Attention detection method fusing multiple discrimination technologies

A detection method and attention technology, applied in the field of computer vision and education informatization, can solve the problems of affecting students' teaching experience and teaching effect, high cost, and large errors of other methods

Pending Publication Date: 2020-10-23
ZHEJIANG UNIV OF TECH
View PDF6 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Some of the methods mentioned above require each student to wear a head-mounted device for measurement, which has the problem o

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
  • Attention detection method fusing multiple discrimination technologies
  • Attention detection method fusing multiple discrimination technologies
  • Attention detection method fusing multiple discrimination technologies

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The present invention will be further described below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, but not to limit the present invention.

[0031] like figure 1 As shown, an attention detection method integrating multiple discriminative techniques of the present invention specifically includes the following steps:

[0032] Step 1: In the face pose estimation stage, the convolutional neural network is used to classify the face pose, and the face is divided into specific pose categories, specifically:

[0033] Step 1.1: Use a deep convolutional neural network to train face images of five different pose categories to obtain a trained face pose classification model M 1 , face pose category label C={c 1 ,c 2 ,c 3 ,c 4 ,c 5}, where c 1 , c 2 , c 3 , c 4 , c 5 Indicates five different face postures, corresponding to the front face, 4...

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 discloses an attention detection method fusing multiple discrimination technologies. The method comprises three stages of human face posture estimation, human face expression analysis and upper body behavior analysis; collected images are subjected to human face posture estimation, human face expression analysis and upper body behavior analysis through a fusion multiple discrimination technology, and then a final attention detection result is obtained in combination with analysis results of the three stages. According to the technology of the invention, no tool is needed, the detection cost is greatly reduced, the economic benefit is improved, and the quantitative analysis of the attention is realized; the attention is divided into four conditions of inattention, attention relative concentration, attention concentration and attention focused concentration according to the quantitative result, and the attention detection accuracy is greatly improved.

Description

technical field [0001] The invention relates to the technical fields of computer vision and educational informatization, in particular to an attention detection method integrating multiple discrimination technologies. Background technique [0002] Whether students concentrate in class is an important indicator of learning efficiency and teaching quality. The traditional analysis of students' attention mainly adopts methods such as classroom observation or scale comparison, and there are obvious deficiencies and lags in the aspects of informatization, standardization and intelligence. With the rapid development of information technology, especially computer vision technology, informatization and intelligence have been widely used in various fields of people's daily life. It is possible to deploy information systems in classrooms to observe and record students' behaviors. Automated observation of student attention provides a technical approach. [0003] With the widespread p...

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
IPC IPC(8): G06K9/00G06K9/62G06N3/04G06N3/08A61B5/16A61B5/11A61B5/00
CPCG06N3/08A61B5/168A61B5/7267A61B5/1128G06V40/174G06V40/172G06N3/045G06F18/25G06F18/214
Inventor 高飞李帅葛一粟卢书芳翁立波张元鸣
Owner ZHEJIANG UNIV OF 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