基于单目视觉的Z轴位置自适应识别定位系统研究  

Research on Z-axis Position Adaptive Recognition and Location System Based on Monocular Vision

作　　者：吴上生[1] 范振辉 杨琪 WU Shangsheng;FAN Zhenhui;YANG Qi(School of Mechanical and Automotive Engineering,South China University of Technology,Guangzhou Guangdong 510640,China;Dongguan Richtek Electronics Co.,Ltd.,Dongguan Guangdong 523650,China)

机构地区：[1]华南理工大学机械与汽车工程学院,广东广州510640 [2]东莞瑞柯电子科技股份有限公司,广东东莞523650

出　　处：《机床与液压》2021年第9期1-5,10,共6页Machine Tool & Hydraulics

摘　　要：针对工业上单目视觉系统难以适应工件Z轴位置变化的问题,开发基于单目视觉的Z轴位置自适应识别定位方法与系统。采用激光三角测距原理检测工件坐标系平面与相机坐标系平面的距离,配合下位机微机控制系统实现工件平台Z轴位置自适应,进一步融合HSV颜色空间模型,通过改进模板匹配算法完成工件识别定位。联合Halcon与Visual Studio进行单目视觉Z轴位置自适应识别定位系统软件开发以及实验验证。结果表明:该系统在工作范围内平均定位误差小于1 mm,具有较好的Z轴位置自适应调节能力和较高的定位精度。Aiming at the problem that the monocular vision system is difficult to adapt to changes of workpiece Z-axis position in industry,a Z-axis position adaptive recognition and location system based on monocular vision was developed.The principle of laser triangulation ranging was used to detect the distance between the workpiece coordinate system plane and the camera coordinate system plane,and cooperated with the lower computer control system,the Z-axis position adaptation of the workpiece platform was realized.Furthermore,the improved template matching algorithm which combined with HSV color space model was used to recognize and locate the workpiece.By combining Halcon with Visual Studio,the software was developed and the experiments were carried out to recognize and locate the workpiece.The experimental results show that the average positioning error of the system is less than 1 mm in the working range,and has good Z-axis position adaptive adjustment ability and high positioning accuracy.

关 键 词：单目视觉 自适应识别定位 激光测距 模板匹配 

分 类 号：TH39[机械工程—机械制造及自动化] TP242[自动化与计算机技术—检测技术与自动化装置]