基于机器视觉的船体双曲度板测量方法

The Measurement Method of Double-Curved Hull Plate Based on Machine Vision

为测量加工后的双曲度船体外板,搭建由双目视觉传感器及三维数控平台组成的线结构光扫描测量系统,研究摄像机标定、结构光提取细化、双目立体匹配等算法,通过三维数控平台控制双目视觉传感器扫描运动实现扫描测量。同时完成对板材边缘的测量,为实现以板材边缘为基准的曲面匹配算法创造条件。试验证明,该视觉测量系统x、y方向精度为0.04 mm,z向测量误差小于0.5 mm,均满足工程应用要求。

In order to measure the processed hyperbolic hull plate, a line structured light scanning measurement system consisting of binocular vision sensor and three-dimensional numerical control platform is built. The algorithms of camera calibration, structure light extraction and refinement, binocular stereo matching is studied. The scanning measurement is realized by controlling the scanning motion of the binocular vision sensor through the three-dimensional numerical control platform. At the same time, the measurement of the edge of the plate is completed, which creates conditions for the realization of surface matching algorithm based on the edge of the plate. The experimental results show that the precision of the vision measurement system in x and y directions is 0.04 mm, and the precision error in z direction is less than 0.5 mm, which meets the requirements of engineering application.