Three-dimensional reconstruction method

Abstract

The invention discloses a three-dimensional reconstruction method capable of obviously increasing the time efficiency of method realization. The three-dimensional reconstruction method comprises the following steps of: (1) feature point matching: carrying out feature extraction on an image by virtue of a sift method, determining a matching relationship by virtue of the nearest neighbour matching method, determining matching by the ratio of a next nearest neighbour Euclidean distance to the nearest neighbour Euclidean distance, and accurately matching by a homographic and self-adaptive non-maximum value suppression processing method; (2) quasi-dense matching: processing the feature matching points obtained in the step (1) by a quasi-dense matching method; (3) re-sampling; (4) generation for an initial surface patch: generating an initial quasi-dense spatial surface patch from the quasi-dense matching points through spatial triangularization; (5) surface patch diffusion: diffusing the initial surface patch by virtue of the characteristic of normal and position similarity of the adjacent surface patches, and gradually obtaining dense spatial surface patches; (6) surface patch filter: eliminating exterior points by virtue of geometric consistency constraint and gray-level consistency constraint.

Description

technical field [0001] The invention belongs to the technical field of computer image processing, and in particular relates to a three-dimensional reconstruction method. Background technique [0002] The ultimate goal of 3D reconstruction is to restore the 3D model of the scene, and image-based 3D reconstruction is one of the main means to obtain the 3D model. This method can be regarded as the reverse process of photography. It is relatively low cost, only needs to provide ordinary camera equipment, and has a wide range of application scenarios. Among them, the multi-view stereo matching method has received extensive attention in the field of 3D reconstruction. [0003] The multi-view stereo matching method (Multi-View Stereo, MVS) uses a single or multiple cameras to collect multiple images of a scene (or object) from different perspectives, and then uses the stereo matching information of these multi-view images to restore the 3D model of the scene. . It includes four ...

AI Technical Summary

Problems solved by technology

[0004] The patch diffusion criterion of the PMVS method is to try to reconstruct a patch for each image block in each image, so the core step of the method is patch diffusion, but because the Harris and DoG methods are used in the PMVS method for image feature point extraction and matching processing, the result is sparse matching points, and the initial patch generated by its triangulation is also sparse, so that the patch diffusion starts from the sparse initial patch, resulting in a large workload and a long time for subsequent diffusion.

Images