CN108805014A - Localization method, device and the computer readable storage medium of mobile charging stake - Google Patents
Localization method, device and the computer readable storage medium of mobile charging stake Download PDFInfo
- Publication number
- CN108805014A CN108805014A CN201810383099.6A CN201810383099A CN108805014A CN 108805014 A CN108805014 A CN 108805014A CN 201810383099 A CN201810383099 A CN 201810383099A CN 108805014 A CN108805014 A CN 108805014A
- Authority
- CN
- China
- Prior art keywords
- mobile charging
- charging stake
- electric vehicle
- stake
- rendering
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02T90/10—Technologies relating to charging of electric vehicles
- Y02T90/16—Information or communication technologies improving the operation of electric vehicles
- Y02T90/167—Systems integrating technologies related to power network operation and communication or information technologies for supporting the interoperability of electric or hybrid vehicles, i.e. smartgrids as interface for battery charging of electric vehicles [EV] or hybrid vehicles [HEV]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S30/00—Systems supporting specific end-user applications in the sector of transportation
- Y04S30/10—Systems supporting the interoperability of electric or hybrid vehicles
- Y04S30/12—Remote or cooperative charging
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Navigation (AREA)
Abstract
The invention discloses a kind of localization method, device and the computer readable storage medium of mobile charging stake, the method includes：The image information in movement locus is obtained, and 3D rendering is generated according to the image information；3D rendering is matched with the image dictionary in database；According to matched result operating instruction is sent to mobile charging stake；The mobile charging stake is run according to operating instruction to predeterminated position, is obtained the charge port position of electric vehicle and is controlled mobile charging stake and is moved to the position.The stake of mobile charging of the embodiment of the present invention changes the mode of fixed charging pile charging, keeps electric vehicle charging more convenient in such a way that unmanned technology looks for vehicle automatically, intelligent；SLAM location technologies are added, keep the positioning of mobile charging stake more accurate.
Description
Technical field
The present invention relates to electric vehicle charging technique field more particularly to a kind of localization method, the devices of mobile charging stake
And computer readable storage medium.
Background technology
To advocate the use of new energy, the use of electric vehicle is more and more wider, and at the same time electric vehicle is charged to
A great problem；For the prior art mostly or using fixed charging pile, fixed charging pile is generally located on parking stall, defect
It is that charge position is fixed.Environment is not that each parking lot is both provided with charging pile yet at present, and electric vehicle is badly in need of charging also
Go for the stop for being provided with charging pile, and often meet parked in front of fixed charging pile be not required to charging vapour
Vehicle interferes electric vehicle charging, at this moment the conducting wire of charging gun is just necessarily required to want long enough, could charged at a distance.
Some the mobile charging piles then occurred are positioned in the case of some GPS signal differences and are deposited using GPS positioning
In certain error, have no idea to realize that precise positioning arrives electric vehicle, it is also necessary to manually mobile charging stake go to look near
The position of charge port, it is inconvenient for use.
Invention content
The main purpose of the present invention is to provide a kind of localization method of mobile charging stake, device and computer-readable storages
Medium, it is intended to realize that mobile charging stake is accurately positioned electric vehicle.
To achieve the above object, the localization method of a kind of mobile charging stake provided by the invention, the mobile charging stake
Localization method includes the following steps：
Step S10 obtains the image information in movement locus, and generates 3D rendering according to the image information；
Step S20 matches 3D rendering with the image dictionary in database；
Step S30 sends operating instruction according to matched result to mobile charging stake；
Step S40, the mobile charging stake are run according to operating instruction to predeterminated position, obtain the charging of electric vehicle
Mouthful position simultaneously controls mobile charging stake and is moved to the position.
Preferably, the image information obtained in movement locus, and the step of 3D rendering is generated according to the image information
Including：
The image information in movement locus is obtained by RGBD vision measurement cameras, and is used according to the image information
ICP algorithm generates 3D rendering.
Preferably, described the step of sending operating instruction to mobile charging stake according to matched result, includes：
When it is stationary state that the 3D rendering matching result, which is objects in front, evacuation is sent to the mobile charging stake
Operating instruction；When it is motion state that the 3D rendering matching result, which is objects in front, sends and stop to the mobile charging stake
The instruction of operation.
Preferably, it is described 3D rendering is matched with the image dictionary in database described in image word in database
Allusion quotation is established using word bag submodel, and step includes：
Step S21 clusters the visual signature in image；
Step S22 establishes image dictionary according to visual signature cluster.
Preferably, it is described 3D rendering is matched with the image dictionary in database in step include：
Whether step S201 inquires the 3D rendering with the visual signature classification in image dictionary according to image dictionary；
Step S202 identifies the object features in 3D rendering according to visual signature classification.
Preferably, the step of charge port position for obtaining electric vehicle includes：
Step S41 matches the license plate number of electric vehicle；
Step S42 acquires the charge port position of electric vehicle after successful match.
Preferably, the step of charge port position for obtaining electric vehicle includes：
Step S43 obtains the model data of electric vehicle；
Step S44, according to the model data automatic identification charge port position of electric vehicle.
Preferably, the image information obtained in movement locus, and according to the step of image information generation 3D rendering
Further include before rapid：
Step S00 obtains the GPS signal of electric vehicle；
Step S01 positions the home position of electric vehicle according to the GPS signal.
In addition, to achieve the above object, the present invention also provides a kind of positioning device of mobile charging stake, the mobile chargings
Stake positioning device include：Memory, processor and it is stored in the shifting that can be run on the memory and on the processor
The finder of dynamic charging pile realizes side as described above when the finder of the mobile charging stake is executed by the processor
The step of method.
In addition, to achieve the above object, it is described computer-readable the present invention also provides a kind of computer readable storage medium
The finder of mobile charging stake is stored on storage medium, it is real when the finder of the mobile charging stake is executed by processor
Now the step of localization method of mobile charging stake as described above.
The localization method of mobile charging stake of the present invention is by obtaining the image information in movement locus, and according to the image
Information generates 3D rendering；3D rendering is matched with the image dictionary in database；According to matched result to mobile charging
Stake sends operating instruction；The mobile charging stake is run according to operating instruction to predeterminated position, obtains the charging of electric vehicle
Mouthful position simultaneously controls mobile charging stake and is moved to the position.The stake of mobile charging of the embodiment of the present invention is automatic by unmanned technology
The mode for looking for vehicle changes the mode of fixed charging pile charging, keeps electric vehicle charging more convenient, intelligent；SLAM is added
Location technology keeps the positioning of mobile charging stake more accurate.
Description of the drawings
Fig. 1 is the flow diagram of the localization method first embodiment of mobile charging stake of the present invention；
Fig. 2 is the flow diagram of the localization method second embodiment of mobile charging stake of the present invention；
Fig. 3 is the flow diagram of the localization method second embodiment of mobile charging stake of the present invention；
Fig. 4 is the flow diagram of the localization method 3rd embodiment of mobile charging stake of the present invention；
Fig. 5 is the flow diagram of the localization method 3rd embodiment of mobile charging stake of the present invention；
Fig. 6 is the flow diagram of the localization method fourth embodiment of mobile charging stake of the present invention；
Fig. 7 is the schematic diagram of the positioning device of mobile charging stake of the present invention.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific implementation mode
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
The present invention provides a kind of localization method of mobile charging stake, and this method is applied under mobile charging situation, first
In embodiment, referring to Fig. 1, the localization method of the mobile charging stake includes the following steps：
Step S10 obtains the image information in movement locus, and generates 3D rendering according to the image information；
In the present embodiment, the intelligent operating system of mobile charging stake obtains the charge request that terminal issues, wherein the end
End can be mobile terminal, such as mobile phone, tablet, intelligent wearable device；And the mobile terminal need to be communicated with electric vehicle
Connection, is stored with the essential information of electric vehicle, such as the location information of electric vehicle, electric vehicle model, current state
Etc..Certainly, the terminal can also be the communication device of electric vehicle itself, such as the intelligent display device on electric vehicle.
The concrete form that above-mentioned terminal may be used in user issues charge request by terminal.Wherein, electric vehicle can be with
It automatically generates charge request and is sent to terminal, it is specifically, accumulative less than preset value or electric vehicle in the electricity of electric vehicle
After reaching preset strokes, electric vehicle automatically generates the charge request, and sends it to terminal.Certainly, the charge request
Can be user when judging that electric vehicle charges according to the state of charge or other information of electric vehicle, at end
The charge request issued on end.
It should be noted simultaneously that the terminal can be sent out WIFI signal or Bluetooth signal to position, Huo Zhezhi
The intelligent operating system of the relevant information of sending and receiving out position information and user's automobile, charging pile easy to remove obtains and movement
Charging pile close to when be identified.The relevant information of wherein automobile includes the information such as vehicle and the license plate number of electric vehicle.It is logical
The vehicle of electric vehicle is crossed, charging pile can be moved easily in subsequent charge directly by the vehicle cab recognition of electric vehicle to electronic
The charge port position of automobile.
The mobile charging stake to match therewith is matched by the vehicle of electric vehicle simultaneously, in electric vehicle and mobile charging
After stake successful match, a specified charge position will be distributed for electric vehicle and mobile charging stake, electric vehicle can be in user
Lower arrival designated position is driven, mobile charging stake then can reach appointed place by automatic Pilot technology.And by driving automatically
It sails during technology reaches appointed place, is kept away during automatic Pilot by SLAM technologies using the present embodiment
The specific location of barrier, path planning and fixation and recognition to electric vehicle.
The avoidance and path planning that automatic Pilot process is realized using the combination SLAM technologies in the present embodiment, are first passed through in advance
The image information in mobile charging stake movement locus is obtained, and 3D rendering is generated according to the image information.Specifically, this implementation
Example obtains the image information in movement locus by RGBD vision measurement cameras, and uses ICP algorithm according to the image information
Directly generate 3D rendering.
When mobile charging stake is run in Euclidean space, to the transformation matrix SE3 of three dimensions, pass through VO (vision mileages
Meter) it solves, that is to say, that the planning of mobile charging stake mobile route is to pass through, VO (visions that RGBD cameras and algorithm are combined
Odometer) come what is completed.The method of visual odometry has two kinds of method of characteristic point and direct method, it is contemplated that mobile charging stake uses
The feature of scene and RGED cameras uses ICP's (iterative closest point, iteration arest neighbors) in the present embodiment
Direct method solves the transformation matrix between two clouds, to set running route.The advantage of direct method is can to build one
Dense map, it is more detail to the object on movement locus.
Can be theoretically the running orbit of mobile charging stake after VO estimates interframe movement.But due to examining
Considering has the problem of cumulative errors (Drift), continues intuitively to solve using figure optimization method (Graph Optimization)
Optimization problem, and carry out rapid solving using sparse algebraically.
Step S20 matches 3D rendering with the image dictionary in database；
In view of the driving trace category of mobile charging stake moves back and forth process repeatedly, winding detects (loop closure
Detection it) will be used to be promoted machine learning ability of the mobile charging stake to once reaching scene.Winding detection mostly uses at present
Bag of words (Bag-of-Word).The problem of it is substantially a detection observation data similarity.In bag of words, lead to
The feature extracted in every image is crossed, their feature vector (descriptor) is clustered, category database is established.Than
As said, people, automobile, bicycle, street lamp etc..Assuming that there are 10000 classes, then, for each image, it can be analyzed and contained
There is which class in database.It is indicated with 1, indicates do not have with 0, then, a vector of 10000 dimensions just can be used in this image
It expresses, and different images, as long as compare their vector.
Image dictionary is established by word bag submodel, then by before finding in each figure and being identified containing which Feature Words
Square object body characteristics, for example, the charge port position of electric vehicle and electric vehicle license plate.Meanwhile it can also use traditional mode identification point
Class method carries out static and 2 points of classification of movement, training grader to the object that can be potentially encountered in path and carries out classification processing,
Computer can formulate different avoidances and around line mode.
Step S30 sends operating instruction according to matched result to mobile charging stake；
The image collected is matched with the image of image dictionary in word bag submodel, matches and ties in the 3D rendering
Fruit is objects in front when being stationary state, and the operating instruction of evacuation is sent to the mobile charging stake；It is matched in the 3D rendering
As a result when to be objects in front be motion state, instruction out of service is sent to the mobile charging stake.
Step S40, the mobile charging stake are run according to operating instruction to predeterminated position, obtain the charging of electric vehicle
Mouthful position simultaneously controls mobile charging stake and is moved to the position.
When the mobile charging stake is reached using automatic Pilot technology according to operating instruction and specifies charge position, moving charging
Electric stake can search the electric vehicle license plate number that acquisition need to charge, and after vehicle successful match, it is electronic that mobile charging stake acquires this again
The position of vehicle charging mouth.Certainly, mobile charging stake can also recall model data input by user from background management system, from
Dynamic identification charge port position, is parked according to the mobile charging stake of charge port position near the position of charge port.
The present embodiment generates 3D rendering by obtaining the image information in movement locus, and according to the image information；It will
3D rendering is matched with the image dictionary in database；According to matched result operating instruction is sent to mobile charging stake；Institute
It states mobile charging stake to run to predeterminated position according to operating instruction, obtain the charge port position of electric vehicle and controls moving charging
Electric stake is moved to the position.The stake of mobile charging of the embodiment of the present invention changes in such a way that unmanned technology looks for vehicle automatically
The mode of fixed charging pile charging, keeps electric vehicle charging more convenient, intelligent；SLAM location technologies are added, make charging pile
Positioning it is more accurate.
Further, Fig. 2 and Fig. 3 are please referred to, based on the localization method first embodiment of mobile charging stake of the present invention, at this
In the localization method second embodiment of invention mobile charging stake, the image dictionary in above-mentioned steps S20 is built using word bag submodel
Vertical, the specific steps established include：
Step S21 clusters the visual signature in image；
Step S22 establishes image dictionary according to visual signature cluster.
The step S20 further includes：
Whether step S201 inquires the 3D rendering with the visual signature classification in image dictionary according to image dictionary；
Step S202 identifies the object features in 3D rendering according to visual signature classification.
In bag of words, by extracting the feature in every image, their visual signature is clustered, class is established
Other database.Such as people, automobile, bicycle, street lamp etc..Assuming that there is 10000 classes, then, for each image,
It can analyze it contains which class in database.It is indicated with 1, indicates do not have with 0, then, this image just can be used 10000
One vector of dimension is expressed, and different images, as long as comparing their vector.It is established according to the cluster of visual signature
Image dictionary.
The present embodiment is established image dictionary by word bag submodel and is acquired on mobile charging stake driving path for matching
Image, to carry out path planning to mobile charging stake according to image, improve safety in mobile charging stake operational process with
Stability.
Further, Fig. 4 and Fig. 5 are please referred to, based on the localization method second embodiment of mobile charging stake of the present invention, at this
In the localization method 3rd embodiment of invention mobile charging stake, the charge port position of the acquisition electric vehicle in the step S40
The step of include：
Step S41 matches the license plate number of electric vehicle；
Step S42 acquires the charge port position of electric vehicle after successful match.
In another embodiment, the step of charge port position for obtaining electric vehicle includes：
Step S43 obtains the model data of electric vehicle；
Step S44, according to the model data automatic identification charge port position of electric vehicle.
When the mobile charging stake is reached using automatic Pilot technology according to operating instruction and specifies charge position, moving charging
Electric stake can search the electric vehicle license plate number that acquisition need to charge, and after vehicle successful match, it is electronic that mobile charging stake acquires this again
The position of vehicle charging mouth.Wherein specific acquisition mode can obtain the image of electric vehicle by taking pictures, and then carry out special
Sign matching, is matched to the charge port position of electric vehicle.
Certainly, mobile charging stake can also recall model data input by user from background management system, and automatic identification is filled
Power port position is parked according to the mobile charging stake of charge port position near the position of charge port.That is the electric vehicle of different automobile types
There is its preset charge port position, need to only obtain the vehicle of electric vehicle, you can obtain the charge port position of electric vehicle.
The present embodiment according to acquisition charge port position and according to vehicle automatic identification charge port position by obtaining electricity
Mobile charging stake is improved to the accuracy of electric vehicle automatic charging and intelligent in electrical automobile charge port position.
Further, referring to Fig. 6, in the localization method fourth embodiment of mobile charging stake of the present invention, in the step
Further include before S10：
Step S00 obtains the GPS signal of electric vehicle；；
Step S01 positions the home position of electric vehicle according to the GPS signal.
In the present embodiment, before mobile charging stake carries out path planning, the approximate location of electric vehicle is first obtained, with contracting
The range of small path planning.
The present invention further provides a kind of positioning devices 100 of mobile charging stake, referring to Fig. 7, the mobile charging stake
Positioning device 100 includes：It storage 101, processor 102 and is stored on the memory 101 and can be on the processor 102
The finder of the mobile charging stake of operation, the finder of the mobile charging stake are realized when being executed by the processor 102
Following method and step：
The image information in movement locus is obtained, and 3D rendering is generated according to the image information；
3D rendering is matched with the image dictionary in database；
According to matched result operating instruction is sent to mobile charging stake；
The mobile charging stake is run according to operating instruction to predeterminated position, obtains the charge port position of electric vehicle simultaneously
Control mobile charging stake is moved to the position.
In the present embodiment, the intelligent operating system of mobile charging stake obtains the charge request that terminal issues, wherein the end
End can be mobile terminal, such as mobile phone, tablet, intelligent wearable device；And the mobile terminal need to be communicated with electric vehicle
Connection, is stored with the essential information of electric vehicle, such as the location information of electric vehicle, electric vehicle model, current state
Etc..Certainly, the terminal can also be the communication device of electric vehicle itself, such as the intelligent display device on electric vehicle.
The concrete form that above-mentioned terminal may be used in user issues charge request by terminal.Wherein, electric vehicle can be with
It automatically generates charge request and is sent to terminal, it is specifically, accumulative less than preset value or electric vehicle in the electricity of electric vehicle
After reaching preset strokes, electric vehicle automatically generates the charge request, and sends it to terminal.Certainly, the charge request
Can be user when judging that electric vehicle charges according to the state of charge or other information of electric vehicle, at end
The charge request issued on end.
It should be noted simultaneously that the terminal can be sent out WIFI signal or Bluetooth signal to position, Huo Zhezhi
The intelligent operating system of the relevant information of sending and receiving out position information and user's automobile, charging pile easy to remove obtains and movement
Charging pile close to when be identified.The relevant information of wherein automobile includes the information such as vehicle and the license plate number of electric vehicle.It is logical
The vehicle of electric vehicle is crossed, charging pile can be moved easily in subsequent charge directly by the vehicle cab recognition of electric vehicle to electronic
The charge port position of automobile.
The mobile charging stake to match therewith is matched by the vehicle of electric vehicle simultaneously, in electric vehicle and mobile charging
After stake successful match, a specified charge position will be distributed for electric vehicle and mobile charging stake, electric vehicle can be in user
Lower arrival designated position is driven, mobile charging stake then can reach appointed place by automatic Pilot technology.And by driving automatically
It sails during technology reaches appointed place, is kept away during automatic Pilot by SLAM technologies using the present embodiment
The specific location of barrier, path planning and fixation and recognition to electric vehicle.
The avoidance and path planning that automatic Pilot process is realized using the combination SLAM technologies in the present embodiment, are first passed through in advance
The image information in mobile charging stake movement locus is obtained, and 3D rendering is generated according to the image information.Specifically, this implementation
Example obtains the image information in movement locus by RGBD vision measurement cameras, and uses ICP algorithm according to the image information
Directly generate 3D rendering.
When mobile charging stake is run in Euclidean space, to the transformation matrix SE3 of three dimensions, pass through VO (vision mileages
Meter) it solves, that is to say, that the planning of mobile charging stake mobile route is to pass through, VO (visions that RGBD cameras and algorithm are combined
Odometer) come what is completed.The method of visual odometry has two kinds of method of characteristic point and direct method, it is contemplated that mobile charging stake uses
The feature of scene and RGED cameras uses ICP's (iterative closest point, iteration arest neighbors) in the present embodiment
Direct method solves the transformation matrix between two clouds, to set running route.The advantage of direct method is can to build one
Dense map, it is more detail to the object on movement locus.
Can be theoretically the running orbit of mobile charging stake after VO estimates interframe movement.But due to examining
Considering has the problem of cumulative errors (Drift), continues intuitively to solve using figure optimization method (Graph Optimization)
Optimization problem, and carry out rapid solving using sparse algebraically.
In view of the driving trace category of mobile charging stake moves back and forth process repeatedly, winding detects (loop closure
Detection it) will be used to be promoted machine learning ability of the mobile charging stake to once reaching scene.Winding detection mostly uses at present
Bag of words (Bag-of-Word).The problem of it is substantially a detection observation data similarity.In bag of words, lead to
The feature extracted in every image is crossed, their feature vector (descriptor) is clustered, category database is established.Than
As said, people, automobile, bicycle, street lamp etc..Assuming that there are 10000 classes, then, for each image, it can be analyzed and contained
There is which class in database.It is indicated with 1, indicates do not have with 0, then, a vector of 10000 dimensions just can be used in this image
It expresses, and different images, as long as compare their vector.
Image dictionary is established by word bag submodel, then by before finding in each figure and being identified containing which Feature Words
Square object body characteristics, for example, the charge port position of electric vehicle and electric vehicle license plate.Meanwhile it can also use traditional mode identification point
Class method carries out static and 2 points of classification of movement, training grader to the object that can be potentially encountered in path and carries out classification processing,
Computer can formulate different avoidances and around line mode.
The image collected is matched with the image of image dictionary in word bag submodel, matches and ties in the 3D rendering
Fruit is objects in front when being stationary state, and the operating instruction of evacuation is sent to the mobile charging stake；It is matched in the 3D rendering
As a result when to be objects in front be motion state, instruction out of service is sent to the mobile charging stake.
When the mobile charging stake is reached using automatic Pilot technology according to operating instruction and specifies charge position, moving charging
Electric stake can search the electric vehicle license plate number that acquisition need to charge, and after vehicle successful match, it is electronic that mobile charging stake acquires this again
The position of vehicle charging mouth.Certainly, mobile charging stake can also recall model data input by user from background management system, from
Dynamic identification charge port position, is parked according to the mobile charging stake of charge port position near the position of charge port.
The present embodiment generates 3D rendering by obtaining the image information in movement locus, and according to the image information；It will
3D rendering is matched with the image dictionary in database；According to matched result operating instruction is sent to mobile charging stake；Institute
It states mobile charging stake to run to predeterminated position according to operating instruction, obtain the charge port position of electric vehicle and controls moving charging
Electric stake is moved to the position.The stake of mobile charging of the embodiment of the present invention changes in such a way that unmanned technology looks for vehicle automatically
The mode of fixed charging pile charging, keeps electric vehicle charging more convenient, intelligent；SLAM location technologies are added, make charging pile
Positioning it is more accurate.
Further, in one embodiment, it is realized when the finder of the mobile charging stake is executed by the processor
Following method and step：
Match the license plate number of electric vehicle；
After successful match, the charge port position of electric vehicle is acquired.
In another embodiment, the step of charge port position for obtaining electric vehicle includes：
Obtain the model data of electric vehicle；
According to the model data automatic identification charge port position of electric vehicle.
When the mobile charging stake is reached using automatic Pilot technology according to operating instruction and specifies charge position, moving charging
Electric stake can search the electric vehicle license plate number that acquisition need to charge, and after vehicle successful match, it is electronic that mobile charging stake acquires this again
The position of vehicle charging mouth.Wherein specific acquisition mode can obtain the image of electric vehicle by taking pictures, and then carry out special
Sign matching, is matched to the charge port position of electric vehicle.
Certainly, mobile charging stake can also recall model data input by user from background management system, and automatic identification is filled
Power port position is parked according to the mobile charging stake of charge port position near the position of charge port.That is the electric vehicle of different automobile types
There is its preset charge port position, need to only obtain the vehicle of electric vehicle, you can obtain the charge port position of electric vehicle.
The present embodiment according to acquisition charge port position and according to vehicle automatic identification charge port position by obtaining electricity
Mobile charging stake is improved to the accuracy of electric vehicle automatic charging and intelligent in electrical automobile charge port position.
Further, in one embodiment, it is realized when the finder of the mobile charging stake is executed by the processor
Following method and step：
Obtain the GPS signal of electric vehicle；；
The home position of electric vehicle is positioned according to the GPS signal.
In the present embodiment, before mobile charging stake carries out path planning, the approximate location of electric vehicle is first obtained, with contracting
The range of small path planning.
In addition, the embodiment of the present invention also proposes a kind of computer readable storage medium, the computer readable storage medium
On be stored with the finder of mobile charging stake, the finder of the mobile charging stake realizes institute as above when being executed by processor
The method stated.
It these are only the preferred embodiment of the present invention, be not intended to limit the scope of the invention, it is every to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of localization method of mobile charging stake, which is characterized in that the localization method of the mobile charging stake includes following step
Suddenly：
Step S10 obtains the image information in movement locus, and generates 3D rendering according to the image information；
Step S20 matches 3D rendering with the image dictionary in database；
Step S30 sends operating instruction according to matched result to mobile charging stake；
Step S40, the mobile charging stake are run according to operating instruction to predeterminated position, obtain the charge port position of electric vehicle
It sets and controls mobile charging stake and be moved to the position.
2. the localization method of mobile charging stake according to claim 1, which is characterized in that the step S10 obtains movement
Image information in track, and the step of generating 3D rendering according to the image information includes：
The image information in movement locus is obtained by RGBD vision measurement cameras, and is calculated using ICP according to the image information
Method generates 3D rendering.
3. the localization method of mobile charging stake according to claim 1, which is characterized in that the step S30, according to matching
Result to mobile charging stake send operating instruction the step of include：
When it is stationary state that the 3D rendering matching result, which is objects in front, the operation of evacuation is sent to the mobile charging stake
Instruction；When it is motion state that the 3D rendering matching result, which is objects in front, sent to the mobile charging stake out of service
Instruction.
4. the localization method of mobile charging stake according to claim 1, which is characterized in that the step S20, by 3D rendering
In being matched with the image dictionary in database, the image dictionary in the database is established using word bag submodel, step
Suddenly include：
Step S21 clusters the visual signature in image；
Step S22 establishes image dictionary according to visual signature cluster.
5. the localization method of mobile charging stake according to claim 4, which is characterized in that the step S20, by 3D rendering
Step in being matched with the image dictionary in database includes：
Whether step S201 inquires the 3D rendering with the visual signature classification in image dictionary according to image dictionary；
Step S202 identifies the object features in 3D rendering according to visual signature classification.
6. the localization method of mobile charging stake according to claim 1, which is characterized in that the step S40 is obtained electronic
The step of charge port position of automobile includes：
Step S41 matches the license plate number of electric vehicle；
Step S42 acquires the charge port position of electric vehicle after successful match.
7. the localization method of mobile charging stake according to claim 1, which is characterized in that the step S40 is obtained electronic
The step of charge port position of automobile includes：
Step S43 obtains the model data of electric vehicle；
Step S44, according to the model data automatic identification charge port position of electric vehicle.
8. according to the localization method of claim 1~7 any one of them mobile charging stake, which is characterized in that the step
S10 obtains the image information in movement locus, and further includes before the step of generating 3D rendering according to the image information：
Step S00 obtains the GPS signal of electric vehicle；
Step S01 positions the home position of electric vehicle according to the GPS signal.
9. a kind of positioning device of mobile charging stake, which is characterized in that the positioning device of the mobile charging stake includes：Storage
Device, processor and the finder for being stored in the mobile charging stake that can be run on the memory and on the processor, institute
State the step realized when the finder of mobile charging stake is executed by the processor such as claim 1-8 any one of them methods
Suddenly.
10. a kind of computer readable storage medium, which is characterized in that be stored with moving charging on the computer readable storage medium
It is realized such as any one of claim 1-8 when the finder of the finder of electric stake, the mobile charging stake is executed by processor
The step of localization method of the mobile charging stake.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810383099.6A CN108805014A (en) | 2018-04-26 | 2018-04-26 | Localization method, device and the computer readable storage medium of mobile charging stake |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810383099.6A CN108805014A (en) | 2018-04-26 | 2018-04-26 | Localization method, device and the computer readable storage medium of mobile charging stake |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108805014A true CN108805014A (en) | 2018-11-13 |
Family
ID=64093033
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810383099.6A Pending CN108805014A (en) | 2018-04-26 | 2018-04-26 | Localization method, device and the computer readable storage medium of mobile charging stake |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108805014A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110723024A (en) * | 2019-11-22 | 2020-01-24 | 安徽科创新能源科技有限责任公司 | Region sharing type charging method, device and system |
| CN111332226A (en) * | 2018-12-18 | 2020-06-26 | 罗伯特·博世有限公司 | Providing surrounding environment information determined based on vehicle to service unit |
| CN113378750A (en) * | 2021-06-23 | 2021-09-10 | 北京哈崎机器人科技有限公司 | Charging pile docking method and device, computer equipment and storage medium |
| CN113628275A (en) * | 2021-08-18 | 2021-11-09 | 北京理工大学深圳汽车研究院(电动车辆国家工程实验室深圳研究院) | Charging port pose estimation method and system, charger robot and storage medium |
| CN113378750B (en) * | 2021-06-23 | 2024-06-07 | 北京哈崎机器人科技有限公司 | Charging pile butt joint method and device, computer equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107911490A (en) * | 2017-12-26 | 2018-04-13 | 数源科技股份有限公司 | Intelligent mobile charging pile group system and its control method |
| CN107924465A (en) * | 2016-03-18 | 2018-04-17 | Jvc 建伍株式会社 | Object detector, object identification method and object identification program |
| US10394248B2 (en) * | 2015-12-21 | 2019-08-27 | Xiaomi Inc. | Charging pile, method and device for recognizing the charging pile |
-
2018
- 2018-04-26 CN CN201810383099.6A patent/CN108805014A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10394248B2 (en) * | 2015-12-21 | 2019-08-27 | Xiaomi Inc. | Charging pile, method and device for recognizing the charging pile |
| CN107924465A (en) * | 2016-03-18 | 2018-04-17 | Jvc 建伍株式会社 | Object detector, object identification method and object identification program |
| CN107911490A (en) * | 2017-12-26 | 2018-04-13 | 数源科技股份有限公司 | Intelligent mobile charging pile group system and its control method |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111332226A (en) * | 2018-12-18 | 2020-06-26 | 罗伯特·博世有限公司 | Providing surrounding environment information determined based on vehicle to service unit |
| CN110723024A (en) * | 2019-11-22 | 2020-01-24 | 安徽科创新能源科技有限责任公司 | Region sharing type charging method, device and system |
| CN113378750A (en) * | 2021-06-23 | 2021-09-10 | 北京哈崎机器人科技有限公司 | Charging pile docking method and device, computer equipment and storage medium |
| CN113378750B (en) * | 2021-06-23 | 2024-06-07 | 北京哈崎机器人科技有限公司 | Charging pile butt joint method and device, computer equipment and storage medium |
| CN113628275A (en) * | 2021-08-18 | 2021-11-09 | 北京理工大学深圳汽车研究院(电动车辆国家工程实验室深圳研究院) | Charging port pose estimation method and system, charger robot and storage medium |
| CN113628275B (en) * | 2021-08-18 | 2022-12-02 | 北京理工大学深圳汽车研究院(电动车辆国家工程实验室深圳研究院) | Charging port pose estimation method and system, charger robot and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11972606B2 (en) | Autonomous vehicle lane boundary detection systems and methods | |
| US11217012B2 (en) | System and method for identifying travel way features for autonomous vehicle motion control | |
| Schwesinger et al. | Automated valet parking and charging for e-mobility | |
| CN108318043A (en) | Method, apparatus for updating electronic map and computer readable storage medium | |
| CN110672111B (en) | Vehicle driving path planning method, device, system, medium and equipment | |
| CN110126817B (en) | Method and system for self-adapting to parking or recalling between any point and fixed point | |
| CN103901895B (en) | Target positioning method based on unscented FastSLAM algorithm and matching optimization and robot | |
| US11100646B2 (en) | Future semantic segmentation prediction using 3D structure | |
| CA3170637A1 (en) | System and method for autonomous vehicle systems simulation | |
| CN108805014A (en) | Localization method, device and the computer readable storage medium of mobile charging stake | |
| CN111723659A (en) | Parking space determining method and device, computer equipment and storage medium | |
| US11508157B2 (en) | Device and method of objective identification and driving assistance device | |
| US20220137636A1 (en) | Systems and Methods for Simultaneous Localization and Mapping Using Asynchronous Multi-View Cameras | |
| US20230047094A1 (en) | Image processing method, network training method, and related device | |
| KR102116725B1 (en) | Apparatus and method for distinguishing position of inlet based on recognition of license plate in stopped state | |
| CN106935059A (en) | One kind positioning looks for car system, positioning to look for car method and location positioning method | |
| CA3139421A1 (en) | Automatic annotation of object trajectories in multiple dimensions | |
| KR20230008000A (en) | Positioning method and apparatus based on lane line and feature point, electronic device, storage medium, computer program and autonomous vehicle | |
| CN114554391A (en) | Parking lot vehicle searching method, device, equipment and storage medium | |
| CN109002633B (en) | Device network modeling method based on separate space | |
| CN106205182A (en) | A kind of Intelligent vehicle-tracing system and method | |
| CN112926415A (en) | Pedestrian avoiding system and pedestrian monitoring method | |
| Jiang et al. | Multilayer map construction and vision-only multi-scale localization for intelligent vehicles in underground parking | |
| CN112833889A (en) | Vehicle positioning method and device | |
| Priya et al. | 3DYOLO: Real-time 3D Object Detection in 3D Point Clouds for Autonomous Driving |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181113 |