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

Photoelectric intelligent garbage sorting method based on DMD and YOLOV5

A garbage sorting and garbage technology, applied in sorting, neural learning methods, character and pattern recognition, etc., can solve the problems of lack of cooperation, cumbersome garbage sorting operations, etc., to achieve low algorithm complexity and time complexity, anti-interference The effect of strong ability and low environmental conditions

Inactive Publication Date: 2021-09-24
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to propose a photoelectric intelligent garbage sorting method based on DMD and YOLOV5 in view of the technical status quo of existing garbage sorting operations that are cumbersome, lack of collaboration, and efficiency needs to be improved

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
  • Photoelectric intelligent garbage sorting method based on DMD and YOLOV5
  • Photoelectric intelligent garbage sorting method based on DMD and YOLOV5
  • Photoelectric intelligent garbage sorting method based on DMD and YOLOV5

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] In this implementation example, the photoelectric intelligent garbage sorting method based on DMD and YOLOV5, the process is as follows figure 1 and figure 2 shown. Used for domestic waste classification, including the following steps:

[0047] Step A. Construct a household daily life garbage image dataset.

[0048] Among them, the common garbage categories in daily life include "paper", "glass", "plastic", "waste batteries", "expired medicines", etc. Users can adjust and improve according to the actual situation of their families;

[0049] Step B. Perform gamma-corrected image enhancement on the image data.

[0050] Among them, due to the shooting problems and lighting problems of the users, the captured images of domestic waste are often too dark, and the brightness of the images is corrected by gamma; the expression of gamma correction is:

[0051]

[0052] Wherein I is the image input, O is the image output, and r is the gamma coefficient. The gamma coeffici...

Embodiment 2

[0061] In this implementation example, the photoelectric intelligent garbage sorting method based on DMD and YOLOV5 is used for garbage sorting in school scenes, including the following steps:

[0062] Step a. Construct a dataset of school trash images.

[0063] These include the common types of garbage in schools, including "paper", "waste books", "plastic water bottles", "waste stationery", "litter leaves", etc. Compared with household garbage classification, there are more types of garbage on campus and The distribution is wide, both in the classroom and outside the classroom, and users can adjust and improve according to the actual situation of the school.

[0064] Step b. Perform spatial domain filtering on the image data.

[0065] Among them, since there are many types of garbage in the school scene and the image will be blurred during the shooting process, the second-order differential image sharpening in the spatial domain filter, that is, Laplace sharpening, is used ...

Embodiment 3

[0073] In this implementation example, the photoelectric intelligent garbage sorting method based on DMD and YOLOV5 is used for garbage sorting in factory production scenarios, including the following steps:

[0074] Step 1). Construct a factory-produced garbage image dataset.

[0075] These include the common types of garbage in the factory production process, including "scrap iron sheets", "scrap steel pipes", "used gloves", etc. Compared with household garbage classification and school garbage classification, the types of garbage in the factory production process are relatively single.

[0076] Step 2). Carry out YCbCr color space conversion to the image data to enhance image saturation.

[0077] Among them, the garbage in the factory production process is similar to the background, and the degree of discrimination is low. By extracting the CbCr component and the brightness Y component of the image data, the image data is converted to the YCbCr color space, thereby enhanci...

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 photoelectric intelligent garbage sorting method based on DMD and YOLOV5, and belongs to the technical field of garbage classification and mechanical intelligent control. The method comprises the following steps: 1, initializing a camera and a mechanical claw; 2, acquiring a garbage image through a camera; 3, constructing a garbage image data set, specifically, decomposing the garbage image into a background and a foreground through a DMD, and extracting the foreground to construct the garbage image data set; 4, inputting the constructed garbage image data set into the YOLOV5 network for training, and obtaining the trained YOLOV5 network as a garbage image recognition model; 5, capturing a to-be-recognized time sequence picture through a camera, dividing the captured to-be-recognized time sequence picture into a background and a foreground by using the DMD, and extracting the foreground to form a test set; and 6, carrying out real-time classification and identification on the foreground in the test set by utilizing the trained garbage image recognition model to obtain the position and the quantity of garbage. The garbage sorting method is high in recognition accuracy, low in algorithm complexity, low in environmental condition requirement and high in anti-jamming capability.

Description

technical field [0001] The invention relates to a photoelectric intelligent garbage sorting method based on DMD and YOLOV5, and belongs to the technical field of garbage sorting and mechanical intelligent control. Background technique [0002] According to certain regulations or standards, sorting, storing, putting and transporting garbage can turn garbage into public resources and improve the resource value and economic value of garbage, which can provide huge economic, social and ecological benefits for the national economy. In cities, garbage is mainly distributed in roads and residential areas. These areas are directly related to residents' living and transportation, and the identification and detection of garbage is very important. With the continuous progress of society and the improvement of people's living standards, the requirements for the living environment are getting higher and higher, and higher requirements are also put forward for the treatment technology of ...

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): G06K9/00G06K9/46G06K9/62G06N3/04G06N3/08B07C5/342
CPCG06N3/08B07C5/3422G06N3/045G06F18/2135G06F18/241
Inventor 刘国栋冯立辉陈子健李亿俍卢继华
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
Features
  • Generate Ideas
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com