Abstract
Trackers based on the Siamese network have achieved remarkable advancements in accuracy and robustness, yet the trackers suffer from enormous computation and memory storage cost, which hinder their rapid inference, making it difficult to deploy in calculation-constrained and memory storage-constrained scenarios. Moreover, a general depthwise correlation attempts to process the entire feature map indiscriminately, which cannot extract more robust features. In this paper, we presented a Lightweight Siamese Network based Tracker (LSNT) to tackle the above issues. In the tracking head part, an extremely efficient module is adopted to simplify the network, so as to maintain a balance with the backbone network in parameter quantity. Furthermore, a novel Spatial-Channel Attention based Depthwise (SCAD) correlation is introduced to enhance the ability of the feature fusion module. Compared with the baseline tracker, LSNT has fewer parameters and calculations, but experiments conducted on the GOT-10k benchmark demonstrate that it achieves comparable performance in terms of accuracy and robustness, thus confirming its efficiency and effectiveness.
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
Ba, J., Mnih, V., Kavukcuoglu, K.: Multiple object recognition with visual attention. arXiv preprint arXiv:1412.7755 (2014)
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
Chen, Z., Zhong, B., Li, G., Zhang, S., Ji, R.: Siamese box adaptive network for visual tracking. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6668–6677 (2020)
Danelljan, M., Bhat, G., Shahbaz Khan, F., Felsberg, M.: Eco: efficient convolution operators for tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6638–6646 (2017)
Danelljan, M., Häger, G., Khan, F., Felsberg, M.: Accurate scale estimation for robust visual tracking. In: British Machine Vision Conference, Nottingham, 1–5 September 2014. BMVA Press (2014)
Danelljan, M., Hager, G., Shahbaz Khan, F., Felsberg, M.: Learning spatially regularized correlation filters for visual tracking. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4310–4318 (2015)
Guo, D., Wang, J., Cui, Y., Wang, Z., Chen, S.: Siamcar: siamese fully convolutional classification and regression for visual tracking. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6269–6277 (2020)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
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 (2014)
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. 1(1), 1–17 (2019)
Kiani Galoogahi, H., Fagg, A., Lucey, S.: Learning background-aware correlation filters for visual tracking. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1135–1143 (2017)
Li, B., Wu, W., Wang, Q., Zhang, F., Xing, J., Yan, J.: Siamrpn++: evolution of siamese visual tracking with very deep networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4282–4291 (2019)
Li, B., Yan, J., Wu, W., Zhu, Z., Hu, X.: High performance visual tracking with siamese region proposal network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8971–8980 (2018)
Mnih, V., Heess, N., Graves, A., Kavukcuoglu, K.: Recurrent models of visual attention. arXiv preprint arXiv:1406.6247 (2014)
Nam, H., Han, B.: Learning multi-domain convolutional neural networks for visual tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4293–4302 (2016)
Pu, S., Song, Y., Ma, C., Zhang, H., Yang, M.H.: Deep attentive tracking via reciprocative learning. arXiv preprint arXiv:1810.03851 (2018)
Qin, Z., et al.: Thundernet: towards real-time generic object detection on mobile devices. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 6718–6727 (2019)
Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. arXiv preprint arXiv:1506.01497 (2015)
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: Mobilenetv 2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510–4520 (2018)
Sauer, A., Aljalbout, E., Haddadin, S.: Tracking holistic object representations. arXiv preprint arXiv:1907.12920 (2019)
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818–2826 (2016)
Valmadre, J., Bertinetto, L., Henriques, J., Vedaldi, A., Torr, P.H.: End-to-end representation learning for correlation filter based tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2805–2813 (2017)
Wang, G., Luo, C., Xiong, Z., Zeng, W.: Spm-tracker: series-parallel matching for real-time visual object tracking. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3643–3652 (2019)
Woo, S., Park, J., Lee, J.Y., Kweon, I.S.: Cbam: convolutional block attention module. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3–19 (2018)
Zhang, Z., Peng, H.: Deeper and wider siamese networks for real-time visual tracking. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4591–4600 (2019)
Zhu, Z., Wu, W., Zou, W., Yan, J.: End-to-end flow correlation tracking with spatial-temporal attention. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 548–557 (2018)
Acknowledgements
This work was supported in part by the National Key R&D Program of China (No. 2018YFC1504104), the National Natural Science Foundation of China (Nos. 71991464/71991460, and 61877056), and the Fundamental Research Funds for the Central Universities of China (No. WK5290000001).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Dong, X., Huang, Z., Zou, L., Wang, F., Zhang, Z. (2021). LSNT: A Lightweight Siamese Network Based Tracker. In: Peng, Y., Hu, SM., Gabbouj, M., Zhou, K., Elad, M., Xu, K. (eds) Image and Graphics. ICIG 2021. Lecture Notes in Computer Science(), vol 12890. Springer, Cham. https://doi.org/10.1007/978-3-030-87361-5_52
Download citation
DOI: https://doi.org/10.1007/978-3-030-87361-5_52
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-87360-8
Online ISBN: 978-3-030-87361-5
eBook Packages: Computer ScienceComputer Science (R0)