Intelligent video surveillance, adaptive tracking of multiple moving objects is a key issue. The paper proposes a method based on the analysis of the sequence of video frames. Motion detection is performed by subtracting the background. Filtration of particles combined with etsya SIFT (scale invariant feature transformation) is used to track where the SIFT key points are used as part of particles to selectively improve. Then, the method of circuit-tiruetsya adapted to write data correspondences between different objects, which can improve the accuracy of detection and reduce the computational complexity. The system can monitor several of objects with higher performance. The method is resistant to mutual occlusion and can be used for intelligent video surveillance systems.
Видео слежение, вычитание фона, идентификация движения, SIFT, фильтрация частиц, Video tracking, background subtraction, the identification of traffic, SIFT, particles filtering
1. Belcher C, Du Y Region-based SIFT approach to iris recognition. Opt Lasers Eng 47 (1):139-147, (2009).
2. Lin MX, Xu XH Multiple object visual tracking from a moving object. In: Proc. the sixth international conference on intelligent systems design and applications, Jinan, China, vol.2, pp. 373-378, (2006).
3. Sun ZH, Zhu SA Real-time segmentation and tracking technique of multiple moving objects in video sequence. J Zhejiang Univ Eng Sci 42(9):1631-1635, (2008).
4. John L. Barron, David J. Fleet, and Steven Beauchemin.Performance of optical flow techniques IJCV 12/1 pp 43-77. (1994).
5. Kilger M A shadow handler in a video-based real-time traffic monitoring system. In: Proceedings of IEEE workshop on applications of computer vision, Palm Springs, California, USA, pp.11-18, (1992).
6. G. F. Savinov O nekotoryh osobennostyah algoritma optimal'noy fil'tracii Kalmana - B'yusi // Aviakosmicheskoe priborostroenie № 6, 2007 g.
7. Lee DS Effective Gaussian mixture learning for video background subtraction. IEEE Trans Pattern Anal Mach Intell 27(5):827-832, (2005).
8. Gupte S, Masoud O, Martin RFK, Papanikolopoulos NP IEEE Transactions on Intelligent Transportation Systems 3(1):37-47, (2002).
9. Nunes E., Conci A., Sanchez A. () Robust Background Subtraction on Traffic Videos Systems, Signals and Image Processing., pp. 1-4, (2011).
10. Yang J, Zhao ZM Shadow processing method based on normalized RGB color model. OptoElectron Eng 34(12):92-96, (2007).
11. M. Shehata, M. Pervez, T. Burr, J. Cai, W. Badawy, A. Radmanesh On eliminating static shadow false alarms in automatic incident detection systems. In: Proceedings of the IEEE Intelligent Transportation Systems Conference, Toronto, 2006, pp.759-764. (2006).
12. Comaniciu, Dorin; Peter Meer. "Mean Shift: A Robust Approach Toward Feature Space Analysis". IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE)24 (5): 603-619. (2002).
13. Comaniciu D, Ramesh V, Meer P Kernel-based object tracking. IEEE Trans Pattern Anal Mach Intell 25(5):564-577 (2003).
14. Arulampalam S, Maskell S, Gordon N, Clapp T A tutorial on particle filters for on-line nonlinear/nongaussian bayesian tracking. IEEE Trans Signal Process 50(2):174-188, (2002).
15. Breitenstein MD, Reichlin F, Leibe B, Koller-Meier E, Gool LV Robust tracking-by-detection using a detector confidence particle filter. In: Proceedings of IEEE International Conference on Computer Vision, Kyoto, Japan, 1515-1522, (2009).
16. Fazli S, Pour HM, Bouzari H “Particle Filter Based Object Tracking with Sift and Color Feature,” Second International Conference on Machine Vision, pp. 89-93, (2009).
17. Aun S. Informacionno-izmeritel'naya sistema slezheniya za dvizhuschimisya ob'ektami / S. Aun, L.M. Sharnin, A.P. Kirpichnikov // VESTNIK Kazanskogo tehnologicheskogo universiteta. - Kazan': KNITU, 2011. - T. 14. №16. - S. 224-232.
18. Wu P, Kong LF, Zhao F, Li X. Particle filter tracking based on color and SIFT features. In: Proceedings of international conference on audio, language and image processing, pp. 932-937, (2008).
19. Comaniciu D, Meer P Mean Shift: a robust approach toward feature space analysis. IEEE Trans Pattern Anal Mach Intell 24(5):603-619, (2002).
20. Mokshin V.V., Yakimov I.M. Metod formirovaniya modeli analiza slozhnoy sistemy / Informacionnye tehnologii, №5. - M.: Izd-vo Novye tehnologii, 2011. - S. 46-51.
21. Lowe, D. G., “Distinctive Image Features from Scale-Invariant Keypoints”, International Journal of Computer Vision, 60, 2, pp. 91-110, (2004).
22. Gao T, Liu ZG, Zhang J Redundant discrete wavelet transforms based moving object recognition and tracking. J Syst Eng Electron 20(5):1115-1123, (2009).
23. Djouadi, A.; Snorrason, O.; Garber, F. "The quality of Training-Sample estimates of the Bhattacharyya coefficient". IEEE Transactions on Pattern Analysis and Machine Intelligence 12 (1): 92-97, (1990).
24. Tao Gao & Guo Li & Shiguo Lian & Jun Zhang / Tracking video objects with feature points based particle filtering Multimedia Tools and Applications May 2012, Volume 58, Issue 1, pp 1-21
