基于单目仿人机器人的障碍物测距方法  

Study on Obstacle Distance Detection Based on Monocular Humanoid Robot

作　　者：彭飞[1] 魏衡华[1] 

机构地区：[1]中国科学技术大学自动化系,合肥230027

出　　处：《计算机系统应用》2013年第8期88-90,119,共4页Computer Systems & Applications

摘　　要：为了能够实时测量机器人与障碍物的距离,提出一种单目视觉的方法.首先将机器人获取的RGB图像转换为HSV图像,在HSV颜色空间对障碍物进行检测和识别,然后利用小孔成像原理和几何坐标变换,计算障碍物与机器人的距离.最后将该方法应用到实验室Darwin仿人机器人上,实验结果表明该方法具有可行性和有效性.In this paper, a monocular vision method is proposed to measure the distance between the robot and the obstacle. Firstly it converts the RGB image which is obtained from the robot to HSV image, then detects and identifies the obstacle in the HSV color space. Secondly it calculates the distance between the robot and obstacle using pinhole imaging principle and geometric coordinate transformation. Finally the method is tested on the Darwin humanoid robot; the result from the experiment proves the effectiveness and feasibility of the method.

关 键 词：单目 测距 障碍物检测 机器人 HSV颜色空间 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]