Manifold Background-Aware Correlation Filter Target Tracking

doi:10.3778/j.issn.1673-9418.2111023

Abstract

Abstract: In order to solve the problem that target is easy to lose in complex scenes such as similar background, occlusion, fast motion and motion blur, a new manifold background-aware correlation filter tracking algorithm is proposed. Firstly, the object tracking region is selected to extract the appearance features of target to establish object model. Then, taking target location as the origin, the manifold search area is constructed by using double expo-nential distribution. According to the target motion speed and direction, the manifold search range and search angle are dynamically adjusted. The background in the manifold search area is extracted, and the filter template is obtained by training the background information and the target feature model. Finally, the filter template is used to determine the target position and track the target. According to the speed and direction of the target motion, the manifold background-aware algorithm proposed adopts dynamic search mechanism to search, which covers the prob-ability space range of the target random motion. It can effectively search targets in complex scenarios, control calculation quantity, and improve the accuracy and speed of the target tracking algorithm. A great quantity of experiments are carried out on the standard dataset OTB100. Experimental results indicate that the proposed algorithm has good performance in accuracy, real time and robustness for target tracking under complex conditions such as similar background, occlusion, fast motion and motion blur in comparison with other mainstream algorithms.

Key words: target tracking, correlation filter, manifold search, alternating direction method of multipliers (ADMM)

摘要： 针对相关滤波跟踪算法在相似背景、遮挡、快速运动、运动模糊等复杂场景下目标易丢失的问题，提出一种新的基于流形背景感知的相关滤波目标跟踪方法。首先，选取目标区域，提取目标的外观特征，建立目标模型；然后，以目标所在位置为原点，采用双指数分布构建流形搜索区域，并根据目标的运动速度和运动方向动态调整流形搜索区域的搜索范围和搜索角度，提取流形搜索区域内的背景信息，将背景信息与目标特征模型进行滤波器训练，得到滤波器模板；最后，以滤波器模板来确定目标位置，进行目标跟踪。提出的流形背景感知算法，根据目标运动的速度和方向，采用动态搜索机制进行搜索，涵盖了目标随机运动的大概率空间范围，在复杂场景下能够有效搜索目标，并控制了计算量，提升了目标跟踪算法的精度和速度。该方法在标准数据集OTB100上进行了大量的实验，实验结果表明，相较于其他主流算法，该算法对相似背景、遮挡、快速运动、运动模糊等复杂条件下的目标跟踪具有很好的准确率、实时性和鲁棒性。

YUAN Heng, ZHAO Xiaoyi. Manifold Background-Aware Correlation Filter Target Tracking[J]. Journal of Frontiers of Computer Science and Technology, 2023, 17(6): 1373-1386.

袁姮, 赵肖祎. 流形背景感知的相关滤波目标跟踪[J]. 计算机科学与探索, 2023, 17(6): 1373-1386.

References

[1] 姜文涛, 涂潮, 刘万军. 背景与方向感知的相关滤波跟踪[J]. 中国图象图形学报, 2021, 26(3): 527-541.
JIANG W T, TU C, LIU W J. Background and direction-aware correlation filter tracking[J]. Journal of Image and Graphics, 2021, 26(3): 527-541.
[2] 茅正冲, 陈海东. 自适应尺度的上下文感知相关滤波跟踪算法[J]. 计算机工程与应用, 2021, 57(3): 168-174.
MAO Z C, CHEN H D. Adaptive scale context-aware corre-lation filter tracking algorithm[J]. Computer Engineering and Applications, 2021, 57(3): 168-174.
[3] 王蓓, 陈金广, 王明明. 复杂场景下的改进核相关滤波跟踪算法[J]. 计算机工程与应用, 2021,?57(2):?198-208.
WANG B, CHEN J G, WANG M M. Improved target tracking algorithm based on kernelized correlation filter in complex scenarios[J]. Computer Engineering and Applic-ations, 2021, 57(2): 198-208.
[4] 何冉,?陈自力,?刘建军, 等.?自适应上下文感知相关滤波目标跟踪[J].?电光与控制,?2019,?26(5): 59-63.
HE R, CHEN Z L, LIU J J, et al. Correlation filter target tracking with adaptive context sensing[J]. Electronics Optics & Control,?2019,?26(5): 59-63.
[5] 卢湖川, 李佩霞, 王栋. 目标跟踪算法综述[J]. 模式识别与人工智能, 2018, 31(1): 61-76.
LU H C, LI P X, WANG D. Visual object tracking: a survey[J]. Pattern Recognition and Artificial Intelligence, 2018, 31(1): 61-76.
[6] 孟琭, 杨旭. 目标跟踪算法综述[J]. 自动化学报, 2019, 45(7): 1244-1260.
MENG L,YANG X. Visual object tracking: a survey[J]. Acta Automatica Sinica, 2019, 45(7): 1244-1260.
[7] 李娜, 吴玲风, 李大湘. 基于相关滤波的长期跟踪算法[J]. 模式识别与人工智能, 2018, 31(10): 899-908.
LI N, WU L F, LI D X. Long-term tracking algorithm based on correlation filter[J]. Pattern Recognition and Artificial Intelligence, 2018, 31(10): 899-908.
[8] 甘林海, 王刚, 刘进忙, 等. 群目标跟踪技术综述[J]. 自动化学报, 2020, 46(3): 411-426.
GAN L H, WANG G, LIU J M, et al. An overview of group target tracking[J]. Acta Automatica Sinica, 2020, 46(3): 411-426.
[9] 李聪, 鹿存跃, 赵珣, 等. 特征融合的尺度自适应相关滤波跟踪算法[J]. 光学学报, 2018, 38(5): 177-184.
LI C, LU C Y, ZHAO X, et al. Scale adaptive correlation filtering tracing algorithm based on feature fusion[J]. Acta Optica Sinica, 2018, 38(5): 177-184.
[10] 刘波, 许廷发, 李相民, 等. 自适应上下文感知相关滤波跟踪[J]. 中国光学, 2019, 12(2): 265-273.
LIU B, XU T F, LI X M, et al. Adaptive context-aware correlation filter tracking[J]. Chinese Journal of Optics, 2019, 12(2): 265-273.
[11] BOLME D S, BEVERIDGE J R, DRAPER B A, et al. Visual object tracking using adaptive correlation filters[C]//Proceedings of the 23rd IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, Jun 13-18, 2010. Washington: IEEE Computer Society, 2010: 2544-2550.
[12] HENRIQUES J F, CASEIRO R, MARTINS P, et al. Exp-loiting the circulant structure of tracking-by-detection with kernels[C]//LNCS 7575: Proceedings of the 12th European Conference on Computer Vision, Florence, Oct 7-13, 2012. Berlin, Heidelberg: Springer, 2012: 702-715.
[13] HENRIQUES J F, CASEIRO R, MARTINS P, et al. High-speed tracking with kernelized correlation filter[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(3): 583-596.
[14] DANELLJAN M, H?GER G, KHAN F S, et al. Learning spatially regularized correlation filters for visual tracking[C]//Proceedings of the 2015 IEEE International Confere-nce on Computer Vision, Santiago, Dec 7-13, 2015. Wash-ington: IEEE Computer Society, 2015: 4310-4318.
[15] GALOOGAHI H K, FAGG A, LUCEY S. Learning back-ground-aware correlation filters for visual tracking[C]//Pro-ceedings of the 2017 IEEE International Conference on Computer Vision, Venice, Oct 22-29, 2017. Washington: IEEE Computer Society, 2017: 1144-1152.
[16] LI F, TIAN C, ZUO W M, et al. Learning spatial-temporal regularized correlation filters for visual tracking[C]//Pro-ceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, Jun 18-22, 2018. Washington: IEEE Computer Society, 2018: 4904-4913.
[17] DAI K N, WANG D, LU H C, et al. Visual tracking via adaptive spatially-regularized correlation filters[C]//Procee-dings of the 2019 IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, Jun 16-20, 2019. Piscataway: IEEE, 2019: 4670-4679.
[18] 晋宏营, 刘美云. 伽尔顿板实验小球分布的研究[J]. 物理与工程, 2012, 22(6): 31-34.
JIN H Y, LIU M Y. Study on balls distribution in Galton board experiment[J]. Physics and Engineering, 2012, 22(6): 31-34.
[19] 彭芳麟. 伽尔顿板实验的计算机模拟[J]. 大学物理, 2005, 24(1): 45-49.
PENG F L. Computational simulation of Galton’s experi-ment[J]. College Physics, 2005, 24(1): 45-49.
[20] 何彬鑫. 计算机模拟伽尔顿板实验及研究[J]. 绍兴文理学院学报, 2006(3): 55-63.
HE B X. Simulation of Galton’s experiment[J]. Journal of Shaoxing College, 2006(3): 55-63.
[21] GALOOGAHI H K, SIM T, LUCEY S. Correlation filters with limited boundaries[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition, Boston, Jun 7-12, 2015. Washington: IEEE Computer Society, 2015: 4630-4638.
[22] 濮定国, 金中. 新的拉格朗日乘子方法[J]. 同济大学学报(自然科学版), 2010, 38(9): 1387-1391.
PU D G, JIN Z. New Lagrangian multiplier methods[J]. Journal of Tongji University (Natural Science), 2010, 38(9): 1387-1391.
[23] WANG Y, YIN W T, ZENG J S. Global convergence of ADMM in nonconvex nonsmooth optimization[J]. Journal of Scientific Computing, 2019, 78(1): 29-63.
[24] WU Y, LIM J, YANG M H. Object tracking benchmark[J]. IEEE Transactions on Pattern Analysis and Machine Intell-igence, 2015, 37(9): 1834-1848.
[25] DANELLJAN M, H?GER G, KHAN F S, et al. Accurate scale estimation for robust visual tracking[C]//Proceedings of the 2014 British Machine Vision Conference, Nottin-gham, Sep 1-5, 2014. Durham: BMVA Press, 2014: 1-65.
[26] BERTINETTO L, VALMADRE J, GOLODETZ S, et al. Staple: complementray learners for real-time tracking[C]//Proceedings of the 2016 IEEE Confenerce on Computer Vision and Pattern Recognition, Las Vegas, Jun 27-30, 2016. Wash-ington: IEEE Computer Society, 2016: 1401-1409.
[27] MUELLER M, SMITH N, GHANEM B. Context-aware corr-elation filter tracking[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, Jul 21-26, 2017. Washington: IEEE Computer Society, 2017: 1387-1395.
[28] LI Y, ZHU J K. A scale adaptive kernel correlation filter tracker with feature integration[C]//LNCS 8926: Proceedings of the 13th ECCV Workshops on Computer Vision, Sep 6-7 and 12, 2014. Cham: Springer, 2014: 254-265.