Abstract
Spatial regularization can effectively solve the unwanted boundary effect of discriminative correlation filters (DCF). However, the predefined mask is independent of the feature, which limits the performance improvement. In this paper, we take the mask as a variable that plays the same role as the filter, and an attention regularization correlation filter (ARCF) is proposed for visual tracking. Especially, the mask is no longer a binary but a real value between 0 and 1, used as the weight of the corresponding feature. Additionally, the temporal coherence is also considered when the filter and the mask are simultaneously optimizing via ADMM algorithm, so the filter can fit the variation of the target in the temporal domain. Extensive experiments on the OTB100 database prove that our algorithm is much better than the traditional SRDCF algorithm both in the performance and speed.
Supported by the National Natural Science Foundation of China (No. 61773397) and the Fundamental Research Funds for the Central Universities (No. 3102019ZY1003).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bertinetto, L., Valmadre, J., Henriques, J.F., Vedaldi, A., Torr, P.H.S.: Fully-convolutional siamese networks for object tracking. In: Hua, G., Jégou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 850–865. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-48881-3_56
Bolme, D.S., Beveridge, J.R., Draper, B.A., Lui, Y.M.: Visual object tracking using adaptive correlation filters. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR, pp. 2544–2550 (2010)
Boyd, S., Boyd, S., Vandenberghe, L., Press, C.U.: Convex Optimization. Cambridge University Press, Cambridge (2004)
Choi, J., Chang, H.J., Yun, S., Fischer, T., Demiris, Y., Choi, J.Y.: Attentional correlation filter network for adaptive visual tracking. In: CVPR, pp. 4828–4837. IEEE Computer Society (2017)
Danelljan, M., Bhat, G., Khan, F.S., Felsberg, M.: ECO: efficient convolution operators for tracking. In: Conference on Computer Vision and Pattern Recognition, CVPR, pp. 6931–6939 (2017)
Danelljan, M., Hager, G., Khan, F.S., Felsberg, M.: Learning spatially regularized correlation filters for visual tracking. In: International Conference on Computer Vision, (ICCV) (2015)
Danelljan, M., Häger, G., Khan, F.S., Felsberg, M.: Discriminative scale space tracking. IEEE Trans. Pattern Anal. Mach. Intell. 39(8), 1561–1575 (2017)
Henriques, J.F., Caseiro, R., Martins, P., Batista, J.: High-speed tracking with kernelized correlation filters. IEEE Trans. Pattern Anal. Mach. Intell. 37(3), 583–596 (2015)
Kiani Galoogahi, H., Fagg, A., Lucey, S.: Learning background-aware correlation filters for visual tracking. In: The IEEE International Conference on Computer Vision (ICCV), October 2017
Kiani Galoogahi, H., Sim, T., Lucey, S.: Correlation filters with limited boundaries. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2015
Kristan, M., et al.: A novel performance evaluation methodology for single-target trackers. IEEE Trans. Pattern Anal. Mach. Intell. 38(11), 2137–2155 (2016)
Li, F., Tian, C., Zuo, W., Zhang, L., Yang, M.H.: Learning spatial-temporal regularized correlation filters for visual tracking. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018
Lukezic, A., Vojír, T., Zajc, L.C., Matas, J., Kristan, M.: Discriminative correlation filter tracker with channel and spatial reliability. Int. J. Comput. Vision 126(7), 671–688 (2018)
Pu, S., Song, Y., Ma, C., Zhang, H., Yang, M.H.: Deep attentive tracking via reciprocative learning. In: Neural Information Processing Systems (2018)
Wang, F., et al.: Residual attention network for image classification. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017
Wang, Q., Teng, Z., Xing, J., Gao, J., Hu, W., Maybank, S.J.: Learning attentions: residual attentional siamese network for high performance online visual tracking. In: CVPR, pp. 4854–4863. IEEE Computer Society (2018)
Wu, Y., Lim, J., Yang, M.: Object tracking benchmark. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1834–1848 (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Qiu, Z., Zha, Y., Zhu, P., Zhang, F. (2019). Learning Attention Regularization Correlation Filter for Visual Tracking. In: Lin, Z., et al. Pattern Recognition and Computer Vision. PRCV 2019. Lecture Notes in Computer Science(), vol 11857. Springer, Cham. https://doi.org/10.1007/978-3-030-31654-9_7
Download citation
DOI: https://doi.org/10.1007/978-3-030-31654-9_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-31653-2
Online ISBN: 978-3-030-31654-9
eBook Packages: Computer ScienceComputer Science (R0)