Fire identification method based on multiple-feature fusion for flames

Abstract

The invention provides a fire identification method based on multiple-feature fusion for flames, and develops a fire identification system with multiple-feature fusion for flames according to the algorithm of the method. The operation principle is to call the camera video monitoring images through the system, and use the background detection algorithm of the system to process the images. The method comprises the following steps of: combining screening of motion fire pixels through motion detection and screening of flame color pixels through RGB color model as an image preprocessing module, wherein the detection calculation based on the inter-frame difference method is fast and does not contain complex calculations, and it is not necessary to consider factor changes such as darkness since the requirements for environment are not high, and the adopted RGB / HIS color model is reasonably stable; characterizing the flames by the number of flame pixels, the convex hulls and the cusps according to the smoke of the flame, the area change, and the features of shape change; combining mature support vector machines for verification; and issuing an alarm when all the above conditions are met. The fire identification method based on multiple-feature fusion for flames can be applied to a real-time camera monitoring system for public security and so on.

Description

technical field [0001] In recent years, due to the rapid development of cities, the popularization rate of video surveillance has been greatly increased. As an emerging interdisciplinary research field, fire detection based on video processing is also one of the current research hotspots in scientific research institutions at home and abroad. Many scientific researchers use digital video surveillance to complete Intelligent fire detection. Nowadays, fire detection has a good prospect in both forest fire prevention and civil public safety. Background technique [0002] With the rapid popularization of urbanization in China, the permanent population in cities is increasing, and the population density is increasing. Once a fire breaks out, it will seriously threaten people's lives and cause great economic losses. Therefore, it is more and more important to protect people's lives and property safety. [0003] In order to prevent the occurrence of fires and the rapid growth of...

AI Technical Summary

Problems solved by technology

First, the flame is continuously changing and has no fixed shape

Second, there is disorder in the boundary of the flame

Third, flames will also be accompanied by certain growth characteristics, and may also be accompanied by smoke

Images