Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Dynamic background modeling method for cooking fume image processing and cooking fume hood

A technology of dynamic background and background modeling, applied in the direction of editing/combining graphics or text, etc., can solve problems such as mislabeling, erratic kitchen fumes, and easy to be disturbed, and achieve the effect of accurate comparison of objects

Pending Publication Date: 2019-02-15
FOSHAN VIOMI ELECTRICAL TECH +1
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, the segmentation processing of oil fume images is mainly carried out manually. This segmentation method is not only inefficient but also susceptible to interference and mislabeling.
[0004] Since kitchen fumes are erratic and easily disturbed by arms, spatulas, etc., the difficulty of image segmentation lies in the inability to find a suitable reference image for comparison, and the solutions in the prior art cannot solve this problem at present.

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
  • Dynamic background modeling method for cooking fume image processing and cooking fume hood

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] A dynamic background modeling method for cooking fume image processing. The visual imaging module of the range hood continuously images the target area of ​​the cooktop, and sends the imaging pictures to the processing module. The processing module takes the received imaging pictures according to the imaging time and The frame sequence is marked, and the imaging moment corresponding to the imaging picture P of the yth frame is T y , the corresponding frame sequence is y, and y is a natural number.

[0045] The frame sequence corresponding to the imaging picture to be processed by oil fume is η, the number of background modeling sampling images used to establish the dynamic background model image is F, the sequence number of the dynamic background model image M is ψ, and ψ is a natural number greater than or equal to F, η is a natural number greater than or equal to ψ, F is a natural number, and F is a natural number greater than 3;

[0046] The process of establishing ...

Embodiment 2

[0067] This embodiment is a range hood based on the dynamic background modeling method of Embodiment 1, and its structure is as follows figure 1 As shown, the smoke machine main body 100 is provided with:

[0068] The visual imaging module continuously images the target area of ​​the cooktop and sends the imaging pictures to the processing module;

[0069] The processing module receives the imaging picture sent by the visual imaging module and processes the imaging picture. The processing module uses the dynamic background modeling method of Embodiment 1 to construct a background model image Mψ for comparing the current frame image.

[0070] Specifically, the visual imaging module is provided with a camera 200, which is built into the housing of the cigarette machine main body 100, and the lens of the camera 200 faces the target area of ​​the stove 400, and the output end of the camera 200 is electrically connected to the processing module. The camera 200 is used to take imag...

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 relates to a dynamic background modeling method and a fume hood for fume image processing, wherein a vision imaging module of the fume hood continuously images a target area of a stove,and sends an imaging picture to the processing module for processing. The frame order of the image to be processed is Eta, and the sequence number of the background model M is Psi; The process of dynamic background modeling is as follows: S1, Judging Eta- Is the difference ofPsi equal to 2, and if so, proceeds to step s3 if Eta- If the difference of. Psi. Is equal to 1, the process proceeds to step S2; 2, selecting an F frame imaging picture as a background model sample image group, and selecting a gray minimum value at each pixel point in that background modeling sampling image to obtain a background model image M; The frame order of the selected F-frame imaging picture is Psi-, Psi 1 toPsi- F+1, F is a natural numb and F is not less than 3; S3, let. Psi. =. Psi. +1, and return to step S2. The invention can provide accurate background model images.

Description

technical field [0001] The invention relates to the technical field of cooking fume processing, in particular to a dynamic background modeling method for cooking fume image processing and a range hood based on the method. Background technique [0002] The kitchen is one of the necessary configurations at home, and the effect of kitchen fume treatment directly affects people's quality of life. In the prior art, there are mainly infrared projection method and physical detection method for detecting the concentration of cooking fume. In the infrared projection method, one end emits infrared light and the other end receives it, and the concentration of oil fume is judged by the intensity of the received infrared light. However, due to the uncertainty of oil fume drifting, there will be interference such as human hand shielding in practice, so it is necessary to install multiple infrared emitters at different positions to ensure relatively accurate oil fume detection, the cost i...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06T11/60
CPCG06T11/60
Inventor 陈小平陈超
Owner FOSHAN VIOMI ELECTRICAL TECH
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
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