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

Flame detection method based on I1I2I3 color space

A technology of I1I2I3 and color space, applied in the field of computer vision recognition, achieves the effect of simple and easy detection method, improved operation speed, and avoids pixel processing

Active Publication Date: 2015-09-23
SHANDONG UNIV
View PDF2 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, it is often limited in large-scale sports venues, forests and other large-scale scenes

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
  • Flame detection method based on I1I2I3 color space
  • Flame detection method based on I1I2I3 color space
  • Flame detection method based on I1I2I3 color space

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0048] A flame detection method based on I1I2I3 color space, the steps are as follows:

[0049] 1) Convert each pixel value in the target image from RGB color space to I by formula (I) 1 I 2 I 3 color space:

[0050]

[0051] The RGB color space and the I1I2I3 color space are both color models representing color images in digital image processing. The general color model contains three components. In the RGB color space and the I1I2I3 color space, any color is mixed by three colors Obtain, the conversion formula between described RGB color space and I1I2I3 color space is (1);

[0052] 2) The target image is divided into several 4x4 sub-blocks, as attached figure 1 As shown, each sub-block is assigned a flag whether it is a flame, and the flag matrix is ​​formed as flag(i, j), where i, j are the horizontal and vertical coordinates of the sub-block in the flag matrix, and the flag matrix indicates the attached figure 2 ;

[0053] 3) For each sub-block, calculate I sepa...

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 discloses a flame detection method based on I1I2I3 color spaces. According to the method, by distinguishing the colors of image pixels, whether the image pixels belong to a flame area can be determined. The method comprises the steps of conducting block processing to an image, and calculating three mean values of each subblock pixel in the I1I2I3 color spaces block by block; by further utilizing multiple rules, namely an equality system, determining whether the three mean values belong to the flame color. The method is simple, feasible and high in realtime performance. According to the method, a video sequence is not related, and therefore the method is independent of the movement which possibly exists in a scene. Therefore, by means of the method, whether the flame area exists in the image can be detected, the stability of the detection effect is guaranteed, and the requirement of the realtime performance is satisfied. The method is applicable to the fields such as forest fire detection and large gymnasium fire detection based on computer vision.

Description

technical field [0001] The invention relates to a flame detection method based on I1I2I3 color space, and belongs to the technical field of computer vision recognition. Background technique [0002] In traditional flame detection technology, the detection effect is often limited by the location and number of sensors. Therefore, it is often limited in large-scale scenes such as large stadiums and forests. Since it is not limited by factors such as space and location, flame detection technology based on computer vision has received more and more attention. In flame detection based on computer vision, the color features, texture features, and dynamic changes of flames are often used. The present invention is mainly based on two aspects of the color feature and the texture feature of the flame. The flame detection algorithm based on computer vision is roughly divided into two steps: 1) Detect the suspected flame area in the static image, also called the candidate area. In th...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/40
CPCG06T7/90
Inventor 刘兆广张行愚杨阳
Owner SHANDONG UNIV
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com