Smoke detection method and system for infrared image temperature information recognition for tunnel fire prevention

Abstract

The invention discloses a smoke detection method and system for tunnel fire-resistant infrared image temperature information identification, wherein the method comprises the following steps: obtaininginfrared images in a tunnel periodically; converting the gray values of the infrared images into temperature values, and obtaining the temperature distribution map of the infrared images; extractingshape features from the temperature distribution map, and obtaining the smoke shapes of two adjacent frames of images; judging whether fire disaster smoke exists or not according to a preset smoke shape change threshold; calculating two smoke shape area gravity centers if the fire disaster smoke exists according to the judgement result, and judging whether the deviation degrees of two gravity centers are less than preset threshold values or not; judging that the two smoke shape area gravity centers are overlapped if the deviation degrees of the two gravity centers are less than the preset threshold values, and sending a fire disaster early warning signal and fire disaster source position information. The method can be used for effectively solving the problem that the image effect of visible light in a tunnel environment is not clear; meanwhile, the problem that the extracting features of a current two-value method are inaccurate is effectively solved.

Description

technical field [0001] The invention relates to the field of fire smoke detection, in particular to a smoke detection method and system for identifying infrared image temperature information for tunnel fire prevention. Background technique [0002] With the expansion of highway construction scale, my country has become the country with the largest number of tunnels and the most complicated conditions in the world. The speed of vehicles and the density of traffic in the tunnel increase, resulting in an obvious upward trend in tunnel fire accidents. The tunnel environment is quite special, and the fire monitoring of the tunnel is particularly important. [0003] However, the data collected by traditional smoke detectors and temperature detectors are easily affected by surrounding environmental factors, which will greatly reduce the accuracy of fire detection and cannot accurately locate the location of the fire. In addition, the use of visible light image detectors for fire ...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to apply infrared image information fusion technology to tunnel fire protection to solve the problem of low accuracy of smoke recognition and judgment

Images