Research of Soccer Robot Target Tracking Algorithm Based on Improved CAMShift

Abstract:

According to the vision needs of robot soccer and CAMShift tracking inefficient in dynamic background, a new tracking algorithm is brought forward to improve the CAMShift in this paper. A real-time updating background model is build, by traversing the search area for all target pixels to statistic and calculate the color probability distribution of the color target, statistical principles and minimum error rate of Bayesian decision theory are used to achieve a more accurate distinction between the target and the background. By comparing with the CAMShift, the new algorithm provides a better robustness in the soccer robot game and can meet the purposes of fast and accurate tracking.

• Periodical: Advanced Materials Research (Volume 221)
• Pages: 610-614
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.221.610
• Online since: March 2011
• Authors: Yi Hu Huang, Jin Li Wang, Xi Mei Jia
• Keywords: Camshift, Machine Vision, Robot Soccer, Target Tracking, Updating Model

References

[1] Huang Jing, Zhao Chen, Zhou Mingming, identification of objects for micro soceer robot based on fast color space transformation. Jornal of Harbin institute of technology, 2003(9), pp.1036-1039.

[2] Karmann KP，Brandt AV. Moving object recognition using an adaptive background memory. Time-Varying Image Processing and Moving Object Recognition [C] ，Elsevier，Amsterdam，Netherlands，1990, pp.289-296.

DOI: 10.1016/c2009-0-13165-3

[3] Liu Xue Chang Fa Liang Wang Huajie, An Object Tracking Method Based on Improved Camshift Algorithm microcomputer information. val. 23, 2007, pp.297-305.

[4] Pérez, P., C. Hue, J. Vermaak and M. Gangnet (2002). Color Based Probabilistic Tracking. In: 7th European Conference on Computer Vision-Part I, pp.661-675.

DOI: 10.1007/3-540-47969-4_44

[5] Sun Zhongsen, Sun Junxi1, Song Jianzhong. Qiao Shuang. Anti-occlusion arithmetic for moving object tracking. Optics and Precision Engineering. Feb. 2007. pp . 267-271.

[6] Paragios N，Deriehe R. Geodesic active contours and level sets for the detection and tracking of moving objects[J]. IEEE Transactions on Patern Analysis and Machine Intelligenee. 22(3), 2000, pp.266-280.

DOI: 10.1109/34.841758

[7] Kurugollu F，Sankur B，Harmanei A E, Color lmage Segmentation Using Histogram Multithresholding and Fusion . Image and Vision ComPuting. 2001, 19(13), pp.915-928.

DOI: 10.1016/s0262-8856(01)00052-x

[8] Gary R. Bradski, Computer Vision Face Tracking For Use in a Perceptual User Interface Intel Technology Journal Q2 '98 pp.1-15.

[9] Dorin Comanieiu，Visvanathan Ramesh，Peter Meer. Kernel-based object tracking [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence，24(5), 2003， pp.564-577.

DOI: 10.1109/tpami.2003.1195991

[10] A. BHATTACHARYYA On a Measure of Divergence between Two Statistical Populations Defined by their Probability Distributions, Bull. Calcutta Math. 1943. pp.99-110.

[11] Xiang Guishan. Stably tracking moving object with active camera in complex environment. Journal of Zhejiang University of Science and Technology. 2009 (4). pp.339-343.

[12] Li Zhenwei, Chen Chong, Zhao You, Moving Object Tracking Method and Implement Based on OpenCV, Modern Electronic Technique pp. val. 20, 2008, pp.128-130.

[13] Shao Wenkun, Huang Ai-min, Wei Qing Research on Moving Object Tracking with Background Motion, computer simulation. May, 2005 (5), pp.182-184.