Method and system for correcting smoke recognition effect of range hood, and range hood

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 problems of inability to achieve lampblack, different, etc., and achieve the effect of improving the accuracy of automatic recognition.

Active Publication Date: 2021-04-06
HONGYANG HOME APPLIANCES
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] In related technologies, it is one of the directions of the range hood industry to apply image recognition technology to the range hood to identify the size of the range hood. However, an insurmountable problem is that the kitchen environment of each user is different, and it is impossible to achieve a consistent result due to the influence of kitchen light. A set of cooking fume recognition algorithms can accurately identify all cooking fumes in the kitchen; on the other hand, adding a camera to the range hood makes the range hood more intelligent. There is no effective solution in the industry to better interact with users during the cooking process and increase users' stickiness to use smart hoods

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
  • Method and system for correcting smoke recognition effect of range hood, and range hood
  • Method and system for correcting smoke recognition effect of range hood, and range hood
  • Method and system for correcting smoke recognition effect of range hood, and range hood

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0071] An embodiment of the present invention provides a method for correcting the smoke recognition effect of a range hood, such as figure 1 As shown, the range hood includes an image acquisition module 100, an identification module 200, a communication module 300 and a control module 400, such as figure 2 As shown, the method includes:

[0072] S01. Obtain image information of cooking fumes;

[0073] S02. Generate machine calibration information according to the image information;

[0074] S03. Obtain manual calibration information of the cooking fume recognition result corresponding to the image information;

[0075] S04. Verifying the manual calibration information, and correcting the position and / or amount of cooking fumes misidentified in the machine calibration information according to the verification results;

[0076] S05. Using the corrected machine calibration information to train an image recognition model of cooking fumes.

[0077] Because the range hood coll...

Embodiment 2

[0079] On the basis of the first embodiment, this embodiment provides a solution for the excessive difference between the manual calibration information and the machine calibration information.

[0080] The image information of the cooking fume is pre-divided by time period and community, for example, a residential area or a street is regarded as a community.

[0081] Comparing the manual calibration information and the machine calibration information of the image information of the cooking oil fumes acquired in each time period and in each community;

[0082] Determining the image information of the cooking fume whose difference between the manual calibration information and the machine calibration information is greater than or equal to a preset threshold as an abnormal environment training set;

[0083] Training an Image Recognition Model of Cooking Fume Using the Abnormal Environment Training Set.

[0084] In an exemplary embodiment of the present invention, for users in ...

Embodiment 3

[0089] This embodiment provides a method for obtaining manual calibration information on the basis of any of the foregoing embodiments.

[0090] In an exemplary embodiment of the present invention, in step S02, machine calibration information is generated according to the image information; it may be executed by the range hood, or the range hood sends the image information to the cloud server, and the cloud server executes it.

[0091] In an exemplary embodiment of the present invention, in step S03, the manual calibration information of the cooking fume identification result can be manually calibrated by the user through the display screen of the user terminal or the display screen of the range hood, or can be manually calibrated by the operator of the cloud server. Manual calibration is performed on the cloud server.

[0092] In step S03, obtaining the manual calibration information of the cooking fume recognition result corresponding to the image information includes at lea...

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 present application proposes a smoke recognition effect correction method and system of a range hood, and a range hood, which relate to the field of smart device improvement. The method includes: acquiring image information of cooking fume; generating machine calibration information according to the image information; acquiring manual calibration information of cooking fume recognition results corresponding to the image information; verifying the manual calibration information, according to The verification result corrects the position and / or amount of cooking oil fume misrecognized in the machine calibration information; and uses the corrected machine calibration information to train an image recognition model of cooking oil fume. Improve the effect of image recognition and detection of smoke through user interaction and verification of user feedback information.

Description

technical field [0001] The invention relates to the field of smart device improvement, in particular to a smoke recognition effect correction method and system of a range hood and a range hood. Background technique [0002] In related technologies, it is one of the directions of the range hood industry to apply image recognition technology to the range hood to identify the size of the range hood. However, an insurmountable problem is that the kitchen environment of each user is different, and it is impossible to achieve a consistent result due to the influence of kitchen light. A set of cooking fume recognition algorithms can accurately identify all cooking fumes in the kitchen; on the other hand, adding a camera to the range hood makes the range hood more intelligent. There is currently no effective solution in the industry to better interact with users during the cooking process and increase users' stickiness to use smart hoods. Contents of the invention [0003] The in...

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 Patents(China)
IPC IPC(8): F24C15/20G06K9/62G06K9/00
CPCF24C15/2021G06V20/41G06F18/22G06F18/214
Inventor 王旭宁孙金彪李宏峰
Owner HONGYANG HOME APPLIANCES
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