OBJECT TRACKING VIA COMPARISON OF COLOR HISTOGRAMS
Abstract
Three versions of a histogram algorithm for tracking objects on video sequences made by an unstable camera are presented. Local color 1D-histograms of pixels and local color 2D-histograms of pairs of adjacent pixels are used in all versions as region features. The histograms are compared by the Bhattacharia criterion. А parallel computing platform CUDA, developed to program GPUs, allows creation of real time or near-real time program realizations of the offered versions. Results of comparison of the versions with the known mean shift algorithm and correlation type algorithms are also presented. It is shown by experiments that the versions are more accurate and reliable than the mean shift algorithm, which estimates similarity of linear approximations of local histograms, and more robust with respect to the video quality than the correlation algorithms.
About the Authors
B. A. Zalesky
Объединенный институт проблем информатики НАН Беларуси
Belarus
Belarus
E. N. Seredin
Объединенный институт проблем информатики НАН Беларуси
Belarus
Belarus
M. V. Yadlouski
Объединенный институт проблем информатики НАН Беларуси
Belarus
Belarus
References
1. Cheng, Y. Mean shift, mode seeking, and clustering / Y. Cheng // IEEE Trans. on Pattern Analysis and Machine Intelligence. – 1998. – № 17(8). – P. 790–799.
2. Yilmaz, A. Object tracking: A survey / A. Yilmaz, O. Javed, M. Shah // ACM Computing Surveys. – 2006. – Vol. 38, № 4. – 45 р.
3. Marimon, D. Orientation histogram-based matching for region tracking / D. Marimon, T. Ebrahimi // Proc. 8th Intern. Workshop on Image Analysis for Multimedia Interactive Services WIAMIS. – Santorini, 2007. – P. 8–12.
4. Lowe, D. Object recognition from local scale invariant features / D. Lowe // Proc. Intern. Conf. on Computer Vision ICCV. – Corfu, 1999. – P. 1150–1157.5. Bay, H. Surf: Speeded up robust features / H. Bay, T. Tuytelaars, L. Van Gool // Proc. 9th Europ. Conf. on Computer Vision ECCV. – Graz, 2006. – P. 404–417.
5. Altmann, J. A Fast Correlation Method for Scale-and Translation-Invariant Pattern Recognition / J. Altmann, H.J. Reitböck // IEEE Trans. Pattern Anal. Mach. Intell. – 1984. – Vol. 6, № 1. – P. 46–57.
6. Object Tracking by Particle Filtering Techniques in Video Sequences / L. Mihaylova [et al.] // Advances and Challenges in Multisensor Data and Information. NATO Security Through Science Series. – Netherlands : IOS Press, 2007. – P. 260–268.
7. Haralick, R.M. Textural Features for Image Classification / R.M. Haralick, K. Shanmugam, I. Dinstein // IEEE Transactions on Systems, Man, and Cybernetics. – 1973. – № 6. – P. 610–621.
8. Comaniciu, D. Real-Time Tracking of Non-Rigid Objects using Mean Shift // D. Comaniciu, V. Ramesh, P. Meer // Proc. IEEE Conf. on Computer Vision and Pattern Recognition, CVPR. – Hilton Head Island, 2000. – Vol. 2. – P. 142–149.
9. Афифи, А. Статистический анализ / А. Афифи, С. Эйзен. – М. : Мир, 1982. – 488 с.
10. Zalesky, B.A. Real Time Object Tracking Algorithm / B.A. Zalesky, E.N. Seredin // Intern. Congress on Computer Science: Information Systems and Technologies, CSIST 2013. – Minsk, 2013. – P. 500–504.
Review
For citations:
Zalesky B.A., Seredin E.N., Yadlouski M.V. OBJECT TRACKING VIA COMPARISON OF COLOR HISTOGRAMS. Informatics. 2015;(2):22-30. (In Russ.)
Views: 845
Email this article 