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

Multi-view real-time human motion, gesture, expression and texture reconstruction system

A human motion, multi-view technology, applied in the field of computer vision, can solve problems such as high environmental requirements

Inactive Publication Date: 2020-11-13
北京未澜科技有限公司
View PDF11 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] It solves the problem that most of the traditional methods for human body reconstruction use wearable sensors or green screen segmentation, which have high environmental requirements

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
  • Multi-view real-time human motion, gesture, expression and texture reconstruction system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] Specific embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings. It should be understood that the specific embodiments described here are only used to illustrate and explain the present invention, and are not intended to limit the present invention.

[0024] First of all, in order to facilitate the understanding of the multi-viewpoint real-time human motion, gesture, expression, and texture reconstruction system provided by the embodiment of the present application, firstly explain its application scenario, the multi-viewpoint real-time human motion, gesture, expression, and texture reconstruction system provided by the embodiment of the present application It is used to provide a system capable of performing three-dimensional reconstruction of the human body; while traditional methods for human body reconstruction mostly use wearable sensors or green screen segmentation methods, which have high requirements o...

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 multi-view real-time human body motion, gesture, expression and texture reconstruction system, which comprises the following steps of: defining a capture area by a plurality of camera frames, and calibrating camera internal parameters and camera external parameters of a plurality of cameras by a camera calibration method; collecting a human body image through the pluralityof calibrated cameras, processing the human body image to transcode the human body image into an RGB image, and then completing single-purpose human body posture estimation; obtaining a hot spot mapand joint affinity of each joint of the human body through single-purpose human body posture estimation, and performing non-maximum suppression on the joint hot spot map to obtain coordinates of eachjoint; therefore, human body three-dimensional joint coordinates are obtained, and a human body three-dimensional reconstruction model is obtained. According to the system, deep learning is utilized to complete estimation of human body postures, and fitting and rendering can be performed on human body models of multiple persons in real time in a test environment.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a multi-viewpoint real-time human body movement, gesture, expression and texture reconstruction system. Background technique [0002] With the improvement of computer computing power and the continuous iteration of graphics cards, deep learning technology has developed rapidly, which has greatly promoted the field of computer vision. The current reconstruction technology is mainly divided into two types, one is to use ordinary RGB cameras to obtain depth information through multi-purpose feature point matching and triangulation, and the other is to directly use depth cameras to obtain depth maps for reconstruction, such as Apple The new iPhoneX released is equipped with a depth camera to complete face reconstruction, pushing this technology to the consumer field. [0003] However, compared with RGB cameras, depth cameras have disadvantages such as large interference from...

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): G06T17/20G06N3/04G06N3/08G06T7/80G06T7/73G06T7/90G06T15/04G06T15/20
CPCG06T17/20G06N3/08G06T7/80G06T7/73G06T7/90G06T15/04G06T15/205G06N3/045
Inventor 张宇翔安亮戴翘楚于涛
Owner 北京未澜科技有限公司
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