56(22): 221503.
虞跃洋, 史泽林, 刘云鹏. 基于前景感知的时空相关滤波跟踪算法 [J]. 激光与光电子学进展. 2019, 56(22): 221503.

【14】Li J P, Shang Z H, Liu H. Visual object tracking algorithm based on correlation filters with hierarchical convolutional features [J]. Computer Science. 2019, 46(7): 252-257.
李健鹏, 尚振宏, 刘辉. 融合多层卷积特征的相关滤波运动目标跟踪算法 [J]. 计算机科学. 2019, 46(7): 252-257.

【15】Wang M M, Liu Y, Huang Z Y. Large margin object tracking with circulant feature maps . [C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 21-26, 2017, Honolulu, HI, USA. New York: IEEE. 2017, 4800-4808.

【16】Danelljan M, Bhat G, Khan F S, et al. ATOM: accurate tracking by overlap maximization . [C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 15-20, 2019, Long Beach, CA, USA. New York: IEEE. 2019, 4655-4664.

【17】Bertinetto L, Valmadre J, Henriques J F, et al. Fully-convolutional siamese networks for object tracking [M]. //Hua G, Jégou H. Computer vision-ECCV 2016 workshops. Lecture notes in computer science. Cham: Springer. 2016, 9914: 850-865.

【18】Ren J M, Gong N S, Han Z Y. Improved target tracking algorithm based on siamese convolution neural network [J]. Journal of Chinese Computer Systems. 2019, 40(12): 2686-2690.
任珈民, 宫宁生, 韩镇阳. 一种改进的基于孪生卷积神经网络的目标跟踪算法 [J]. 小型微型计算机系统. 2019, 40(12): 2686-2690.

【19】Li B, Wu W, Wang Q, et al. SiamRPN++: evolution of Siamese visual tracking with very deep networks . [C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 15-20, 2019, Long Beach, CA, USA. New York: IEEE. 2019, 4277-4286.

【20】Zhou D Y, Duan X P. Target tracking method based on siamese network and attention mechanism Information & Communications[J]. 0, 2019(12): 61-63.
周迪雅, 段喜萍. 基于孪生网络与注意力机制的目标跟踪方法 信息通信[J]. 0, 2019(12): 61-63.

【21】Ilg E, Mayer N, Saikia T, et al. FlowNet 2.0: evolution of optical flow estimation with deep networks . [C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 21-26, 2017, Honolulu, HI, USA. New York: IEEE. 2017, 1647-1655.

【22】Yang T, Chan A B. Learning dynamic memory networks for object tracking [M]. //Ferrari V, Hebert M, Sminchisescu C, et al. Computer vision—ECCV 2018. Lecture notes in computer science. Cham: Springer. 2018, 11213: 153-169.

【23】Paszke A, Gross S, Massa F, high-performance deep learning library[EB/OL], et al. -12-03)[2020-03-05] . 2019, org/abs/1912: 01703.Paszke A, Gross S, Massa F, high-performance deep learning library[EB/OL], et al. -12-03)[2020-03-05] . 2019, org/abs/1912: 01703.

【24】Bertinetto L, Valmadre J, Golodetz S, et al. Staple: complementary learners for real-time tracking . [C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 27-30, 2016, Las Vegas, NV, USA. New York: IEEE. 2016, 1401-1409.

【25】Zhang Z P, Peng H W. Deeper and wider Siamese networks for real-time visual tracking . [C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 15-20, 2019, Long Beach, CA, USA. New York: IEEE. 2019, 4586-4595.

【26】Li X, Ma C, Wu B Y, et al. Target-aware deep tracking . [C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 15-20, 2019, Long Beach, CA, USA. New York: IEEE. 2019, 1369-1378.

【27】Fan H, Ling H B. Siamese cascaded region proposal networks for real-time visual tracking . [C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 15-20, 2019, Long Beach, CA, USA. New York: IEEE. 2019, 7944-7953.

【28】Wang G T, Luo C, Xiong Z W, et al. SPM-tracker: series-parallel matching for real-time visual object tracking . [C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 15-20, 2019, Long Beach, CA, USA. New York: IEEE. 2019, 3638-3647.

引用该论文

Zhang Jing,Hao Zhihui,Liu Jing. Template-Updating Algorithm Based on Optical Flow Mapping in Object Tracking[J]. Laser & Optoelectronics Progress, 2020, 57(22): 221507

张静,郝志晖,刘婧. 目标跟踪中基于光流映射的模板更新算法[J]. 激光与光电子学进展, 2020, 57(22): 221507

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF