Forest fire smoke recognizing method and device

Abstract

The invention provides a forest fire smoke recognizing method and device. The method includes the steps of recognizing smoke pixels and non-smoke pixels by means of a multi-channel threshold method and the reflective rates or the brightness temperature values of 36 spectrum channels, obtaining input characteristics of a neural network classifier from the reflective rates or the brightness temperature values of the 36 spectrum channels, training the neural network classifier by means of smoke input characteristics of the smoke pixels and non-smoke input characteristics of the non-smoke pixels, obtaining a smoke recognizing and classifying unit, and precisely recognizing the smoke pixels and the non-smoke pixels by means of the smoke recognizing and classifying unit. The method achieves precise classification of the smoke pixels, and the probability that cloud pixels are mistaken for the smoke pixels is greatly reduced due to the fact that the non-smoke pixels include the cloud pixels. Besides, due to the fact that the smoke pixels include thin-smoke pixels, the thin-smoke pixels can be precisely recognized by means of the smoke recognizing and classifying unit, and precision of thin-smoke area recognition is further improved.

Description

technical field [0001] The present application relates to the technical field of fire detection, in particular to a method and device for identifying forest fire smoke. Background technique [0002] Forest fire is one of the major disasters in the world today, which is characterized by strong suddenness and great destructive power. Forest fires will cause major economic losses, and the large amount of greenhouse gases and aerosols released by forest fires will change the chemical composition of the earth's atmosphere, which will have a major impact on the global environment and climate. Smoke is a product of the early stages of a forest fire. Therefore, the smoke recognition of forest fires is an important part of forest fire detection, which can provide a basic guarantee for the modern management of forest and grassland fire prevention. [0003] Many researchers at home and abroad use NOAA / AVHRR (National Oceanic and Atmospheric Administration / The Advanced Very High Resol...

AI Technical Summary

Problems solved by technology

Its main disadvantage is that there are only 5 channels in AVHRR data, and there is great uncertainty in the method of obtaining training samples, so it is difficult to recognize thin smoke

[0006] Xie et al. (2007) proposed a multi-channel threshold algorithm to identify smoke pixels based on spectral analysis of 8 spectral band data of MODIS with different types of ground objects, although this method has a high performance for the detection of thick smoke Accuracy, but the detection accuracy for thin smoke areas is very low, and the threshold needs to be changed appropriately with changes in seasons and regions, and the stability is poor

[0007] Wang Jing et al. (2011) proposed the combination of Kmeans and Fisher classifiers to realize the recognition of smoke areas, which significantly improved the accuracy of thin smoke area recognition, but there are still missed detection of thin smoke pixels and misclassification of cloud pixels into Disadvantages of smoke cells

[0008] It can be seen that the various smoke identification methods in the prior art have the disadvantages of poor accuracy in identifying thin smoke areas, and it is easy to misclassify cloud pixels into smoke pixels

Images