CN112660655A - Intelligent classification garbage bin based on degree of depth study - Google Patents
Intelligent classification garbage bin based on degree of depth study Download PDFInfo
- Publication number
- CN112660655A CN112660655A CN202011439780.1A CN202011439780A CN112660655A CN 112660655 A CN112660655 A CN 112660655A CN 202011439780 A CN202011439780 A CN 202011439780A CN 112660655 A CN112660655 A CN 112660655A
- Authority
- CN
- China
- Prior art keywords
- activation
- garbage
- module
- convolution
- classification
- 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.)
- Granted
Links
Images
Classifications
-
- 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
- Processing Of Solid Wastes (AREA)
Abstract
The invention discloses an intelligent classification garbage can based on deep learning, which comprises a base, wherein a shell is arranged on the base, a cover is arranged at the top of the shell, a putting-in opening is formed in the upper end of the shell, a first baffle surrounding the putting-in opening is arranged in the shell, a camera is arranged on one side, facing the putting-in opening, of the first baffle, a first steering engine is arranged on one side, facing away from the putting-in opening, of the first baffle, a rotatable partition plate is arranged at the lower end of the first baffle, and the first steering engine is connected with the partition plate through a first gear set and used for controlling the partition plate to rotate. The invention can automatically classify and identify the objects put into the garbage can, and select the corresponding garbage inner can to store the objects according to the classification result, thereby realizing the automatic classification of the garbage.
Description
Technical Field
The invention relates to the field of garbage cans, in particular to an intelligent classification garbage can based on deep learning.
Background
Everyone throws away a lot of rubbish every day, and in some areas that refuse management is better, most rubbish can get innoxious processing such as sanitary landfill, burning, compost, and the rubbish in more places is often simply piled up or buried, leads to the spread of foul smell, and pollutes soil and groundwater.
The cost of harmless treatment of garbage is very high, and the cost of treating one ton of garbage is about one hundred yuan to several hundred yuan according to different treatment modes. People consume a large amount of resources, produce the garbage in a large scale, consume the garbage in a large amount, and produce the garbage in a large amount. The consequences will be unthinkable.
The purpose of garbage classification is to recycle the recovered products, including material utilization and energy utilization, by utilizing the existing production capacity for the purpose of shunting and processing the wastes, and to landfill and dispose of the waste which is temporarily unusable. But current waste classification relies on the manual work to classify before abandoning, and current garbage bin can't carry out automatic classification.
Disclosure of Invention
Aiming at the defects in the prior art, the intelligent classification garbage can based on deep learning provided by the invention solves the problem that automatic classification cannot be realized by the existing garbage can.
In order to achieve the purpose of the invention, the invention adopts the technical scheme that:
the intelligent classification garbage can based on deep learning comprises a base, wherein a shell is arranged on the base, a cover is arranged at the top of the shell, a putting-in opening is formed in the upper end of the shell, a first baffle surrounding the putting-in opening is arranged inside the shell, a camera is arranged on one side, facing the putting-in opening, of the first baffle, a first steering engine is arranged on one side, facing away from the putting-in opening, of the first baffle, a rotatable partition plate is arranged at the lower end of the first baffle, and the first steering engine is connected with the partition plate through a first gear set and used for controlling the partition plate to rotate;
a rotary supporting piece capable of freely rotating is arranged at the center of the base, a classification barrel is arranged on the rotary supporting piece, a plurality of garbage storage chambers are arranged on the classification barrel, and an inner garbage barrel is placed in each garbage storage chamber; the classification barrel is connected with a second steering engine through a second gear set, and the second steering engine is arranged on the base; the base is also provided with a main control unit and a power supply module; the camera, the first steering engine, the second steering engine and the power supply module are respectively connected with the main control unit; a door body for taking out the garbage inner barrel is arranged on the shell;
and the main control unit is used for identifying the image shot by the camera by adopting a neural network model, acquiring the type of the input object, controlling the second steering engine to rotate the garbage inner barrel corresponding to the type of the input object to the position right below the partition plate, and controlling the first steering engine to rotate the partition plate to enable the input object to fall into the corresponding garbage inner barrel to finish garbage classification.
Further, a distance and temperature sensor is arranged on one side of the first baffle, which is far away from the throwing port, and the distance and temperature sensor is connected with the main control unit; and the distance and temperature sensor is used for acquiring the temperature and the stacking height of the objects in the garbage storage chamber.
Furthermore, a wireless communication module is arranged on the base and connected with the main control unit.
Further, the distance and temperature sensor comprises a temperature sensing module with the model number of DS18B20 and an ultrasonic ranging module with the model number of HC-SR 04.
Furthermore, an included angle formed by the first baffle towards the throwing opening is smaller than or equal to the opening angle of the garbage inner barrel.
Furthermore, the classification barrel comprises a central shaft arranged on the rotary supporting piece, a bottom plate is arranged at the lower end of the central shaft, a second baffle is arranged on the bottom plate, and a garbage storage chamber is enclosed by the second baffle bottom plate.
Further, the neural network model adopted by the master control unit includes:
a convolution pooling module, including 4 convolution kernels with sizes of 9 × 9, 6 × 6, 3 × 3 and 1 × 1, for performing convolution on the image shot by the camera to obtain 3 feature maps of 112 × 112 × 32 and 1 feature map of 224 × 224 × 32, and performing 1 × 1 convolution on the feature maps of 224 × 224 × 32 to obtain 2 × 2 pooling with a step size of 2, to obtain 112 × 112 × 32 feature maps corresponding to the feature maps of 224 × 224 × 32, to obtain 4 feature maps of 112 × 112 × 32;
the first cascading module is used for cascading the 4 112 multiplied by 32 characteristic maps obtained by the convolution pooling module to obtain a 112 multiplied by 128 characteristic map;
the convolution module comprises 2 convolution kernels with the sizes of 4 multiplied by 4 and 2 multiplied by 2 respectively, and is used for performing convolution on the 112 multiplied by 128 characteristic graphs obtained by the first cascade module respectively to obtain 2 characteristic graphs of 56 multiplied by 64;
the second cascade module is used for cascading the 256 × 56 × 64 feature maps obtained by the convolution module to obtain 1 56 × 56 × 128 feature map;
the activation module is used for activating the 56 multiplied by 128 feature map obtained by the second cascade module and then outputting an activated feature map with the size of 7 multiplied by 1024;
the global average pooling module is used for performing global average pooling on the 7 multiplied by 1024 activation characteristic graph output by the activation module and then connecting the activation characteristic graph with the full connection layer;
and the full connection layer is used for carrying out classification and identification and obtaining a classification result.
Further, the activation module comprises three activation units: a first activation unit, a second activation unit, and a third activation unit, wherein:
the first activation unit is used for sequentially performing 1 × 1 convolution, batch normalization and 3 × 3 2-dimensional convolution kernel convolution on the 56 × 56 × 128 feature graph obtained by the second cascade module to obtain a 28 × 28 × 256 feature graph, and performing activation function activation on the 28 × 28 × 256 feature graph to obtain a first activation feature graph;
the second activation unit is used for sequentially performing 1 × 1 convolution, batch normalization and 3 × 3 2-dimensional convolution kernel convolution on the first activation characteristic diagram obtained by the first activation unit to obtain a 14 × 14 × 512 characteristic diagram, and performing activation function activation on the 14 × 14 × 512 characteristic diagram to obtain a second activation characteristic diagram;
the third activation unit is used for sequentially performing 1 × 1 convolution, batch normalization and 3 × 3 2-dimensional convolution kernel convolution on the second activation characteristic diagram obtained by the second activation unit to obtain a 7 × 7 × 1024 characteristic diagram, and performing activation function activation on the 7 × 7 × 1024 characteristic diagram to obtain a third activation characteristic diagram; wherein the third activation profile is an output of the activation module.
The invention has the beneficial effects that:
1. the invention can automatically classify and identify the objects put into the garbage can, and select the corresponding garbage inner can to store the objects according to the classification result, thereby realizing the automatic classification of the garbage.
2. The distance and temperature sensor can measure the stacking height and temperature of objects in the garbage inner barrel, and when the height or the temperature reaches a set value, the distance and temperature sensor can send a message to related personnel through the wireless communication module to inform the related personnel of timely cleaning.
3. The small convolution kernel energy in the neural network model adopted by the main control unit can extract small-range features, the large convolution kernel energy can extract large-range features, and the feature maps obtained after convolution and pooling retain features in different ranges after cascading, so that garbage objects in different sizes can be respectively identified conveniently.
4. The neural network model adopted by the main control unit uses different convolution kernels and pooling layers to carry out convolution \ pooling, and then characteristic diagrams obtained after the convolution \ pooling are cascaded, so that parameters in the convolutional neural network can be effectively reduced, the calculation amount is reduced, and the hardware requirement on the main control unit is further effectively reduced.
Drawings
FIG. 1 is a schematic structural view of the present invention;
FIG. 2 is an exploded view of the base and the classification bucket;
fig. 3 is a schematic diagram of a training process of the neural network model.
Wherein: 1. a cover; 2. a housing; 3. a first baffle plate; 4. a camera; 5. a throwing port; 6. a partition plate; 7. a first steering engine; 8. a distance and temperature sensor; 9. a classification bucket; 10. a first gear set; 11. a garbage inner barrel; 12. a second gear set; 13. a second steering engine; 14. a main control unit; 15. a rotating support; 16. a power supply module; 17. a base; 18. a central shaft; 19. a second baffle; 20. a door body.
Detailed Description
The following description of the embodiments of the present invention is provided to facilitate the understanding of the present invention by those skilled in the art, but it should be understood that the present invention is not limited to the scope of the embodiments, and it will be apparent to those skilled in the art that various changes may be made without departing from the spirit and scope of the invention as defined and defined in the appended claims, and all matters produced by the invention using the inventive concept are protected.
As shown in fig. 1 and 2, the intelligent classification trash can based on deep learning comprises a base 17, a shell 2 is arranged on the base 17, a cover 1 is arranged at the top of the shell 2, a throwing opening 5 is arranged at the upper end of the shell 2, a first baffle 3 surrounding the throwing opening 5 is arranged inside the shell 2, a camera 4 is arranged on one side, facing the throwing opening 5, of the first baffle 3, a first steering gear 7 is arranged on one side, facing away from the throwing opening 5, of the first baffle 3, a rotatable partition plate 6 is arranged at the lower end of the first baffle 3, and the first steering gear 7 is connected with the partition plate 6 through a first gear set 10 and used for controlling the partition plate 6 to rotate;
a rotary supporting piece 15 capable of freely rotating is arranged at the center of the base 17, a classification barrel 9 is arranged on the rotary supporting piece 15, a plurality of garbage storage chambers are arranged on the classification barrel 9, and an inner garbage barrel 11 is arranged in each garbage storage chamber; the classification barrel 9 is connected with a second steering engine 13 through a second gear set 12, and the second steering engine 13 is arranged on a base 17; the base 17 is also provided with a main control unit 14 and a power supply module 16; the camera 4, the first steering engine 7, the second steering engine 13 and the power module 16 are respectively connected with the main control unit 14; the shell 2 is provided with a door body 20 for taking out the garbage inner barrel 11;
and the main control unit 14 is used for identifying the image shot by the camera 4 by adopting a neural network model, acquiring the type of the input object, controlling the second steering engine 13 to rotate the garbage inner barrel 11 corresponding to the type of the input object to be right below the partition plate 6, and controlling the first steering engine 7 to rotate the partition plate 6 to enable the input object to fall into the corresponding garbage inner barrel 11, so that garbage classification is completed.
A distance and temperature sensor 8 is further arranged on one side, away from the putting-in opening 5, of the first baffle 3, and the distance and temperature sensor 8 is connected with a main control unit 14; and the distance and temperature sensor 8 is used for acquiring the temperature and the stacking height of the objects in the garbage storage chamber.
The base 17 is further provided with a wireless communication module, and the wireless communication module is connected with the main control unit 14.
The distance and temperature sensor 8 comprises a temperature sensing module of type DS18B20 and an ultrasonic ranging module of type HC-SR 04.
The included angle formed by the first baffle 3 towards the throwing opening 5 is less than or equal to the opening angle of the garbage inner barrel 11.
The sorting barrel 9 comprises a central shaft 18 arranged on the rotary supporting member 15, a bottom plate is arranged at the lower end of the central shaft 18, a second baffle plate 19 is arranged on the bottom plate, and a garbage storage chamber is enclosed by the bottom plate of the second baffle plate 19.
As shown in fig. 3, the neural network model adopted by the master control unit 14 includes:
a convolution pooling module, including 4 convolution kernels with sizes of 9 × 9, 6 × 6, 3 × 3 and 1 × 1, respectively, for performing convolution on the image shot by the camera 4 to obtain 3 feature maps of 112 × 112 × 32 and 1 feature map of 224 × 224 × 32, and performing 1 × 1 convolution on the feature maps of 224 × 224 × 32 to obtain 2 × 2 pooling with a step size of 2, to obtain 112 × 112 × 32 feature maps corresponding to the feature maps of 224 × 224 × 32, to obtain 4 feature maps of 112 × 112 × 32;
the first cascading module is used for cascading the 4 112 multiplied by 32 characteristic maps obtained by the convolution pooling module to obtain a 112 multiplied by 128 characteristic map;
the convolution module comprises 2 convolution kernels with the sizes of 4 multiplied by 4 and 2 multiplied by 2 respectively, and is used for performing convolution on the 112 multiplied by 128 characteristic graphs obtained by the first cascade module respectively to obtain 2 characteristic graphs of 56 multiplied by 64;
the second cascade module is used for cascading the 256 × 56 × 64 feature maps obtained by the convolution module to obtain 1 56 × 56 × 128 feature map;
the activation module is used for activating the 56 multiplied by 128 feature map obtained by the second cascade module and then outputting an activated feature map with the size of 7 multiplied by 1024;
the global average pooling module is used for performing global average pooling on the 7 multiplied by 1024 activation characteristic graph output by the activation module and then connecting the activation characteristic graph with the full connection layer;
and the full connection layer is used for carrying out classification and identification and obtaining a classification result.
The activation module includes three activation units: a first activation unit, a second activation unit, and a third activation unit, wherein:
the first activation unit is used for sequentially performing 1 × 1 convolution, batch normalization and 3 × 3 2-dimensional convolution kernel convolution on the 56 × 56 × 128 feature graph obtained by the second cascade module to obtain a 28 × 28 × 256 feature graph, and performing activation function activation on the 28 × 28 × 256 feature graph to obtain a first activation feature graph;
the second activation unit is used for sequentially performing 1 × 1 convolution, batch normalization and 3 × 3 2-dimensional convolution kernel convolution on the first activation characteristic diagram obtained by the first activation unit to obtain a 14 × 14 × 512 characteristic diagram, and performing activation function activation on the 14 × 14 × 512 characteristic diagram to obtain a second activation characteristic diagram;
the third activation unit is used for sequentially performing 1 × 1 convolution, batch normalization and 3 × 3 2-dimensional convolution kernel convolution on the second activation characteristic diagram obtained by the second activation unit to obtain a 7 × 7 × 1024 characteristic diagram, and performing activation function activation on the 7 × 7 × 1024 characteristic diagram to obtain a third activation characteristic diagram; wherein the third activation profile is an output of the activation module.
In one embodiment of the invention, garbage objects are thrown on the partition plate 6 from the throwing opening 5, the camera 4 shoots the garbage objects and identifies the garbage objects through the main control unit 14, the main control unit 14 starts the second steering engine 13 according to an identification result to rotate the garbage inner barrel 11 corresponding to the identified type to be right below the partition plate 6, then the first steering engine 7 is started to rotate the partition plate 6, so that the garbage objects on the partition plate 6 fall into the corresponding garbage inner barrel 11, and the first steering engine 7 rotates the partition plate 6 to be closed. In the rotation process of the garbage inner barrel 11, the distance and temperature sensor 8 can detect the temperature and the object stacking height of the garbage inner barrel 11 positioned below the distance and temperature sensor, and when the temperature or the object stacking height reaches a preset value, the main control unit 14 starts the wireless communication module to send a message to related personnel to inform the related personnel of timely cleaning.
When the related personnel arrive at the corresponding garbage can, the garbage inner barrel 11 placed in the classification barrel 9 can be taken out by opening the door body 20, and the garbage in the garbage inner barrel 11 is dumped. Related personnel can manually rotate the classification barrel 9 to take out different garbage inner barrels 11, and can also send an active rotation instruction to the main control unit 14 through the terminal and the wireless communication module to control the second steering engine 13 to rotate to take out different garbage inner barrels 11.
When needs overhaul garbage bin inside, can dismantle lid 1 and overhaul the part of first steering wheel 7 department. The housing 2 and base 17 can be separated to allow for servicing of the components within the base 17 or the sorting cask 9. First steering wheel 7 and distance and temperature sensor 8's pencil can be walked to the base 17 through the back of first baffle 3, the inside of shell 2 in and link to each other with main control unit 14, can guarantee the inside isolation of categorised bucket 9 and base 17, avoids object or liquid to get into damage parts in the base 17.
In the concrete implementation process, the classification recognition result has a plurality of classifications, a mixing inner barrel can be arranged for storing, and manual garbage classification can be carried out again when related personnel clear up garbage.
In conclusion, the invention can automatically classify and identify the objects put into the garbage can, and select the corresponding garbage inner can 11 to store the objects according to the classification result, thereby realizing automatic garbage classification.
Claims (8)
1. The intelligent classification garbage can based on deep learning is characterized by comprising a base (17), wherein a shell (2) is arranged on the base (17), a cover (1) is arranged at the top of the shell (2), a putting-in opening (5) is formed in the upper end of the shell (2), a first baffle (3) surrounding the putting-in opening (5) is arranged inside the shell (2), a camera (4) is arranged on one side, facing the putting-in opening (5), of the first baffle (3), a first steering engine (7) is arranged on one side, facing away from the putting-in opening (5), of the first baffle (3), a rotatable partition plate (6) is arranged at the lower end of the first baffle (3), and the first steering engine (7) is connected with the partition plate (6) through a first gear set (10) and used for controlling the partition plate (6) to rotate;
a rotary support piece (15) capable of freely rotating is arranged at the center of the base (17), a classification barrel (9) is arranged on the rotary support piece (15), a plurality of garbage storage chambers are arranged on the classification barrel (9), and an inner garbage barrel (11) is arranged in each garbage storage chamber; the classification barrel (9) is connected with a second steering engine (13) through a second gear set (12), and the second steering engine (13) is arranged on the base (17); the base (17) is also provided with a main control unit (14) and a power supply module (16); the camera (4), the first steering engine (7), the second steering engine (13) and the power supply module (16) are respectively connected with the main control unit (14); a door body (20) for taking out the garbage inner barrel (11) is arranged on the shell (2);
the main control unit (14) is used for identifying images shot by the camera (4) by adopting a neural network model, obtaining the type of an input object, controlling the second steering engine (13) to rotate the garbage inner barrel (11) corresponding to the type of the input object to the position right below the partition plate (6), controlling the first steering engine (7) to rotate the partition plate (6) to enable the input object to fall into the corresponding garbage inner barrel (11), and finishing garbage classification.
2. The intelligent classification garbage can based on deep learning according to claim 1, wherein a distance and temperature sensor (8) is further arranged on one side of the first baffle (3) away from the putting-in opening (5), and the distance and temperature sensor (8) is connected with the main control unit (14); and the distance and temperature sensor (8) is used for acquiring the temperature and the stacking height of the objects in the garbage storage chamber.
3. The intelligent classification garbage can based on deep learning as claimed in claim 2, wherein a wireless communication module is further arranged on the base (17), and the wireless communication module is connected with the main control unit (14).
4. The intelligent deep learning based classification trash can of claim 2, wherein the distance and temperature sensor (8) comprises a temperature sensing module model DS18B20 and an ultrasonic ranging module model HC-SR 04.
5. The intelligent classification garbage can based on deep learning as claimed in claim 1, wherein the included angle formed by the first baffle (3) towards the throwing opening (5) is less than or equal to the opening angle of the garbage inner can (11).
6. The intelligent classification garbage can based on deep learning as claimed in claim 1, wherein the classification garbage can (9) comprises a central shaft (18) arranged on the rotary support member (15), a bottom plate is arranged at the lower end of the central shaft (18), a second baffle plate (19) is arranged on the bottom plate, and the bottom plate of the second baffle plate (19) encloses a garbage storage chamber.
7. The intelligent deep learning based classification trash can of claim 1, wherein the neural network model adopted by the master control unit (14) comprises:
a convolution pooling module, which comprises 4 convolution kernels with the sizes of 9 × 9, 6 × 6, 3 × 3 and 1 × 1 respectively, and is used for performing convolution on the image shot by the camera (4) to obtain 3 feature maps of 112 × 112 × 32 and 1 feature map of 224 × 224 × 32, performing 1 × 1 convolution on the feature maps of 224 × 224 × 32 to obtain 2 × 2 pooling with the step size of 2, and obtaining 112 × 112 × 32 feature maps corresponding to the feature maps of 224 × 224 × 32 to obtain 4 feature maps of 112 × 112 × 32;
the first cascading module is used for cascading the 4 112 multiplied by 32 characteristic maps obtained by the convolution pooling module to obtain a 112 multiplied by 128 characteristic map;
the convolution module comprises 2 convolution kernels with the sizes of 4 multiplied by 4 and 2 multiplied by 2 respectively, and is used for performing convolution on the 112 multiplied by 128 characteristic graphs obtained by the first cascade module respectively to obtain 2 characteristic graphs of 56 multiplied by 64;
the second cascade module is used for cascading the 256 × 56 × 64 feature maps obtained by the convolution module to obtain 1 56 × 56 × 128 feature map;
the activation module is used for activating the 56 multiplied by 128 feature map obtained by the second cascade module and then outputting an activated feature map with the size of 7 multiplied by 1024;
the global average pooling module is used for performing global average pooling on the 7 multiplied by 1024 activation characteristic graph output by the activation module and then connecting the activation characteristic graph with the full connection layer;
and the full connection layer is used for carrying out classification and identification and obtaining a classification result.
8. The intelligent classification trash can based on deep learning of claim 7, wherein the activation module comprises three activation units: a first activation unit, a second activation unit, and a third activation unit, wherein:
the first activation unit is used for sequentially performing 1 × 1 convolution, batch normalization and 3 × 3 2-dimensional convolution kernel convolution on the 56 × 56 × 128 feature graph obtained by the second cascade module to obtain a 28 × 28 × 256 feature graph, and performing activation function activation on the 28 × 28 × 256 feature graph to obtain a first activation feature graph;
the second activation unit is used for sequentially performing 1 × 1 convolution, batch normalization and 3 × 3 2-dimensional convolution kernel convolution on the first activation characteristic diagram obtained by the first activation unit to obtain a 14 × 14 × 512 characteristic diagram, and performing activation function activation on the 14 × 14 × 512 characteristic diagram to obtain a second activation characteristic diagram;
the third activation unit is used for sequentially performing 1 × 1 convolution, batch normalization and 3 × 3 2-dimensional convolution kernel convolution on the second activation characteristic diagram obtained by the second activation unit to obtain a 7 × 7 × 1024 characteristic diagram, and performing activation function activation on the 7 × 7 × 1024 characteristic diagram to obtain a third activation characteristic diagram; wherein the third activation profile is an output of the activation module.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011439780.1A CN112660655B (en) | 2020-12-10 | 2020-12-10 | Intelligent classification garbage bin based on degree of depth study |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011439780.1A CN112660655B (en) | 2020-12-10 | 2020-12-10 | Intelligent classification garbage bin based on degree of depth study |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112660655A true CN112660655A (en) | 2021-04-16 |
CN112660655B CN112660655B (en) | 2022-11-29 |
Family
ID=75401932
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011439780.1A Active CN112660655B (en) | 2020-12-10 | 2020-12-10 | Intelligent classification garbage bin based on degree of depth study |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112660655B (en) |
Citations (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2006021005A (en) * | 2004-07-09 | 2006-01-26 | Daiwa Sokuryo Sekkei Kk | Kitchen system, and method and device for treating food and waste |
CN107578060A (en) * | 2017-08-14 | 2018-01-12 | 电子科技大学 | A kind of deep neural network based on discriminant region is used for the method for vegetable image classification |
JP2018062423A (en) * | 2016-10-15 | 2018-04-19 | 中川 明紀 | Attachment for garbage box |
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 |
CN109606991A (en) * | 2019-01-11 | 2019-04-12 | 郑州大学 | Intelligent garbage bin and refuse classification method based on deep learning |
CN109625680A (en) * | 2019-01-28 | 2019-04-16 | 中国地质大学(武汉) | A kind of intelligent recognition classification recycling dustbin |
DE202019103055U1 (en) * | 2018-08-03 | 2019-06-12 | Yu Hsuan Yang | Automatic waste sorting facility |
CA3032188A1 (en) * | 2018-01-31 | 2019-07-31 | Pin-Han Ho | Deep convolutional neural network architecture and system and method for building the deep convolutional neural network architecture |
CN110316496A (en) * | 2019-08-19 | 2019-10-11 | 浙江工业大学 | A kind of intelligent garbage identification sorter Internet-based |
CN110466911A (en) * | 2019-04-08 | 2019-11-19 | 江西理工大学 | Automatic sorting garbage bin and classification method |
CN110861852A (en) * | 2019-11-28 | 2020-03-06 | 石家庄邮电职业技术学院(中国邮政集团公司培训中心) | Automatic classification garbage can based on visual identification and classification method |
CN111301900A (en) * | 2020-03-29 | 2020-06-19 | 贵州云贤悦成科技有限公司 | Intelligent garbage classification device and control system |
CN111332651A (en) * | 2020-03-16 | 2020-06-26 | 河海大学常州校区 | Photoelectric sensing garbage bin based on degree of depth study |
CN111553426A (en) * | 2020-04-29 | 2020-08-18 | 河海大学 | Low-overhead household garbage classification method based on dense convolutional network |
CN211282284U (en) * | 2019-07-30 | 2020-08-18 | 成都工业学院 | Garbage classification throwing device and system |
CN211282309U (en) * | 2019-12-03 | 2020-08-18 | 广西科技大学 | Automatic classification garbage can |
WO2020206862A1 (en) * | 2019-04-08 | 2020-10-15 | 江西理工大学 | Automatic sorting system |
CN112009899A (en) * | 2020-07-13 | 2020-12-01 | 西安建筑科技大学 | Garbage classification box constructed based on convolutional neural network |
CN112036475A (en) * | 2020-08-28 | 2020-12-04 | 江南大学 | Fusion module, multi-scale feature fusion convolutional neural network and image identification method |
-
2020
- 2020-12-10 CN CN202011439780.1A patent/CN112660655B/en active Active
Patent Citations (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2006021005A (en) * | 2004-07-09 | 2006-01-26 | Daiwa Sokuryo Sekkei Kk | Kitchen system, and method and device for treating food and waste |
JP2018062423A (en) * | 2016-10-15 | 2018-04-19 | 中川 明紀 | Attachment for garbage box |
CN107578060A (en) * | 2017-08-14 | 2018-01-12 | 电子科技大学 | A kind of deep neural network based on discriminant region is used for the method for vegetable image classification |
CA3032188A1 (en) * | 2018-01-31 | 2019-07-31 | Pin-Han Ho | Deep convolutional neural network architecture and system and method for building the deep convolutional neural network architecture |
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 |
DE202019103055U1 (en) * | 2018-08-03 | 2019-06-12 | Yu Hsuan Yang | Automatic waste sorting facility |
CN109606991A (en) * | 2019-01-11 | 2019-04-12 | 郑州大学 | Intelligent garbage bin and refuse classification method based on deep learning |
CN109625680A (en) * | 2019-01-28 | 2019-04-16 | 中国地质大学(武汉) | A kind of intelligent recognition classification recycling dustbin |
CN110466911A (en) * | 2019-04-08 | 2019-11-19 | 江西理工大学 | Automatic sorting garbage bin and classification method |
WO2020206862A1 (en) * | 2019-04-08 | 2020-10-15 | 江西理工大学 | Automatic sorting system |
CN211282284U (en) * | 2019-07-30 | 2020-08-18 | 成都工业学院 | Garbage classification throwing device and system |
CN110316496A (en) * | 2019-08-19 | 2019-10-11 | 浙江工业大学 | A kind of intelligent garbage identification sorter Internet-based |
CN110861852A (en) * | 2019-11-28 | 2020-03-06 | 石家庄邮电职业技术学院(中国邮政集团公司培训中心) | Automatic classification garbage can based on visual identification and classification method |
CN211282309U (en) * | 2019-12-03 | 2020-08-18 | 广西科技大学 | Automatic classification garbage can |
CN111332651A (en) * | 2020-03-16 | 2020-06-26 | 河海大学常州校区 | Photoelectric sensing garbage bin based on degree of depth study |
CN111301900A (en) * | 2020-03-29 | 2020-06-19 | 贵州云贤悦成科技有限公司 | Intelligent garbage classification device and control system |
CN111553426A (en) * | 2020-04-29 | 2020-08-18 | 河海大学 | Low-overhead household garbage classification method based on dense convolutional network |
CN112009899A (en) * | 2020-07-13 | 2020-12-01 | 西安建筑科技大学 | Garbage classification box constructed based on convolutional neural network |
CN112036475A (en) * | 2020-08-28 | 2020-12-04 | 江南大学 | Fusion module, multi-scale feature fusion convolutional neural network and image identification method |
Also Published As
Publication number | Publication date |
---|---|
CN112660655B (en) | 2022-11-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110316496A (en) | A kind of intelligent garbage identification sorter Internet-based | |
CN203402565U (en) | Trash can capable of classifying trash | |
CN212654888U (en) | Automatic categorised intelligent garbage bin | |
CN111301886B (en) | Garbage classification and recovery system based on RBF neural network and control method | |
CN210417800U (en) | Automatic classification dustbin | |
CN103318582A (en) | Automatic classification trash can | |
CN108438592A (en) | A kind of townm refuse specification processing system | |
CN106890843A (en) | Classification ball domestic garbage treating system and method | |
CN110355188A (en) | Based on the multiple wisdom garbage classification sludge reduction onsite recycling system utilized in soil | |
CN110723431A (en) | Garbage classification method based on BP neural network recognition system | |
CN110834835A (en) | Intelligent garbage classification processing method and system based on internet big data | |
CN111619992A (en) | Intelligent garbage classification system and method based on machine vision | |
Nandhini et al. | Electronically assisted automatic waste segregation | |
CN111232497A (en) | Multifunctional automatic classification garbage can based on geneva mechanism | |
CN112660655B (en) | Intelligent classification garbage bin based on degree of depth study | |
CN205738954U (en) | Intelligent refuse classification device | |
CN206307559U (en) | A kind of intelligent system for providing refuse bag and classification recovery rubbish | |
CN111703792B (en) | Intelligent garbage classification transfer station and control method thereof | |
CN111137602B (en) | Garbage classification method and garbage classification system based on artificial intelligence | |
CN205327895U (en) | Environmental protection sortable garbage bin is moulded to living beings straw wood | |
CN210437814U (en) | Intelligent recognition classification recycling garbage can | |
CN110963201A (en) | Intelligent garbage classification circulating system | |
CN214191135U (en) | Garbage throwing device | |
CN217576626U (en) | Classification garbage can | |
CN214932814U (en) | Automatic garbage classification's dustbin |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |