Desarrollo de un sistema de control de acceso en base a detección de temperatura corporal y al correcto uso de mascarillas en tiempo real.

Abstract

The purpose of this work is to develop a real-time access control system using a Raspberry Pi 4, which integrates temperature measurement by means of a thermographic camera and the detection of the correct use of the mask by means of convolutional neural networks (CNN), with a model built based on Tensorflow and MobileNetV2 that works on the video obtained from the thermographic camera using OpenCV and the RTSP protocol. If a person does not meet any of these requirements, access will not be granted. The implementation consists of three modules: body temperature detection, detection of the correct use of the mask and access control. The requirements for the design of the prototype are detailed, as well as the configuration of the equipment and the necessary coding for its operation. As a result, the access control system establishes six classification cases: high temperature and low temperature in faces without a mask, with a mask that is incorrectly placed and with a mask that is correctly placed.