Correlogram-Based Perceptual Similarity in Vehicle Probabilistic Tracking

Abstract:

This paper addresses the problem of dissimilarity measurement and incorporates an auto-correlogram operator into probabilistic tracking. Perceptual similarity measurement based upon color correlogram is proposed to weigh the candidates and obtain the expectation state vector of tracked vehicles. The object color is represented in perceptually better-organized HSV color space, which produced improvement over the original method that used in the RGB color space. Properly quantized HSV color space improved the efficiency of auto-correlogram computation and robustness to changes in color content and variations in illumination. Experimental results demonstrate that the efficiency of HSV color correlogram in weighing samples is better than that of RGB auto-correlogram and HSV color histogram in traffic scene applications.

• Periodical: Applied Mechanics and Materials (Volumes 121-126)
• Pages: 3860-3864
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.121-126.3860
• Online since: October 2011
• Authors: Yan Fen Mao, Ming Chen
• Keywords: Color Correlogram, Image Processing Application, Particle Filtering, Perceptual Similarity Measure, Probabilistic Tracking

References

[1] S. Santini, R. Jain: Similarity Measures, IEEE Trans. Pattern Analysis and Machine Intelligence, 21( 9): 871-883, (1999).

DOI: 10.1109/34.790428

[2] A. Loza, L. Mihaylova, N. Canagarajah, D. Bull: Structural similarity-based object tracking in video sequence. The 9th International Conference on Information Fusion, 10-13, (2006).

DOI: 10.1109/icif.2006.301574

[3] K. Nummiaro, K.E. Merier, V.L. Gool: An adaptive color-based particle filter. Image and Vision Computing, 21(1), 99-110, (2003).

DOI: 10.1016/s0262-8856(02)00129-4

[4] B.E. Meier, F. Ade: Using the condensation algorithm to implement tracking for mobile robots. European Conference on Computer Vision. Zurich, Switzerland, 73-80, (1999).

DOI: 10.1109/eurbot.1999.827624

[5] P. Pérez, C. Hue, J. Vermaak, et al.: Color-based probabilistic tracking. The 7th European Conference on Computer Vision-Part I. London, UK: Springer-Verlag, 661-675, (2002).

DOI: 10.1007/3-540-47969-4_44

[6] J. Huang: Color-spatial image indexing and application. Cornell University, (1998).

[7] Y. Tsai, A. Chen, K. Essig: Efficient image retrieval approaches for different similarity requirements. IS&T/SPIE's 12th Annual International Symposium Electronic Imaging 2000 Science & Technology. San Jose, USA, 471-482, (2000).

[8] P. Pérez, J. Vermaak, A. Blake: Data fusion for tracking with particles. Proceedings of the IEEE, 92(3): 495-513, (2004).

DOI: 10.1109/jproc.2003.823147

[9] N.J. Gordon, D.J. Salmon, A.F.M. Smith, Novel approach to nonlinear/non-Gaussian Bayesian state estimation, IEE Proceedings-F, 140(2): 107-113, (1993).

DOI: 10.1049/ip-f-2.1993.0015

[10] M. Isard, A. Blake: Condensation–conditional density propagation for visual tracking. International Journal of Computer Vision. 29(1): 5-28, (1998).