Method and system for realizing smoke detection by using deep learning classification model

Abstract

The invention discloses a method for realizing smoke detection by using a deep learning classification model. The method comprises the following steps of: getting a frame of smoke image from the videostream; processing the smoke image with a Gaussian mixture model to obtain a motion region of the smoke image to be removed; processing the image using a dark channel smoke removing algorithm to obtain a smokeless image model; obtaining a difference image between the smoke image to be removed and the smokeless image model; binarizing the difference image to obtain a suspected smoke area; obtaining the intersection area between the motion area and the suspected smoke area, entering the intersection area into the trained deep learning classification model to get the final smoke recognition result; marking the smoke area in the smoke image to be removed according to the smoke recognition result. The method and system for realizing smoke detection by using deep learning classification model use a lightweight deep learning classification model to achieve higher accuracy and detection rate, reduce the false detection rate, and realize the effect of real-time detection.

Description

technical field [0001] The invention belongs to the technical field of image processing, and more specifically relates to a method and system for realizing smoke detection by using a deep learning classification model. Background technique [0002] Fire is one of the disasters with the highest probability of occurrence among natural disasters and social disasters, which poses a serious threat to human life and life. The early stage of a fire is often accompanied by the generation of a large amount of smoke. If the smoke can be detected timely and accurately, it will have far-reaching significance for fire warning and fire fighting. [0003] The video smoke detection methods mainly used today are artificial feature extraction methods based on color features, edge detection, LBP operator, wavelet transform, etc., but these detection methods have some problems that cannot be ignored: first, due to the shape and color of smoke The features extracted by these methods have poor g...

AI Technical Summary

Problems solved by technology

[0003] The video smoke detection methods mainly used today are artificial feature extraction methods based on color features, edge detection, LBP operator, wavelet transform, etc., but these detection methods have some problems that cannot be ignored: first, due to the shape and color of smoke The features extracted by these methods have poor generalization ability, resulting in low accuracy and detection rate, high false detection rate, and limited application scenarios; second, these methods often need to use the entire image as input, and calculate The amount is large and the real-time performance is poor; third, in order to obtain better recognition results, the ordinary deep learning classification model usually adopts a more complex model structure, resulting in a large number of model parameters and a large amount of algorithm calculation

Images