Unlock instant, AI-driven research and patent intelligence for your innovation.

Classroom student behavior identification method based on computer vision

A computer vision, student technology, applied in computer parts, computing, character and pattern recognition, etc., can solve the problems of reduced recognition accuracy, skeletal key point judgment, slow model loading and processing speed, etc., to reduce model size, reduce Adverse effects, effects of increasing speed

Pending Publication Date: 2022-03-11
EAST CHINA NORMAL UNIV
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The human joint diagrams extracted by these two behaviors are similar, and cannot be judged directly using bone key points
The existing technology will greatly reduce the recognition accuracy when encountering occluded scenes, and it is also

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
  • Classroom student behavior identification method based on computer vision
  • Classroom student behavior identification method based on computer vision
  • Classroom student behavior identification method based on computer vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The present invention will be further described in detail below in conjunction with specific embodiments and accompanying drawings. The process, conditions, experimental methods, etc. for implementing the present invention, except for the content specifically mentioned below, are common knowledge and common knowledge in this field, and the present invention has no special limitation content.

[0028] refer to figure 1 , the present invention first extracts the key points of the human body as posture information, and inputs the posture information of the key points of the human body into the CNN network to identify four behaviors: sitting upright and listening to lectures, raising hands, turning sideways and bowing the head. Afterwards, the present invention uses the compressed model of YOLO v3 target detection to perform target detection on the student's hand area in the classroom scene. Finally, the present invention fuses the hand area information and posture informa...

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 a classroom student behavior identification method based on computer vision. A human body key point detection algorithm and a target detection algorithm are adopted to identify student behaviors in two stages. Firstly, a human body posture is judged based on human body key points, secondly, hand actions are judged through interaction of hands and objects, and recognition of four behaviors of sitting for listening, hand raising, side leaning and head lowering and two hand behaviors of taking a mobile phone and taking notes is completed. According to the invention, real-time detection of mobile phone playing and writing behaviors can be realized.

Description

technical field [0001] The invention relates to the field of classroom student behavior recognition using computer vision technology, in particular to a computer vision-based classroom student behavior recognition method. Background technique [0002] Classroom is the key to education, which often determines the quality of teaching and the cultivation of students' quality. Paying attention to students' learning behavior and classroom performance in the classroom is an important basis for establishing the teaching evaluation system. The traditional classroom behavior evaluation of students is realized by manual observation and recording, which is obviously time-consuming and labor-intensive. Today, with the vigorous development of artificial intelligence, more and more artificial intelligence technologies are used to identify the behavior of students in the classroom. [0003] Human behavior can be divided into four categories according to the degree of complexity, which ar...

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): G06V40/20G06V10/25G06V10/82G06N3/04
CPCG06N3/045
Inventor 沈超敏赵春彭亚新张桂戌陈杰
Owner EAST CHINA NORMAL UNIV