第13卷第5期 智能系统学报 Vol.13 No.5 2018年10月 CAAI Transactions on Intelligent Systems Oct.2018 D0:10.11992/tis.201705010 网络出版地址:http:/kns.cnki.net/kcms/detail/23.1538.TP.20180418.0900.002.html 一种基于Mark点的点胶机器人视觉目标定位方法 彭刚2,熊超2,夏成林2,林斌3 (1.华中科技大学自动化学院,湖北武汉430074;2.华中科技大学图像信息处理与智能控制教育部重点实验 室,湖北武汉430074,3.深圳市海思科自动化技术有限公司,广东深圳518109) 摘要:针对工业生产中PCB点胶机器人的视觉定位问题,提出了一种基于Mak点辅助的视觉定位算法。分 析了传统模板匹配、Sit、Surf等算法在Mark点识别与定位中的不足,同时考虑到Mark点所具有的规则几何特 征以及算法对于实时性的要求,提出了一种基于Mk点几何特征的改进型模板匹配算法。实验结果表明.这 种基于Mak点几何特征的改进型模板匹配算法具有良好的平移、缩放、旋转不变性,能够准确识别并定位 Mak点,从而实现对PCB上相关点胶目标点的定位,并满足工程可靠性和实时性的要求。 关键词:PCB;点胶机器人;Mak点;轴助;视觉定位;几何特征;改进型模板匹配;不变性 中图分类号:TP242文献标志码:A文章编号:1673-4785(2018)05-0728-06 中文引用格式:彭刚,熊超,夏成林,等.一种基于Mak点的点胶机器人视觉目标定位方法J.智能系统学报,2018,13(5): 728-733. 英文引用格式:PENG Gang,XIONG Chao,XIA Chenglin,etal.A method of vision target localization for dispensing robot based on mark point Jl.CAAI transactions on intelligent systems,2018,13(5):728-733. A method of vision target localization for dispensing robot based on mark point PENG Gang,XIONG Chao,XIA Chenglin',LIN Bin (1.School of Automation,Huazhong University of Science and Technology,Wuhan 430074,China;2.Key Laboratory of Image Pro- cessing and Intelligent Control of Education Ministry,Huazhong University of Science and Technology,Wuhan 430074,China; 3.Shenzhen Haisike Automation Technology Co.Ltd.,Shenzhen 518109,China) Abstract:To address the problem of visual localization of polychlorinated biphenyl (PCB)-dispensing robots in indus- trial production,a visual localization algorithm based on mark point is proposed in this paper.The results of traditional template matching,Sift and Surf algorithms,were compared and it was found that these algorithms are inadequate for the identification and location of Mark point.Meanwhile,the geometry features of the Mark point and the real-time re- quirements of the algorithm were considered so that an improved template-matching algorithm based on Mark point geometry features was realized.Experimental results show that this improved template-matching algorithm based on Mark point geometry features can keep good invariance under translation,scale,and rotation,which can accurately identify and locate the mark points,and then indirectly locate the PCB target points while satisfying engineering reliabil- ity and real-time constraints. Keywords:PCB:dispensing robot:Mark point:assistant:visual localization:geometric features:improved template matching;invariance 在3C行业的印刷电路板(PCB)制造过程中,点辅助的方式。首先,机器人系统对PCB上的 为了实现点胶机器人对目标的定位,常采用Mark Mark点进行视觉定位,然后根据Mark点与目标 的相对位置关系,可计算出目标位置。其中,Mark 收稿日期:2017-05-09.网络出版日期:2018-04-18. 基金项目:2016年深圳市科技计划项目(CYZZ20160412111639184) 点定位精度直接影响点胶精度。通过优化Mark 通信作者:彭刚.E-mail:penggang(@hust.edu.cn. 点识别与定位算法,可以提高操作的定位精度和DOI: 10.11992/tis.201705010 网络出版地址: http://kns.cnki.net/kcms/detail/23.1538.TP.20180418.0900.002.html 一种基于 Mark 点的点胶机器人视觉目标定位方法 彭刚1,2,熊超1,2,夏成林2 ,林斌3 (1. 华中科技大学 自动化学院,湖北 武汉 430074; 2. 华中科技大学 图像信息处理与智能控制教育部重点实验 室,湖北 武汉 430074; 3. 深圳市海思科自动化技术有限公司,广东 深圳 518109) 摘 要:针对工业生产中 PCB 点胶机器人的视觉定位问题,提出了一种基于 Mark 点辅助的视觉定位算法。分 析了传统模板匹配、Sift、Surf 等算法在 Mark 点识别与定位中的不足,同时考虑到 Mark 点所具有的规则几何特 征以及算法对于实时性的要求,提出了一种基于 Mark 点几何特征的改进型模板匹配算法。实验结果表明,这 种基于 Mark 点几何特征的改进型模板匹配算法具有良好的平移、缩放、旋转不变性,能够准确识别并定位 Mark 点,从而实现对 PCB 上相关点胶目标点的定位,并满足工程可靠性和实时性的要求。 关键词:PCB;点胶机器人;Mark 点;辅助;视觉定位;几何特征;改进型模板匹配;不变性 中图分类号:TP242 文献标志码:A 文章编号:1673−4785(2018)05−0728−06 中文引用格式:彭刚, 熊超, 夏成林, 等. 一种基于 Mark 点的点胶机器人视觉目标定位方法[J]. 智能系统学报, 2018, 13(5): 728–733. 英文引用格式:PENG Gang, XIONG Chao, XIA Chenglin, et al. A method of vision target localization for dispensing robot based on mark point[J]. CAAI transactions on intelligent systems, 2018, 13(5): 728–733. A method of vision target localization for dispensing robot based on mark point PENG Gang1,2 ,XIONG Chao1,2 ,XIA Chenglin2 ,LIN Bin3 (1. School of Automation, Huazhong University of Science and Technology, Wuhan 430074, China; 2. Key Laboratory of Image Processing and Intelligent Control of Education Ministry, Huazhong University of Science and Technology, Wuhan 430074, China; 3. Shenzhen Haisike Automation Technology Co. Ltd., Shenzhen 518109, China) Abstract: To address the problem of visual localization of polychlorinated biphenyl (PCB)-dispensing robots in industrial production, a visual localization algorithm based on mark point is proposed in this paper. The results of traditional template matching, Sift and Surf algorithms, were compared and it was found that these algorithms are inadequate for the identification and location of Mark point. Meanwhile, the geometry features of the Mark point and the real-time requirements of the algorithm were considered so that an improved template-matching algorithm based on Mark point geometry features was realized. Experimental results show that this improved template-matching algorithm based on Mark point geometry features can keep good invariance under translation, scale, and rotation, which can accurately identify and locate the mark points, and then indirectly locate the PCB target points while satisfying engineering reliability and real-time constraints. Keywords: PCB; dispensing robot; Mark point; assistant; visual localization; geometric features; improved template matching; invariance 在 3C 行业的印刷电路板 (PCB) 制造过程中, 为了实现点胶机器人对目标的定位,常采用 Mark 点辅助的方式。首先,机器人系统对 PCB 上的 Mark 点进行视觉定位,然后根据 Mark 点与目标 的相对位置关系,可计算出目标位置。其中,Mark 点定位精度直接影响点胶精度。通过优化 Mark 点识别与定位算法,可以提高操作的定位精度和 收稿日期:2017−05−09. 网络出版日期:2018−04−18. 基金项目:2016 年深圳市科技计划项目 (CYZZ20160412111639184). 通信作者:彭刚. E-mail:penggang@hust.edu.cn. 第 13 卷第 5 期 智 能 系 统 学 报 Vol.13 No.5 2018 年 10 月 CAAI Transactions on Intelligent Systems Oct. 2018