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

Garbage classification and intelligent recovery method for AI image recognition

A technology of garbage classification and recycling methods, applied in image analysis, neural learning methods, image enhancement, etc., can solve the problems of unsatisfactory recognition rate and low efficiency

Active Publication Date: 2021-03-26
SOUTH CHINA AGRI UNIV
View PDF12 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide a garbage classification and intelligent recycling method based on AI image recognition. Using target detection technology and classification algorithm, it can effectively solve the problem of garbage type, quantity and volume recognition and prediction, and carry out classification identification and intelligent recycling of garbage. So as to solve the problems of low efficiency and unsatisfactory recognition rate in the existing technology

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
  • Garbage classification and intelligent recovery method for AI image recognition
  • Garbage classification and intelligent recovery method for AI image recognition
  • Garbage classification and intelligent recovery method for AI image recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0056] The invention discloses a garbage classification and intelligent recycling method for AI map recognition. In conjunction with the accompanying drawings, the specific steps of the invention are described as follows:

[0057] Step 1. Take pictures of the garbage to be identified. A large number of garbage pictures obtained by taking pictures are marked and established to contain garbage target bounding boxes, volumes, and types of garbage image datasets and divided into training sets and verification sets.

[0058] In this step, the acquired garbage pictures are marked, including the bounding box, volume and type of the garbage target, and then the marked garbage image data is made into a Pascal VOC dataset format, and then the image dataset is divided into a training set according to a certain ratio and validation set. In this embodiment, the garbage image data set focuses on four types of garbage objects (ie, plastic bags, plastic bottles, cans, and cartons), and the im...

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 garbage classification and intelligent recovery method for AI image recognition, and the method comprises the steps: photographing to-be-recognized garbage, marking a garbageimage obtained through photographing, and building a garbage image data set containing a garbage target boundary frame, the size and the type; constructing an improved YOLOv3 network model based on hole convolution, redesigning a loss function of the network model in combination with a relationship between a photographing angle and a distance of a camera when photographing the garbage and a frameprediction mechanism of the YOLOv3 network model, and training the network model by utilizing the garbage image data set to obtain a prediction model; performing type, quantity and volume estimationon garbage in the to-be-detected garbage image acquired from the garbage point; and obtaining a final garbage classification prediction result by setting a confidence threshold and non-maximum suppression. And based on the garbage classification prediction results of all the to-be-recycled garbage points, garbage recycling order delivery of the recycling vehicle is carried out in combination witha path planning function of an online map.

Description

technical field [0001] The invention relates to the fields of image processing and artificial intelligence, in particular to a garbage classification and intelligent recycling method for AI map recognition. Background technique [0002] At this stage, with the acceleration of urbanization and the rapid increase of urban population, the amount of garbage generated in cities every day has increased sharply; many cities have the phenomenon of garbage accumulation. The current method for garbage classification is mainly to manually classify and detect garbage, but manual classification and detection have defects such as low efficiency, high cost, and the recognition rate is affected by subjective factors, which cannot meet the growing demand for garbage classification and recycling; some current images Although the recognition algorithm has a good effect in some application scenarios, because the garbage volume, garbage quantity, type and other characteristics need to be conside...

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): G06K9/00G06K9/62G06T7/62G06F16/29G01C21/20G06Q50/26
CPCG06T7/62G06N3/08G06F16/29G01C21/20G06Q50/26G06T2207/20081G06T2207/20084G06V20/00G06V2201/07G06N3/045G06F18/24G06F18/214
Inventor 包世泰沈玉冰苏芷漩曾锦添姚策益黄展鹏
Owner SOUTH CHINA AGRI UNIV
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