Multi-feature fusion based infrared forest fire judgment method

Abstract

The invention discloses a multi-feature fusion based infrared forest fire judgment method. The method comprises the following steps: A, inputting an infrared image sequence; B, performing binarization processing; C, performing morphological processing; D, extracting flame features; E, performing SVM classification judgment on the flame features; F, performing classification decision-making by utilizing a Bayes classifier; and G, judging whether a fire occurs or not through data in the step F. The flame features in the step D include an infrared flame height characteristic, an infrared flame gradient characteristic, an infrared flame moving characteristic and a flame spectrum characteristic. According to the multi-feature fusion based infrared forest fire judgment method provided by the invention, the fire can be detected quickly, accurately and safely in the early stage of the forest fire, so that the judgment precision of forest fire prevention is greatly improved and the working efficiency is improved.

Description

technical field [0001] The invention belongs to the field of infrared image recognition, and specifically refers to a forest fire judging method using multi-feature fusion infrared images for flame detection and recognition. Background technique [0002] Forest fire is a natural disaster that is sudden, destructive and difficult to rescue. During the 38 years from 1950 to 1987, an average of 15,838 forest fires occurred nationwide, with a fire incidence rate of 13.9 per 100,000 hectares, an average annual forest area of ​​940,000 hectares, and an average forest fire damage rate of 8.5%. It is 8 times the average level of the world in the same period, and the average annual casualty of forest fires in the whole country is 800 people. Relevant experts estimated that during this period, a total of 955 million cubic meters of wood was burned across the country. Calculated at the value of 150 yuan per meter, the national direct economic loss is as high as 143.3 billion yuan, ac...

AI Technical Summary

Problems solved by technology

[0004] At present, most infrared image fire recognition methods are aimed at indoor fires, and a few infrared fire recognition methods are used to detect forest fires. Among them, the existing infrared thermal imaging fire prevention methods are to convert infrared images into false colors for temperature detection. It is judged as a fire when the temperature threshold is reached. However, this will be affected by many interference factors in the forest environment, such as sunlight and high-temperature objects such as electric towers, which greatly reduces the correct recognition rate and cannot effectively carry out forest fire prevention.

Moreover, simple image threshold segmentation is difficult to accurately identify fires, and it is impossible to quickly, accurately and safely detect fires in the early stages of forest fires.

Images