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

Torch smoke dust monitoring method based on visual perception

A visual perception, torch technology, applied in image data processing, instrument, character and pattern recognition, etc., can solve the problems of difficult data samples, poor robustness, noise interference, etc.

Active Publication Date: 2020-02-21
BEIJING UNIV OF TECH
View PDF7 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Deep networks require a large number of training samples, but it is difficult to actually collect a large number of data samples, resulting in data scarcity
In addition, deep networks are sensitive to noise interference and have poor robustness

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
  • Torch smoke dust monitoring method based on visual perception
  • Torch smoke dust monitoring method based on visual perception
  • Torch smoke dust monitoring method based on visual perception

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] (1) Flame area detection

[0055] By observing the typical flaring gas combustion photos collected on-site in petrochemical enterprises, such as figure 1 . Divide the photos into three categories: "no flame and smoke", "flame and no smoke", and "flame and smoke". The presence of flame is a prerequisite for the presence of smoke, therefore, the first task of the proposed VMFM is to identify the presence or absence of flame. First, downsample the collected RGB image to reduce the image size by 3 times, and then calculate the wide-tuned color channel between the red channel corresponding to the flame and the blue channel corresponding to the sky to identify the existence of the flame:

[0056] D. flame =F 1 B 1 (P R -P B ) (11)

[0057] Among them, D flame Indicates the detection result of the flame area; P R ,P B respectively represent the pixel values ​​of the R (red) and B (blue) channels of the downsampled RGB image; B 1 In order to distinguish the threshol...

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 torch smoke dust monitoring method based on visual perception, and belongs to the crossing field of image processing and environment perception. According to the VMFM provided by the invention, firstly, whether flame exists in an image is identified by utilizing a wide tuning color channel, then the position of the flame is determined by combining rapid significance detection and a K-means method, finally, a potential torch smoke area is searched by taking the flame area as a center, and finally, whether torch smoke exists or not is detected. Experimental results on aplurality of video sequences acquired from a petrochemical plant show that the method is superior to existing related methods in monitoring performance and calculation efficiency. According to the torch smoke dust monitoring method based on vision, torch smoke dust can be found in time, and sufficient combustion of torch gas is guaranteed.

Description

technical field [0001] The vision-based torch smoke monitoring method (VMFM) designed by the invention can detect the torch smoke in time and ensure the full combustion of the torch gas. The VMFM proposed by the present invention first uses the wide tuning color channel to identify whether there is a flame in the image, then combines the fast saliency detection and K-means method to determine the position of the flame, and finally searches for the potential flare smoke area centered on the flame area and finally detects Presence of flare soot. Experimental results on multiple video sequences collected from petrochemical plants show that the monitoring system proposed by the present invention is superior to existing related methods in terms of monitoring performance and computing efficiency. The vision-based flaring soot monitoring method belongs to the intersection field of image processing and environmental perception. Background technique [0002] Vent flare is an indisp...

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): G06K9/32G06K9/46G06K9/62G06T5/00G06T5/30G06T7/11G06T7/136G06T7/90
CPCG06T7/90G06T7/11G06T5/30G06T7/136G06T2207/20032G06V10/255G06V10/44G06V10/462G06F18/23213G06T5/70
Inventor 顾锞董江涛乔俊飞李硕
Owner BEIJING UNIV 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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com