移动焊接机器人的工件识别及焊缝起始位置定位

上海交通大学学报（自然版） ›› 2012, Vol. 46 ›› Issue (07): 1054-1058.

移动焊接机器人的工件识别及焊缝起始位置定位

邓勇军a，吴明辉b，陈锦云a，陈善本a

(上海交通大学 a.机器人智能化技术实验室；b.机器人研究所，上海 200240)

收稿日期:2011-06-15 出版日期:2012-07-30 发布日期:2012-07-30
基金资助:
国家高技术研究发展计划（863）项目（2009AAA042221），上海市科委重点基础研究项目（09JC1407100）

Recognition of Work-piece and Location of Initial Seam Position for Mobile Welding Robot

DENG Yong-Jun-a, WU Ming-Hui-b, CHEN Jin-Yun-a, CHEN Shan-Ben-a

(a. Intelligentized Robotic Welding Technology Lab; b. Robotics Institute,Shanghai Jiaotong University， Shanghai 200240, China)

Received:2011-06-15 Online:2012-07-30 Published:2012-07-30

摘要/Abstract

摘要： 摘要：
考虑到非结构空间焊接的特殊性,通过视觉技术，基于圆投影和Zernike矩，提出了一种两步模板匹配法检测待焊工件是否出现在视觉区域；结合霍夫直线检测方法，设计了一套提取特征直线算法，并确定焊缝起始点在图像中的亚像素位置.由移动机器人在不同角度拍摄工件图像，圆投影和Zernike矩计算结果验证了其表征模板特性的有效性，具有旋转抗性，而且对于光照条件及摄像机视野的鲁棒性好，焊缝起始位置定位结果满足视觉计算需要. 关键词：
自主焊接；移动机器人；视觉技术；工件识别中图分类号： TG 409
文献标志码： A

Abstract: Considering the environmental characters of welding in unstructured space, via vision technology, a twosteps template matching method for workpiece recognition based on circle projection and Zernike moments was presented. An algorithm based on Hough line detection was designed to extract special lines which were used to calculate initial seam position with subpixel precision. Experiment was carried out by mobile welding robot, and series of templates were acquired by snapping workpiece images with different rotation angles. Circle projection results and Zernike moments were calculated, and they could effectively represent features of templates for typical workpiece, meanwhile errors due to rotation could be eliminated. These algorithms were proved to perform satisfied robustness of illumination and camera view. Subpixel location of initial seam position can satisfy the need for visual calculation.

Key words: autonomous welding, mobile welding robot, vision technology, workpiece regcognition

邓勇军a, 吴明辉b, 陈锦云a, 陈善本a. 移动焊接机器人的工件识别及焊缝起始位置定位 [J]. 上海交通大学学报（自然版）, 2012, 46(07): 1054-1058.

DENG Yong-Jun-a, WU Ming-Hui-b, CHEN Jin-Yun-a, CHEN Shan-Ben-a. Recognition of Work-piece and Location of Initial Seam Position for Mobile Welding Robot[J]. Journal of Shanghai Jiaotong University, 2012, 46(07): 1054-1058.

参考文献

［1］Shen H Y, Wu J, Lin T, et al. Arc welding robot system with seam tracking and weld pool control based on passive vision［J］. The International Journal of Advanced Manufacturing Technology, 2007, 39(78): 669678.
［2］Zhu Z Y, Lin T, Piao Y J, et al. Recgnition of the intial position of weld based on the image pattern match technology for welding robot［J］. International Journal of Advanced Manufacturing, 2005, 26(78): 784788.
［3］Chen X Z, Chen S B, Lin T, et al. Practical method to locate the initial weld position using visual technology［J］. International Journal of Advanced Manufacturing, 2006, 30(78): 663668.
［4］Wong R Y, Hall E L. Sequential hierarchical scene matching［J］. IEEE Transactions on Computers Archive, 1978, 27(4):359366.
［5］Ye B, Peng J X. Improvement and invariance analysis of Zernike moments using as a regionbased shape descriptor［J］. Journal of Pattern Recognition and Image Analysis, 2002, 12(4): 419428.
［6］Aoyagi S, Hattori N, Kohama A, et al. Object detection and recognition using template matching with SIFT features assisted by invisible floor marks［J］. Journal of Robotics and Mechatronics, 2009, 21(6): 689697.
［7］Mukundan R, Ramakrishnan K R. Fast computation of legendre and zenic moments［J］. Pattern Recognition, 1995, 28(9): 14331442.
［8］ChoHuak T, Chin R T. On image analysis by the methods of moments［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1988, 10(4): 496513.
［9］Wu M H, Gao X F, Fu Z, et al. The mechanism design of a wheeled climbing welding robot with passing obstacles capability［J］. Robotic Welding, Intelligence and Automation, 2011, 88(5): 401409.