Abstract
Siamese network based trackers have received extensive attention with their trade-off between accuracy and speed. In particular, Siamese Region Proposal Network (SiamRPN) tracker can get more accurate bounding box with proposal refinement, yet, most siamese trackers are lack of discrimination without target classification and robustness without online learning module. To tackle the problem, in this paper, we propose an ensemble tracking framework based on SiamRPN tracker, consisting of two components: (1) Correlation Filter module with hierarchical features fusion; and (2) SiamRPN module. The Correlation Filter module fully exploits both the semantic features for classification and the lower-level features for precise localization through online learning process. By cascading the Correlation Filter to SiamRPN tracker, which can equip with discrimination power. The entire network based on multitask learning strategy is trained in an end-to-end manner, which enhances both robustness and module adaptability effect. In extensive experiments evaluations on GOT-10K test dataset, OTB2015 and VOT2016 benchmarks, our tracking approach obtains better performance than other trackers, including SiamRPN tracker, by a notable margin.
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
Wang, Q., Gao, J., Xing, J., et al.: DCFNet: discriminant correlation filters network for visual tracking. arXiv:1704.04057 (2017)
Li, B., Yan, J., Wu, W., et al.: High performance visual tracking with siamese region proposal network. In: 2018 31st IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, 18–23 June 2018, pp. 8971–8980 (2018)
Henriques, J.F., Caseiro, R., Martins, P., Batista, J.: High-speed tracking with kernelized correlation filters. 2015 IEEE Trans. Pattern Anal. Mach. Intell. J. 37(3), 583–596 (2015)
Ma, C., Huang, J.-B., Yang, X., Yang, M.-H.: Hierarchical convolutional features for visual tracking. In: 2015 IEEE International Conference on Computer Vision, ICCV 2015, Santiago, Chile, 11–18 December 2015, pp. 3074–3082 (2015)
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
He, A., Luo, C., Tian, X., Zeng, W.: A twofold Siamese network for real-time object tracking. In:2018 31st IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, 18–23 June 2018, pp. 4834–4843 (2018)
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In:2015 29th Annual Conference on Neural Information Processing Systems, NIPS 2015, Montreal, Canada, 07–12 December 2015, pp. 91–99 (2015)
Qi, Y., Zhang, S., Qin, L., Yao, H., et al.: Hedged deep tracking. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Seattle, WA, 27–30 June 2016, pp. 4303–4311 (2016)
Han, B., Sim, J., Adam, H.: BranchOut: regularization for online ensemble tracking with convolutional neural networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, 21–26 July 2017, pp. 521–530 (2017)
Lin, T.-Y., Dollar, P., Girshick, R.: Feature pyramid networks for object detection. In: 2017 30th IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, 21–26 July 2017, pp. 936–944 (2017)
Huang, L., Zhao, X., Huang, K.: GOT-10k: a large high-diversity benchmark for generic object tracking in the wild. IEEE Trans. Pattern Anal. Mach. Intell. J. 37(9) (2018)
Wu, Y., Lim, J., Yang, M.-H.: Object tracking benchmark. 2015 IEEE Trans. Pattern Anal. Mach. Intell. J. 37(9), 1834–1848 (2015)
Kristan, M., et al.: The visual object tracking VOT2016 challenge results. In: Hua, G., Jégou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 777–823. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-48881-3_54
Danelljan, M., Bhat, G., Shahbaz Khan, F., et al.: ECO: efficient convolution operators for tracking. In: 2017 30th IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, 21–26 July (2017)
Bertinetto, L., Valmadre, J., Golodetz, S., et al.: Complementary learners for real-time tracking. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Seattle, WA, 27–30 June 2016, pp. 1401–1409 (2016)
Fan, H., Ling, H.: Siamese cascaded region proposal networks for real-time visual tracking. In: 2019 32st IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, 16–20 June (2019)
Acknowledgments
The research is partly supported by National Natural Science Foundation of China (61806017).
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
Cui, S., Tian, S., Yin, X. (2019). Combined Correlation Filters with Siamese Region Proposal Network for Visual Tracking. In: Gedeon, T., Wong, K., Lee, M. (eds) Neural Information Processing. ICONIP 2019. Lecture Notes in Computer Science(), vol 11954. Springer, Cham. https://doi.org/10.1007/978-3-030-36711-4_12
Download citation
DOI: https://doi.org/10.1007/978-3-030-36711-4_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-36710-7
Online ISBN: 978-3-030-36711-4
eBook Packages: Computer ScienceComputer Science (R0)