基于颜色信息足球机器人视觉跟踪算法  

Fast vision trace algorithm of MIROSOT based on color information

作　　者：欧宗瑛[1] 袁野[2] 张艳珍[1] 

机构地区：[1]大连理工大学机械工程学院CAD&CG研究所,辽宁大连116024 [2]大连理工大学电子与信息学院自动化系,辽宁大连116024

出　　处：《大连理工大学学报》2000年第6期729-732,共4页Journal of Dalian University of Technology

摘　　要：机器人足球比赛是一项非常复杂的高技术对抗活动 ,其中快速准确地识别小球和机器人小车是决策及控制的基础 .在足球机器人视觉跟踪中 ,颜色信息是最主要的识别分割依据 ,由于 HSV模型更接近人眼对颜色的感知 ,在不同光照条件下 ,色调参数 H数值较稳定 ,比较适合用做识别处理的基础 .因此使用色调 H和亮度 V作为识别颜色的参数 ,同时为了提高识别速度 ,作了一些改进 ,并提出一种橙色高尔夫球和机器人小车的快速识别算法 .试验快速准确 ,证明了该算法的可靠性和有效性 .MIROSOT is a complex competition game. Quickly and correctly identifying the position and the movement of the golf ball and robot vehicles is the foundation of making decision and control in winning MIROSOT competitions. In a MIROSOT system, the ball, robot vehicles and background are painted with specified colors, and these different specified colors will serve as indexes for identifying the moving objects. However, the RGB color data of a specified moving object are quite dispersive in different lighting circumstances. To solve this problem, a new algorithm for identifying specified color based on parameters H and V with HSV color model is proposed in this paper. This paper also introduces a fast algorithm for identifying the ball and robot vehicles which might be adjacent each other. The running experiments show that the algorithm is reliable and efficient.

关 键 词：视觉跟踪 机器人视觉 HSV颜色模型 足球机器人 颜色信息 

分 类 号：TP242.62[自动化与计算机技术—检测技术与自动化装置]