Abstract
In recent years, the method based on discriminative correlation filter has been shown excellent performance in short-term visual tracking. However, discriminative correlation filter-based method heavily suffers from the problem of the multiple peaks and model drift in responds maps incurred by occlusion and rotation. To solve the above problem, we proposed convolution operators for visual tracking based on spatial–temporal regularization. Firstly, we add spatial–temporal regularization in loss function, which will guarantee continuity of the model in time. And we use preconditioned conjugate gradient algorithm to obtain filter coefficients. Secondly, we proposed channel reliability to estimate quality of the learned filter and fuse the different reliability coefficients to weight response map in location. We set a threshold to reduce the number of iteration in location and accelerate the compute speed of algorithm. Finally, we use two different correlation filters to estimate location and scale of target, respectively. Extensively experiment in five video sequences show that our tracker has been significantly improved performance in case of occlusion and rotation. The AUC in success plot improves 33.2% than ECO-HC and 41.5% than STRCF, respectively.
Similar content being viewed by others
References
Yin G, Liu B, Zhu H et al (2019) A large scale urban surveillance video dataset for multiple-object tracking and behavior analysis. CoRR. arXiv:1904.11784
Peng C, Cao D, Wu Y et al (2019) Robot visual guide with Fourier-Mellin based visual tracking. Front Optoelectron 12(4):413–421
Huang R, Liang H, Chen J et al (2016) Lidar based dynamic obstacle detection, tracking and recognition method for driverless cars. Robot 38:437–443
Cooley JW, Lewis PAW, Welch PD (1988) The fast fourier transform and its applications. IEEE Trans Educ 12(1):27–34
Bolme DS, Beveridge JR, Draper BA, Lui YM (2010) Visual object tracking using adaptive correlation filters. In: CVPR
Henriques J, Caseiro R, Martins P, Batista J (2015) Highspeed tracking with kernelized correlation filters. IEEE Trans Pattern Anal Mach Intell 2015(37):583–596
Danelljan M, Hager G, Shahbaz Khan F, Felsberg M (2015) Learning spatially regularized correlation filters for visual tracking. In: ICCV, pp 4310–4318
Galoogahi HK, Fagg A, Lucey S (2017) Learning background-aware correlation filters for visual tracking
Boyd S, Parikh N, Chu E et al (2010) Distributed optimization and statistical learning via the alternating direction method of multipliers. Found Trends Mach Learn 3(1):1–122
Lukezic A, Vojr T, Cehovin Zajc L, Matas J, Kristan M (2017) Discriminative correlation filter with channel and spatial reliability. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4847–4856
Galoogahi HK, Sim T, Lucey S (2015) Correlation filters with limited boundaries. In: CVPR, pp 4630–4638
Li Y, Zhu J (2014) A scale adaptive kernel correlation filter tracker with feature integration. In: ECCV workshops
Danelljan M, Hager G, Khan F, Felsberg M (2017) Discriminative scale space tracking. In: TPAMI
Wang N, Zhou W, Tian Q et al (2018) Multi-cue Correlation filters for robust visual tracking. In: 2018 IEEE/CVF conference on computer vision and pattern recognition (CVPR). IEEE
Danelljan M, Hager G, Khan FS et al (2015) Convolutional features for correlation filter based visual tracking. In: 2015 IEEE international conference on computer vision workshop (ICCVW). IEEE Computer Society
Danelljan M, Robinson A, Shahbaz Khan F, Felsberg M (2016) Beyond correlation filters: learning continuous convolution operators for visual tracking. In: ECCV
Danelljan M, Bhat G, Shahbaz Khan F, Felsberg M (2017) ECO: efficient convolution operators for tracking. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6931–6939
Wang J, Zhang F, Huang J, Wang W, Yuan C (2019) A nonconvex penalty function with integral convolution approximation for compressed sensing. Sig Process 158:116–128
Xu H, Caramanis C, Sanghavi S (2012) Robust PCA via outlier pursuit. IEEE Trans Inf Theory 58(5):3047–3064
Li F, Cheng T, Zuo W et al (2018) Learning spatial-temporal regularized correlation filters for visual tracking. In: IEEE conference on computer vision and pattern recognition, Salt Lake City, pp 4904–4913
Xu T, Feng Z, Wu X, Kittler J (2019) Learning adaptive discriminative correlation filters via temporal consistency preserving spatial feature selection for robust visual tracking. IEEE Trans Image Process 28(11):5596–5609
Sun C, Wang D, Lu H, Yang M (2018) Correlation tracking via joint discrimination and reliability learning. In: Proceedings of European conference on computer vision
Johnander J, Danelljan M, Khan FS et al (2017) DCCO: towards deformable continuous convolution operators
Gladh S, Danelljan M, Khan FS et al (2016) Deep motion features for visual tracking. pp 1243–1248
Crammer K, Dekel O, Keshet J, Shalev-Shwartz S, Singer Y (2006) Online passive-aggressive algorithms. JMLR 7(3):551–585
Wu Y, Lim J, Yang MH (2015) Object tracking benchmark. IEEE Trans Pattern Anal Mach Intell 37(9):1834–1848
Acknowledgements
This work was supported by Scientific Research Program Funded by Shaanxi Science and Technology Department (2019GY-022, 2019GY-066), National Natural Science Foundation of China (61671362), Science and Technology Program of Weiyang District Science and Technology Department (201923).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
There are no conflicts of interests.
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
Wang, P., Sun, M., Wang, H. et al. Convolution operators for visual tracking based on spatial–temporal regularization. Neural Comput & Applic 32, 5339–5351 (2020). https://doi.org/10.1007/s00521-020-04704-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-020-04704-1