Classroom behavior detection system based on computer vision

Abstract

The present invention discloses a classroom behavior detection system based on the computer vision, and belongs to the technical field of digital image processing and education information. The systemcomprises a video collection module, a data storing module and a background processing module. The video collection module collects classroom video information; the background processing module converts the video information into image information, and collects attitude information of students, position information of the students, identity information of the students from the image information,determines the behavior of students through the attitude information of the students, and associates the behavior of students, student seats and student identity. The detection system disclosed by thepresent invention has low hardware requirements, can detect ordinary two-dimensional video information, can automatically identify student identity through a face recognition algorithm, can obtain student positions through human body position and seat matching, can adapt to different locations, dynamic change in student seats and other complex and changeable scenes.

Description

technical field [0001] The invention belongs to the field of digital image processing and the field of education information technology, and more specifically relates to a classroom behavior detection system based on computer vision. Background technique [0002] In recent years, with the breakthrough development of machine learning, especially deep learning, combined with the advantages of the era of big data, the technology of digital image signal processing has also made a qualitative leap, in face detection, face recognition, head pose estimation , and various technologies such as body posture detection have gradually matured, and even reached a level beyond human beings. [0003] At the same time, due to the development of hardware technology, more complete information can also be collected through more advanced cameras. For example, through Kinect, a somatosensory device, in addition to collecting ordinary color pictures, it can also collect three-dimensional data of ...

AI Technical Summary

Problems solved by technology

However, this system cannot adapt to the situation where the number of students in the university classroom is not fixed, the student seats are not fixed, and the classroom environment is not fixed, and it is not scalable.

Images