Adaptive Context-Aware and Structural Correlation Filter for Visual Tracking
Source abstract
Abstract
Accurate visual tracking is a challenging issue in computer vision. Correlation filter (CF) based methods are sought in visual tracking based on their efficiency and high performance. Nonetheless, traditional CF-based trackers have insufficient context information, and easily drift in scenes of fast motion or background clutter. Moreover, CF-based trackers are sensitive to partial occlusion, which may reduce their overall performance and even lead to failure in tracking challenge. In this paper, we presented an adaptive context-aware (CA) and structural correlation filter for tracking. Firstly, we propose a novel context selecting strategy to obtain negative samples. Secondly, to gain robustness against partial occlusion, we construct a structural correlation filter by learning both the holistic and local models. Finally, we introduce an adaptive updating scheme by using a fluctuation parameter. Extensive comprehensive experiments on object tracking benchmark (OTB)-100 datasets demonstrate that our proposed tracker performs favorably against several state-of-the-art trackers.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Video Surveillance and Tracking Methods · Human Pose and Action Recognition · Advanced Vision and Imaging
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Systems Engineering Institute, Xi’an Jiaotong University, Xi’an 710049, China
Xi’an Jiaotong University Suzhou Academy, Suzhou 215123, China
Funding
National Natural Science Foundation of China · Natural Science Foundation of Jiangsu Province
References (49)
Show source-provided references
1. Struck: Structured output tracking with kernels10.1109/TPAMI.2015.2509974 ↗
2. Kwon, J., and Lee, K.M. (2010, January 13–18). Visual tracking decomposition. Proceedings of the 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA.10.1109/CVPR.2010.5539821 ↗
3. Kwon, J., and Lee, K.M. (2011, January 6–13). Tracking by sampling trackers. Proceedings of the 2011 International Conference on Computer Vision, Barcelona, Spain.
4. Zhong, W., Lu, H.C., and Yang, M.H. (2012, January 16–21). Robust object tracking via sparsity-based collaborative model. Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI, USA.
5. Kalal, Z., Matas, J., and Mikolajczyk, K. (2010, January 13–18). P-n learning: Bootstrapping binary classifiers by structural constraints. Proceedings of the 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA.10.1109/CVPR.2010.5540231 ↗
6. Jia, X., Lu, H.C., and Yang, M.H. (2012, January 16–21). Visual tracking via adaptive structural local sparse appearance model. Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI, USA.
7. Wu, Y., Lim, J., and Yang, M. (2013, January 23–28). Online object tracking: A benchmark. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Portland, OR, USA.10.1109/CVPR.2013.312 ↗
8. Object tracking benchmark10.1109/TPAMI.2014.2388226 ↗
9. LIRIS, F. (2014, January 6–12). The visual object tracking vot2014 challenge results. Proceedings of the ECCV: European Conference on Computer Vision, Computer Vision—ECCV 2014 Workshops, Zurich, Switzerland.
10. Kristan, M., Leonardis, A., Matas, J., Felsberg, M., Pflugfelder, R., Cehovin, L., Vojir, T., Hager, G., Lukezic, A., and Fernandez, G. (15–16, January 8–10). The visual object tracking vot2016 challenge results. Proceedings of the Computer Vision—ECCV 2016 Workshops, Amsterdam, The Netherlands.
11. Galoogahi, H.K., Fagg, A., Huang, C., Ramanan, D., and Lucey, S. (2017, January 22–29). Need for speed: A benchmark for higher frame rate object tracking. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.10.1109/ICCV.2017.128 ↗
12. Milan, A., Leal-Taixé, L., Reid, I., Roth, S., and Schindler, K. (arXiv, 2016). MOT16: A benchmark for multi-object tracking, arXiv.
13. 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 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA.10.1109/CVPR.2010.5539960 ↗
14. Exploiting the circulant structure of tracking-by-detection with kernels10.1007/978-3-642-33765-9_50 ↗
15. High-speed tracking with kernelized correlation filters10.1109/TPAMI.2014.2345390 ↗
16. Li, Y., and Zhu, J.K. (2014, January 6–12). A scale adaptive kernel correlation filter tracker with feature integration. Proceedings of the European Conference on Computer Vision, Computer Vision—ECCV 2014 Workshops, Zurich, Switzerland.10.1007/978-3-319-16181-5_18 ↗
17. 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 ↗
18. Bertinetto, L., Valmadre, J., Golodetz, S., Miksik, O., and Torr, P.H.S. (July, January 26). Staple: Complementary learners for real-time tracking. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2016, Las Vegas, NV, USA.10.1109/CVPR.2016.156 ↗
19. Danelljan, M., Hager, G., Khan, F.S., and Felsberg, M. (2015, January 7–13). Learning spatially regularized correlation filters for visual tracking. Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV), Washington, DC, USA.10.1109/ICCV.2015.490 ↗
20. Mueller, M., Smith, N., and Ghanem, B. (2017, January 21–26). Context-aware correlation filter tracking. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017), Honolulu, HI, USA.10.1109/CVPR.2017.152 ↗
21. Galoogahi, H.K., Fagg, A., and Lucey, S. (2017, January 22–29). Learning background-aware correlation filters for visual tracking. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.10.1109/ICCV.2017.129 ↗
22. Visual tracking: An experimental survey10.1109/TPAMI.2013.230 ↗
23. Recent advances and trends in visual tracking: A review10.1016/j.neucom.2011.07.024 ↗
24. Visual tracking and recognition using appearance-adaptive models in particle filters10.1109/TIP.2004.836152 ↗
25. Lee, K.C., and Kriegman, D. (2005, January 20–25). Online learning of probabilistic appearance manifolds for video-based recognition and tracking. Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Diego, CA, USA.
26. Incremental learning for robust visual tracking10.1007/s11263-007-0075-7 ↗
27. Li, X., Hu, W.M., Zhang, Z.F., Zhang, X.Q., and Luo, G. (2007, January 14–21). Robust visual tracking based on incremental tensor subspace learning. Proceedings of the 2007 IEEE 11th International Conference on Computer Vision, Rio De Janeiro, Brazil.10.1109/ICCV.2007.4408950 ↗
28. Wen, J., Gao, X.B., Li, X.L., and Tao, D.C. (2009, January 11–14). Incremental learning of weighted tensor subspace for visual tracking. Proceedings of the 2009 IEEE International Conference on Systems, Man and Cybernetics, San Antonio, TX, USA.10.1109/ICSMC.2009.5346874 ↗
29. Zhang, K.H., Zhang, L., and Yang, M.H. (2012, January 7–13). Real-time compressive tracking. Proceedings of the Computer Vision—ECCV 2012, 12th European Conference on Computer Vision, Florence, Italy.10.1007/978-3-642-33712-3_62 ↗
30. Dinh, T.B., Vo, N., and Medioni, G. (2011, January 20–25). Context tracker: Exploring supporters and distracters in unconstrained environments. Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Colorado Springs, CO, USA.10.1109/CVPR.2011.5995733 ↗
31. Khattak, A.S., Raja, G., and Anjum, N. (2018). Adaptive framework for multi-feature hybrid object tracking. Appl. Sci., 8.10.3390/app8112294 ↗
32. Chen, Z., Hong, Z., and Tao, D. (arXiv, 2015). An experimental survey on correlation filter-based tracking, arXiv.
33. Danelljan, M., Khan, F.S., Felsberg, M., and van de Weijer, J. (2014, January 24–27). Adaptive color attributes for real-time visual tracking. Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, OH, USA.10.1109/CVPR.2014.143 ↗
34. Output constraint transfer for kernelized correlation filter in tracking10.1109/TSMC.2016.2629509 ↗
35. Li, C.B., and Yang, B. (2018). Robust scale adaptive visual tracking with correlation filters. Appl. Sci., 8.10.3390/app8112037 ↗
36. Danelljan, M., Hager, G., Khan, F.S., and Felsberg, M. (2015, January 7–13). Convolutional features for correlation filter based visual tracking. Proceedings of the 2015 IEEE International Conference on Computer Vision Workshop (ICCVW), Washington, DC, USA.10.1109/ICCVW.2015.84 ↗
37. Beyond correlation filters: Learning continuous convolution operators for visual tracking10.1007/978-3-319-46454-1_29 ↗
38. Xiao, J.J., Qiao, L.B., Stolkin, R., and Leonardis, A. (2016, January 11–14). Distractor-supported single target tracking in extremely cluttered scenes. Proceedings of the Computer Vision—ECCV 2016, 14th European Conference, Amsterdam, The Netherlands.10.1007/978-3-319-46493-0_8 ↗
39. Qie, C.G., Guo, G.J., Yan, Y., Zhang, L.M., and Wang, H.Z. (2018, January 20–24). Improved correlation filter tracking with hard negative mining. Proceedings of the 2018 24th International Conference on Pattern Recognition (ICPR), Beijing, China.10.1109/ICPR.2018.8545388 ↗
40. Jeong, S., and Paik, J. (2018). Partial block scheme and adaptive update model for kernelized correlation filters-based object tracking. Appl. Sci., 8.10.3390/app8081349 ↗
41. Sun, X., Cheung, N.M., Yao, H.X., and Guo, Y.L. (2017, January 22–29). Non-rigid object tracking via deformable patches using shape-preserved kcf and level sets. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.10.1109/ICCV.2017.586 ↗
42. Liu, S., Zhang, T.Z., Cao, X.C., and Xu, C.S. (July, January 26). Structural correlation filter for robust visual tracking. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2016, Las Vegas, NV, USA.10.1109/CVPR.2016.467 ↗
43. Deformable part-based tracking by coupled global and local correlation filters10.1016/j.jvcir.2016.04.018 ↗
44. Fan, H., and Xiang, J. (2017, January 4–9). Robust visual tracking via local-global correlation filter. Proceedings of the 2017 AAAI Conference on Artificial Intelligence, San Francisco, CA, USA.10.1609/aaai.v31i1.11207 ↗
45. Jeong, S.W., Kim, G.S., and Lee, S.K. (2017). Effective visual tracking using multi-block and scale space based on kernelized correlation filters. Sensors, 17.10.3390/s17030433 ↗
46. Ma, C., Yang, X.K., Zhang, C.Y.Y., and Yang, M.H. (2015, January 7–12). Long-term correlation tracking. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.10.1109/CVPR.2015.7299177 ↗
47. Toeplitz and circulant matrices: A review10.1561/0100000006 ↗
48. Davis, P.J. (2012). Circulant Matrices, American Mathematical Society.
49. Dalal, N., and Triggs, B. (2005, January 20–25). Histograms of oriented gradients for human detection. Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Diego, CA, USA.