Supercharge Your Innovation With Domain-Expert AI Agents!

Intelligent image detection method of smoke and fire in cable trench under low-light environment

A cable channel and intelligent image technology, applied in the field of image processing, can solve the problems of low detection accuracy and unsuitable detection of small smoke targets, reduce the probability of smoke false detection and improve the detection ability

Active Publication Date: 2022-06-28
STATE GRID CORP OF CHINA +1
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide an intelligent image detection method for smoke and fire in a cable channel in a low-light environment, which is used to solve the problem of low detection accuracy of early smoke and small targets in the prior art and the inability to adapt to the low-light environment Technical issues detected

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
  • Intelligent image detection method of smoke and fire in cable trench under low-light environment
  • Intelligent image detection method of smoke and fire in cable trench under low-light environment
  • Intelligent image detection method of smoke and fire in cable trench under low-light environment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0080] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0081] refer to figure 1 , the present invention comprises the steps:

[0082] Step 1) Get training image set and test image set:

[0083] Obtain 3000 video frame images containing smoke from the surveillance video of the low-light camera, and form a smoke image sample set P={P 1 ,P 2 ,...,P i ,...,P 3000 }, mark the smoke area in the smoke image sample set P with a rectangular frame, and obtain the smoke label sample set L={L 1 ,L 2 ,...,L i ,...,L 3000 }, the size of the label corresponding to the smoke image and the image is the same, and both are three-channel images. We divide the smoke image sample set P into the training set and the test set, and randomly select 2400 images to form the training sample set P a ={P 1 a ,P 2 a ,...,P j a ,...,P 2400 a } and the corresponding 2400 smoke image labels to form a traini...

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 an intelligent image detection method for smoke and fire in a cable channel in a low-light environment. The realization steps are: obtaining a training sample set and a test sample set, and constructing various modules for feature extraction and modules such as an attention mechanism , build a smoke detection network FSSD and perform iterative training, perform single Gaussian background modeling on video images captured by low-light cameras, perform median filtering and limit contrast histogram equalization operations, and then send them to the trained network to obtain smoke detection result. The present invention adopts the method of combining single Gaussian background modeling, median filter and self-adaptive histogram equalization of limited contrast, so that the smoke image under low-light environment has been enhanced, and the method is combined with the FSSD with attention mechanism The network combination improves the early smoke detection capability and detection accuracy, and reduces the false detection rate.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to an intelligent image detection method for smoke and fire, in particular to an intelligent image detection method for smoke and fire in a cable channel in a low-light environment, which can be used for cable channel smoke in a low-light environment Fire detection, early warning, etc. Background technique [0002] With the development of artificial intelligence and the widespread popularization of image recognition technology, intelligent monitoring of smoke and fire through video surveillance will be an important means of future fire warning. Because the cable in the cable trench is below the ground and the environment is dark, when the cable fails and causes a fire, it is difficult for the staff to find it, which will cause serious consequences once a cable trench fire accident occurs. The smoke is usually generated before the flame, so how to identify the smoke in the lo...

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): G08B17/12G08B17/10G06V20/52G06V20/40G06V10/774G06K9/62G06N3/04G06N3/08
CPCG08B17/125G08B17/10G06N3/08G06V20/41G06V20/52G06N3/045G06F18/214
Inventor 王战红高洁张斌付涛刘纲武峰利许小渭
Owner STATE GRID CORP OF CHINA
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com