CN110110752A - A kind of identification of rubbish and classification method, device and terminal device - Google Patents
A kind of identification of rubbish and classification method, device and terminal device Download PDFInfo
- Publication number
- CN110110752A CN110110752A CN201910259503.3A CN201910259503A CN110110752A CN 110110752 A CN110110752 A CN 110110752A CN 201910259503 A CN201910259503 A CN 201910259503A CN 110110752 A CN110110752 A CN 110110752A
- Authority
- CN
- China
- Prior art keywords
- rubbish
- identified
- identification
- recognition result
- sensing data
- 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
-
- E—FIXED CONSTRUCTIONS
- E01—CONSTRUCTION OF ROADS, RAILWAYS, OR BRIDGES
- E01H—STREET CLEANING; CLEANING OF PERMANENT WAYS; CLEANING BEACHES; DISPERSING OR PREVENTING FOG IN GENERAL CLEANING STREET OR RAILWAY FURNITURE OR TUNNEL WALLS
- E01H1/00—Removing undesirable matter from roads or like surfaces, with or without moistening of the surface
- E01H1/005—Mobile installations, particularly for upkeeping in situ road or railway furniture, for instance road barricades, traffic signs; Mobile installations particularly for upkeeping tunnel walls
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/35—Categorising the entire scene, e.g. birthday party or wedding scene
Abstract
The application is suitable for technical field of data processing, provide a kind of identification of rubbish and classification method, device and terminal device, the described method includes: receiving image data to be identified, the image data to be identified is handled using prediction picture processing model, obtains the recognition result of object;When the recognition result is rubbish, rubbish clearance order is returned to, the rubbish clearance order is for controlling the sensing data that sweeping robot acquires the object using preset sensor;The sensing data is received, the sensing data is inputted to preset garbage classification model, obtains the rubbish type of the object;Cleaning modes instruction corresponding with the rubbish type is returned to, the cleaning modes instruction clears up the object according to corresponding cleaning modes for controlling the sweeping robot.The application can solve existing sweeping robot and carry out garbage classification, the bad problem of classifying quality using the mode of picture match.
Description
Technical field
The application belongs to technical field of data processing more particularly to a kind of identification of rubbish and classification method, device and terminal
Equipment.
Background technique
With the development of science and technology, more and more sci-tech products enter in the work and life of people, sweeping robot
It is exactly one of.
Most of sweeping robot is house type sweeping robot at present, and cleaning range is smaller, primarily to cleaning ash
Dirt, food debris, hair and several simple rubbish such as water stain, garbage classification is cleared up it is of less demanding, typically without setting rubbish
Rubbish classification feature.
But for the sweeping robot of outwork, the range of cleaning is big, and environment is complicated, rubbish type multiplicity,
It needs to carry out Rational Classification to rubbish, subsequent garbage disposal could be convenient for.
Current sweeping robot is mainly matched by the picture that camera is shot, and big data training and identification are passed through
Rubbish type in picture, matching degree depends on big data learning training effect, for large-scale place and this model of outdoor location
Big and environment complexity scene is enclosed, needs huge picture library to be trained, since the similarity of image content is matching result
Whether accurate key factor, and sweeping robot shooting picture when, the factors such as shooting angle, exposure rate, color and sound state
The matching result of picture will be influenced, therefore bad using the picture progress matched method using effect of rubbish type.
To sum up, existing sweeping robot carries out garbage classification using the mode of picture match, and classifying quality is bad.
Summary of the invention
In view of this, the embodiment of the present application provides a kind of identification of rubbish and classification method, device and terminal device, with solution
Certainly existing sweeping robot carries out garbage classification, the bad problem of classifying quality using the mode of picture match.
The first aspect of the embodiment of the present application provides a kind of identification of rubbish and classification method, comprising:
Receive image data to be identified, using prediction picture processing model to the image data to be identified at
Reason, obtains the recognition result of object;
When the recognition result is rubbish, rubbish clearance order is returned to, the rubbish clearance order is swept the floor for controlling
Robot acquires the sensing data of the object using preset sensor;
The sensing data is received, the sensing data is inputted to preset garbage classification model, obtains the object
The rubbish type of body;
Cleaning modes instruction corresponding with the rubbish type is returned to, the cleaning modes instruction is for controlling described sweep the floor
Robot clears up the object according to corresponding cleaning modes.
The second aspect of the embodiment of the present application provides a kind of identification of rubbish and sorter, comprising:
Rubbish identification module, for receiving image data to be identified, using prediction picture processing model to described wait know
Other image data is handled, and the recognition result of object is obtained;
Data acquisition module, for returning to rubbish clearance order when the recognition result is rubbish, the rubbish is removed
Instruct the sensing data that the object is acquired for controlling sweeping robot using preset sensor;
The sensing data is inputted preset rubbish point for receiving the sensing data by garbage classification module
Class model obtains the rubbish type of the object;
Classification cleaning modul, for returning to cleaning modes instruction corresponding with the rubbish type, the cleaning modes refer to
It enables and clears up the object according to corresponding cleaning modes for controlling the sweeping robot.
The third aspect of the embodiment of the present application provides a kind of terminal device, including memory, processor and is stored in
In the memory and the computer program that can run on the processor, when the processor executes the computer program
It realizes such as the step of the above method.
The fourth aspect of the embodiment of the present application provides a kind of computer readable storage medium, the computer-readable storage
Media storage has computer program, realizes when the computer program is executed by processor such as the step of the above method.
Existing beneficial effect is the embodiment of the present application compared with prior art:
It the use of prediction picture processing model judgment object whether is rubbish in the rubbish identification of the application and classification method,
Rubbish type is not identified, reduces the requirement to prediction picture processing model and image data to be identified, work as object
When the recognition result of body is rubbish, returns to rubbish clearance order control sweeping robot and use the biography of preset sensor acquisition object
Sensing data is inputted the identification that preset garbage classification model carries out rubbish type by sensor data, improves rubbish type identification
Accuracy, it is determined that after rubbish type, return to corresponding with rubbish type cleaning modes and instruct, instructed by cleaning modes
It controls sweeping robot and clears up object according to corresponding cleaning modes, solve existing sweeping robot and use picture match
Mode carries out garbage classification, the bad problem of classifying quality.
Detailed description of the invention
It in order to more clearly explain the technical solutions in the embodiments of the present application, below will be to embodiment or description of the prior art
Needed in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description is only some of the application
Embodiment for those of ordinary skill in the art without creative efforts, can also be attached according to these
Figure obtains other attached drawings.
Fig. 1 is the implementation process schematic diagram of a kind of rubbish identification and classification method provided by the embodiments of the present application;
Fig. 2 is the schematic diagram of a kind of rubbish identification and sorter provided by the embodiments of the present application;
Fig. 3 is the schematic diagram of terminal device provided by the embodiments of the present application.
Specific embodiment
In being described below, for illustration and not for limitation, the tool of such as particular system structure, technology etc is proposed
Body details, so as to provide a thorough understanding of the present application embodiment.However, it will be clear to one skilled in the art that there is no these specific
The application also may be implemented in the other embodiments of details.In other situations, it omits to well-known system, device, electricity
The detailed description of road and method, so as not to obscure the description of the present application with unnecessary details.
In order to illustrate technical solution described herein, the following is a description of specific embodiments.
It should be appreciated that ought use in this specification and in the appended claims, term " includes " instruction is described special
Sign, entirety, step, operation, the presence of element and/or component, but be not precluded one or more of the other feature, entirety, step,
Operation, the presence or addition of element, component and/or its set.
It is also understood that mesh of the term used in this present specification merely for the sake of description specific embodiment
And be not intended to limit the application.As present specification and it is used in the attached claims, unless on
Other situations are hereafter clearly indicated, otherwise " one " of singular, "one" and "the" are intended to include plural form.
It will be further appreciated that the term "and/or" used in present specification and the appended claims is
Refer to any combination and all possible combinations of one or more of associated item listed, and including these combinations.
As used in this specification and in the appended claims, term " if " can be according to context quilt
Be construed to " when ... " or " once " or " in response to determination " or " in response to detecting ".Similarly, phrase " if it is determined that " or
" if detecting [described condition or event] " can be interpreted to mean according to context " once it is determined that " or " in response to true
It is fixed " or " once detecting [described condition or event] " or " in response to detecting [described condition or event] ".
In addition, term " first ", " second " etc. are only used for distinguishing description, and should not be understood as in the description of the present application
Indication or suggestion relative importance.
Embodiment one:
A kind of rubbish that the embodiment of the present application one provides is identified below and classification method is described, please refers to attached drawing 1,
Rubbish identification and classification method in the embodiment of the present application one include:
Step S101, image data to be identified is received, using prediction picture processing model to the picture to be identified
Data are handled, and the recognition result of object is obtained;
Sweeping robot can be shot to be identified during the regions Mobile cleaning such as large-scale place by camera
Image data.
When receiving image data to be identified, prediction picture processing model can be used to image data to be identified
It is handled, obtains the recognition result of object.
Currently using image recognition carry out rubbish type identification when, image recognition model not only to differentiate object whether be
Rubbish will also accurately differentiate rubbish type, and the requirement to image recognition model is high, and training process needs huge picture library, and
And to the image quality requirements of the image data to be identified of sweeping robot shooting during image recognition mode use
Height causes rubbish type identification wrong probably due to the factors such as shooting angle, exposure rate, color and sound state influence picture quality
Accidentally.
And in the identification of the rubbish of the present embodiment and classification method, it only uses image data to be identified and carries out rubbish knowledge
Not, it does not require to differentiate rubbish type, significantly reduces the requirement to prediction picture processing model, reduce modeling difficulty, and
And the image data of sweeping robot shooting high quality is not required yet.
Step S102, when the recognition result is rubbish, rubbish clearance order is returned to, the rubbish clearance order is used for
Control sweeping robot acquires the sensing data of the object using preset sensor;
When recognition result is rubbish, returning to rubbish clearance order can when sweeping robot receives rubbish clearance order
To be moved to around object according to rubbish clearance order, the sensing data of preset sensor acquisition object is used.
Preset sensor can include but is not limited to sonic transducer, optical sensor, temperature sensor, humidity sensor and again
One of quantity sensor is a variety of.
Step S103, the sensing data is received, the sensing data is inputted to preset garbage classification model, is obtained
To the rubbish type of the object;
When receiving sensing data, sensing data is inputted in preset garbage classification model, obtain object
Rubbish type.
It can be convenient the identification for accurately carrying out rubbish type, such as a transparent bottle using sensing data, such as
It is plastic bottle or vial that fruit, which carries out identification bottle by image data, and a large amount of image data is needed to be trained, and
There are higher error rates, and if collecting sensor parameters by sensors such as optical sensor, weight sensors carries out rubbish
The identification of rubbish type, not only identification process is simple, but also the accuracy rate identified is much higher than the standard identified by image data
True rate.
Step S104, cleaning modes instruction corresponding with the rubbish type is returned to, the cleaning modes instruction is for controlling
It makes the sweeping robot and clears up the object according to corresponding cleaning modes.
Different rubbish types can correspond to different cleaning modes, after the rubbish type of object has been determined, can return
Cleaning modes instruction corresponding with rubbish type is returned, control sweeping robot clears up object according to corresponding cleaning modes.
Further, described to receive image data to be identified, using prediction picture processing model to described to be identified
Image data is handled, and the recognition result for obtaining object specifically includes:
A1, receive image data to be identified, using prediction picture processing model to the image data to be identified into
Row processing, obtains the first profile characteristic value of object;
When carrying out rubbish identification using image data to be identified, prediction picture processing model can be used to be identified
Image data handled, obtain the first profile characteristic value of object.
Prediction picture processing model can be selected according to the actual situation, such as can be developed by Opencv function library
It realizes.
A2, the first profile characteristic value is matched with the second contour feature value in junk data library;
Staff can store the second contour feature value of preparatory collected various rubbish objects to junk data library
In, when obtaining the first profile characteristic value of object, first profile characteristic value is matched with the second contour feature value, according to
Whether matching result judgment object is rubbish.
If A3, the first profile characteristic value and the second contour feature value successful match, the identification of the object
It as a result is rubbish.
If first profile characteristic value and the second contour feature value successful match, then it represents that the recognition result of object is rubbish
Rubbish can be cleared up.
In addition, when the recognition result is rubbish, being returned when using contour feature value judgment object whether for rubbish
Rubbish clearance order, the rubbish clearance order is for controlling the biography that sweeping robot acquires the object using preset sensor
Sensor data specifically include:
When the recognition result is rubbish, sensor type is determined according to the first profile characteristic value of the object;
Rubbish clearance order corresponding with the sensor type is returned to, the rubbish clearance order is for controlling sweeper
Device people acquires the sensing data of the object using preset sensor corresponding with the sensor type.
Such as object first profile characteristic value corresponding with bottle the second contour feature value successful match when, can control
Sweeping robot acquires sensing data using all types of sensors, can also determine rubbish according to first profile characteristic value
The sensor type of Classification and Identification, such as sweeping robot have multiple sensors, but select one or more of them specific aim
Sensor acquire sensing data, according to sensing data recognize bottle material, determine rubbish type.
Further, described to receive image data to be identified, using prediction picture processing model to described to be identified
Image data is handled, and the recognition result of object is obtained further include:
If B1, the first profile characteristic value are with the second contour feature value, it fails to match, in such a way that first warns
It warns;
If first profile characteristic value is with the second contour feature value, it fails to match, then it represents that without corresponding in junk data library
Data, it may not also be rubbish that object, which may be rubbish, at this time, and sweeping robot can ignore the object without cleaning, or
It can be warned by the first mode of warning, staff is reminded to carry out manual identified.
First mode of warning can be the modes such as text, voice, vibration, and the first specific setting for warning mode can basis
Actual needs is selected.
B2, artificial identification information is received, if the manual identified information is rubbish, the recognition result of the object is rubbish
Rubbish and the first profile characteristic value is stored in the junk data library, if the manual identified information is non-junk, institute
The recognition result for stating object is non-junk.
After staff carries out manual identified to object, manual identified information can be returned to, if manual identified is believed
Breath is rubbish, then the recognition result of object is rubbish, the first profile characteristic value can be stored in junk data library at this time, rich
The second contour feature value in rich junk data library.
If manual identified information is non-junk, then it represents that the object is not rubbish, and the recognition result of object is non-rubbish
Rubbish.
Further, described to receive the sensing data, the sensing data is inputted to preset garbage classification mould
Type, the rubbish type for obtaining the object specifically include:
C1, the sensing data is received, the sensing data is inputted into preset garbage classification model and is matched, is sentenced
It is disconnected whether successful match;
When receiving sensing data, sensing data can be inputted in preset garbage classification model and be matched,
Identify the rubbish type of object.
It is can be set in preset garbage classification model there are many rubbish type, corresponding biography is set for every kind of rubbish type
The sensing data received is compared with sensor parameters threshold value, determines rubbish type by sensor parameter threshold, for example,
The sensor parameters threshold values such as temperature, humidity, sound, light, the weight of a certain rubbish type can be set, then by sensing data
It is compared with these sensor parameters threshold values, if all meeting the standard of the rubbish type, it is determined that the rubbish class of the object
Type.
If C2, successful match obtain the rubbish type of the object;
If the sensing data of object meets the standard of certain a kind of rubbish type, successful match then obtains the object
Rubbish type.
If C3, it fails to match, warn in such a way that second warns simultaneously recipient's work point category information, according to described artificial
Classification information obtains the rubbish type of the object.
If the sensing data of object can not be matched with the standard of each rubbish type in preset garbage classification model,
It can be warned by the second mode of warning, staff is reminded to carry out manual identified rubbish type.
Second mode of warning can be the modes such as text, voice, vibration, and the second specific setting for warning mode can basis
Actual needs is selected.
After staff carries out the identification of rubbish type to object, manual sort's information is returned, is manually divided when receiving
When category information, the rubbish type of object can be obtained according to manual sort's information.
In addition, manual sort's information can also include the corresponding sensor parameters standard of the rubbish type, when obtaining object
Rubbish type when, the rubbish type and the corresponding sensor parameters standard of the rubbish type can also be added to preset rubbish
Rubbish disaggregated model improves the classification capacity of preset garbage classification model.
Above-mentioned rubbish identification and classification method can be applied on the remote equipments such as server, can also apply in sweeper
On the processor of device people local, for example, sweeping robot can acquire image data and sensing data to be identified, then on
Server is passed to, whether is rubbish and discrimination rubbish type by server identification object, returns to corresponding instruction and arrive sweeper
Device people;Alternatively, after sweeping robot can acquire image data and sensing data to be identified, directly in sweeping robot
It is handled on local processor, whether identification object is rubbish and discrimination rubbish type.Above-mentioned rubbish identification and classification
The concrete application mode of method, can be configured according to the actual situation.
In the rubbish identification and classification method that the present embodiment one provides, whether model judgment object is handled using prediction picture
For rubbish, rubbish type is not identified, reduces and prediction picture processing model and image data to be identified are wanted
It asks, when the recognition result of object is rubbish, returns to rubbish clearance order control sweeping robot and acquired using preset sensor
Sensing data is inputted the identification that preset garbage classification model carries out rubbish type, improves rubbish by the sensing data of object
The accuracy of type identification, it is determined that after rubbish type, return to cleaning modes instruction corresponding with rubbish type, pass through cleaning
Mode instruction controls sweeping robot and clears up object according to corresponding cleaning modes, solves existing sweeping robot and uses figure
The matched mode of piece carries out garbage classification, the bad problem of classifying quality.
When by image data judgment object to be identified whether being rubbish, the first profile feature of object can be extracted
Value, is matched with the second contour feature value in junk data library by first profile characteristic value, is judged according to matching result
Whether object is rubbish.
When that can not be matched by first profile characteristic value with the second contour feature value in junk data library, can pass through
First mode of warning is warned, and staff is reminded to carry out manual identified, further increases the accuracy of rubbish identification.
When carrying out garbage classification, sensing data can be inputted to preset garbage classification model and matched, matching at
Function then obtains the rubbish type of rubbish, and it fails to match, then rubbish type can be determined by way of manual sort, thus really
Protect the accuracy of garbage classification.
It should be understood that the size of the serial number of each step is not meant that the order of the execution order in above-described embodiment, each process
Execution sequence should be determined by its function and internal logic, the implementation process without coping with the embodiment of the present application constitutes any limit
It is fixed.
Embodiment two:
The embodiment of the present application two provides a kind of identification of rubbish and sorter, for purposes of illustration only, only showing and the application
Relevant part, as shown in Fig. 2, rubbish identification and sorter include,
Rubbish identification module 201, for receiving image data to be identified, using prediction picture processing model to it is described to
The image data of identification is handled, and the recognition result of object is obtained;
Data acquisition module 202, for returning to rubbish clearance order, the rubbish when the recognition result is rubbish
Clearance order is for controlling the sensing data that sweeping robot acquires the object using preset sensor;
The sensing data is inputted preset rubbish for receiving the sensing data by garbage classification module 203
Disaggregated model obtains the rubbish type of the object;
Classification cleaning modul 204, for returning to cleaning modes instruction corresponding with the rubbish type, the cleaning modes
Instruction clears up the object according to corresponding cleaning modes for controlling the sweeping robot.
Further, the rubbish identification module specifically includes:
Characteristic value submodule, for receiving image data to be identified, using prediction picture processing model to described wait know
Other image data is handled, and the first profile characteristic value of object is obtained;
Matched sub-block, for carrying out the second contour feature value in the first profile characteristic value and junk data library
Matching;
Identify submodule, if for the first profile characteristic value and the second contour feature value successful match, institute
The recognition result for stating object is rubbish.
Further, the rubbish identification module further include:
First warns submodule, if it fails to match with the second contour feature value for the first profile characteristic value,
Then warn in such a way that first warns;
Manual identified submodule, for receiving artificial identification information, if the manual identified information is rubbish, the object
The recognition result of body is rubbish and the first profile characteristic value is stored in the junk data library, if the manual identified is believed
Breath is non-junk, then the recognition result of the object is non-junk.
Further, the garbage classification module specifically includes:
The sensing data is inputted preset rubbish point for receiving the sensing data by category of model submodule
Class model is matched, and judges whether successful match;
Successful classification submodule obtains the rubbish type of the object if being used for successful match;
Manual sort's submodule, if being warned in such a way that second warns for it fails to match and receiving manual sort
Information obtains the rubbish type of the object according to manual sort's information.
It should be noted that the contents such as information exchange, implementation procedure between above-mentioned apparatus/unit, due to the application
Embodiment of the method is based on same design, concrete function and bring technical effect, for details, reference can be made to embodiment of the method part, this
Place repeats no more.
Embodiment three:
Fig. 3 is the schematic diagram for the terminal device that the embodiment of the present application three provides.As shown in figure 3, the terminal of the embodiment is set
Standby 3 include: processor 30, memory 31 and are stored in the meter that can be run in the memory 31 and on the processor 30
Calculation machine program 32.The processor 30 realizes above-mentioned rubbish identification and classification method embodiment when executing the computer program 32
In step, such as step S101 to S104 shown in FIG. 1.Alternatively, when the processor 30 executes the computer program 32
Realize the function of each module/unit in above-mentioned each Installation practice, such as the function of module 201 to 204 shown in Fig. 2.
Illustratively, the computer program 32 can be divided into one or more module/units, it is one or
Multiple module/units are stored in the memory 31, and are executed by the processor 30, to complete the application.Described one
A or multiple module/units can be the series of computation machine program instruction section that can complete specific function, which is used for
Implementation procedure of the computer program 32 in the terminal device 3 is described.For example, the computer program 32 can be divided
It is cut into rubbish identification module, data acquisition module, garbage classification module and classification cleaning modul, each module concrete function is such as
Under:
Rubbish identification module, for receiving image data to be identified, using prediction picture processing model to described wait know
Other image data is handled, and the recognition result of object is obtained;
Data acquisition module, for returning to rubbish clearance order when the recognition result is rubbish, the rubbish is removed
Instruct the sensing data that the object is acquired for controlling sweeping robot using preset sensor;
The sensing data is inputted preset rubbish point for receiving the sensing data by garbage classification module
Class model obtains the rubbish type of the object;
Classification cleaning modul, for returning to cleaning modes instruction corresponding with the rubbish type, the cleaning modes refer to
It enables and clears up the object according to corresponding cleaning modes for controlling the sweeping robot.
The terminal device 3 can be the calculating such as desktop PC, notebook, palm PC and cloud server and set
It is standby.The terminal device may include, but be not limited only to, processor 30, memory 31.It will be understood by those skilled in the art that Fig. 3
The only example of terminal device 3 does not constitute the restriction to terminal device 3, may include than illustrating more or fewer portions
Part perhaps combines certain components or different components, such as the terminal device can also include input-output equipment, net
Network access device, bus etc..
Alleged processor 30 can be central processing unit (Central Processing Unit, CPU), can also be
Other general processors, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), field programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor is also possible to any conventional processor
Deng.
The memory 31 can be the internal storage unit of the terminal device 3, such as the hard disk or interior of terminal device 3
It deposits.The memory 31 is also possible to the External memory equipment of the terminal device 3, such as be equipped on the terminal device 3
Plug-in type hard disk, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card dodge
Deposit card (Flash Card) etc..Further, the memory 31 can also both include the storage inside list of the terminal device 3
Member also includes External memory equipment.The memory 31 is for storing needed for the computer program and the terminal device
Other programs and data.The memory 31 can be also used for temporarily storing the data that has exported or will export.
It is apparent to those skilled in the art that for convenience of description and succinctly, only with above-mentioned each function
Can unit, module division progress for example, in practical application, can according to need and by above-mentioned function distribution by different
Functional unit, module are completed, i.e., the internal structure of described device is divided into different functional unit or module, more than completing
The all or part of function of description.Each functional unit in embodiment, module can integrate in one processing unit, can also
To be that each unit physically exists alone, can also be integrated in one unit with two or more units, it is above-mentioned integrated
Unit both can take the form of hardware realization, can also realize in the form of software functional units.In addition, each function list
Member, the specific name of module are also only for convenience of distinguishing each other, the protection scope being not intended to limit this application.Above system
The specific work process of middle unit, module, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, is not described in detail or remembers in some embodiment
The part of load may refer to the associated description of other embodiments.
Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
It is implemented in hardware or software, the specific application and design constraint depending on technical solution.Professional technician
Each specific application can be used different methods to achieve the described function, but this realization is it is not considered that exceed
Scope of the present application.
In embodiment provided herein, it should be understood that disclosed device/terminal device and method, it can be with
It realizes by another way.For example, device described above/terminal device embodiment is only schematical, for example, institute
The division of module or unit is stated, only a kind of logical function partition, there may be another division manner in actual implementation, such as
Multiple units or components can be combined or can be integrated into another system, or some features can be ignored or not executed.Separately
A bit, shown or discussed mutual coupling or direct-coupling or communication connection can be through some interfaces, device
Or the INDIRECT COUPLING or communication connection of unit, it can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, each functional unit in each embodiment of the application can integrate in one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
If the integrated module/unit be realized in the form of SFU software functional unit and as independent product sale or
In use, can store in a computer readable storage medium.Based on this understanding, the application realizes above-mentioned implementation
All or part of the process in example method, can also instruct relevant hardware to complete, the meter by computer program
Calculation machine program can be stored in a computer readable storage medium, the computer program when being executed by processor, it can be achieved that on
The step of stating each embodiment of the method.Wherein, the computer program includes computer program code, the computer program generation
Code can be source code form, object identification code form, executable file or certain intermediate forms etc..The computer-readable medium
It may include: any entity or device, recording medium, USB flash disk, mobile hard disk, magnetic that can carry the computer program code
Dish, CD, computer storage, read-only memory (ROM, Read-Only Memory), random access memory (RAM,
Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium etc..It should be noted that described
The content that computer-readable medium includes can carry out increasing appropriate according to the requirement made laws in jurisdiction with patent practice
Subtract, such as does not include electric carrier signal and electricity according to legislation and patent practice, computer-readable medium in certain jurisdictions
Believe signal.
Embodiment described above is only to illustrate the technical solution of the application, rather than its limitations;Although referring to aforementioned reality
Example is applied the application is described in detail, those skilled in the art should understand that: it still can be to aforementioned each
Technical solution documented by embodiment is modified or equivalent replacement of some of the technical features;And these are modified
Or replacement, the spirit and scope of each embodiment technical solution of the application that it does not separate the essence of the corresponding technical solution should all
Comprising within the scope of protection of this application.
Claims (10)
1. a kind of rubbish identification and classification method characterized by comprising
Image data to be identified is received, the image data to be identified is handled using prediction picture processing model,
Obtain the recognition result of object;
When the recognition result is rubbish, rubbish clearance order is returned to, the rubbish clearance order is for controlling machine of sweeping the floor
People acquires the sensing data of the object using preset sensor;
The sensing data is received, the sensing data is inputted to preset garbage classification model, obtains the object
Rubbish type;
Cleaning modes instruction corresponding with the rubbish type is returned to, the cleaning modes instruction is for controlling the machine of sweeping the floor
People clears up the object according to corresponding cleaning modes.
2. rubbish identification as described in claim 1 and classification method, which is characterized in that described to receive picture number to be identified
According to, using prediction picture processing model the image data to be identified is handled, the recognition result for obtaining object is specific
Include:
Image data to be identified is received, the image data to be identified is handled using prediction picture processing model,
Obtain the first profile characteristic value of object;
The first profile characteristic value is matched with the second contour feature value in junk data library;
If the first profile characteristic value and the second contour feature value successful match, the recognition result of the object is rubbish
Rubbish.
3. rubbish identification as claimed in claim 2 and classification method, which is characterized in that described to receive picture number to be identified
According to, using prediction picture processing model the image data to be identified is handled, the recognition result for obtaining object also wraps
It includes:
If the first profile characteristic value is with the second contour feature value, it fails to match, is shown in such a way that first warns
It is alert;
Artificial identification information is received, if the manual identified information is rubbish, the recognition result of the object is rubbish and will
The first profile characteristic value is stored in the junk data library, if the manual identified information is non-junk, the object
Recognition result be non-junk.
4. rubbish identification as described in claim 1 and classification method, which is characterized in that it is described to receive the sensing data,
The sensing data is inputted to preset garbage classification model, the rubbish type for obtaining the object specifically includes:
The sensing data is received, the sensing data is inputted into preset garbage classification model and is matched, is judged whether
Successful match;
If successful match, the rubbish type of the object is obtained;
If it fails to match, warn in such a way that second warns simultaneously recipient's work point category information, is believed according to the manual sort
Breath obtains the rubbish type of the object.
5. a kind of rubbish identification and sorter characterized by comprising
Rubbish identification module, for receiving image data to be identified, using prediction picture processing model to described to be identified
Image data is handled, and the recognition result of object is obtained;
Data acquisition module, for returning to rubbish clearance order, the rubbish clearance order when the recognition result is rubbish
The sensing data of the object is acquired for controlling sweeping robot using preset sensor;
The sensing data is inputted preset garbage classification mould for receiving the sensing data by garbage classification module
Type obtains the rubbish type of the object;
Classification cleaning modul, for returning to cleaning modes instruction corresponding with the rubbish type, the cleaning modes instruction use
The object is cleared up according to corresponding cleaning modes in controlling the sweeping robot.
6. rubbish identification as claimed in claim 5 and sorter, which is characterized in that the rubbish identification module specifically wraps
It includes:
Characteristic value submodule, for receiving image data to be identified, using prediction picture processing model to described to be identified
Image data is handled, and the first profile characteristic value of object is obtained;
A matched sub-block, for carrying out the second contour feature value in the first profile characteristic value and junk data library
Match;
Identify submodule, if for the first profile characteristic value and the second contour feature value successful match, the object
The recognition result of body is rubbish.
7. rubbish identification as claimed in claim 6 and sorter, which is characterized in that the rubbish identification module further include:
First warns submodule, if it fails to match with the second contour feature value for the first profile characteristic value, with
First mode of warning is warned;
Manual identified submodule, for receiving artificial identification information, if the manual identified information is rubbish, the object
Recognition result is rubbish and the first profile characteristic value is stored in the junk data library, if the manual identified information is
Non-junk, then the recognition result of the object is non-junk.
8. rubbish identification as claimed in claim 5 and sorter, which is characterized in that the garbage classification module is specifically wrapped
It includes:
The sensing data is inputted preset garbage classification mould for receiving the sensing data by category of model submodule
Type is matched, and judges whether successful match;
Successful classification submodule obtains the rubbish type of the object if being used for successful match;
Manual sort's submodule, if warn in such a way that second warns simultaneously recipient's work point category information for it fails to match,
The rubbish type of the object is obtained according to manual sort's information.
9. a kind of terminal device, including memory, processor and storage are in the memory and can be on the processor
The computer program of operation, which is characterized in that the processor realizes such as Claims 1-4 when executing the computer program
The step of any one the method.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists
In when the computer program is executed by processor the step of any one of such as Claims 1-4 of realization the method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910259503.3A CN110110752A (en) | 2019-04-01 | 2019-04-01 | A kind of identification of rubbish and classification method, device and terminal device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910259503.3A CN110110752A (en) | 2019-04-01 | 2019-04-01 | A kind of identification of rubbish and classification method, device and terminal device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110110752A true CN110110752A (en) | 2019-08-09 |
Family
ID=67484757
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910259503.3A Pending CN110110752A (en) | 2019-04-01 | 2019-04-01 | A kind of identification of rubbish and classification method, device and terminal device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110110752A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110490246A (en) * | 2019-08-15 | 2019-11-22 | 中云信安(深圳)科技有限公司 | Rubbish classification determines method, apparatus, storage medium and electronic equipment |
CN110897555A (en) * | 2019-11-29 | 2020-03-24 | 北京石头世纪科技股份有限公司 | Garbage classification method, device, medium and electronic equipment |
CN110924340A (en) * | 2019-11-25 | 2020-03-27 | 武汉思睿博特自动化系统有限公司 | Mobile robot system for intelligently picking up garbage and implementation method |
CN111008571A (en) * | 2019-11-15 | 2020-04-14 | 万翼科技有限公司 | Indoor garbage treatment method and related product |
CN114869187A (en) * | 2022-05-30 | 2022-08-09 | 广州软件学院 | Cleaning method and system of intelligent fish tank cleaning robot |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105268654A (en) * | 2014-06-30 | 2016-01-27 | 张晓冬 | Intelligent garbage classification device based on multiple sensors of single chip microcomputer |
CN106185115A (en) * | 2016-07-19 | 2016-12-07 | 西华大学 | A kind of classified-refuse recovery system |
CN106302397A (en) * | 2016-07-29 | 2017-01-04 | 北京北信源软件股份有限公司 | A kind of equipment identification system based on device-fingerprint |
CN106444786A (en) * | 2016-11-29 | 2017-02-22 | 北京小米移动软件有限公司 | Control method, device and electronic equipment of floor mopping robot |
CN107457788A (en) * | 2017-08-09 | 2017-12-12 | 苏州阿甘机器人有限公司 | A kind of family expenses are swept the floor and looked for something robot and its method of work |
CN107877521A (en) * | 2017-11-06 | 2018-04-06 | 广西富迈科技有限公司 | Article identifies and processing method, robot terminal and storage medium |
CN108009583A (en) * | 2017-11-30 | 2018-05-08 | 速感科技(北京)有限公司 | A kind of intelligent movable equipment looked for something and intelligent method of looking for something |
CN108275394A (en) * | 2018-02-11 | 2018-07-13 | 陕西科技大学 | A kind of automatic classification appts. for house refuse |
-
2019
- 2019-04-01 CN CN201910259503.3A patent/CN110110752A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105268654A (en) * | 2014-06-30 | 2016-01-27 | 张晓冬 | Intelligent garbage classification device based on multiple sensors of single chip microcomputer |
CN106185115A (en) * | 2016-07-19 | 2016-12-07 | 西华大学 | A kind of classified-refuse recovery system |
CN106302397A (en) * | 2016-07-29 | 2017-01-04 | 北京北信源软件股份有限公司 | A kind of equipment identification system based on device-fingerprint |
CN106444786A (en) * | 2016-11-29 | 2017-02-22 | 北京小米移动软件有限公司 | Control method, device and electronic equipment of floor mopping robot |
CN107457788A (en) * | 2017-08-09 | 2017-12-12 | 苏州阿甘机器人有限公司 | A kind of family expenses are swept the floor and looked for something robot and its method of work |
CN107877521A (en) * | 2017-11-06 | 2018-04-06 | 广西富迈科技有限公司 | Article identifies and processing method, robot terminal and storage medium |
CN108009583A (en) * | 2017-11-30 | 2018-05-08 | 速感科技(北京)有限公司 | A kind of intelligent movable equipment looked for something and intelligent method of looking for something |
CN108275394A (en) * | 2018-02-11 | 2018-07-13 | 陕西科技大学 | A kind of automatic classification appts. for house refuse |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110490246A (en) * | 2019-08-15 | 2019-11-22 | 中云信安(深圳)科技有限公司 | Rubbish classification determines method, apparatus, storage medium and electronic equipment |
CN110490246B (en) * | 2019-08-15 | 2022-05-03 | 中云信安(深圳)科技有限公司 | Garbage category determination method and device, storage medium and electronic equipment |
CN111008571A (en) * | 2019-11-15 | 2020-04-14 | 万翼科技有限公司 | Indoor garbage treatment method and related product |
CN111008571B (en) * | 2019-11-15 | 2023-04-18 | 万翼科技有限公司 | Indoor garbage treatment method and related product |
CN110924340A (en) * | 2019-11-25 | 2020-03-27 | 武汉思睿博特自动化系统有限公司 | Mobile robot system for intelligently picking up garbage and implementation method |
CN110897555A (en) * | 2019-11-29 | 2020-03-24 | 北京石头世纪科技股份有限公司 | Garbage classification method, device, medium and electronic equipment |
CN114869187A (en) * | 2022-05-30 | 2022-08-09 | 广州软件学院 | Cleaning method and system of intelligent fish tank cleaning robot |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110110752A (en) | A kind of identification of rubbish and classification method, device and terminal device | |
CN109344894A (en) | Garbage classification recognition methods and device based on Multi-sensor Fusion and deep learning | |
Pope | Model-based object recognition | |
CN111012261A (en) | Sweeping method and system based on scene recognition, sweeping equipment and storage medium | |
CN110813792B (en) | Intelligent garbage recognition and classification method | |
CN110087193A (en) | Information uploading method, device, electronic equipment and the readable storage medium storing program for executing of dustbin | |
WO2002001505A1 (en) | Information converting system | |
CN111813997A (en) | Intrusion analysis method, device, equipment and storage medium | |
CN107808126A (en) | Vehicle retrieval method and device | |
CN109598301B (en) | Detection area removing method, device, terminal and storage medium | |
CN111428822A (en) | Article identification method, device and equipment, intelligent container and intelligent container system | |
CN113642474A (en) | Hazardous area personnel monitoring method based on YOLOV5 | |
CN110516625A (en) | A kind of method, system, terminal and the storage medium of rubbish identification classification | |
CN110069546A (en) | A kind of data classification method, device for classifying data and terminal device | |
CN111274886A (en) | Deep learning-based pedestrian red light violation analysis method and system | |
CN115545441A (en) | Road garbage detection method, system, terminal and storage medium | |
CN116682098A (en) | Automatic urban household garbage identification and classification system and method | |
Shankar et al. | A framework to enhance object detection performance by using YOLO algorithm | |
CN111767902A (en) | Method, device and equipment for identifying dangerous goods of security check machine and storage medium | |
CN114955289A (en) | Intelligent garbage classification recycling and management method and intelligent classification garbage can | |
CN110516751A (en) | Processing method, system and the equipment of three-dimensional data | |
US11276285B2 (en) | Artificial intelligence based motion detection | |
CN108960343A (en) | A kind of solid waste recognition methods, system, device and readable storage medium storing program for executing | |
CN111401370A (en) | Method, model and system for identifying junk images and assigning and managing tasks | |
CN112734699A (en) | Article state warning method and device, storage medium and electronic 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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190809 |
|
RJ01 | Rejection of invention patent application after publication |