Video smog fine classification method based on color model and motion characteristics

Abstract

The invention discloses a video smog fine classification method based on a color model and motion characteristics, comprising steps of differentiating and constructing a color model on the basis of a gauss mixing model and a background, detecting a motion pixel point and performing initial screening, obtaining a motion object connected region, extracting a motion changing characteristic, setting a threshold and determining whether a suspicious smoke area exists, performing pre-processing on the suspicious smoke area, extracting a SIFT characteristic on the basis of an image block, combining with an SVM optimization random forest algorithm, performing training based on the suspicious smoke area image block and thus realizing the fine classification of the fire hazard smoke, the cigarette smoke, the water vapor, etc. The video smog fine classification method based on color model and motion characteristics performs video smoke detection based on the color model and the motion characteristic and by targeting the fine classification, realizes real-time fast smoke detection, effectively eliminates the interference having similar effect interference sources with the fire hazard smoke, and improves the detection efficiency and accuracy.

Description

technical field [0001] The invention relates to the fields of computer image processing and intelligent recognition, in particular to a method for finely classifying video smoke based on color models and motion features. Background technique [0002] In recent years, with the popularization of video surveillance systems in cities and key fire protection units, and the continuous development of artificial intelligence and pattern recognition technologies, video-based fire detection methods have received more and more attention. The video fire detection method has the advantages of high efficiency, real-time, intelligence, low cost, and convenience. Real-time fire detection is very positive for detecting fire earlier and avoiding greater losses. [0003] Video fire detection methods mainly include flame detection methods and smoke detection methods. The smoke detection method is to detect the smoke generated by the fire to detect the fire, and judge whether there is still a s...

AI Technical Summary

Problems solved by technology

[0004] In the process of realizing the present invention, the inventors found that the prior art has at least the following problems: Although there have been many related researches on video smoke detection and some achievements have been made, affected by the maturity and cost of the technology, based on Smoke-based video fire detection technology is not yet widely available

There are existing algorithms for interference sources that have similar effects to fire smoke (such as cigarette smoke, mosquito coil smoke, water vapor, etc.). At present, there is no algorithm that can achieve a better elimination effect. Further improve the accuracy rate and reduce the false alarm rate fundamentally; the environment with a more complex background has a greater impact on the extraction and detection of smoke areas, and the existing algorithms are less effective in dealing with this background; some existing algorithms with better detection performance The required time complexity cannot fully meet the real-time processing requirements of the monitoring system, thus losing the most important meaning of video smoke detection technology

Images