Please wait a minute...
 首页  期刊介绍 期刊订阅 联系我们 横山亮次奖 百年刊庆
 
最新录用  |  预出版  |  当期目录  |  过刊浏览  |  阅读排行  |  下载排行  |  引用排行  |  横山亮次奖  |  百年刊庆
清华大学学报(自然科学版)  2019, Vol. 59 Issue (6): 445-452    DOI: 10.16511/j.cnki.qhdxxb.2019.26.004
  机械工程 本期目录 | 过刊浏览 | 高级检索 |
基于组合激光结构光的视觉传感器检测算法及图像处理流程优化
孙博文, 朱志明, 郭吉昌, 张天一
清华大学 机械工程系, 先进成形制造教育部重点实验室, 北京 100084
Detection algorithms and optimization of image processing for visual sensors using combined laser structured light
SUN Bowen, ZHU Zhiming, GUO Jichang, ZHANG Tianyi
Key Laboratory for Advanced Materials Processing Technology of Ministry of Education, Department of Mechanical Engineering, Tsinghua University, Beijing 100084, China
全文: PDF(2285 KB)  
输出: BibTeX | EndNote (RIS)      
摘要 基于激光结构光的视觉传感器广泛应用于焊接领域的坡口检测和焊缝跟踪。该文提出了一种基于组合激光结构光的新型视觉传感器,独特的光路结构设计避免了传感器应用于不同焊接位姿时繁琐的外参数标定,仅依靠传感器内部固有参数(应用前需校准)和焊接坡口图像的特征点坐标值,即可实现焊接坡口参数的在线检测,有效增强了传感器的适应性。通过对不同图像处理算法的改进和合理组合,对图像处理流程进行了优化。动态感兴趣区(region of interest,ROI)区域提取算法可快速寻获有价值的激光线和特征点所在区域,有效提升了后续图像处理速度;顶帽变换与自适应二值化组合,在将激光线灰度值均匀化的同时,实现了激光线与背景图像的有效区分。运用基于LOG(Laplacian of Gaussian)算子的边缘识别算法,可提取出激光线的单像素边缘;采用最小二乘法对所求得的激光中心线离散点进行直线拟合,通过联立直线方程求交点的方式,实现了对焊接坡口特征点图像坐标值的准确识别。借助Visual Studio平台,运用改进的图像处理算法、优化的图像处理流程和检测算法,对特征参数不同的V形焊接坡口进行检测试验,检测误差均在±4%以内,验证了所提出视觉传感器及其检测算法和图像处理流程的合理性和适用性。
服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
孙博文
朱志明
郭吉昌
张天一
关键词 视觉传感器图像处理动态感兴趣区提取顶帽变换自适应二值化边缘识别    
Abstract:Visual sensors based on laser structured light are widely used in the welding field for detection of welding grooves and tracking of weld seams. This paper describes a visual sensor based on combined laser structured light where the light paths within the visual sensor are designed to eliminate the need to calibrate the external sensor parameters for different positions and postures to provide on-line detection of welding groove parameters using only the internal sensor parameters (which require calibration) and the feature point coordinates of the welding groove image. Thus, this method is much more adaptable than previous methods. The image processing is optimized by improving and combining various image processing algorithms. A dynamic region of interest region extraction algorithm is used to quickly find the region that includes the laser lines and feature points to significantly improve the subsequent image processing speed. Then, a top hat transformation and self-adaptive binarization are used to homogenize the gray values of the laser lines that differentiates the laser lines from the background. After that, an edge recognition algorithm based on the Laplacian of Gaussian (LOG) operator is used to extract the single pixel edges of the laser lines which are used to then identify the discrete points of the laser center lines that are fit to linear equations by the least squares method. Finally, these linear equations are used to accurately calculate the image coordinates of the feature points of the welding groove. All these image processing algorithms were implemented in Visual Studio for tests to detect V-shaped welding grooves with various characteristic parameters. The detection errors are all within ±4%, which shows that the detection algorithms are reasonable and applicable for image processing of welding processes with visual sensors.
Key wordsvisual sensor    image processing    dynamic region of interest extraction    top hat transformation    adaptive binarization    edge recognition
收稿日期: 2018-10-31      出版日期: 2019-06-01
基金资助:国家自然科学基金面上项目(51775301)
通讯作者: 朱志明,教授,E-mail:zzmdme@tsinghua.edu.cn     E-mail: zzmdme@tsinghua.edu.cn
引用本文:   
孙博文, 朱志明, 郭吉昌, 张天一. 基于组合激光结构光的视觉传感器检测算法及图像处理流程优化[J]. 清华大学学报(自然科学版), 2019, 59(6): 445-452.
SUN Bowen, ZHU Zhiming, GUO Jichang, ZHANG Tianyi. Detection algorithms and optimization of image processing for visual sensors using combined laser structured light. Journal of Tsinghua University(Science and Technology), 2019, 59(6): 445-452.
链接本文:  
http://jst.tsinghuajournals.com/CN/10.16511/j.cnki.qhdxxb.2019.26.004  或          http://jst.tsinghuajournals.com/CN/Y2019/V59/I6/445
  图1 基于组合激光结构光的视觉 传感器检测原理
  图2 图像处理过程
  图3 动态 ROI区域提取图
  图4 顶帽变换前的图像三维可视化图
  图5 顶帽变换后的图像三维可视化图
  图6 CCD图像预处理
  图7 自适应二值化和中值滤波后的 三维可视化图和顶视图
  图8 应用4种不同算子的边缘识别效果
  图9 激光中心线的提取效果
  图10 焊接坡口的特征点提取效果
  图11 焊接坡口检测系统实物
  表1 焊接坡口特征尺寸参数检测结果(3次测量平均值)
[1] 罗璐, 林三宝, 伏喜斌, 等. 基于激光视觉的焊缝特征信息检测技术研究[J]. 焊接, 2008(7):33-37. LUO L, LIN S B, FU X B, et al. Inspection technology on joint feature information based on laser vision[J]. Welding & Joining, 2008(7):33-37. (in Chinese)
[2] LEE S K, NA S J. A study on automatic seam tracking in pulsed laser edge welding by using a vision sensor without an auxiliary light source[J]. Journal of Manufacturing Systems, 2002, 21(4):302-315.
[3] 于英飞, 郭吉昌, 朱志明. 焊接可视化技术的发展与研究现状[J]. 焊接, 2017(12):4-8. YU Y F, GUO J C, ZHU Z M. Development and research status of welding visualization technology[J]. Welding & Joining, 2017(12):4-8. (in Chinese)
[4] 郭吉昌, 朱志明, 于英飞, 等. 焊接领域激光结构光视觉传感技术的研究及应用[J]. 中国激光, 2017, 44(12):7-16. GUO J C, ZHU Z M, YU Y F, et al. Research and application of visual sensing technology based on laser structured light in welding industry[J]. Chinese Journal of Laser, 2017, 44(12):7-16. (in Chinese)
[5] 章妍. 基于铝合金GTAW焊三光路视觉传感的熔池特征提取[D]. 上海:上海交通大学, 2014. ZHANG Y. Visual characters extraction of weld pool based on three path meseurement during aluminum alloy GTAW process[D]. Shanghai:Shanghai Jiao Tong University, 2014. (in Chinese)
[6] 刘志辉. 坡口及焊缝数字轮廓的激光光栅视觉测量[D]. 兰州:兰州理工大学, 2018. LIU Z H. Laser grating vision measurement of groove and weld digital contour[D]. Lanzhou:Lanzhou University of Technology, 2018. (in Chinese)
[7] 冈萨雷斯, 伍兹. 数字图像处理[M]. 阮秋琦, 阮宇智, 译. 北京:电子工业出版社. 2011. GONZALEZ R C, WOODS R E. Digital image processing[M]. RUAN Q Q, RUAN Y Z, trans. Beijing:Publishing House of Electronic Industry. 2011. (in Chinese)
[8] 刘子腾, 白瑞林, 王秀平. 基于激光视觉的角焊缝图像特征点提取[J]. 焊接学报, 2016, 37(2):89-93. LIU Z T, BAI R L, WANG X P. Image feature extraction of fillet weld based on laser vision[J]. Transactions of the China Welding Institution, 2016, 37(2):89-93. (in Chinese)
[9] 郭吉昌, 朱志明, 孙博文. 基于视觉的焊枪空间位姿实时检测技术[J]. 电焊机, 2018, 48(9):1-7. GUO J C, ZHU Z M, SUN B W. Real-time detection of position and attitude for welding torch based on vision[J]. Electric Welding Machine, 2018, 48(9):1-7. (in Chinese)
[10] GUO J C, ZHU Z M, SUN B W, et al. Principle of an innovative visual sensor based on combined laser structured lights and its experimental verification[J]. Optics & Laser Technology, 2019, 111:35-44.
[11] GUO J C, ZHU Z M, SUN B W, et al. A novel multifunctional visual sensor based on combined laser structured lights and its anti-jamming detection algorithms[J]. Welding in the World, 2018. DOI:10.1007/s40194-018-0654-y.
[12] 王璇. 焊接机器人焊缝信息视觉检测系统研究[D]. 天津:河北工业大学, 2013. WANG X. Research on visual detection sensor of welding robot[D]. Tianjin:Hebei University of Technology. (in Chinese)
[13] 赵军. 大构件焊缝磨抛机器人视觉测量技术的研究[D]. 长春:吉林大学, 2014. ZHAO J. Research on grinding/polishing robotic vision measurement technology for weld beads of large structural parts[D]. Changchun:Jilin University, 2014. (in Chinese)
[14] 沈同平, 王元茂, 方芳, 等. 基于灰度形态学的图像边缘特征提取算法研究[J]. 兰州文理学院学报(自然科学版), 2018, 32(2):58-61. SHEN T P, WANG Y M, FANG F, et al. Edge feature extraction algorithm based on gray morphology[J]. Journal of Lanzhou University of Arts and Science (Natural Sciences), 2018, 32(2):58-61. (in Chinese)
[15] 范九伦, 赵凤. 灰度图像的二维Otsu曲线阈值分割法[J]. 电子学报, 2007, 35(4):751-755. FAN J L, ZHAO F. Two-dimensional Otsu's curve thresholding segmentation method for gray-level images[J]. Acta Electronica Sinica, 2007, 35(4):751-755. (in Chinese)
[16] 郭佳. 基于光照不均匀图像的自适应二值化方法研究[D]. 武汉:武汉科技大学, 2013. GUO J. The research of binarization method based on non-uniform illumination images[D]. Wuhan:Wuhan University of Science and Technology, 2013. (in Chinese)
[17] 陈铖. 焊缝跟踪系统中基于C++的图像处理技术研究[D]. 成都:西南交通大学, 2017. CHEN C. Research on image processing technology based on C++ in weld tracking system[D]. Chengdu:Southwest Jiaotong University, 2017. (in Chinese)
[18] 刘习文, 王国荣, 石永华. 单条纹激光引导焊缝跟踪图像处理[J]. 焊接学报, 2006, 27(6):25-28, 32. LIU X W, WANG G R, SHI Y H. Image processing in welding seam tracking based on single stripe laser[J]. Transactions of the China Welding Institution, 2006, 27(6):25-28, 32. (in Chinese)
[19] 刘蕊. 数字图像中边缘检测算法的研究[D]. 镇江:江苏科技大学, 2009. LIU R. Digital image edge detection algorithm[D]. Zhenjiang:Jiangsu University of Science and Technology, 2009. (in Chinese)
[20] 张铮, 徐超, 任淑霞, 等. 数字图像处理与机器视觉[M]. 2版. 北京:人民邮电出版社, 2014. ZHANG Z, XU C, REN S X, et al. Digital image processing and machine vision[M]. 2nd ed. Beijing:Post & Telecom Press, 2014. (in Chinese)
[21] 管力明, 李磊, 林剑. 基于改进LOG算子的图像边缘检测方法[J]. 机电工程, 2010, 27(12):113-115. GUAN L M, LI L, LIN J. Image edge detection method based on improved LOG operator[J]. Journal of Mechanical & Electrical Engineering, 2010, 27(12):113-115. (in Chinese)
[22] 李莹莹, 张志毅, 袁林. 线结构光光条中心提取综述[J]. 激光与光电子学进展, 2013, 50(10):100002. LI YY, ZHANG Z Y, YUAN L. Survey on linear structured light stripe center extraction[J]. Laser & Optoelectronics Progress, 2013, 50(10):100002. (in Chinese)
[1] 张思敏, 王国磊, 于乾坤, 华宵桐, 宋立滨, 陈恳. 基于图像处理的喷涂雾锥角影响因素分析[J]. 清华大学学报(自然科学版), 2019, 59(2): 103-110.
[2] 聂鼎, 安雪晖. 基于图像处理的净浆扩展度测量工具开发[J]. 清华大学学报(自然科学版), 2016, 56(12): 1249-1254.
[3] 史琳, 许然, 许强辉, 须颖, 郑立才. 基于显微CT技术的结焦砂3维孔隙结构精细表征[J]. 清华大学学报(自然科学版), 2016, 56(10): 1079-1084.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
版权所有 © 《清华大学学报(自然科学版)》编辑部
本系统由北京玛格泰克科技发展有限公司设计开发 技术支持:support@magtech.com.cn