基于计算机视觉的卷烟包装方正度测量方法

A method for measuring degree of square of cigarette packet based on computer vision

为准确测量卷烟包装的方正度,提出了一种基于计算机视觉的盒包方正度测量方法。首先对测量装置中各器件间的几何参数以及相机参数和镜头畸变校正系数进行确定;其次通过图像处理算法获得光栅条纹图像,利用相移法和多频外差原理法获取绝对相位值,并结合高度-相位转换关系得到盒包表面各像素点的三维坐标信息;最后通过旋转盒包获取4个不同角度的盒包三维信息,构建点云并计算盒包方正度。结果表明,本文方法的角度测量误差低于0.2°,方正度重复测量标准偏差0.01,测量时间小于3 s,其稳定性和测量精度均能够满足卷烟包装方正度的测量要求。该方法为解决接触式测量过程中盒包形变问题提供了一种技术手段。

In order to measure the degree of square of cigarette packet accurately, a method based on computer vision was proposed. The method includes the following steps： first, determine the geometric parameters between components in the measurement device, camera parameters and the lens distortion correction coefficient; second, obtain raster lines image via image processing algorithm, absolute phase values via phase-shift method and multi-frequency heterodyne principle, and 3D coordinate data of each pixel point on packet surface via the relationship between height and phase; finally, acquire the 3D information of the packet from 4 different angles via turning the packet, then establish the cloud of points and calculate the degree of square of the packet. The results showed that the error of angle measurement was lower than 0.2°, and the standard deviation of repeated measurement for degree of square was 0.01, test time less than 3 seconds. This method features good stability and measurement precision, it provides a technical means for avoiding the deformation of cigarette packet in the process in contact measurement.