CN109817018A - A kind of automatic parking method and relevant apparatus - Google Patents
A kind of automatic parking method and relevant apparatus Download PDFInfo
- Publication number
- CN109817018A CN109817018A CN201910126734.7A CN201910126734A CN109817018A CN 109817018 A CN109817018 A CN 109817018A CN 201910126734 A CN201910126734 A CN 201910126734A CN 109817018 A CN109817018 A CN 109817018A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- parking
- image
- parking stall
- relative position
- 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
Landscapes
- Traffic Control Systems (AREA)
Abstract
This application discloses a kind of automatic parking method and relevant apparatus.Vision data, i.e. multiple image are obtained by vehicle-mounted photographic device, parking lot map is established using image thereafter, the parking stall line realizing vehicle location and identify vacant parking stall and the relative position of vehicle, to realize relative positioning.Finally, according to the relative position of parking stall line and vehicle, automatic parking is realized.This method relies on vision data realization and parks, and vehicle or user terminal are not necessarily to carry out data interaction with parking system, thus, the hidden danger of existing Information Security and privacy when avoiding data interaction.In addition, this method is not necessarily to install the special installation to match with parking lot on vehicle, thus, the consumption burden of parking of automatic parking is realized by the way that user is effectively reduced.Also, this method can be applied to any parking scene, therefore applicability is wider.
Description
Technical field
This application involves field of intelligent transportation technology, more particularly to a kind of automatic parking method and relevant apparatus.
Background technique
With the continuous improvement of people's living standards, automobile quantity is also gradually increasing, automobile has become people's life
In one of the most convenient and fast vehicles.It is safe and smooth for new hand driver or for the unfamiliar driver of parking lot landform
It parks and is one and compares stern challenge in ground.For this purpose, more and more parking lots want to utilize automatic pool by parking lot
Vehicle system assists vehicle to realize automatic parking.
However, generally requiring in existing technology by installing the spy interacted with parking system on vehicle at present
Different equipment realizes automatic parking, and therefore, vehicle is required to dock with each parking lot progress data when different parking lots are parked.
At this point, the data safety of vehicle is difficult to obtain effective guarantee.In addition, the partial personal information of car owner is stored on some vehicles,
Therefore, the personal information of car owner is also likely to be present the hidden danger of safety and privacy.
It can be seen that how to guarantee that the data safety of vehicle and user are that this field is badly in need of solving during automatic parking
The technical issues of.
Summary of the invention
Based on the above issues, it this application provides a kind of automatic parking method and relevant apparatus, is realized by vehicle vision
Automatic parking, without carrying out data interaction, vehicle and use during guarantee is parked between vehicle and parking system during parking
The Information Security at family.
The embodiment of the present application discloses following technical solution:
In a first aspect, the application provides a kind of automatic parking method, comprising:
Obtain the multiple image of the vehicle photographic device that sustainable utilization is vehicle-mounted in driving process in parking lot acquisition；It is described
In multiple image, an at least frame image includes the parking stall line of vacant parking stall；
According to the multiple image, parking lot map is established using vision simultaneous localization and mapping vSLAM method, is obtained
Obtain the position of the vehicle described in the coordinate system of the parking lot map；
Obtain the relative position of parking stall line and the vehicle described in the coordinate system of the parking lot map；
According to the relative position of the parking stall line and the vehicle, the vehicle parking is controlled to the vacant parking stall.
Optionally, the relative position according to the parking stall line and the vehicle controls described in the vehicle parking cause
Vacant parking stall specifically includes:
According to the relative position of a plurality of the parking stall line and the vehicle of the vacant parking stall, the vacant parking stall is determined
With the relative position of the vehicle；
According to the relative position of the vacant parking stall and the vehicle, the vehicle parking is controlled to the vacant parking stall.
Optionally, before the control vehicle parking to the vacant parking stall, the method also includes:
According to the relative position of the vacant parking stall and the vehicle, the parking path of the vehicle is planned；
The control vehicle parking is specifically included to the vacant parking stall:
The vehicle is controlled to park according to the parking path to the vacant parking stall.
Optionally, described according to the multiple image, stopped using the foundation of vision simultaneous localization and mapping vSLAM method
Parking lot map, specifically includes:
The fisrt feature point in each frame image is extracted in identification；
According to the fisrt feature point, images match is carried out to each frame image；
By the fisrt feature point in the image of successful match, determine that the photographic device acquires successful match described in each frame
Image when, the vehicle is relative to the distance of the fisrt feature point and the relative position of the vehicle and initial position；
The position of initial position vehicle when being the image of successful match described in photographic device acquisition first frame；
According to the vehicle relative to the distance of the fisrt feature point and the opposite position of the vehicle and initial position
It sets, constructs the parking lot map.
Optionally, the position for obtaining the vehicle described in the coordinate system of the parking lot map, specifically includes:
Obtain the position of the photographic device described in the coordinate system of the parking lot map；
According to the relative mounting location of the position of the photographic device and the photographic device on the vehicle, obtain
Obtain the position of the vehicle described in the coordinate system of the parking lot map.
Optionally, multiple photographic devices are provided on the vehicle, the acquisition vehicle is run in parking lot
The multiple image for the photographic device acquisition that sustainable utilization is vehicle-mounted in journey, specifically includes:
The vehicle is obtained in the parking lot in driving process, the ring of the multiple photographic device acquisitions of sustainable utilization
Visible image；
Image will be looked around described in each frame and is spliced into a frame overhead view image, obtains multiframe overhead view image.
Second aspect, the application provide a kind of automatic parking device, comprising:
Image collection module, for obtaining vehicle, the vehicle-mounted photographic device of sustainable utilization is adopted in driving process in parking lot
The multiple image of collection；In the multiple image, an at least frame image includes the parking stall line of vacant parking stall；
Module is positioned and builds, for utilizing the vision simultaneous localization and mapping side vSLAM according to the multiple image
Method establishes parking lot map, obtains the position of the vehicle described in the coordinate system of the parking lot map；
Relative position obtains module, for obtaining the parking stall line described in the coordinate system of the parking lot map and the vehicle
Relative position；
Control module of parking controls the vehicle parking for the relative position according to the parking stall line and the vehicle
To the vacant parking stall.
Optionally, the control module of parking, specifically includes:
Relative position determination unit, for opposite with the vehicle according to a plurality of parking stall line of the vacant parking stall
Position determines the relative position of the vacant parking stall Yu the vehicle；
Control unit of parking controls the vehicle pool for the relative position according to the vacant parking stall and the vehicle
Vehicle is to the vacant parking stall.
Optionally, described device further include:
Path planning module plans the vehicle for the relative position according to the vacant parking stall and the vehicle
Parking path；
The control unit of parking, specifically includes:
First, which parks, controls subelement, parks according to the parking path to the vacant vehicle for controlling the vehicle
Position.
Optionally, described to position and build module, it specifically includes:
Feature point recognition unit extracts the fisrt feature point in each frame image for identification；
Image matching unit, for carrying out images match to each frame image according to the fisrt feature point；
Distance and relative position determination unit, described in determining by the fisrt feature point in the image of successful match
When photographic device acquires the image of successful match described in each frame, distance of the vehicle relative to the fisrt feature point, and
The relative position of the vehicle and initial position；The initial position is that the photographic device acquires successful match described in first frame
Image when the vehicle position；
Map constructing unit, for according to the vehicle relative to the fisrt feature point distance and the vehicle
With the relative position of initial position, the parking lot map is constructed.
Optionally, described to position and build module, it specifically includes:
First positioning unit, for obtaining the position of the photographic device described in the coordinate system of the parking lot map；
Second positioning unit, for the position and the photographic device according to the photographic device in the vehicle
Relative mounting location, obtain the vehicle described in the coordinate system of the parking lot map position.
Optionally, multiple photographic devices are provided on the vehicle, described image obtains module, specifically includes:
Image acquisition unit is looked around, for obtaining the vehicle in the parking lot in driving process, sustainable utilization is more
Image is looked around in a photographic device acquisition；
Image mosaic unit being spliced into a frame overhead view image for will look around image described in each frame, obtaining multiframe and overlooking
Image.
Compared to the prior art, the application has the advantages that
Automatic parking method provided by the present application obtains vision data, i.e. multiple image by vehicle-mounted photographic device,
Parking lot map is established using image afterwards, the parking stall line realizing vehicle location and identify vacant parking stall and the relative position of vehicle,
To realize relative positioning.Finally, according to the relative position of parking stall line and vehicle, automatic parking is realized.
It parks it can be seen that this method relies on vision data realization, vehicle or user terminal is not necessarily to and parking system
Data interaction is carried out, thus, the hidden danger of existing Information Security and privacy when avoiding data interaction.In addition, this method without
The special installation to match with parking lot need to be installed on vehicle, thus, the pool of automatic parking is realized by the way that user is effectively reduced
Vehicle consumption burden.Also, this method can be applied to any parking scene, therefore applicability is wider.
Detailed description of the invention
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of application without any creative labor, may be used also for those of ordinary skill in the art
To obtain other drawings based on these drawings.
Fig. 1 is a kind of flow chart of automatic parking method provided by the embodiments of the present application；
Fig. 2 is the flow chart of another automatic parking method provided by the embodiments of the present application；
Fig. 3 is a kind of vacant parking stall schematic diagram provided by the embodiments of the present application；
Fig. 4 is a kind of structural schematic diagram of automatic parking device provided by the embodiments of the present application.
Specific embodiment
Describe as discussed above, at present it is some realize automatic parkings or parking path planning methods generally require vehicle or
User terminal and parking system carry out data interaction.To cause the Information Security of vehicle and user that cannot ensure.
Based on this, this application provides a kind of automatic parking method and relevant apparatus, based on being moored automatically from vehicle vision
Vehicle.This method utilizes thereafter merely with the multiple image obtained in parking lot from the photographic device that vehicle loads, i.e. vision data
VSLAM method creates parking lot map, and realizes vehicle location, and obtains the relative position of vacant parking stall stop line and vehicle
Relationship finally realizes automatic parking.Data interaction is carried out due to being not necessarily to vehicle or user terminal and parking system during this,
Therefore, it is capable of the safety of effective guarantee vehicle and user data.
In order to enable those skilled in the art to better understand the solution of the present invention, below in conjunction in the embodiment of the present invention
Attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is only this
Invention a part of the embodiment, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art exist
Every other embodiment obtained under the premise of creative work is not made, shall fall within the protection scope of the present invention.
First embodiment
Referring to Fig. 1, which is a kind of flow chart of automatic parking method provided by the embodiments of the present application.
As shown in Figure 1, automatic parking method provided in this embodiment, comprising:
Step 101: obtaining the multiframe of the vehicle photographic device that sustainable utilization is vehicle-mounted in driving process in parking lot acquisition
Image.
In the present embodiment, vehicle-mounted photographic device can be the depth camera for capableing of sampling depth image, be also possible to general
Logical imaging device.Photographic device can be set in roof, be specifically as follows one, or multiple.It is right in the present embodiment
It is not limited in the concrete type of photographic device, installation site and quantity.
For vehicle in parking lot in driving process, photographic device can be continuously shot multiframe figure under the manipulation of driver
Picture.It is of course also possible to shoot one section of video, several frame images are further extracted from video for subsequent processing.
The frequency that photographic device acquires image can be according in the speed and/or parking lot that vehicle is driven a vehicle in parking lot
Environment is configured.In practical applications, image can be acquired as frequently as possible, to the greatest extent may be used with guaranteeing to have in consecutive frame image
Common trait point more than energy.And then guarantees the accuracy of subsequent builds map and realize the accuracy of vehicle location.
It should be noted that in the multiple image, at least to have in a frame image comprising vacant for realization automatic parking
The parking stall line of parking stall.
Step 102: according to the multiple image, being established and stopped using vision simultaneous localization and mapping vSLAM method
Place figure obtains the position of the vehicle described in the coordinate system of the parking lot map.
In the embodiment of the present application, vision simultaneous localization and mapping (Visual Simultaneous is utilized
Locatization and Mapping, vSLAM) method realize vehicle positioning.It is in specific implementation, mainly by means of step
Characteristic point in 101 multiple images obtained constructs the connection between each frame image.Then, according to the connection between each frame image
System, the positional relationship and/or distance relation of building vehicle and characteristic point common in each frame image.To final to realize to whole
The building of map in a parking lot scene, knows position of the vehicle in the map of parking lot.
Step 103: obtaining the relative position of parking stall line and the vehicle described in the coordinate system of the parking lot map.
Due to having been set up parking lot map, and specify vehicle in parking lot map after step 102 executes
Interior position, while the stop line at least deposited in multiple image in one frame of image comprising vacant vehicle in parking lot therefore can
Using the relative position in the parking lot map by stop line as characteristic point, between acquisition this feature point and vehicle.
Step 104: according to the relative position of the parking stall line and the vehicle, controlling the vehicle parking to described vacant
Parking stall.
In the map of parking lot, the opposite position of the parking stall line and vehicle in position and image due to there is known vehicle
It sets, while there are certain positional relationships with vacant parking stall for parking stall line, therefore, passes through these positional relationship energy that convert in this step
Vehicle is set to reach vacant parking stall according to the mobile distance accordingly of control, enough to realize automatic parking.
For example, being located at the center of the rectangle of four parking stall lines building, the end of four parking stall lines according to the position of vacant parking stall
The relative position with vehicle is put it is known that the relative position of vehicle and vacant parking stall can be obtained in turn.It is current by planning vehicle
Path between position and vacant parking stall controls vehicle according to the route, can smoothly moor vehicle into the vacant parking stall.
It is above automatic parking method provided by the embodiments of the present application.This method obtains vehicle in parking lot expert first
The multiple image for the photographic device acquisition that sustainable utilization is vehicle-mounted during sailing；In the multiple image, an at least frame image packet
Parking stall line containing vacant parking stall；Thereafter, according to the multiple image, vision simultaneous localization and mapping vSLAM method is utilized
Parking lot map is established, the position of the vehicle described in the coordinate system of the parking lot map is obtained；Also, acquisition stops described
The relative position of parking stall line and the vehicle described in the coordinate system of parking lot map；Finally, according to the parking stall line and the vehicle
Relative position, control the vehicle parking to the vacant parking stall.
It parks it can be seen that this method relies on vision data realization, vehicle or user terminal is not necessarily to and parking system
Data interaction is carried out, thus, the hidden danger of existing Information Security and privacy when avoiding data interaction.In addition, this method without
The special installation to match with parking lot need to be installed on vehicle, thus, the pool of automatic parking is realized by the way that user is effectively reduced
Vehicle consumption burden.Also, this method can be applied to any parking scene, therefore applicability is wider.
Based on previous embodiment, the application also provides another automatic parking method.Below with reference to embodiment and attached drawing pair
This method is described in detail.
Second embodiment
Referring to fig. 2, which is the flow chart of another automatic parking method provided by the embodiments of the present application.
As shown in Fig. 2, automatic parking method provided in this embodiment, comprising:
Step 201: obtaining the multiframe of the vehicle photographic device that sustainable utilization is vehicle-mounted in driving process in parking lot acquisition
Image, in the multiple image, an at least frame image includes the parking stall line of vacant parking stall.
It should be noted that step 201 is identical as the implementation of step 101 in previous embodiment in the present embodiment.It closes
It can be found in previous embodiment in the associated description of step 201, no longer repeated herein.
Step 202: the fisrt feature point in each frame image is extracted in identification.
As an example, continuing through vehicle-mounted photographic device in the driving process of parking lot in vehicle has taken 10 frame figures
Picture, wherein the black square alarm on the metope of parking lot has been taken in the 3rd frame, the 4th frame and the 5th frame image.It can incite somebody to action
The top left corner apex of the alarm is as a fisrt feature point.
That is, in this step, this you can well imagine the top left corner apex taken in the 3rd frame, the 4th frame and the 5th frame image.
In the present embodiment, fisrt feature point specifically can be common existing characteristic point in consecutive frame image, above-mentioned
In example, the top left corner apex of alarm can be, naturally it is also possible to it is lower-left angular vertex, upper right angular vertex, bottom right angular vertex,
Either other shared characteristic points.Therefore, in the present embodiment, for fisrt feature point particular content without limit.
It is understood that fisrt feature point may be one, it is also possible to be multiple in consecutive frame image.For example, the
There is the top left corner apex of alarm and the handle tail end of fire extinguisher on 3 frame images and the 4th frame image jointly.Therefore, it alarms
The top left corner apex of device and the handle tail end of fire extinguisher are respectively the characteristic point that the 3rd frame image and the 4th frame image share, that is, the 3rd
Two fisrt feature points of frame image and the 4th frame image.
Step 203: according to the fisrt feature point, images match being carried out to each frame image.
Due to having recognized common existing characteristic point, i.e. fisrt feature point in consecutive frame image, therefore can will have
The consecutive frame image of fisrt feature point carries out images match.It is understood that vehicle is held during because obtaining multiple image
Supervention gives birth to movement, and accordingly, there exist the positions of fisrt feature point on the adjacent image of fisrt feature point to certainly exist difference.Together
When, the change in location of fisrt feature point in the picture can correspondingly embody the actual change situation of vehicle location.
This step is illustrated below.
For example, extracting the top left corner apex that the fisrt feature point that the 3rd frame and the 4th frame image have is alarm；4th frame
The fisrt feature point having with the 5th frame image is the handle tail end of fire extinguisher；The fisrt feature that 5th frame and the 6th frame image have
Point is the tip of road surface arrow.It, can accordingly, respectively by the 3rd frame and the 4th frame image, the 4th frame and the 5th frame in this step
Image and the 5th frame and the 6th frame image carry out images match.
It is understood that in practical applications, the quantity of the point of fisrt feature present in consecutive frame image is more, have
The number of image frames of same fisrt feature point is more, and image matching effect is more accurate, and each object relative positional relationship judgement in space is got over
Accurately.
Step 204: by the fisrt feature point in the image of successful match, determining that the photographic device acquires described in each frame
When the image of successful match, the vehicle is relative to the distance of the fisrt feature point and the vehicle and initial position
Relative position.
If there are fisrt feature point, images match successes in consecutive frame image.Correspondingly, if in consecutive frame image
There is no fisrt feature points, then images match fails.Therefore, the image of successful match is specifically referred to comprising at least one the first spy
Levy the image of point.
It should be noted that the initial position of vehicle refers to a photographic device acquisition frame successful match at first in this step
Image when the location of vehicle.
As an example, if the 3rd frame, the 4th frame and the 5th frame include same characteristic point A, by the execution of step 203, the
Successful match between 3 frames, the 4th frame and the 5th frame image.Since the 3rd frame image is a frame figure at first in the image of successful match
Picture, can be using the position of vehicle when obtaining the 3rd frame image as the initial position of vehicle.It, can by images match in this step
When obtaining the 3rd frame of shooting, the 4th frame and the 5th frame image, vehicle is respectively L at a distance from fisrt feature point A1、L2And L3, and
The relative position of vehicle and initial position is respectively (0,0), (x2-x0,y2-y0) and (x3-x0,y3-y0)。
Step 205: according to the vehicle relative to the distance of the fisrt feature point and the vehicle and initial position
Relative position, construct the parking lot map.
It is understood that the number of image frames that acquisition obtains is more, the image of successful match is more, and first in image is special
Sign point is more, and the parking lot map of building is more accurate.
Step 206: according to the relative position of a plurality of the parking stall line and the vehicle of the vacant parking stall, determine described in
The relative position of vacant parking stall and the vehicle.
Since in the multiple image of acquisition, an at least frame image includes the parking stall line of vacant parking stall therefore can be by vehicle
Bit line is as the feature in image, and by certain points in feature, such as endpoint and/or angle point are as second feature point.
After step 205 executes, the parking lot map constructed is obtained, therefore, second feature point can have been directly obtained
With relative position of the vehicle in parking lot.
It is contacted it is understood that each parking stall line exists with second feature point, i.e., parking stall line includes second feature point；
Meanwhile vacant parking stall is contacted with the presence of parking stall line, i.e., a plurality of parking stall line constitutes vacant parking stall.Therefore, correspondingly, according to multiple
The relative position of two characteristic points and vehicle may finally obtain the relative position of vacant parking stall and vehicle.
Step 206 is illustrated below with reference to example.
Referring to Fig. 3, which is a kind of vacant parking stall schematic diagram provided by the embodiments of the present application.
As shown in figure 3, vacant parking stall is made of four parking stalls line ab, bc, cd and ad.Wherein, the rectangle that parking stall line is constituted
Angle point a, b, c and d of vacant parking stall can be respectively as second feature points.When a, b, c and d and vehicle in the map of parking lot
Relative position it is known that if with the central point u of rectangle vacant parking stall, i.e., mass center can then hold very much as the position of vacant parking stall
It changes places and obtains the relative position of central point u and vehicle according to the relative position of second feature point and vehicle.To determine vacant vehicle
The relative position of position and vehicle.
The specific strategy with parking path planning it should be noted that the specific positioning method of vacant parking stall and control are parked
It is related.Above example is using the position of the central point u of vacant parking stall as the position of vacant parking stall, certainly, in a particular application, root
According to control park with parking path planning specific strategy, it is also possible to using a, b, c or d point as the position of vacant parking stall, or
Using other boundary points of vacant parking stall, characteristic point as parking stall position.Therefore, the positioning in the present embodiment, for vacant parking stall
Method is without specifically limiting.
Step 207: according to the relative position of the vacant parking stall and the vehicle, planning the parking path of the vehicle.
In the case that position of the vehicle in the map of parking lot is determining, the relative position of vacant parking stall and vehicle determines,
Can the path easily to vehicle automatic parking plan.
Certainly, in practical applications, also the size of the objects such as barrier, wall, column can be determined according to parking lot map
And the relative position with vehicle, so that planning, which obtains, can hide open the above obstruction row when planning the parking path of vehicle
The object of vehicle smoothly moors the path into vacant parking stall.
Step 208: controlling the vehicle and park according to the parking path to the vacant parking stall.
It is understood that needing when control vehicle parking in view of controling parameters such as speed, corner, turn signals.This reality
It applies in example, when vehicle starts to execute automatic parking, vehicle can be controlled according to above-mentioned by the automatic parking device installed on vehicle
Parking path is parked to vacant parking stall, and in parking process is travelled according to the speed of planning, steering angle, carves open when needed
With closing turn signal.
It is above automatic parking method provided by the embodiments of the present application.This method passes through the fisrt feature in identification image
Point, and images match is carried out based on fisrt feature point；By images match obtain vehicle relative to the fisrt feature point away from
From and the vehicle and initial position relative position；Thereafter, parking lot map is constructed, then determines vacant parking stall and vehicle
Relative position；Final planning automatic parking path, and vehicle is controlled according to the parking path automatic parking of planning to vacant vehicle
Position.This method is suitable for realizing automatic parking in any strange parking lot, and applicability is wider, and improve automatic parking can
By property.
It is understood that in the aforementioned embodiment, if the setting installation site and vehicle centroid of vehicle mounted imaging apparatus
It is overlapped, and using centroid position as the position of vehicle, then position of the photographic device in the map coordinates system of parking lot can be used as
Position of the vehicle in the map coordinates system of parking lot.And if vehicle mounted imaging apparatus is not overlapped with the mass center of vehicle, and with matter
Heart position is the position of vehicle, then, can also position according to photographic device and camera shooting in technical solution provided by the present application
Relative mounting location of the device on vehicle obtains the centroid position of vehicle in the map coordinates system of parking lot as vehicle location.
As an example, photographic device is (Δ x relative to the position of fisrt feature point in the map coordinates system of parking lot1,Δ
y1), vehicle centroid is (Δ x relative to the position of photographic device2,Δy2), then with center coordination vehicle in the case where, vehicle phase
Position for fisrt feature point is (Δ x1+Δx2,Δy1+Δy2)。
In addition, multiple image can be and directly be shot acquisition using photographic device, also in embodiment provided by the present application
It can be the overhead view image looking around image and being spliced shot by multiple vehicle mounted imaging apparatus.
It is illustrated below by citing.Four photographic devices have been installed on vehicle, are respectively used to shooting vehicle front, a left side
The image of side, rear and right side.Vehicle is in parking lot in driving process, and four photographic devices are according under same control command
Image is acquired according to same frequency acquisition.To which in automatic parking method provided in this embodiment, what is finally got is one
The another frame of frame looks around image.It is handled by image mosaic, can finally obtain the overhead view image of the another frame of a frame.Thereafter, then
The processing of vSLAM method is carried out to overhead view image.
Based on previous embodiment, correspondingly, the application also provides a kind of automatic parking device.Below with reference to embodiment and attached
The specific implementation of the device is described in figure.
3rd embodiment
Referring to fig. 4, which is a kind of structural schematic diagram of automatic parking device provided by the embodiments of the present application.
As shown in figure 4, automatic parking device provided in this embodiment, comprising: image collection module 401 positions and build figure
Module 402, relative position obtain module 403 and control module 404 of parking.
Wherein, image collection module 401, sustainable utilization is vehicle-mounted in driving process for obtaining vehicle in parking lot takes the photograph
The multiple image acquired as device；In the multiple image, an at least frame image includes the parking stall line of vacant parking stall；
Module 402 is positioned and builds, for utilizing vision simultaneous localization and mapping according to the multiple image
VSLAM method establishes parking lot map, obtains the position of the vehicle described in the coordinate system of the parking lot map；
Relative position obtains module 403, for obtaining the parking stall line described in the coordinate system of the parking lot map and institute
State the relative position of vehicle；
Control module of parking 404 controls the vehicle pool for the relative position according to the parking stall line and the vehicle
Vehicle is to the vacant parking stall.
It is above automatic parking device provided in this embodiment, which relies on vision data realization and park, vehicle
Or user terminal is not necessarily to carry out data interaction with parking system, thus, when avoiding data interaction existing Information Security and
The hidden danger of privacy.In addition, the device is not necessarily to install the special installation to match with parking lot on vehicle, thus, by having
Effect reduces the consumption burden of parking that user realizes automatic parking.Also, the device can be applied to any parking scene, therefore suitable
It is wider with property.
As a kind of possible implementation, the control module 404 of parking is specifically included:
Relative position determination unit, for opposite with the vehicle according to a plurality of parking stall line of the vacant parking stall
Position determines the relative position of the vacant parking stall Yu the vehicle；
Control unit of parking controls the vehicle pool for the relative position according to the vacant parking stall and the vehicle
Vehicle is to the vacant parking stall.
As a kind of possible implementation, described device further include:
Path planning module plans the vehicle for the relative position according to the vacant parking stall and the vehicle
Parking path；
The control unit of parking, specifically includes:
First, which parks, controls subelement, parks according to the parking path to the vacant vehicle for controlling the vehicle
Position.
It is described to position and build module 402 as a kind of possible implementation, it specifically includes:
Feature point recognition unit extracts the fisrt feature point in each frame image for identification；
Image matching unit, for carrying out images match to each frame image according to the fisrt feature point；
Distance and relative position determination unit, described in determining by the fisrt feature point in the image of successful match
When photographic device acquires the image of successful match described in each frame, distance of the vehicle relative to the fisrt feature point, and
The relative position of the vehicle and initial position；The initial position is that the photographic device acquires successful match described in first frame
Image when the vehicle position；
Map constructing unit, for according to the vehicle relative to the fisrt feature point distance and the vehicle
With the relative position of initial position, the parking lot map is constructed.
It is described to position and build module 402 as a kind of possible implementation, it specifically includes:
First positioning unit, for obtaining the position of the photographic device described in the coordinate system of the parking lot map；
Second positioning unit, for the position and the photographic device according to the photographic device in the vehicle
Relative mounting location, obtain the vehicle described in the coordinate system of the parking lot map position.
As a kind of possible implementation, multiple photographic devices are provided on the vehicle, described image obtains
Module 401, specifically includes:
Image acquisition unit is looked around, for obtaining the vehicle in the parking lot in driving process, sustainable utilization is more
Image is looked around in a photographic device acquisition；
Image mosaic unit being spliced into a frame overhead view image for will look around image described in each frame, obtaining multiframe and overlooking
Image.
It should be noted that all the embodiments in this specification are described in a progressive manner, each embodiment it
Between same and similar part may refer to each other, each embodiment focuses on the differences from other embodiments.
For equipment and system embodiment, since it is substantially similar to the method embodiment, so describe fairly simple,
The relevent part can refer to the partial explaination of embodiments of method.Equipment and system embodiment described above is only schematic
, wherein unit may or may not be physically separated as illustrated by the separation member, as unit prompt
Component may or may not be physical unit, it can and it is in one place, or may be distributed over multiple networks
On unit.Some or all of the modules therein can be selected to achieve the purpose of the solution of this embodiment according to the actual needs.
Those of ordinary skill in the art can understand and implement without creative efforts.
The above, only a kind of specific embodiment of the application, but the protection scope of the application is not limited thereto,
Within the technical scope of the present application, any changes or substitutions that can be easily thought of by anyone skilled in the art,
Should all it cover within the scope of protection of this application.Therefore, the protection scope of the application should be with scope of protection of the claims
Subject to.
Claims (12)
1. a kind of automatic parking method characterized by comprising
Obtain the multiple image of the vehicle photographic device that sustainable utilization is vehicle-mounted in driving process in parking lot acquisition；The multiframe
In image, an at least frame image includes the parking stall line of vacant parking stall；
According to the multiple image, parking lot map is established using vision simultaneous localization and mapping vSLAM method, is obtained
The position of vehicle described in the coordinate system of the parking lot map；
Obtain the relative position of parking stall line and the vehicle described in the coordinate system of the parking lot map；
According to the relative position of the parking stall line and the vehicle, the vehicle parking is controlled to the vacant parking stall.
2. according to right to go 1 described in automatic parking method, which is characterized in that it is described according to the parking stall line and the vehicle
Relative position, control the vehicle parking and cause the vacant parking stall, specifically include:
According to the relative position of a plurality of the parking stall line and the vehicle of the vacant parking stall, the vacant parking stall and institute are determined
State the relative position of vehicle；
According to the relative position of the vacant parking stall and the vehicle, the vehicle parking is controlled to the vacant parking stall.
3. automatic parking method according to claim 2, which is characterized in that in the control vehicle parking to described
Before vacant parking stall, the method also includes:
According to the relative position of the vacant parking stall and the vehicle, the parking path of the vehicle is planned；
The control vehicle parking is specifically included to the vacant parking stall:
The vehicle is controlled to park according to the parking path to the vacant parking stall.
4. automatic parking method according to any one of claim 1 to 3, which is characterized in that described according to the multiframe
Image is established parking lot map using vision simultaneous localization and mapping vSLAM method, is specifically included:
The fisrt feature point in each frame image is extracted in identification；
According to the fisrt feature point, images match is carried out to each frame image；
By the fisrt feature point in the image of successful match, determine that the photographic device acquires the figure of successful match described in each frame
When picture, the vehicle is relative to the distance of the fisrt feature point and the relative position of the vehicle and initial position；It is described
The position of initial position vehicle when being the image of successful match described in photographic device acquisition first frame；
According to the vehicle relative to the distance of the fisrt feature point and the relative position of the vehicle and initial position,
Construct the parking lot map.
5. automatic parking method according to any one of claim 1 to 3, which is characterized in that the acquisition stops described
The position of vehicle described in the coordinate system of parking lot map, specifically includes:
Obtain the position of the photographic device described in the coordinate system of the parking lot map；
According to the relative mounting location of the position of the photographic device and the photographic device on the vehicle, obtain
The position of vehicle described in the coordinate system of the parking lot map.
6. automatic parking method according to any one of claim 1 to 3, which is characterized in that be provided on the vehicle
Multiple photographic devices, it is described to obtain what the vehicle photographic device that sustainable utilization is vehicle-mounted in driving process in parking lot acquired
Multiple image specifically includes:
The vehicle is obtained in the parking lot in driving process, the panoramic view of the multiple photographic device acquisitions of sustainable utilization
Picture；
Image will be looked around described in each frame and is spliced into a frame overhead view image, obtains multiframe overhead view image.
7. a kind of automatic parking device characterized by comprising
Image collection module, for obtaining the acquisition of the vehicle photographic device that sustainable utilization is vehicle-mounted in driving process in parking lot
Multiple image；In the multiple image, an at least frame image includes the parking stall line of vacant parking stall；
Module is positioned and builds, for being built using vision simultaneous localization and mapping vSLAM method according to the multiple image
Vertical parking lot map, obtains the position of the vehicle described in the coordinate system of the parking lot map；
Relative position obtains module, for obtaining the parking stall line described in the coordinate system of the parking lot map and the vehicle
Relative position；
Control module of parking controls the vehicle parking to institute for the relative position according to the parking stall line and the vehicle
State vacant parking stall.
8. according to right to go 7 described in automatic parking device, which is characterized in that the control module of parking specifically includes:
Relative position determination unit, for the opposite position according to a plurality of the parking stall line and the vehicle of the vacant parking stall
It sets, determines the relative position of the vacant parking stall Yu the vehicle；
Control unit of parking controls the vehicle parking extremely for the relative position according to the vacant parking stall and the vehicle
The vacant parking stall.
9. automatic parking device according to claim 8, which is characterized in that described device further include:
Path planning module plans parking for the vehicle for the relative position according to the vacant parking stall and the vehicle
Path；
The control unit of parking, specifically includes:
First, which parks, controls subelement, parks according to the parking path to the vacant parking stall for controlling the vehicle.
10. automatic parking device according to any one of claims 7 to 9, which is characterized in that described to position and build artwork
Block specifically includes:
Feature point recognition unit extracts the fisrt feature point in each frame image for identification；
Image matching unit, for carrying out images match to each frame image according to the fisrt feature point；
Distance and relative position determination unit, for determining the camera shooting by the fisrt feature point in the image of successful match
When device acquires the image of successful match described in each frame, the vehicle is relative to the distance of the fisrt feature point and described
The relative position of vehicle and initial position；The initial position is the figure that the photographic device acquires successful match described in first frame
As when the vehicle position；
Map constructing unit, for according to the vehicle relative to the distance of the fisrt feature point and the vehicle and just
The relative position of beginning position constructs the parking lot map.
11. automatic parking device according to any one of claims 7 to 9, which is characterized in that described to position and build artwork
Block specifically includes:
First positioning unit, for obtaining the position of the photographic device described in the coordinate system of the parking lot map；
Second positioning unit, for phase of the position and the photographic device according to the photographic device on the vehicle
To installation site, the position of the vehicle described in the coordinate system of the parking lot map is obtained.
12. automatic parking device according to any one of claims 7 to 9, which is characterized in that be provided on the vehicle
Multiple photographic devices, described image obtain module, specifically include:
Image acquisition unit is looked around, for obtaining the vehicle in the parking lot in driving process, the multiple institutes of sustainable utilization
That states photographic device acquisition looks around image；
Image mosaic unit being spliced into a frame overhead view image for will look around image described in each frame, obtaining multiframe overhead view image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910126734.7A CN109817018A (en) | 2019-02-20 | 2019-02-20 | A kind of automatic parking method and relevant apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910126734.7A CN109817018A (en) | 2019-02-20 | 2019-02-20 | A kind of automatic parking method and relevant apparatus |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109817018A true CN109817018A (en) | 2019-05-28 |
Family
ID=66607042
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910126734.7A Pending CN109817018A (en) | 2019-02-20 | 2019-02-20 | A kind of automatic parking method and relevant apparatus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109817018A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110415555A (en) * | 2019-08-30 | 2019-11-05 | 的卢技术有限公司 | A kind of recognition methods of effective scribing line parking stall and system based on deep learning |
| CN110497901A (en) * | 2019-08-30 | 2019-11-26 | 的卢技术有限公司 | A kind of parking position automatic search method and system based on robot VSLAM technology |
| CN110544386A (en) * | 2019-09-18 | 2019-12-06 | 奇瑞汽车股份有限公司 | parking space identification method and device and storage medium |
| CN111016887A (en) * | 2019-12-23 | 2020-04-17 | 深圳市豪恩汽车电子装备股份有限公司 | Automatic parking device and method for motor vehicle |
| CN111428547A (en) * | 2019-06-24 | 2020-07-17 | 杭州海康威视数字技术股份有限公司 | Parking space determining method and device |
| CN111746521A (en) * | 2020-06-29 | 2020-10-09 | 芜湖雄狮汽车科技有限公司 | Parking route planning method, device, equipment and storage medium |
| CN111986506A (en) * | 2020-07-20 | 2020-11-24 | 苏州易航远智智能科技有限公司 | Mechanical parking space parking method based on multi-vision system |
| CN112037567A (en) * | 2020-09-04 | 2020-12-04 | 中国第一汽车股份有限公司 | Passenger-riding parking method, device, equipment and storage medium |
| CN112115741A (en) * | 2019-06-20 | 2020-12-22 | 上海汽车集团股份有限公司 | Parking garage position detection method and device |
| CN112419776A (en) * | 2020-10-16 | 2021-02-26 | 爱驰汽车（上海）有限公司 | Autonomous parking method and device, automobile and computing equipment |
| CN113012457A (en) * | 2021-02-18 | 2021-06-22 | 湖南国科微电子股份有限公司 | Navigation parking method, device, equipment and medium for underground garage |
| CN114613193A (en) * | 2022-03-22 | 2022-06-10 | 重庆长安汽车股份有限公司 | Calculation force sharing-based parking space acquisition method, storage medium, system and vehicle |
| CN114783172A (en) * | 2021-01-22 | 2022-07-22 | 广州汽车集团股份有限公司 | Method and system for identifying empty parking space of parking lot and computer readable storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140292541A1 (en) * | 2011-12-14 | 2014-10-02 | Ronen Korman | Method and system for automatic vacant parking place locator |
| CN105015419A (en) * | 2015-07-17 | 2015-11-04 | 中山大学 | Automatic parking system and method based on stereoscopic vision localization and mapping |
| KR101682281B1 (en) * | 2014-12-01 | 2016-12-05 | 호서대학교 산학협력단 | Parking lot automatic guide system |
| CN109094556A (en) * | 2018-07-25 | 2018-12-28 | 深圳大学 | A kind of automatic parking method and system based on parking stall characteristic point |
| CN109229095A (en) * | 2018-10-30 | 2019-01-18 | 百度在线网络技术（北京）有限公司 | For determining the method, apparatus, equipment and storage medium of automatic parking effect |
-
2019
- 2019-02-20 CN CN201910126734.7A patent/CN109817018A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140292541A1 (en) * | 2011-12-14 | 2014-10-02 | Ronen Korman | Method and system for automatic vacant parking place locator |
| KR101682281B1 (en) * | 2014-12-01 | 2016-12-05 | 호서대학교 산학협력단 | Parking lot automatic guide system |
| CN105015419A (en) * | 2015-07-17 | 2015-11-04 | 中山大学 | Automatic parking system and method based on stereoscopic vision localization and mapping |
| CN109094556A (en) * | 2018-07-25 | 2018-12-28 | 深圳大学 | A kind of automatic parking method and system based on parking stall characteristic point |
| CN109229095A (en) * | 2018-10-30 | 2019-01-18 | 百度在线网络技术（北京）有限公司 | For determining the method, apparatus, equipment and storage medium of automatic parking effect |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112115741B (en) * | 2019-06-20 | 2024-02-20 | 上海汽车集团股份有限公司 | Parking garage position detection method and device |
| CN112115741A (en) * | 2019-06-20 | 2020-12-22 | 上海汽车集团股份有限公司 | Parking garage position detection method and device |
| CN111428547A (en) * | 2019-06-24 | 2020-07-17 | 杭州海康威视数字技术股份有限公司 | Parking space determining method and device |
| CN111428547B (en) * | 2019-06-24 | 2024-03-01 | 杭州海康威视数字技术股份有限公司 | Parking space determining method and device |
| CN110415555B (en) * | 2019-08-30 | 2020-09-29 | 的卢技术有限公司 | Effective lineation parking space identification method and system based on deep learning |
| CN110497901B (en) * | 2019-08-30 | 2020-12-22 | 的卢技术有限公司 | Parking space automatic searching method and system based on robot VSLAM technology |
| CN110415555A (en) * | 2019-08-30 | 2019-11-05 | 的卢技术有限公司 | A kind of recognition methods of effective scribing line parking stall and system based on deep learning |
| CN110497901A (en) * | 2019-08-30 | 2019-11-26 | 的卢技术有限公司 | A kind of parking position automatic search method and system based on robot VSLAM technology |
| CN110544386A (en) * | 2019-09-18 | 2019-12-06 | 奇瑞汽车股份有限公司 | parking space identification method and device and storage medium |
| CN111016887A (en) * | 2019-12-23 | 2020-04-17 | 深圳市豪恩汽车电子装备股份有限公司 | Automatic parking device and method for motor vehicle |
| CN111746521A (en) * | 2020-06-29 | 2020-10-09 | 芜湖雄狮汽车科技有限公司 | Parking route planning method, device, equipment and storage medium |
| CN111986506A (en) * | 2020-07-20 | 2020-11-24 | 苏州易航远智智能科技有限公司 | Mechanical parking space parking method based on multi-vision system |
| CN111986506B (en) * | 2020-07-20 | 2022-04-01 | 苏州易航远智智能科技有限公司 | Mechanical parking space parking method based on multi-vision system |
| CN112037567A (en) * | 2020-09-04 | 2020-12-04 | 中国第一汽车股份有限公司 | Passenger-riding parking method, device, equipment and storage medium |
| CN112419776A (en) * | 2020-10-16 | 2021-02-26 | 爱驰汽车（上海）有限公司 | Autonomous parking method and device, automobile and computing equipment |
| CN114783172A (en) * | 2021-01-22 | 2022-07-22 | 广州汽车集团股份有限公司 | Method and system for identifying empty parking space of parking lot and computer readable storage medium |
| CN114783172B (en) * | 2021-01-22 | 2024-05-17 | 广州汽车集团股份有限公司 | Parking lot empty space recognition method and system and computer readable storage medium |
| CN113012457B (en) * | 2021-02-18 | 2022-06-07 | 湖南国科微电子股份有限公司 | Navigation parking method, device, equipment and medium for underground garage |
| CN113012457A (en) * | 2021-02-18 | 2021-06-22 | 湖南国科微电子股份有限公司 | Navigation parking method, device, equipment and medium for underground garage |
| CN114613193A (en) * | 2022-03-22 | 2022-06-10 | 重庆长安汽车股份有限公司 | Calculation force sharing-based parking space acquisition method, storage medium, system and vehicle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109817018A (en) | A kind of automatic parking method and relevant apparatus | |
| CN112802346B (en) | Autonomous parking system and method based on cloud sharing and map fusion | |
| CN103473951B (en) | A kind of Automatic Carpark Control System based on telepresenc | |
| CN103465906B (en) | A kind of parking area automatic train stop implementation method based on telepresenc | |
| WO2022110049A1 (en) | Navigation method, apparatus, and system | |
| CN111976717B (en) | Intelligent parking method and device | |
| US20170253237A1 (en) | Vehicle vision system with automatic parking function | |
| CN106598039B (en) | A kind of Intelligent Mobile Robot barrier-avoiding method based on laser radar | |
| CN106846870A (en) | The intelligent parking system and method for the parking lot vehicle collaboration based on centralized vision | |
| CN110316182A (en) | A kind of automated parking system and method | |
| CN110562248B (en) | Automatic parking system and automatic parking method based on unmanned aerial vehicle | |
| CN110126820A (en) | Automated parking system, method of parking and vehicle | |
| CN102729902A (en) | Embedded panoramic display device and method served for automobile safe driving | |
| CN202686138U (en) | Embedded panoramic display device for realizing automobile safe driving | |
| Wen et al. | On the road with gpt-4v (ision): Early explorations of visual-language model on autonomous driving | |
| JP2001101566A (en) | Traffic safety confirming system | |
| CN113085896B (en) | Auxiliary automatic driving system and method for modern rail cleaning vehicle | |
| CN109094556A (en) | A kind of automatic parking method and system based on parking stall characteristic point | |
| EP3757866A1 (en) | Harbor area monitoring method and system, and central control system | |
| CN105015418B (en) | Vehicle-carrying display screen video switching method | |
| CN103398710A (en) | Navigation system for entering and leaving port of ships and warships under night-fog weather situation and construction method thereof | |
| CN108830264A (en) | A kind of the platform occupant detection system and method for unmanned bus | |
| CN109739243A (en) | A kind of vehicle positioning method, automatic Pilot control method and related system | |
| US20220319192A1 (en) | Driving assistance device, driving assistance method, and non-transitory computer-readable medium | |
| CN109624854A (en) | A kind of 360 ° of panoramas auxiliary visible system suitable for special vehicle |
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: 20190528 |