Stereo matching method of three-dimensional reconstruction

Abstract

The invention discloses a stereo matching method of three-dimensional reconstruction. The method comprises the steps that first, the accumulation phenomenon of Harris image feature points is improved, the defect of low pixel accuracy is overcome, inhibiting factors are introduced to enable the image feature points to be evenly distributed, and then a Gauss curved surface fitting and interpolating method is used for enabling the acquired image feature points to achieve a sub-pixel level; then SIFT is used for describing the image feature points to generate a feature vector for matching, the problem that the Harris image feature points are sensitive to image gradation nonlinear transformation is solved, then a random sampling algorithm RANSAC with good robustness is used for estimating a fundamental matrix, at the same time, mismatching point pairs are further removed, and at last under guide of the fundamental matrix, convection matching is conducted to search for unmatched image feature point pairs which possibly reflect object structures. The stereo matching method of three-dimensional reconstruction enables the surface structure of objects to be better restored, and is effectively used for non-calibration image information three-dimensional reconstruction.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a stereo matching method in three-dimensional reconstruction. Background technique [0002] The three-dimensional reconstruction based on video sequence images is to ensure that the reconstructed object surface information can correctly express the structure of the object, and the image feature point extraction and matching of video sequence images is the first step in the three-dimensional reconstruction. The extraction and matching of image feature points in 3D reconstruction is a research direction and research hotspot that has attracted much attention in the field of computer vision in recent years. It is the basis of many computer vision theories and practical applications, such as camera calibration, 3D reconstruction, object detection, Motion analysis, etc.; at the same time, image feature point extraction and matching is also a bottleneck in the field of computer ...

AI Technical Summary

Problems solved by technology

However, in some cases where there is no calibration or incomplete information, the epipolar constraint is not available. This requires a relatively accurate estimation of the basic matrix according to the previous rough matching before the epipolar constraint can be used. This affects the accuracy of the three-dimensional stereo matching. Higher requirements are put forward, and the difficulty of image feature point matching is further increased

[0004] At present, the commonly used image feature point extraction algorithm is the Harris algorithm. The Harris image feature points can reflect the structural characteristics of the object, but sometimes there will be corner accumulation in the local area, which is prone to matching errors in the later matching. At the same time, it will reduce the matching efficiency, and the Harris image feature points are pixel-level, which will affect the matching accuracy.

Images