Intelligent entrance guard method

Abstract

The invention discloses an intelligent entrance guard control method. The method comprises the following steps of: establishing and marking a mask wearing detection data set; generating a training anchor box suitable for an entrance guard; training an improved YOLOv3 model is; adjusting the confidence coefficient of the model to obtain a mask wearing detection model; acquiring an entrance guard monitoring video image; detecting and judging whether a target exists in the entrance guard monitoring video image or not; under the condition that the target does not exist, obtaining the entrance guard monitoring video image, otherwise, acquiring the position of the target and judging the category of the target, under the condition that the target does not wear a mask, giving out an alarm and displaying a detection result, otherwise, detecting the body temperature of the target, under the condition that the body temperature of the target exceeds a body temperature threshold, giving out an alarm and displaying a detection result, and otherwise, opening the entrance guard gate and continuing the detection of the next frame of video image. With the intelligent entrance guard control method adopted, whether a person wears a mask or not and whether the body temperature is normal or not in a video can be detected in real time, the problems of missing detection and wrong detection caused by complex conditions such as high person advancing speed, object shielding and dim light are effectively reduced, the detection speed is high, and the accuracy is high.

Description

technical field [0001] The invention belongs to the technical field of video surveillance security, and relates to an intelligent access control method. Background technique [0002] All domestic enterprises, shopping malls, and communities are equipped with relevant staff at the entrance to check the temperature of the entering personnel and check whether they are wearing masks. However, this human supervision method increases the operating cost of the enterprise and is inefficient. In order to improve efficiency and reduce the cost of manual supervision as much as possible, intelligent access control detection has become the common choice of many enterprises, shopping malls and communities. [0003] In recent years, researchers have done a lot of innovative research work on image detection in two detection methods based on sensors and image processing. However, problems such as low positioning accuracy, slow measurement speed, and low accuracy rate make it unsuitable for...

AI Technical Summary

Problems solved by technology

[0005] In order to solve the deficiencies in the prior art, this application provides an intelligent access control method, which can detect in real time whether the person in the video information is wearing a mask and whether the body temperature is normal, effectively reducing the complexity caused by the fast moving speed of the person, the obstruction of the object, and the dim light. The problem of missed detection and wrong detection caused by the situation has the advantages of fast detection speed and high detection accuracy

Images