光学学报, 2014, 34 (3): 0315002, 网络出版: 2014-02-28
具重复特征的大物面自动视觉检测中的亚像素级拼接
Sub-Pixel Stitching Method for Large Object with Duplicate Texture of Automatic Visual Inspection
机器视觉 图像处理 亚像素图像拼接 重复纹理特征 光栅 machine vision image processing sub-pixel image stitching duplicate texture grating
摘要
针对自动视觉检测系统中,难以获得具有重复纹理特征的大面积物体的高精度图像问题,提出了一种二维图像光栅的亚像素级定位拼接新方法。采用光栅尺记录物体的位置信息,引入圆盘格标定板对二维运动平台X、Y轴与相机X、Y轴之间的夹角进行准确标定,并建立基于全局物理直角坐标系的二维拼接模型完成图像的拼接。实验结果表明,该方法的标定重复精度可以达到10-4 rad量级,拼接的物理误差为8 μm,拼接精度比校正前提高了近8倍,比已见报道提高1倍以上。该方法已成功应用于导航卫星接收天线电路的在线检测设备,并可广泛推广至检测精度要求达到亚像素级的机器视觉自动化检测领域。
Abstract
Focused on the problems that it′s difficult to obtain high precision mosaic image of object having duplicate texture in the automatic visual inspection system, a new two-dimensional (2D) image mosaic method based on sub-pixel grating positioning is presented. The method uses grating to record positions of object and calibration plate to accurately calibrate angles of X and Y axes between platform and camera, and build a 2D stitching model based on global Cartesian coordinate system to complete image stitching. Experimental results show that the method′s calibration repeatability reaches 10-4 rad order of magnitude, with average physical error of 8 μm, and stitching precision increases nearly 8 times than that of not correction, 2 times better than the method that has been reported. The method has been successfully used in the online automatic inspection equipment for ceramic substrate of navigation satellite′s receiving antenna circuit. The research result can be widely applied in machine vision automated inspection fields that require sub-pixel level detection precision.
宋昀岑, 陈伟, 叶玉堂, 刘娟秀, 黄柄权, 郭涛, 赵津. 具重复特征的大物面自动视觉检测中的亚像素级拼接[J]. 光学学报, 2014, 34(3): 0315002. Song Yunceng, Chen Wei, Ye Yutang, Liu Juanxiu, Huang Binquan, Guo Tao, Zhao Jin. Sub-Pixel Stitching Method for Large Object with Duplicate Texture of Automatic Visual Inspection[J]. Acta Optica Sinica, 2014, 34(3): 0315002.