An Improved Representation for Object Tracking Algorithm

Abstract:

Aiming at the shortcoming of feature space representation in traditional mean shift, we propose an improved object tracking method. At first, the target model region is segmented into overlapped square, and their histograms are computed. Then, the feature space is constituted which has introduced spatial information into. So the accuracy is enhanced. After computing the feature space of target candidate region, the mean shift is employed to find the new target location. The result shows that the improved method can track the object more robust, accurately and quickly.

• Periodical: Applied Mechanics and Materials (Volumes 16-19)
• Pages: 1020-1024
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.16-19.1020
• Online since: October 2009
• Authors: Yu Ming Gu, Jie Liu, Kuo Liu, Zhao Yao
• Keywords: Color Space, Feature Space Representation, Object Tracking, Real-Time Tracking

References

[1] D. Comaniciu, V. Ramesh and P. Meer: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Vol. 2 (2000), pp.142-149.

[2] D. Xu, Y. Wang and J. An: In Proceedings of the Image and Vision Computing New Zealand (IVCNZ'05), University of Otago, Dunedin, New Zealand, November, (2005).

DOI: 10.26473/atlaanz.2015.1.1/001

[3] H.A. Kwang and J.C. Myjung: The 3rd International Conference on Ubiquitous Robots and Ambient Intelligence, Seoul, Korea, 2006, pp.15-17.

[4] A.B. Rao, R. K Srihari and Z.F. Zhang: 11th IEEE International Conference on Tools with Artificial Intelligence, 1999, pp.183-186.

[5] S.D. Birchfield and S. Rangarajan: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Vol. 2 (2005), pp.1158-1163.

[6] M.J. Lucena, J.M. Fuertes and Blanca: IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 2b (2003), pp.1296-1311.