Mountain fire monitoring and recognizing method and device based on 360-degree panoramic infrared fisheye camera

Abstract

The invention discloses a mountain fire monitoring and recognizing method and device based on a 360-degree panoramic infrared fisheye camera and belongs to the technical field of forest fire monitoring and recognizing. The method is mainly characterized in that infrared images collected by the 360-degree panoramic infrared fisheye camera, the temperature value and smoke concentration are combined, processed and analyzed, wherein the temperature value and the smoke concentration are collected in a corresponding region, so that analyzed features are applied to a recognition model for recognition, and whether a fire breaks out in the monitoring region is judged. The device comprises a data acquisition module, a data control module, a data transmission module, a data processing module, a data storage module and a power management module. The mountain fire monitoring and recognizing method and device overcome the interference of natural light and the like in the fire recognition process, and the missing report rate and the false alarm rate of fires are lowered.

Description

technical field [0001] The present invention relates to the technical field of forest fire monitoring and identification near power transmission corridors, in particular to a method of combining images collected by a 360-degree panoramic infrared fisheye camera with temperature values ​​and smoke concentrations collected in corresponding areas to determine whether a fire has occurred in the monitored area A method also relates to the device used in the method. Background technique [0002] As the construction of the national power grid continues to strengthen, the number of transmission corridors will continue to increase. Some transmission corridors may have various potential safety hazards, and the impact of forest fires on them is increasing. Forest fires may lead to the downfall of power transmission corridors, resulting in huge economic losses and serious social impacts. It can be seen that the study of forest fire monitoring technology in transmission corridors is of ...

AI Technical Summary

Problems solved by technology

4. Satellite remote sensing, using polar-orbiting meteorological satellites, land resource satellites, geostationary satellites, and low-orbit satellites to detect forest fires. This method has a wide range of detection, fast data collection, continuous data, and is not affected by terrain conditions. Image True, but the use of satellite remote sensing will occupy a large amount of data, and it is difficult to detect fire hazards in the early stage

[0004] The current fire identification and location methods based on images (videos) are all aimed at indoors (warehouses, factories, etc.). Complex and changeable characteristics bring great difficulty to the identification of fire

At the same time, due to the small fire point of the early fire, it further increases the difficulty of the image-based fire recognition method.

It is difficult to obtain satisfactory results by simply using the image threshold method (patent application number 200710016778.1) or only relying on features from the image for fire recognition

Images