Fusion of Multiple Attention Mechanisms and Background Feature Adaptive Update Strategies in Siamese Networks for Single-Object Tracking
Source abstract
Abstract
Single-object tracking algorithms based on Siamese full convolutional networks have attracted much attention from researchers owing to their improvement in precision and speed. Since this tracking model only learns a similarity model offline, it is not able to obtain more useful feature discrimination information to adapt to the various variations of targets in complex scenes. To improve the performance of this tracking model, we propose a Siamese network tracking algorithm that incorporates multiple attention mechanisms and an adaptive updating strategy for background features. First, a backbone feature extraction network is proposed that utilizes a small convolutional kernel to fuse jump-layer connectivity features, thereby improving the feature representation capability of the network. Second, an adaptive update strategy for background features is proposed to improve the model’s ability to discriminate between the object and background features. Third, the fusion of multiple attention mechanisms is proposed so that the model learns to focus on the channel, spatial, and coordinate features. Fourth, the response fusion operation is proposed after the inter-correlation operation to enrich the output response of the model. Finally, our algorithm is trained using the GOT-10K dataset and evaluated by testing on the object tracking benchmark datasets OTB100 and VOT2018. The test results show that compared with other algorithms, our algorithm can effectively cope with the problem of degradation of the tracking performance in complex environments, and it can further improve the tracking precision and precision under the premise of ensuring the tracking speed.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Video Surveillance and Tracking Methods · Infrared Target Detection Methodologies · Fire Detection and Safety Systems
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Institute of Applied Electronics, Chinese Academy of Engineering Physics, Mianyang 621025, China
Graduate School, China Academy of Engineering Physics, Mianyang 621999, China
Funding
China Academy of Engineering Physics
References (42)
Show source-provided references
1. Object Tracking: A Survey10.1145/1177352.1177355 ↗
2. Deep visual tracking: Review And experimental comparison10.1016/j.patcog.2017.11.007 ↗
3. Zheng, C., and Usagawa, T. (2018, January 24–27). A rapid webcam-based eye tracking method for human computer interaction. Proceedings of the 2018 International Conference on Control, Automation and Information Sciences (ICCAIS), Hangzhou, China.10.1109/ICCAIS.2018.8570532 ↗
4. Handling pedestrians in self-driving cars using image tracking and alternative path generation with Frenét frames10.1016/j.cag.2019.08.004 ↗
5. Wu, Y., Lim, J., and Yang, M.-H. (2013, January 23–28). Online object tracking: A benchmark. Proceedings of the 2013 IEEE International Conference on Computer Vision and Pattern Recogintion (CVPR), Portland, OR, USA.10.1109/CVPR.2013.312 ↗
6. Object tracking benchmark10.1109/TPAMI.2014.2388226 ↗
7. Wu, Y., Cheng, J., Wang, J., and Lu, H. (October, January 29). Real-time visual tracking via Incremental Covariance Tensor Learning. Proceedings of the 2009 IEEE 12th International Conference on Computer Vision (ICCV), Kyoto, Japan.10.1109/ICCV.2009.5459369 ↗
8. A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking10.1109/78.978374 ↗
9. Comaniciu, D., Ramesh, V., and Meer, P. (2000, January 15). Real-time tracking of non-rigid objects using mean shift. Proceedings of the IEEE International Conference on Computer Vision and Pattern Recogintion (CVPR), Hilton Head, SC, USA.
10. Kernel-based object tracking10.1109/TPAMI.2003.1195991 ↗
11. Bolme, D.S., Beveridge, J.R., Draper, B.A., and Lui, Y.M. (2010, January 13–18). Visual Object Tracking using Adaptive Correlation Filters. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA, IEEE.10.1109/CVPR.2010.5539960 ↗
12. High-Speed Tracking with Kernelized Correlation Filters10.1109/TPAMI.2014.2345390 ↗
13. Henriques, J.F., Caseiro, R., Martins, P., and Batista, J. (2012, January 7–13). Exploiting the Circulant Structure of Tracking-by-Detection with Kernels. Proceedings of the 12th European Conference on Computer Vision, Florence, Italy.10.1007/978-3-642-33765-9_50 ↗
14. Ma, C., Huang, J.B., Yang, X., and Yang, M.H. (2015, January 7–13). Hierarchical Convolutional Features for Visual Tracking. Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, Chile.10.1109/ICCV.2015.352 ↗
15. Danelljan, M., Hager, G., Shahbaz Khan, F., and Felsberg, M. (2015, January 7–13). Learning spatially regularized correlation filters for visual tracking. Proceedings of the 2005 IEEE International Conference on Computer Vision (ICCV), Santiago, Chile.10.1109/ICCV.2015.490 ↗
16. Li, Y., and Zhu, J. (12, January 6–7). A scale adaptive kernel correlation filter tracker with feature integration. Proceedings of the European Conference on Computer Vision, Zurich, Switzerland.
17. Bertinetto, L., Valmadre, J., Golodetz, S., Miksik, O., and Torr, P.H.S. (2016, January 27–30). Staple: Complementary learners for real-time tracking. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.156 ↗
18. Signature verification using a “Siamese” time delay neural network10.1142/S0218001493000339 ↗
19. Zagoruyko, S., and Komodakis, N. (2015, January 7–12). Learning to compare image patches via convolutional neural networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.10.1109/CVPR.2015.7299064 ↗
20. Bertinetto, L., Valmadre, J., Henriques, J.F., Vedaldi, A., and Torr, P.H.S. (15–16, January 8–10). Fully-convolutional siamese networks for object tracking. Proceedings of the Computer Vision—ECCV 2016 Workshops (ECCV), Amsterdam, The Netherlands.10.1007/978-3-319-48881-3_56 ↗
21. Abdelpakey, M.H., Shehata, M.S., and Mohamed, M.M. (2018). DensSiam: End-to-end densely-siamese network with self-attention model for object tracking. International Symposium on Visual Computing, Springer.10.1007/978-3-030-03801-4_41 ↗
22. Li, B., Yan, J., Wu, W., Zhu, Z., and Hu, X. (2018, January 18–23). High performance visual tracking with siamese region network. Proceedings of the 2018 IEEE/CVF Conference of Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00935 ↗
23. Xu, Y., Wang, Z., Li, Z., Yuan, Y., and Yu, G. (2020, January 7–12). Siamfc++: Towards robust and accurate visual tracking with object estimation guidelines. Proceedings of the 34th AAAI Conference on Artificial Intelligence (AAAI-20), New York, NY, USA.10.1609/aaai.v34i07.6944 ↗
24. Li, B., Wu, W., Wang, Q., Zhang, F., Xing, J., and Yan, J. (2019, January 15–20). SiamRPN++: Evolution of siamese visual tracking with very deep networks. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.00441 ↗
25. Li, Y., and Zhang, X. (2019). SiamVGG: Visual Tracking using Deeper Siamese Networks. arXiv.
26. Wang, Q., Zhang, L., Bertinetto, L., Hu, W., and Torr, P.H.S. (2019, January 15–20). Fast Online Object Tracking and Segmentation: A Unifying Approach. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.00142 ↗
27. Valmadre, J., Bertinetto, L., Henriques, J., Vedaldi, A., and Torr, P.H.S. (2017, January 21–26). End-to-end representation learning for correlation filter based tracking. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.531 ↗
28. Krizhevsky, A., Sutskever, I., and Hinton, G.E. (2012, January 3–6). ImageNet classification with deep convolutional neural networks. Proceedings of the Advances in Neural Information Processing Systems, Lake Tahoe, NV, USA.
29. Parkhi, O.M., Vedaldi, A., and Zisserman, A. (2015, January 7–10). Deep face recognition. Proceedings of the British Machine Vision Conference (BMVC), Swansea, UK.
30. Chaudhari, S., Polatkan, G., Ramanath, R., and Mithal, V. (2019). An attentive survey of attention models. arXiv.
31. He, A., Luo, C., Tian, X., and Zeng, W. (2018, January 18–23). A twofold siamese network for realtime object tracking. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.10.1109/CVPR.2018.00508 ↗
32. Zhu, X., Cheng, D., Zhang, Z., Lin, S., and Dai, J. (November, January 27). An empirical study of spatial attention mechanisms in deep networks. Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Republic of Korea.10.1109/ICCV.2019.00679 ↗
33. Woo, S., Park, J., Lee, J.-Y., and Kweon, I.S. (2018, January 8–14). CBAM: Convolutional block attention module. Proceedings of the Computer Vision—ECCV 2018 (ECCV), Munich, Germany.10.1007/978-3-030-01234-2_1 ↗
34. Hou, Q., Zhou, D., and Feng, J. (2021, January 20–25). Coordinate attention for efficient mobile network design. Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.10.1109/CVPR46437.2021.01350 ↗
35. Hu, J., Shen, L., and Sun, G. (2018, January 18–23). Squeeze-and-excitation networks. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00745 ↗
36. Wang, Q.L., Wu, B.G., Zhu, P.F., Li, P.H., Zuo, W.M., and Hu, Q.H. (2020, January 13–19). ECA-Net: Efficient channel attention for deep convolutional neural network. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR42600.2020.01155 ↗
37. GOT-10k: A large high-diversity benchmark for generic object tracking in the wild10.1109/TPAMI.2019.2957464 ↗
38. Sun, L., Fan, B., and Peng, Y. (2018, January 9–11). Adaptive Scale Correlation Filter Tracker with Feature Fusion. Proceedings of the 30th Chinese Conference on Control and Decision Making, Shenyang, China.10.1109/CCDC.2018.8408173 ↗
39. Zhang, J., Ma, S., and Sclaroff, S. (2014, January 6–12). MEEM: Robust Tracking via Multiple Experts Using Entropy Minimization. Proceedings of the 13th European Conference on Computer Vision, Zurich, Switzerland.10.1007/978-3-319-10599-4_13 ↗
40. Danelljan, M., Häger, G., Khan, F., and Felsberg, M. (2014, January 1–5). Accurate Scale Estimation for Robust Visual Tracking. Proceedings of the British Machine Vision Conference, Nottingham, UK.10.5244/C.28.65 ↗
41. DCFNet: Discriminant Correlation Filters Network for Visual Tracking10.1007/s11390-023-3788-3 ↗
42. Kristan, M., Leonardis, A., Matas, J., Felsberg, M., Pfugfelder, R., Zajc, L.C., Vojir, T., Bhat, G., Lukezic, A., and Eldesokey, A. (2018, January 8–14). The sixth visual object tracking VOT2018 challenge results. Proceedings of the Computer Vision—ECCV 2018 Workshops (ECCV), Munich, Germany.