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

Kitchen ventilator cooking fume recognition method and kitchen ventilator

A lampblack machine and lampblack technology, which is applied in the fields of lampblack removal, character and pattern recognition, heating method, etc., can solve the problem of inaccurate lampblack recognition results of lampblack image data frames, inability to accurately control kitchen electrical equipment, and inability to correctly calculate key characteristic smoke. The actual change amount and other issues, to achieve the effect of ensuring the use habits and quality

Active Publication Date: 2020-06-30
JOYOUNG CO LTD
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

As a result, the image data acquired by the camera cannot correctly calculate the actual change of the key feature smoke during the working process of the equipment, so that it is impossible to accurately control the kitchen appliances
[0003] Most of the current oil fume processing algorithms are based on the premise that the image quality of the real-time oil fume data frame as an input parameter is ideal enough, but due to the large difference between the actual oil fume image data frame and the laboratory environment, it will lead to The final oil fume recognition result is inaccurate
[0004] The traditional way to deal with the above problems is usually to adjust the light intensity of the supplementary light and then send the images acquired by the camera to the algorithm processing unit for processing. When the kitchen is in a high-exposure environment, even if the oil fume is very small, a large value of the oil fume may be calculated due to the influence of the high exposure of the lens. There may be a large difference between the image after simple brightness adjustment and the actual object.

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
  • Kitchen ventilator cooking fume recognition method and kitchen ventilator
  • Kitchen ventilator cooking fume recognition method and kitchen ventilator
  • Kitchen ventilator cooking fume recognition method and kitchen ventilator

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0099] Such as Figure 4 As shown, in order to solve the impact of ambient light on image recognition, parameters such as brightness, grayscale, and color that may have a greater impact on recognition are selected. In sunny days, no direct light, and bright environments, the image effect of this embodiment is processed. The numerical range of the correct recognition result is used as the parameter benchmark, and the brightness value, color, gray value and other parameters obtained by the camera at the current moment are compared with the parameter benchmark, and when the value is not within the benchmark range, adjust the relevant parameters until the value falls. Within the reference range, the image processed by the above process is re-identified to correspond to the oil fume information, and the process is as follows:

[0100] 1. Adjust the photosensitive parameters of the hue head based on the brightness, grayscale, and color parameter benchmarks of the pre-established sta...

Embodiment 2

[0107] This embodiment illustrates the process of image brightness adjustment:

[0108] Upgrade the conventional lighting device of the range hood to a lighting with adjustable brightness value, and choose a lens with a large enough light input for the camera recognition module so that it can have better adaptability in the case of excessive light or too dark light . The brightness adjustment process in the image recognition process is as follows: Figure 5 As shown, first obtain the brightness value of the photosensitive device of the camera. If the brightness value is lower than the reference range, it means that the current ambient light is dark. At this time, the exposure time of the lens is increased step by step. The power consumption of the camera increases, and the heat of the camera makes the current noise of the captured image larger. Therefore, it is necessary to set the exposure level threshold, which can allow the camera to freely adjust the exposure time without...

Embodiment 3

[0110] This embodiment illustrates the process of image color adjustment:

[0111] After the above brightness adjustment, the brightness value of the image data collected by the cooker hood in real time has been adjusted to the reference range, but no matter how high or low the exposure parameters of the camera are adjusted or the brightness value of the captured image is directly adjusted, the image quality will be affected. And almost all image recognition technologies are based on the grayscale image after image data frame binarization, so the image quality loss caused by brightness adjustment must be restored before the grayscale image processing. The camera-side and color-related parameters include image contrast, hue, and saturation. Its adjustment process is as follows Figure 6 Shown: first obtain the image contrast, chroma and saturation values ​​of the color card area, and compare with the established color reference, so that the three parameters of the color card a...

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 kitchen ventilator cooking fume recognition method and a kitchen ventilator. The method comprises the steps that an image collecting device is used for obtaining the currentlight ray state, light sensitization parameters of the image collecting device are adjusted, and imaging parameter information of the image collecting device is in the imaging parameter information value range in the standard light ray state; the image collecting device is used for obtaining target image information, and the obtained target image information is compared with preset image datum information; the imaging brightness information of the kitchen ventilator and / or the target image attribute information are / is adjusted, and the target image information is in the preset image datum information value range; and according to the adjusted target image information, the cooking fume amount information corresponding to a target image is determined.

Description

technical field [0001] The invention relates to the technical field of smart home appliances, in particular to a method for identifying oil fume of a range hood and the range hood. Background technique [0002] It has become a trend in the development of the industry to use image recognition for oil fume recognition on hoods and stoves. One of the core problems of image recognition algorithm processing in the kitchen environment is that the adaptability and accuracy of the recognition algorithm cannot be guaranteed. Since the actual kitchen environment of the user is different, the same user’s kitchen environment will be different in different time periods of the year and in a day. The light intensity at different time points is not the same. It is impossible for the same set of algorithms to be suitable for all these situations. As a result, the image data acquired by the camera cannot correctly calculate the actual change of the key characteristic smoke during the operat...

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): F24C15/20G06K9/20G06K9/00G06K9/62
CPCF24C15/2021G06V20/00G06V10/141G06F18/22
Inventor 朱泽春孙金彪
Owner JOYOUNG CO LTD
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