An improved Openpose-based classroom multi-person abnormal behavior and mask wearing detection method

Abstract

The invention discloses an improved Openpose-based classroom multi-person abnormal behavior and mask wearing detection method, and the method comprises the steps of detecting students with abnormal behaviors in a classroom through employing the improved Openpose and the position and position relation of all joint points in student postures and an SSD mask detection algorithm integrated with an FPN; reminding students timely to participate in class and feeding back results to teachers, and performing teaching reform and summarization after class. According to the method, the improved Openpose model, the multi-person mask detection model and the intelligent health module are utilized; abnormal behaviors of the students in class can be detected and fed back to the teacher in time, the students can be reminded to join the class, and in addition, the invention can also remind students sitting up for a long time to get up.

Description

technical field [0001] The invention relates to the technical field of an improved Openpose-based classroom abnormal behavior of multiple people and a mask wearing detection method, in particular to an improved Openpose classroom multi-person abnormal behavior and a mask wearing detection method. Background technique [0002] Artificial intelligence related fields can be said to be the leader in emerging technologies in recent years. With the continuous deepening of its research, the application direction of artificial intelligence technology has become more and more extensive. One of the important application directions is the detection of human body posture, which has a wide range of applications and rich application value in the fields of behavior detection, video capture and computer graphics. [0003] In traditional teaching, the evaluation of teaching behavior is usually based on human analysis. The evaluation results are relatively subjective and require a long perio...

AI Technical Summary

Problems solved by technology

The disadvantage of this method is that this method spends a lot of money but only stays at the level of collecting classroom surveillance video, and does not do a deeper level of classroom teaching quality evaluation

The disadvantage of this method is: the student violation detection module is used to count the student violation situation in the room according to the fixed time interval, which lacks real-time performance

For example, the front of the mask is dark and facing outwards; this method does not determine whether the person is wearing the mask correctly

Images