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

A method for flame detection in indoor scenes

A technology for indoor scenes and detection methods, which is applied to instruments, computing, character and pattern recognition, etc., can solve the problems of difficult to accurately detect and track small flames, and achieve the effect of short calculation time, low false alarm rate and small amount of calculation.

Active Publication Date: 2019-04-02
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The present invention provides an indoor scene flame detection method for the above shortcomings, which solves the problem in the prior art that it is difficult to accurately detect and track whether there are initial flames or small flames that may cause fires

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
  • A method for flame detection in indoor scenes
  • A method for flame detection in indoor scenes
  • A method for flame detection in indoor scenes

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0063] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0064] Step 1. Input the video to be detected, extract each frame image of the video and perform noise reduction and contrast enhancement preprocessing operations;

[0065] Step 2. Use the inter-frame difference method to obtain the differential image of each frame image after preprocessing, and obtain a region of interest (ROI) with improved resolution; the specific process is:

[0066] Step 21. Read in each frame of image preprocessed in step 1, and calculate the difference between the two frames of images in time sequence. Through the difference image, the interference of the invariant object in the background can be removed, and the detection target (flame target) can be determined. range, to get the region of interest (ROI);

[0067] Step 22, obtain the region of interest (ROI) that improves resolution with bicubic interpolation algorithm, involve...

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 in an indoor scene, which belongs to the application field of visible light image and video processing, and solves the problem in the prior art that it is difficult to accurately detect and track whether there are initial flames or small flames that may cause fires. The present invention is based on the color space conversion and segmentation of visible light images, combined with the morphological characteristics of flames for discrimination, because the component channels of flame images in the YCbCr color space have obvious gradient strength and gradient distribution characteristics, and support vector machines are used to identify them. The HOG feature is used for learning and recognition, and the tracking of the flame target is realized through the instantaneous frame difference and centroid drift algorithm in the dynamic video. Tests on a large number of indoor flame images and video samples show that this method has higher recognition rate, faster detection speed, lower false alarm rate and higher reliability than traditional methods. The invention is aimed at the detection and tracking of initial flames, small flames and the like.

Description

technical field [0001] A flame detection method in an indoor scene is used for the detection of flames, and relates to the application field of visible light image target recognition and detection, and specifically relates to the detection and tracking of initial flames and small flames. Background technique [0002] Fire is one of the most common serious disasters, which directly endangers human life and property, causes environmental pollution, and even ecological balance. At present, the automatic fire alarm technology at home and abroad is mainly based on the detection of sensors. However, in large spaces such as outdoor warehouses and large indoor warehouses, the sensor signal becomes very weak due to the huge space. Even high-precision sensors cannot work due to various interfering noises. The vision-based fire detection technology detects the various visual features accompanying the fire, so as to realize whether the fire has occurred or not. In recent years, due t...

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 Patents(China)
IPC IPC(8): G06K9/00
CPCG06V20/36G06V20/44G06V20/41
Inventor 杨琛张圳李丹姜哲燕肇一李倩仪彭真明
Owner UNIV OF ELECTRONICS SCI & TECH OF 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

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