A method and system for secondary identification of mountain fire fire points

Abstract

The embodiment of the present invention discloses a method and system for secondary screening of fire points of mountain fires, which are used for secondary screening of hot spots monitored by satellites, reducing misjudgment of fire points in satellite monitoring, and improving the accuracy of early warning of mountain fires on power transmission lines. The method in the embodiment of the present invention includes: S1, obtaining historical satellite hotspot information as sample data, and performing feature extraction on the sample data under two different situations of real fire point and false fire point, and obtaining the extracted feature quantity; S2, for The extracted feature quantities are normalized, and the input space vector is constructed according to the normalized feature quantities; S3, the input space vector is used as the input, and the result of the real fire point or the false fire point corresponding to the input space vector is used as Output, establish the SVM classification model and train the SVM classification model; S4, input the satellite remote sensing hotspot information according to the trained SVM classification model, and obtain the output result of fire point discrimination.

Description

technical field [0001] The invention relates to the technical field of mountain fire identification, in particular to a method and system for secondary identification of mountain fire points. Background technique [0002] Wildfire is one of the important factors affecting the safe and stable operation of the power grid. Wildfire near the transmission line corridor can easily cause line tripping, and it is difficult to successfully reclose after a fault occurs, affecting the reliability of power supply. Using satellites to monitor the occurrence of wildfires can detect wildfires on transmission lines in time and provide guidance for emergency response. [0003] However, after using satellite remote sensing technology to obtain hotspot information, a second screening of hotspots is required. First of all, due to factors such as clouds, flares, and urban heat sources, satellite hotspots are not necessarily all real fires. Secondly, the algorithm for extracting fire points is ...

AI Technical Summary

Problems solved by technology

The existing fire point secondary identification method generally adopts the expert scoring method, which largely relies on expert experience, and it is difficult to continuously adjust according to different regions and different climates, and cannot meet the accuracy requirements of existing mountain fire monitoring

Images