Reverse Validation Based Adaptive Particle Filter Algorithm for Object Tracking

Abstract:

To improves tracking drift which often occurs in adaptive tracking, an algorithm based on the fusion of tracking and detection is proposed in this paper. Firstly, tracking object frame by frame via color histogram and particle filtering. Secondly, reversely validating the tracking result based on particle filtering. Finally, relocating the object based on SIFT features matching and voting when drift occurs. Object appearance model is updated at the same time. The algorithm can not only sense tracking drift but also relocate the object whenever needed. Experimental results demonstrate that this algorithm outperforms state-of-the-art algorithms on many challenging sequences.

• Periodical: Advanced Materials Research (Volumes 1044-1045)
• Pages: 1302-1308
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.1044-1045.1302
• Online since: October 2014
• Authors: Shao Mei Li*, Kai Wang, Chao Gao, Ya Wen Wang
• Keywords: Object Tracking, Particle Filter, Reverse Validation

References

[1] A. Adam, E. Rivlin, and I. Shimshoni. Robust fragmentsbased tracking using the integral histogram. In CVPR, (2006).

DOI: 10.1109/cvpr.2006.256

[2] S. M. Shahed Nejhum, J. Ho, and M. -H. Yang. Visual tracking with histograms and articulating blocks. In CVPR, (2008).

DOI: 10.1109/cvpr.2008.4587575

[3] G. Hua and Y. Wu. Measurement integration under inconsistency for robust tracking. In CVPR, (2006).

[4] L. Zhang and L. van der Maaten. Structure preserving object tracking. In CVPR, (2013).

[5] Z. Kalal, K. Mikolajczyk, and J. Matas. Tracking-Learning-detection. TPAMI, 34(7), (2012).

[6] E. Rosten, R. Porter, and T. Drummond. Faster and better: A machine learning approach to corner detection. TPAMI, 32(1), (2010).

[7] S. Leutenegger, M. Chli, and R. Y. Siegwart. BRISK: Binary robust invariant scalable keypoints. In ICCV, (2011).

DOI: 10.1109/iccv.2011.6126542

[8] N. Georg, P. Roman. Consensus-based Matching and Tracking of Keypoints for Object Tracking. http: /www. gnebehay. com/cmt.

[9] Z. Kalal, J. Matas, and K. Mikolajczyk. Online learning of robust object detectors during unstable tracking. In Proceedings of the IEEE On-line Learning for Computer Vision Workshop, (2009).

DOI: 10.1109/iccvw.2009.5457446

[10] Z. Kalal, J. Matas, and K. Mikolajczyk. P-N learning: Bootstrapping binary classifiers by structural constraints. In 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June (2010).

DOI: 10.1109/cvpr.2010.5540231

[11] Z. Kalal, K. Mikolajczyk, and J. Matas. Forward-Backward Error: Automatic Detection of Tracking Failures. In International Conference on Pattern Recognition, (2010).

DOI: 10.1109/icpr.2010.675

[12] Yang C J, Duraiswami R, Davis L. Fast multiple object tracking via a hierarchical particle filter[C]. Proceedings of the Tenth IEEE International Conference on Computer Vision. Piscataway, NJ, USA: IEEE, (2005).

DOI: 10.1109/iccv.2005.95

[13] Hammersley J M. Monte Carlo Methods[M]. New York: Methuen's Monographs, (1964).

[12] R. Rosipal and N. Kramer. Overview and recent advances in partial least squares[M]. in Latent Structures Feature Selection. New York: Springer-Verlag, (2006).

[13] H. Wold. Partial least squares[M]. in Encyclopedia of Statistical Science, vol. 6, S. Kotz and N. L. Johnson, Eds. New York: Wiley, (1985).

[14] Q. Wang, F. Chen,W. -L. Xu, and M. -H. Yang. Object Tracking via Partial Least Squares Analysis[J]. IEEE Transaction on Image Processing, (2012).

[15] D. Lowe. Distinctive image features from scale-invariant keypoints. IJCV, (2004).

[16] Ming Li, Liuqing Yuan, Wenxiadu, An Adaptive Motion Model and Multi-feature Cues Based on Particle Filter for Object Tracking. JOURNAL OF MULTIMEDIA, 7(5), (2012).

DOI: 10.4304/jmm.7.5.364-371

[17] M. Everingham, L. V. Gool, C. Williams, J. Winn, and A. Zisserman. The pascal visual object classes (VOC) challenge[J]. International Journal of Computer Vision[J], (2010).

DOI: 10.1007/s11263-009-0275-4

[18] S. Hare, A. Saffari, and P. H. S. Torr. Struck: Structured Output Tracking with Kernels[C]. Proceedings of the IEEE International Conference on Computer Vision, Barcelona, Spain, (2011).

DOI: 10.1109/iccv.2011.6126251