Brief review of object tracking algorithms in recent years: correlated filtering and deep learning

Lu Meng; Chengxin Li

doi:10.11834/jig.190111

Scholar View | Views : 0 下载量: 419 CSCD: 5

PDF
Export
Share
Collection
Album

Brief review of object tracking algorithms in recent years: correlated filtering and deep learning
Vol. 24, Issue 7, Pages: 1011-1016(2019)
Received：28 March 2019，

Revised：2019-4-25，

Published：16 July 2019
DOI： 10.11834/jig.190111
稿件说明：

移动端阅览

DOI：

Lu Meng, Chengxin Li. Brief review of object tracking algorithms in recent years: correlated filtering and deep learning[J]. Journal of Image and Graphics, 2019, 24(7): 1011-1016. DOI： 10.11834/jig.190111.

摘要

目的

目标跟踪是计算机视觉领域的重要组成部分。近年来，基于相关滤波和深度学习的目标跟踪算法层出不穷，本文拟对经典的若干目标跟踪算法进行阐述与分析。

方法

首先，对基于相关滤波跟踪算法的基础理论进行介绍，针对相关滤波算法在特征改进类、尺度改进类、消除边界效应类、图像分块类与目标响应自适应类方面进行总结；接下来，从3个方面对基于深度学习的目标跟踪算法进行阐述与分析：目标分类、结构化回归、孪生网络，并对有代表性的跟踪算法的优势与缺陷进行较深层次的解读。

结果

通过列举跟踪算法在相关滤波阶段、深度学习阶段针对不同的改进机制的改进算法，总结各阶段算法的优缺点。对目标跟踪算法的最新进展进行阐述，最终对目标跟踪算法的未来发展方向进行总结。

结论

基于相关滤波的目标算法在实时性方面表现优秀，但对于复杂背景干扰、相似物遮挡等情况仍然需要优化。深层的卷积特征对于目标有强大的表示力，通过使相关滤波算法与深度学习结合，大幅度提升了算法表现力。基于深度学习的跟踪算法则更侧重于跟踪的性能，大多无法满足实时性。孪生神经网络的使用对于基于深度学习类目标跟踪算法产生了很大的推动，兼顾了算法的性能和实时性。

Abstract

Objective

Target tracking is an important part of computer vision. In recent years

target tracking algorithms based on correlation filtering and deep learning have been emerging in endlessly. This paper will elaborate on and analyze some classical target tracking algorithms.

Method

First

this paper introduces the basic theory of the tracking algorithms based on correlation filtering. And it will also give a summary in terms of the feature improvement

scale improvement

elimination boundary effect

image segmentation

and target response adaptive classes of the correlation filtering algorithms are summarized. Next

the target tracking algorithms based on deep learning are expounded and analyzed from three aspects: target classification

structured regression

and Siamese neural network. An in-depth interpretation of the advantages and defects of representative tracking algorithms is also provided.

Result

The advantages and disadvantages of each phase algorithm are summarized through an enumeration of the enhanced tracking algorithms for different improved mechanisms in the correlation filtering and deep learning phases. This paper expounds on the latest progress of target tracking algorithms and summarizes their future development direction.

Conclusion

The target algorithm based on correlation filtering performs well in real-time performance but still requires optimization for complex background interference and similar object occlusion. The deep convolution feature has a strong representation of the target

and when the correlation filtering algorithm is combined with deep learning

the performance of the algorithm is greatly improved. Tracking algorithms based on deep learning objectives are highly focused on tracking performance

and most of them cannot achieve real-time performance. The use of the Siamese neural network has greatly promoted the deep tracking-based target tracking algorithm by taking into account the performance and real-time performance of the algorithm.

关键词

Keywords

references

Zhang T Z, Xu C S, Yang M H. Multi-task correlation particle filter for robust object tracking[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, Hawaii, USA: IEEE, 2017: 4819-4827.[ DOI: 10.1109/CVPR.2017.512 http://dx.doi.org/10.1109/CVPR.2017.512 ]

Zhang K H, Zhang L, Yang M H. Real-time compressive tracking[C]//Proceedings of 2012 European Conference on Computer Vision. Florence, Italy: Springer, 2012: 864-877.[ DOI: 10.1007/978-3-642-33712-3_62 http://dx.doi.org/10.1007/978-3-642-33712-3_62 ]

Sun C, Wang D, Lu H C, et al. Correlation tracking via joint discrimination and reliability learning[C]//Proceedings of 2017 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT, USA: IEEE, 2018: 489-497.[ DOI: 10.1109/CVPR.2018.00058 http://dx.doi.org/10.1109/CVPR.2018.00058 ]

Li B, Wu W, Wang Q, et al. SiamRPN++: evolution of Siamese visual tracking with very deep networks[C]//Proceedings of 2019 IEEE Conference on Computer Vision and Pattern Recognition. Long Beach, CA, USA: IEEE, 2019.

Wang N, Zhou W G, Tian Q, et al. Multi-cue correlation filters for robust visual tracking[C]//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT, USA: IEEE, 2018: 4844-4853.[ DOI: 10.1109/CVPR.2018.00509 http://dx.doi.org/10.1109/CVPR.2018.00509 ]

Danelljan M, Häger G, Khan F S, et al. Learning spatially regularized correlation filters for visual tracking[C]//Proceedings of 2015 IEEE International Conference on Computer Vision. Santiago, Chile: IEEE, 2016: 4310-4318.[ DOI: 10.1109/ICCV.2015.490 http://dx.doi.org/10.1109/ICCV.2015.490 ]

Lukežic A, Vojír T, Zajc L C, et al. Discriminative correlation filter with channel and spatial reliability[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA: IEEE, 2017: 4847-4856.[ DOI: 10.1109/CVPR.2017.515 http://dx.doi.org/10.1109/CVPR.2017.515 ]

Fan H, Xiang J H. Robust visual tracking via local-global correlation filter[C]//Proceedings of the 31st AAAI Conference on Artificial Intelligence. San Francisco: AAAI, 2017: 4025-4031.

Sui Y, Wang G H, Zhang L. Correlation filter learning toward peak strength for visual tracking[J]. IEEE Transactions on Cybernetics, 2018, 48(4):1290-1303.[DOI:10.1109/TCYB.2017.2690860]

Fan H, Ling H B. SANet: Structure-aware network for visual tracking[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA: IEEE, 2017: 2217-2224.[ DOI: 10.1109/CVPRW.2017.275 http://dx.doi.org/10.1109/CVPRW.2017.275 ]

Wang L J, Ouyang W L, Wang X G, et al. Visual tracking with fully convolutional networks[C]//Proceedings of 2015 IEEE International Conference on Computer Vision. Santiago, Chile: IEEE, 2015: 3119-3127.[ DOI: 10.1109/ICCV.2015.357 http://dx.doi.org/10.1109/ICCV.2015.357 ]

Danelljan M, Robinson A, Khan F S, et al. Beyond correlation filters: learning continuous convolution operators for visual tracking[C]//Proceedings of the 14th European Conference on Computer Vision. Amsterdam, The Netherlands: Springer, 2016: 472-488.[ DOI: 10.1007/978-3-319-46454-1_29 http://dx.doi.org/10.1007/978-3-319-46454-1_29 ]

Bertinetto L, Valmadre J, Henriques J F, et al. Fully-convolutional siamese networks for object tracking[C]//Proceedings of European Conference on Computer Vision. Amsterdam, The Netherlands: Springer, 2016: 850-865.[ DOI: 10.1007/978-3-319-48881-3_56 http://dx.doi.org/10.1007/978-3-319-48881-3_56 ]

Li B, Yan J J, Wu W, et al. High performance visual tracking with Siamese region proposal network[C]//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT, USA: IEEE, 2018: 8971-8980.[ DOI: 10.1109/CVPR.2018.00935 http://dx.doi.org/10.1109/CVPR.2018.00935 ]

Zhang Z P, Peng H W. Deeper and wider Siamese networks for real-time visual tracking[C]//Proceedings of 2019 IEEE Conference on Computer Vision and Pattern Recognition. Long Beach, CA: IEEE, 2019.

Wang Q, Zhang L, Bertinetto L, et al. Fast online object tracking and segmentation: a unifying approach[EB/OL].[2019-03-10] https://arxiv.org/pdf/1812.05050.pdf https://arxiv.org/pdf/1812.05050.pdf .

Alert me when the article has been cited

提交

Single target tracking in satellite videos

Siamese network with pixel-pair for hyperspectral image anomaly detection

Dynamic update correlation filter tracking based on appearance representation analysis

Adaptive scale sudden change object tracking

Adaptive convolutional feature selection for real-time visual tracking