Fire behavior early warning method based on machine learning monitoring video image smog

Abstract

The invention discloses a fire behavior early warning method based on machine learning monitoring video image smog. The method is characterized by comprising the steps of firstly, collecting and marking an image data set of various smog scenes, wherein the type of non-fire-behavior early warning smog scenes is A, and the type of fire behavior early warning smog scenes is B; secondly, conducting non-fire-behavior early warning smog scene training through a context target detection layer; thirdly, conducting fire behavior early warning smog scene training through the context target detection layer, and repeating the second step, wherein training images are B-type fire behavior early warning smog images; fourthly, detecting suspected fire behavior images. The method has the advantage of solving the problem that a traditional machine learning method classifier cannot accurately distinguish whether detected smog is produced by fire disasters or not. The context relation of the area where smog is located is judged through a context target detection method, and the false warning rate and warning omission rate are reduced on the premise of improving the fire behavior early warning rate.

Description

technical field [0001] The invention relates to a fire early warning method for monitoring video image smoke based on machine learning, and belongs to the technical field of video image processing. Background technique [0002] As we all know, when a fire is in the smoldering stage at the beginning of the fire or when the flame is small, smoke has already been produced, and the smoke has the characteristics of fast information transmission in a large space. With the development of computer vision, digital image processing, machine learning and other technologies, the laying of artificial intelligence cameras, video-based fire detection and early warning technology has gradually been researched and progressed. Fire detection and early warning technology based on video images is a new fire detection and early warning method based on digital image processing and analysis. Fire detection based on digital image processing has low cost, high accuracy and large amount of informatio...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the deficiencies in the prior art, the object of the present invention is to provide a fire warning method based on machine learning to monitor smoke in video images, which solves the problem that the traditional machine learning method classifier cannot accurately distinguish whether the detected smoke is caused by fire.

Images