Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Real-time three-dimensional reconstruction method for human face based on RGBD camera

A three-dimensional reconstruction and face technology, applied in the field of computer vision, can solve problems such as good expression effect, and achieve the effect of good expression effect, small amount of calculation, and easy calculation.

Active Publication Date: 2018-06-12
SHENZHEN ORBBEC CO LTD
View PDF8 Cites 28 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problem that there is no real-time three-dimensional face reconstruction method with good expression effect in the prior art, the present invention provides a real-time three-dimensional face reconstruction method based on RGBD camera

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Real-time three-dimensional reconstruction method for human face based on RGBD camera
  • Real-time three-dimensional reconstruction method for human face based on RGBD camera

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0015] The Development of 3D Reconstruction of Human Face

[0016] Real-time 3D reconstruction of human face is a very important research problem. This research field has a wide range of application scenarios, such as intelligent monitoring, robotics, and human-computer interaction. With the development of technologies such as computer vision, image processing, and learning, more and more face reconstruction methods have been proposed. Ordinary video cameras can provide rich color and texture information, which is very useful for 3D reconstruction of faces, but the data captured by them are easily affected by illumination changes, and in some complex scenes, the texture of background and foreground may highly similar. Compared with traditional two-dimensional grayscale or color images, depth images can provide distance information of the subject to the camera. Using the depth value of each pixel position and the internal parameter information of the camera, the shape and siz...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a real-time three-dimensional reconstruction method for a human face based on an RGBD camera, which comprises the steps of S1, collecting a color image and a depth image; S2, obtaining a first point set; S3, solving the head attitude, an identity coefficient and an expression coefficient of the human, and constructing the data offset of a texture image; S4, calculating a current human face model and a human face three-dimensional geometric model; and S5, obtaining an updated human face three-dimensional geometric model. The beneficial effects are that the three-dimensional reconstruction method for the human face based on the RGBD camera further constructs the data offset of the texture image on the basis of a human face multilinear model and a human face hybrid shape model by using the collected color image and depth image so as to obtain the human face three-dimensional geometric model, and the method is small in calculation amount and easy to realize real-timecalculation; and precise geometric detail and texture modeling is achieved by adopting a small storage capacity, thereby being a real-time human face three-dimensional reconstruction method with a good expression effect.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a real-time three-dimensional reconstruction of human face based on an RGBD camera. Background technique [0002] With the development of RGBD cameras and computer vision, 3D reconstruction technology shows broad application prospects. Among them, the rapid reconstruction of face geometry and reflectance based on RGBD cameras on smart mobile devices will have a wide impact in consumer entertainment, animation production, remote collaboration and other fields. [0003] There are two main ways to realize 3D reconstruction of face based on RGBD camera: 1. The method based on multi-linear model and mixed shape model of face; 2. The general 3D reconstruction method based on Volume. The former is to linearly combine several face geometric templates to obtain the final 3D model. The number of geometric templates determines the expressive ability of the model. Therefore, the mod...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06T17/00
CPCG06T17/00G06T2207/10024G06T2207/10028G06T2207/30201
Inventor 刘烨斌安亮黄源浩
Owner SHENZHEN ORBBEC CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com