3D face grid reconstruction method based on video image

A video image, 3D technology, applied in the field of 3D face mesh reconstruction, can solve the problems of manual initialization, high computational cost, neglect, etc.

Active Publication Date: 2016-11-23
SHENZHEN WEITESHI TECH
View PDF3 Cites 27 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The 2D recognition method has few anchor points for locating the shape and appearance, and the 3D method has strong distinguishability and robustness, but matching high-resolution 3D models requires large calculation costs and requires manual initialization
However, the use of cascaded regression applications has been neglected in 3D methods

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
  • 3D face grid reconstruction method based on video image
  • 3D face grid reconstruction method based on video image
  • 3D face grid reconstruction method based on video image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0067] It should be noted that, in the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The present invention will be further described in detail below in conjunction with the drawings and specific embodiments.

[0068] figure 1 It is a system flowchart of a video image-based 3D face mesh reconstruction method and device of the present invention. Such as figure 1 As shown, the present invention provides a kind of 3D face mesh reconstruction method based on video image, and its main content comprises:

[0069] (1) 2D face image input in the video;

[0070] (2) Establishing a linear shape model;

[0071] (3) Estimating face feature points by cascading regression;

[0072] (4) Matching through 3D models;

[0073] (5) 3D reconstruction of the face.

[0074] The 2-dimensional face image input in the video includes the input of face images in various video images;

[0075] Establishing a dense...

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 3D face grid reconstruction method based on a video image. The method mainly includes: inputting a 2D face image in video; building a linear shape model; estimating a face mark point through cascade regression; matching through a 3D model; performing 3D reconstruction on a face. The linear model is built, position and clarity of the mark point are estimated, and face shape is reconstructed by matching a local 3D model; 3D cascade regression is adopted, so that marks in faces in action change are maintained uniform; by selecting a compact 3D point set, the face is completely marked, so that position change of the marks is avoided, and the problems of nonuniformity and self-closing of action change locating points are solved. In addition, 3D marks are adopted for 2D projection, so that calculation expense is reduced greatly. A 3D grid does not contain a background, so that the method is high in universality and good in real-time effect.

Description

technical field [0001] The invention relates to image processing, in particular to performing 3D face grid reconstruction on collected video images by using image data analysis. Background technique [0002] The 3D face mesh reconstruction method based on video images can be used for criminal monitoring, face reconstruction without criminal fingerprints or identity information, can also be used for 3D printing, and can also be used for 3D human face modeling. In fields such as animation production, it has a great influence on various fields. Face recognition methods can be divided into two categories, 2D recognition methods and 3D recognition methods. The 2D recognition method has few anchor points for locating the shape and appearance, and the 3D method has strong distinguishability and robustness, but matching high-resolution 3D models requires large calculation costs and requires manual initialization. [0003] In recent years, 2D recognition methods and 3D recognition...

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): G06T17/30
CPCG06T17/30G06T2200/04
Inventor 夏春秋
Owner SHENZHEN WEITESHI TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap