Three-dimensional coordinate positioning method based on machine vision

Abstract

The invention discloses a three-dimensional coordinate positioning method based on machine vision. The method comprises the steps of (S1) performing image acquisition, preprocessing and contour extraction on a workpiece, (S2) performing distance normalization processing on a feature vector, (S3) determining a candidate matching point set, (S4) obtaining an initial matching point set, and (S5) removing a mismatched point pair. According to the scheme of the invention, a shape context is introduced into the stereo matching of a binocular visual workpiece image, a centroid constraint condition isintroduced, the shape context and a gradient direction histogram are fused to form a joint similarity measurement, an RANSAC is introduced to eliminate mismatched points, high matching precision anda fast matching speed are achieved, and the rapid and accurate workpiece depth information extraction and 3D positioning requirements of binocular vision in the industry are satisfied.

Description

technical field [0001] The invention belongs to the field of robot vision positioning, and relates to a three-dimensional coordinate positioning method based on machine vision. Background technique [0002] With the development of machine vision technology, binocular vision is widely used in object recognition, virtual reality, industrial inspection, robot navigation and aerospace and other fields. In recent years, binocular vision-based workpiece recognition and positioning to provide image information for robot 3-D automatic grasping has become a research focus, among which stereo matching and 3-D information reconstruction of key grasping points are the main research contents. [0003] As a key technology of binocular vision, stereo matching aims to determine the corresponding relationship between pairs of stereo images. A matching algorithm with high precision, fast speed and strong robustness has become the goal pursued by the majority of researchers. Among them, the f...

AI Technical Summary

Problems solved by technology

[0008] The purpose of the present invention is to provide a three-dimensional coordinate positioning method based on machine vision. By introducing the shape context into the stereo matching of the binocular vision workpiece image, and introducing the centroid constraint condition, the shape context and the gradient direction histogram are fused to form a joint similarity measure , introduced RANSAC to eliminate mismatching points, achieved higher matching accuracy and faster matching speed, met the requirements of binocular vision for fast and accurate workpiece depth information extraction and 3-D positioning in industry, and effectively solved the problem of traditional shape The similarity calculation of the context histogram needs to traverse the contour sampling points, the calculation complexity is high, and it cannot meet the real-time requirements of the industry

Images