Check patentability & draft patents in minutes with Patsnap Eureka AI!

Face key point positioning method and device, terminal and storage medium

A face key point and positioning method technology, applied in neural learning methods, instruments, biological neural network models, etc., can solve problems such as limited algorithm performance, low positioning accuracy, difficult face key points, etc., to achieve face key points The effect of positioning improvement

Pending Publication Date: 2022-03-15
深圳市美通视讯科技有限公司
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of the related technologies mentioned above, the inventor believes that although the use of a relatively large network can improve the positioning accuracy, there will be a problem of efficiency, and it is difficult to perform real-time face key point positioning; The amount of parameters is relatively small, but the algorithm performance is limited and the positioning accuracy is low

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
  • Face key point positioning method and device, terminal and storage medium
  • Face key point positioning method and device, terminal and storage medium
  • Face key point positioning method and device, terminal and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053]In order to make the purpose, technical solutions and advantages of this application clearer, the following in conjunction with the attached figure 1 - attached Figure 7 And embodiment, this application is described in further detail. It should be understood that the specific embodiments described here are only used to explain the present application, not to limit the present application.

[0054] In recent years, with the rapid development of convolutional neural networks, a large number of methods based on deep learning have been proposed. Among them, two types of methods based on coordinate regression and heat map regression are favored because their performance is superior to traditional methods. The coordinate regression method uses image information to directly predict the coordinate values ​​of the key points of the face, while the heat map regression method converts the problem of face key point positioning into a heat map estimation problem for solution. Gene...

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 relates to the field of computer vision, in particular to a face key point positioning method and device, a terminal and a storage medium, and the method comprises the steps: obtaining face image information in real time; carrying out key point positioning on the face image information by adopting a lightweight coordinate regression network model and outputting key point positioning information; wherein the lightweight coordinate regression network model adopts an SE-Sandglass structure as a backbone network. According to the invention, face key point positioning is realized based on the lightweight coordinate regression network model, the method can be applied to a system with limited computing resources, real-time face key point positioning is realized, and the positioning precision is improved.

Description

technical field [0001] The present application relates to the field of computer vision, in particular to a method, device, terminal and storage medium for locating key points of a human face. Background technique [0002] With the development of modern life, cars are becoming more and more popular in life. The rapid increase in the number of cars has brought convenience to people, but it has also led to more traffic accidents, among which the proportion of accidents caused by the driver's personal factors is as high as 70%. above. Therefore, the development of a fatigue driving monitoring system is an effective means to reduce the incidence of traffic accidents, and face key point positioning is an essential function of the system. Functional modules such as yawn judgment, blink judgment, and distraction judgment in the fatigue driving monitoring system all rely on the continuous and stable face key point positioning algorithm. According to the face key point positioning al...

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): G06V40/16G06V10/46G06V10/82G06N3/04G06N3/08G06K9/62G06V10/764
CPCG06N3/08G06N3/045G06F18/241
Inventor 孙雨涵陈永辉
Owner 深圳市美通视讯科技有限公司
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com