Abstract
In recent years, deep convolutional features have been applied to discriminative correlation filters-based methods, which have achieved impressive performance in tracking. Most of them utilize hierarchical features from a certain layer. However, this is not always sufficient to learn target appearance changes and to suppress the background interference in complicated interfering factors (e.g., deformation, fast motion, low resolution, and rotations). In this paper, we propose an adaptive multi-branch correlation filter tracking method, by constructing multi-branch models and using an adaptive selection strategy to improve the accuracy and robustness of visual tracking. Specially, the multi-branch models are introduced to tolerate temporal changes of the object, which can serve different circumstances. In addition, the adaptive selection strategy incorporates both foreground and background information to learn background suppression. To further improve the tracking performance, we propose a measurement method to handle tracking failures from unreliable samples. Extensive experiments on OTB-2013, OTB-2015, and VOT-2016 datasets show that the proposed tracker has comparable performance compared to state-of-the-art tracking methods. Especially, on the OTB-2015, our method significantly improves the baseline with a gain of 5.5% in overlap precision.
Similar content being viewed by others
References
Gao J, Zhang T, Yang X, Xu C (2017) Deep relative tracking. IEEE Trans Image Process 99:1
Qi Y, Qin L, Zhang J, Zhang S, Huang Q, Yang M-H (2018) Structure-aware local sparse coding for visual tracking. IEEE Trans Image Process 27(8):1
Xuan S et al (2013) A fully online and unsupervised system for large and high-density area surveillance: tracking, semantic scene learning and abnormality detection. Acm Trans Intell Syst Technol 4(2):1–21
Ojha S, Sakhare S (2015) Image processing techniques for object tracking in video surveillance—a survey. In: International conference on pervasive computing
Rautaray SS, Agrawal A (2015) Vision based hand gesture recognition for human computer interaction: a survey. Artif Intell Rev 43(1):1–54
Cho H, Seo YW, Kumar BVKV, Rajkumar RR (2014) A multi-sensor fusion system for moving object detection and tracking in urban driving environments. In: IEEE international conference on robotics & automation
Kristian M, Matas J, Leonardis A, Porikli F (2016) A novel performance evaluation methodology for single-target trackers. IEEE Trans Pattern Anal Mach Intell 38(11):2137–2155
Wu Y, Lim J, Yang MH (2013) Online object tracking: a benchmark. In: Computer vision and pattern recognition. pp 2411–2418
Kalal Z, Mikolajczyk K, Matas J (2012) Tracking-learning-detection. IEEE Trans Pattern Anal Mach Intell 34(7):1409–1422
Henriques JF, Caseiro R, Martins P, Batista J (2015) High-speed tracking with kernelized correlation filters. IEEE Trans Pattern Anal Mach Intell 37(3):583–596
Chao M, Huang JB, Yang X, Yang MH (2016) Hierarchical convolutional features for visual tracking. In: IEEE international conference on computer vision
Ma C, Yang X, Zhang C, Yang MH (2015) Long-term correlation tracking. In: Computer vision & pattern recognition
Danelljan M, Hager G, Shahbaz Khan F, Felsberg M (2015) Learning spatially regularized correlation filters for visual tracking. In: The IEEE international conference on computer vision (ICCV)
Li F, Tian C, Zuo W, Zhang L, Yang MH (2018) Learning spatial-temporal regularized correlation filters for visual tracking. In: The IEEE conference on computer vision and pattern recognition (CVPR)
Danelljan M, Häger G, Shahbaz Khan F, Felsberg M (2014) Accurate scale estimation for robust visual tracking. In: Proceedings of the British machine vision conference
Li Y, Zhu J (2014) Tracker with feature integration. In: European conference on computer vision, pp 254–265
Danelljan M, Khan FS, Felsberg M, Weijer JVD (2014) Adaptive color attributes for real-time visual tracking. In: Computer vision and pattern recognition, pp 1090–1097
Yang K, Song H, Zhang K, Liu Q (2019) Hierarchical attentive Siamese network for real-time visual tracking. Neural Comput Appl 2:1–2
Valmadre J, Bertinetto L, Henriques J, Vedaldi A, Torr PHS (2017) End-to-end representation learning for correlation filter based tracking. In: The IEEE conference on computer vision and pattern recognition (CVPR)
Gao J, Zhang T, Yang X, Xu C (2018) P2T: part-to-target tracking via deep regression learning. IEEE Trans Image Process 27(6):3074–3086
Qi Y, Zhang S, Zhang W, Su L, Huang Q, Yang M-H (2019) Learning attribute-specific representations for visual tracking. In: AAAI
Gao J, Zhang T, Xu C (2019) SMART: joint sampling and regression for visual tracking. IEEE Trans Image Process 28(8):3923–3935
Qi Y et al (2018) Hedging deep features for visual tracking. IEEE Trans Pattern Anal Mach Intell 99:1
Danelljan M, Bhat G, Khan FS, Felsberg M (2017) ECO: efficient convolution operators for tracking. In: IEEE conference on computer vision & pattern recognition
Chao M, Huang JB, Yang X, Yang MH (2017) Robust visual tracking via hierarchical convolutional features. IEEE Trans Pattern Anal Mach Intell 99:1
Mueller M, Smith N, Ghanem B (2017) Context-aware correlation filter tracking. In: Computer vision and pattern recognition, pp 1387–1395
Kiani Galoogahi H, Fagg A, Lucey S (2017) Learning background-aware correlation filters for visual tracking. In: The IEEE International Conference on Computer Vision (ICCV)
Yi W, Jongwoo L, Ming-Hsuan Y (2015) Object tracking benchmark. IEEE Trans Pattern Anal Mach Intell 37(9):1834–1848
Kristan M et al. (2016) The visual object tracking VOT2016 challenge results. In: IEEE international conference on computer vision workshops
González RC, Woods RE (1993) Digital image proccesing. Prentice Hall Int 49(3):423–435
Bolme DS, Beveridge JR, Draper BA, Lui YM (2010) Visual object tracking using adaptive correlation filters. In: Computer vision and pattern recognition, pp 2544–2550
Least-squares R, Rifkin R, Yeo G, Poggio T (2003) Regularized least-squares classification. Adv Learn Theory Methods Model Appl NATO Sci Ser III Comput Syst Sci 190:131–154
Danelljan M, Hager G, Shahbaz Khan F, Felsberg M (2016) Adaptive decontamination of the training set: a unified formulation for discriminative visual tracking. In: The IEEE conference on computer vision and pattern recognition (CVPR)
Danelljan M, Robinson A, Shahbaz Khan F, Felsberg M (2016) Beyond correlation filters: learning continuous convolution operators for visual tracking. In: Computer vision—ECCV 2016, Cham, pp 472–488
He Z, Fan Y, Zhuang J, Yuan D, Bai HL (2017) Correlation filters with weighted convolution responses. In: IEEE international conference on computer vision workshop
Avidan S (2007) Ensemble tracking. IEEE Trans Pattern Anal Mach Intell 29(2):261–271
Saffari A, Leistner C, Santner J, Godec M, Bischof H (2009) On-line random forests. In: 2009 IEEE 12th international conference on computer vision workshops, ICCV Workshops, pp 1393–1400
Meshgi K, Oba S, Ishii S (2018) Efficient diverse ensemble for discriminative co-tracking. In: 2018 IEEE/CVF conference on computer vision and pattern recognition, pp 4814–4823
Nam H, Baek M, Han B (2016) Modeling and propagating CNNs in a tree structure for visual tracking. CoRR 1608:07242
Wang N, Zhou W, Tian Q, Hong R, Wang M, Li H (2018) Multi-cue correlation filters for robust visual tracking. In: The IEEE conference on computer vision and pattern recognition (CVPR)
Chaudhuri K, Freund Y, Hsu D (2009) A parameter-free hedging algorithm. In: International conference on neural information processing systems
Zhang T, Xu C, Yang MH (2018) Learning multi-task correlation particle filters for visual tracking. IEEE Trans Pattern Anal Mach Intell 99:1
Zhang J, Ma S, Sclaroff S (2014) MEEM: robust tracking via multiple experts using entropy minimization. In: Computer vision—ECCV 2014, Cham, pp 188–203
Leang I, Herbin S, Girard B, Droulez J (2018) On-line fusion of trackers for single-object tracking. Pattern Recognit 74:459–473
Crammer K, Dekel O, Keshet J, Shalev-Shwartz S, Singer Y (2006) Online passive-aggressive algorithms. J Mach Learn Res 7(3):551–585
Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: 3rd international conference on learning representations, ICLR 2015, San Diego, CA, May 7–9, 2015, conference track proceedings
Deng J, Dong W, Socher R, Li LJ, Li K, Li FF (2009) ImageNet: a large-scale hierarchical image database. In: IEEE conference on computer vision & pattern recognition
Vedaldi A, Lenc K (2015) MatConvNet—convolutional neural networks for MATLAB
Danelljan M, Hager G, Khan FS, Felsberg M (2016) Convolutional features for correlation filter based visual tracking. In: IEEE international conference on computer vision workshop
Bertinetto L, Valmadre J, Henriques JF, Vedaldi A, Torr PHS (2016) Fully-convolutional siamese networks for object tracking. In: European conference on computer vision
Bertinetto L, Valmadre J, Golodetz S, Miksik O, Torr P (2016) Staple: complementary learners for real-time tracking. In: Computer vision & pattern recognition
Li X, Ma C, Wu B, He Z, Yang M-H (2019) Target-aware deep tracking. In: The IEEE conference on computer vision and pattern recognition (CVPR)
Acknowledgements
This work is supported by the National Natural Science Foundation of China (Nos. 61872326, 61672475, 61772526); Shandong Provincial Natural Science Foundation (ZR2019MF044).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
We declare that we have no conflicts of interest to this work.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Li, X., Huang, L., Wei, Z. et al. Adaptive multi-branch correlation filters for robust visual tracking. Neural Comput & Applic 33, 2889–2904 (2021). https://doi.org/10.1007/s00521-020-05126-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-020-05126-9