Online education scene student attention recognition method for CPU operation optimization

A recognition method and attention technology, applied in the field of computer vision, can solve problems such as high performance overhead, and achieve the effect of reducing performance overhead, reducing cost, and increasing overall fit

Pending Publication Date: 2021-04-02
NORTHWESTERN POLYTECHNICAL UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The method based on camera video information needs to process and recognize continuous video frames, and has a large performance overhead, which is difficult to meet the needs of practical applications.

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
  • Online education scene student attention recognition method for CPU operation optimization
  • Online education scene student attention recognition method for CPU operation optimization
  • Online education scene student attention recognition method for CPU operation optimization

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment

[0042] 1. Implementation conditions

[0043] In this embodiment, the central processing unit is CPU i7-6700HQ@2.60GHz, memory 32G, graphics processor is Geforce GTX1070 GPU, Windows 10 operating system, using Pytorch deep learning framework and TVM model reasoning framework.

[0044] The data used in the embodiment is collected from the computer camera data under the online education environment of 112 students, including 9068 sections of video clips with a length of 10 seconds, including 7255 sections of training videos, 1813 sections of test videos, and the attention score S∈[0, 1.0], 0 means that the attention is not focused, and 1.0 means that the attention is fully focused, and the attention score is marked by 5 annotators.

[0045] 2. Implementation content

[0046] First, use the training set data to train the deep model. Then, use the TVM inference framework to optimize the inference of the deep model, and test the error between the attention score and the real v...

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 online education scene student attention recognition method for CPU operation optimization. The method comprises the steps: firstly carrying out the face detection and facekey point detection of each frame of image in a training data set through employing an MTCNN face recognition model, obtaining a face image and face key points, carrying out the face alignment throughemploying affine transformation based on the face key points, and performing attention scoring on the human face; constructing an EngageCNN model on the basis of an EngageDetection network, performing full-supervised training on the EngageCNN model by adopting an aligned face image and an attention score, and optimizing the operation speed of the EngageCNN model on a common CPU to obtain an optimized EngageCNN model; performing attention evaluation on the face image of the student in the class process by adopting the optimized EngageCNN model. The method is high in processing speed, high in accuracy and capable of conducting face detection on the low-resolution image.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and in particular relates to a method for identifying a student's attention. Background technique [0002] With the development of the times, the society pays more and more attention to education, and people's cognition and research on the teaching process have become more in-depth, and they have begun to realize the complexity of student behavior in classroom teaching. Online education is different from teaching in the classroom. Teachers cannot see all the students intuitively to understand the students' classroom engagement status. Using technical means to obtain students' classroom engagement status will provide powerful help for teachers to improve students' classroom learning efficiency. Student attention recognition is an important research project in the smart classroom. At present, there are two main technical routes for attention recognition tasks: the method based on wearable ...

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): G06K9/00G06N3/04G06Q50/20
CPCG06Q50/205G06V40/171G06V40/172G06N3/045
Inventor 王琦吴越李学龙
Owner NORTHWESTERN POLYTECHNICAL UNIV
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