Video smoke detecting method based on multi-feature fusion

Abstract

The invention discloses a video smoke detecting method based on multi-feature fusion. The video smoke detecting method includes extracting motion targets from a training video sequence, judging whether or not a suspected smoke area according to color features, extracting shape irregularity features, area growth features and K background fuzzy features from the suspected smoke area to combine into feature vectors to combine into feature vector, subjecting the feature vector into positive and negative sample division to obtain training samples; using the feature vector of the training samples as output and sample types as output and training a classifier; extracting the feature vector from images to be detected by the same method, and inputting the feature vector to judge whether smoke is or not. The features can be extracted from the suspected smoke area, smoke can be comprehensively judged and detection efficiency of smoke is improved.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and more specifically relates to a video smoke detection method based on multi-feature fusion. Background technique [0002] Fire is a very common disaster. With the continuous development of society and the continuous increase of social wealth, the occurrence of fire not only causes huge economic losses and destroys the harmonious ecological environment, but also seriously threatens people's property and life safety, and affects the stability, prosperity and development of society. The earlier the fire is accurately discovered, the more likely it is to minimize the loss in all aspects. As an important product in the early stage of fire, smoke can be accurately detected to give early warning of fire. [0003] The vast majority of traditional smoke detectors still use smoke, temperature, light, combustible gas and composite detectors that combine several of them. These detectors rely on...

AI Technical Summary

Problems solved by technology

However, in the real situation where the comprehensive environment is complex, the existing algorithms still have some deficiencies, mainly due to the high false detection.

Images