足球机器人视觉图像分割算法 - 吉林大学学报.pdf

第43卷　 增刊 吉林 大 学 学报 ( 工 学版 ) 　 Vol.43　 Sup. 2013年3月 Journal of Jilin University (Engineering and Technology Edition) 　 Mar. 2013 足球机器人视觉图像分割算法 李晓瑜,杨马英 (浙江工业大学信息工程学院,杭州310023) 摘　 要:为提高机器人在比赛中对多目标提取及识别的准确度和效率,采用离线的自适应阈值 颜色分类法,同时识别不同颜色的多个目标物,对颜色的变化有一定的适应性;然后用改进的 数学形态学中的膨胀腐蚀算法对颜色分类后的图像滤波,该方法在保证图像处理效率的同时 提高分割精度;最后使用种子填充法来实现同时分割和多目标特征提取,减少像素点遍历次 数,提高算法效率。 实验证明,通过上述方法可以使足球机器人适应一定的光照变化,准确快 速地分割多个目标。 关键词:足球机器人;视觉系统;图像分割;目标识别 中图分类号:TP391　 　 文献标志码:A　 　 文章编号:1671-5497(2013)Sup.-0260-05 Objective segmentation method of video image in robot soccer LI Xiao-yu,YANG Ma-ying (College of Information Engineering College,Zhejiang University of Technology,Hangzhou310023,China) Abstract:In order to improvethe accuracy and efficiency of multi-objective extraction andrecognition inrobot soccer image processing,offline adaptive threshold value color classification was adopted,different colors of multiple targetswere identified,which had certain flexibility to the color changes.An improved corrosion and expansion algorithm in mathematical morphology was proposed to filter the image whose color was classified, thus improved the image processing efficiency and enhanced the segmentation accuracy.Seed filling method was employedto simultaneously implement segmentation andmulti-objectivefeatureextraction,andthereby the times of pixel traverse was reduced and the efficiency of the algorithm was increased.It is illustrated by the experiments that the above method can make the robot soccer adapt to certain illumination change and make multi-objective segmentation accurately and rapidly. Key words:robot soccer;visual system;image segmentation;target recognition 　 　 视觉与图像处理系统是机器人研究的重要内 出决策,给出机器人动作指令;最后通过通信模块 [1-2