CN113173349A - Garbage classification system and method - Google Patents
Garbage classification system and method Download PDFInfo
- Publication number
- CN113173349A CN113173349A CN202110490307.4A CN202110490307A CN113173349A CN 113173349 A CN113173349 A CN 113173349A CN 202110490307 A CN202110490307 A CN 202110490307A CN 113173349 A CN113173349 A CN 113173349A
- Authority
- CN
- China
- Prior art keywords
- garbage
- image
- neural network
- network 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.)
- Withdrawn
Links
Images
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
-
- 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
- B65F1/10—Refuse receptacles; Accessories therefor with refuse filling means, e.g. air-locks
-
- 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 classification system, comprising: the image acquisition device is used for shooting garbage to be classified to obtain an acquired image; the processing device is connected with the image acquisition device and is used for identifying the acquired image according to a neural network model to obtain the type information of the garbage to be classified; and the driving device is connected with the processing device and drives a mechanical arm to put the garbage to be classified into the corresponding garbage can according to the type information. The garbage classification method comprises the following steps: s1; the image acquisition device shoots images of the garbage; s2: the processing device judges the type of the garbage according to the neural network model; s3: the processing device controls the driving device according to the type information; s4: the mechanical arm puts the garbage to be classified into the corresponding garbage can. The invention has the beneficial effects that: the automatic sorting of the garbage is realized through the image recognition method, and the garbage is thrown in through the mechanical device, so that the defects that the conventional manual sorting of the garbage is easy to make mistakes and high in cost are overcome, and the efficiency and the accuracy of garbage sorting are improved.
Description
Technical Field
The invention relates to the technical field of automation control, in particular to a garbage classification system and a garbage classification method.
Background
In recent years, with the development of economy and the improvement of living standard, the harmless treatment mode of domestic garbage gradually enters the visual field of people, and related measures for garbage classification treatment are also carried out in China.
In the prior art, the garbage classification treatment mainly depends on administrative laws and regulations, and public is required to classify and release garbage at different times from the source; or a specially-assigned person is arranged in the garbage disposal center to sort the garbage. Both of these approaches are inefficient, inconvenient and easily incur a conflicting mind.
Disclosure of Invention
In view of the above problems in the prior art, a garbage classification system and method are provided.
The specific technical scheme is as follows:
a waste classification system comprising: the image acquisition device is used for shooting garbage to be classified to obtain an acquired image; the processing device is connected with the image acquisition device and is used for identifying the acquired image according to a neural network model to obtain the type information of the garbage to be classified; and the driving device is connected with the processing device and drives a mechanical arm to put the garbage to be classified into the corresponding garbage can according to the type information.
Preferably, the mechanical arm is a six-degree-of-freedom claw type mechanical arm or a three-degree-of-freedom sucker type mechanical arm, and the mechanical arm is driven by the driving device to transfer a predetermined angle from an initial position to a predetermined direction.
Preferably, the training set used for training the neural network model is a garbage image; the garbage image specifically comprises images of six types of garbage, namely metal, glass, paper, hardboard, plastic and general garbage; the number of samples of the garbage image is 2000-2500.
Preferably, the processing device inputs the neural network model after preprocessing the garbage image; and the neural network model performs 100 iterations on the garbage image, wherein the step length is 70, and the trained neural network model is obtained.
Preferably, the pre-treatment process comprises: carrying out normalization processing on the garbage image; turning the garbage image in a random horizontal direction and a random vertical direction;
and adjusting the garbage image into an image with the resolution of 150 x 150.
Preferably, the neural network model has 13 convolutional layers, 3 fully-linked layers.
Preferably, the processing means further classifies the garbage into recyclable garbage and dry garbage according to a result output by the neural network model.
Preferably, the trash can comprises a recyclable trash can and a dry trash can; the recyclable garbage bin and the dry garbage bin are arranged in front of the mechanical arm in parallel along the initial direction of the mechanical arm; or the recyclable garbage bin and the dry garbage bin are arranged in front of the mechanical arm and perpendicular to the initial direction of the mechanical arm; or the recyclable garbage can and the dry garbage can are respectively arranged on two sides of the mechanical arm.
A garbage classification method specifically comprises the following steps:
s1; the image acquisition device shoots an image of the garbage to be classified;
s2: the processing device judges the type of the garbage to be classified according to the neural network model;
s3: the processing device controls the driving device according to the type;
s4: the driving device controls the mechanical arm to throw the garbage to be classified into the recyclable garbage can or the dry garbage can.
The technical scheme has the following advantages or beneficial effects: the automatic sorting of the garbage is realized through the image recognition method, and the garbage is thrown in through the mechanical device, so that the defects that the conventional manual sorting of the garbage is easy to make mistakes and high in cost are overcome, and the efficiency and the accuracy of garbage sorting are improved.
Drawings
Embodiments of the present invention will now be described more fully hereinafter with reference to the accompanying drawings. The drawings are, however, to be regarded as illustrative and explanatory only and are not restrictive of the scope of the invention.
FIG. 1 is a block diagram of a system according to an embodiment of the present invention;
FIG. 2 is a schematic view of a robotic arm according to an embodiment of the present invention;
FIG. 3 is a schematic view of a trash can according to an embodiment of the present invention;
FIG. 4 is a schematic view of another embodiment of a trash can;
FIG. 5 is a schematic view of another trash can arrangement according to an embodiment of the present invention;
fig. 6 is a flowchart of a garbage classification method according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, 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 invention.
It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict.
The invention is further described with reference to the following drawings and specific examples, which are not intended to be limiting.
The present invention includes a waste classification system comprising: the image acquisition device 3 is used for shooting garbage to be classified to obtain an acquired image; the processing device 4 is connected with the image acquisition device 3 and is used for identifying the acquired image according to a neural network model to obtain the type information of the garbage to be classified; and the driving device 2 is connected with the processing device 4 and drives a mechanical arm 1 to put the garbage to be classified into the corresponding garbage can according to the type information.
In a preferred embodiment, the robot arm 1 is a six-degree-of-freedom claw robot or a three-degree-of-freedom chuck robot, and the robot arm 1 is driven by the driving device 2 to transfer a predetermined angle from an initial position to a predetermined direction.
Particularly, the claw type mechanical arm and the sucker type mechanical arm can effectively treat garbage with different volumes, types and qualities, and the availability of the whole system is improved.
In a preferred embodiment, the image capturing device 3 is arranged at the front end of the robot arm 1.
In a preferred embodiment, the training set used to train the neural network model is a garbage sample image; the garbage sample image specifically comprises images of six types of garbage, namely metal, glass, paper, hardboard, plastic and general garbage; the number of samples of the garbage training image is 2000-2500.
In a preferred embodiment the number of samples of the garbage sample image is 2259.
In a preferred embodiment, the processing device inputs the neural network model after preprocessing the garbage sample image; and (4) carrying out 100 iterations on the garbage image by the neural network model, wherein the step length is 70, and obtaining the trained neural network model.
By setting 100 iterations, the training of the neural network model on the garbage sample graph can be effectively guaranteed, and the accuracy of the neural network is improved.
In a preferred embodiment, the pre-treatment process comprises: carrying out normalization processing on the garbage sample image; overturning the garbage sample image in a random horizontal direction and a random vertical direction; the garbage sample image is adjusted to an image of resolution 150 x 150.
Specifically, the image size can be effectively reduced on the basis of keeping image details by carrying out normalization processing on the garbage sample image, and convergence of a neural network model is facilitated; by randomly overturning the garbage sample images, the interference of the similar characteristics of part of the garbage sample images caused by the same image acquisition equipment at the same visual angle on the neural network model can be eliminated.
In a preferred embodiment, the neural network model has 13 convolutional layers, 3 fully-linked layers.
In a preferred embodiment, the VGG16 model can be used for identifying the images of the garbage to be classified, and the SGD algorithm is used for optimizing the training process of the neural network model, so that a better training effect and shorter training time are obtained, and the training efficiency of the neural network model is improved.
Furthermore, 248 test sample images are adopted to test the neural network model after the neural network model is trained, and the test result shows that the accuracy of the neural network model is up to 91%.
In a preferred embodiment, the processing means 4 further separates the garbage into recoverable garbage and dry garbage according to the results output by the neural network model.
In a preferred embodiment, as shown in fig. 3-5, the trash can includes a recyclable trash can 5 and a dry trash can 6; the recyclable garbage can 5 and the dry garbage can 6 are arranged in front of the mechanical arm 1 in parallel along the initial direction of the mechanical arm 1; or the recyclable garbage can 5 and the dry garbage can 6 are arranged in front of the mechanical arm 1 and are vertical to the initial direction of the mechanical arm 1; or the recyclable garbage can 5 and the dry garbage can 6 are respectively arranged at two sides of the mechanical arm 1.
Further, according to the different placement modes of the garbage cans, the driving device 2 can be controlled by the processing device 4 to drive the mechanical arm 1 to throw the garbage to be classified into the corresponding garbage cans in different directions and angles.
Specifically, each steering gear rotation angle of the mechanical arm 1 corresponding to different garbage cans is stored in the processing device 4, the type of garbage to be classified is judged through the neural network model, the processing device 4 selects to throw the garbage to be classified into the recyclable garbage can 5 or the dry garbage can 6 and sends an instruction to the driving device 2, the driving device 2 controls each steering gear of the mechanical arm 1 to rotate to an angle corresponding to the instruction sent by the processing device 4 according to the instruction sent by the processing device 4, and the garbage to be classified is thrown into the recyclable garbage can 5 or the dry garbage can 6.
Furthermore, the steering engine rotation angles stored in the processing device 4 are of three types, and respectively correspond to an initial angle, an angle corresponding to the recyclable garbage can 5 and an angle corresponding to the dry garbage can 6.
In a preferred embodiment, the steering engine rotation angle stored in the processing device 4 is a mixly file, so that subsequent maintenance personnel can quickly adjust the corresponding steering engine angle according to actual conditions.
A garbage classification method, as shown in fig. 5, specifically includes:
s1; the image acquisition device shoots images of the garbage to be classified;
s2: the processing device judges the type of the garbage to be classified according to the neural network model;
s3: the processing device controls the driving device according to the type;
s4: the driving device controls the mechanical arm to throw the garbage to be classified into the recyclable garbage can or the dry garbage can.
While the invention has been described with reference to a preferred embodiment, it will be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the spirit and scope of the invention.
Claims (9)
1. A waste sorting system, comprising:
the image acquisition device is used for shooting garbage to be classified to obtain an acquired image;
the processing device is connected with the image acquisition device and is used for identifying the acquired image according to a neural network model to obtain the type information of the garbage to be classified;
and the driving device is connected with the processing device and drives a mechanical arm to put the garbage to be classified into the corresponding garbage can according to the type information.
2. The waste sorting system of claim 2, wherein the robotic arm is a six-degree-of-freedom claw-type robotic arm or a three-degree-of-freedom suction cup-type robotic arm, and the robotic arm is driven by the driving device to transfer a predetermined angle from an initial position to a predetermined direction.
3. The garbage classification system of claim 2, wherein the training set used to train the neural network model is a garbage sample image;
the garbage sample image specifically comprises images of six types of garbage, namely metal, glass, paper, hardboard, plastic and general garbage;
the number of the garbage sample images is 2000-2500.
4. The garbage classification system according to claim 3, wherein the processing device inputs the neural network model after preprocessing the garbage sample image;
and the neural network model performs 100 iterations on the garbage sample image, wherein the step length is 70, and the trained neural network model is obtained.
5. The waste classification system according to claim 4, characterized in that the pre-processing procedure comprises:
carrying out normalization processing on the garbage image;
turning the garbage image in a random horizontal direction and a random vertical direction;
and adjusting the garbage image into an image with the resolution of 150 x 150.
6. The garbage classification system of claim 4, wherein the neural network model has 13 convolutional layers, 3 fully-linked layers.
7. The garbage classification system of claim 3, wherein the processing means further classifies the garbage into recyclable garbage and dry garbage according to the result output by the neural network model.
8. The waste classification system as claimed in claim 5, wherein the waste bin comprises a recyclable waste bin and a dry waste bin;
the recyclable garbage bin and the dry garbage bin are arranged in front of the mechanical arm in parallel along the initial direction of the mechanical arm;
or the recyclable garbage bin and the dry garbage bin are arranged in front of the mechanical arm and perpendicular to the initial direction of the mechanical arm;
or the recyclable garbage can and the dry garbage can are respectively arranged on two sides of the mechanical arm.
9. A garbage classification method, which is applied to the garbage classification system according to any one of claims 1 to 8, specifically comprising:
s1; the image acquisition device shoots an image of the garbage to be classified;
s2: the processing device judges the type of the garbage to be classified according to the neural network model;
s3: the processing device controls the driving device according to the type;
s4: the driving device controls the mechanical arm to throw the garbage to be classified into the recyclable garbage can or the dry garbage can.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110490307.4A CN113173349A (en) | 2021-05-06 | 2021-05-06 | Garbage classification system and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110490307.4A CN113173349A (en) | 2021-05-06 | 2021-05-06 | Garbage classification system and method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113173349A true CN113173349A (en) | 2021-07-27 |
Family
ID=76928343
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110490307.4A Withdrawn CN113173349A (en) | 2021-05-06 | 2021-05-06 | Garbage classification system and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113173349A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113682675A (en) * | 2021-07-31 | 2021-11-23 | 北京五指术健康科技有限公司 | Automatic garbage sorting system and method based on driving device |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
KR102027951B1 (en) * | 2019-06-07 | 2019-10-04 | 권일수 | Method and apparatus for controlling integrated circuit manufacturing process |
CN110589282A (en) * | 2019-08-16 | 2019-12-20 | 喻鑫童 | Intelligent garbage classification method based on machine learning and automatic garbage sorting device |
CN110861853A (en) * | 2019-11-29 | 2020-03-06 | 三峡大学 | Intelligent garbage classification method combining vision and touch |
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 |
CN112591333A (en) * | 2020-12-11 | 2021-04-02 | 江西理工大学 | Automatic garbage classification device and method based on artificial intelligence |
CN112733936A (en) * | 2021-01-08 | 2021-04-30 | 北京工业大学 | Recyclable garbage classification method based on image recognition |
-
2021
- 2021-05-06 CN CN202110490307.4A patent/CN113173349A/en not_active Withdrawn
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
KR102027951B1 (en) * | 2019-06-07 | 2019-10-04 | 권일수 | Method and apparatus for controlling integrated circuit manufacturing process |
CN110589282A (en) * | 2019-08-16 | 2019-12-20 | 喻鑫童 | Intelligent garbage classification method based on machine learning and automatic garbage sorting device |
CN110861853A (en) * | 2019-11-29 | 2020-03-06 | 三峡大学 | Intelligent garbage classification method combining vision and touch |
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 |
CN112591333A (en) * | 2020-12-11 | 2021-04-02 | 江西理工大学 | Automatic garbage classification device and method based on artificial intelligence |
CN112733936A (en) * | 2021-01-08 | 2021-04-30 | 北京工业大学 | Recyclable garbage classification method based on image recognition |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113682675A (en) * | 2021-07-31 | 2021-11-23 | 北京五指术健康科技有限公司 | Automatic garbage sorting system and method based on driving device |
CN113682675B (en) * | 2021-07-31 | 2022-08-02 | 北京五指术健康科技有限公司 | Automatic garbage sorting system and method based on driving device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110314854B (en) | Workpiece detecting and sorting device and method based on visual robot | |
CN100590428C (en) | Automatic decting method and device for wheel hub casting fault based on image understanding | |
CN102539443B (en) | Bottle body defect automatic detection method based on machine vision | |
CN107138431B (en) | A kind of components identification method for separating and system based on machine vision | |
JPH01196501A (en) | Object recognizing apparatus for robot | |
CN111862028B (en) | Wood defect detecting and sorting device and method based on depth camera and depth learning | |
CN1485616A (en) | Fowl eggs quality non-destruction automatic detection grading apparatus and process | |
CN107084992A (en) | A kind of capsule detection method and system based on machine vision | |
CN108672316A (en) | A kind of micro parts quality detecting system based on convolutional neural networks | |
CN104483320A (en) | Digitized defect detection device and detection method of industrial denitration catalyst | |
CN110466911A (en) | Automatic sorting garbage bin and classification method | |
CN106269564B (en) | Ore sorting process and equipment based on image recognition technology and mechanical arm | |
US11203494B2 (en) | System and method for sorting moving objects | |
CN113173349A (en) | Garbage classification system and method | |
CN112364944A (en) | Deep learning-based household garbage classification method | |
CN114029943A (en) | Target grabbing and positioning method and system based on image data processing | |
CN113859803A (en) | Intelligent identification trash can and intelligent identification method thereof | |
CN112975970A (en) | Vision grabbing mechanical arm system | |
CN108176603A (en) | The more code name recognition methods of engine link and its automatic sorting apparatus | |
CN1141665C (en) | Micro image characteristic extracting and recognizing method | |
CN202471610U (en) | Automatic bottle body defect detecting device based on machine vision | |
CN215708916U (en) | Intelligent recognition garbage can | |
CN112270378A (en) | Computer vision-based artificial intelligent sorting method for waste glass | |
CN111453244A (en) | Full-automatic classification garbage can based on cloud identification and classification method thereof | |
CN114677597B (en) | Gear defect visual inspection method and system based on improved YOLOv5 network |
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 | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210727 |
|
WW01 | Invention patent application withdrawn after publication |