CN113191420A - Garbage classification method and intelligent garbage can - Google Patents
Garbage classification method and intelligent garbage can Download PDFInfo
- Publication number
- CN113191420A CN113191420A CN202110459712.XA CN202110459712A CN113191420A CN 113191420 A CN113191420 A CN 113191420A CN 202110459712 A CN202110459712 A CN 202110459712A CN 113191420 A CN113191420 A CN 113191420A
- Authority
- CN
- China
- Prior art keywords
- garbage
- classification
- data set
- training model
- classified
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000010813 municipal solid waste Substances 0.000 title claims abstract description 190
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000012549 training Methods 0.000 claims abstract description 69
- 238000007781 pre-processing Methods 0.000 claims abstract description 23
- 238000013526 transfer learning Methods 0.000 claims abstract description 11
- 238000000605 extraction Methods 0.000 claims abstract description 8
- 230000006870 function Effects 0.000 claims description 12
- 239000002699 waste material Substances 0.000 claims description 10
- 238000013434 data augmentation Methods 0.000 claims description 7
- 238000013527 convolutional neural network Methods 0.000 claims description 4
- 230000007246 mechanism Effects 0.000 claims description 4
- 238000005457 optimization Methods 0.000 claims description 4
- 230000003190 augmentative effect Effects 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 9
- 238000004064 recycling Methods 0.000 description 4
- 230000009193 crawling Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000013508 migration Methods 0.000 description 2
- 230000005012 migration Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 239000010847 non-recyclable waste Substances 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 239000010819 recyclable waste Substances 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000010926 waste battery Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computational Linguistics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a garbage classification method and an intelligent garbage can, wherein the classification method comprises the following steps: acquiring a basic data set, and preprocessing the basic data set to obtain a preprocessed data set; selecting a pre-training model for transfer learning, inputting the pre-processing data set and the garbage classification labels into the pre-training model for training, and constructing a garbage training model; collecting image data of garbage to be classified, and inputting the image data into a garbage training model for feature extraction to obtain garbage features corresponding to the garbage to be classified; and matching the garbage features with the features in the garbage training model, and obtaining the classification result of the garbage to be classified according to the matching result. According to the embodiment of the invention, after a large amount of preprocessing data is acquired, the pre-training model is selected for transfer learning to construct the garbage training model, and the garbage to be classified is subjected to feature extraction and matching through the garbage training model, so that various types of garbage in life can be comprehensively identified, and the garbage classification effect can be effectively improved.
Description
Technical Field
The invention relates to the technical field of garbage classification, in particular to a garbage classification method and an intelligent garbage can.
Background
With the development of economy, the living standard of people is gradually improved, and the yield of the produced garbage is greatly increased like a eruption type. The problem of garbage classification and recycling is becoming more and more serious, and the garbage classification and recycling is becoming an indispensable part of the daily life of residents. However, the current garbage classification effect is not obvious, and mainly comprises two reasons, namely lack of publicity and popularization education for garbage classification and recycling in China; on the other hand, people have incomplete knowledge of garbage classification. Therefore, how to effectively classify the garbage to improve the utilization rate of the garbage and reduce the pollution of the garbage is very important. The existing garbage classification method can only identify garbage with fixed shapes, and can not comprehensively identify various garbage in life, so that the garbage classification effect is poor.
Disclosure of Invention
The invention provides a garbage classification method and an intelligent garbage can, and aims to solve the technical problem that the existing garbage classification method can only identify garbage with fixed shapes and cannot comprehensively identify various garbage in life, so that the garbage classification effect is poor.
A first embodiment of the present invention provides a garbage classification method, including:
acquiring a basic data set, and preprocessing the basic data set to obtain a preprocessed data set;
selecting a pre-training model for transfer learning, inputting the pre-processing data set and the garbage classification labels into the pre-training model for training, and constructing a garbage training model;
collecting image data of garbage to be classified, and inputting the image data into the garbage training model for feature extraction to obtain garbage features corresponding to the garbage to be classified;
and matching the garbage features with the features in the garbage training model, obtaining the classification labels of the garbage to be classified according to the matching result, and taking the classification labels as the classification result of the garbage to be classified.
Further, the acquiring a basic data set and preprocessing the basic data set to obtain a preprocessed data set specifically include:
and acquiring a basic data set, and preprocessing the basic data set by adopting a data augmentation method to obtain a preprocessed data set.
Further, preprocessing the basic data set by using a data augmentation method to obtain a preprocessed data set, including:
carrying out horizontal overturning, vertical overturning, Gaussian noise and Gaussian fuzzy operation on the basic data set to expand the basic data set; and augmenting the base data set by introducing external data.
Further, selecting a pre-training model for transfer learning, inputting the pre-processing data set and the garbage classification label into the pre-training model for training, and constructing a garbage training model, specifically:
selecting a convolutional neural network as a pre-training model, adding a CBAM (convolutional code modulation) attention mechanism module to a first convolutional layer of the pre-training model, adding a Dropout layer to a full-link layer of the pre-training model, and adopting a cross entropy loss function as a loss function and an SGD (serving gateway device) as an optimization function;
and inputting the preprocessed data set and the garbage classification labels into the pre-training model for fine-tuning training, and constructing a garbage training model.
Further, the garbage classification method further comprises the following steps: after the classification result of the garbage to be classified is obtained, the classification result is played through voice, and when no classification instruction manually input by a user is detected within preset time, a valve of a garbage collection device corresponding to the classification result is controlled to be opened.
Further, the classification labels include recyclable waste, non-recyclable waste, and other waste.
The invention provides an intelligent garbage can, which comprises a shell, a cover plate, a classification and identification cavity and a plurality of garbage collection devices, wherein the cover plate is arranged at the top of the shell, the classification and identification cavity for performing classification and identification on garbage to be classified is arranged below the cover plate, and the bottom of the classification and identification cavity is provided with an inner door communicated to the plurality of garbage collection devices through a transmission pipeline;
the classification and identification cavity is provided with an image acquisition module and a garbage classification device, the image acquisition module is used for acquiring image data of garbage to be classified in the classification and identification cavity, and the garbage classification device is used for executing the garbage classification method.
Further, the intelligent garbage can further comprises a pressure sensor arranged on the cover plate, and the pressure sensor is used for detecting whether the cover plate has a pressure value exceeding a threshold value.
Further, the garbage classification device is also used for controlling the cover plate to be opened when the pressure value detected by the pressure sensor exceeds the threshold value.
Furthermore, the intelligent garbage can further comprises infrared detectors arranged on the garbage collecting devices, and the infrared detectors are used for detecting whether the garbage capacity of the garbage collecting devices reaches a preset value or not through infrared light.
According to the embodiment of the invention, after a large amount of preprocessing data is acquired, the pre-training model is selected for transfer learning to construct the garbage training model, and the garbage to be classified is subjected to feature extraction and matching through the garbage training model, so that various types of garbage in life can be comprehensively identified, and the garbage classification effect can be effectively improved.
Drawings
Fig. 1 is a schematic flow chart of a garbage classification method according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of an intelligent trash can according to an embodiment of the present invention.
Fig. 3 is another schematic structural diagram of an intelligent trash can according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
In the description of the present application, it is to be understood that the terms "first", "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implying any number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present application, "a plurality" means two or more unless otherwise specified.
In the description of the present application, it is to be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meaning of the above terms in the present application can be understood in a specific case by those of ordinary skill in the art.
Referring to fig. 1, in a first embodiment of the present invention, a method for garbage classification is provided, including:
s1, acquiring a basic data set, and preprocessing the basic data set to obtain a preprocessed data set;
in the embodiment of the invention, the basic data sets are real and high-quality data resources, and comprise 40 common junk picture data sets in the schedule life. It should be noted that each garbage corresponds to a classification label, and the classification label includes recyclable garbage, non-recyclable garbage, and other garbage. Specifically, waste such as waste glass, fabric, furniture, electrical and electronic products and the like which are suitable for recycling and can be recycled are classified as recyclable garbage; waste such as waste batteries, waste medicines, waste lamp tubes and the like which are harmful to the health of people and the natural environment and are specially treated are classified as non-recyclable garbage; waste other than the above two types of waste is classified as other waste.
S2, selecting a pre-training model for transfer learning, inputting the pre-processing data set and the garbage classification label into the pre-training model for training, and constructing a garbage training model;
s3, collecting image data of the garbage to be classified, and inputting the image data into a garbage training model for feature extraction to obtain garbage features corresponding to the garbage to be classified;
and S4, matching the garbage features with the features in the garbage training model, obtaining the classification labels of the garbage to be classified according to the matching result, and taking the classification labels as the classification result of the garbage to be classified.
As a specific implementation manner of the embodiment of the present invention, a basic data set is obtained, and the basic data set is preprocessed to obtain a preprocessed data set, which specifically includes:
and acquiring a basic data set, and preprocessing the basic data set by adopting a data augmentation method to obtain a preprocessed data set.
Illustratively, preprocessing the basic data set by using a data augmentation method to obtain a preprocessed data set includes: carrying out horizontal overturning, vertical overturning, Gaussian noise and Gaussian fuzzy operation on the basic data set to expand the basic data set; and augmenting the base data set by importing external data. Specifically, expand basic data set including data crawling and two steps of data screening through introducing external data, wherein the data crawling is realized through web crawler technique, and web crawler's flow is: firstly, sending a request to a remote server to acquire an HTML (hypertext markup language) file of a target webpage; the HTML file is then tracked to obtain corresponding file data. Because the number of categories in the basic data set is unbalanced, the embodiment of the invention uses a web crawler mode to perform data expansion on the categories with less number in the basic data set from the hundredth gallery, firstly inputs the name keywords of the pictures to be crawled, and then inputs the number of the pictures to be crawled and the stored folders to perform picture crawling.
According to the embodiment of the invention, the basic data set is expanded through data augmentation, so that the overfitting phenomenon possibly occurring in the model training process due to too few basic data sets is avoided, the generalization capability of the model is improved, and the garbage classification achieves a better effect.
As a specific implementation manner of the embodiment of the present invention, a pre-training model is selected for migration learning, a pre-processing data set and a garbage classification label are input into the pre-training model for training, and a garbage training model is constructed, specifically:
selecting a convolutional neural network as a pre-training model, adding a CBAM (convolutional neural network) attention mechanism module to a first convolutional layer of the pre-training model, adding a Dropout layer to a full-link layer of the pre-training model, and adopting a cross entropy loss function as a loss function and an SGD (serving gateway device) as an optimization function;
and inputting the preprocessed data set and the garbage classification label into a pre-training model for fine-tuning training, and constructing a garbage training model.
In the embodiment of the invention, a ResNext 101-32 x16 d-WSL network is used as a basic network structure for migration learning, a CBAM (CBAM attention mechanism) module is added to a first-layer convolutional layer to enhance the image feature characterization capability, the important features of an image are focused to inhibit unnecessary features, and the weights of other layers except a fully-connected layer are fixed. According to the embodiment of the invention, a Dropout layer is added to the full-link layer of the pre-training model, the cross entropy loss function is used as a loss function, and the SGD is used as an optimization function, so that overfitting can be effectively reduced. The image data of the garbage to be classified is classified based on transfer learning, other parameters in the network are kept unchanged, only the last layers of the pre-training model are modified, and the parameters of the last layers are obtained by retraining on the new data set. The parameters of other layers are kept unchanged and used as a feature extractor, and then the whole network is trained by using a smaller learning rate, so that the calculation time and the resources required by calculation can be effectively reduced, the possibility of occurrence of overfitting can be effectively reduced, and the classification effect is effectively improved.
As a specific implementation manner of the embodiment of the present invention, the garbage classification method further includes: after the classification result of the garbage to be classified is obtained, the classification result is played through voice, and when the classification instruction manually input by a user is not detected within the preset time, the valve of the garbage collection device corresponding to the classification result is controlled to be opened.
In the embodiment of the invention, after the classification result of the garbage to be classified is obtained, the recognized classification result is played through voice, and after listening to the classification result, if the recognition is not correct, the user can manually select the correct classification result within 10 seconds of the voice information playing. And the internal controller executing the garbage classification method acquires a manual selection result of a user and uploads the result to the server to update the data of the server so as to realize data sharing.
The embodiment of the invention has the following beneficial effects:
according to the embodiment of the invention, after a large amount of preprocessing data is acquired, the pre-training model is selected for transfer learning to construct the garbage training model, and the garbage to be classified is subjected to feature extraction and matching through the garbage training model, so that various types of garbage in life can be comprehensively identified, and the garbage classification effect can be effectively improved.
Referring to fig. 2-3, a second embodiment of the present invention provides the intelligent trash can shown in fig. 2, which includes a housing, a cover plate 1, a classification and identification cavity 2 and a plurality of trash collection devices, wherein the cover plate 1 is disposed at the top of the housing, the classification and identification cavity 2 for classifying and identifying trash to be classified is disposed below the cover plate 1, and an inner door 3 communicated to the plurality of trash collection devices through a transmission pipeline is disposed at the bottom of the classification and identification cavity 2;
the classification and identification cavity 2 is provided with an image acquisition module and a garbage classification device, the image acquisition module is used for acquiring image data of garbage to be classified in the classification and identification cavity 2, and the garbage classification device is used for executing the garbage classification method.
In the embodiment of the present invention, after the garbage classification device obtains the garbage classification result, the garbage to be classified is transmitted to the corresponding garbage collection device according to the classification result, wherein the garbage collection device includes a recyclable garbage collection device 5, a non-recyclable garbage collection device 4 and another garbage collection device 6.
Optionally, the image acquisition module comprises an X-ray tube 8 and a camera 7.
As a specific implementation manner of the embodiment of the present invention, the intelligent trash can further includes a pressure sensor disposed on the cover plate 1, and the pressure sensor is configured to detect whether a pressure value exceeding a threshold value exists in the cover plate 1. As a specific implementation manner of the embodiment of the present invention, the garbage classification device is further configured to control the cover plate 1 to open when the pressure value detected by the pressure sensor exceeds the threshold value.
After detecting that rubbish is thrown above the cover plate 1, the cover plate 1 is controlled to be opened so that the rubbish to be classified slides into the classification recognition cavity 2.
As a specific implementation manner of the embodiment of the present invention, the intelligent trash can further includes an infrared detector disposed on each trash collecting device, and the infrared detector is configured to detect whether the trash capacity of each trash collecting device reaches a preset value through infrared light.
In the embodiment of the invention, the infrared detector is arranged above each garbage collection device, and whether the capacity of the garbage collection device is full can be accurately judged through the infrared detector, so that the garbage of the garbage collection device can be cleaned in time, and the garbage classification efficiency is improved.
Illustratively, the intelligent garbage can provided by the embodiment of the invention can obtain electric energy required by operation by arranging the solar cell panel, and can ensure normal operation when an external power supply is abnormal.
Please refer to fig. 3, which is another schematic structural diagram of an intelligent trash can according to an embodiment of the present invention.
The embodiment of the invention has the following beneficial effects:
according to the embodiment of the invention, after a large amount of preprocessing data is acquired, the pre-training model is selected for transfer learning to construct the garbage training model, and the garbage to be classified is subjected to feature extraction and matching through the garbage training model, so that various types of garbage in life can be comprehensively identified, and the garbage classification effect can be effectively improved.
The foregoing is a preferred embodiment of the present invention, and it should be noted that it would be apparent to those skilled in the art that various modifications and enhancements can be made without departing from the principles of the invention, and such modifications and enhancements are also considered to be within the scope of the invention.
Claims (10)
1. A method of sorting waste, comprising:
acquiring a basic data set, and preprocessing the basic data set to obtain a preprocessed data set;
selecting a pre-training model for transfer learning, inputting the pre-processing data set and the garbage classification labels into the pre-training model for training, and constructing a garbage training model;
collecting image data of garbage to be classified, and inputting the image data into the garbage training model for feature extraction to obtain garbage features corresponding to the garbage to be classified;
and matching the garbage features with the features in the garbage training model, obtaining the classification labels of the garbage to be classified according to the matching result, and taking the classification labels as the classification result of the garbage to be classified.
2. The method of garbage classification according to claim 1, wherein the obtaining of the basic data set and the preprocessing of the basic data set to obtain a preprocessed data set specifically comprises:
and acquiring a basic data set, and preprocessing the basic data set by adopting a data augmentation method to obtain a preprocessed data set.
3. The method of garbage classification of claim 2 wherein preprocessing the base dataset using a data augmentation method to obtain a preprocessed dataset comprises:
carrying out horizontal overturning, vertical overturning, Gaussian noise and Gaussian fuzzy operation on the basic data set to expand the basic data set; and augmenting the base data set by introducing external data.
4. The garbage classification method according to claim 1, wherein the selecting a pre-training model for transfer learning, inputting the pre-processing data set and the garbage classification label into the pre-training model for training, and constructing the garbage training model specifically comprises:
selecting a convolutional neural network as a pre-training model, adding a CBAM (convolutional code modulation) attention mechanism module to a first convolutional layer of the pre-training model, adding a Dropout layer to a full-link layer of the pre-training model, and adopting a cross entropy loss function as a loss function and an SGD (serving gateway device) as an optimization function;
and inputting the preprocessed data set and the garbage classification labels into the pre-training model for fine-tuning training, and constructing a garbage training model.
5. The method of sorting garbage according to claim 1, further comprising: after the classification result of the garbage to be classified is obtained, the classification result is played through voice, and when no classification instruction manually input by a user is detected within preset time, a valve of a garbage collection device corresponding to the classification result is controlled to be opened.
6. The method of garbage classification of claim 1 wherein the classification tags include recyclable garbage, non-recyclable garbage and other garbage.
7. An intelligent garbage can is characterized by comprising a shell, a cover plate, a classification and identification cavity and a plurality of garbage collection devices, wherein the cover plate is arranged at the top of the shell, the classification and identification cavity for classifying and identifying garbage to be classified is arranged below the cover plate, and the bottom of the classification and identification cavity is provided with an inner door communicated to the plurality of garbage collection devices through a transmission pipeline;
the classification and identification cavity is provided with an image acquisition module and a garbage classification device, the image acquisition module is used for acquiring image data of garbage to be classified in the classification and identification cavity, and the garbage classification device is used for executing the garbage classification method according to any one of claims 1 to 6.
8. The intelligent trash can of claim 7, further comprising a pressure sensor disposed on the lid panel, the pressure sensor configured to detect whether a pressure value exceeding a threshold magnitude exists on the lid panel.
9. The intelligent trash can of claim 8, wherein the trash classification device is further configured to control the lid to open when a pressure value detected by the pressure sensor exceeds a threshold magnitude.
10. The intelligent garbage can of claim 7, further comprising an infrared detector disposed on each garbage collection device, wherein the infrared detector is configured to detect whether the garbage capacity of each garbage collection device reaches a preset value by infrared light.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110459712.XA CN113191420A (en) | 2021-04-27 | 2021-04-27 | Garbage classification method and intelligent garbage can |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110459712.XA CN113191420A (en) | 2021-04-27 | 2021-04-27 | Garbage classification method and intelligent garbage can |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113191420A true CN113191420A (en) | 2021-07-30 |
Family
ID=76979494
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110459712.XA Pending CN113191420A (en) | 2021-04-27 | 2021-04-27 | Garbage classification method and intelligent garbage can |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113191420A (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109455432A (en) * | 2018-11-19 | 2019-03-12 | 珠海格力电器股份有限公司 | A kind of refuse classification method and garbage recovery device |
| CN112488162A (en) * | 2020-11-17 | 2021-03-12 | 中南民族大学 | Garbage classification method based on active learning |
-
2021
- 2021-04-27 CN CN202110459712.XA patent/CN113191420A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109455432A (en) * | 2018-11-19 | 2019-03-12 | 珠海格力电器股份有限公司 | A kind of refuse classification method and garbage recovery device |
| CN112488162A (en) * | 2020-11-17 | 2021-03-12 | 中南民族大学 | Garbage classification method based on active learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Rabano et al. | Common garbage classification using mobilenet | |
| Sreelakshmi et al. | Capsule neural networks and visualization for segregation of plastic and non-plastic wastes | |
| WO2020206862A1 (en) | Automatic sorting system | |
| Yang et al. | WasNet: A neural network-based garbage collection management system | |
| CN110626662A (en) | Image recognition-based garbage self-classification method and device | |
| WO2019000929A1 (en) | Garbage sorting and recycling method, garbage sorting equipment, and garbage sorting and recycling system | |
| CN110294236A (en) | A kind of garbage classification monitoring apparatus, method and server system | |
| CN113158956A (en) | Garbage detection and identification method based on improved yolov5 network | |
| US20220301299A1 (en) | Device and method for automatically identifying and categorizing waste, and directing a desired user action | |
| CN111301886B (en) | Garbage classification and recovery system based on RBF neural network and control method | |
| CN111959995A (en) | Garbage classification voice interaction system based on ROS | |
| WO2021179596A1 (en) | Garbage classification method and smart household appliance | |
| CN111126138A (en) | AI image recognition method for garbage classification | |
| CN113052005B (en) | Garbage sorting method and garbage sorting device for household service | |
| Qiao | Integration model for multimedia education resource based on internet of things | |
| CN110738131A (en) | Garbage classification management method and device based on deep learning neural network | |
| CN113220878A (en) | Knowledge graph-based OCR recognition result classification method | |
| Sirawattananon et al. | Designing of IoT-based smart waste sorting system with image-based deep learning applications | |
| CN110472075A (en) | A kind of isomeric data classification storage method and system based on machine learning | |
| Hin et al. | An Intelligent Smart Bin for Waste Management | |
| Belsare et al. | An integrated approach of IoT and WSN using wavelet transform and machine learning for the solid waste image classification in smart cities | |
| Arunkumar et al. | An internet of things based waste management system using hybrid machine learning technique | |
| CN113191420A (en) | Garbage classification method and intelligent garbage can | |
| Mittal et al. | Trash classification: classifying garbage using deep learning | |
| Elangovan et al. | A deep learning based multiclass segregation of e-waste using hardware software co-simulation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |