CN109977975A - Article recovery system and article recovery method - Google Patents
Article recovery system and article recovery method Download PDFInfo
- Publication number
- CN109977975A CN109977975A CN201711456501.0A CN201711456501A CN109977975A CN 109977975 A CN109977975 A CN 109977975A CN 201711456501 A CN201711456501 A CN 201711456501A CN 109977975 A CN109977975 A CN 109977975A
- Authority
- CN
- China
- Prior art keywords
- article
- module
- robot
- server
- information
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Manipulator (AREA)
Abstract
The present invention provides a kind of article recovery systems, including robot and server;The robot includes control module, and connect respectively with control module for detecting whether sensor, the photographing module for acquiring item image information, the human-computer interaction module for inputting taxonomy of goods information, the communication module for the item image information and taxonomy of goods information to be uploaded to server for thering is user to rest in front of robot;The server is used to receive the item image information of communication module upload and the taxonomy of goods information of user's input, server includes the vision processing module for handling item image information to generate article characteristic information, for the study module according to article characteristics information architecture article characteristics model, and the vision library for storing the taxonomy of goods information that the article characteristics model and user are inputted by human-computer interaction module.The taxonomy of goods recycling of precise and high efficiency may be implemented in the present invention.
Description
Technical field
The present invention relates to taxonomy of goods recovery technology field, in particular to a kind of article recovery system and article recycling side
Method.
Background technique
As the improvement of people's living standards, the life of people has been come into the public places such as more and more market, amusement parks
It is living.How the rubbish that people generate in shopping and recreation to be accurately subjected to classification recycling, becomes cleaning industry and be badly in need of
It solves the problems, such as.
Current existing method is all that class indication is arranged on dustbin by artificial, is carried out by people's consciousness
Waste sorting recycle.This mode cannot be guaranteed the correctness of classification recycling, and the correctness of garbage classification depends entirely on a
The consciousness of people lacks subjective initiative.
Summary of the invention
Present invention seek to address that one of the problems of the prior art, improve the accuracy rate and effect of rubbish and other items classification recycling
Rate provides a kind of article recovery system.
Article recovery system of the invention includes robot and server;The robot includes control module, Yi Jifen
It is not connect with control module for detecting whether there is user to rest on sensor in front of robot, for acquiring images of items
The photographing module of information, the human-computer interaction module for inputting taxonomy of goods information, for by the item image information and
Taxonomy of goods information is uploaded to the communication module of server;The server is used to receive the images of items letter of communication module upload
The taxonomy of goods information of breath and user's input, server includes for handling item image information to generate article characteristic information
Vision processing module, it is described for the study module according to article characteristics information architecture article characteristics model, and for storing
The vision library of article characteristics model, taxonomy of goods information and article characteristics information.
The present invention is recycled by using the classification that robot carries out human lives' rubbish and other items, and makes robot and cloud
Server is communicated, special by the article characteristics information for acquiring robot and article pre-stored in server by server
Sign model is matched, to realize the function of the Fast Classification recycling of rubbish and other items.If match unsuccessful, robot can
To prompt user to input taxonomy of goods information by human-computer interaction module, while study module, Ke Yitong are provided in server
The overfitting module article characteristics model new according to article characteristics information architecture, and by article characteristics information, article characteristics model
It is corresponding with the taxonomy of goods information of user's input to store into the vision library of server, when occurring ware again, be
System can be by the article characteristics information and last stored that occur again article characteristics information and article characteristics mould in vision library
Type is matched, to obtain corresponding taxonomy of goods information, can carry out the classification recycling of precise and high efficiency in this way.Of the invention
Article recovery system has the ability of self study, effectively increases the efficiency and accuracy of taxonomy of goods recycling.Object of the invention
Product recovery system can constantly learn and establish new article characteristics model while realizing automatic garbage classification, and will figure
It is completed as the function of processing, matching and self study is placed in cloud server, the system requirements to recycling terminal can be reduced,
Reduce the configuration of recycling terminal.
According to one embodiment of present invention, the robot further includes drive module, and the drive module is for driving
Robot ambulation.
According to one embodiment of present invention, the robot further includes navigation module, the navigation module and the control
The connection of molding block, the track route for planning robot.Robot can be roamed by the route that navigation module is planned,
Improve the recovery efficiency of human lives' rubbish and other items in megastore or public place of entertainment.
According to one embodiment of present invention, the human-computer interaction module includes voice module and touch screen module.It is described
Voice module is for prompting user to input taxonomy of goods information by touch screen module.
According to one embodiment of present invention, the robot further includes multiple storage barrels and pallet, the pallet setting
It is used for article to be recycled described in classification storage for carrying article to be recycled, the multiple storage barrel in the top of storage barrel,
The drive module is also used to that the storage barrel and pallet is driven to act.The drive module can drive multiple storage barrels to move
So that the storage barrel of specified classification moves to below pallet, and drive pallet rotation so that article thereon falls to specified storage
It deposits in bucket.
Another aspect of the present invention provides a kind of method of article recycling, and the article recovery method is by that can carry out nothing
The robot and server of line communication complete, comprising the following steps:
S1: whether robot detection front has user's stop;
S2: when detecting that there is user's stop in front, the control module control photographing module detection robot of robot
It whether there is article to be recycled on pallet, such as exist, photographing module shoots article photo;
S3: the control module of robot controls communication module for the article photo upload to server;
S4: the vision processing module of the server extracts article characteristic information by article photo, and by the article
Characteristic information is matched with the article characteristics model being pre-stored in server vision library;
S5: such as successful match, then server sends successful match instruction to the communication module of robot, and robot passes through control
The article to be recycled is put into the storage barrel specified in robot by molding block;Such as match unsuccessful, the server is to machine
The communication module of device people sends the unsuccessful instruction of matching and the article characteristics information is stored the machine into the vision library of server
The human-computer interaction module of device people reminds user's input taxonomy of goods information and will be in the taxonomy of goods information by communication module
It reaches server and is stored in vision library, the study module of the server is special according to the article characteristics information architecture article
Sign model is stored in vision library and corresponding with the taxonomy of goods information of user's input.
The present invention carries out taxonomy of goods recycling by using the robot and cloud server that can be communicated wirelessly to each other, by
Server matches the article characteristics information that robot acquires with the pre-stored article characteristics model in server, thus real
The function of existing article Fast Classification recycling.If match unsuccessful, robot can prompt user defeated by human-computer interaction module
Enter taxonomy of goods information, while being provided with study module in server, it can be by study module according to article characteristics information structure
Build article characteristics model, and deposit taxonomy of goods information that article characteristics information, article characteristics model and user input is corresponding
Store up into the vision library of server, when occurring ware again, system can by the article characteristics information occurred again with
Article characteristics information and article characteristics model of the last stored in vision library are matched, to obtain corresponding taxonomy of goods
Information can carry out the classification recycling of precise and high efficiency in this way.Article recovery method of the invention is realizing automatic garbage classification
It can constantly learn and establish new article characteristics model simultaneously, effectively increase the efficiency and accuracy of taxonomy of goods recycling.
The study module building is completed server after article characteristics model is stored in vision library and is sent to robot
The article to be recycled is put into specified storage barrel by instruction.
According to one embodiment of present invention, pass through navigation module control in the control module of step S1 foregoing description robot
Drive module processed is roamed, and after taxonomy of goods to be recycled is completed and detects that the user in front of robot leaves, controls mould
Block, which controls robot by navigation module, to be continued to roam.
According to one embodiment of present invention, the human-computer interaction module is inputted by voice prompting user by touch screen
Taxonomy of goods information.
According to one embodiment of present invention, as prestored storing articles spy in the article characteristics information and the vision library
When sign Model Matching is unsuccessful, server sends to the communication module of robot and instructs, and robot is shot more by photographing module
It opens article photo to be recycled and is uploaded to server, the vision processing module of the server extracts institute by multiple article photos
State article characteristics information.
Detailed description of the invention
Fig. 1 is the schematic diagram of article recovery system in one embodiment of the invention;
Fig. 2 is the flow chart of article recovery method in one embodiment of the invention.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, below in conjunction with attached drawing and specific implementation
Example, the present invention will be described in further detail.It should be appreciated that specific embodiment described herein is only to explain this hair
It is bright, but not to limit the present invention.
As shown in Figure 1, article recovery system of the invention includes robot 100 and server 200, the robot 100
It can be carried out wireless communication between server 200.The robot includes control module 101, and the control module 101 is used for
The modules work that control robot ambulation and control are arranged in robot.The robot 100 further includes and controls
The drive module 106 that module 101 connects, the drive module 106 can drive robot under the control of control module 101
100 walkings.The robot further includes the navigation module 107 connecting with control module, and the navigation module 107 is for establishing machine
The 2 d plane picture of the walking environment of device people 100 simultaneously passes to control module 101, so that robot 100 roams in walking environment,
The i.e. described navigation module 107 is used for the roaming track route of planning robot.According to one embodiment of present invention, the navigation
Module 107 can be laser navigation module commonly used in the art.
The robot 100 further includes the sensor 102 connecting with control module 101, and the sensor 102 is for detecting
Whether 100 front of robot has stopped user, and the sensor 102 can be infrared sensor.When sensor 102 detects machine
When having user's stop before device people 100, control module 101, which controls drive module 106, makes 100 stop motion of robot.The machine
Device people 100 further includes pallet and multiple storage barrels below pallet, and the multiple storage barrel is to be recycled for classification storage
Article, the drive module 106 is also used to drive the storage barrel and pallet to act.Mould is controlled after robot stop motion
Block 101, which controls photographing module 103 connected to it and detects, whether there is article to be recycled on the pallet of robot, if there is
It then controls photographing module 103 and shoots article photo, the photographing module 103 can be monocular camera.The robot 100 also wraps
Communication module 105 is included, the communication module 105 is connect with control module 101 and photographing module 103, is used for photographing module 103
The article photo upload of shooting is to server 200.The communication module 105 is by article photo upload to the method for server 200
For known to those skilled in the art, details are not described herein again.
The robot 100 further includes the human-computer interaction module 104 connecting with control module 101, in specific condition
Lower prompt user inputs taxonomy of goods information.The human-computer interaction module 104 is also connect with communication module 105, is used for user
The taxonomy of goods information of input is sent to server 200 by communication module 105.
Server 200 is used to receive the information of the transmission of robot communication module 105.The server includes visual processes mould
Block 201, study module 202 and vision library 203.The article that the vision processing module 201 is used to shoot photographing module 103 shines
Piece is handled to generate article characteristic information, and the treatment process includes article profile, the color, ash extracted in article photo
The information such as degree and histogram.The server 200 is by the article characteristics information that vision processor 201 extracts and is pre-stored in vision
Pre-stored article characteristics model in library 203 is matched, if article characteristics information exists in vision library 203, i.e., with view
Feel library 203 in pre-stored article characteristics Model Matching success, then server 200 to the communication module 105 of robot send
With successfully instructing, communication module 105 sends an instruction to control module 101, and control module 101 passes through control drive module 106
The article is put into specified storage barrel, and controlling makes robot continue to roam.
The server 200 further includes study module 202.When the article characteristics information that above-mentioned vision processor 201 extracts
When unsuccessful with pre-stored article characteristics Model Matching in vision library 203, i.e., the article to be recycled is the unknown classification of robot
Article, then study module 202 be used for according to the article characteristics information architecture article characteristics model, specifically can be by online
The mode that study and off-line learning combine constructs article characteristic model.And by the article characteristics information, article characteristics model with
And user is stored in vision library 203 by the taxonomy of goods information that human-computer interaction module 104 inputs, and facilitates occur next time similar
Classification is compared when article.
The present invention is recycled by using the classification that robot carries out human lives' rubbish and other items, and makes robot and cloud
Server is communicated, special by the article characteristics information for acquiring robot and article pre-stored in server by server
Sign model is matched, to realize the function of article Fast Classification.If match unsuccessful, robot can pass through man-machine friendship
Mutual module prompt user inputs taxonomy of goods information, while study module is provided in server, can pass through study module root
Article characteristic model, and the object that article characteristics information, article characteristics model and user are inputted are constructed according to the characteristic information of article
Product classification information is corresponding to be stored into the vision library of server, and when occurring ware again, system will can go out again
The article characteristics information and article characteristics model of existing article characteristics information and last stored in vision library are matched, thus
Corresponding taxonomy of goods information is obtained, the classification recycling of precise and high efficiency can be carried out in this way.Article recovery system tool of the invention
The ability of standby self study, effectively increases the efficiency and accuracy of taxonomy of goods recycling.
As shown in Fig. 2, another aspect of the present invention provides a kind of method of article recycling.Robot under original state
100 are in roaming state under the common driving of navigation module 107 and drive module 106.Sensor in robot is set
Whether 102 real-time detections have user to rest on before robot, as robot continues to keep roaming state without if.Work as sensor
102 when having detected that user is rested on before robot, robot by photographing module 102 judge on the pallet of robot whether
Need to be recycled article presence, when testing result is no, execute previous step, i.e., whether control sensor 102 continues to test and have
User rests in front of robot;When testing result is to need to be recycled article on pallet, then photographing module 103 acquires article figure
Server 200 is sent to as information and by communication module 105.
Server 200 by vision processing module 201 extract article characteristic information and in vision library 203 be pre-stored object
Product characteristic model is matched, such as successful match, then judges the taxonomy of goods information for robot 100 it is known that server 200
It sends successful match to instruct to the communication module 105 of robot, robot control module 101 controls drive module 106 for article
It is put into specified storage barrel, and controls robot and continue to roam.
When the pre-stored taxonomy of goods information in the article characteristics information of extraction and vision library is inconsistent, illustrate this wait return
Receive the article that article is the unknown classification of robot 100.At this point, server 200 passes through communication module 105 to control module transmission
With unsuccessful instruction, control module 101 controls human-computer interaction module 104 and user is prompted to input taxonomy of goods information, and by user
The taxonomy of goods information of input is sent to server by communication module 105, and is stored in vision library 103.Specifically, man-machine
Interactive module 104 may include voice module and touch screen module, and the voice module is for prompting user to pass through touch screen mould
Block inputs taxonomy of goods information.Meanwhile control module 101 controls photographing module 103 and is continuously shot multiple article photos, and should
For multiple article photo uploads to server 200, the vision processing module 201 in server 200 carries out multiple article photos
Processing generates article characteristic information, and the article characteristics information is delivered to study module 202 and is used to construct article characteristic model,
And the article characteristics information and article characteristics model are stored in the taxonomy of goods information pair in vision library 203 with user's input
It answers.Server 200 is classified to the transmission of robot 100 and is successfully instructed at this time, and control module 101 controls drive module and places an article within
In specified storage barrel, and controls robot and continue to roam.This completes the processes of entire article recycling classification.
The above described specific embodiments of the present invention are not intended to limit the scope of the present invention..Any basis
Any other various changes and modifications made by technical concept of the invention should be included in the guarantor of the claims in the present invention
It protects in range.
Claims (10)
1. a kind of article recovery system characterized by comprising robot and server;The robot includes control module,
And connect respectively with control module for detecting whether there is user to rest on sensor in front of robot, for acquiring object
The photographing module of product image information, the human-computer interaction module for inputting taxonomy of goods information, for the images of items to be believed
Breath and taxonomy of goods information are uploaded to the communication module of server;The server is used to receive the article of communication module upload
The taxonomy of goods information of image information and user's input, server includes for handling item image information to generate article characteristics
The vision processing module of information, for the study module according to article characteristics information architecture article characteristics model, and for depositing
Store up the vision library of the article characteristics model, taxonomy of goods information and article characteristics information.
2. article recovery system as described in claim 1, which is characterized in that the robot further includes drive module, described
Drive module is for driving robot ambulation.
3. article recovery system as claimed in claim 2, which is characterized in that the robot further includes navigation module, described
Navigation module is connect with the control module, the track route for planning robot.
4. article recovery system as described in claim 1, which is characterized in that the human-computer interaction module include voice module and
Touch screen module.
5. product recovery system as described in claim 1, which is characterized in that the robot further includes multiple storage barrels and support
Disk, the top that storage barrel is arranged in the pallet are used for classification storage for carrying article to be recycled, the multiple storage barrel
The article to be recycled, the drive module are also used to that the storage barrel and pallet is driven to act.
6. a kind of method of article recycling, which is characterized in that the article recovery method is by the robot that can carry out wireless communication
It is completed with server, comprising the following steps:
S1: whether robot detection front has user's stop;
S2: when detecting that there is user's stop in front, the pallet of the control module control photographing module detection robot of robot
It is upper to whether there is article to be recycled, such as exist, photographing module shoots article photo;
S3: the control module of robot controls communication module for the article photo upload to server;
S4: the vision processing module of the server extracts article characteristic information by article photo, and by the article characteristics
Information is matched with the article characteristics model being pre-stored in server vision library;
S5: such as successful match, then server sends successful match instruction to the communication module of robot, and robot passes through control mould
The article to be recycled is put into the storage barrel specified in robot by block;Such as match unsuccessful, the server is to robot
Communication module send matching it is unsuccessful instruction and by the article characteristics information store into the vision library of server, robot
Human-computer interaction module remind user to input taxonomy of goods information and to be uploaded to the taxonomy of goods information by communication module
Server is simultaneously stored in vision library, and the study module of server is deposited according to the article characteristics information architecture article characteristics model
It stores up in vision library and corresponding with the taxonomy of goods information of user's input.
7. the method for article recycling as claimed in claim 6, which is characterized in that article characteristics are completed in the study module building
Server sends instruction to robot and the article to be recycled is put into specified storage barrel after model is stored in vision library
In.
8. the method for article recycling as claimed in claim 6, which is characterized in that in the control of step S1 foregoing description robot
Module controls drive module by navigation module and is roamed, when taxonomy of goods to be recycled is completed and is detected in front of robot
After user leaves, control module controls robot by navigation module and continues to roam.
9. the method for article recycling as claimed in claim 6, which is characterized in that the human-computer interaction module passes through voice prompting
User inputs taxonomy of goods information by touch screen.
10. the method for article recycling as claimed in claim 6, which is characterized in that such as the article characteristics information and the view
When pre-stored article characteristics Model Matching in feel library is unsuccessful, server sends to the communication module of robot and instructs, machine
People shoots multiple article photos to be recycled by photographing module and is uploaded to server, and the vision processing module of the server is logical
It crosses multiple article photos and extracts the article characteristics information.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711456501.0A CN109977975B (en) | 2017-12-28 | 2017-12-28 | Article recycling system and article recycling method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711456501.0A CN109977975B (en) | 2017-12-28 | 2017-12-28 | Article recycling system and article recycling method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109977975A true CN109977975A (en) | 2019-07-05 |
CN109977975B CN109977975B (en) | 2022-11-22 |
Family
ID=67074366
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711456501.0A Active CN109977975B (en) | 2017-12-28 | 2017-12-28 | Article recycling system and article recycling method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109977975B (en) |
Citations (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
ATA288886A (en) * | 1986-10-30 | 1988-03-15 | Ife Gmbh | DEVICE FOR WASTE SORTING PLANTS |
JP2005121587A (en) * | 2003-10-20 | 2005-05-12 | Asahi Kasei Engineering Kk | Sorter and sorting means of plastic |
EP2187339A1 (en) * | 2008-11-12 | 2010-05-19 | Fundación Robotiker | Method for integrating spectral and spatial features for classifying materials |
EP2255894A1 (en) * | 2008-03-05 | 2010-12-01 | NEC Corporation | Delivery classification device, method for classifying delivery, program and computer readable recording medium |
CN103464380A (en) * | 2013-05-23 | 2013-12-25 | 南昌航空大学 | Intelligent garbage classification robot |
CN104044842A (en) * | 2014-06-23 | 2014-09-17 | 陈斌 | Garbage sorting platform and method based on two-dimensional code recognition technology |
WO2014179667A2 (en) * | 2013-05-03 | 2014-11-06 | Ecowastehub Corp. | Solid waste identification & segregation system |
US20140341436A1 (en) * | 2013-05-15 | 2014-11-20 | Canon Kabushiki Kaisha | Classifying materials using texture |
CN104281602A (en) * | 2013-07-05 | 2015-01-14 | 厦门市博维科技有限公司 | Recognition method and system |
CN104318421A (en) * | 2014-11-20 | 2015-01-28 | 北京盈创高科新技术发展有限公司 | System and method for realizing reverse logistics in field of recycling of renewable resources |
CN104615769A (en) * | 2015-02-15 | 2015-05-13 | 小米科技有限责任公司 | Image classification method and device |
CN104881926A (en) * | 2015-04-16 | 2015-09-02 | 四川长虹电器股份有限公司 | Self-service recycling system of waste mobile phones |
CN104915344A (en) * | 2014-03-10 | 2015-09-16 | 联想(北京)有限公司 | Information processing method and electronic equipment |
CN204938049U (en) * | 2015-09-25 | 2016-01-06 | 蒋曙 | A kind of garbage recovering apparatus |
CN205058045U (en) * | 2015-10-26 | 2016-03-02 | 众德迪克科技(北京)有限公司 | Robot with vision servo |
CN105564864A (en) * | 2015-12-18 | 2016-05-11 | 美的集团股份有限公司 | Garbage can, garbage sorting method for garage can and garbage sorting system for garage can |
US20160307070A1 (en) * | 2013-12-27 | 2016-10-20 | Huawei Technologies Co., Ltd. | Method for Recognizing Target Object in Image, and Apparatus |
CN106453551A (en) * | 2016-10-09 | 2017-02-22 | 东南大学 | Task planning and executing device and method for goods delivery robot in office |
CN107077659A (en) * | 2016-09-26 | 2017-08-18 | 达闼科技(北京)有限公司 | A kind of intelligent inventory management system, server, method, terminal and program product |
CN107491912A (en) * | 2017-07-10 | 2017-12-19 | 杭州南江机器人股份有限公司 | A kind of empty shelf recovery method, device and system |
-
2017
- 2017-12-28 CN CN201711456501.0A patent/CN109977975B/en active Active
Patent Citations (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
ATA288886A (en) * | 1986-10-30 | 1988-03-15 | Ife Gmbh | DEVICE FOR WASTE SORTING PLANTS |
JP2005121587A (en) * | 2003-10-20 | 2005-05-12 | Asahi Kasei Engineering Kk | Sorter and sorting means of plastic |
EP2255894A1 (en) * | 2008-03-05 | 2010-12-01 | NEC Corporation | Delivery classification device, method for classifying delivery, program and computer readable recording medium |
EP2187339A1 (en) * | 2008-11-12 | 2010-05-19 | Fundación Robotiker | Method for integrating spectral and spatial features for classifying materials |
WO2014179667A2 (en) * | 2013-05-03 | 2014-11-06 | Ecowastehub Corp. | Solid waste identification & segregation system |
US20140341436A1 (en) * | 2013-05-15 | 2014-11-20 | Canon Kabushiki Kaisha | Classifying materials using texture |
CN103464380A (en) * | 2013-05-23 | 2013-12-25 | 南昌航空大学 | Intelligent garbage classification robot |
CN104281602A (en) * | 2013-07-05 | 2015-01-14 | 厦门市博维科技有限公司 | Recognition method and system |
US20160307070A1 (en) * | 2013-12-27 | 2016-10-20 | Huawei Technologies Co., Ltd. | Method for Recognizing Target Object in Image, and Apparatus |
CN104915344A (en) * | 2014-03-10 | 2015-09-16 | 联想(北京)有限公司 | Information processing method and electronic equipment |
CN104044842A (en) * | 2014-06-23 | 2014-09-17 | 陈斌 | Garbage sorting platform and method based on two-dimensional code recognition technology |
CN104318421A (en) * | 2014-11-20 | 2015-01-28 | 北京盈创高科新技术发展有限公司 | System and method for realizing reverse logistics in field of recycling of renewable resources |
CN104615769A (en) * | 2015-02-15 | 2015-05-13 | 小米科技有限责任公司 | Image classification method and device |
CN104881926A (en) * | 2015-04-16 | 2015-09-02 | 四川长虹电器股份有限公司 | Self-service recycling system of waste mobile phones |
CN204938049U (en) * | 2015-09-25 | 2016-01-06 | 蒋曙 | A kind of garbage recovering apparatus |
CN205058045U (en) * | 2015-10-26 | 2016-03-02 | 众德迪克科技(北京)有限公司 | Robot with vision servo |
CN105564864A (en) * | 2015-12-18 | 2016-05-11 | 美的集团股份有限公司 | Garbage can, garbage sorting method for garage can and garbage sorting system for garage can |
CN107077659A (en) * | 2016-09-26 | 2017-08-18 | 达闼科技(北京)有限公司 | A kind of intelligent inventory management system, server, method, terminal and program product |
CN106453551A (en) * | 2016-10-09 | 2017-02-22 | 东南大学 | Task planning and executing device and method for goods delivery robot in office |
CN107491912A (en) * | 2017-07-10 | 2017-12-19 | 杭州南江机器人股份有限公司 | A kind of empty shelf recovery method, device and system |
Non-Patent Citations (3)
Title |
---|
杨秀秀 等: "智能分类垃圾箱系统设计", 《黑龙江科技信息》 * |
杨航: "智能垃圾分类终端软件设计与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
贺向宇: "面向智能分类回收的塑料瓶机器视觉识别技术研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅰ辑》 * |
Also Published As
Publication number | Publication date |
---|---|
CN109977975B (en) | 2022-11-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2018053847A1 (en) | Smart inventory management system, server and method, terminal, and program product | |
CN109409175B (en) | Settlement method, device and system | |
Wang et al. | Binge watching: Scaling affordance learning from sitcoms | |
US20200097724A1 (en) | Machine-learning-assisted self-improving object-identification system and method | |
JP6695539B1 (en) | Article sorting apparatus, article sorting system and article sorting method | |
US11587149B2 (en) | Associating shoppers together | |
CN111145257B (en) | Article grabbing method and system and article grabbing robot | |
JP2021030219A (en) | Article sorting apparatus and article sorting method | |
CN107395730A (en) | Information pushing method and device | |
CN110345407B (en) | Intelligent posture correcting desk lamp based on deep learning and posture correcting method | |
KR20180054407A (en) | Apparatus for recognizing user emotion and method thereof, and robot system using the same | |
CN102054165A (en) | Image processing apparatus and image processing method | |
CN107564196A (en) | Storing apparatus control method and device | |
KR102285625B1 (en) | Non-contact type recognition apparatus and method of object's attibutes | |
CN109977975A (en) | Article recovery system and article recovery method | |
KR101100240B1 (en) | System for object learning through multi-modal interaction and method thereof | |
Xia et al. | Video emotion recognition using hand-crafted and deep learning features | |
KR102181815B1 (en) | Personalized arrangement robot and arrangement method using the same | |
CN114180422B (en) | Elevator control method, device, electronic equipment and readable storage medium | |
CN106997449A (en) | Robot and face identification method with face identification functions | |
JP6921448B1 (en) | Control program and control method for new object operation robot, and new object operation system | |
US20220172413A1 (en) | Method for generating realistic content | |
CN211858135U (en) | Intelligent service robot | |
CN111461005A (en) | Gesture recognition method and device, computer equipment and storage medium | |
CN110363278A (en) | Parent-child interaction method, robot, server and parent-child interaction system |
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 |