A Binocular 3D Reconstruction Method

Abstract

The invention discloses a binocular three-dimensional reconstruction method comprising the following steps of: 1) acquiring an image of an object to be reconstructed by two image acquisition apparatuses with the same model in order to obtain a left image and a right image; 2) calibrating the image acquisition apparatuses by a chessboard method, computing the internal and external parameter and a lens distortion coefficient, processing the left image and the right image to remove distortion in the images; 3) extracting features from the two processed images in the step 2) to obtain the feature points of the two images; 4) matching the feature points by using the feature points of the two images in the step 3) to obtain feature point pairs; 5) performing epipolar geometric constraint detection on the obtained feature point pairs to remove mismatched feature point pairs; and 6) computing three-dimensional coordinates of corresponding points, in a world coordinate system, of the obtained feature points by using the reserved feature point pairs. The binocular three-dimensional reconstruction method may reduce abnormal points and acquires an accurate three-dimensional reconstruction model.

Description

【Technical field】 [0001] The invention relates to computer vision, in particular to a binocular three-dimensional reconstruction method. 【Background technique】 [0002] 3D model reconstruction is a very important research field in computer vision, and it has been widely used in the three major fields of industry, medical treatment and entertainment. At present, 3D model reconstruction is divided into four categories according to technical methods, using structured light reconstruction methods, tomographic reconstruction methods, time-of-flight reconstruction methods, and stereo imaging reconstruction methods. Among them, stereo imaging reconstruction methods are mainly divided into two categories, that is, a reconstruction method using a single image and a reconstruction method using multiple images. The method of reconstruction using a single image can be summarized into the shape from X category, such as shape from contour (contour-based reconstruction), shape from shadin...

AI Technical Summary

Problems solved by technology

The usual binocular 3D reconstruction method, the basic process includes: (1) image acquisition, (2) feature extraction, (3) feature matching, (4) 3D coordinate calculation, the problem after the reconstruction is that step (4) 3D coordinate Abnormal points are easy to appear in the calculation, which will affect the reconstruction effect of the 3D model

Images