Building electrical fire risk assessment and prediction method based on artificial intelligence

The invention relates to the field of image processing, and provides a building electrical fire risk assessment and prediction method based on artificial intelligence, and the method comprises the steps: collecting an infrared image when a heating source works, and converting the infrared image into a gray image; determining a guide parameter of each window after noise reduction based on texture information of the grayscale image; performing image enhancement processing on the infrared image by using the guide parameter; and determining whether a fire risk exists based on the enhanced infrared image. According to the method, the guide parameters after noise reduction are calculated by taking the grayscale image as the guide image, and then the infrared image is enhanced, so that the image enhancement effect can be improved, and the accuracy of fire assessment can be improved.