Large-scale part three-dimensional reconstruction method based on image sequence

Abstract

The large part three-dimensional reconstruction method based on the image sequence comprises the following steps that S1, an unmanned aerial vehicle carrying a camera flies around a target part, and ato-be-reconstructed image sequence is obtained; s2, adopting an SIFT algorithm and an SURF algorithm to jointly extract image feature points; s3, estimating camera motion by calculating an essentialmatrix and a basic matrix based on the sparse feature points obtained by the SIFT corner points and the SURF corner points, and registering three-dimensional space points to obtain sparse point cloudof a three-dimensional scene; s4, judging whether the optimized sparse point cloud has a symmetrical repeated structure or not; and S5, taking the sparse point cloud as seed point and reference imageinput, and performing dense reconstruction based on a dense three-dimensional point construction method of multiple views to obtain a low-resolution depth map. The three-dimensional point recovery andcorrection method based on the image sequence has the advantages that the three-dimensional point recovery and correction method based on the image sequence is provided, and construction from the image sequence to the space sparse three-dimensional points is achieved.

Description

technical field [0001] The invention relates to a method for three-dimensional reconstruction of large components based on visual images. Background technique [0002] The overall process of image-based 3D reconstruction technology is as follows: first, image input is obtained by taking images of objects from different perspectives, then extracting feature points of the image set, establishing mutual relations through the matching relationship of feature points between images, and then using multi-view geometric principles to calculate and obtain 3D point coordinates and estimate the camera pose, and then optimize the 3D information through the beam adjustment method to obtain the corresponding sparse 3D result output; the feature point extraction and matching process will be affected by factors such as illumination, occlusion, or repeated appearance of a certain structure in the scene. Getting wrong results will seriously affect the calculation results of the camera project...

AI Technical Summary

Problems solved by technology

[0014] Although the above methods can achieve better reconstruction results, there are still many problems in the overall reconstruction technology; for example, in the incremental method, the matching time efficiency of the image-to-feature point matching stage is low, and clustering operations need to be performed on the feature point descriptors etc. to speed up the matching effect; the repetitive structure in the scene will cause mismatching and cause confusion in the reconstruction results, etc., it needs to start from the geometric structure, time series or background content to obtain the correct reconstruction results; and the overall dense reconstruction less efficient process

Images