Method for establishing relation between scene stereoscopic depth and vision difference in binocular stereoscopic vision system

Abstract

The invention discloses a method for establishing a relation between a scene stereoscopic depth and a vision difference in a binocular stereoscopic vision system. the method comprises the steps of firstly, solving inner parameters, and relative rotary matrixes and translation vectors of left and right cameras; then, analyzing a main error source and an error model of the binocular stereoscopic vision system; then, analyzing influences of the main error on a base line length and the vision difference of the parallel binocular stereoscopic vision system; then, establishing a common relation model of the scene stereoscopic depth and the vision difference in the binocular stereoscopic vision system; obtaining depth information by a laser distance measuring instrument by selecting a certain amount of demarcation points and carrying out demarcation based on a least square method to solve a relation model between the scene stereoscopic depth and the vision difference in the binocular stereoscopic vision system; and finally, solving the vision difference in left and right images through a corresponding fixed matching method so as to realize accurate recovery and three-dimensional reestablishment of the scene stereoscopic depth. The method has the beneficial effect of directly, simply, accurately and extremely improving the accuracy of the stereoscopic depth recovery and the three-dimensional reestablishment.

Description

technical field [0001] The invention relates to a scene depth recovery and three-dimensional reconstruction method of a stereo vision system with arbitrary configuration, in particular to a model of the general relationship between scene stereo depth and parallax in a parallel binocular stereo vision system, which is suitable for machine vision and photogrammetry Scene Stereo Depth Restoration and 3D Reconstruction in Scene. It belongs to the field of advanced manufacturing and automation. Background technique [0002] The research on binocular stereo vision is one of the hot issues in the field of machine vision. The binocular stereo vision system can realize the stereo depth recovery and 3D reconstruction of scene points. The stereoscopic depth restoration of the scene is to obtain the distance of the scene point relative to a certain camera along the main optical axis direction according to the pixel coordinates of the corresponding image point of the scene point in the ...

AI Technical Summary

Problems solved by technology

However, under realistic conditions, the idealized configuration of the standard parallel binocular stereo vision system is difficult to realize. On the one hand, it is impossible to adjust the positional relationship between the left and right cameras to be completely parallel by mechanical means

For the non-standard parallel binocular stereo vision system, there are mainly error sources such as lens distortion, perspective error and system error in the binocular stereo vision system, which lead to certain problems in the scene stereo depth and parallax relationship model of the binocular stereo vision system. The change of the scene reduces the accuracy of scene stereoscopic depth restoration and 3D reconstruction

[0004] At present, since there is no method that can directly perform scene depth restoration and 3D reconstruction, the existing methods all use indirect methods for scene depth restoration and 3D reconstruction, which are mainly divided into two categories: the first category is through image The method of correction converts the image in the non-parallel axis stereo vision system into the image in the standard parallel axis stereo vision system, and then calls the depth restoration and 3D reconstruction method of the standard parallel axis stereo vision system; the other second type is to convert the scene point The projection lines in the two cameras are reversely extended, and then the optimal method is used to find the closest point to the two projection lines in the scene for depth restoration and 3D reconstruction

The second type of method usually requires initial value estimation first, and then iterative optimization, which is time-consuming and easy to converge to a local optimal solution, so it is rarely used in practical applications.

Therefore, at present, the first type of method is generally used for scene depth restoration and 3D reconstruction in stereo vision, but when using the first type of method, it is necessary to perform image correction first, which is also a time-consuming step, and it will be in the transformation process of image correction Errors are generated in the scene, which affects the scene stereo depth and parallax relationship model, and also reduces the accuracy of scene stereo depth recovery and 3D reconstruction

Images