Fire hazard detection and tracking method of small unmanned helicopter

Abstract

The invention discloses a fire hazard detection and tracking method of a small unmanned helicopter. The method comprises following steps of initializing a system; starting a ground station system and a GIS platform; acquiring color images and infrared images; according to colors, finding out a suspicious image in the color images, and according to the gray scale, finding out a suspicious image in the color images; extracting colors of and gray scale co-occurrence matrix characteristics the suspicious region in the color images; extracting the circularity degree and area change rate characteristics of the suspicious image in the infrared images; judging whether a fire hazard occurs by use of SVM classification decision after an offline training; calculating fire point coordinates in the infrared images and sending the fire point coordinates to a holder through an onboard processor, wherein the holder tracks the fire points in real time; acquiring pose angles of an infrared camera through an inertia measurement unit of the holder; calculating latitude and longitude positioning information of the fire points by combining the latitude and the longitude, the height, the deviation angle information and the pose angle of the small unmanned helicopter through a ground station; and finally, precisely positioning and calibrating the fire points on a map through the GIS platform.

Description

technical field [0001] The invention relates to the technical field of unmanned aerial vehicle fire detection and early warning, in particular to a fire detection and tracking method for a small unmanned helicopter. Background technique [0002] my country is one of the countries most severely affected by natural disasters in the world. There are many types of disasters, wide distribution areas, high frequency of occurrence, and heavy losses. For sudden disasters, especially fires and mountain torrents with limited scope, strong suddenness, great hazards, and difficult to quickly and large-scale ground search and detection, early detection and early warning is a critical means of disaster reduction. At present, the domestic early warning system basically adopts means and methods of fixed-point observation, such as conventional forest fire prevention and lookout posts. However, due to terrain and cost factors, it is difficult for the observation and early warning network to ...

AI Technical Summary

Problems solved by technology

However, due to the constraints of economic and technical conditions, it is still difficult to achieve real-time and large-scale accurate three-dimensional monitoring. The low-cost small unmanned helicopter ultra-low-altitude mobile observation platform is a feasible way to solve this key problem.

[0004] At present, remote sensing technologies such as high-altitude meteorological satellites have been used in the early warning and monitoring of disasters in China. However, due to the lack of relevant small flying platforms, the construction of an accurate and real-time three-dimensional early warning system based on low-altitude autonomous mobile network platforms has not yet been carried out.

Images