Flame and dense smoke detection method based on YOLOv3

A detection method and flame detection technology, applied in the cross research field of computer vision and machine learning, can solve problems such as insufficient reliability, sensors are easily affected by environmental factors, poor sensitivity, etc., to avoid complex work, and to achieve fast and accurate detection. high rate effect

Pending Publication Date: 2020-05-01
HOHAI UNIV
View PDF1 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] Purpose of the invention: In view of the problems that the sensors in the prior art are easily affected by environmental fact...

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 and dense smoke detection method based on YOLOv3
  • Flame and dense smoke detection method based on YOLOv3
  • Flame and dense smoke detection method based on YOLOv3

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0051] The invention provides a flame and smoke detection method based on YOLOv3, which monitors fires in important places through an on-site video monitoring system. When flame or smoke is detected, it will automatically alarm and display the location of the fire, providing real-time data for firefighters. Such as figure 1 As shown, the method includes the following steps:

[0052] Step 1, collect images containing flames and thick smoke, and establish initial data sets for flames and thick smoke; specifically include:

[0053] Step 1-1, obtain a certain amount of images and videos containing flames and thick smoke through self-shooting and online crawling;

[0054] Steps 1-2, use the ffmpeg framework to extract flame / smoke image frames from the flame video, mark the flame and smoke areas for all images, and generate flame datasets and sm...

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 and dense smoke detection method based on YOLOv3. The method comprises the following steps: establishing a flame data set and a dense smoke data set; enhancing data ina random horizontal overturning, cutting and rotating mode; respectively training a flame model and a dense smoke model by using a YOLOv3 algorithm, and fusing the flame model and the dense smoke model into a final model; in an existing video monitoring system, adding a flame and smoke detection module; acquiring a monitoring scene video in real time based on a camera of a video monitoring system,and extracting an image frame from the video based on an ffmpeg framework; detecting each frame of image by adopting a fusion detection model, determining whether flames and dense smoke exist in theimages or not, and marking the positions of the flames and the dense smoke; when a fire is detected, giving an alarm automatically, linking automatic fire-fighting equipment wherein a camera providesreal-time monitoring. According to the invention, effective fire monitoring and danger early warning of important places can be realized; and the invention has the advantages of no dependence on manual characteristics, low detection cost, high detection speed, high accuracy and the like.

Description

technical field [0001] The invention belongs to the cross research field of computer vision and machine learning, and more specifically relates to a flame and smoke detection method based on YOLOv3. Background technique [0002] The occurrence of fire will endanger the safety of people's lives and properties, and fires in important places such as substations, hospitals, libraries, forests, etc. will cause irreparable losses. In these important places, timely identification and early warning of flames are of great significance to the personal safety of professionals and the safety of public property. [0003] When a fire occurs, it is usually accompanied by dense smoke, high temperature, high brightness, etc. Therefore, parameters such as smoke density, flame brightness, and temperature are often used as important parameters for fire detection. Accordingly, smoke sensors, temperature sensors, etc. are often used for fire detection. However, the sensor is susceptible to env...

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): G06K9/00G06F16/951G06N3/04G06N3/08G06T5/00G08B17/12
CPCG06T5/002G06T5/001G06N3/084G06F16/951G08B17/125G06V20/41G06V20/46G06N3/045
Inventor 钱惠敏施非周军黄浩乾卢新彪
Owner HOHAI UNIV
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