SIFT-Based Target Recognition in Robot Soccer


Article Preview

A novel scale-invariant feature transform (SIFT) algorithm is proposed for soccer target recognition application in a robot soccer game. First, the method of generating scale space is given, extreme points are detected. This gives the precise positioning of the extraction step and the SIFT feature points. Based on the gradient and direction of the feature point neighboring pixels, a description of the key points of the vector is generated. Finally, the matching method based on feature vectors is extracted from SIFT feature points and implemented on the image of the football in a soccer game. By employing the proposed SIFT algorithm for football and stadium key feature points extraction and matching, significant increase can be achieved in the robot soccer ability to identify and locate the football.



Edited by:

Hun Guo, Taiyong Wang, Dunwen Zuo, Zijing Wang, Jun Li and Ji Xu




Y. H. Du et al., "SIFT-Based Target Recognition in Robot Soccer", Key Engineering Materials, Vol. 693, pp. 1419-1427, 2016

Online since:

May 2016




* - Corresponding Author

[1] Wang Hongmei , Zhang Ke, Li Yanjun . Progress image matching, J. Computer Engineering and Application, 2004, 40 (19): 42-47.

[2] Zhao Hui. SIFT feature matching technology lecture. http: / www. qiji. cn / epint / abs / 3059. Html.

[3] RAN GAL, DANIEL COHEN. OR. Salient geometric features for partial shape matching and similarity,J. ACM Transactions on Graphics(TOG), 2006, 25(1): 130-135.


[4] KAZUYUKI MIYAZAWA, KOICHI ITO, TAKAFUMIIAOKI, eta1. An Effective Approach for Iris Recognition Using Phase-Based Image Matching,J. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, 10(30): 1741-1756.


[5] Liu Bo, Hu Aiping, Fan Junbo. Soccer recognition based on a color grayscale image,J. Jiangsu Polytechnic University, 2009, 40 (19): 68-71.

[6] Yang Dongchao, Bin Yang , Zhang Jiwen. Robot soccer recognition based on color and shape, J. Journal of Computer Applications, 2008, 38 (19): 174-176.

[7] Liu Zhan, Dou Haobin, Luo Dingsheng . Socce rfusion odometry information and visual self-localization method. [J] Fuzzy pattern recognition and artificial intelligence, 2013, 21 (19): 57-62.

[8] Cao Aizeng, Shi Guangxing, Liu Feng . robot Soccer recognition algorithm Study,J. Jinan University (Natural Science), 2006, 20 (3) : 35-237.

[9] Mu Ying , Ma Jing. Soccer recognition based DSP,J. Automation & Instrumentation, 2012, 2 (4) : 91-92.

[10] Pan Yabin, Liu Guodong. An improved humanoid soccer robot color target recognition algorithm.,J. Computer Application Research, 2011, 28 (3): 1195-1198.

[11] Zan Jie, Cai Zongying, Yan Guorui. A robot soccer detection and recognition based on feature detection, J. Guangxi University: Natural Science Edition, 2012, 37 (5): 913-920.

[12] David G. Lowe. Object Reconnition from Local Scale-Invariant Features,J. Proc of the International Conference Computer Vision, 1999; 1-20.

[13] David G. Lowe. Distinctive image features fromscale invariant key points, J. IJCV, 2004. 60(2): 91-110.

[14] David G. Lowe. Fitting parameterized three-dimensional modelsto images IEEE Trans on Pattern Analysis and Machine Intelligence, J. 2001, 13(5): 441–450.


[15] TONGL. Scale—Space theory: a basic for analyzing stuctures at different scales,J. Scales Joumal of Applied Statistics, 1994, 21(2): 224-270.

Fetching data from Crossref.
This may take some time to load.