Three-dimensional human face reconstruction method based on stereoscopic vision

Abstract

The invention relates to a three-dimensional human face reconstruction method based on stereoscopic vision of two eyes. Steps for implementing the method are as follows: (1) using two cameras to respectively take a picture of a human face from two different angles; (2) respectively determining an internal parameter matrix and an external parameter matrix of each camera; (3) carrying out extreme line correction and picture conversion according to the determined data; (4) utilizing a Harris corner detection operator to extract characteristics of the human face, and carrying out initial matchingby utilizing a local template window method and extreme line restriction; (5) starting from an initial matching assemblage, and obtaining a sparse matching assemblage by utilizing a seed point growing algorithm; (6) taking the sparse matching assemblage as a guiding point and carrying out a dynamic planning algorithm so as to finish dense matching; and (7) calculating three-dimensional coordinates of actual physical points on the human face according to the determined data and the matching relationship, thereby reconstructing a three-dimensional point cloud of the human face.

Description

Technical field: [0001] The invention belongs to the technical field of binocular stereo vision, relates to the problem of three-dimensional face reconstruction based on stereo vision, and in particular relates to a method for obtaining a three-dimensional face cloud using a seed point growth algorithm and a dynamic programming algorithm based on guide point constraints . Background technique: [0002] Binocular stereo vision technology is a passive three-dimensional measurement technology, which includes camera calibration, image pair matching, three-dimensional information restoration and other main processes. The 3D face reconstruction technology based on binocular stereo vision takes two face images with two calibrated CCDs placed at different angles, and then establishes the correspondence between the pixels of the two images to restore the 3D face coordinate information. Stereo vision technology can obtain dense 3D point cloud coordinates of the face without projecti...

AI Technical Summary

Problems solved by technology

The accuracy of global optimal algorithm matching is high, but the algorithm is complex and the amount of calculation is large, which is not conducive to the realization of real-time acquisition and calculation

[0004] The existing 3D face reconstruction algorithms based on binocular stereo vision have obvious shortcomings: they either use a purely local optimal algorithm or a purely global optimal algorithm, so the algorithm cannot guarantee both the accuracy of the reconstruction and the accuracy of the reconstruction. Speed; and the prior model knowledge of the face is relatively rich. The face is mainly composed of major organs such as eyes, nose, and mouth. The common feature of them is that the contour line is relatively obvious.

However, the existing algorithms do not make full use of this rich prior knowledge, or even use it, but too many human intervention factors are added to the algorithm, and human assistance is needed to extract some feature points or feature lines, which reduces the The degree of automation of the reconstruction algorithm is not conducive to building a complete reconstruction system

[0005] Due to the above shortcomings, the existing 3D face reconstruction algorithms cannot obtain satisfactory reconstruction results in practical applications.

Images