计算机工程与应用 ›› 2011, Vol. 47 ›› Issue (23): 181-184.

• 图形、图像、模式识别 • 上一篇    下一篇

移动机器人目标分割及测距方法研究

沈春生,王耀南   

  1. 湖南大学 电气与信息工程学院,长沙 410082
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2011-08-11 发布日期:2011-08-11

Study on mobile robot object?segmentation and distance detection method

SHEN Chunsheng,WANG Yaonan   

  1. College of Electrical and Information Engineering,Hunan University,Changsha 410082,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-08-11 Published:2011-08-11

摘要: 对于移动机器人单目视觉避障导航问题,研究了室内环境中多障碍物目标图像分割与目标定位。提出一种将HSI彩色图像空间序列分割与Otsu法选取阈值相结合的图像分割方法,并采用基于亮度均值的幂次变换方法改进亮度空间的对比度,从背景环境中分割提取出多个目标所在区域的像素坐标。基于透视投影原理,应用目标定位的几何方法得到目标的空间坐标。该方法在Pioneer-2移动机器人平台上进行了实验,论证了所提出方法的实用性和有效性。

关键词: 移动机器人, 视觉导航, 图像分割, 幂次变换, 目标定位

Abstract: A method for mobile robot navigation indoor using monocular vision is discussed.It provides a method for color image segmentation in HSI color model in succession using Otsu method to select the threshold,and suggests a mean brightness based powertransform method to improve the contrast of the brightness space,adapts to light changing of indoor environment and extracts the pixel coordinates of multiple targets.Based on perspective projection,it discusses geometry method to calculate the world coordinates of the objects.Experiment results with the Pioneer-2 mobile robot and data analysis show the method’s validity and practicability.

Key words: mobile robot, vision-based navigation, image segmentation, powertransform, object location