CN208165794U - A kind of intelligent classification dustbin - Google Patents
A kind of intelligent classification dustbin Download PDFInfo
- Publication number
- CN208165794U CN208165794U CN201721509769.1U CN201721509769U CN208165794U CN 208165794 U CN208165794 U CN 208165794U CN 201721509769 U CN201721509769 U CN 201721509769U CN 208165794 U CN208165794 U CN 208165794U
- Authority
- CN
- China
- Prior art keywords
- dustbin
- rubbish
- intelligent
- classification
- sliding rail
- 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.)
- Expired - Fee Related
Links
- 239000010813 municipal solid waste Substances 0.000 claims abstract description 56
- 238000004891 communication Methods 0.000 claims abstract description 17
- 239000002699 waste material Substances 0.000 claims abstract description 13
- 238000001514 detection method Methods 0.000 abstract description 6
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000000034 method Methods 0.000 description 11
- 230000004807 localization Effects 0.000 description 2
- 238000004064 recycling Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000032258 transport Effects 0.000 description 2
- 230000002950 deficient Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
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)
- Refuse Collection And Transfer (AREA)
Abstract
The utility model discloses a kind of intelligent classification dustbin, it is successively arranged from left to right at the top of the dustbin including headlamp, camera and communication apparatus, staving is equipped with pipeline below the headlamp, sliding rail is equipped with below the pipe end, the sliding rail is equipped with intelligent carriage, the intelligent carriage is connected with communication apparatus, it is successively arranged recyclable rubbish dustbin below the sliding rail, non-recyclable rubbish dustbin, Harmful Waste dustbin, Other Waste dustbin, fails to identify rubbish dustbin, the dustbin bottom is power-supply device.Beneficial effect：It may be implemented in fast target detection and identification in the higher situation of accuracy rate, real-time perfoming can classify after rubbish puts into dustbin.
Description
Technical field
The utility model belongs to garbage recovery device field, especially a kind of intelligent classification dustbin.
Background technique
Garbage classification is that the premise of scientific disposal is carried out to rubbish, is the basis of rubbish processing to be harmless and recycling,
The Ke Xunhuanliyong and environmental protection of resource is had a very important significance.
The rubbish of China most cities uses the mode of " concentrating mixed collection-collective conveyance-centralized processing " at present, no
But classification processing difficulty is increased, the waste of huge manpower, resource is also resulted in.Although the Waste sorting recycle in China works
It has been be in full swing that, but Waste sorting recycle facility is too simple, only identified by several with " recyclable ", " not can be recycled "
Dustbin composition.Since common people's garbage classification knowledge is more deficient, tend not to correctly be sorted out rubbish, so at this stage
Classification garbage can not play guidance resident and consciously carry out the effect of garbage classification dispensing.
Summary of the invention
Technology contents：The purpose of the invention is to overcome the classification of conventional garbage bucket difficult, a kind of intelligence is established
It can classification garbage can.
Technical solution：
What the purpose of this utility model was realized in：The device and method of intelligent classification dustbin：
Technical solution：A kind of intelligent classification dustbin, it is characterised in that：It is successively arranged from left to right at the top of the dustbin
Including headlamp, camera and communication apparatus, staving is equipped with pipeline below the headlamp, is equipped with below the pipe end
Sliding rail, the sliding rail are equipped with intelligent carriage, and the intelligent carriage is connected with communication apparatus, are successively arranged below the sliding rail
Recyclable rubbish dustbin, Harmful Waste dustbin, Other Waste dustbin, fails to identify rubbish at non-recyclable rubbish dustbin
Rubbish dustbin, the dustbin bottom are power-supply device.
Preferably, loading container is equipped with above the intelligent carriage, the pipeline is used to the rubbish of investment falling into intelligence
On the container of trolley.
Preferably, the container is that structure may be reversed.
Preferably, STM32F103 series monolithic built in the intelligent carriage.
Device includes：Lighting device, camera, power supply device, network communication equipment, sliding rail, intelligent carriage and core
Handle computer；
The intelligent garbage bin refuse classification method be based on as acquisition module, network communication module, picture recognition module and
Rubbish transports module and realizes.Wherein, image capture module is made of lighting device and camera, is responsible for the picture number of acquisition rubbish
It is responsible for the collected data of image capture module being transferred to server according to, network communication module.Picture recognition module is located at remote
Journey server is responsible for carrying out identification classification to rubbish image, judges what classification the rubbish belongs to.Finally obtained information is led to
It crosses network communication module and passes dustbin back, and module is transported by rubbish, rubbish is poured into designated position.
Specific step is as follows for the localization method：
(1) foundation of Image Classifier：First in server end by having mark, different classes of rubbish to a large amount of
Image is trained with YOLO algorithm, building one classifier for classifying to rubbish image.
(2) rubbish image sampling：It can be fallen into a fixed container after rubbish investment dustbin, have illumination above container
Equipment and camera are acquired rubbish image.
(3) characteristics of image identifies：After collecting rubbish image, image can be passed back server by network communication module, and will
The image is classified by trained classifier, to make not change what type rubbish belongs to.
(4) classification is thrown：Network communication equipment can receive the classification results of server end, and be thrown rubbish by sliding rail
It is put into the dustbin of corresponding classification.
Beneficial effect：The utility model classifies automatically to rubbish using YOLO algorithm, relative to other target detections
For algorithm by multiple processes such as object recognition task class object regional prediction and class prediction, YOLO predicts target area and mesh
Mark class prediction is integrated in single Neural model, is realized the fast target detection in the higher situation of accuracy rate and is known
Not, real-time perfoming can classify after rubbish puts into dustbin.
Detailed description of the invention
Fig. 1 is utility model device schematic diagram.
Fig. 2 is the system flow chart of the utility model.
Specific embodiment
The present invention is further illustrated with reference to the accompanying drawings and examples.
This intelligent classification dustbin implementation method：
As shown in Figure 1, device includes：Camera 1, headlamp 2, pipeline 3, intelligent carriage 4, communication equipment 5, sliding rail 6；It can
Recycling rubbish dustbin 7, not recyclable rubbish dustbin 8, Other Waste dustbin 10, fail to identify at Harmful Waste dustbin 9
Rubbish dustbin 11, power-supply device 12, the camera 1 and headlamp 2 are fixed at the top of dustbin, the light tunnel
3 for the rubbish of investment to be fallen into the container of intelligent carriage 4, and single-chip microcontroller built in intelligent carriage 4 can control the movement of trolley,
One container is installed, for placing rubbish to be sorted at the top of trolley.The container can be controlled to from single-chip microcontroller to a rollover
Turn, so that rubbish be poured into dustbin；The image data that the communication equipment 5 is used to will acquire is passed server back and is known
Not, and receive after identifying as a result, the intelligent carriage 4 is moved in dustbin by sliding rail 6.Power-supply device 12 is entire
Intelligent garbage bin power supply.
The intelligent garbage bin refuse classification method be based on as acquisition module, network communication module, picture recognition module and
Rubbish transports module and realizes.As shown in Fig. 2, specific step is as follows for the localization method：
A. the foundation of Image Classifier：It is each to recyclable rubbish, non-recyclable rubbish, Harmful Waste, Other Waste first
It collects a thousand sheets image data and is labeled.The data marked are trained by YOLO algorithm to construct classifier.
Specifically, object detection is processed into a regression problem by YOLO algorithm, it is input with whole figure, directly defeated
Layer is returned out, obtains the generic of picture, is substantially increased detection speed while guaranteeing certain precision, is met
The requirement of real-time detection.
The implementation method of algorithm is as follows：Piece image is divided into S*S grid first, if the center of some object is fallen in
In this grid, then this grid is just responsible for predicting this object.Each grid will predict B bounding box, each
Bounding box will also be attached to other than returning the position of itself and predict a confidence level.Each bounding box
Predict that totally 5 values, each grid will also predict a classification information, be denoted as C class for (x, y, w, h) and confidence level.Then S*S net
Lattice.Export the classifier of S*S* (5*B+C) classification.Classification information and bounding the box prediction of each grid forecasting
Reliability information is multiplied, and just obtains the probability for belonging to some classification of each bounding box.
For training the loss function of YOLO classifier as follows:
It is the process for minimizing loss function by stochastic gradient descent to the process of mark sample training.In turn
Picture classification device is obtained, for classification and Detection later.
B. rubbish image sampling：It is fallen into the container on intelligent carriage 4 after rubbish investment dustbin by pipeline 3.Camera shooting
First 1 acquisition data simultaneously pass image back server by communication equipment 5.
C. classification belonging to the rubbish image is calculated by YOLO algorithm after received server-side to image, and returns to possibility
The maximum result of property.
D. classification is thrown：Network communication equipment can receive the classification results of server end, and send result to intelligence
Single-chip microcontroller in trolley, controls trolley movement by single-chip microcontroller, and trolley is moved to above specified dustbin by sliding rail, and
Rubbish is poured by refuse container overturning on single-chip microcontroller control trolley and is formulated in dustbin.
Claims (4)
1. a kind of intelligent classification dustbin, it is characterised in that：Be successively arranged from left to right at the top of the dustbin including headlamp,
Camera and communication apparatus, headlamp lower section staving are equipped with pipeline, are equipped with sliding rail, the cunning below the pipe end
Rail is equipped with intelligent carriage, and the intelligent carriage is connected with communication apparatus, is successively arranged recyclable rubbish below the sliding rail
Dustbin, Harmful Waste dustbin, Other Waste dustbin, fails to identify rubbish dustbin, institute at non-recyclable rubbish dustbin
Stating dustbin bottom is power-supply device.
2. a kind of intelligent classification dustbin according to claim 1, it is characterised in that：Loading is equipped with above the intelligent carriage
Container, the pipeline are used to fall into the rubbish of investment the container of intelligent carriage.
3. a kind of intelligent classification dustbin according to claim 2, it is characterised in that：The container is that structure may be reversed.
4. a kind of intelligent classification dustbin according to claim 1, it is characterised in that：Built in the intelligent carriage
STM32F103 series monolithic.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201721509769.1U CN208165794U (en) | 2017-11-14 | 2017-11-14 | A kind of intelligent classification dustbin |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201721509769.1U CN208165794U (en) | 2017-11-14 | 2017-11-14 | A kind of intelligent classification dustbin |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN208165794U true CN208165794U (en) | 2018-11-30 |
Family
ID=64386021
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201721509769.1U Expired - Fee Related CN208165794U (en) | 2017-11-14 | 2017-11-14 | A kind of intelligent classification dustbin |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN208165794U (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109368079A (en) * | 2018-12-10 | 2019-02-22 | 浙江梧斯源通信科技股份有限公司 | A kind of automatic garbage classification system and method |
| CN109516037A (en) * | 2019-01-25 | 2019-03-26 | 李�昊 | A kind of classification garbage can based on machine vision |
| CN109573383A (en) * | 2018-12-27 | 2019-04-05 | 深兰科技（上海）有限公司 | Dustbin |
| CN109606991A (en) * | 2019-01-11 | 2019-04-12 | 郑州大学 | Intelligent garbage bin and refuse classification method based on deep learning |
| CN109928107A (en) * | 2019-04-08 | 2019-06-25 | 江西理工大学 | A kind of automatic classification system |
| CN110263675A (en) * | 2019-06-03 | 2019-09-20 | 武汉联一合立技术有限公司 | Garbage target recognition system and recognition method of community security robot |
| CN110406839A (en) * | 2019-08-30 | 2019-11-05 | 湘潭大学 | Method, apparatus, intelligent garbage bin and the storage medium of Waste sorting recycle |
| CN110466911A (en) * | 2019-04-08 | 2019-11-19 | 江西理工大学 | Automatic sorting garbage bin and classification method |
| CN110562624A (en) * | 2019-09-05 | 2019-12-13 | 索异智能科技(上海)有限公司 | classification dustbin |
| CN110589309A (en) * | 2019-10-28 | 2019-12-20 | 中国矿业大学 | Automatic garbage classification device and method based on machine vision |
| CN110795999A (en) * | 2019-09-21 | 2020-02-14 | 万翼科技有限公司 | Garbage delivery behavior analysis method and related product |
| CN115331129A (en) * | 2022-10-14 | 2022-11-11 | 彼图科技(青岛)有限公司 | Junk data identification method based on unmanned aerial vehicle and artificial intelligence |
-
2017
- 2017-11-14 CN CN201721509769.1U patent/CN208165794U/en not_active Expired - Fee Related
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109368079A (en) * | 2018-12-10 | 2019-02-22 | 浙江梧斯源通信科技股份有限公司 | A kind of automatic garbage classification system and method |
| CN109573383A (en) * | 2018-12-27 | 2019-04-05 | 深兰科技（上海）有限公司 | Dustbin |
| CN109606991B (en) * | 2019-01-11 | 2022-02-08 | 郑州大学 | Intelligent garbage can and garbage classification method based on deep learning |
| CN109606991A (en) * | 2019-01-11 | 2019-04-12 | 郑州大学 | Intelligent garbage bin and refuse classification method based on deep learning |
| CN109516037A (en) * | 2019-01-25 | 2019-03-26 | 李�昊 | A kind of classification garbage can based on machine vision |
| CN109928107A (en) * | 2019-04-08 | 2019-06-25 | 江西理工大学 | A kind of automatic classification system |
| CN110466911A (en) * | 2019-04-08 | 2019-11-19 | 江西理工大学 | Automatic sorting garbage bin and classification method |
| US11436571B2 (en) | 2019-04-08 | 2022-09-06 | Jiangxi University Of Science And Technology | Automatic classification system |
| CN110263675A (en) * | 2019-06-03 | 2019-09-20 | 武汉联一合立技术有限公司 | Garbage target recognition system and recognition method of community security robot |
| CN110263675B (en) * | 2019-06-03 | 2024-02-20 | 武汉联一合立技术有限公司 | Garbage target identification system and method of community security robot |
| CN110406839A (en) * | 2019-08-30 | 2019-11-05 | 湘潭大学 | Method, apparatus, intelligent garbage bin and the storage medium of Waste sorting recycle |
| CN110562624A (en) * | 2019-09-05 | 2019-12-13 | 索异智能科技(上海)有限公司 | classification dustbin |
| CN110795999A (en) * | 2019-09-21 | 2020-02-14 | 万翼科技有限公司 | Garbage delivery behavior analysis method and related product |
| CN110589309A (en) * | 2019-10-28 | 2019-12-20 | 中国矿业大学 | Automatic garbage classification device and method based on machine vision |
| CN115331129A (en) * | 2022-10-14 | 2022-11-11 | 彼图科技(青岛)有限公司 | Junk data identification method based on unmanned aerial vehicle and artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN208165794U (en) | A kind of intelligent classification dustbin | |
| CN109606991B (en) | Intelligent garbage can and garbage classification method based on deep learning | |
| CN109928107B (en) | Automatic classification system | |
| CN109201514B (en) | Waste sorting recycle method, garbage classification device and classified-refuse recovery system | |
| CN110355188B (en) | Smart garbage classification in-situ reduction recycling system based on multiple land utilization | |
| CN110589282A (en) | Intelligent garbage classification method based on machine learning and automatic garbage sorting device | |
| CN104148301A (en) | Waste plastic bottle sorting device and method on basis of cloud computing and image recognition | |
| CN110937280B (en) | Audio-visual combination based intelligent garbage classification and recovery method and terminal | |
| CN111559588A (en) | Intelligent garbage can for classified garbage throwing and classified garbage throwing method | |
| CN110861853B (en) | Intelligent garbage classification method combining vision and touch | |
| CN110040396A (en) | Intelligent garbage bin based on big data, machine learning is made decisions on one's own System and method for | |
| CN201997485U (en) | Garbage auto-separation device | |
| Nafiz et al. | Convowaste: An automatic waste segregation machine using deep learning | |
| CN110466911A (en) | Automatic sorting garbage bin and classification method | |
| Demetriou et al. | Real-time construction demolition waste detection using state-of-the-art deep learning methods; single–stage vs two-stage detectors | |
| CN210847267U (en) | Building solid waste sorting device based on CCD camera and high spectrum camera detection | |
| CN206701918U (en) | A kind of garbage sorting device of Multi-sensor Fusion | |
| CN207929583U (en) | Building waste on-line sorting system based on the detection of dot matrix EO-1 hyperion | |
| CN114715562B (en) | Recognition method for kitchen waste illegal throwing behavior | |
| CN205318622U (en) | Traffic jams controlling means based on image | |
| CN108423332A (en) | The dustbin that automatic classification is delivered | |
| Omar et al. | Multimedia inorganic waste separator | |
| CN104978782B (en) | Passenger flow analysing method based on touch screen technology | |
| CN111079548A (en) | Solid waste online identification method based on target height information and color information | |
| CN112537565B (en) | Household garbage classification collecting and transporting system, device and method based on Internet of things |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20181130 Termination date: 20191114 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |