Cigarette smoke detection method based on video monitoring

Abstract

The invention provides a cigarette smoke detection method based on video monitoring. The method is divided into a classifier training phase and a cigarette smoke detection phase. In the classifier training phase, geometrical characteristics and Hog characteristics of all prepared positive and negative sample sets are extracted, a support vector machine is used for training the extracted characteristic vectors, and a classifier is generated; and in the cigarette smoke detection phase, firstly, a Gaussian mixture model is utilized to obtain a foreground motion region from a video image obtained by a monitoring camera, then noisy points and cavities are removed by means of morphological filtering, projection histograms in X and Y directions are counted according to the characteristics of cigarette smoke, a precise interested region is obtained, finally characteristics of the interested region are extracted and combined into characteristic vectors, the characteristic vectors are input into the classifier, and whether the interested region has cigarette smoke is judged. The method provided by the invention has the advantages that the interference resistance is high, the detection sensitivity is high, the false alarm rate is low, the cigarette smoke can be recognized in realized, the position of the cigarette smoke is determined, and the cigarette control work of indoor public places is facilitated.

Description

technical field [0001] The invention relates to the fields of image processing and pattern recognition, in particular to a method for detecting cigarette smoke based on video monitoring. Background technique [0002] Smoking is a common bad behavior in people's daily life, and the harm of smoking has been gradually known by the public. The "Beijing Regulations on Smoking Control" came into effect on June 1, 2015. It clearly stipulates that smoking is prohibited in all public places, indoor areas of workplaces and public transportation, and stipulates that cultural relics units, stadiums and some outdoor venues where minors are the main activities Smoking is prohibited in places, but there is a lack of an efficient and convenient means to carry out supervision and management of smoking control. Manual management needs to invest a lot of manpower and material resources, and it cannot guarantee accurate and timely detection and suppression of smoking behavior. [0003] Howeve...

AI Technical Summary

Problems solved by technology

The "Beijing Regulations on Smoking Control" came into effect on June 1, 2015. It clearly stipulates that smoking is prohibited in all public places, indoor areas of workplaces and public transportation, and stipulates that cultural relics units, stadiums and some outdoor venues where minors are the main activities Smoking is prohibited in places, but there is a lack of an efficient and convenient means to carry out supervision and management of smoking control

Manual management requires a

Images