Abstract：Humanoid soccer robots need to adapt to the conditions in human soccer games such as detecting a soccer ball that does not have predefined characteristics such as a definite color and that may blend in with the playing field. For such conditions, the problem cannot be solved by classical detection strategies based on a single colorblock. In this study, the ball color is split into a specific color and a shared color. Two rounds of labelling are used to generate a color lookup table. Color-blocks obtained by pixel-level segmentation are used in a marco-pixel clustering method based on a connecting relationship graph to generate several ball candidates. The best ball object is estimated via the membership function by fuzzy logic. Tests show that the method is able to detect unpredefined balls even in a very disturbed environment and at large distances from the robot and is also able to avoid confusion with the border lines and other robots on the field without excessive computing requirements. The calculations can reach a high framerate of 15 frames per second. This strategy provides an efficient detection method using strictly limited computing resources for robot soccer players.
 NADARAJAH S, SUNDARAJ K. Vision in robot soccer:A review[J]. Artificial Intelligence Review, 2015, 44(3):289-310.  JOSEPH R, DIVVALA S, GIRSHICK R, et al. You only look once:Unified, real-time object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA:IEEE, 2016:779-788.  JONATHAN L, EVAN S, TREVOR D. Fully convolutional networks for semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Boston, MA, USA:IEEE, 2015:3431-3440.  RAHMAN A, WIDODO N S. Colored ball position tracking method for goalkeeper humanoid robot soccer[J]. Telecommunication Computing Electronics and Control, 2013, 11(1):11-16.  TRIFAN A, NEVES A J R, CUNHA B, et al. UAVision:A modular time-constrained vision library for soccer robots[C]//Robot Soccer World Cup. Switzerland:Springer, Cham, 2014:490-501.  李晓瑜, 杨马英. 足球机器人视觉图像分割算法[J]. 吉林大学学报(工学版), 2013(s1):260-264. LI X Y, YANG M Y. Objective segmentation method of video image in robot soccer[J]. Journal of Jilin University (Engineering and Technology Edition), 2013(s1):260-264. (in Chinese)  杜鑫峰, 熊蓉, 褚健. 仿人足球机器人视觉系统快速识别与精确定位[J]. 浙江大学学报(工学版), 2009, 43(11):1975-1981. DU X F, XIONG R, CHU J, et al. Fast recognition and precise localization of humanoid soccer robot vision system[J]. Journal of Zhejiang University (Engineering Science). 2009, 43(11):1975-1981. (in Chinese)  BUDDEN D, FENN S, WALKER J, et al. A novel approach to ball detection for humanoid robot soccer[C]//Australasian Joint Conference on Artificial Intelligence. Berlin Heidelberg:Springer, 2012:827-838.  MAZZEO P L, SPAGNOLO P, LEO M, et al. Ball detection in soccer images using isophote's curvature and discriminative features[J]. Pattern Analysis and Applications, 2016, 19(3):709-718.  BRUCE J, BALCH T, VELOSO M. Fast and inexpensive color image segmentation for interactive robots[C]//Proceedings of 2000 IEEE/RSJ International Conference on Intelligent Robots and Systems, Takamatsu, Japan:IEEE, 2000(3):2061-2066.  ABUBAKER A, QAHWAJI R, IPSON S, et al. One scan connected component labeling technique[C]//IEEE International Conference on Signal Processing and Communications, Dubai, United Arab Emirates:IEEE, 2007:1283-1286.  HARTL A, VISSER U, ROFER T. Robust and efficient object recognition for a humanoid soccer robot[C]//RoboCup 2013:Robot World Cup XVⅡ. Berlin Heidelberg:Springer, 2013:396-407.  THRUN S. Probabilistic robotics[M]. Cambridge:MIT Press, 2006.  张继文, 刘莉, 陈恳. 小型仿人足球机器人MOS-7的系统设计及局部优化[J]. 清华大学学报(自然科学版), 2016, 56(8):811-817. ZHANG J W, LIU L, CHEN K. System design and local optimization of a small humanoid soccer robot MOS-7[J]. Journal of Tsinghua University (Science and Technology), 2016, 56(8):811-817. (in Chinese)