ABSTRACT
Recently, Discriminative Correlation Filter based trackers have increasingly become popular in the domain of visual object tracking, which is benefited by their effective and robustness in terms of tracking performance. However, the significant variations of target appearance, such as Occlusion or Deformation, always suppress the performance improvement. Although the multi-feature fusion strategy partly alleviates the above factors, the synthetic scheme also ambiguates the overall presentation ability of multiple features and results in degradation of discriminative power during classification filter learning. In this paper, we present a novel tracking framework based on the correlation filter with multiple kernel learning. Instead of directly integrating different features, we decompose a tracking process into several module, including low-dimension modules and high-dimension modules. The handcraft features extracted from low-dimension modules are robust to the small variation of target while the semantic convolutional features from the high-dimension modules can distinguish the target object from the relative complex tracking environment. In addition, we also design a reliability detection mechanism based on the confidence map to accurately measure the important degree of each kernel learning and precisely estimate the target state in the subsequent frames. For verifying our proposed tracker, we conduct extensive experiments on several standard sequence benchmark. Experiment results show that our proposed trackers perform favorably against other state-of-the-art trackers.
- G. Wu, and W. Kang. 2017. Vision-based fingertip tracking utilizing curvature points clustering and hash model representation. IEEE Transactions on Multimedia, Vol. 19, No. 8, pp. 1730-1741.Google ScholarDigital Library
- T. Guan, and C. Wang. 2009. Registration based on scene recognition and natural features tracking techniques for wide-area augmented reality systems, IEEE Transactions on Multimedia, Vol. 11, No. 8, pp. 1393-1406.Google ScholarDigital Library
- K.-H. Lee, and J.-N. Hwang. 2015. On-road pedestrian tracking across multiple driving recorders. IEEE Transactions on Multimedia. Vol. 17, No. 9, pp. 1429-1438.Google ScholarDigital Library
- D. S. Bolme, J. R. Beveridge, B. A. Draper, and Y. M. Lui. 2010. Visual Object Tracking Using Adaptive Correlation Filters. In 2010 IEEE computer society conference on computer vision and pattern recognition, pp. 2544-2550.Google Scholar
- J. F. Henriques, R. Caseiro, P. Martins, and J. Batista. 2015. High-speed Tracking with Kernelized Correlation Filters. IEEE Transactions on Pattern Analysis and Machine Intelligence. Vol. 37, No. 3, pp. 583-596.Google ScholarDigital Library
- A. Krizhevsky, I. Sutskever, and G. E. Hinton. 2012. Imagenet classification with deep conVolutional neural networks. Advances in neural information processing systems. Vol. 25, pp. 1097-1105.Google Scholar
- C. Ma, J.-B. Huang, X. Yang, and M.-H. Yang. 2015. Hierarchical conVolutional features for visual tracking. In Proceedings of the IEEE international conference on computer vision. pp. 3074-3082.Google ScholarDigital Library
- C. Ma, J.-B. Huang, X. Yang, and M.-H. Yang. 2018. Robust visual tracking via hierarchical conVolutional features. IEEE transactions on pattern analysis and machine intelligence. Vol. 41, No. 11, pp. 2709-2723.Google Scholar
- L. Bertinetto, J. Valmadre, J. F. Henriques, A. Vedaldi, and P. H. Torr. 2016. Fully-conVolutional siamese networks for object tracking. In European conference on computer vision. pp. 850-8657.Google Scholar
- J. Valmadre, L. Bertinetto, J. Henriques, A. Vedaldi, and P. H. Torr. 2017. 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.Google Scholar
- M. Tang, B. Yu, F. Zhang, and J. Wang. 2018. High-speed tracking with multi-kernel correlation filters. In Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 4874-4883.Google Scholar
- M. Gönen, and E. Alpaydın. 2011. Multiple kernel learning algorithms. Journal of machine learning research. Vol. 12, No. 7, pp. 2211-2268.Google ScholarDigital Library
- A. Bibi, and B. Ghanem. 2015. Multi-template Scale-Adaptive Kernelized Correlation Filters. In Proceedings of the IEEE International Conference on Computer Vision Workshops. pp. 613-620.Google Scholar
- J. F. Henriques, R. Caseiro, P. Martins, and J. Batista. 2012. Exploiting the Circulant Structure of Tracking-by-Detection with Kernels. ECCV. pp. 702-715.Google Scholar
- M. Danelljan, G. Hager, F. S. Khan, and M. Felsberg. 2016. Discriminative Scale Space Tracking. IEEE Transactions on Pattern Analysis & Machine Intelligence. Vol. 39, No. 8, pp. 1561-1575.Google ScholarDigital Library
- M. Danelljan, G. Hager, F. Shahbaz Khan, and M. Felsberg. 2015. Learning spatially regularized correlation filters for visual tracking. In Proceedings of the IEEE international conference on computer vision. pp. 4310-4318.Google Scholar
- M. Danelljan, F. S. Khan, M. Felsberg, and J. V. D. Weijer. 2014. Adaptive Color Attributes for Real-time Visual Tracking. In Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 1090-1097.Google ScholarDigital Library
- L. Bertinetto, J. Valmadre, S. Golodetz, O. Miksik, and P. H. S. Torr. 2016. Staple: Complementary Learners for Real-Time Tracking. In Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 1401-1409.Google ScholarCross Ref
- M. Mueller, N. Smith, and B. Ghanem. 2017. Context-Aware Correlation Filter Tracking. In Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 1396-1404.Google Scholar
- H. K. Galoogahi, A. Fagg, and S. Lucey. 2017. Learning Background-aware Correlation Filters for Visual Tracking. In Proceedings of the IEEE international conference on computer vision. pp. 1135-1143.Google Scholar
- M. Danelljan, G. Hager, F. Shahbaz Khan, and M. Felsberg. 2015. ConVolutional features for correlation filter based visual tracking. In Proceedings of the IEEE international conference on computer vision workshops. pp. 58-66.Google Scholar
- M. Wang, Y. Liu, and Z. Huang. 2017. Large margin object tracking with circulant feature maps. In Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 4021-4029.Google Scholar
- R. Rifkin, G. Yeo, and T. Poggio. 2003. Regularized least-squares classification. Nato Science Series Sub Series III Computer and Systems Sciences. Vol. 190, pp. 131-154.Google Scholar
- H.-C. Choi, and S.-Y. Oh. 2012. Robust segment-based object tracking using generalized hyperplane approximation. Pattern Recognition. Vol. 45, No. 8, pp. 2980-2991.Google ScholarDigital Library
- Y. Wu, J. Lim, and M.-H. Yang. 2013. Online object tracking: A benchmark. In Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 2411-2418.Google ScholarDigital Library
- Y. Wu, J. Lim, and M. H. Yang. 2015. Object Tracking Benchmark. IEEE Transactions on Pattern Analysis & Machine Intelligence. Vol. 37, No. 9, pp. 1834-1848.Google ScholarDigital Library
- P. Liang, E. Blasch, and H. Ling. 2015. Encoding color information for visual tracking: Algorithms and benchmark. IEEE Transactions on Image Processing. Vol. 24, No. 12, pp. 5630-5644.Google ScholarDigital Library
- M. Tang, and J. Feng. 2015. Multi-kernel correlation filter for visual tracking. In Proceedings of the IEEE international conference on computer vision. pp. 3038-3046.Google Scholar
- A. Vedaldi, and K. Lenc. 2015. Matconvnet: ConVolutional neural networks for matlab. In Proceedings of the 23rd ACM international conference on Multimedia. pp. 689-692.Google Scholar
- Chin-Shiuh Shieh, Yong-Shixa Jhan, Yuan-Li Liu, Mong-Fong Horng and Tsair-Fwu Lee. 2018. Video Object Tracking with Heuristic Optimization Methods, Journal of Image and Graphics, Vol. 6, No. 2, pp. 95-99.Google ScholarCross Ref
- Aggregating Correlation Filter with Multiple Kernels Learning for Robust Visual Object Tracking
Recommendations
Robust Correlation Filter Tracking with Shepherded Instance-Aware Proposals
MM '18: Proceedings of the 26th ACM international conference on MultimediaIn recent years, convolutional neural network (CNN) based correlation filter trackers have achieved state-of-the-art results on the benchmark datasets. However, the CNN based correlation filters cannot effectively handle large scale variation and ...
A multiple feature fused model for visual object tracking via correlation filters
AbstractCommon tracking algorithms only use a single feature to describe the target appearance, which makes the appearance model easily disturbed by noise. Furthermore, the tracking performance and robustness of these trackers are obviously limited. In ...
Coupling deep correlation filter and online discriminative learning for visual object tracking
Advances in mathematical models and optimization introduce powerful tools for solving the visual object tracking problem, but this fundamental problem remains unsolved due to various challenges such as illumination variation, deformation and occlusion. ...
Comments