华南理工大学学报(自然科学版) ›› 2018, Vol. 46 ›› Issue (1): 131-138,144.doi: 10.3969/j.issn.1000-565X.2018.01.017

• 计算机科学与技术 • 上一篇    下一篇

基于形状上下文特征和ICP的高精度轮廓视觉检测算法

刘屿1,孙坤1,谢宏威2   

  1. 1. 华南理工大学 自动化科学与工程学院,广东 广州 510640;
    2. 广州大学 机械与电气工程学院,广东 广州 510006
  • 收稿日期:2017-03-26 修回日期:2017-06-25 出版日期:2018-01-25 发布日期:2017-12-01
  • 通信作者: 谢宏威( 1981-) ,男,副研究员,主要从事机器视觉及其相关应用研究工作 E-mail:xhw_cn@foxmail.com
  • 作者简介:刘屿( 1977) ,男,副研究员,主要从事分布参数系统控制、视觉检测研究
  • 基金资助:
     广东省自然科学基金资助项目( 2015A030310308) ;
    广东省科技计划项目( 2017B090910006,2016B010126001, 2016B090927010,2016A010102021,2015B090901049) ;
    华南理工大学中央高校基本科研业务费专项资金资助项目 ( 2017ZD058)

High Accurate Contour Vision Algorithm Based on Shape Context and ICP

LIU Yu1 SUN Kun1 XIE Hongwei2    

  1. 1. School of Automation Science and Engineering,South China University of Technology,Guangzhou 510640,Guangdong,China;
    2. School of Mechanical and Electrical Engineering,Guangzhou University,Guangzhou 510006,Guangdong,China)

  • Received:2017-03-26 Revised:2017-06-25 Online:2018-01-25 Published:2017-12-01
  • Contact: 谢宏威( 1981-) ,男,副研究员,主要从事机器视觉及其相关应用研究工作 E-mail:xhw_cn@foxmail.com
  • About author:刘屿( 1977) ,男,副研究员,主要从事分布参数系统控制、视觉检测研究
  • Supported by:
    The Natural Science Foundation of Guangdong Province of China( 2015A030310308) and the Science and Technology Planning Project of Guangdong Province ( 2017B090910006,2016B010126001,2016B090927010, 2016A010102021,2015B090901049) 

摘要: 为了解决任意形状工件轮廓尺寸的高精度检测问题, 本文提出一种基于形状上下文特征和迭代最近点的轮廓视觉检测算法. 首先, 在图像中采用基于局部面积的边缘提取算法提取工件的亚像素边缘, 并过滤掉噪声和补齐轮廓. 然后, 基于从粗到精的匹配策略, 先使用形状上下文特征进行粗匹配, 再使用迭代最近点算法进行精匹配. 最后, 提出邻域法来计算出轮廓偏差. 实验结果表明, 本文所提出的算法检测精度达到0.5个像素, 可以满足实际应用的需要.

关键词: 轮廓检测, 形状上下文, 迭代最近点, 边缘提取

Abstract: In order to solve the problems of high precision contour measurement with arbitrary shape, a high accurate vision algorithm is proposed based on shape context descriptor and iterative closest point (ICP). Firstly, the sub-pixel edge of workpiece is extracted by using edge extraction algorithm based on local area, then the noise is filtered out and contour is completed. Secondly, based on coarse-to-fine matching strategy, the coarse matching is performed by using shape context descriptor and the fine matching is performed by using iterative closest point for obtaining the sub-pixel accuracy contour matching. Finally, the neighbor-method is proposed to calculate the contour errors. The experimental results show that the detection accuracy of the proposed algorithm can reach to 0.5 pixel, which can meet the needs of practical application.

Key words: contour measurement, shape context, iterative point clouds, sub-pixel edge detection

中图分类号: