Attendance rate detection method and system based on offline classroom monitoring

Abstract

The invention discloses an attendance rate detection method and system based on offline classroom monitoring, and the method comprises the steps: training a head and body joint detection network model, and optimizing the weight of the model through weighted joint loss; acquiring an offline classroom monitoring video, and extracting key frame images at intervals of a certain frame number; inputting the key frame image into a trained human head and human body joint detection network model to obtain a human head candidate box; adopting a post-processing algorithm to remove repeated frames, background frames and unreasonable frames in the candidate frames so as to obtain the number of people contained in the current key frame; and dividing the number of people detected in the key frame by the number of people to be in class to obtain the attendance rate corresponding to the key frame. According to the method, the attendance number can be obtained, then the attendance rate corresponding to the key frame is obtained, the detection method is high in accuracy, real-time performance and automation degree, and a manager can be helped to rapidly know the real-time distribution condition of the attendance rate of a classroom.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to an attendance rate detection method and system based on offline classroom monitoring. Background technique [0002] There are many types of indicators for offline classroom quality evaluation, such as attendance rate, head-up rate, front row sitting rate, abnormal behavior detection, etc. Among them, attendance rate is a very important indicator. It represents the enthusiasm and interest of students in the classroom, and can also be used as an important reference index for evaluating the level of teachers. At present, there are many commonly used attendance rate statistics methods, but they all have certain disadvantages. For example, offline roll call will take up class time, face attendance machines, fingerprint clock-in machines, etc. need extra budget to purchase equipment, WeChat applet clock-in may There are cases of proxy sign-in and remote sign-in with photos. ...

Images