Fire safety risk early warning method and system based on visual perception

Abstract

The invention provides a fire safety risk early warning method and system based on visual perception. The method comprises the steps of inputting a fire safety risk index sequence and a fire operation ROI region image into a first network branch, and outputting first fire operation detection scene complexity and a guidance parameter sequence; inputting a wide-view-angle image of the fire operation area into a second network branch to obtain a first regression value sequence and a second regression value sequence; inputting the wide-view-angle image of the fire operation area into a third network branch, performing convolution by the third network branch according to the guidance parameter sequence, the first regression value sequence and the second regression value sequence, and outputting a second fire operation detection scene complexity and a fire safety risk index abnormal value; and generating fire safety early warning information according to the fire risk index abnormal value. The number of times of longitudinal convolution and transverse convolution during extraction of the fire operation image features is adaptively adjusted, redundant information is removed, the detection precision is improved, a more accurate fire risk index abnormal value is obtained, and early warning information is generated.

Description

technical field [0001] This application relates to the fields of artificial intelligence and production safety, in particular to a method and system for fire safety risks based on visual perception. Background technique [0002] In enterprise security, fire safety is of paramount importance. The hot work in the daily maintenance process of enterprises is likely to cause safety accidents, and there are potential safety risks. Hot work usually refers to welding and cutting operations in fire-free areas defined by chemical companies, and temporary operations that may generate flames, sparks, and hot surfaces by using blowtorches, electric drills, and grinding wheels in flammable and explosive places. Different environments have different requirements for hot work operations. Conversely, hot work operations have different requirements on the surrounding environment. The operator's actions also have a certain impact on the safety of hot work, and now the main detection method ...

AI Technical Summary

Problems solved by technology

[0003] The problem with the existing detection methods is that human detection may be highly subjective, and it is difficult to accurately judge whether there is a fire safety risk in the hot work at this moment, and there is a certain lag in human detection, which cannot realize timely perception, resulting in The fire safety risk warning is not timely, which brings safety hazards

Images