CN110626662A - Image recognition-based garbage self-classification method and device - Google Patents
Image recognition-based garbage self-classification method and device Download PDFInfo
- Publication number
- CN110626662A CN110626662A CN201910969660.3A CN201910969660A CN110626662A CN 110626662 A CN110626662 A CN 110626662A CN 201910969660 A CN201910969660 A CN 201910969660A CN 110626662 A CN110626662 A CN 110626662A
- Authority
- CN
- China
- Prior art keywords
- garbage
- image
- image recognition
- recycling device
- picture
- 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
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65F—GATHERING OR REMOVAL OF DOMESTIC OR LIKE REFUSE
- B65F1/00—Refuse receptacles; Accessories therefor
- B65F1/0033—Refuse receptacles; Accessories therefor specially adapted for segregated refuse collecting, e.g. receptacles with several compartments; Combination of receptacles
- B65F1/0053—Combination of several receptacles
- B65F1/006—Rigid receptacles stored in an enclosure or forming part of it
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65F—GATHERING OR REMOVAL OF DOMESTIC OR LIKE REFUSE
- B65F1/00—Refuse receptacles; Accessories therefor
- B65F1/14—Other constructional features; Accessories
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65F—GATHERING OR REMOVAL OF DOMESTIC OR LIKE REFUSE
- B65F1/00—Refuse receptacles; Accessories therefor
- B65F1/0033—Refuse receptacles; Accessories therefor specially adapted for segregated refuse collecting, e.g. receptacles with several compartments; Combination of receptacles
- B65F2001/008—Means for automatically selecting the receptacle in which refuse should be placed
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65F—GATHERING OR REMOVAL OF DOMESTIC OR LIKE REFUSE
- B65F2210/00—Equipment of refuse receptacles
- B65F2210/138—Identification means
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65F—GATHERING OR REMOVAL OF DOMESTIC OR LIKE REFUSE
- B65F2210/00—Equipment of refuse receptacles
- B65F2210/176—Sorting means
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02W—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO WASTEWATER TREATMENT OR WASTE MANAGEMENT
- Y02W30/00—Technologies for solid waste management
- Y02W30/10—Waste collection, transportation, transfer or storage, e.g. segregated refuse collecting, electric or hybrid propulsion
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a garbage self-classification system and a recovery device based on image recognition, which comprises: the image acquisition device can acquire a garbage image and display the acquired image on a display screen; the image recognition module is realized by a deep learning technology, a convolutional neural network is used for processing and calculating the picture, and the feature extraction of the picture can be enhanced by combining an attention mechanism in computer vision in the process of feature extraction; after the image recognition system returns the recognition result, the garbage recycling device responds to open the garbage cans of the corresponding categories, and a user puts the garbage into the corresponding garbage cans. The garbage recycling device can be thrown to the roadside of a street for use, and can integrate the system to a garbage recycling device with a small volume, so that the garbage recycling device is used at home, and the garbage recycling device is simple in structure, low in cost and wide in applicability.
Description
Technical Field
The invention relates to the field of garbage recovery, in particular to a garbage self-classification method and equipment based on image recognition.
Background
The garbage classification means that the garbage is classified into different categories according to the properties of the garbage, particularly the household garbage generated in daily life, and the categories are numerous. The classified garbage throwing can protect ecological environment well, bring convenience to garbage recovery and improve the resource value and economic value of garbage. In 2019, in 6 months, nine departments such as the department of living and construction, the department of reform committee, the department of ecological environment, and the like jointly issue a notice of departments such as the department of housing, the department of urban and rural construction, and the like, about the comprehensive development of the classification work of the domestic garbage in cities on the national level and above. From 2019, the domestic garbage classification work is started comprehensively in cities on the national level and above. In 2019, the 'Shanghai municipal domestic waste management regulation' in 7 months has been officially implemented, the garbage classification is first implemented in Shanghai, and some news reports that some citizens receive a ticket because the garbage classification is incorrect. It is expected that garbage classification is an irreversible trend in social development.
The garbage classification comes into daily life, so knowledge about the garbage classification is necessary to learn. However, there are hundreds of types of garbage in daily life, it is difficult to remember which type each type of garbage belongs to, and there is not much effort for office workers to classify the garbage. With the development of deep learning and successful application in computer vision, image recognition techniques can be combined with the problem of garbage classification.
The invention provides a garbage classification system based on image recognition, and the garbage classification system is applied to garbage classification garbage cans. Some intelligent trash cans exist, such as trash cans based on speech recognition and intelligent trash cans based on image recognition, but are rarely combined with garbage classification. According to the image recognition-based garbage classification system provided by the invention, garbage can classification can be returned and a throwing opening corresponding to the classification can be opened by only placing the garbage in front of an image acquisition device of a garbage can by a garbage throwing person and recognizing the acquired image by the image recognition and recognition system.
The technology related by the invention is mainly the application of deep learning in the aspect of image recognition, and the model is trained through a labeled garbage classification picture data set to finally obtain a garbage classification application model. And finally, applying the model to the garbage cans, and controlling the opening and closing of the garbage cans of different categories through the identification device.
Disclosure of Invention
The utility model provides a rubbish is from categorised system and recovery plant based on image recognition, includes: the image acquisition device can acquire a garbage image and display the acquired image on a display screen; the image recognition module is realized by a deep learning technology, a convolutional neural network is used for processing and calculating the picture, and the feature extraction of the picture can be enhanced by combining an attention mechanism in computer vision in the process of feature extraction; after the image recognition system returns the recognition result, the garbage recycling device responds to open the garbage cans of the corresponding categories, and a user puts the garbage into the corresponding garbage cans.
The image pickup device is provided with a button in front of the garbage can, the button is pressed, the image acquisition device is started, garbage is placed in the front of the camera to wait for the image acquisition device to acquire images, and after the acquisition is finished, a voice prompt 'the image acquisition is finished' is provided, and the acquired images are displayed on the display screen.
The image recognition system in the image recognition module is realized by a deep learning technology. The picture is processed and calculated using a convolutional neural network. The model is trained primarily by training on a labeled garbage picture supervised dataset. The input of the model is a three-channel image acquired by an image acquisition device; through a simple data processing process, an input image is converted into a three-dimensional matrix and further used as the input of a model. In the image feature extraction part, the image is processed through the two convolution layers and the two pooling layers, and deep features of the image are continuously extracted. And (3) continuously reducing the size of the image and deepening the number of channels of the image through convolution and pooling operations, and finally stretching the three-dimensional matrix into a one-dimensional vector capable of representing the main characteristics of the image. In the process of feature extraction, attention mechanism in computer vision can be combined to enhance feature extraction of the picture.
The one-dimensional feature vector of the picture (the embedded representation of the picture) serves as the input for the next fully connected layer of the model. One-dimensional vectors are mapped to four-dimensional vectors (i.e., length-4 vectors) through two fully-connected layers. And finally, normalizing the four-dimensional vector through a softmax layer, converting the four-dimensional vector into category probability for output, and returning the category corresponding to the maximum probability as the result of image recognition. The model is trained by adopting cross entropy as an objective function and an Adam optimizer. The fully connected layer can use dropout techniques to prevent the model from overfitting.
After the image recognition system returns the recognition result, the garbage recycling device responds to open the garbage cans of the corresponding categories, and a user puts the garbage into the corresponding garbage cans.
The invention has the beneficial effects that: garbage is from categorised garbage bin based on image recognition is used for helping people to carry out waste classification, realizes that the classification of rubbish is put in and is retrieved, has not only improved the rate of recovery of rubbish greatly, has still reduced people waste classification's wrong fraction rate.
The invention has wide applicability, can be used by being thrown to the roadside of a street, and can integrate the system to a garbage recovery device with smaller volume to realize household use.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below.
FIG. 1: the image recognition convolution neural network model diagram of the invention.
FIG. 2: the invention relates to an image recognition and voice prompt device.
FIG. 3: the invention discloses an overall view of a garbage recycling device.
FIG. 4: the system of the invention is a flow chart.
The reference numerals in the figures have the following meanings: 1-1 camera; 1-2 camera switch; 1-3 voice prompt device, 1-4 display screen; 2-1, a box body; 2-2 of a garbage can; 2-3, a throwing port; 2-4 storage batteries; 2-5 solar panels; 2-6 image recognition and voice integration device; 2-7 box doors.
Detailed Description
The invention relates to a garbage can, in particular to a garbage classification and recovery device based on deep learning image recognition. The invention mainly comprises three parts: image acquisition device, image recognition system and rubbish recovery plant.
The image pickup device is provided with a button in front of the garbage can, the button is pressed, the image acquisition device is started, garbage is placed in the front of the camera to wait for the image acquisition device to acquire images, and after the acquisition is finished, a voice prompt 'the image acquisition is finished' is provided, and the acquired images are displayed on the display screen.
The image recognition system in the image recognition module is realized by a deep learning technology. As shown in fig. 1, the picture is processed and computed using a convolutional neural network. The model is trained primarily by training on a labeled garbage picture supervised dataset. The input of the model is a three-channel image acquired by an image acquisition device; through a simple data processing process, an input image is converted into a three-dimensional matrix and further used as the input of a model. In the image feature extraction part, the image is processed through the two convolution layers and the two pooling layers, and deep features of the image are continuously extracted. And (3) continuously reducing the size of the image and deepening the number of channels of the image through convolution and pooling operations, and finally stretching the three-dimensional matrix into a one-dimensional vector capable of representing the main characteristics of the image. In the process of feature extraction, attention mechanism in computer vision can be combined to enhance feature extraction of the picture.
The one-dimensional feature vector of the picture (the embedded representation of the picture) serves as the input for the next fully connected layer of the model. One-dimensional vectors are mapped to four-dimensional vectors (i.e., length-4 vectors) through two fully-connected layers. And finally, normalizing the four-dimensional vector through a softmax layer, converting the four-dimensional vector into category probability for output, and returning the category corresponding to the maximum probability as the result of image recognition. The model is trained by adopting cross entropy as an objective function and an Adam optimizer. The fully connected layer can use dropout techniques to prevent the model from overfitting.
After the image recognition system returns the recognition result, the garbage recycling device responds to open the garbage cans of the corresponding categories, and a user puts the garbage into the corresponding garbage cans.
As shown in fig. 2, the image pickup apparatus mainly includes: 1-1 camera; 1-2 camera switch; 1-3 voice prompt device, 1-4 display screen. The user presses the switch of making a video recording, and speech device suggestion "please place the discarded object in the place ahead of the camera", then the camera carries out image pickup, and after finishing gathering, speech device suggestion "image acquisition finishes".
As shown in fig. 3, the garbage recycling bin mainly includes: 2-1, a box body; 2-2 of a garbage can; 2-3, a throwing port; 2-4 storage batteries; 2-5 solar panels; 2-6 image recognition and voice integration device; 2-7 box doors. The 2-1 box body is an appearance part of the intelligent garbage can, and four 2-2 garbage cans are arranged inside the intelligent garbage can and respectively correspond to four types of kitchen garbage, recoverable garbage, harmful garbage and other garbage. The manager can take out the 2-2 garbage bin to clean the garbage or replace the garbage bin by opening the 2-1 box body. The 2-3 throwing openings are positioned at the front part of the 2-1 box body and correspond to the garbage accommodating devices of each category. The 2-4 storage battery is used for supplying power to the 2-6 picture recognition and voice integration device, and the storage battery is connected with the 2-5 solar panel and can charge the storage battery through the solar panel. The 2-2 garbage bin can be replaced and cleaned by opening the 2-7 bin body door.
The foregoing is a more detailed description of the present invention in connection with specific preferred embodiments thereof, and it is not intended that the specific embodiments of the present invention be limited to these descriptions. For those skilled in the art to which the invention pertains, other embodiments that do not depart from the gist of the invention are intended to be within the scope of the invention.
Claims (4)
1. The utility model provides a rubbish is from categorised system and recovery plant based on image recognition which characterized in that: the image recognition garbage self-classification system and the garbage recycling equipment comprise an image acquisition device, an image recognition system and garbage recycling equipment.
2. The garbage self-classification system and recycling device based on image recognition as claimed in claim 1, wherein: the image pickup device is provided with a button in front of the garbage can, the button is pressed, the image acquisition device is started, garbage is placed in the front of the camera to wait for the image acquisition device to acquire images, and after the acquisition is finished, a voice prompt 'the image acquisition is finished' is provided, and the acquired images are displayed on the display screen.
3. The garbage self-classification system and recycling device based on image recognition as claimed in claim 2, wherein: the image recognition system is realized through a deep learning technology, and a convolutional neural network is used for processing and calculating the picture.
4. The garbage self-classification system and recycling device based on image recognition as claimed in claim 3, wherein: after the image recognition system returns the recognition result, the garbage recycling device responds to open the garbage cans of the corresponding categories, and a user puts the garbage into the corresponding garbage cans.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910969660.3A CN110626662A (en) | 2019-10-12 | 2019-10-12 | Image recognition-based garbage self-classification method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910969660.3A CN110626662A (en) | 2019-10-12 | 2019-10-12 | Image recognition-based garbage self-classification method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110626662A true CN110626662A (en) | 2019-12-31 |
Family
ID=68976453
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910969660.3A Pending CN110626662A (en) | 2019-10-12 | 2019-10-12 | Image recognition-based garbage self-classification method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110626662A (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111056191A (en) * | 2020-01-14 | 2020-04-24 | 中国药科大学 | Intelligent garbage collection system capable of classifying and delivering multiple garbage |
CN111444977A (en) * | 2020-04-03 | 2020-07-24 | 成都禧来科技有限公司 | Method for realizing automatic garbage classification |
CN111559586A (en) * | 2020-04-29 | 2020-08-21 | 南京信息职业技术学院 | Household intelligent garbage classification and identification system and method |
CN111661531A (en) * | 2020-06-05 | 2020-09-15 | 广东慧福信息科技有限公司 | Medical waste recovery system and data storage method thereof |
CN112149573A (en) * | 2020-09-24 | 2020-12-29 | 湖南大学 | Garbage classification and picking robot based on deep learning |
CN112241679A (en) * | 2020-09-14 | 2021-01-19 | 浙江理工大学 | Automatic garbage classification method |
CN112407655A (en) * | 2020-11-26 | 2021-02-26 | 重庆广播电视大学重庆工商职业学院 | Garbage classification and recovery system based on Internet of things |
CN112884033A (en) * | 2021-02-06 | 2021-06-01 | 浙江净禾智慧科技有限公司 | Household garbage classification detection method based on convolutional neural network |
CN115432331A (en) * | 2022-10-10 | 2022-12-06 | 浙江绿达智能科技有限公司 | Intelligent classification dustbin |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN206032298U (en) * | 2016-08-31 | 2017-03-22 | 上海阳淳电子股份有限公司 | Rubbish intelligent classification display terminal |
CN106742964A (en) * | 2017-03-16 | 2017-05-31 | 黄驿钦 | Rubbish magazine |
CN107054937A (en) * | 2017-03-23 | 2017-08-18 | 广东数相智能科技有限公司 | A kind of refuse classification suggestion device and system based on image recognition |
CN107054936A (en) * | 2017-03-23 | 2017-08-18 | 广东数相智能科技有限公司 | A kind of refuse classification prompting dustbin and system based on image recognition |
CN107600791A (en) * | 2017-08-31 | 2018-01-19 | 芜湖职业技术学院 | Interactive automatic garbage classification collection box |
CN108182455A (en) * | 2018-01-18 | 2018-06-19 | 齐鲁工业大学 | A kind of method, apparatus and intelligent garbage bin of the classification of rubbish image intelligent |
CN108341184A (en) * | 2018-03-01 | 2018-07-31 | 安徽省星灵信息科技有限公司 | A kind of intelligent sorting dustbin |
-
2019
- 2019-10-12 CN CN201910969660.3A patent/CN110626662A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN206032298U (en) * | 2016-08-31 | 2017-03-22 | 上海阳淳电子股份有限公司 | Rubbish intelligent classification display terminal |
CN106742964A (en) * | 2017-03-16 | 2017-05-31 | 黄驿钦 | Rubbish magazine |
CN107054937A (en) * | 2017-03-23 | 2017-08-18 | 广东数相智能科技有限公司 | A kind of refuse classification suggestion device and system based on image recognition |
CN107054936A (en) * | 2017-03-23 | 2017-08-18 | 广东数相智能科技有限公司 | A kind of refuse classification prompting dustbin and system based on image recognition |
CN107600791A (en) * | 2017-08-31 | 2018-01-19 | 芜湖职业技术学院 | Interactive automatic garbage classification collection box |
CN108182455A (en) * | 2018-01-18 | 2018-06-19 | 齐鲁工业大学 | A kind of method, apparatus and intelligent garbage bin of the classification of rubbish image intelligent |
CN108341184A (en) * | 2018-03-01 | 2018-07-31 | 安徽省星灵信息科技有限公司 | A kind of intelligent sorting dustbin |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111056191A (en) * | 2020-01-14 | 2020-04-24 | 中国药科大学 | Intelligent garbage collection system capable of classifying and delivering multiple garbage |
CN111444977A (en) * | 2020-04-03 | 2020-07-24 | 成都禧来科技有限公司 | Method for realizing automatic garbage classification |
CN111559586A (en) * | 2020-04-29 | 2020-08-21 | 南京信息职业技术学院 | Household intelligent garbage classification and identification system and method |
CN111661531A (en) * | 2020-06-05 | 2020-09-15 | 广东慧福信息科技有限公司 | Medical waste recovery system and data storage method thereof |
CN112241679A (en) * | 2020-09-14 | 2021-01-19 | 浙江理工大学 | Automatic garbage classification method |
CN112241679B (en) * | 2020-09-14 | 2024-02-20 | 浙江理工大学 | Automatic garbage classification method |
CN112149573A (en) * | 2020-09-24 | 2020-12-29 | 湖南大学 | Garbage classification and picking robot based on deep learning |
CN112407655A (en) * | 2020-11-26 | 2021-02-26 | 重庆广播电视大学重庆工商职业学院 | Garbage classification and recovery system based on Internet of things |
CN112884033A (en) * | 2021-02-06 | 2021-06-01 | 浙江净禾智慧科技有限公司 | Household garbage classification detection method based on convolutional neural network |
CN112884033B (en) * | 2021-02-06 | 2021-10-22 | 浙江净禾智慧科技有限公司 | Household garbage classification detection method based on convolutional neural network |
CN115432331A (en) * | 2022-10-10 | 2022-12-06 | 浙江绿达智能科技有限公司 | Intelligent classification dustbin |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110626662A (en) | Image recognition-based garbage self-classification method and device | |
CN110428019B (en) | Intelligent garbage classification method and modularized intelligent garbage classification processing system | |
CN110155572B (en) | Intelligent community garbage classification system and method | |
CN109359697A (en) | Graph image recognition methods and inspection system used in a kind of power equipment inspection | |
CN111301886B (en) | Garbage classification and recovery system based on RBF neural network and control method | |
CN111860193B (en) | Text-based pedestrian retrieval self-supervision visual representation learning system and method | |
CN111186656A (en) | Target garbage classification method and intelligent garbage can | |
CN111814750A (en) | Intelligent garbage classification method and system based on deep learning target detection and image recognition | |
CN111453249A (en) | Intelligent kitchen garbage classification barrel based on image analysis | |
Alsabei et al. | Waste classification by fine-tuning pre-trained CNN and GAN | |
CN111126155A (en) | Pedestrian re-identification method for generating confrontation network based on semantic constraint | |
CN111797787B (en) | Waste image detection and classification system based on Internet of things technology | |
CN117088015A (en) | Intelligent garbage disposal method, system and storage medium | |
CN212048939U (en) | Intelligent garbage recycling device for community | |
CN209922092U (en) | Material recycling bin capable of automatically identifying human face and garbage types | |
Hin et al. | An Intelligent Smart Bin for Waste Management | |
CN110921142A (en) | Community garbage recycling and classifying management system | |
CN110775483A (en) | Community intelligent garbage recycling device and method, electronic equipment and storage medium | |
CN213474299U (en) | Electronic scale weighing system | |
CN210804050U (en) | Garbage classification barrel with centralized remote supervision | |
CN114492658A (en) | Real-time household garbage detection method and device, electronic equipment and medium | |
CN112668678A (en) | Intelligent garbage classification recycling system platform | |
CN114332715A (en) | Method, device and equipment for identifying snow through automatic meteorological observation and storage medium | |
CN112478488A (en) | Automatic garbage sorting and collecting system and method | |
CN112849837A (en) | Intelligent garbage classification box based on voice recognition and cloud service platform |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20191231 |
|
WD01 | Invention patent application deemed withdrawn after publication |