Research of ASM Object Tracking Method Combining Kalman Estimation

Abstract:

ASM is a statistical model applied to match contours of non-rigid object. The actual contour may much different from the initial contour and the result is likely to converge to an error contour. Kalman filter is adopted to track the current frame for the prediction and acts as the initial state of the ASM, and then applies the ASM to correct the contour of the object. Experimental results show that the method proposed in this paper allows the model to converge to the target contour quickly and accurately. It has good stability and robustness.

• Periodical: Advanced Materials Research (Volumes 1049-1050)
• Pages: 1595-1598
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.1049-1050.1595
• Online since: October 2014
• Authors: Li Guo Zhang, Mei Jin, Ju Jin, Guo Hui Yu
• Keywords: Active Shape Model, Initial Localization, Kalman Filter, Position Estimation

References

[1] Y. Fu,A.T. Erdem A.M. Tekalp, Tracking visible boundary of objects using occlusion adaptive motion snake[J], IEEE Trans. Image Process. 2009, (12): 2051-(2060).

DOI: 10.1109/83.887973

[2] N. Peterfreund, Robust tracking of position and velocity with Kalman snakes[J]. IEEE Trans. Pattern Anal. Mach. Intell. 1999, 21(6): 564–569.

DOI: 10.1109/34.771328

[3] Terzopoulos D., Szeliski R. Tracking with kalman snakes[M]. In Blake A. and Yuille A., editors, Active Vision, chapter 1, pages 3-20. MIT Press, (1992).

[4] Coots T F. Taylor CJ, Lanitis A. Multi-resolution search with active shape models[c]Proceedings of the 12th International Corlference on Pattern Recognition, Manchester, 1994, 1: 610-612.

DOI: 10.1109/icpr.1994.576375

[5] Rudy N, Robot localization and Kalman filter Dutch Utrecht University. 2003.