Line extraction from images of industrial components based on CAD

ZHANG Chun-sen; HU Ping-bo

doi:10.3788/OPE.20111909.2214

您当前的位置：

首页 >

文章列表页 >

Line extraction from images of industrial components based on CAD

Article | 更新时间：2020-08-12

- Line extraction from images of industrial components based on CAD
- Optics and Precision Engineering Vol. 19, Issue 9, Pages: 2214-2221(2011)
- 作者机构：
  
  西安科技大学测绘科学与技术学院,陕西西安,710054
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20111909.2214
  CLC： TP391.4
- Received：17 December 2010，
  
  Revised：17 February 2011，
  
  Published Online：26 September 2011，
  
  Published：26 September 2011
- 稿件说明：
移动端阅览
张春森, 胡平波. 基于CAD技术实现工业零部件图像直线特征提取[J]. 光学精密工程, 2011,19(9): 2214-2221

ZHANG Chun-sen, HU Ping-bo. Line extraction from images of industrial components based on CAD[J]. Editorial Office of Optics and Precision Engineering, 2011,19(9): 2214-2221
张春森, 胡平波. 基于CAD技术实现工业零部件图像直线特征提取[J]. 光学精密工程, 2011,19(9): 2214-2221 DOI： 10.3788/OPE.20111909.2214.

ZHANG Chun-sen, HU Ping-bo. Line extraction from images of industrial components based on CAD[J]. Editorial Office of Optics and Precision Engineering, 2011,19(9): 2214-2221 DOI： 10.3788/OPE.20111909.2214.

摘要

针对工业零部件序列图像量测与重建中的线特征提取问题

提出了一种以CAD设计数据为引导

高精度检测图像中直线的数学模型。以三维计算机辅助设计(CAD)数据为基础

通过求解CAD三维直角坐标系与图像坐标系间的参数转换关系

将物方线特征投影至图像上

得到图像线特征初值范围。利用自适应最小二乘模板匹配提取出边缘点序列

对生成的上述点序列采用最小二乘法进行拟合

得到图像线特征的直线方程。通过求解图像相交直线的交点

高精度地获得表达工业零部件轮廓的直线段。采用上述算法对真实工业零部件图像进行了线特征提取

重建的直线长度与游标卡尺量测的直线长度之差的中误差为0.232 mm。实验结果表明

文中所给算法自动化程度高、稳定性强

可用于规则工业零部件高精度图像量测与重建。

Abstract

For feature extraction from image measurements and reconstruction from industrial component images

a mathematical model guided by Computer Aided Design(CAD) data is put forward to detect image lines with high accuracy. Firstly

using CAD data

the line initial values are obtained by projecting object line features through the conversion of 3D CAD coordinate and images. Then a sequence of edge points are extracted by adaptive least squares template matching (LSTM) and leads to image line equations from these points based on the principle of least squares fitting. Finally the contours of industrial components are obtained accurately by solving the intersections of image intersecting lines. By using the algorithm on real images of industrial components

we perform a line feature extraction experiment with an average standard deviation of 0.232 mm between the rebuilt line and the actual line length.This proves that the algorithm has high automation extraction and strong stability

and can be used to the image measurement and reconstruction of industrial components with high accuracy.

关键词

Keywords

references

于起峰,尚洋. 摄影测量学原理与应用研究[M]. 北京:科学出版社,2009. YU Q F, SH Y. Videometrics: Principles and Researches [M].Beijing: Science Press, 2009.(in Chinese)[2] 管海燕,郭建星. 一种高精度的工业钣金件图像直线提取算法[J]. 地理空间信息, 2005,3(2):54-56. GUAN H Y, GUO J X. Lines extraction of industrial sheetmetal parts [J]. Geospatial Information, 2005, 3(2):54-56. (in Chinese)[3] 张春森,姜楠. 一种子像素级图像测量直线提取算法[J]. 中国矿业大学学报(自然科学版),2009,38(6):903-908. ZHANG CH S,JIANG N. Image lines feature extraction with sub-pixel [J]. Journal of China University of Mining and Technology, 2009, 38(6):903-908. (in Chinese)[4] 陈胜勇,刘盛. 基于OpenCV的计算机视觉技术实现[M]. 北京:科学出版社,2002. CHEN SH Y, LIU SH. Computer Vision Technology Based on the OpenCV[M]. Beijing: Science Press, 2002. (in Chinese)[5] 伍济钢,宾鸿赞. 机器视觉的薄片零件尺寸检测系统 [J]. 光学精密工程,2007,15(1):124-128. WU J G, BIN H Z. Dimensional inspecting system of thin sheet parts based on machine vision [J]. Opt. Precision Eng., 2007,15(1):124-128. (in Chinese)[6] 吴敬文. 基于DXF的数字地图投影与坐标系转换方法研究[J]. 海洋测绘,2009,29(1):28-30. WU J W. The research of the transformation among different coordinate systems and projections of digital map based on DXF file[J]. Hydrographic Surveying and Charting, 2009, 29(1):28-30. (in Chinese)[7] 张磊,车仁生,黄庆成. 无图纸检测中的CAD/CMM软件接口技术 [J]. 光学精密工程,2002,29(4):370-373. ZHANG L, CHE R SH, HUANG Q CH. Software interface technology of the CAD/CMM system in paperless inspection [J]. Opt. Precision Eng., 2002, 29(4):370-373. (In Chinese)[8] ACKEMANN F. High Precision Digital Image Correlation [M]. German: University of Stuttgart Press, 1983.[9] GRUEN A. Adaptive least square correlation: a powerful image matching technique[J].South African Journal of Photogrammetry and Remote Sensing.1985,3(14):175-187.[10] 张祖勋,张剑清.数字摄影测量学[M]. 武汉: 武汉大学出版社,1997. ZHANG Z X, ZHANG J Q. Digital Photogrammetry[M]. Wuhan: Wuhan University Science Press, 1997. (in Chinese)[11] 高春甫,唐可洪,胡庆玉,等. 机械手姿态识别的立体视觉匹配[J]. 光学精密工程,2010,18(2):465-469. GAO CH F, TANG K H, HU Q Y, et al..Stereo vision matching for posture recognition of manipulator [J]. Opt. Precision Eng., 2010,18(2):465-469. (in Chinese)

Views

638

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

EIS for ground-based imaging systems supporting scene switching perception

Infrared CO₂ gas sensor based on space double beams and its measurement model

Treating with Surface Figure Error of Mirror/Lens by Means of Surface Equation

Related Author

SONG Liduo

LI Hongwen

WANG Minghao

YANG Qingyun

ZHANG Shixue

WANG Chao

LI Ya-ping

ZHANG Guang-jun

Related Institution

Changchun Institute of Optics，Fine Mechanics and Physics，Chinese Academy of Sciences

Academy for Advanced Interdisciplinary Studies， Northeast Normal University

Key Laboratory for Precision Optical-mechanical-electric Integration Technology of the Ministry of Education, Beijing University of Aeronautics and Astronautics

Changchun Institute of Optics and Fine Mechanics, Chinese Academy of Sciences

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰