计算机应用 ›› 2016, Vol. 36 ›› Issue (4): 1132-1136.DOI: 10.11772/j.issn.1001-9081.2016.04.1132

• 虚拟现实与数字媒体 • 上一篇    下一篇

野外环境下图像中坑区域的提取方法

孟令江1,2, 王挺1, 姚辰1   

  1. 1. 中国科学院 沈阳自动化研究所, 沈阳 110000;
    2. 中国科学院大学, 北京 100049
  • 收稿日期:2015-08-31 修回日期:2015-11-16 出版日期:2016-04-10 发布日期:2016-04-08
  • 通讯作者: 孟令江
  • 作者简介:孟令江(1983-),男,内蒙古包头人,硕士研究生,主要研究方向:机器视觉; 王挺(1978-),男,辽宁沈阳人,副研究员,博士,主要研究方向:机器人控制、特种机器人、模式识别、智能系统; 姚辰(1964-),男,辽宁沈阳人,研究员,博士,主要研究方向:机器人控制、特种机器人。

Image segmentation method of pit area in wild environment

MENG Lingjiang1,2, WANG Ting1, YAO Chen1   

  1. 1. Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang Liaoning 110000, China;
    2. University of Chinese Academy of Sciences, Beijing 100049, China
  • Received:2015-08-31 Revised:2015-11-16 Online:2016-04-10 Published:2016-04-08

摘要: 在野外环境中有很多坑区域,这对野外工作机器人的移动带来了困难,因此引入视觉方法来实现对坑的检测。首先根据工程要求去除掉一部分不满足大小的疑似区域,再利用坑区域边缘梯度去除掉一部分疑似区域,之后计算与椭圆相似度来确定灰度分割阈值,并通过分析坑与椭圆相似度曲线来确定相似度阈值,以从疑似区域中分离出坑区域。经过使用200幅不同角度、场景和坑数量的图像进行测试,结果表明该方法能够在复杂野外环境下很好地提取出坑区域,对坑轮廓的规整度不敏感,能够适应复杂的环境,是一种有效的方法。

关键词: 坑区域, 阈值分割, 直方图, 梯度, 椭圆相似度

Abstract: It is difficult for robot to move in wild environment because of pit areas, so a visual coping method was put forward to detect those pit areas. Firstly, according to project requirements, a part of suspected areas with small size were removed, as well as some the suspected areas with edge gradient. Secondly, the oval similarity was calculated to determine gray level segmentation threshold, and the similarity threshold was confirmed by analyzing the oval similarity curve, which was used to separate pit areas from the suspected pit areas. At last, the simulation results on 200 pictures with different angles, scenes and pit umbers show that the proposed method can be applied to extract pit area in complex environment, and is also not sensitive to outline regularity of pit area; besides, it can adapt to complex environment.

Key words: pit area, threshold segmentation, histogram, gradient, oval similarity

中图分类号: