Binocular Stereo Vision Automatic Measurement Method Based on Parallax Optimization Algorithm

Abstract

The invention discloses a parallax optimization algorithm-based binocular stereo vision automatic measurement method. The method comprises the steps of 1, obtaining a corrected binocular view; 2, matching by using a stereo matching algorithm and taking a left view as a base map to obtain a preliminary disparity map; 3, for the corrected left view, enabling a target object area to be a colorized master map and other non-target areas to be wholly black; 4, acquiring a complete disparity map of the target object area according to the target object area; 5, for the complete disparity map, obtaining a three-dimensional point cloud according to a projection model; 6, performing coordinate reprojection on the three-dimensional point cloud to compound a coordinate related pixel map; 7, using a morphology method to automatically measure the length and width of a target object. By adopting the method, a binocular measuring operation process is simplified, the influence of specular reflection, foreshortening, perspective distortion, low textures and repeated textures on a smooth surface is reduced, automatic and intelligent measuring is realized, the application range of binocular measuring is widened, and technical support is provided for subsequent robot binocular vision.

Description

technical field [0001] The invention relates to the field of binocular stereo vision measurement, in particular to a binocular stereo vision automatic measurement method based on a parallax optimization algorithm. Background technique [0002] In recent years, the application of robot self-guided, unmanned driving, concealed military reconnaissance, medical diagnosis and industrial inspection has become more and more extensive. important basis. The measurement technology based on binocular stereo vision is an efficient and non-contact advanced detection, measurement and identification technology with considerable development prospects and a wide range of applications. [0003] At present, most of the applications of binocular vision measurement focus on measuring distance, which has certain limitations; and in the application of measuring the size of space objects, it is necessary to select target pixels or set special feature points, which cannot realize automatic object d...

AI Technical Summary

Problems solved by technology

[0003] At present, most applications of binocular vision measurement focus on measuring distance, which has certain limitations; while in the application of measuring the size and size of space objects, it is necessary to select target pixels or set special feature points, which cannot realize the automatic detection of objects. Extraction and automatic measurement hinder the intellectualization and mechanization of industrial production; and the manual operation steps in the traditional measurement method not only increase labor costs but also make the steps more complicated; the qualified detection of parts in industrial inspection is only The detection in a fixed scene cannot realize the automatic measurement of the size of the relative moving object; and for the moving object, it is very inaccurate to manually select the target pixel, and it cannot achieve real-time performance.

More importantly, due to the influence of specular reflection on smooth surfaces, projection reduction, perspective distortion, low texture and repeated texture on binocular matching, the target pixels manually selected may not have effective 3D information

Images