CN109684979A - A kind of refuse classification method based on image recognition technology, device and electronic equipment - Google Patents
A kind of refuse classification method based on image recognition technology, device and electronic equipment Download PDFInfo
- Publication number
- CN109684979A CN109684979A CN201811554844.5A CN201811554844A CN109684979A CN 109684979 A CN109684979 A CN 109684979A CN 201811554844 A CN201811554844 A CN 201811554844A CN 109684979 A CN109684979 A CN 109684979A
- Authority
- CN
- China
- Prior art keywords
- rubbish
- sorted
- identified
- ratio
- preset
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/20—Scenes; Scene-specific elements in augmented reality scenes
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65F—GATHERING OR REMOVAL OF DOMESTIC OR LIKE REFUSE
- B65F1/00—Refuse receptacles; Accessories therefor
- B65F1/10—Refuse receptacles; Accessories therefor with refuse filling means, e.g. air-locks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mechanical Engineering (AREA)
- Multimedia (AREA)
- Processing Of Solid Wastes (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to image identification technical fields, disclose a kind of refuse classification method based on image recognition technology, device and electronic equipment, for being identified in dustbin to the rubbish to be sorted of dispensing, this method comprises: standby mode judges in rubbish identification region with the presence or absence of rubbish to be sorted;If acquiring the image information of rubbish to be sorted in the rubbish identification region by camera there are rubbish to be sorted in the rubbish identification region;Described image information and preset garbage classification model are subjected to match cognization, judge that identified rubbish accounts for the ratio of the rubbish to be sorted;If the ratio reaches preset proportion threshold value, the control information for opening flip lid is sent to dustbin cover control device.The present invention may be implemented quickly, accurately identify rubbish type, improve the recognition efficiency classified to rubbish.
Description
Technical field
The present invention relates to image identification technical field more particularly to a kind of garbage classification sides based on image recognition technology
Method, device and electronic equipment.
Background technique
Garbage classification is the reform to garbage collection disposition traditional approach, is a kind of science effectively disposed to rubbish
Management method.How the situation that people deteriorate in face of growing Municipal Garbage Yield and environmental aspect passes through garbage classification management,
It realizes that waste resources utilize, and reduce refuse disposal amount to the maximum extent, improves living environment quality, be that our times various countries are common
One of pressing issues of concern.
However, existing various refuse classification methods are complicated, people lack the full knowledge of garbage classification, it is difficult in short-term
Interior to form good garbage classification habit, it is even more impossible to accurately remember and judge which kind of class complicated numerous rubbish belong to actually
Type launches discarding to correspond to Accurate classification, poses a big pressure to urban environment and garbage disposal.Each classification caused by this
Dustbin is not carried out due garbage classification effect, causes very big burden for subsequent garbage disposal work.As it can be seen that in rubbish
There is garbage classification low efficiency in classification aspect.
Summary of the invention
The problem of the purpose of the present invention is to solve above-mentioned garbage classification low efficiencys of the existing technology, provides one kind
Refuse classification method, device and electronic equipment based on image recognition technology.
The purpose of the present invention is achieved through the following technical solutions:
In a first aspect, the embodiment of the present invention provides a kind of refuse classification method based on image recognition technology, comprising steps of
Standby mode judges in rubbish identification region with the presence or absence of rubbish to be sorted;
If there are rubbish to be sorted in the rubbish identification region, acquired in the rubbish identification region by camera
The image information of rubbish to be sorted;
Described image information and preset garbage classification model are subjected to match cognization, judge identified rubbish account for it is described to
The ratio of sorting rubbish;
If the ratio reaches preset proportion threshold value, the control for opening flip lid is sent to dustbin cover control device
Information.
Optionally, if there are rubbish to be sorted in the rubbish identification region, the rubbish is acquired by camera
In rubbish identification region after the image information of rubbish to be sorted, the method also includes:
Quality estimation is carried out to described image information, if the quality of described image information is less than preset quality threshold,
The first prompt information is issued, and enters standby mode after preset first waiting time.
Optionally, the image information that rubbish to be sorted in the rubbish identification region is acquired by camera, comprising:
Camera by the way that multiple angles are arranged in obtains multiple image informations of multiple angles;
Multiple described image informations and preset garbage classification model are subjected to match cognization, judge that being identified rubbish accounts for institute
State the ratio of rubbish to be sorted, comprising:
Union calculating is carried out by the junk information identified based on multiple described image informations, is calculated according to the union
As a result, judging that the identified rubbish accounts for the ratio of the rubbish to be sorted.
It is optionally, described that Quality estimation is carried out to described image information, comprising:
Judge whether described image information light is less than X candela, whether the single rubbish image pixel identified is less than Y
Whether pixel, and/or the image area of single rubbish identified are less than Z%, wherein X, Y, Z are positive number.
Optionally, the ratio for judging identified rubbish and accounting for the rubbish to be sorted, comprising:
If the ratio is less than the preset proportion threshold value, issue to prompt user to adjust the rubbish to be sorted
Second prompt information of disposing way, and enter standby mode after preset second waiting time.
Optionally, the ratio for judging identified rubbish and accounting for the rubbish to be sorted, further includes:
If the ratio is more than or equal to the preset proportion threshold value, judge in the identified rubbish with the presence or absence of not
Same type rubbish;
If it exists, then third prompt information is issued to prompt user to adjust the type of rubbish to be sorted, and preset
Enter standby mode after the third waiting time.
Optionally, it if the ratio reaches preset proportion threshold value, is opened to the transmission of dustbin cover control device
Open the control information of flip lid, comprising:
If the ratio is more than or equal to the preset proportion threshold value, and different type is not present in the identified rubbish
Rubbish, then record is encoded with the identified matched classification of rubbish, and Xiang Suoshu dustbin cover control device sends to open and turn over
The control information of lid;
Flip lid was opened and after preset 4th waiting time, closes dustbin cover and enters standby mode.
Optionally, the method also includes:
It presets the protection period, is not responding in the protection period except the rubbish to be sorted for the identification process of the rubbish to be sorted
The rubbish of Other Waste identifies request except rubbish.
Second aspect, the embodiment of the present invention provide a kind of garbage classification device based on image recognition technology, comprising:
Identification module judges in rubbish identification region for standby mode with the presence or absence of rubbish to be sorted;
Acquisition module, if for there are rubbish to be sorted in the rubbish identification region, by described in camera acquisition
The image information of rubbish to be sorted in rubbish identification region;
Matching module judges to be known for described image information and preset garbage classification model to be carried out match cognization
Other rubbish accounts for the ratio of the rubbish to be sorted;
Sending module is sent if reaching preset proportion threshold value for the ratio to dustbin cover control device
Open the control information of flip lid.
The third aspect, the embodiment of the present invention provide a kind of electronic equipment, comprising: memory, processor and are stored in described
On memory and the computer program that can run on the processor, the processor are realized when executing the computer program
Step in refuse classification method provided in this embodiment based on image recognition technology.
Fourth aspect, the embodiment of the present invention provide a kind of computer readable storage medium, the computer-readable storage medium
Computer program is stored in matter, the computer program is realized provided in this embodiment based on image knowledge when being executed by processor
Step in the refuse classification method of other technology.
Bring of the present invention is judged in rubbish identification region the utility model has the advantages that in the embodiment of the present invention by standby mode
With the presence or absence of rubbish to be sorted;If there are rubbish to be sorted in the rubbish identification region, the rubbish is acquired by camera
The image information of rubbish to be sorted in rubbish identification region;Described image information and preset garbage classification model are subjected to matching knowledge
Not, judge that identified rubbish accounts for the ratio of the rubbish to be sorted;If the ratio reaches preset proportion threshold value, to rubbish
Bucket turnover control device sends the control information for opening flip lid.The embodiment of the present invention due to can be acquired according to camera it is described to
Then the image information of sorting rubbish is matched with preset garbage classification model, determine the corresponding identified rubbish,
Ratio of the identified rubbish in the rubbish to be sorted is judged again, if the ratio has reached preset ratio threshold
Value will send the control information for opening bung to dustbin cover control device, dustbin cover is made to open garbage throwing, this
Sample can be realized the automatic classification to the rubbish to be sorted, quickly, accurately identify rubbish type, raising classifies to rubbish
Recognition efficiency.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is a kind of refuse classification method network architecture diagram based on image recognition technology provided by the invention;
Fig. 2 is a kind of flow chart of the refuse classification method based on image recognition technology provided by the invention;
Fig. 3 is the flow chart of another refuse classification method based on image recognition technology provided by the invention;
Fig. 4 is the flow chart of another refuse classification method based on image recognition technology provided by the invention;
Fig. 5 is a kind of schematic diagram of the garbage classification device based on image recognition technology provided by the invention;
Fig. 6 is the schematic diagram of another garbage classification device based on image recognition technology provided by the invention;
Fig. 7 is the schematic diagram of another garbage classification device based on image recognition technology provided by the invention;
Fig. 8 is the schematic diagram of another garbage classification device based on image recognition technology provided by the invention;
Fig. 9 is the schematic diagram of another garbage classification device based on image recognition technology provided by the invention;
Figure 10 is the schematic diagram of another garbage classification device based on image recognition technology provided by the invention;
Figure 11 is the structural schematic diagram of a kind of electronic equipment provided by the invention provided.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
A kind of refuse classification method based on image recognition technology provided by the invention.
Invention for clearer description this programme is intended to, and is first configured to the scene of this programme.As shown in Figure 1, mentioning
A kind of refuse classification method network architecture diagram based on image recognition technology is supplied, the above-mentioned network architecture includes: for acquisition figure
The camera 1 of picture carries out the system 2 of Classification and Identification, and the dustbin cover control of control dustbin cover switch to rubbish
Device 3.First rubbish identification region is detected, judges whether there is rubbish to be sorted, camera 1 as system 2 outside
Image obtains tool, can be one, is also possible to more, and can voluntarily adjust to multiple angles.Certainly by camera 1
Dynamic detection rubbish identification region, can quickly scan rubbish to be sorted;Rubbish to be sorted if it exists, then by camera 1 from
Different angle is captured, and is obtained multiple image informations and is uploaded in system 2, the image information and rubbish that system will acquire
Disaggregated model carries out matching classification, obtains the identified rubbish with the dustbin corresponding types of rubbish present position to be sorted, and
It calculates and is identified ratio A of the rubbish in rubbish to be sorted in multiple image informations, by system 2 by image information and rubbish
Disaggregated model is matched, and determines identified rubbish, the Fast Classification for treating sorting rubbish may be implemented, to calculate image letter
It is identified ratio of the rubbish in rubbish to be sorted in breath, data are provided;Moreover be compared ratio A with proportion threshold value B,
If ratio A reaches proportion threshold value B, the control information for opening dustbin cover is sent to dustbin cover control device 3, this
Sample can quickly, while accurately identify rubbish type, enhance user to the understanding of rubbish type, improve the environmental protection meaning of user
Know.
Fig. 2 is referred to, Fig. 2 is a kind of refuse classification method based on image recognition technology provided in an embodiment of the present invention
Flow diagram, as shown in Figure 2, comprising the following steps:
S101, standby mode judge in rubbish identification region with the presence or absence of rubbish to be sorted.
Wherein, rubbish identification region can be the dustbin inlet for being set in advance in each type, for temporarily depositing
Put the region that rubbish is identified, rubbish to be sorted can be need to carry out classification processing put it is a variety of to corresponding types dustbin
The rubbish of type or a type of rubbish, such as: it can be rubbish from cooking, recyclable rubbish, Harmful Waste and remaining rubbish
The various garbages such as rubbish type or a kind of rubbish type, rubbish from cooking may include dish green tops, leftovers leftovers etc., can be recycled
Rubbish may include waste paper, plastics, glass, metal and cloth etc., and Harmful Waste may include refuse battery, waste daylight lamp tube, give up
Mercurial thermometer, Expired drug etc., Other Waste may include brick and tile ceramics, the dregs, health in addition to above-mentioned a few class rubbish
Between waste paper etc. be difficult to waste recycled etc., such as: have the multiple types such as dish green tops, pop can, refuse battery in rubbish to be sorted
There was only one seed type rubbish of leftovers, bone and dish green tops in the rubbish of type or rubbish to be sorted.
Specifically, whether there is rubbish to be sorted in above-mentioned judgement rubbish identification region, it can be and lead in the standby state
It crosses at least one set of camera from different perspectives to detect rubbish identification region, camera obtains work as the image of system
Tool, such as: it can be the image for sampling successive frame in rubbish identification region in such a way that camera acquires sequential frame image,
Wherein, image sampling can be and is sampled according to the speed of fps (frame/second), such as: fps=20,25 etc., according to circumstances
It can preset, if the image information of successive frame that judgement is got and preset there is no the image information of rubbish mismatch, tables
Show that rubbish to be sorted has been put into rubbish identification region to need to carry out Classification and Identification, then system obtains the presence of camera shooting overhead pass
The image information of rubbish to be sorted.Certainly, it whether there is rubbish to be sorted in above-mentioned judgement rubbish identification region, can also be logical
It crosses gravity sensor, photoelectric sensor etc. to incude rubbish identification region, judges whether there is rubbish to be sorted, such as:
There is gravity sensor in the bottom preset of rubbish identification region, after being put into rubbish to be sorted, gravity sensor just will receive weight
Power effect, then to system transmission, there are junk information to be sorted.In embodiments of the present invention, to judging in rubbish identification region
With the presence or absence of rubbish to be sorted mode without limitation.
If there are rubbish to be sorted in S102, the rubbish identification region, the rubbish is acquired by camera and is identified
The image information of rubbish to be sorted in region.
Wherein, image information can be camera and treat sorting rubbish multiple topographies collected in different angle
Image information can be including multiple types such as rubbish from cooking, recyclable rubbish, Harmful Waste and Other Wastes in image information
The image information of type rubbish, part rubbish can also be blocked, and the imperfect image information of the part rubbish is presented.When rubbish identifies
There are when rubbish to be sorted in region, the image information of successive frame is sampled from different perspectives by camera, be conducive to system and obtain
Multiple image informations are carried out detection identification by multiple image informations for taking the successive frame of camera shooting overhead pass.
S103, described image information and preset garbage classification model are subjected to match cognization, judge that identified rubbish accounts for
The ratio of the rubbish to be sorted.
Wherein, garbage classification model is to train to be preset in system database in advance, be can be through convolutional Neural net
Network (Convolutional Neural Network)) characteristic value is extracted, i.e., the image of the rubbish identified to needs is believed
Characteristic value extracts in breath, then handles the characteristic value extracted, after Processing with Neural Network, is identifying
The distinctive points of single rubbish and Other Waste will be extracted, such as: characteristic value can be color, brightness, shape, line
Reason, size etc..Certainly, before extracting to characteristic value, a large amount of image training data is needed, wherein image training number
It obtaining, then the image data got being tested, by each image training data according to can be from relevant departments
Multiple images are repeatedly tested when different size, different brightness, and the size of image can be carried out according to specific requirements
Setting, such as: 300 × 400 pixels etc..After system carries out study many times to each image data, image can be obtained
In each rubbish data test result and form the sample of each rubbish, then all samples are counted, form rubbish point
Class model completes training process.The garbage classification model formed by way of convolutional neural networks can provide more rubbish
Type can treat sorting rubbish and carry out accurately identification judgement, improve recognition efficiency.
Wherein, at least one of the dustbin corresponding types rubbish that identified rubbish can be and identified.
System judges multiple images by the way that the image information of multiple images and preset garbage classification model are carried out match cognization
Rubbish type in image information determines in every image information and shared by the identified rubbish image of corresponding dustbin same type
Then the ratio of whole image can be by way of superposition calculation ratio mean value, calculate and be identified rubbish in multiple images
The image of rubbish accounts for the ratio of total figure picture, such as: preparing the corresponding dustbin of rubbish launched is recyclable rubbish bucket, then by knowing
Other rubbish is recyclable rubbish, if sharing 3 images, judges that recyclable rubbish in first image accounts for the ratio of whole image
It is 50%, it is 60% that recyclable rubbish, which accounts for the ratio of whole image, in second image, and recyclable rubbish accounts in third image
The ratio of whole image is 70%, and with mean value computation ratio, then ratio is 60%.Certainly, it is to be sorted to judge that identified rubbish accounts for
The mode of the ratio of rubbish, in embodiments of the present invention without limitation.
If S104, the ratio reach preset proportion threshold value, is sent to dustbin cover control device and open flip lid
Control information.
Wherein, proportion threshold value can be previously according to requiring to be arranged, and dustbin cover control device can be for controlling
The device that dustbin cover opens and closes.When the ratio that identified rubbish accounts for rubbish to be sorted has reached proportion threshold value, such as:
Proportion threshold value is 50%, and the ratio that the identified rubbish judged accounts for rubbish to be sorted reaches 70%.Then, system will be sent out
It send the control information opened and renovated to dustbin cover control device, the corresponding dustbin of opening of dustbin cover control device is allowed to turn over
Lid is completed rubbish identification process, is launched to rubbish.
It should be noted that above-mentioned standby mode can refer to the booting of system but without any substantive work
State.
In the embodiment of the present invention, judged in rubbish identification region by standby mode with the presence or absence of rubbish to be sorted;If
There are rubbish to be sorted in the rubbish identification region, then acquire rubbish to be sorted in the rubbish identification region by camera
Image information;Described image information and preset garbage classification model are subjected to match cognization, judge that identified rubbish accounts for institute
State the ratio of rubbish to be sorted;If the ratio reaches preset proportion threshold value, opened to the transmission of dustbin cover control device
Open the control information of flip lid.Image information of the embodiment of the present invention since the rubbish to be sorted can be acquired according to camera,
Then it is matched with preset garbage classification model, determines the corresponding identified rubbish, then judge the identified rubbish
Ratio of the rubbish in the rubbish to be sorted will be to dustbin cover if the ratio has reached preset proportion threshold value
Control device send open bung control information, make dustbin cover open garbage throwing, can be realized in this way to it is described to
The automatic classification of sorting rubbish quickly, accurately identifies rubbish type, improves the recognition efficiency classified to rubbish.
A kind of optional embodiment passes through camera shooting if there are rubbish to be sorted in the rubbish identification region
Head acquires in the rubbish identification region after the image information of rubbish to be sorted, the method also includes:
Quality estimation is carried out to described image information, if the quality of described image information is less than preset quality threshold,
The first prompt information is issued, and enters standby mode after preset first waiting time.
Wherein, carrying out Quality estimation can indicate that an identification state current to image information judges, such as light
Line, pixel etc., certainly, if system can not also judge light from being furnished with light;Quality threshold can be according to requiring
It presets, and quality threshold can be and require multiple states while reach some condition, is also possible to single status and reaches
Some condition, such as: only light and pixel are judged, light and pixel is needed to reach the threshold value respectively set simultaneously, or
Person only judges pixel, and pixel is needed to meet threshold value.Wherein, the first prompt information can be voice messaging, such as: system is pre-
First configure phonetic function, the voice messaging issued can be similar informations such as " placement positions that please adjust rubbish ", can also be with
It is text information, such as: system is provided with caption display screen in advance, and can have similar " please adjust the pendulum of rubbish on a display screen
Put position " etc. as word-information display, naturally it is also possible to be to have voice messaging and Word message prompting simultaneously, and text
Information and voice messaging can be pre-configured with multilingual.In this way, user is notified to treat sorting rubbish and adjust, be conducive to wait divide
The identification of class rubbish further progress, and have voice messaging and Word message prompting simultaneously, be conducive to dysaudia or eyesight
The special users such as obstacle, which give, preferably to be prompted.In embodiments of the present invention, prompting mode is without limitation.Wherein, it first waits
Time can be time including issuing the first prompt information and user treats the time that sorting rubbish is adjusted, and be also possible to
It is treated the time that sorting rubbish is adjusted for user, time span can be arranged previously according to demand, such as: 10 seconds, 15 seconds
Deng in embodiments of the present invention, without limitation.
Specifically, that is to say when the Quality estimation to image information is unsatisfactory for quality threshold requirement less than quality threshold
When, system can issue the first prompt information, then wait user to treat sorting rubbish and be adjusted.Such as: quality threshold is to know
The rubbish light to be sorted being clipped to is not less than 800 candelas, when the rubbish light to be sorted recognized is 400 candelas, system
The voice messaging and word-information display of similar " position that rubbish to be sorted please be adjust " can be issued, is then waited 10 seconds, then
Quality estimation once is carried out to image information, if detecting light still and being 400 candelas or in light error tolerance, is held
Wrong range, which can be, to be preset, such as: light between 380~420 candelas, then, system enters standby mode no longer
Identification, certainly, before entering standby mode, the number of the first prompt information of sending can be to be preset as needed, such as:
Issue " position that rubbish to be sorted please be adjust " voice messaging and text information 5 times after, detect rubbish light to be sorted
Still less than 800 candelas, not up to quality threshold, then system will enter standby mode.In this way, can let the user know that
The detection case of sorting rubbish is conducive to treat sorting rubbish and makes multiple adjustment, smoothly completes the Quality estimation of image information
Process.
In embodiments of the present invention, it if the quality of described image information is greater than or equal to preset quality threshold, does not send out
First suggestion voice out, and execute S103.
A kind of optional embodiment, the figure that rubbish to be sorted in the rubbish identification region is acquired by camera
As information, comprising:
Camera by the way that multiple angles are arranged in obtains multiple image informations of multiple angles;
Multiple described image informations and preset garbage classification model are subjected to match cognization, judge that being identified rubbish accounts for institute
State the ratio of rubbish to be sorted, comprising:
Union calculating is carried out by the junk information identified based on multiple described image informations, is calculated according to the union
As a result, judging that the identified rubbish accounts for the ratio of the rubbish to be sorted.
Wherein, it is preset with camera in rubbish identification region, which can be to each area of rubbish identification region
Domain is detected, and the entrance of rubbish to be sorted is judged whether there is, and camera can be one, is also possible to more, camera can
Multiple angles are voluntarily adjusted to be detected.After having detected that rubbish enters, camera can acquire to be sorted from different perspectives
Multiple image informations of rubbish, then judge in multiple image informations, rubbish barrel type corresponding with rubbish identification region
The rubbish matched, i.e., identified rubbish, then calculates in every image information, is identified region shared by rubbish in whole image
Ratio in information, then calculated in multiple image informations by union, all identified rubbish accounts for the ratio of all images information,
It obtains a result.Calculating final ratio can be proportionally mean value computation, such as: there are three image informations altogether, are identified rubbish
It is 50%, 60% and 70% that accounting is distinguished in three image informations, that ratio mean value is 60%, that is, identified rubbish
The accounting 60% in rubbish to be sorted.In embodiments of the present invention, without limitation to the mode of the ratio of calculating.
A kind of optional embodiment, it is described that Quality estimation is carried out to described image information, comprising:
Judge whether described image information light is less than X candela, whether the single rubbish image pixel identified is less than Y
Whether pixel, and/or the image area of single rubbish identified are less than Z%, wherein X, Y, Z are positive number.
Wherein it is possible to be simultaneously to light, the single rubbish image pixel identified and the single rubbish identified
Image area limited in advance, can be while meeting above three condition, the requirement for reaching Quality estimation could be calculated;?
It can be the preset condition of any two met in three;It can also be any one preset condition in satisfaction three, this
Sample can more accurately obtain the image information of rubbish to be sorted, obtain relatively sharp image, facilitate rubbish belonging to judgement
Rubbish type.Wherein, X indicates the brightness size of light, and Y can indicate the size of pictorial element, that is to say the size of pixel, and scheme
Dimensional units of the pixel element as resolution ratio usually indicate to scheme so that pixel per inch PPI (Pixels Per Inch) is unit
As the size of resolution ratio, such as: in 400 × 400PPI resolution ratio, i.e. expression horizontal direction and vertical direction in per inch length
Pixel number be all 400, certainly, there is 160,000 (400 × 400) pixels in also referred to as one square inch.It is carrying out to image
Quality estimation when, be to treat the part of sorting rubbish to be judged, can be with so will appear the imperfect image of single rubbish
It is identified by the image area to single rubbish, judges that the area that single rubbish is shown in image accounts for single rubbish whole
The ratio of area, because each rubbish is there may be being blocked, such as: a plastic bottle has blocked portion by melon seed cases
Partial image, one block of glass are by carton shield portions area etc..Wherein, the area for judging that single rubbish is shown in image accounts for this
The ratio of single rubbish entire area can be judged by the shape to single rubbish, edge, texture etc..Such as: to light
Line mass and the single rubbish image pixel identified are defined, and threshold value is followed successively by 200 candelas and 4,000,000 pixels, that
When light intensity reaches 500 candelas, and the single rubbish image pixel identified is 8,000,000 pixel, then it represents that quality is sentenced
It is disconnected to reach quality threshold.In embodiments of the present invention, without limitation to the condition of Quality estimation.
A kind of optional embodiment, the ratio for judging identified rubbish and accounting for the rubbish to be sorted, comprising:
If the ratio is less than the preset proportion threshold value, issue to prompt user to adjust the rubbish to be sorted
Second prompt information of disposing way, and enter standby mode after preset second waiting time.
Wherein, if in multiple image informations, the ratio that all identified rubbish accounts for all rubbish to be sorted is less than ratio threshold
Value, system adjust position, light, the angle etc. of rubbish to be sorted, the second prompt letter by the second prompt information prompting user is issued
Breath can be voice messaging, be also possible to text information, and wait within the second waiting time, the second waiting time can be 5
Second, 10 seconds etc., it can preset as needed, if detecting again after the second waiting time, detect that rubbish to be sorted does not have
It adjusts, then stops rubbish identification process, into standby mode.For example, proportion threshold value is 60%, the ratio detected is
50%, system then issues " please adjust rubbish position to be sorted " voice messaging and the text information with content, then waits 10 seconds,
If presetting error tolerance to the ratio is ± 5%, then then terminating to know when the ratio detected again is between 45%-55%
Other process enters standby mode, if detecting ratio lower than 45%, can also be that continuing to issue the request of the second prompt information adjusts
Whole rubbish position to be sorted.It makes adjustment in this way, being conducive to user and treating sorting rubbish.
A kind of optional embodiment, the ratio for judging identified rubbish and accounting for the rubbish to be sorted, further includes:
If the ratio is more than or equal to the preset proportion threshold value, judge in the identified rubbish with the presence or absence of not
Same type rubbish;
If it exists, then third prompt information is issued to prompt user to adjust the type of rubbish to be sorted, and preset
Enter standby mode after the third waiting time.
Wherein, it if the ratio for judging that identified rubbish accounts for rubbish to be sorted reaches proportion threshold value, needs to judge to be known
In other rubbish, if there are different type rubbish, such as: identified rubbish is recyclable rubbish, then by with preset rubbish
Disaggregated model carries out match cognization, detects in recyclable rubbish with the presence or absence of rubbish from cooking or non-recyclable rubbish etc..If by
It identifying in rubbish there are different type rubbish, system can issue third prompt information and user is reminded to rearrange rubbish,
The third prompt information can be voice messaging or/and text information, such as: identified rubbish is recyclable rubbish, then the
Three prompt informations can be " containing rubbish from cooking in identified rubbish, please take out rubbish from cooking ", and simultaneity factor will be shown
Text information with content is on preset display screen.Then it is detected in identified rubbish again within the third waiting time
There is no different type rubbish or different type rubbish accounting to be no more than some value, then can send the control for opening flip lid
Information, third waiting time can preset, and can be 30 seconds, 60 seconds etc..Such as: identified rubbish is recyclable rubbish, 30
It is detected again in second, judges the image information of all recyclable rubbishes of image information detected, or detect to return
There are 0.5% rubbish from cooking image informations in the image information of receipts rubbish, then, the control letter for opening flip lid will be sent
Breath.If but detect recyclable rubbish again in 30 seconds, the image information of rubbish from cooking is still remained in testing result, and
The image information of rubbish from cooking has been more than 0.5%, then system will terminate rubbish identification process, into standby mode.In this way, having
Conducive to quick identification sorting rubbish, user is improved to the understanding of different type rubbish, while improving the environmental consciousness of user.
Fig. 3 is referred to, Fig. 3 is another refuse classification method based on image recognition technology provided in an embodiment of the present invention
Flow diagram, as shown in Figure 3, comprising the following steps:
S201, standby mode judge in rubbish identification region with the presence or absence of rubbish to be sorted.
If there are rubbish to be sorted in S202, the rubbish identification region, the rubbish is acquired by camera and is identified
The image information of rubbish to be sorted in region.
S203, described image information and preset garbage classification model are subjected to match cognization, judge that identified rubbish accounts for
The ratio of the rubbish to be sorted.
If S204, the ratio are more than or equal to the preset proportion threshold value, and there is no not in the identified rubbish
Same type rubbish, then record is encoded with the identified matched classification of rubbish, and Xiang Suoshu dustbin cover control device is sent
Open the control information of flip lid.
Wherein, classification coding can be the coding set in advance for the rubbish of each type, such as: recyclable rubbish is compiled
Code is C, and recyclable rubbish is not D etc., naturally it is also possible to use garbage classification mark as coding, or using text etc. as volume
Code, in embodiments of the present invention, without limitation.Control information can be for expressing the letter for opening or closing dustbin cover
Breath.The dispensing of identified rubbish is counted in this way, being conducive to internal system.
S205, flip lid were opened and after preset 4th waiting time, closed dustbin cover and entered standby mode.
Wherein, the 4th waiting time referred to that the release time of identified rubbish, the 4th waiting time can be 5 seconds, 10 seconds
Deng if the 4th waiting time was 5 seconds, after 5 seconds, system can send the control information for closing dustbin cover to dustbin
Turnover control device, dustbin cover is closed, and system enters standby mode, the dispensing of identified rubbish can be allowed to have in this way
One buffer time.
In the embodiment of the present invention, judged in rubbish identification region by standby mode with the presence or absence of rubbish to be sorted;If
There are rubbish to be sorted in the rubbish identification region, then acquire rubbish to be sorted in the rubbish identification region by camera
Image information;Described image information and preset garbage classification model are subjected to match cognization, judge that identified rubbish accounts for institute
State the ratio of rubbish to be sorted;If the ratio is more than or equal to the preset proportion threshold value, and in the identified rubbish not
There are different type rubbish, then record is encoded with the identified matched classification of rubbish, Xiang Suoshu dustbin cover control dress
Set the control information for sending and opening flip lid;Flip lid was opened and after preset 4th waiting time, closes dustbin cover and enters
Standby mode.The embodiment of the present invention can acquire the image information of the rubbish to be sorted according to camera, then with it is preset
Garbage classification model is matched, and determines the corresponding identified rubbish, then judges the identified rubbish described wait divide
Ratio in class rubbish will be sent if the ratio has reached preset proportion threshold value to dustbin cover control device
The control information of bung is opened, corresponding record is identified the classification coding of rubbish, so that dustbin cover is opened garbage throwing, in this way
It can be realized the automatic classification to the rubbish to be sorted, quickly, accurately identify rubbish type, what raising classified to rubbish
Recognition efficiency.
As an alternative embodiment, as shown in figure 4, Fig. 4 is provided in an embodiment of the present invention another based on figure
As the flow diagram of the refuse classification method of identification technology.Most start system to be in standby, works as camera detection
To needing after sorting rubbish enters rubbish identification region, the image information that camera can treat sorting rubbish is acquired, and
System is sent by acquired image information, system carries out a Quality estimation to multiple images received again, works as image
After the quality of information reaches preset quality threshold, by by the image information of rubbish to be sorted and preset garbage classification model
It is matched, identifies the identified rubbish in rubbish to be sorted, judge identified ratio of the rubbish in rubbish to be sorted, such as
After the fruit ratio reaches preset proportion threshold value, judge there is no different type rubbish in identified rubbish, then, it is
System will send the control information of control dustbin cover unlatching to dustbin cover control device, allow and complete the identified of classification
Rubbish is able to launch into dustbin, certainly, during identification, if quality threshold, quilt is not achieved in the quality of above-mentioned image
The ratio that identification rubbish accounts for rubbish to be sorted is not achieved proportion threshold value or recognizes in identified rubbish that there are other types rubbish
Rubbish, system all can remind user to adjust rubbish by issuing prompt information, that is, voice messaging and/or text information
It is whole, it is identified by repeatedly judging, more detailed image information can be got, and accurately identify to image information, mentioned
The high recognition efficiency to rubbish type, is rapidly completed assorting process.
As an alternative embodiment, the method also includes:
It presets the protection period, is not responding in the protection period except the rubbish to be sorted for the identification process of the rubbish to be sorted
The rubbish of Other Waste identifies request except rubbish.
Wherein, the protection period can be including since acquiring image information to the first waiting time, the second waiting time,
Between any two period that three waiting time or the 4th waiting time terminate during this section, during the period, system
Only response is carrying out the rubbish to be sorted of Classification and Identification, and to the Classification and Identification that the Other Waste being added in the meantime is issued
Request is not responding to, and that is to say that there are sequencings.In this manner it is ensured that smooth to the rubbish to be sorted for carrying out Classification and Identification
Classification and Identification is completed, recognition efficiency is improved, prevents many and diverse detection process from occurring.
Fig. 5 is referred to, Fig. 5 is a kind of garbage classification device based on image recognition technology provided in an embodiment of the present invention
Flow diagram, device include:
Identification module 401 judges in rubbish identification region for standby mode with the presence or absence of rubbish to be sorted;
Acquisition module 402, if acquiring rubbish for there are rubbish to be sorted in rubbish identification region by camera and knowing
The image information of rubbish to be sorted in other region;
Matching module 403, for image information and preset garbage classification model to be carried out match cognization, judgement is identified
Rubbish accounts for the ratio of rubbish to be sorted;
Sending module 404 is opened if reaching preset proportion threshold value for ratio to the transmission of dustbin cover control device
Open the control information of flip lid.
Optionally, as shown in fig. 6, device further include:
Judgment module 405, for carrying out Quality estimation to image information, if the quality of image information is less than preset quality
Threshold value then issues the first prompt information, and enters standby mode after preset first waiting time.
Optionally, acquisition module 402 is used to obtain multiple figures of multiple angles by the camera that multiple angles are arranged in
As information.
Matching module 403 is used to carry out union calculating by the junk information identified based on multiple image informations, according to
Union calculated result judges that identified rubbish accounts for the ratio of rubbish to be sorted.
Optionally, as shown in fig. 7, judgment module 405 includes:
First judging unit 4051, for judging whether image information light is less than X candela, the single rubbish identified
Whether image pixel is less than Y pixel, and/or whether the image area of the single rubbish identified is less than Z%, wherein X, Y, Z
For positive number.
Optionally, as shown in figure 8, matching module 403 includes:
First prompt unit 4031 issues if being less than preset proportion threshold value for ratio to prompt user to adjust
Second prompt information of rubbish disposing way to be sorted, and enter standby mode after preset second waiting time.
Optionally, as shown in figure 9, matching module 403 further include:
Second judgment unit 4032 judges in identified rubbish if being more than or equal to preset proportion threshold value for ratio
With the presence or absence of different type rubbish.
Second prompt unit 4033, for if it exists, then issuing third prompt information to prompt user's adjustment to be sorted
The type of rubbish, and enter standby mode after the preset third waiting time.
Optionally, as shown in Figure 10, sending module 404 includes:
Transmission unit 4041, if being more than or equal to preset proportion threshold value for ratio, and there is no not in identified rubbish
Same type rubbish, then record is encoded with the matched classification of identified rubbish, is sent to dustbin cover control device and is opened flip lid
Control information.
Opening unit 4042 is closed dustbin cover and is entered for renovating unlatching and after preset 4th waiting time
Standby mode.
Optionally, preset the protection period for the identification process of rubbish to be sorted, be not responding in the protection period except rubbish to be sorted it
The rubbish of outer Other Waste identifies request.
Community management device provided in an embodiment of the present invention can be realized each reality in the embodiment of the method for Fig. 2 and Fig. 3
Mode and corresponding beneficial effect are applied, to avoid repeating, which is not described herein again.
It is the structural schematic diagram of a kind of electronic equipment provided in an embodiment of the present invention referring to Figure 11, Figure 11, as shown in figure 11,
Include: processor 1101, memory 1102 and is stored in the computer that can be run on memory 1102 and on processor 1101
Program, in which:
Processor 1101 is used for, and executes following steps:
Standby mode judges in rubbish identification region with the presence or absence of rubbish to be sorted;
If there are rubbish to be sorted in rubbish identification region, rubbish to be sorted in rubbish identification region is acquired by camera
The image information of rubbish;
Image information and preset garbage classification model are subjected to match cognization, judge that identified rubbish accounts for rubbish to be sorted
Ratio;
If ratio reaches preset proportion threshold value, the control letter for opening flip lid is sent to dustbin cover control device
Breath.
Optionally, it if there are rubbish to be sorted in rubbish identification region, is acquired in rubbish identification region by camera
After the image information of rubbish to be sorted, method further include:
Quality estimation is carried out to image information, if the quality of image information is less than preset quality threshold, issues first
Prompt information, and enter standby mode after preset first waiting time.
Optionally, pass through the image information of rubbish to be sorted in camera acquisition rubbish identification region, comprising:
Camera by the way that multiple angles are arranged in obtains multiple image informations of multiple angles;
Multiple image informations and preset garbage classification model are subjected to match cognization, it is to be sorted to judge that identified rubbish accounts for
The ratio of rubbish, comprising:
Union calculating is carried out by the junk information identified based on multiple image informations to be sentenced according to union calculated result
Disconnected identified rubbish accounts for the ratio of rubbish to be sorted.
Optionally, Quality estimation is carried out to image information, comprising:
Judge whether image information light is less than X candela, whether the single rubbish image pixel identified is less than Y picture
Whether element, and/or the image area of single rubbish identified are less than Z%, wherein X, Y, Z are positive number.
Optionally, judge to be identified the ratio that rubbish accounts for rubbish to be sorted in image information, comprising:
If ratio is less than preset proportion threshold value, issue to prompt user to adjust rubbish disposing way to be sorted the
Two prompt informations, and enter standby mode after preset second waiting time.
Optionally, judge to be identified the ratio that rubbish accounts for rubbish to be sorted in image information, further includes:
If ratio is more than or equal to preset proportion threshold value, judge to whether there is different type rubbish in identified rubbish;
If it exists, then third prompt information is issued to prompt user to adjust the type of rubbish to be sorted, and preset
Enter standby mode after the third waiting time.
Optionally, it if ratio reaches preset proportion threshold value, is sent to dustbin cover control device and opens flip lid
Control information, comprising:
If ratio is more than or equal to preset proportion threshold value, and different type rubbish is not present in identified rubbish, then record
It is encoded with the matched classification of identified rubbish, the control information for opening flip lid is sent to dustbin cover control device;
Flip lid was opened and after preset 4th waiting time, closes dustbin cover and enters standby mode.
Optionally, method further include:
It is preset the protection period for the identification process of rubbish to be sorted, is not responding to other rubbish in addition to rubbish to be sorted in the protection period
The rubbish of rubbish identifies request.
Garbage classification device provided in an embodiment of the present invention can be realized each reality in the embodiment of the method for Fig. 2 and Fig. 3
Mode and corresponding beneficial effect are applied, to avoid repeating, which is not described herein again.
The embodiment of the present invention also provides a kind of computer readable storage medium, and meter is stored on computer readable storage medium
Calculation machine program, the computer program are realized provided in an embodiment of the present invention based on image recognition technology when being executed by processor 1101
Refuse classification method embodiment each process, and identical technical effect can be reached, it is no longer superfluous here to avoid repeating
It states.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, which can be stored in a computer-readable storage medium,
The program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, the storage medium can for magnetic disk, CD,
Read-only memory (Read-Only Memory, ROM) or random access memory (Random Access Memory, letter
Claim RAM) etc..
The above content is a further detailed description of the present invention in conjunction with specific preferred embodiments, and it cannot be said that
A specific embodiment of the invention is only limited to these instructions.General technical staff of the technical field of the invention is come
It says, without departing from the inventive concept of the premise, a number of simple deductions or replacements can also be made, all shall be regarded as belonging to this hair
Bright protection scope.
Claims (11)
1. a kind of refuse classification method based on image recognition technology, for knowing in dustbin to the rubbish to be sorted of dispensing
Not characterized by comprising
Standby mode judges in rubbish identification region with the presence or absence of rubbish to be sorted;
If there are rubbish to be sorted in the rubbish identification region, acquired in the rubbish identification region by camera wait divide
The image information of class rubbish;
Described image information and preset garbage classification model are subjected to match cognization, it is described to be sorted to judge that identified rubbish accounts for
The ratio of rubbish;
If the ratio reaches preset proportion threshold value, the control letter for opening flip lid is sent to dustbin cover control device
Breath.
2. if the method according to claim 1, wherein there are rubbish to be sorted in the rubbish identification region
Rubbish is then acquired in the rubbish identification region after the image information of rubbish to be sorted by camera, the method also includes:
Quality estimation is carried out to described image information, if the quality of described image information is less than preset quality threshold, is issued
First prompt information, and enter standby mode after preset first waiting time.
3. the method according to claim 1, wherein described acquired in the rubbish identification region by camera
The image information of rubbish to be sorted, comprising:
Camera by the way that multiple angles are arranged in obtains multiple image informations of multiple angles;
Multiple described image informations and preset garbage classification model are subjected to match cognization, judge identified rubbish account for it is described to
The ratio of sorting rubbish, comprising:
Union calculating is carried out by the junk information identified based on multiple described image informations, is calculated and is tied according to the union
Fruit judges that the identified rubbish accounts for the ratio of the rubbish to be sorted.
4. according to the method described in claim 2, it is characterized in that, described carry out Quality estimation to described image information, comprising:
Judge whether described image information light is less than X candela, whether the single rubbish image pixel identified is less than Y picture
Whether element, and/or the image area of single rubbish identified are less than Z%, wherein X, Y, Z are positive number.
5. according to the method described in claim 3, it is characterized in that, described judge that identified rubbish accounts for the rubbish to be sorted
Ratio, comprising:
If the ratio is less than the preset proportion threshold value, issues and put to prompt user to adjust the rubbish to be sorted
Second prompt information of mode, and enter standby mode after preset second waiting time.
6. according to the method described in claim 3, it is characterized in that, described judge that identified rubbish accounts for the rubbish to be sorted
Ratio, further includes:
If the ratio is more than or equal to the preset proportion threshold value, judge in the identified rubbish with the presence or absence of inhomogeneity
Type rubbish;
If it exists, then third prompt information is issued to prompt user to adjust the type of rubbish to be sorted, and in preset third
Enter standby mode after waiting time.
If 7. according to the method described in claim 6, it is characterized in that, the ratio reaches preset proportion threshold value,
The control information for opening flip lid is sent to dustbin cover control device, comprising:
If the ratio is more than or equal to the preset proportion threshold value, and different type rubbish is not present in the identified rubbish
Rubbish, then record is encoded with the identified matched classification of rubbish, and Xiang Suoshu dustbin cover control device, which is sent, opens flip lid
Control information;
Flip lid was opened and after preset 4th waiting time, closes dustbin cover and enters standby mode.
8. the method according to claim 1, wherein the method also includes:
Preset the protection period for the identification process of the rubbish to be sorted, be not responding in the protection period except the rubbish to be sorted it
The rubbish of outer Other Waste identifies request.
9. a kind of garbage classification device based on image recognition technology characterized by comprising
Identification module judges in rubbish identification region for standby mode with the presence or absence of rubbish to be sorted;
Acquisition module, if acquiring the rubbish by camera for there are rubbish to be sorted in the rubbish identification region
The image information of rubbish to be sorted in identification region;
Matching module judges identified rubbish for described image information and preset garbage classification model to be carried out match cognization
Rubbish accounts for the ratio of the rubbish to be sorted;
Sending module sends to dustbin cover control device and opens if reaching preset proportion threshold value for the ratio
The control information of flip lid.
10. a kind of electronic equipment characterized by comprising memory, processor and be stored on the memory and can be in institute
The computer program run on processor is stated, the processor is realized when executing the computer program as in claim 1 to 8
Step in described in any item refuse classification methods based on image recognition technology.
11. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium
Program is realized when the computer program is executed by processor and is based on image recognition as described in any item of the claim 1 to 8
Step in the refuse classification method of technology.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811554844.5A CN109684979B (en) | 2018-12-18 | 2018-12-18 | Image recognition technology-based garbage classification method and device and electronic equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811554844.5A CN109684979B (en) | 2018-12-18 | 2018-12-18 | Image recognition technology-based garbage classification method and device and electronic equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109684979A true CN109684979A (en) | 2019-04-26 |
CN109684979B CN109684979B (en) | 2021-11-30 |
Family
ID=66186882
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811554844.5A Active CN109684979B (en) | 2018-12-18 | 2018-12-18 | Image recognition technology-based garbage classification method and device and electronic equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109684979B (en) |
Cited By (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110321972A (en) * | 2019-07-22 | 2019-10-11 | 上海五赫自动化科技中心 | A kind of wet refuse classification acceptance test method and its realization device |
CN110395504A (en) * | 2019-08-06 | 2019-11-01 | 高晓东 | Garbage classification judges the personal method and device for whether carrying out garbage classification |
CN110458067A (en) * | 2019-07-31 | 2019-11-15 | 卓尔智联(武汉)研究院有限公司 | Portray method, computer installation and the readable storage medium storing program for executing of user's portrait |
CN110472565A (en) * | 2019-08-14 | 2019-11-19 | 六安智华工业自动化技术有限公司 | A kind of determination method of the garbage classification ability based on motion capture |
CN110482072A (en) * | 2019-07-02 | 2019-11-22 | 上海净收智能科技有限公司 | Refuse classification method, system, medium, garbage containing device and cloud platform |
CN110510276A (en) * | 2019-08-02 | 2019-11-29 | 苏州市伏泰信息科技股份有限公司 | A kind of garbage classification equipment based on based on image recognition |
CN110606292A (en) * | 2019-09-17 | 2019-12-24 | 蔡亦圣 | Automatic classification garbage can based on artificial intelligence and classification method |
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 |
CN110795999A (en) * | 2019-09-21 | 2020-02-14 | 万翼科技有限公司 | Garbage delivery behavior analysis method and related product |
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 |
CN111318470A (en) * | 2019-07-02 | 2020-06-23 | 王多 | Method and device for identifying article type |
CN111753844A (en) * | 2020-06-30 | 2020-10-09 | 烟台艾睿光电科技有限公司 | Dry and wet garbage classification method, classification box and classification system |
CN112027424A (en) * | 2020-09-23 | 2020-12-04 | 深圳市康灵盾智能厨具设备有限公司 | Garbage classification and recovery system and garbage classification and recovery method |
CN112183783A (en) * | 2020-10-15 | 2021-01-05 | 张良虎 | Intelligent garbage classification method and system |
CN112298844A (en) * | 2019-07-29 | 2021-02-02 | 杭州海康威视数字技术股份有限公司 | Garbage classification monitoring method and device |
CN112365758A (en) * | 2020-11-10 | 2021-02-12 | 阿尔飞思(昆山)智能物联科技有限公司 | Education version garbage classification method, device and system |
WO2021036145A1 (en) * | 2019-08-29 | 2021-03-04 | 深圳创维-Rgb电子有限公司 | Garbage sorting method, apparatus and system, and computer-readable storage medium |
CN112765193A (en) * | 2020-12-28 | 2021-05-07 | 苏州信颐系统集成有限公司 | Management system for garbage classification data acquisition equipment |
CN113682686A (en) * | 2021-08-04 | 2021-11-23 | 浙江联运知慧科技有限公司 | AI algorithm-based monitoring overflow alarm identification method for automatic bag breaking classification box |
CN113837099A (en) * | 2021-09-26 | 2021-12-24 | 浙江力石科技股份有限公司 | Method and device for classifying garbage in image |
CN114275416A (en) * | 2022-01-19 | 2022-04-05 | 平安国际智慧城市科技股份有限公司 | Kitchen waste classification method, device, equipment and medium based on image recognition |
CN114345892A (en) * | 2021-12-24 | 2022-04-15 | 苏州嘉诺智能装备有限公司 | Garbage classification processing system and method |
CN114629933A (en) * | 2020-12-10 | 2022-06-14 | 广东省中医院(广州中医药大学第二附属医院、广州中医药大学第二临床医学院、广东省中医药科学院) | Garbage disposal method and device for hospital |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106275945A (en) * | 2016-08-17 | 2017-01-04 | 浪潮电子信息产业股份有限公司 | A kind of garbage recovery device, garbage classification system and using method |
CN106395186A (en) * | 2016-12-05 | 2017-02-15 | 上海商溱环保节能科技有限公司 | Intelligent urban waste bin |
CN107054936A (en) * | 2017-03-23 | 2017-08-18 | 广东数相智能科技有限公司 | A kind of refuse classification prompting dustbin and system based on image recognition |
CN107092914A (en) * | 2017-03-23 | 2017-08-25 | 广东数相智能科技有限公司 | Refuse classification method, device and system based on image recognition |
CN107640480A (en) * | 2017-10-19 | 2018-01-30 | 广东拜登网络技术有限公司 | The method and apparatus and storage medium and terminal device of refuse classification retrospect |
CN107985841A (en) * | 2017-12-25 | 2018-05-04 | 广东南方碳捕集与封存产业中心 | A kind of method of garbage classification and a kind of dustbin |
CN108182455A (en) * | 2018-01-18 | 2018-06-19 | 齐鲁工业大学 | A kind of method, apparatus and intelligent garbage bin of the classification of rubbish image intelligent |
CN108341184A (en) * | 2018-03-01 | 2018-07-31 | 安徽省星灵信息科技有限公司 | A kind of intelligent sorting dustbin |
-
2018
- 2018-12-18 CN CN201811554844.5A patent/CN109684979B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106275945A (en) * | 2016-08-17 | 2017-01-04 | 浪潮电子信息产业股份有限公司 | A kind of garbage recovery device, garbage classification system and using method |
CN106395186A (en) * | 2016-12-05 | 2017-02-15 | 上海商溱环保节能科技有限公司 | Intelligent urban waste bin |
CN107054936A (en) * | 2017-03-23 | 2017-08-18 | 广东数相智能科技有限公司 | A kind of refuse classification prompting dustbin and system based on image recognition |
CN107092914A (en) * | 2017-03-23 | 2017-08-25 | 广东数相智能科技有限公司 | Refuse classification method, device and system based on image recognition |
CN107640480A (en) * | 2017-10-19 | 2018-01-30 | 广东拜登网络技术有限公司 | The method and apparatus and storage medium and terminal device of refuse classification retrospect |
CN107985841A (en) * | 2017-12-25 | 2018-05-04 | 广东南方碳捕集与封存产业中心 | A kind of method of garbage classification and a kind of dustbin |
CN108182455A (en) * | 2018-01-18 | 2018-06-19 | 齐鲁工业大学 | A kind of method, apparatus and intelligent garbage bin of the classification of rubbish image intelligent |
CN108341184A (en) * | 2018-03-01 | 2018-07-31 | 安徽省星灵信息科技有限公司 | A kind of intelligent sorting dustbin |
Cited By (30)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110482072A (en) * | 2019-07-02 | 2019-11-22 | 上海净收智能科技有限公司 | Refuse classification method, system, medium, garbage containing device and cloud platform |
CN111318470A (en) * | 2019-07-02 | 2020-06-23 | 王多 | Method and device for identifying article type |
CN110482072B (en) * | 2019-07-02 | 2022-09-30 | 上海净收智能科技有限公司 | Garbage classification method, system, medium, garbage storage device and cloud platform |
CN110321972A (en) * | 2019-07-22 | 2019-10-11 | 上海五赫自动化科技中心 | A kind of wet refuse classification acceptance test method and its realization device |
CN112298844A (en) * | 2019-07-29 | 2021-02-02 | 杭州海康威视数字技术股份有限公司 | Garbage classification monitoring method and device |
CN112298844B (en) * | 2019-07-29 | 2023-09-22 | 杭州海康威视数字技术股份有限公司 | Garbage classification supervision method and device |
CN110458067A (en) * | 2019-07-31 | 2019-11-15 | 卓尔智联(武汉)研究院有限公司 | Portray method, computer installation and the readable storage medium storing program for executing of user's portrait |
CN110510276A (en) * | 2019-08-02 | 2019-11-29 | 苏州市伏泰信息科技股份有限公司 | A kind of garbage classification equipment based on based on image recognition |
CN110395504A (en) * | 2019-08-06 | 2019-11-01 | 高晓东 | Garbage classification judges the personal method and device for whether carrying out garbage classification |
CN110472565B (en) * | 2019-08-14 | 2023-07-11 | 广东绿润环境科技有限公司 | Method for judging garbage classification capacity based on motion capture |
CN110472565A (en) * | 2019-08-14 | 2019-11-19 | 六安智华工业自动化技术有限公司 | A kind of determination method of the garbage classification ability based on motion capture |
WO2021036145A1 (en) * | 2019-08-29 | 2021-03-04 | 深圳创维-Rgb电子有限公司 | Garbage sorting method, apparatus and system, and computer-readable storage medium |
CN110606292A (en) * | 2019-09-17 | 2019-12-24 | 蔡亦圣 | Automatic classification garbage can based on artificial intelligence and classification method |
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 |
CN110795999A (en) * | 2019-09-21 | 2020-02-14 | 万翼科技有限公司 | Garbage delivery behavior analysis method and related product |
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 |
CN111753844A (en) * | 2020-06-30 | 2020-10-09 | 烟台艾睿光电科技有限公司 | Dry and wet garbage classification method, classification box and classification system |
CN112027424A (en) * | 2020-09-23 | 2020-12-04 | 深圳市康灵盾智能厨具设备有限公司 | Garbage classification and recovery system and garbage classification and recovery method |
CN112183783A (en) * | 2020-10-15 | 2021-01-05 | 张良虎 | Intelligent garbage classification method and system |
CN112183783B (en) * | 2020-10-15 | 2023-12-29 | 明喆集团股份有限公司 | Intelligent garbage classification method and system |
CN112365758A (en) * | 2020-11-10 | 2021-02-12 | 阿尔飞思(昆山)智能物联科技有限公司 | Education version garbage classification method, device and system |
CN114629933A (en) * | 2020-12-10 | 2022-06-14 | 广东省中医院(广州中医药大学第二附属医院、广州中医药大学第二临床医学院、广东省中医药科学院) | Garbage disposal method and device for hospital |
CN114629933B (en) * | 2020-12-10 | 2024-07-12 | 广东省中医院(广州中医药大学第二附属医院、广州中医药大学第二临床医学院、广东省中医药科学院) | Garbage treatment method and device for hospital |
CN112765193A (en) * | 2020-12-28 | 2021-05-07 | 苏州信颐系统集成有限公司 | Management system for garbage classification data acquisition equipment |
CN113682686B (en) * | 2021-08-04 | 2022-07-15 | 浙江联运知慧科技有限公司 | AI algorithm-based monitoring overflow alarm identification method for automatic bag breaking classification box |
CN113682686A (en) * | 2021-08-04 | 2021-11-23 | 浙江联运知慧科技有限公司 | AI algorithm-based monitoring overflow alarm identification method for automatic bag breaking classification box |
CN113837099A (en) * | 2021-09-26 | 2021-12-24 | 浙江力石科技股份有限公司 | Method and device for classifying garbage in image |
CN114345892A (en) * | 2021-12-24 | 2022-04-15 | 苏州嘉诺智能装备有限公司 | Garbage classification processing system and method |
CN114275416A (en) * | 2022-01-19 | 2022-04-05 | 平安国际智慧城市科技股份有限公司 | Kitchen waste classification method, device, equipment and medium based on image recognition |
Also Published As
Publication number | Publication date |
---|---|
CN109684979B (en) | 2021-11-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109684979A (en) | A kind of refuse classification method based on image recognition technology, device and electronic equipment | |
CN110697273B (en) | Household garbage intelligent recognition and automatic classification system and method based on iterative learning control | |
CN110428019B (en) | Intelligent garbage classification method and modularized intelligent garbage classification processing system | |
CN107054936A (en) | A kind of refuse classification prompting dustbin and system based on image recognition | |
CN109703939A (en) | Intelligent garbage recovery system and method | |
CN111573039B (en) | Intelligent garbage classification processing system based on big data | |
CN104495139A (en) | Garbage dropping box and class-based dropping method of garbage | |
CN110294236A (en) | A kind of garbage classification monitoring apparatus, method and server system | |
CN110428352B (en) | Intelligent garbage classification method for wearable equipment and modularized garbage classification system | |
CN204433513U (en) | Case thrown in by rubbish | |
CN108116820A (en) | A kind of Intelligent refuse classification device | |
CN111559588A (en) | Intelligent garbage can for classified garbage throwing and classified garbage throwing method | |
KR20220156603A (en) | Method and electronic device for automated waste management | |
CN106275945A (en) | A kind of garbage recovery device, garbage classification system and using method | |
CN108910340A (en) | A kind of control method and system of intelligent garbage bin | |
CN111453249A (en) | Intelligent kitchen garbage classification barrel based on image analysis | |
CN111661508A (en) | Intelligent garbage classification recycling device based on interaction of Internet and Internet of things | |
CN111832749B (en) | Garbage bag identification method and related device | |
CN113859803A (en) | Intelligent identification trash can and intelligent identification method thereof | |
CN112651318A (en) | Image recognition-based garbage classification method, device and system | |
CN115564376A (en) | Garbage throwing management system and garbage storage system | |
CN111767804A (en) | Recyclable garbage image classification method and system based on artificial intelligence | |
CN115082863A (en) | Intelligent garbage classified putting scanning system and method | |
CN215708916U (en) | Intelligent recognition garbage can | |
CN117465862A (en) | Intelligent garbage can management method and device |
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 |