基于双目视觉的板材平面测量研究

Study on Plane Measurement of Plate Based on Binocular Vision

针对传统人工测量板材尺寸精度较低、工作量大、易导致板材表面受损等局限,基于双目视觉技术设计了一种板材尺寸视觉测量系统;通过双目相机采集棋盘格图像,采用MATLAB进行相机标定和图像校正,拍摄左右图像并通过半全局立体匹配算法(SGM,semi global matching)进行特征点立体匹配,重建出目标三维点云模型;为提高目标特征点坐标获取的准确性,提出基于HARRIS的亚像素检测方法;采用区域生长算法结合膨胀和腐蚀操作提取板材表面轮廓,根据三角测量原理计算出板材轮廓上各点的三维坐标从而实现板材的尺寸测量,并进行点云重建增强三维展示效果;实践结果表明亚像素检测方法在角点提取上存在优势,在实际板材测量应用中实现了高精度尺寸测量,满足了工业测量需求。

Aiming at the limitations of traditional manual measurement of plate dimension,such as low dimensional accuracy,large workload,and easy damage to the plate surface,based on binocular vision technology,a vision measurement system for plate dimension is designed.The checkerboard image is collected by binocular camera,the camera calibration and image correction are carried out by MATLAB,the left and right images are taken,and the feature points are stereoscopically matched by the semi global matching(SGM)algorithm to reconstruct the three-dimensional point cloud model of the target.In order to improve the accuracy of target feature point coordinate,a sub-pixel detection method based on HARRIS is proposed.Combined with the expansion and corrosion operations,the region growing algorithm is used to extract the surface contour of the plate,according to the principle of triangulation,the three-dimensional coordinates of each point on the plate contour are calculated to realize the dimension measurement of the plate,and the point cloud reconstruction is performed to enhance the three-dimensional display effect.The practice results show that the sub-pixel detection method has advantages in corner extraction,and the high-precision dimension measurement is realized in actual plate measurement applications,and it meets the requirement of industrial measurement.