IMPLEMENTATION OF OBJECT TRACKING ALGORITHMS ON THE BASIS OF CUDA TECHNOLOGY
Abstract
A fast version of correlation algorithm to track objects on video-sequences made by a nonstabilized camcorder is presented. The algorithm is based on comparison of local correlations of the object image and regions of video-frames. The algorithm is implemented in programming technology CUDA. Application of CUDA allowed to attain real time execution of the algorithm. To improve its precision and stability, a robust version of the Kalman filter has been incorporated into the flowchart. Tests showed applicability of the algorithm to practical object tracking.
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
References
1. Yilmaz, A. Object tracking: A survey / A. Yilmaz, O. Javed, M. Shah // ACM Computing Surveys. – 2006. – Vol. 38, № 4.
2. Marimon, D. Orientation histogram-based matching for region tracking / D. Marimon, T. Ebrahimi // Proc. 8th Int. Workshop on Image Analysis for Multimedia Interactive Services WIAMIS. – Santorini, 2007. – P. 8–12.
3. Lowe, D. Object recognition from local scale invariant features / D. Lowe // Proc. Int. Conf. on Computer Vision ICCV. – Corfu, 1999. – P. 1150–1157.
4. Bay, H. Surf: Speeded up robust features / H. Bay, T. Tuytelaars, L. Van Gool // Proc. 9th Europ. Proc. 8th Int. 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. Simon. D. Optimal State Estimation. Kalman, H∞, and Nonlinear Approaches / D. Simon. – New Jersey : John Wiley & Sons, 2006. – 526 p.
8. Сандерс, Дж. Технология CUDA в примерах: введение в программирование графических процессоров / Дж. Сандерс, Э. Кэндрот. – М. : ДМК Пресс, 2011. – 232 с.
9. Боресков, А.В. Основы работы с технологией CUDA / А.В. Боресков, А.А. Харламов. – М. : ДМК Пресс, 2010. – 232 с.
10. Zalesky, B.A. Scale invariant algorithm to match regions on aero and satellite images /B.A. Zalesky, P.V. Lukashevich // Proc. 11th Int. Conf. on Pattern recognition and information processing PRIP 2011. – Minsk, 2011. – P. 25–31.
Review
For citations:
Zalesky B.A., Seredin E.N. IMPLEMENTATION OF OBJECT TRACKING ALGORITHMS ON THE BASIS OF CUDA TECHNOLOGY. Informatics. 2014;(1):77-84. (In Russ.)
Views: 806
Email this article 