Face feature point real-time detection method and detection system based on three-dimensional reconstruction

Abstract

The invention discloses a face feature point real-time detection method and system based on three-dimensional reconstruction, and the method comprises the steps: (1) collecting a face image frame, andreconstructing a face geometric model in real time through employing a geometric reconstruction algorithm; (2) preprocessing the human face geometric model, and extracting human face point cloud data; (3) inputting the human face point cloud data into a FacePointNet consisting of a coarse PlainFPN network and a block cascade network Cascading FPN to carry out human face three-dimensional featurepoint detection, so as to obtain human face three-dimensional feature points; Wherein the coarse PlainFPN network is used for detecting cheek edge feature points and coarse-precision internal featurepoints of a human face, and the Cascade FPN divides human face point cloud data into a plurality of blocks according to the coarse-precision internal feature points and detects the fine-precision internal feature points of each block respectively. By using the method of the invention, the accuracy and real-time performance of the face three-dimensional feature point detection method can be improved.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and in particular relates to a real-time detection method and detection system of facial feature points based on three-dimensional reconstruction. Background technique [0002] With the popularization of mobile RGB-D cameras, consumer-grade RGB-D cameras mounted on mobile devices will directly reach consumer end users, which is bound to bring profound progress to 3D vision. The 3D information modeling of the face is the basis of various fields such as mobile security, mobile AR, and mobile VR, and provides infinite possibilities for more abundant mobile applications. In the 3D information of the face, the most expressive and practical value is the geometric grid, appearance texture and 3D feature points of the face. However, the computing power and storage capacity of mobile devices are limited, so it is necessary to design a friendly interactive system and efficient algorithms on mobile...

AI Technical Summary

Problems solved by technology

However, some models of the existing algorithms are too complex and the operation efficiency is low, while the accuracy of the other part of the model results cannot meet the requirements

Images