Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Fire identification method based on multiple-feature fusion for flames

A technology of multi-feature fusion and flame, which is applied in the direction of fire alarms, fire alarms, character and pattern recognition that rely on radiation effects

Inactive Publication Date: 2019-01-11
CHINA UNIV OF PETROLEUM (EAST CHINA)
View PDF6 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

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

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Fire identification method based on multiple-feature fusion for flames
  • Fire identification method based on multiple-feature fusion for flames
  • Fire identification method based on multiple-feature fusion for flames

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0085] The design of the system in the present invention will be fully described below in conjunction with the accompanying drawings in the embodiments of the present invention:

[0086] Such as figure 1 As shown, the present invention is a schematic diagram of the overall architecture of the fire recognition system based on flame multi-feature fusion. The system consists of four parts: data storage layer, service layer, function module layer, and interaction layer.

[0087] Such as figure 2 As shown, the overall flowchart of a fire recognition method based on flame multi-feature fusion in the present invention includes: video information acquisition; video image processing; continuous image information acquisition; fire detection preprocessing; motion detection; color detection; Features; support vector machine for verification; alarm information stored in the database.

[0088] Such as image 3 As shown, the functional block diagram of the fire recognition system based o...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

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...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G08B17/12G06K9/00G06T7/90
CPCG06T7/90G08B17/125G06T2207/10016G06T2207/10024G06V20/42G06V20/52
Inventor 宫法明李传涛袁向兵宫文娟马玉辉丁洪金岳寒冰王超奇
Owner CHINA UNIV OF PETROLEUM (EAST CHINA)
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products