Partial Block Scheme and Adaptive Update Model for Kernelized Correlation Filters-Based Object Tracking
Source abstract
Abstract
In visual object tracking, the dynamic environment is a challenging issue. Partial occlusion and scale variation are typical challenging problems. We present a correlation-based object tracking based on the discriminative model. To attenuate the influence by partial occlusion, partial sub-blocks are constructed from the original block, and each of them operates independently. The scale space is employed to deal with scale variation using a feature pyramid. We also present an adaptive update model with a weighting function to calculate the frame-adaptive learning rate. Theoretical analysis and experimental results demonstrate that the proposed method can robustly track drastic deformed objects. The sparse update reduces the computational cost for real-time tracking. Although the partial block scheme generation increases the computational cost, we present a novel sparse update approach to reduce the computational cost drastically for real-time tracking. The experiments were performed on a variety of sequences, and the proposed method exhibited better performance compared with the state-of-the-art trackers.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Video Surveillance and Tracking Methods · Advanced Vision and Imaging · Human Pose and Action Recognition
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Image, Chung-Ang University, Seoul 06974, Korea
Funding
Institute for Information and communications Technology Promotion
References (40)
Show source-provided references
1. Ensemble tracking10.1109/TPAMI.2007.35 ↗
2. Grabner, H., Grabner, M., and Bischof, H. (2006, January 4–7). Real-time tracking via on-line boosting. Proceedings of the British Machine Vision Conference (BMVC), Edinburgh, UK.10.5244/C.20.6 ↗
3. Saffari, A., Leistner, C., Santner, J., Godec, M., and Bischof, H. (October, January 27). On-line random forests. Proceedings of the 3rd IEEE ICCV Workshop on On-line Computer Vision, Kyoto, Japan.
4. Support vector tracking10.1109/TPAMI.2004.53 ↗
5. Hare, S., Saffari, A., and Torr, P. (2011, January 6–13). Struck: Structured output tracking with kernels. Proceedings of the IEEE Conference on Computer Vision (ICCV), Barcelona, Spain.10.1109/ICCV.2011.6126251 ↗
6. Robust object tracking with online multiple instance learning10.1109/TPAMI.2010.226 ↗
7. Real-time visual tracking via online weighted multiple instance learning10.1016/j.patcog.2012.07.013 ↗
8. Zhang, K., Zhang, L., and Yang, M.-H. (2012, January 7–13). Real-time compressive tracking. Proceedings of the European Conference on Computer Vision (ECCV), Florence, Italy.10.1007/978-3-642-33712-3_62 ↗
9. Tracking-learning-detection10.1109/TPAMI.2011.239 ↗
10. Online selection of discriminative tracking features10.1109/TPAMI.2005.205 ↗
11. Incremental learning for robust visual tracking10.1007/s11263-007-0075-7 ↗
12. Wang, D., and Lu, H. (2014, January 23–28). Visual tracking via probability continuous outlier model. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, OH, USA.10.1109/CVPR.2014.445 ↗
13. Kwon, J., and Lee, K.M. (2010, January 13–18). Visual tracking decomposition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), San Francisco, CA, USA.10.1109/CVPR.2010.5539821 ↗
14. Mei, X., and Ling, H. (October, January 27). Robust visual tracking using L1 minimization. Proceedings of the IEEE Conference on Computer Vision (ICCV), Kyoto, Japan.
15. Adam, A., Rivlin, E., and Shimshoni, I. (2006, January 17–22). Robust fragments-based tracking using the integral histogram. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), New York, NY, USA.
16. Zhang, T., Bibi, A., and Ghanem, B. (2016, January 21–26). In defense of sparse tracking: Circulant sparse tracker. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2016.421 ↗
17. Zhang, T., Ghanem, B., Liu, S., and Ahuja, N. (2012, January 16–24). Robust visual tracking via multi-task sparse learning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI, USA.
18. Zhang, T., Ghanem, B., Liu, S., and Ahuja, N. (2012, January 7–13). Low-rank sparse learning for robust visual tracking. Proceedings of the European Conference on Computer Vision (ECCV), Florence, Italy.10.1007/978-3-642-33783-3_34 ↗
19. 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 (CVPR), San Francisco, CA, USA.10.1109/CVPR.2010.5539960 ↗
20. 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 European Conference on Computer Vision (ECCV), Florence, Italy.10.1007/978-3-642-33765-9_50 ↗
21. High-speed tracking with kernelized correlation filters10.1109/TPAMI.2014.2345390 ↗
22. Danelljan, M., Hager, 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 ↗
23. Danelljan, M., Khan, F.S., Felsberg, M., and van de Weijer, J. (2014, January 23–28). Adaptive color attributes for real-time visual tracking. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, OH, USA.10.1109/CVPR.2014.143 ↗
24. Shu, G., Dehghan, A., Oreifej, O., Hand, E., and Shah, M. (2012, January 16–24). Part-based multiple-person tracking with partial occlusion handling. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI, USA.
25. Akin, O., and Mikolajczyk, K. (2014, January 24). Online Learning and Detection with Part-based Circulant Structure. Proceedings of the IEEE International Conference on Pattern Recognition (ICPR), Stockholm, Sweden.10.1109/ICPR.2014.725 ↗
26. Exploiting Spatial Structure from Parts for Adaptive Kernelized Correlation Filter Tracker10.1109/LSP.2016.2545705 ↗
27. Zhang, T., Jia, K., Xu, C., Ma, Y., and Ahuja, N. (2014, January 23–28). Partial occlusion handling for visual tracking via robust part matching. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, OH, USA.10.1109/CVPR.2014.164 ↗
28. Bertinetto, L., Valmadre, J., Golodetz, S., Miksik, O., and Torr, P.H.S. (2016, January 21–26). Staple: Complementary Learners for Real-Time Tracking. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2016.156 ↗
29. Danelljan, M., Hager, G., Khan, F.S., and Felsberg, M. (2015, January 11–18). Learning spatially regularized correlation filters for visual tracking. Proceedings of the IEEE Conference on Computer Vision (ICCV), Santiago, Chile.10.1109/ICCV.2015.490 ↗
30. Li, Y., and Zhu, J. (2014, January 6–12). A scale adaptive kernel correlation filter tracker with feature integration. Proceedings of the European Conference on Computer Vision (ECCV), Zurich, Switzerland.10.1007/978-3-319-16181-5_18 ↗
31. Ruan, Y., and Wei, Z. (2016). Real-Time Visual Tracking through Fusion Features. Sensors, 16.10.3390/s16070949 ↗
32. Grabner, H., Leistner, C., and Bischof, H. (2008, January 12–18). Semi-supervised on-line boosting for robust tracking. Proceedings of the European Conference on Computer Vision (ECCV), Marseille, France.10.1007/978-3-540-88682-2_19 ↗
33. Zhong, W., Lu, H., and Yang, Mi. (2012, January 16–24). Robust object tracking via sparsity-based collaborative model. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI, USA.
34. Jia, X., Lu, H., and Yang, Mi. (2012, January 16–24). Visual tracking via adaptive structural local sparse appearance model. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI, USA.
35. Sevilla-Lara, L., and Learned-Miller, E.G. (2012, January 16–24). Distribution fields for tracking. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI, USA.10.1109/CVPR.2012.6247891 ↗
36. Oron, S., Bar-Hillel, A., Levi, D., and Avidan, S. (2012, January 16–24). Locally orderless tracking. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI, USA.10.1109/CVPR.2012.6247895 ↗
37. He, S., Yang, Q., Lau, R., Wang, J., and Yang, Mi. (2013, January 23–28). Visual tracking via locality sensitive histograms. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Portland, OR, USA.10.1109/CVPR.2013.314 ↗
38. Scholkopf, B., and Smola, A. (2002). Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond, The MIT Press.10.7551/mitpress/4175.001.0001 ↗
39. 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 ↗
40. Object detection with discriminatively trained part-based models10.1109/TPAMI.2009.167 ↗