Face contour point cloud model reconstruction method and device based on multiple cameras

Abstract

The invention provides a face contour point cloud model reconstruction method and device based on multiple cameras. The reconstruction method comprises the following steps: 1) obtaining a face point cloud model based on a Kinect2 camera; 2) triangularizing the obtained point cloud model to obtain a grid model, and performing grid refinement based on an edge scoring function to obtain a complete face point cloud model; 3) acquiring a group of facial feature points based on a binocular camera, and acquiring three-dimensional coordinates of the facial feature points; 4) obtaining point clouds corresponding to the facial feature points in a Kinect2 facial model based on an iterative closest point algorithm, and solving a point cloud conversion matrix of Kinect2 and a binocular camera by usinga singular value decomposition method; and 5) performing position registration on the complete face point cloud model based on the point cloud conversion matrix to obtain a face point cloud model. Theinvention further provides a facial contour point cloud model reconstruction device based on the Kinect2 and the binocular camera so as to realize the facial contour point cloud model reconstructionmethod.

Description

technical field [0001] The invention belongs to the field of three-dimensional point cloud reconstruction, and in particular relates to a multi-camera-based facial contour point cloud model reconstruction method and device. [0002] technical background [0003] With the continuous development of robots, in the fields of oral medicine, facial massage, and beauty care, the research on robots for human facial operations is increasing. When robots in these fields perform operations, they need to obtain more accurate three-dimensional contour information of the face for accurate pose control and operation of the robot. [0004] The acquisition of facial contour point cloud can be realized by 3D reconstruction technology. Currently, 3D reconstruction technology includes contact method and non-contact method. The main representative of the contact method is the three-coordinate measurement method. This method has high precision, but the equipment is expensive and difficult to main...

AI Technical Summary

Problems solved by technology

However, due to the characteristics of no specific corner points and relatively uniform skin color in the facial contour, the complexity of the stereo matching process is increased, and the acquisition of the facial model takes a long time, so it is not suitable for the rapid acquisition of the facial model; the active measurement adopts the method of projected light, Obtaining the three-dimensional information of the irradiated object has the advantages of high efficiency and simple operation. The disadvantage is that the phase change will occur when measuring the object with a large curvature change, which will affect the measurement accuracy of the object.

Among them, the Kinect2 camera has the advantages of high stability in facial model acquisition and face detection, and can quickly acquire facial 3D point clouds. There is a large deviation between the 3D point cloud model of the face and its actual position

Images