Fire behavior early warning method based on machine learning monitoring video image smog

A machine learning and video image technology, applied in neural learning methods, instruments, computer components, etc., can solve the problem that the classifier cannot accurately distinguish smoke

Active Publication Date: 2018-08-03
NANJING JULI INTELLIGENT MFG TECH INST CO LTD
View PDF15 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the deficiencies in the prior art, the object of the present invention is to provide a fire warning method based on machine learning to monitor sm...

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 behavior early warning method based on machine learning monitoring video image smog
  • Fire behavior early warning method based on machine learning monitoring video image smog
  • Fire behavior early warning method based on machine learning monitoring video image smog

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0060] The present invention will be further described below in conjunction with the accompanying drawings. The following examples are only used to illustrate the technical solution of the present invention more clearly, but not to limit the protection scope of the present invention.

[0061] like figure 1 As shown, the method specifically includes the following steps:

[0062] Step 1) Collect and mark image data sets of various smoke scenes, among which non-fire warning smoke scenes are classified into category A, and fire warning smoke scenes are classified into category B.

[0063] Non-fire warning smoke scenes are classified into category A, including: setting off firecrackers, car exhaust emissions, existing firefighters extinguishing fires, temples burning incense and smoking, picnic fires and smoke, chimney smoke and other outdoor smoke scenes ; The fire warning smoke scene is classified into category B, including: building fire scene, forest fire scene, warehouse fir...

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 fire behavior early warning method based on machine learning monitoring video image smog. The method is characterized by comprising the steps of firstly, collecting and marking an image data set of various smog scenes, wherein the type of non-fire-behavior early warning smog scenes is A, and the type of fire behavior early warning smog scenes is B; secondly, conducting non-fire-behavior early warning smog scene training through a context target detection layer; thirdly, conducting fire behavior early warning smog scene training through the context target detection layer, and repeating the second step, wherein training images are B-type fire behavior early warning smog images; fourthly, detecting suspected fire behavior images. The method has the advantage of solving the problem that a traditional machine learning method classifier cannot accurately distinguish whether detected smog is produced by fire disasters or not. The context relation of the area where smog is located is judged through a context target detection method, and the false warning rate and warning omission rate are reduced on the premise of improving the fire behavior early warning rate.

Description

technical field [0001] The invention relates to a fire early warning method for monitoring video image smoke based on machine learning, and belongs to the technical field of video image processing. Background technique [0002] As we all know, when a fire is in the smoldering stage at the beginning of the fire or when the flame is small, smoke has already been produced, and the smoke has the characteristics of fast information transmission in a large space. With the development of computer vision, digital image processing, machine learning and other technologies, the laying of artificial intelligence cameras, video-based fire detection and early warning technology has gradually been researched and progressed. Fire detection and early warning technology based on video images is a new fire detection and early warning method based on digital image processing and analysis. Fire detection based on digital image processing has low cost, high accuracy and large amount of informatio...

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): G06K9/00G06K9/62G06N3/08
CPCG06N3/08G06V20/40G06V20/46G06V20/10G06F18/23G06F18/24147
Inventor 张登银赵烜朱昊赵莎莎
Owner NANJING JULI INTELLIGENT MFG TECH INST CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap