Flue gas layer height detection method and detection system based on image recognition

Abstract

The invention provides a flue gas layer height detection method and detection system based on image recognition. The detection system comprises a flue gas image collection module used for collecting a full-view-field flue gas layer image in a to-be-monitored space; a space coordinate construction module is used for constructing a space three-dimensional coordinate system of a to-be-monitored space and carrying out space position association with the flue gas image collection module so as to realize fixed-point collection of full-view-field flue gas layer images; a flue gas image processing module is used for extracting a gray value of the full-view-field flue gas layer image and recognizing pixel points belonging to a flue gas area according to the gray value; a flue gas layer height collection module is used for determining the flue gas layer height according to the coordinate values of the lower edge points of the pixel points belonging to the flue gas region. According to the general law of fire flue gas science, region division of the flue gas layer, the transition layer and the cold air layer is performed on the space to be monitored through the K-means clustering algorithm, so that the height of the flue gas layer can be recognized more accurately and quickly.

Description

technical field [0001] The invention relates to the technical field of fire detection, in particular to a smoke layer height detection method and detection system based on image recognition. Background technique [0002] In a building fire, the height of the smoke layer is an important parameter affecting personnel safety. It plays a very important role in the application of fire area simulation model, smoke exhaust system effectiveness evaluation and performance-based fire protection design. In a real fire, there is no very clear boundary between the upper layer of smoke and the lower layer of air, but a transition layer with a certain thickness. In this environment, the height of the smoke layer often takes the height of a certain virtual boundary plane (hereinafter referred to as the interface) in the transition layer. And this virtual interface needs to be obtained by a certain calculation method according to the difference in characteristics of the gas in the smoke la...

AI Technical Summary

Problems solved by technology

In these cases, although the smoke can form obvious stratification, the overall temperature of the smoke layer is low and the gradient is small, which is unfavorable for the calculation of the height of the smoke layer

Among them, the small temperature gradient will make the calculation results of subjective methods such as the N percentage method very sensitive to artificially given parameter values. In this case, it is difficult to correctly calculate the height of the smoke layer with artificially given parameter values; When the temperature is low, the corresponding temperature data tends to oscillate more obviously, which makes the homogeneous degree method also face greater difficulties

Images