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

RGB reconstruction-based method for identifying flame/smoke after forest image cutting

A recognition method and image technology, applied in character and pattern recognition, instruments, computer components, etc., can solve problems such as inability to effectively distinguish combustion smoke from natural smoke, high misjudgment rate, and low system applicability

Active Publication Date: 2017-05-31
HARBIN INST OF TECH
View PDF6 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0011] The purpose of the present invention is to solve the problem of low system applicability and high misjudgment rate caused by existing methods that are difficult to avoid misidentification caused by the sun under the background of forest fire prevention, and that existing methods cannot effectively distinguish combustion smoke from natural smoke. question

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
  • RGB reconstruction-based method for identifying flame/smoke after forest image cutting
  • RGB reconstruction-based method for identifying flame/smoke after forest image cutting
  • RGB reconstruction-based method for identifying flame/smoke after forest image cutting

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0075] Hereinafter, the present invention will be further described in detail with reference to the examples. The embodiments of the present invention are not limited to processing pictures, but can also be used for video image processing, and can also be used for object recognition when other target RGB values ​​differ from the background RGB values.

[0076] The present invention designs a method for segmenting flame and smoke images in the forest background based on a common camera installed in the highlands of the forest area, shooting real-time pictures for forest fire monitoring and recognition, and cutting out suspicious areas, stripping information areas and background areas, and Delete the small area and only keep the most important area in the original image, and then extract the image features of the information area to determine whether there is a fire, and effectively avoid the misjudgment of the sun and natural smoke.

[0077] The method for identifying the flame and s...

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 RGB reconstruction-based method for identifying flame / smoke after forest image cutting, relates to an RGB reconstruction-based technology for identifying flame / smoke after forest image cutting, and aims to solve the problems of low system adaptability and high misjudgment rate of an existing flame / smoke identification method. The method comprises the steps of destroying a background region to the maximum extent based on different values of three RGB components of a flame / smoke region and the background region, thereby continuously shrinking a target region; in the process of shrinking the target region, only considering regions with most remarkable features, namely, connected regions conforming to the features and having maximum areas, and deleting small regions possibly causing misjudgment; and after corrected grayscale formula processing of flame features is enhanced, performing filtering, cutting, corrosion and expansion, and judging whether the region is a suspected smoke or flame region according to a proportion of non negative elements. The method is applied to an occasion for identifying flame / smoke in forest fire prevention.

Description

Technical field [0001] The invention relates to a flame / smoke recognition technology based on RGB reconstruction of forest images after cutting. Background technique [0002] In recent years, with the rapid development of industry and society, it has brought great convenience to people and also brought great damage to the environment. The world’s forests are decreasing at a rate of 2,000 hectares per year, an area equivalent to 2,800 football fields, and the rate of decrease is gradually accelerating. The loss of forest area caused by forest fires is particularly huge. Forest fires are a serious natural disaster in many forestry countries, and both developed and developing countries lack effective means to control forest fires. my country is a country with relatively few forest resources. Forest fires have caused very serious losses to our Shaolin country. Effective prevention and reduction of forest fires are currently very urgent issues. An important part of forest fire prev...

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): G06K9/00G06K9/46
CPCG06V20/188G06V10/462
Inventor 吴宣利肖雨桐邓啸沙学军吴玮李卓明
Owner HARBIN INST OF TECH
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