Target reconstruction method based on geometric constraint

Abstract

The invention relates to a target reconstruction method based on a geometric constraint and belongs to the computer vision field. The method comprises the following steps of through a structure from motion (SFM) method, acquiring initial point cloud; through image characteristic point clustering, acquiring a classification result of characteristic points, wherein the classification result means aneighborhood relation of similar portions in an image; carrying out normal characteristic clustering of the initial point cloud, and using a corresponding relation between the classification result ofthe image characteristic points and an initial point cloud clustering result to define a geometric structure of the initial point cloud; using the geometric structure to acquire a sparse portion in the initial point cloud, defining the portion as a ''hole'', and then using a combined structure constraint of a ''hole'' area to carry out fitting of a space plane and a curved surface through an RANSAC method and a least square method; and sampling a fitted surface, adding an acquired three-dimensional point into the initial point cloud so as to acquire a dense point cloud model, and finally using a Poisson surface to reconstruct and acquire a three-dimensional model of a target. Through an experiment result, implementation of the method is verified and a good effect is achieved.

Description

technical field [0001] The invention relates to a method for object reconstruction based on geometric constraints, which uses the geometric structure constraints existing in the point cloud of the object's three-dimensional space to perform three-dimensional reconstruction on the object; the method solves the lack of reconstruction results caused by sparse texture in traditional algorithms Part of the repair problem further improves the reconstruction effect of smoother or overexposed surfaces. The invention belongs to the field of computer vision. Background technique [0002] Image-based 3D reconstruction has always been a research hotspot in the direction of computer vision. In 1983, Martin proposed the method of using the outline of the object in the image to reconstruct, and then in 1986 and 1987, Chien and Potsmesil respectively proposed the use of orthogonal A method for projecting and extracting an object model and a method for constructing an object model using mult...

AI Technical Summary

Problems solved by technology

The present invention effectively improves the limitations of the existing methods that easily generate holes for missing texture parts, and combines the geometric constraints of image neighborhood information corresponding to three-dimensional points, and achieves better experimental results

Images