Smog fire detection method and smog fire detection device

A fireworks detection and smoke technology, applied in the field of image processing, can solve the problem of low accuracy of fireworks detection

Active Publication Date: 2017-08-01
ZHEJIANG DAHUA TECH CO LTD
View PDF5 Cites 40 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The embodiment of the present invention provides a pyrotechnic detection method a

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
  • Smog fire detection method and smog fire detection device
  • Smog fire detection method and smog fire detection device
  • Smog fire detection method and smog fire detection device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0086] figure 1 A schematic diagram of a pyrotechnic detection process provided by an embodiment of the present invention, the process includes the following steps:

[0087] S101: Determine whether the day mode or the night mode is currently used, if it is determined that the day mode is currently used, go to S102, if it is determined that the night mode is currently used, go to S103.

[0088] A smoke detection method provided by an embodiment of the present invention is applied to a processor of an image acquisition device.

[0089] For daytime and night, there is a clear difference in the images captured by the image acquisition equipment for fireworks. When fireworks appear during the day, the smoke spreads faster than the flames, and the flames are easily blocked by occluders and will be affected by light at the initial stage of appearance. Influenced by this, the flame cannot be detected in time during the day; when fireworks appear at night, due to the low brightness at...

Embodiment 2

[0107] In order to make the determination of the target smoke area more accurate, on the basis of the above embodiments, in the embodiment of the present invention, the determination of the target smoke area according to the attribute information of the pixels in each suspected smoke area includes:

[0108] For each suspected smoke area, divide the suspected smoke area into a plurality of sub-areas, and determine whether the suspected smoke area is a candidate smoke area according to the energy of each pixel in each sub-area and the preset change trend of smoke characteristics;

[0109] The target smoke area is determined according to the dynamic texture feature of each pixel in the candidate smoke area and a preset smoke dynamic texture feature model.

[0110] Specifically, when the suspected smoke area is divided into multiple sub-areas, the number of divided sub-areas can be preset, and the suspected smoke area can be divided into multiple sub-areas according to the number. ...

Embodiment 3

[0117] On the basis of the above embodiments, in order to make the determination of candidate smoke pixels more accurate, in the embodiment of the present invention, it is determined whether each pixel in the frame of image is a candidate according to the pixel value of the pixel in the frame of image Smoke pixels include:

[0118] According to the first reference image, the preset first interval and the preset second interval, determine whether the frame image is the first target frame image and / or the second target frame image, wherein the second interval is greater than the first interval;

[0119] If it is determined that the frame image is the first target frame image, according to the currently saved first reference image for the first update and the gray value of the first target frame image, perform the first update for the first reference image The gray value is updated and saved; if it is determined that the frame image is the second target frame image, according to t...

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 smog fire detection method and a smog fire detection device. The smog fire detection method comprises steps that when a daytime mode is adopted, candidate smog pixel points are determined according to pixel values of pixel points in a frame of image; every suspected smog area is determined according to the candidate smog pixel points; according to the attribute information of the pixel points in every suspected smog area, target smog areas are determined; when a nighttime mode is adopted, suspected flame pixel points are determined according to the gray values of the pixel points in the fame of image; flame flickering areas are determined according to the gray values of the suspected flame pixel points; according to the attribute information of the pixel points in every flame flickering area, target flame areas are determined. According to the embodiments of the invention, when the daytime mode is adopted, the target smog areas are determined according to the attribute information of the pixel points in every suspected smog area; when the nighttime mode is adopted, the target flame areas are determined according to the attribute information of the pixel points in every flame flickering area, and the smog fire detection is more accurate.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a smoke detection method and device. Background technique [0002] For a long time, forest fireworks have occurred frequently all over the world. Forest fireworks are one of the most common serious disasters. They not only cause huge damage to forest vegetation and animal survival, but even threaten human production and life. Therefore, accurate detection of forest fireworks is of paramount importance. important. [0003] With the improvement of intelligent technology and the high-definition of cameras, it becomes feasible to use video surveillance to detect fireworks in forests and other situations. In the pyrotechnics detection system provided in the prior art, for the acquired image, the moving target pixel in the image is identified, and whether the pyrotechnics occurs is determined by judging whether the target pixel is a pyrotechnic pixel. However, in the...

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): G06K9/00G06V10/764
CPCG06V20/47G06V20/52G08B17/125G08B25/08G06V10/764G06F18/2433G08B17/005G06V20/20G06V20/188G06V20/194
Inventor 郑佳田建国潘华东
Owner ZHEJIANG DAHUA TECH 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