CN108182455A - A kind of method, apparatus and intelligent garbage bin of the classification of rubbish image intelligent - Google Patents
A kind of method, apparatus and intelligent garbage bin of the classification of rubbish image intelligent Download PDFInfo
- Publication number
- CN108182455A CN108182455A CN201810049145.9A CN201810049145A CN108182455A CN 108182455 A CN108182455 A CN 108182455A CN 201810049145 A CN201810049145 A CN 201810049145A CN 108182455 A CN108182455 A CN 108182455A
- Authority
- CN
- China
- Prior art keywords
- image
- rubbish
- classification
- module
- network model
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Mechanical Engineering (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Health & Medical Sciences (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of method of rubbish image intelligent classification, realization process is to acquire rubbish image by including the high definition collecting device of camera first；The rubbish image of acquisition is pre-processed；Convolution and pondization processing are carried out to pretreated rubbish image, characteristic image extraction is carried out, then characteristic image is identified；According to recognition result, recyclable rubbish classification is determined whether.The method of rubbish image intelligent classification is compared with prior art, can classification be identified to collected rubbish image by camera and image recognition processor, controller, for the purpose of judging whether rubbish is recyclable, without manual sort's rubbish, the environmental consciousness of people is improved, reduces waste pollution, it promotes sustainable development, it is highly practical, it is applied widely, it is easy to spread.
Description
Technical field
The present invention relates to computer application technology, specifically a kind of highly practical, rubbish image intelligent classification
Method, apparatus and intelligent garbage bin.
Background technology
Artificial Intelligence Development speed is getting faster, and the application range of image identification is more and more wider, in Vehicle number plate recognition, machine
There is outstanding behaviours in the fields such as device people and mobile end equipment.The appearance of deep learning method makes the discrimination of image identification significantly
It improves and with more robustness.However the consciousness in current garbage classification is weak, the classification mode of communal facility dustbin is inadequate
Clearly, cause citizen is often unconscious recyclable rubbish is miscarried to not recyclable dustbin or conversely, therefore still needed
Staff rearranges the rubbish of classification garbage can, and garbage reclamation flow is complicated, the effect of garbage classification is not obvious, also
Increase the amount of labour of staff.
Based on this, the present invention propose it is a kind of solve the above problems, the method, apparatus of rubbish image intelligent classification and intelligent rubbish
Rubbish bucket.
Invention content
The technical assignment of the present invention is to be directed to more than shortcoming, provides a kind of highly practical, rubbish image intelligent classification
Method, apparatus and intelligent garbage bin.
A kind of method of rubbish image intelligent classification, realization process be,
First, rubbish image is acquired by including the high definition collecting device of camera first；
2nd, the rubbish image of acquisition is pre-processed；
3rd, convolution is carried out to pretreated rubbish image and pondization is handled, characteristic image extraction is carried out, then to characteristic image
It is identified；
4th, according to recognition result, determine whether recyclable rubbish classification.
Pretreatment in the step 2 refers to carry out enhancing processing to image, and enhancing processing includes noise and eliminates, schemes
As smooth and image sharpening processing procedure, enhancing processing is realized by image recognition processor.
Characteristic image in the step 3 is trained by image recognition processor by neural network model to be obtained, the nerve
Network model is for the neural network model of trained mistake and including following 15 layers：Under cross one another four convolutional layers and four
Sample level, three full articulamentums, three active coatings, a classification layer, wherein, full articulamentum is used for adjustment parameter, makes network more
Stable, active coating is used to improve network speed；In the neural network model, the image pre-processed in step 2 is by intersecting
After convolution and the down-sampling processing of progress, weighting parameter is extracted in the 10th layer of active coating as image by image recognition processor
Feature.
Characteristic image in the step 3 is identified by preset sorter network model realization, which is
The network model trained by characteristic image after characteristic image is obtained, is directly inputted in the sorter network model and completes
Characteristic image is identified, recognition result is then returned into image recognition processor, image recognition processor is according to identification
As a result judge whether recyclable, judge recyclable rubbish classification.
A kind of device of rubbish image intelligent classification, including,
Image capture module acquires rubbish image using the high definition collecting device including camera；
Picture recognition module after the rubbish image for image capture module to be acquired is pre-processed, carries out convolution and pond
Processing completes characteristic image extraction, and characteristic image is identified；
According to the recognition result of picture recognition module, characteristic image is sorted out for graphic collection module：Determine whether to return
Receive rubbish classification.
In described image identification module, pretreatment is carried out to rubbish image and refers to carry out including noise elimination, image smoothing
Enhancing with image sharpening processing procedure is handled.
In described image identification module, characteristic image is extracted, neural network model is passed through by image recognition processor
Training obtains, and the neural network model is for the neural network model of trained mistake and including following 15 layers：Cross one another four
A convolutional layer and four down-sampling layers, three full articulamentums, three active coatings, a classification layer, in the neural network model,
The image of pretreatment extracts the 10th layer of active coating after intersecting the convolution carried out and down-sampling processing by image recognition processor
Feature of the middle weighting parameter as image.
In described image classifying module, characteristic image is sorted out through preset sorter network model realization, the sorter network
Model is the network model trained by characteristic image, after characteristic image is obtained, is directly inputted to the sorter network model
Characteristic image is identified in middle completion, and recognition result then is returned to image recognition processor, image recognition processor root
Judge whether according to recognition result recyclable, judge recyclable rubbish classification.
A kind of intelligent garbage bin, including,
The device of above-mentioned rubbish image intelligent classification, is also configured with control signal mode in the device of rubbish image intelligent classification
Block after the judgement of the device completion rubbish classification of rubbish image intelligent classification, finds corresponding dustbin control device number simultaneously
By the way that signaling module is controlled to be sent to control signal；
Dustbin control device is configured with the signal receiving module being used cooperatively with control signaling module, receives corresponding control
After signal processed, corresponding dustbin bung is opened.
In the dustbin control device also sequence include controller power source module, loudspeaker module, indicating lamp module and
Motor is controlled, wherein, when signal is controlled to be sent in signal receiving module, controller power source module is raised one's voice for reference numeral
Device module, indicating lamp module and control motor power supply, loudspeaker module put into the position of dustbin by voice reminder；Indicator light
Module energization bright light is as prompting；Control motor then opens corresponding dustbin bung.
The method, apparatus and intelligent garbage bin of a kind of rubbish image intelligent classification of the present invention, have the following advantages：
The method, apparatus and intelligent garbage bin of a kind of rubbish image intelligent classification proposed by the present invention, can by camera and
Classification is identified to collected rubbish image in image recognition processor, controller, for the purpose of judging whether rubbish is recyclable,
Without manual sort's rubbish, the environmental consciousness of people is improved, waste pollution is reduced, promotes sustainable development；It is corresponded to by controlling
Voice reminder, the indicator light of type dustbin are reminded and the opening and closing of dustbin cover, so as to simplify garbage reclamation flow, reduces work
Person works measure, highly practical, applied widely, easy to spread.
Description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
The embodiment of invention, for those of ordinary skill in the art, without creative efforts, can also basis
The attached drawing of offer obtains other attached drawings.
Attached drawing 1 is the work flow diagram of intelligent garbage bin according to an embodiment of the invention.
Attached drawing 2 is the method block diagram of intelligent garbage bin image identification classification according to an embodiment of the invention.
Attached drawing 3 is intelligent garbage bin pattern recognition device block diagram according to an embodiment of the invention.
Attached drawing 4 is intelligent garbage bin control device block diagram according to an embodiment of the invention.
Attached drawing 5 is intelligent garbage barrel structure block diagram according to an embodiment of the invention.
Attached drawing 6 is intelligent garbage bin solid master drawing according to an embodiment of the invention.
Attached drawing 7 is neural network model schematic diagram according to an embodiment of the invention.
Specific embodiment
In order to which those skilled in the art is made to more fully understand the present invention program, With reference to embodiment to this hair
It is bright to be described in further detail.Obviously, described embodiment is only part of the embodiment of the present invention rather than whole
Embodiment.Based on the embodiments of the present invention, those of ordinary skill in the art are obtained without making creative work
The every other embodiment obtained, shall fall within the protection scope of the present invention.
It, can be by dustbin it is an object of the invention to propose a kind of method of intelligent garbage bin image identification classification
The collected rubbish image of high definition camera of side identifies rubbish type, according to the type of rubbish according to image processor
Judge whether it is recyclable, judgement belong to which type of recoverable version rubbish.
As shown in attached drawing 1- Fig. 3, Fig. 7, a kind of method of rubbish image intelligent classification, realization process is,
First, rubbish image is acquired by including the high definition collecting device of camera first；
2nd, the rubbish image of acquisition is pre-processed；
3rd, convolution is carried out to pretreated rubbish image and pondization is handled, characteristic image extraction is carried out, then to characteristic image
It is identified；
4th, according to recognition result, determine whether recyclable rubbish classification.
Pretreatment in the step 2 refers to carry out enhancing processing to image, and enhancing processing includes noise and eliminates, schemes
As smooth and image sharpening processing procedure, enhancing processing is realized by image recognition processor.
Characteristic image in the step 3 is trained by image recognition processor by neural network model to be obtained, the nerve
Network model is for the neural network model of trained mistake and including following 15 layers：Under cross one another four convolutional layers and four
Sample level, three full articulamentums, three active coatings, a classification layer, wherein, full articulamentum is used for adjustment parameter, makes network more
Stable, active coating is used to improve network speed；In the neural network model, the image pre-processed in step 2 is by intersecting
After convolution and the down-sampling processing of progress, weighting parameter is extracted in the 10th layer of active coating as image by image recognition processor
Feature.
The feature not only can will preferably describe image, reduce overfitting, it is often more important that also wanting can be fine
Distinguish different classes of image in ground.
A total of 15 layers of the CNN neural network image training patterns that the present invention is built, structure improves discrimination, to rubbish
The identification of rubbish has better stability.Preset sorter network used in the present invention can be a variety of models, according to user's
The quantity with image is needed, different graders can be chosen and be compared, such as support vector machines, radial direction base grader, BP god
Through network, according to the best results of experiment support vector machines, fastest discrimination highest.
Characteristic image in the step 3 is identified by preset sorter network model realization, which is
The network model trained by characteristic image after characteristic image is obtained, is directly inputted in the sorter network model and completes
Characteristic image is identified, recognition result is then returned into image recognition processor, image recognition processor is according to identification
As a result judge whether recyclable, judge recyclable rubbish classification.
As shown in Figure 1, a kind of device of rubbish image intelligent classification, including,
Image capture module acquires rubbish image using the high definition collecting device including camera；
Picture recognition module after the rubbish image for image capture module to be acquired is pre-processed, carries out convolution and pond
Processing completes characteristic image extraction, and characteristic image is identified；
According to the recognition result of picture recognition module, characteristic image is sorted out for graphic collection module：Determine whether to return
Receive rubbish classification.
Generally, rubbish image is acquired by high definition camera.
In described image identification module, pretreatment is carried out to rubbish image and refers to carry out including noise elimination, image smoothing
Enhancing with image sharpening processing procedure is handled.
In described image identification module, characteristic image is extracted, neural network model is passed through by image recognition processor
Training obtains, and the neural network model is for the neural network model of trained mistake and including following 15 layers：Cross one another four
A convolutional layer and four down-sampling layers, three full articulamentums, three active coatings, a classification layer, in the neural network model,
The image of pretreatment extracts the 10th layer of active coating after intersecting the convolution carried out and down-sampling processing by image recognition processor
Feature of the middle weighting parameter as image.
In described image classifying module, characteristic image is sorted out through preset sorter network model realization, the sorter network
Model is the network model trained by characteristic image, after characteristic image is obtained, is directly inputted to the sorter network model
Characteristic image is identified in middle completion, and recognition result then is returned to image recognition processor, image recognition processor root
Judge whether according to recognition result recyclable, judge recyclable rubbish classification.
Image type is divided into recyclable and not recyclable, determines the rubbish for secondary judgement is needed after recyclable to belong to and can return
Which type of type is received, it is finer to classify to recyclable rubbish, battery, made of paper is such as divided into according to recyclable rubbish type
Product, plastic products and other recyclable rubbishes.
As shown in attached drawing 1- Fig. 7, a kind of intelligent garbage bin, including,
The device of above-mentioned rubbish image intelligent classification, is also configured with control signal mode in the device of rubbish image intelligent classification
Block after the judgement of the device completion rubbish classification of rubbish image intelligent classification, finds corresponding dustbin control device number simultaneously
By the way that signaling module is controlled to be sent to control signal；
Dustbin control device is configured with the signal receiving module being used cooperatively with control signaling module, receives corresponding control
After signal processed, corresponding dustbin bung is opened.
The dustbin of the present invention when in use, acquires rubbish image, then by image recognition processor to described first
Rubbish image carries out four times and intersects convolution and down-sampling processing, and rubbish figure is extracted in the 10th layer of active coating of preset neural network
Characteristic image is sent into preset sorter network and is identified and classifies by the characteristic image of picture, final to obtain rubbish image kind
Class.Judged whether according to the type of rubbish it is recyclable, judgement belong to which type of recoverable version rubbish.Thus, it is possible to it obtains
Rubbish image type finds corresponding controller, and control garbage cover is opened, and thus simplifies rubbish manual recovery flow.
In the dustbin control device also sequence include controller power source module, loudspeaker module, indicating lamp module and
Motor is controlled, wherein, when signal is controlled to be sent in signal receiving module, controller power source module is raised one's voice for reference numeral
Device module, indicating lamp module and control motor power supply, loudspeaker module put into the position of dustbin by voice reminder；Indicator light
Module energization bright light is as prompting；Control motor then opens corresponding dustbin bung.
It can be GPU that the device of wherein rubbish image intelligent classification, which includes image recognition processor,
(GraphicsProcessing Unit, graphics processor), conducive to convolution budget SoC (System on Chip, it is system-level
Chip) and chip sensor.
Dustbin control device is microprogram control unit, and microprogram control unit design is convenient, simple in structure, modification or expansion
It is all convenient, the function of a machine instruction is changed, need to only rearrange corresponding microprogram.It is raised with microprogram control unit control peripheral hardware
Sound device, indicator light and motor, motor control bearing.
One dustbin control device controls the dustbin of a type, loudspeaker module in dustbin control device,
Indicating lamp module and control three modules of motor are series connection, and three functions are all realized, while bright light, voice broadcast carry
Wake up and open the lid of corresponding type dustbin.In the process, other controllers do not receive control signal, and acquiescence is to disconnect shape
State, lamp does not work, without voice broadcast and dustbin cover closed state.
In described below, dustbin control device is represented with controller.
M1 acquires rubbish image by image capture module.
In one embodiment of the invention, can rubbish image be acquired by high definition camera in real time（Such as rubbish
Picture）, it should explanation, the high definition camera are mounted on right over dustbin, preferable position at daylighting, with side
Just the rubbish image of high quality is collected.
In addition, it is necessary to the situation for allowing for the darks such as cloudy day and night of explanation, using with flash lamp and sense
The high definition cam device of light device improves the quality of image, improves the discrimination of rubbish.
Specifically, after intelligent garbage bin, which is powered, to be run, high definition camera is in an open state, and photoreceptor is according to light
Whether line traffic control opens flash lighting, when infrared radiation detection apparatus detects hand infrared information, high-definition camera shooting, collecting rubbish
Rubbish image.
In addition, it is necessary to explanation is, it is contemplated that dark, hand shake etc. influence the feelings of imaging and discrimination
Condition, high-definition camera Quick Acquisition three open rubbish image, to ensure the accuracy of Image Acquisition and quality.
In other embodiments of the invention, rubbish image is stored in storage by camera after rubbish image is collected
In equipment, which checks and applies as the people that a record can facilitate waste manager or the record is needed to investigate,
The host CPU (Central Processing Unit, central processing unit) of dustbin is periodically by built-in WIFI in memory
Data upload server and cleanup memory.
M2 is carried out at convolution and down-sampling the rubbish image by the image recognition processor of picture recognition module
Reason, and feature is extracted, the feature is identified according to preset sorter network model classification to obtain the type of rubbish.Its
Process such as Fig. 3.
In an embodiment of the present invention, image know method for distinguishing as shown in Fig. 2, the preset neural network model in total
There are 15 layers, four convolutional layers, four down-sampling layers, three full articulamentums, three active coatings, a classification layer.Convolution is adopted under
Sample, which intersects, to carry out, and full articulamentum is for adjustment parameter, makes network more stable, and active coating is for improving network speed.
Extract feature of the weighting parameter as image in the 10th layer of active coating.The feature not only can will preferably describe image, subtract
Few overfitting, it is often more important that can also distinguish different classes of image well.
In addition, it is necessary to explanation, since image is in gatherer process, is obscured etc. a variety of by light, position and movement
The influence of factor, in order to improve discrimination, image recognition processor first pre-processes rubbish image carries out image identification again,
Preprocessing process includes image enhancement processing, and image enhancement processing includes noise elimination, image smoothing and image sharpening etc..
In an embodiment of the present invention, recognition result is the type of rubbish（For example, banana skin, plastic bottle, battery, ice cream
Rod, toilet paper, polybag etc.）, the preset neural network model was trained by above-mentioned rubbish type.It should illustrate
It is that high-definition camera Quick Acquisition three opens same type of rubbish image, three are sequentially sent to obtain in preset neural network
To recognition result, three results are unanimously determined as rubbish image type, and the consistent other kinds of situation of two results is to tie
Subject to the identical type of fruit, three recognition results are all different, are subject to first recognition result.
Specifically, intelligent garbage bin（That is, the host CPU of intelligent garbage bin）After acquiring rubbish image, by rubbish image transmitting
To image recognition processor, image recognition processor first pre-processes rubbish image, is divided into three steps：Noise is eliminated, image
Smooth and image sharpening, then image recognition processor pretreated rubbish image is rolled up by preset neural network
Long-pending to handle, then down-sampling is handled, and after four convolution and down-sampling cross processing, image is carried out to connect entirely with adjustment parameter,
Using smooth preset function to the image after connecting entirely into line activating to improve network speed, extraction image is sent into preset god
Characteristic parameter is sent into preset sorter network and is identified by the parameter of the active coating after network processes as characteristic parameter.
Three same type of rubbish images, three are sequentially sent to obtain recognition result in preset neural network, three results one
Cause is determined as rubbish image type, the consistent other kinds of situation of two results, is subject to result majority, three identification knots
Fruit is all different, is subject to first recognition result.
It should be noted that the convolution operation in the embodiment is actually with different convolution kernels（Wave filter）With image
Convolution algorithm is carried out, is macroscopically said, when people identifies certain object, it is generally recognized that from the local feature recognition of object to the overall situation
, in addition to this, the characteristic of image is also to contact between similar local pixel more to polymerize, mutually from pixel contact it is weaker.It is logical
It crosses convolution collecting image and integrally carries out convolution, as local sensing, topography's information that convolution goes out repeatedly takes out global letter
Breath, so as to judge.What the feature that goes out of convolution nuclear convolution of this part can be repeated, which be used in, learns other features
On, so same convolution kernel, the principle that as weights are shared in convolution can be selected when selection convolution kernel.
In addition, the down-sampling processing described in the embodiment, i.e., reduce the image pixel after convolution, so as to reach by half
Reduce the purpose of image redundancy.
Convolution and down-sampling processing described in the embodiment are to intersect to carry out, and a secondary volume is carried out to the image of input
After product, down-sampling is carried out, obtained down-sampled images are carried out with the operation of a convolution and down-sampling again, intersects and carries out four times
To characteristic image.
Full connection described in the embodiment can be understood as convolution kernel as one-dimensional convolution, and the characteristic layer of front is with after
The pixel of the characteristic layer in face is one-to-one to be connected, and purpose is adjustment parameter.
It is to be connected entirely with extracting parameter after a preset function activation as characteristic parameter primary in the embodiment, and
Entire preset neural network is performed by the intersection of full connection and preset function activation three times, is constructed described complete pre-
If neural network be to shift to an earlier date training network.
Preset sorter network in the embodiment and preset the neural network network that be two different, sorter network can
To be any network that can carry out Classification and Identification, which trained by characteristic image, therefore also when identification
Input feature vector image is obtained in recognition result deposit memory.
Due to three photos of the same rubbish of shooting in the embodiment, when the continuously identification three of preset Classification and Identification network
After photo, extract three results in memory and be compared, three same type of rubbish images, three be sequentially sent to it is pre-
If neural network in obtain recognition result, three results are unanimously determined as rubbish image type, two results it is consistent one its
The situation of his type, is subject to result majority, and three recognition results are all different, and first recognition result of being subject to is transferred to M3
Image type classifying module.
M3 image type classifying modules according to the recognition result that M2 is transmitted by the type of rubbish be divided into recyclable rubbish and
Not recyclable rubbish, recyclable rubbish type are divided into as four kinds of battery, paper products, plastic products and other recyclable rubbishes, root
According to output result result is exported to M4 control signaling modules.
Specifically, judging the step of which type rubbish belong to here is：All rubbish recognition results are returned according to classification
It is respectively that recyclable rubbish, battery, paper products, plastic products and other recyclable rubbishes, such as milk box do not give up for five matrixes
The paper products such as carton, toilet paper are with a matrix type as data, when the input results of M2 are compared with character string forms, when
It compares the character string for successfully exporting corresponding type and is passed to M4 control signaling modules as result is exported.
M4-M9 processes as shown in figure 4,
The result of dustbin type that M4 control signaling modules are transmitted according to M3 is connect using chip with sensor sends out control letter
Number it is transmitted to corresponding kind of quasi-controller M5.
M5 receives signaling module and receives the controller signals that M4 is sent, and handles signal and M6 controller power sources is controlled to connect.
M6 controller power source modules are responsible for controlling the opening and closing of power supply, power on after signal is received 45 seconds, disconnect later
Power supply.The opening/closing time of dustbin cover is controlled with this, power-off can be with energy-saving and emission-reduction in time.
After M7 loudspeaker modules power supply is connected, voice reminder is sent out by loud speaker, such as：Not recyclable rubbish please throw to
Corresponding type dustbin.
Specifically, the type of rubbish is taken out from memory（Not recyclable rubbish, battery, paper products, plastic products and its
His recyclable rubbish）In addition it please throw to corresponding type dustbin.
M8 indicating lamp modules control the connection of power supply according to M6, and connection circuit control light bulb is bright, and the color of lamp is according to can return
Receipts green is not recyclable good in dustbin advancer with yellow.
M9 bung die opening and closing root tubers are connected according to M6 control power supplys, and operation motor opens dustbin cover, dustbin by bearing
It is full open position that lid, which snaps into card slot, timing 30 seconds since full open position, and motor closes dustbin cover by bearing,
Different classes of dustbin is obscured to avoid passerby.
To sum up, the design frame chart of whole dustbin according to intelligent garbage bin as shown in figure 5, such as include identification rubbish type
Method, dustbin image identification and control device realize it is a kind of intelligence recycling dustbin, first acquire rubbish image, secondly
The rubbish image is carried out to intersect convolution and down-sampling processing four times by described image recognition processor, in preset nerve
The characteristic image of the 10th layer of active coating extraction rubbish image of network, characteristic image is sent into preset sorter network and is known
Not and classify, the final rubbish image type that obtains is to control the opening and closing of dustbin, so as to which dustbin be made to be recycled with intelligent classification
Effect, have the function that energy-saving and emission-reduction.
As shown in fig. 6, L is dustbin, L1 is not recyclable dustbin for the three-dimensional master drawing of dustbin, L2, L3, L4, L5 according to
It is secondary to recycle dustbin, dustbin bracket for other recyclable rubbish buckets, battery recycling dustbin, plastics recovery dustbin, the scraps of paper
Intermediate circle S represents infrared camera, and coupled R is image recognition processor, and connection is put inside dustbin bracket
Power cord, be connected with the controller K of the dustbin of various species, controller and D are dustbin cover bearing and G is dustbin
Lid motor is connected, and is in addition to this connected with indicator light and loud speaker Y, when the power is turned on, indicator light, loud speaker and motor, axis
Hold series connection running.
The foregoing is merely presently preferred embodiments of the present invention, and scope of patent protection of the invention includes but not limited to above-mentioned tool
Body embodiment, all within the spirits and principles of the present invention, any modification, equivalent substitution, improvement and etc. done should all include
Within the scope of patent protection of the present invention.
The those skilled in the art can readily realize the present invention with the above specific embodiments,.Herein
It applies specific case to be expounded the principle of the present invention and embodiment, the explanation of above example is only intended to help
Understand the method and its core concept of the present invention.It should be pointed out that it for those skilled in the art, is not taking off
Under the premise of from the principle of the invention, can also to the present invention, some improvement and modification can also be carried out, these improvement and modification also fall into this
In invention scope of the claims.
Claims (10)
1. a kind of method of rubbish image intelligent classification, which is characterized in that its realization process is,
First, rubbish image is acquired by including the high definition collecting device of camera first；
2nd, the rubbish image of acquisition is pre-processed；
3rd, convolution is carried out to pretreated rubbish image and pondization is handled, characteristic image extraction is carried out, then to characteristic image
It is identified；
4th, according to recognition result, determine whether recyclable rubbish classification.
2. the method for a kind of rubbish image intelligent classification according to claim 1, which is characterized in that in the step 2
It pre-processes and refers to carry out enhancing processing to image, enhancing processing includes noise elimination, image smoothing and image sharpening and processes
Journey, enhancing processing are realized by image recognition processor.
3. the method for a kind of rubbish image intelligent classification according to claim 1, which is characterized in that in the step 3
Characteristic image is trained by neural network model by image recognition processor and obtained, which is trained mistake
Neural network model and including following 15 layers：Cross one another four convolutional layers and four down-sampling layers, three full articulamentum, three
A active coating, a classification layer, wherein, full articulamentum is used for adjustment parameter, makes network more stable, and active coating is used to improve net
Network speed；In the neural network model, the image pre-processed in step 2 is by intersecting the convolution carried out and down-sampling processing
Afterwards, feature of the weighting parameter as image in the 10th layer of active coating is extracted by image recognition processor.
4. the method for a kind of rubbish image intelligent classification according to claim 1, which is characterized in that in the step 3
Characteristic image is identified by preset sorter network model realization, which is the net trained by characteristic image
Network model after characteristic image is obtained, is directly inputted in the sorter network model and completes that characteristic image is identified, then
Recognition result is returned into image recognition processor, image recognition processor judges whether recyclable, judgement according to recognition result
Recyclable rubbish classification.
5. a kind of device of rubbish image intelligent classification, which is characterized in that including,
Image capture module acquires rubbish image using the high definition collecting device including camera；
Picture recognition module after the rubbish image for image capture module to be acquired is pre-processed, carries out convolution and pond
Processing completes characteristic image extraction, and characteristic image is identified；
According to the recognition result of picture recognition module, characteristic image is sorted out for graphic collection module：Determine whether to return
Receive rubbish classification.
6. the device of a kind of rubbish image intelligent classification according to claim 5, which is characterized in that described image identifies mould
In block, pretreatment is carried out to rubbish image and refers to the increasing for carrying out including noise elimination, image smoothing and image sharpening processing procedure
It manages strength.
7. the device of a kind of rubbish image intelligent classification according to claim 5, which is characterized in that described image identifies mould
In block, characteristic image is extracted, acquisition, the neural network mould are trained by neural network model by image recognition processor
Type is for the neural network model of trained mistake and including following 15 layers：Cross one another four convolutional layers and four down-samplings
Layer, three full articulamentums, three active coatings, a classification layer, in the neural network model, the image of pretreatment is by intersecting
After convolution and the down-sampling processing of progress, weighting parameter is extracted in the 10th layer of active coating as image by image recognition processor
Feature.
8. the device of a kind of rubbish image intelligent classification according to claim 5, which is characterized in that described image sorts out mould
In block, characteristic image is sorted out through preset sorter network model realization, and the sorter network model is trains by characteristic image
The network model crossed after characteristic image is obtained, is directly inputted in the sorter network model and completes to know characteristic image
Not, recognition result is then returned into image recognition processor, image recognition processor judges whether to return according to recognition result
It receives, judges recyclable rubbish classification.
9. a kind of intelligent garbage bin, which is characterized in that including,
The device of above-mentioned rubbish image intelligent classification, is also configured with control signal mode in the device of rubbish image intelligent classification
Block after the judgement of the device completion rubbish classification of rubbish image intelligent classification, finds corresponding dustbin control device number simultaneously
By the way that signaling module is controlled to be sent to control signal；
Dustbin control device is configured with the signal receiving module being used cooperatively with control signaling module, receives corresponding control
After signal processed, corresponding dustbin bung is opened.
10. a kind of intelligent garbage bin according to claim 9, which is characterized in that also suitable in the dustbin control device
Sequence includes controller power source module, loudspeaker module, indicating lamp module and control motor, wherein, when control signal is sent to letter
When in number receiving module, controller power source module is the loudspeaker module of reference numeral, indicating lamp module and control motor power supply,
Loudspeaker module puts into the position of dustbin by voice reminder；Indicating lamp module energization bright light is as prompting；Control motor then
Open corresponding dustbin bung.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810049145.9A CN108182455A (en) | 2018-01-18 | 2018-01-18 | A kind of method, apparatus and intelligent garbage bin of the classification of rubbish image intelligent |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810049145.9A CN108182455A (en) | 2018-01-18 | 2018-01-18 | A kind of method, apparatus and intelligent garbage bin of the classification of rubbish image intelligent |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108182455A true CN108182455A (en) | 2018-06-19 |
Family
ID=62550923
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810049145.9A Pending CN108182455A (en) | 2018-01-18 | 2018-01-18 | A kind of method, apparatus and intelligent garbage bin of the classification of rubbish image intelligent |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108182455A (en) |
Cited By (55)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108820647A (en) * | 2018-08-30 | 2018-11-16 | 深圳市研本品牌设计有限公司 | Rubbish put-on method and system based on image recognition |
| CN109190691A (en) * | 2018-08-20 | 2019-01-11 | 小黄狗环保科技有限公司 | The method of waste drinking bottles and pop can Classification and Identification based on deep neural network |
| CN109250353A (en) * | 2018-08-30 | 2019-01-22 | 深圳市研本品牌设计有限公司 | A kind of dustbin and storage medium with image identification function |
| CN109573396A (en) * | 2018-10-09 | 2019-04-05 | 董卫华 | A kind of classification of images dustbin |
| CN109606991A (en) * | 2019-01-11 | 2019-04-12 | 郑州大学 | Intelligent garbage bin and refuse classification method based on deep learning |
| CN109635795A (en) * | 2018-10-22 | 2019-04-16 | 小黄狗环保科技有限公司 | A kind of Intelligent supplemental lighting method improving Bottle & Can discrimination based on VGG16 network model |
| CN109684979A (en) * | 2018-12-18 | 2019-04-26 | 深圳云天励飞技术有限公司 | A kind of refuse classification method based on image recognition technology, device and electronic equipment |
| CN109696258A (en) * | 2019-01-11 | 2019-04-30 | 黄永芹 | Environmentally friendly big data mechanism for monitoring |
| CN109753890A (en) * | 2018-12-18 | 2019-05-14 | 吉林大学 | A kind of pavement garbage object intelligent recognition and cognitive method and its realization device |
| CN109940024A (en) * | 2019-03-22 | 2019-06-28 | 深兰科技（上海）有限公司 | The method and recyclable device that a kind of pair of waste is classified |
| CN109987364A (en) * | 2019-05-17 | 2019-07-09 | 贵州大学 | A kind of New Intelligent Garbage Can and its control method |
| CN110001875A (en) * | 2019-03-22 | 2019-07-12 | 中国科学院合肥物质科学研究院 | It is a kind of to be cleaned and the water surface robot classified and Refloatation method of classifying for garbage on water |
| CN110008961A (en) * | 2019-04-01 | 2019-07-12 | 深圳市华付信息技术有限公司 | Text real-time identification method, device, computer equipment and storage medium |
| CN110053897A (en) * | 2019-05-09 | 2019-07-26 | 苏州博学智能科技有限公司 | A kind of Intelligent classification dustbin |
| CN110210635A (en) * | 2019-06-05 | 2019-09-06 | 周皓冉 | A kind of intelligent classification recovery system that can identify waste |
| CN110371531A (en) * | 2019-07-12 | 2019-10-25 | 上海电机学院 | A kind of Intelligent refuse classification station |
| 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 |
| CN110414409A (en) * | 2019-07-24 | 2019-11-05 | 上海工程技术大学 | A kind of cell automatic garbage classification intelligent garbage bin |
| CN110427896A (en) * | 2019-08-07 | 2019-11-08 | 成都理工大学 | A kind of garbage classification intelligence system based on convolutional neural networks |
| CN110466911A (en) * | 2019-04-08 | 2019-11-19 | 江西理工大学 | Automatic sorting garbage bin and classification method |
| CN110503041A (en) * | 2019-08-23 | 2019-11-26 | 珠海格力电器股份有限公司 | Method for identifying garbage category of garbage, terminal device and storage medium |
| CN110597251A (en) * | 2019-09-03 | 2019-12-20 | 三星电子（中国）研发中心 | Method and device for controlling intelligent mobile equipment |
| CN110589285A (en) * | 2019-09-17 | 2019-12-20 | 西安咏圣达电子科技有限公司 | Visual garbage classification auxiliary system, method and device based on artificial intelligence |
| CN110602446A (en) * | 2019-08-26 | 2019-12-20 | 恒大智慧科技有限公司 | Garbage recovery reminding method and system and storage medium |
| CN110606292A (en) * | 2019-09-17 | 2019-12-24 | 蔡亦圣 | Automatic classification garbage can based on artificial intelligence and classification method |
| CN110626662A (en) * | 2019-10-12 | 2019-12-31 | 张颢宸 | Image recognition-based garbage self-classification method and device |
| CN110683240A (en) * | 2019-10-30 | 2020-01-14 | 西安航空学院 | Garbage classification processing system based on image processing |
| CN110694934A (en) * | 2019-09-01 | 2020-01-17 | 阿尔飞思(昆山)智能物联科技有限公司 | Intelligent dry garbage classification cloud system and working method thereof |
| CN110697273A (en) * | 2019-08-27 | 2020-01-17 | 酆雨舟 | Intelligent household garbage identification and automatic classification system and method based on iterative learning control |
| CN110723431A (en) * | 2019-09-19 | 2020-01-24 | 太原理工大学 | Garbage classification method based on BP neural network recognition system |
| CN110723432A (en) * | 2019-09-20 | 2020-01-24 | 精锐视觉智能科技（深圳）有限公司 | Garbage classification method and augmented reality equipment |
| CN110738131A (en) * | 2019-09-20 | 2020-01-31 | 广州游艺云物联网技术有限公司 | Garbage classification management method and device based on deep learning neural network |
| CN110803406A (en) * | 2019-10-18 | 2020-02-18 | 宁波大学 | Intelligent classification dustbin based on degree of depth study |
| CN110851866A (en) * | 2019-11-12 | 2020-02-28 | 福建福链科技有限公司 | Garbage classification method and system based on block chain |
| CN110852263A (en) * | 2019-11-11 | 2020-02-28 | 北京智能工场科技有限公司 | Mobile phone photographing garbage classification recognition method based on artificial intelligence |
| CN110921146A (en) * | 2019-11-28 | 2020-03-27 | 蚌埠学院 | Household garbage classification method and system based on internet big data and image processing technology |
| CN110991271A (en) * | 2019-11-15 | 2020-04-10 | 万翼科技有限公司 | Garbage classification processing method and related products |
| CN111010492A (en) * | 2018-10-08 | 2020-04-14 | 瑞昱半导体股份有限公司 | Image processing circuit and related image processing method |
| CN111056183A (en) * | 2019-11-29 | 2020-04-24 | 华东师范大学 | Real-time intelligent garbage self-classification system based on ZYNQ |
| CN111160186A (en) * | 2019-12-20 | 2020-05-15 | 上海寒武纪信息科技有限公司 | Intelligent garbage classification processing method and related products |
| CN111241967A (en) * | 2020-01-06 | 2020-06-05 | 珠海格力电器股份有限公司 | Garbage classification method, system, terminal equipment and storage medium |
| CN111361877A (en) * | 2020-01-23 | 2020-07-03 | 杭州睿杨环境科技有限公司 | Intelligent garbage classification terminal processor |
| CN111453247A (en) * | 2020-03-13 | 2020-07-28 | 江苏美的清洁电器股份有限公司 | Garbage classification method and intelligent household appliance |
| CN111517034A (en) * | 2020-05-09 | 2020-08-11 | 安徽工程大学 | Automatic classification garbage can and classification method and system thereof |
| WO2021056975A1 (en) * | 2019-09-26 | 2021-04-01 | 五邑大学 | Method and apparatus for automatic waste sorting, and storage medium |
| CN112777170A (en) * | 2020-12-28 | 2021-05-11 | 中标慧安信息技术股份有限公司 | Garbage classification system |
| US11014742B2 (en) | 2018-08-03 | 2021-05-25 | Beijing Xiaomi Mobile Software Co., Ltd. | Method and device for collecting garbage |
| CN112827846A (en) * | 2021-01-04 | 2021-05-25 | 西安建筑科技大学 | Automatic garbage classification device and method |
| CN112911209A (en) * | 2020-11-21 | 2021-06-04 | 泰州无印广告传媒有限公司 | LED display array driving system and method |
| CN112949633A (en) * | 2021-03-05 | 2021-06-11 | 中国科学院光电技术研究所 | Improved YOLOv 3-based infrared target detection method |
| CN113173349A (en) * | 2021-05-06 | 2021-07-27 | 上海市格致中学 | Garbage classification system and method |
| CN113362333A (en) * | 2021-07-07 | 2021-09-07 | 李有俊 | Garbage classification box management method and device |
| CN114873097A (en) * | 2022-04-11 | 2022-08-09 | 青岛理工大学 | Intelligent classification garbage bin based on object recognition |
| CN115187969A (en) * | 2022-09-14 | 2022-10-14 | 河南工学院 | Lead-acid battery recovery system and method based on visual identification |
| CN115890699A (en) * | 2022-11-04 | 2023-04-04 | 爱凤环环保科技有限公司 | Interactive garbage classification supervises and leads robot |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101767702A (en) * | 2010-01-07 | 2010-07-07 | 北京理工大学 | Intelligent garbage classification collecting device and method |
| CN106000904A (en) * | 2016-05-26 | 2016-10-12 | 北京新长征天高智机科技有限公司 | Automatic sorting system for household refuse |
| CN106845408A (en) * | 2017-01-21 | 2017-06-13 | 浙江联运知慧科技有限公司 | A kind of street refuse recognition methods under complex environment |
| CN106874954A (en) * | 2017-02-20 | 2017-06-20 | 佛山市络思讯科技有限公司 | The method and relevant apparatus of a kind of acquisition of information |
| CN107133650A (en) * | 2017-05-10 | 2017-09-05 | 合肥华凌股份有限公司 | Food recognition methods, device and the refrigerator of refrigerator |
-
2018
- 2018-01-18 CN CN201810049145.9A patent/CN108182455A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101767702A (en) * | 2010-01-07 | 2010-07-07 | 北京理工大学 | Intelligent garbage classification collecting device and method |
| CN106000904A (en) * | 2016-05-26 | 2016-10-12 | 北京新长征天高智机科技有限公司 | Automatic sorting system for household refuse |
| CN106845408A (en) * | 2017-01-21 | 2017-06-13 | 浙江联运知慧科技有限公司 | A kind of street refuse recognition methods under complex environment |
| CN106874954A (en) * | 2017-02-20 | 2017-06-20 | 佛山市络思讯科技有限公司 | The method and relevant apparatus of a kind of acquisition of information |
| CN107133650A (en) * | 2017-05-10 | 2017-09-05 | 合肥华凌股份有限公司 | Food recognition methods, device and the refrigerator of refrigerator |
Cited By (68)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109250342B (en) * | 2018-08-03 | 2021-08-31 | 北京小米移动软件有限公司 | Garbage collection method and device |
| US11014742B2 (en) | 2018-08-03 | 2021-05-25 | Beijing Xiaomi Mobile Software Co., Ltd. | Method and device for collecting garbage |
| CN109190691A (en) * | 2018-08-20 | 2019-01-11 | 小黄狗环保科技有限公司 | The method of waste drinking bottles and pop can Classification and Identification based on deep neural network |
| CN109250353A (en) * | 2018-08-30 | 2019-01-22 | 深圳市研本品牌设计有限公司 | A kind of dustbin and storage medium with image identification function |
| CN108820647A (en) * | 2018-08-30 | 2018-11-16 | 深圳市研本品牌设计有限公司 | Rubbish put-on method and system based on image recognition |
| CN111010492A (en) * | 2018-10-08 | 2020-04-14 | 瑞昱半导体股份有限公司 | Image processing circuit and related image processing method |
| CN111010492B (en) * | 2018-10-08 | 2022-05-13 | 瑞昱半导体股份有限公司 | Image processing circuit and related image processing method |
| CN109573396A (en) * | 2018-10-09 | 2019-04-05 | 董卫华 | A kind of classification of images dustbin |
| CN109635795B (en) * | 2018-10-22 | 2023-05-16 | 小黄狗环保科技有限公司 | Intelligent light supplementing method for improving bottle and tank recognition rate based on VGG16 network model |
| CN109635795A (en) * | 2018-10-22 | 2019-04-16 | 小黄狗环保科技有限公司 | A kind of Intelligent supplemental lighting method improving Bottle & Can discrimination based on VGG16 network model |
| CN109753890A (en) * | 2018-12-18 | 2019-05-14 | 吉林大学 | A kind of pavement garbage object intelligent recognition and cognitive method and its realization device |
| CN109684979A (en) * | 2018-12-18 | 2019-04-26 | 深圳云天励飞技术有限公司 | A kind of refuse classification method based on image recognition technology, device and electronic equipment |
| CN109753890B (en) * | 2018-12-18 | 2022-09-23 | 吉林大学 | Intelligent recognition and sensing method for road surface garbage and implementation device thereof |
| CN109606991A (en) * | 2019-01-11 | 2019-04-12 | 郑州大学 | Intelligent garbage bin and refuse classification method based on deep learning |
| CN109606991B (en) * | 2019-01-11 | 2022-02-08 | 郑州大学 | Intelligent garbage can and garbage classification method based on deep learning |
| CN109696258A (en) * | 2019-01-11 | 2019-04-30 | 黄永芹 | Environmentally friendly big data mechanism for monitoring |
| CN110001875B (en) * | 2019-03-22 | 2024-04-12 | 中国科学院合肥物质科学研究院 | Water surface robot for cleaning and classifying water surface garbage and classified salvaging method |
| CN110001875A (en) * | 2019-03-22 | 2019-07-12 | 中国科学院合肥物质科学研究院 | It is a kind of to be cleaned and the water surface robot classified and Refloatation method of classifying for garbage on water |
| CN109940024A (en) * | 2019-03-22 | 2019-06-28 | 深兰科技（上海）有限公司 | The method and recyclable device that a kind of pair of waste is classified |
| CN110008961A (en) * | 2019-04-01 | 2019-07-12 | 深圳市华付信息技术有限公司 | Text real-time identification method, device, computer equipment and storage medium |
| CN110466911A (en) * | 2019-04-08 | 2019-11-19 | 江西理工大学 | Automatic sorting garbage bin and classification method |
| CN110053897A (en) * | 2019-05-09 | 2019-07-26 | 苏州博学智能科技有限公司 | A kind of Intelligent classification dustbin |
| CN109987364A (en) * | 2019-05-17 | 2019-07-09 | 贵州大学 | A kind of New Intelligent Garbage Can and its control method |
| CN110210635A (en) * | 2019-06-05 | 2019-09-06 | 周皓冉 | A kind of intelligent classification recovery system that can identify waste |
| CN110371531A (en) * | 2019-07-12 | 2019-10-25 | 上海电机学院 | A kind of Intelligent refuse classification station |
| CN110414409A (en) * | 2019-07-24 | 2019-11-05 | 上海工程技术大学 | A kind of cell automatic garbage classification intelligent garbage bin |
| CN110427896A (en) * | 2019-08-07 | 2019-11-08 | 成都理工大学 | A kind of garbage classification intelligence system based on convolutional neural networks |
| CN110503041A (en) * | 2019-08-23 | 2019-11-26 | 珠海格力电器股份有限公司 | Method for identifying garbage category of garbage, terminal device and storage medium |
| CN110602446A (en) * | 2019-08-26 | 2019-12-20 | 恒大智慧科技有限公司 | Garbage recovery reminding method and system and storage medium |
| CN110697273B (en) * | 2019-08-27 | 2023-12-01 | 酆雨舟 | Household garbage intelligent recognition and automatic classification system and method based on iterative learning control |
| CN110697273A (en) * | 2019-08-27 | 2020-01-17 | 酆雨舟 | Intelligent household garbage identification and automatic classification system and method based on iterative learning control |
| 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 |
| CN110694934A (en) * | 2019-09-01 | 2020-01-17 | 阿尔飞思(昆山)智能物联科技有限公司 | Intelligent dry garbage classification cloud system and working method thereof |
| CN110597251A (en) * | 2019-09-03 | 2019-12-20 | 三星电子（中国）研发中心 | Method and device for controlling intelligent mobile equipment |
| CN110606292A (en) * | 2019-09-17 | 2019-12-24 | 蔡亦圣 | Automatic classification garbage can based on artificial intelligence and classification method |
| CN110589285A (en) * | 2019-09-17 | 2019-12-20 | 西安咏圣达电子科技有限公司 | Visual garbage classification auxiliary system, method and device based on artificial intelligence |
| CN110723431A (en) * | 2019-09-19 | 2020-01-24 | 太原理工大学 | Garbage classification method based on BP neural network recognition system |
| CN110738131A (en) * | 2019-09-20 | 2020-01-31 | 广州游艺云物联网技术有限公司 | Garbage classification management method and device based on deep learning neural network |
| CN110723432A (en) * | 2019-09-20 | 2020-01-24 | 精锐视觉智能科技（深圳）有限公司 | Garbage classification method and augmented reality equipment |
| WO2021056975A1 (en) * | 2019-09-26 | 2021-04-01 | 五邑大学 | Method and apparatus for automatic waste sorting, and storage medium |
| CN110626662A (en) * | 2019-10-12 | 2019-12-31 | 张颢宸 | Image recognition-based garbage self-classification method and device |
| CN110803406A (en) * | 2019-10-18 | 2020-02-18 | 宁波大学 | Intelligent classification dustbin based on degree of depth study |
| CN110683240A (en) * | 2019-10-30 | 2020-01-14 | 西安航空学院 | Garbage classification processing system based on image processing |
| CN110852263B (en) * | 2019-11-11 | 2021-08-03 | 北京智能工场科技有限公司 | Mobile phone photographing garbage classification recognition method based on artificial intelligence |
| CN110852263A (en) * | 2019-11-11 | 2020-02-28 | 北京智能工场科技有限公司 | Mobile phone photographing garbage classification recognition method based on artificial intelligence |
| CN110851866A (en) * | 2019-11-12 | 2020-02-28 | 福建福链科技有限公司 | Garbage classification method and system based on block chain |
| CN110991271A (en) * | 2019-11-15 | 2020-04-10 | 万翼科技有限公司 | Garbage classification processing method and related products |
| CN110921146A (en) * | 2019-11-28 | 2020-03-27 | 蚌埠学院 | Household garbage classification method and system based on internet big data and image processing technology |
| CN111056183B (en) * | 2019-11-29 | 2021-10-15 | 华东师范大学 | Real-time intelligent garbage self-classification system based on ZYNQ |
| CN111056183A (en) * | 2019-11-29 | 2020-04-24 | 华东师范大学 | Real-time intelligent garbage self-classification system based on ZYNQ |
| CN111160186A (en) * | 2019-12-20 | 2020-05-15 | 上海寒武纪信息科技有限公司 | Intelligent garbage classification processing method and related products |
| CN111160186B (en) * | 2019-12-20 | 2023-05-19 | 上海寒武纪信息科技有限公司 | Intelligent garbage classification processing method and related products |
| CN111241967A (en) * | 2020-01-06 | 2020-06-05 | 珠海格力电器股份有限公司 | Garbage classification method, system, terminal equipment and storage medium |
| CN111241967B (en) * | 2020-01-06 | 2023-08-15 | 珠海格力电器股份有限公司 | Garbage classification method, garbage classification device, terminal equipment and storage medium |
| CN111361877A (en) * | 2020-01-23 | 2020-07-03 | 杭州睿杨环境科技有限公司 | Intelligent garbage classification terminal processor |
| CN111453247A (en) * | 2020-03-13 | 2020-07-28 | 江苏美的清洁电器股份有限公司 | Garbage classification method and intelligent household appliance |
| CN111517034A (en) * | 2020-05-09 | 2020-08-11 | 安徽工程大学 | Automatic classification garbage can and classification method and system thereof |
| CN112911209A (en) * | 2020-11-21 | 2021-06-04 | 泰州无印广告传媒有限公司 | LED display array driving system and method |
| CN112777170B (en) * | 2020-12-28 | 2021-10-26 | 中标慧安信息技术股份有限公司 | Garbage classification system |
| CN112777170A (en) * | 2020-12-28 | 2021-05-11 | 中标慧安信息技术股份有限公司 | Garbage classification system |
| CN112827846A (en) * | 2021-01-04 | 2021-05-25 | 西安建筑科技大学 | Automatic garbage classification device and method |
| CN112827846B (en) * | 2021-01-04 | 2023-08-22 | 西安建筑科技大学 | Automatic garbage classification device and method |
| CN112949633A (en) * | 2021-03-05 | 2021-06-11 | 中国科学院光电技术研究所 | Improved YOLOv 3-based infrared target detection method |
| CN113173349A (en) * | 2021-05-06 | 2021-07-27 | 上海市格致中学 | Garbage classification system and method |
| CN113362333A (en) * | 2021-07-07 | 2021-09-07 | 李有俊 | Garbage classification box management method and device |
| CN114873097A (en) * | 2022-04-11 | 2022-08-09 | 青岛理工大学 | Intelligent classification garbage bin based on object recognition |
| CN115187969A (en) * | 2022-09-14 | 2022-10-14 | 河南工学院 | Lead-acid battery recovery system and method based on visual identification |
| CN115890699A (en) * | 2022-11-04 | 2023-04-04 | 爱凤环环保科技有限公司 | Interactive garbage classification supervises and leads robot |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108182455A (en) | A kind of method, apparatus and intelligent garbage bin of the classification of rubbish image intelligent | |
| CN109606991B (en) | Intelligent garbage can and garbage classification method based on deep learning | |
| CN110697273B (en) | Household garbage intelligent recognition and automatic classification system and method based on iterative learning control | |
| CN109344894A (en) | Garbage classification recognition methods and device based on Multi-sensor Fusion and deep learning | |
| US11335086B2 (en) | Methods and electronic devices for automated waste management | |
| CN108509978A (en) | The multi-class targets detection method and model of multi-stage characteristics fusion based on CNN | |
| CN111974704A (en) | Garbage classification detection system and method based on computer vision | |
| CN111186656A (en) | Target garbage classification method and intelligent garbage can | |
| CN110163069B (en) | Lane line detection method for driving assistance | |
| CN110427800A (en) | Video object acceleration detection method, apparatus, server and storage medium | |
| CN107600791A (en) | Interactive automatic garbage classification collection box | |
| CN103324955A (en) | Pedestrian detection method based on video processing | |
| CN110228673A (en) | A kind of intelligent classification dustbin | |
| CN112707058B (en) | Detection method, system, device and medium for standard actions of kitchen waste | |
| CN111517034A (en) | Automatic classification garbage can and classification method and system thereof | |
| CN110466911A (en) | Automatic sorting garbage bin and classification method | |
| CN109871789A (en) | Vehicle checking method under a kind of complex environment based on lightweight neural network | |
| CN108537751A (en) | A kind of Thyroid ultrasound image automatic segmentation method based on radial base neural net | |
| CN109886086A (en) | Pedestrian detection method based on HOG feature and Linear SVM cascade classifier | |
| CN105718947B (en) | Lung Cancer Images sophisticated category method based on LBP and wavelet moment fusion feature | |
| CN111874487A (en) | Environment-friendly garbage bin that possesses automatic waste classification | |
| Mitra | Detection of waste materials using deep learning and image processing | |
| CN107545257A (en) | A kind of automatic target recognition method based on loading pre-training convolutional network | |
| CN113705638A (en) | Mobile vehicle-mounted intelligent garbage information management method and system | |
| CN110155556A (en) | A kind of intelligent classification 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180619 |