基于结构光投影三维重建的人脸特征检测  

Face Feature Detection Based on Structured Light Projection Three-Dimensional Reconstruction

作　　者：夏晨旭 郝群 张一鸣[2] 张韶辉 李凡飞 杨智慧 孙建坤 Xia Chenxu;Hao Qun;Zhang Yiming;Zhang Shaohui;Li Fanfei;Yang Zhihui;Sun Jiankun(School of Opto-Electronic Engineering,Chang Chun University of Science and Technology,Changchun 130022,Jilin,China;School of Optics and Photonics,Beijing Institute of Technology,Beijing 100081,China)

机构地区：[1]长春理工大学光电工程学院,吉林长春130022 [2]北京理工大学光电学院,北京100081

出　　处：《激光与光电子学进展》2023年第22期178-184,共7页Laser & Optoelectronics Progress

基　　金：科技部重点研发引力波专项(2021YFC2202400)。

摘　　要：人的面部结构信息具有非常高的独特性,通过对人脸进行三维测量和重建,所得数据可以用于人脸识别、医学整形等用途。利用结构光投影技术,通过投射特定编码的近红外光栅条纹到人脸上,解算得到人脸的三维形貌。同时根据二维纹理图像进行人脸特征点的检测与识别,获取人脸关键特征点的分布。最后结合二维分布的特征点和三维的点云信息,实现对人脸关键特征信息的准确获取与理解,为未来三维人脸检测的应用,如医学医疗、人脸识别检测、虚拟人类的数据输入等提供参考。The facial structure information of a person includes a high degree of uniqueness.Data obtained from 3D measurements and reconstruction of the face is useful in facial recognition and medical plastic surgery.In this study,structured light projection technology is used to project a specially coded near-infrared grating stripe onto the face to facilitate the calculation of a 3D appearance of the face.Simultaneously,the facial feature points are detected using 2D texture images,and the distribution of key facial feature points is obtained.Finally,accurate acquisition and understanding of key facial feature information is achieved by combining 2D distributed feature points and 3D point cloud information.This provides reference for future applications of 3D facial detection,such as medical treatment,facial recognition detection,and virtual human data input.

关 键 词：结构光 三维重建 人脸特征检测 近红外条纹 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]