Correlation Filters Based on Strong Spatio-Temporal for Robust RGB-T Tracking
Abstract
In this paper, we propose a strong spatio-temporal mechanism with correlation filters to solve multi-modality tracking tasks. First, we use the features of the previous four frames as spatio-temporal features, then aggregate the spatio-temporal features into the filters learning and positioning of the adjacent frame. Second, we enhance the temporal and spatial characteristics of the current frame filter by learning the previous four frame filters and spatial penalty. From the experimental results on the GTOT, VOT-TIR2019 and RGBT234 datasets, our strong spatio-temporal correlation filters has achieved excellent performance.
This paper was recommended by Regional Editor Tongquan Wei.
References
- 1. , Distractor-aware tracking with multi-task and dynamic feature learning, J. Circuits Syst. Comput. 30(2) (2021) 2150031. Link, ISI, Google Scholar
- 2. , Object tracking in satellite videos based on a lightweight network, J. Circuits Syst. Comput. 30(6) (2020) 2150099. Link, ISI, Google Scholar
- 3. , Robust object tracking using joint color-texture histogram, Int. J. Pattern Recognit. Artif. Intell. 23 (2009) 1245–1263. Link, ISI, Google Scholar
- 4. , Object motion detection and tracking by an artificial intelligence approach, Int. J. Pattern Recognit. Artif. Intell. 22 (2008) 915–928. Link, ISI, Google Scholar
- 5. , Multiple object detection and tracking in complex background, Int. J. Pattern Recognit. Artif. Intell. 31 (2017) 1755003. Link, ISI, Google Scholar
- 6. , Cross-modal ranking with soft consistency and noisy labels for robust RGB-T tracking, Europeon Conf. Computer Vision (Springer, Cham, 2018), pp. 831–847. Crossref, Google Scholar
- 7. , Quality-aware feature aggregation network for robust RGBT tracking, IEEE Trans. Intell. Veh. 6(1) (2020) 121–130. Crossref, Google Scholar
- 8. , Weighted sparse representation regularized graph learning for RGB-T object tracking, Proc. 25th ACM Int. Conf. Multimedia, 2017, pp. 1856–1864. Crossref, Google Scholar
- 9. , Learning modality-consistency feature templates: A robust RGB-infrared tracking system, IEEE Trans. Ind. Electron. 66 (2019) 9887–9897. Crossref, ISI, Google Scholar
- 10. , Multi-adapter RGBT tracking, Proc. IEEE Int. Conf. Computer Vision Workshops, 2019, pp. 2262–2270. Crossref, Google Scholar
- 11. , Cross-modal pattern-propagation for RGB-T tracking, Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition, 2020, pp. 7064–7073. Crossref, Google Scholar
- 12. , Fast RGB-T tracking via cross-modal correlation filters, Neurocomputing 334 (2019) 172–181. Crossref, ISI, Google Scholar
- 13. , Learning soft-consistent correlation filters for RGB-T object tracking, Chinese Conf. Pattern Recognition and Computer Vision (PRCV) (Springer, 2018), pp. 295–306. Crossref, Google Scholar
- 14. , Learning spatial-temporal regularized correlation filters for visual tracking, Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2018, pp. 4904–4913. Crossref, Google Scholar
- 15. , Learning background-aware correlation filters for visual tracking, Proc. IEEE Int. Conf. Computer Vision, 2017, pp. 1135–1143. Crossref, Google Scholar
- 16. , Visual object tracking using adaptive correlation filters, 2010 IEEE Computer Society Conf. Computer Vision and Pattern Recognition (IEEE, 2010), pp. 2544–2550. Crossref, Google Scholar
- 17. , High-speed tracking with kernelized correlation filters, IEEE Trans. Pattern Anal. Mach. Intell. 37 (2014) 583–596. Crossref, ISI, Google Scholar
- 18. , Exploiting the circulant structure of tracking-by-detection with kernels, European Conf. Computer Vision (Springer, 2012), pp. 702–715. Crossref, Google Scholar
- 19. , Multi-cue correlation filters for robust visual tracking, Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2018, pp. 4844–4853. Crossref, Google Scholar
- 20. , Accurate scale estimation for robust visual tracking, in British Machine Vision Conf.,
Nottingham ,September 1–5 , BMVA Press, 2014. Crossref, Google Scholar - 21. , A scale adaptive kernel correlation filter tracker with feature integration, European Conf. Computer Vision (Springer, 2014), pp. 254–265. Google Scholar
- 22. , Target tracking based on correlation filter for scale offset, IOP Conf. Series: Materials Science and Engineering, Vol. 790 (IOP Publishing, 2020), p. 012038. Crossref, Google Scholar
- 23. , Learning spatially regularized correlation filters for visual tracking, IEEE Int. Conf. Computer Vision, 2015, pp. 4310–4318. Crossref, Google Scholar
- 24. , Attentional correlation filter network for adaptive visual tracking, Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2017, pp. 4807–4816. Crossref, Google Scholar
- 25. , Fast kernelized correlation filter without boundary effect, Proc. IEEE/CVF Winter Conf. Applications of Computer Vision, 2021, pp. 2999–3008. Crossref, Google Scholar
- 26. , Beyond correlation filters: Learning continuous convolution operators for visual tracking, European Conf. Computer Vision (Springer, 2016), pp. 472–488. Crossref, Google Scholar
- 27. , Eco: Efficient convolution operators for tracking, Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2017, pp. 6638–6646. Crossref, Google Scholar
- 28. , Bscf: Learning background suppressed correlation filter tracker for wireless multimedia sensor networks, Ad Hoc Netw. 111 (2021) 102340. Crossref, ISI, Google Scholar
- 29. , Visual tracking with long-short term based correlation filter, IEEE Access 8 (2020) 20257–20269. Crossref, ISI, Google Scholar
- 30. , Object tracking in video with correlation filter and using histogram of gradient feature, J. Soft Comput. Inf. Technol. 9 (2020) 43–55. Google Scholar
- 31. , Background spatial correlation filter in multi-channel object tracking, J. Phys. Conf. Ser. 1453 (2020) 012110. Crossref, Google Scholar
- 32. , Robust collaborative discriminative learning for RGB-infrared tracking, Proc. AAAI Conf. Artificial Intelligence, Vol. 32, 2018, pp. 7008–7015. Crossref, Google Scholar
- 33. , Grayscale-thermal object tracking via multitask laplacian sparse representation, IEEE Trans. Syst. Man Cybern. Syst. 47 (2017) 673–681. Crossref, ISI, Google Scholar
- 34. , Multiple source data fusion via sparse representation for robust visual tracking, 14th Int. Conf. Information Fusion (IEEE, 2011), pp. 1–8. Google Scholar
- 35. , Fusion tracking in color and infrared images using joint sparse representation, Sci. China Inf. Sci. 55 (2012) 590–599. Crossref, Google Scholar
- 36. , Learning collaborative sparse representation for grayscale-thermal tracking, IEEE Trans. Image Process. 25 (2016) 5743–5756. Crossref, ISI, Google Scholar
- 37. , Deep adaptive fusion network for high performance RGBT tracking, Proc. IEEE/CVF Int. Conf. Computer Vision Workshops ( IEEE, 2019). Crossref, Google Scholar
- 38. , Dense feature aggregation and pruning for RGBT tracking, Proc. 27th ACM Int. Conf. Multimedia, 2019, pp. 465–472. Crossref, Google Scholar
- 39. , Fusing two-stream convolutional neural networks for RGB-T object tracking, Neurocomputing 281 (2018) 78–85. Crossref, ISI, Google Scholar
- 40. , Dsiammft: An RGB-T fusion tracking method via dynamic siamese networks using multi-layer feature fusion, Signal Process. Image Commun. 84 (2020) 115756. Crossref, ISI, Google Scholar
- 41. A. Lu, C. Li, Y. Yan, J. Tang and B. Luo, RGBT tracking via multi-adapter network with hierarchical divergence loss, arXiv:2011.07189 (2020). Google Scholar
- 42. , Challenge-aware RGBT tracking, European Conf. Computer Vision (Springer, 2020), pp. 222–237. Crossref, Google Scholar
- 43. , Learning discriminative update adaptive spatial-temporal regularized correlation filter for RGB-T tracking, J. Vis. Commun. Image Represent. 72 (2020) 102881. Crossref, ISI, Google Scholar
- 44. , Thermo-visual feature fusion for object tracking using multiple spatiogram trackers, Mach. Vis. Appl. 19 (2008) 483–494. Crossref, ISI, Google Scholar
- 45. , Comparison of fusion methods for thermo-visual surveillance tracking, 2006 9th Int. Conf. Information Fusion (IEEE, 2006), pp. 1–7. Crossref, Google Scholar
- 46. , Two-stage modality-graphs regularized manifold ranking for RGB-T tracking, Signal Process. Image Commun. 68 (2018) 207–217. Crossref, ISI, Google Scholar
- 47. , Visual tracking via adaptive spatially-regularized correlation filters, Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2019, pp. 4670–4679. Crossref, Google Scholar
- 48. , RGB-T object tracking: Benchmark and baseline, Pattern Recognit. 96 (2019) 106977. Crossref, ISI, Google Scholar
- 49. , The seventh visual object tracking vot2019 challenge results, Proc. IEEE/CVF Int. Conf. Computer Vision Workshops, 2019. Crossref, Google Scholar
- 50. , Discriminative correlation filter with channel and spatial reliability, Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2017, pp. 6309–6318. Crossref, Google Scholar
- 51. , Sowp: Spatially ordered and weighted patch descriptor for visual tracking, IEEE Int. Conf. Computer Vision, 2015, pp. 3011–3019. Crossref, Google Scholar