自主机器人指定颜色形状属性物体的识别方法  

A Method of Recognizing Objects Specified by Color and Shape in Mobile Robots

作　　者：冯占英[1] 李永霞[1] 盛洪[1] 

机构地区：[1]北京联合大学自动化学院,北京100101

出　　处：《北京联合大学学报》2011年第1期14-19,共6页Journal of Beijing Union University

基　　金：北京联合大学自然科学类校级项目(11102HB0801)

摘　　要：机器人在自主行进的过程中,依靠视觉系统自动捕捉目标,并将目标物识别出,是智能机器人的关键技术之一。为解决机器人移动过程中对已知颜色形状属性的目标物的识别问题,对基于YUV颜色空间的种子填充彩色图像分割方法进行改进,在各种背景下有效地实现机器人视觉系统对已知颜色形状的目标物的识别,对变化光照具有较强的适应性。When the autonomous mobile robot moves,it depends on vision system to catch and recognize the tar-geted objects.Therefore,vision system is one of the key technologies for robot intelligent.In order to solve the problem of recognizing color and shape specified objects in the autonomous mobile,a seed fill method based on HUV model is improved.After the shortcoming of color recognition was overcome by means of shape recognition together with color recognition,relognition became more effectively.Through experiments,the recognizing of targe-ted objects with specified color and shape were effectively realized in a variety of background,and the adaptability to changed light was very well improved.

关 键 词：自主机器人 HUV色彩模型 机器视觉 种子填充法 

分 类 号：TP242.6[自动化与计算机技术—检测技术与自动化装置]