Intelligent firefighter posture monitoring method and system

Abstract

The invention provides an intelligent firefighter posture monitoring method and system. The method comprises the steps: acquiring a first monitoring image is acquired, and analyzing a first portrait from the first monitoring image; obtaining a second monitoring image and analyzing a second portrait from the second monitoring image; acquiring a third monitoring image and analyzing a third portraitfrom the third monitoring image; obtaining a personnel posture monitoring result according to the first portrait, the second portrait, the third portrait and a preset machine learning model, wherein the first monitoring image, the second monitoring image and the third monitoring image are monitoring images obtained by monitoring a monitoring area at different angles. According to the invention, the portrait information at different angles can be analyzed according to the existing machine learning model through the portrait information at different angles based on the monitoring results of themonitoring area at different angles, so that the personnel posture monitoring result can be obtained, and the method has higher accuracy and higher operation efficiency.

Description

technical field [0001] The invention relates to the technical field of fire safety management, in particular to a system and method for intelligent firefighter posture monitoring. Background technique [0002] In the field of smart fire protection technology, the detection of personnel posture is a very important detection. Its purpose is to accurately detect and track the posture of personnel in the monitoring area, and to detect dangerous postures of personnel in time. [0003] The detection of human posture in the prior art, such as the published patent document: CN 107886069 A, can only detect people from a plane angle, so the constructed posture detection results are also limited to the plane. This will lead to a problem. In many cases, the plane detection results of different actions of personnel may be the same, which will lead to the fact that potentially dangerous actions cannot be discovered in time, or actions that do not have danger themselves will be detected. ...

AI Technical Summary

Problems solved by technology

This will lead to a problem. In many cases, the plane detection results of different actions of personnel may be the same, which will lead to the fact that potentially dangerous actions cannot be discovered in time, or actions that do not have danger themselves will be detected. It is misjudged as dangerous. Although the action result can be further confirmed by calling the surveillance video, it will take more time and reduce the efficiency of dealing with the problem. Therefore, the above problems need to be improved urgently

Images