CN105957393A - Parking space identification method and device - Google Patents
Parking space identification method and device Download PDFInfo
- Publication number
- CN105957393A CN105957393A CN201610282333.7A CN201610282333A CN105957393A CN 105957393 A CN105957393 A CN 105957393A CN 201610282333 A CN201610282333 A CN 201610282333A CN 105957393 A CN105957393 A CN 105957393A
- Authority
- CN
- China
- Prior art keywords
- road
- streetscape
- point
- streetscape point
- basis
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
- G08G1/145—Traffic control systems for road vehicles indicating individual free spaces in parking areas where the indication depends on the parking areas
- G08G1/147—Traffic control systems for road vehicles indicating individual free spaces in parking areas where the indication depends on the parking areas where the parking area is within an open public zone, e.g. city centre
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
Abstract
The embodiments of the invention disclose a parking space identification method and device. The method comprises the steps of: according to obtained street scenery points, driving directions at the street scenery points and a set matching rule, carrying out matching between the street scenery points and roads included in a basic road network, and determining the roads associated with the street scenery points in the basic road network; and according to street scenery pictures at the street scenery points, identifying whether sparking spaces exist at two sides of the roads associated with the street scenery points. According to the technical scheme, the parking spaces at two sides of the roads associated with the street scenery points are determined by the identification of parking spaces at two sides of the roads in the street scenery pictures, and compared with the prior art, the manual work for sparking space coordinate information determination is avoided, and the identification efficiency of the parking spaces is improved.
Description
Technical field
The present invention relates to electronic map technique field, particularly relate to recognition methods and the device on a kind of parking stall.
Background technology
In the user of electronic chart, the user that drives occupies sizable part.This type of user is for parking stall
Information compare concern.Therefore, in order to attract user, in electronic chart, labelling parking space information is the heaviest
Want.
At present, mainly by manually determining that the coordinate information on parking stall carries out parking stall identification, cause stopping
The recognition efficiency of position is relatively low so that only comprise large parking lot and Large Underground Parking Space etc. in electronic chart at present
Large-scale parking space number evidence, and the parking space number evidence of road both sides cannot be gathered.
Summary of the invention
In view of this, the embodiment of the present invention provides recognition methods and the device on a kind of parking stall, to improve parking
The recognition efficiency of position.
First aspect, embodiments provides the recognition methods on a kind of parking stall, including:
According to the direction of traffic at the streetscape point obtained, described streetscape point and the matched rule of setting, by described
Streetscape point mates with the road comprised in the road network of basis, determines that described streetscape point is in the road network of described basis
The road of association；
According to the Streetscape picture at described streetscape point, identify whether the road both sides that described streetscape point associates exist
Parking stall.
Second aspect, embodiments provides the identification device on a kind of parking stall, including:
Streetscape Point matching module, is used for the direction of traffic at according to the streetscape point obtained, described streetscape point and sets
Fixed matched rule, mates described streetscape point with the road comprised in the road network of basis, determines described street
Sight spot is the road of association in the road network of described basis；
Parking stall identification module, for according to the Streetscape picture at described streetscape point, identifies that described streetscape point closes
Whether the road both sides of connection exist parking stall.
The technical scheme that the embodiment of the present invention provides, according to the direction of traffic at streetscape point, streetscape point and coupling
Rule, determines streetscape point road of association in the road network of basis, identifies subsequently in the Streetscape picture at streetscape point
Whether road both sides exist parking stall, if having, it is determined that the road both sides of streetscape point association exist parking stall,
That is, the method is by identifying that in Streetscape picture, the parking stall of road both sides determines the road two that streetscape point associates
The parking stall of side, avoids the coordinate information manually determining parking stall, improves parking compared to prior art
The recognition efficiency of position.
Accompanying drawing explanation
Fig. 1 a is the flow chart of the recognition methods on a kind of parking stall that the embodiment of the present invention one provides；
Fig. 1 b is the schematic diagram of a kind of Radix Rumicis Streetscape picture that the embodiment of the present invention one provides；
Fig. 1 c is the schematic diagram of a kind of sphere Streetscape picture that the embodiment of the present invention one provides；
Fig. 1 d is the schematic diagram of a kind of lay-by that the embodiment of the present invention one improves；
Fig. 2 a is the flow chart of the recognition methods on a kind of parking stall that the embodiment of the present invention two provides；
Fig. 2 b is the schematic diagram of a kind of streetscape point that the embodiment of the present invention two provides；
Fig. 2 c is the schematic diagram of a kind of sampled point that the embodiment of the present invention two provides；
Fig. 3 is the structure chart identifying device on a kind of parking stall that the embodiment of the present invention three provides.
Detailed description of the invention
The present invention is described in further detail with embodiment below in conjunction with the accompanying drawings.It is understood that this
Specific embodiment described by place is used only for explaining the present invention, rather than limitation of the invention.The most also need
It is noted that for the ease of describing, accompanying drawing illustrate only part related to the present invention and not all knot
Structure.
Embodiment one
Fig. 1 a is the flow chart of the recognition methods on a kind of parking stall that the embodiment of the present invention one provides.The present embodiment
Method can be performed by the identification device on parking stall, this device can be real by the way of hardware and/or software
Existing, and typically can be integrated in map application server, and the method for the present embodiment is generally applicable to mark
The situation of road in electronic map both sides parking space information.See Fig. 1 a, the parking stall that the present embodiment provides
Recognition methods specifically includes as follows:
Direction of traffic at S11, the streetscape point of foundation acquisition, described streetscape point and the matched rule of setting, will
Described streetscape point mates with the road comprised in the road network of basis, determines that described streetscape point is on described basis road
The road of association in net.
In the present embodiment, streetscape point refers to the streetscape of the streetscape collecting device being arranged in streetscape collecting vehicle
The coordinate of collection point, the direction of traffic at streetscape point refers to the direction of traffic of streetscape collecting vehicle at streetscape point.
Matched rule is based on what the certainty of measurement of streetscape collecting device determined, basis road network comprise road shape and
Annexation between road.
Concrete, the distance of the road comprised in streetscape point and basis road network can be calculated, calculate at streetscape point
Direction of traffic and basis road network in the differential seat angle of road that comprises, determine according to the matched rule set subsequently
The distance of streetscape point association and the coupling weight of differential seat angle, and then determine streetscape point and basis based on coupling weight
The initial matching degree of the road comprised in road network, and determine that streetscape point is in the road network of basis according to initial matching degree
The road of association.Wherein, the coupling weight of distance can be with the certainty of measurement positive correlation of streetscape point coordinates, angle
The coupling weight of degree can be with the certainty of measurement negative correlation of streetscape point coordinates.
Before carrying out streetscape Point matching operation, it is also possible to include using spatial index algorithm, from basis road network
In filter out the road network that streetscape point may map, obtain the screening road network after range shorter, thus only by streetscape
Point mates with the road comprised in screening road network, and without the road that will comprise in streetscape point and basis road network
Road is all mated, and reduces the number of times of the path adaptation operation of streetscape point, improves streetscape point and basis road
Matching efficiency between the road comprised in net.
It should be noted that the path adaptation mode to streetscape point is not especially limited in the present embodiment.Such as,
Streetscape point can also be carried out projection matching, if the projection of streetscape point falls based on the road comprised in the road network of basis
On a road in office, then show the road that this road is the association of streetscape point；Appoint if the projection of streetscape point does not falls within
On one road, then combine the direction of traffic at streetscape point and the matched rule of setting, from the projection with streetscape point
Road in the range of certain distance selects the road of streetscape point association.
S12, according to the Streetscape picture at described streetscape point, identify road both sides that described streetscape point associates are whether
There is parking stall.
As shown in Figure 1 b, the Streetscape picture at streetscape point refers to Radix Rumicis streetscape collecting device and adopts at streetscape point
The Radix Rumicis Streetscape picture that collection arrives, wherein Radix Rumicis streetscape collecting device can be 360 ° of full-view cameras.Concrete,
The road arranged on left and right sides that in Streetscape picture, streetscape collecting vehicle is travelled can be identified by manual work mode
Whether roadside exists parking stall.Preferably, Streetscape picture is projected on sphere, obtain sphere Streetscape picture
(with reference to Fig. 1 c), then use image recognition technology, in identification sphere Streetscape picture, whether the roadside, both sides of road
There is curb parking, compared to the parking stall by the road both sides in artificial cognition Streetscape picture, decrease
Artificial workload, improves parking stall recognition efficiency.
Subsequently, according to the Streetscape picture at described streetscape point, identify that the road both sides that described streetscape point associates are
No there is parking stall, including: if left side and/or the right side of road exist in the Streetscape picture at described streetscape point
Parking stall, it is determined that left side and/or the right side of the road of streetscape point association exist parking stall；Otherwise, it determines street
There is not parking stall in left side and/or the right side of the road of sight spot association.
The technical scheme that the present embodiment provides, according to the direction of traffic at streetscape point, streetscape point and matched rule,
Determine streetscape point road of association in the road network of basis, identify road two in the Streetscape picture at streetscape point subsequently
Whether side exists parking stall, if having, it is determined that the road both sides of streetscape point association exist parking stall, i.e. should
By identifying the parking stall of road both sides in Streetscape picture, road both sides that method can determine that streetscape point associates
Parking stall, avoids the coordinate information manually determining parking stall, improves parking stall compared to prior art
Recognition efficiency.
Exemplary, determining that described streetscape point after the road of association, identifies institute in the road network of described basis
State streetscape point association road both sides whether there is parking stall before, it is also possible to including: along described basis road
The road comprised in net, the streetscape associating described road clicks on row filter.
Concrete, after determining the mapping relations between the road comprised in streetscape point and basis road network, according to road
Road grade and the road distance of setting, click on row filter to the streetscape of road association, such as, from basis road network
In every road comprising, length retains a streetscape point at a certain distance, rejects unnecessary streetscape point, with
The parking stall, road both sides reducing follow-up streetscape point association identifies workload, and makes the streetscape point on road equal
Even distribution.Wherein category of roads is different, and the distance length that road is corresponding is different, and the scope of distance length is permissible
For 20m-50m.
Exemplary, according to the Streetscape picture at described streetscape point, identify the road two that described streetscape point associates
After whether side exists parking stall, it is also possible to including: continuous print parking stall, linking-up road both sides, formed and stop
Band.
Concrete, after determining the parking space information of the road left and right sides, by continuous print streetscape point left and/or right side
Have and/or data without parking stall are connected, thus discrete road arranged on left and right sides parking space information is become
Both sides, road continuous print lay-by (dotted portion with reference in Fig. 1 d), compared in prior art with stop
For unit build parking space number evidence, it is possible to for user apparent provide road both sides parking space information,
Improve the satisfaction of Consumer's Experience further.
Embodiment two
The present embodiment provides the recognition methods on a kind of new parking stall on the basis of above-described embodiment one.Figure
2a is the flow chart of the recognition methods on a kind of parking stall that the embodiment of the present invention two provides.See Fig. 2 a, this reality
The recognition methods executing the parking stall that example provides specifically includes as follows:
Direction of traffic at S21, the streetscape point of foundation acquisition, described streetscape point and the matched rule of setting, meter
Calculate the initial matching degree of the road comprised in described streetscape point and described basis road network, and according to described initial
Degree of joining determines described streetscape point road of association in the road network of described basis.
Concrete, as shown in Figure 2 b, as a example by the arbitrary streetscape point α obtained, use spatial index algorithm,
From the road network of basis, filter out the road network that streetscape point α may map, obtain the screening road network after range shorter,
Wherein screening road network is the crossroad that road A, B, C and D are constituted.
Subsequently, the distance between the road comprised in streetscape point and screening road network, and the row at streetscape point are calculated
Car direction and the differential seat angle of road, according to calculated distance and differential seat angle and true according to matched rule
The coupling weight of fixed distance and differential seat angle, calculates streetscape point and screen the road comprised in road network initial
Degree of joining.And it is possible to the road maximum with the initial matching degree of streetscape point is defined as streetscape point on screening road
In net, the road of association, i.e. obtains the preliminary path adaptation result of streetscape point.
S22, according to the road that comprises and described initial matching degree in described streetscape point, described basis road network, right
The crossing streetscape comprised in region, wheelpath crossing clicks on line displacement and processes, and obtains offseting streetscape point.
In the present embodiment, wheelpath can determine according to streetscape point, and region, wheelpath crossing refers to
The region at place, mark cross point, streetscape point in crossing refers to the streetscape point in region, wheelpath crossing.Due to
The coordinate collection of streetscape point is inevitably present error, causes the road of the streetscape point association determined in S21
There may be error, the especially road of crossing streetscape point association there may be bigger error.In order to reduce this
Error, can determine streetscape point phase according to the road comprised in streetscape point, basis road network and initial matching degree
Ratio is in the side-play amount of basis road network, and based on side-play amount, crossing streetscape is clicked on line displacement process, is offset
Streetscape point, thus improve the follow-up crossing streetscape point association in the road network of basis determined based on skew streetscape point
The accuracy of road.
Concrete, S22 may include that
A, according to the road that comprises and described initial matching degree in described streetscape point, described basis road network, determine
Described streetscape point and the offset vector of described basis road network.
With reference to Fig. 2 b, exemplary, according to the road comprised in described streetscape point, described basis road network and institute
State initial matching degree, determine the offset vector of described streetscape point and described basis road network, may include that foundation
Described streetscape point-rendering wheelpath, determines wheelpath cross point β；According to described wheelpath cross point
The initial matching degree of the road comprised in β and described basis road network, the road comprised from the road network of described basis
Cross point determines the lane departure point γ that described wheelpath cross point associates；To be handed over by described wheelpath
Crunode β points to the vector of described lane departure point γ, is defined as the inclined of described streetscape point and described basic road network
Move vector.It should be noted that wheelpath cross point can not be streetscape point.
If handing over also, it should be noted basis road network exists the multiple roads associated with wheelpath cross point
Crunode, then according to initial matching degree, select the road of wheelpath cross point association from multiple road junctions
Road offset point, as being defined as the association of wheelpath cross point by the road junction that initial matching degree is maximum
Lane departure point.
B, according to described offset vector, the crossing streetscape comprised in region, wheelpath crossing is clicked on line displacement
Process, obtain offseting streetscape point.
S23, according to the direction of traffic at described skew streetscape point, described skew streetscape point and described matched rule,
Revise crossing streetscape point road of association in the road network of described basis.
Concrete, calculate the distance of the road comprised in skew streetscape point and basis road network, and calculate skew street
The differential seat angle of the road comprised in the direction of traffic at sight spot and basis road network, according to skew streetscape point association
Distance and differential seat angle, and matched rule, tie the preliminary path adaptation of the crossing streetscape point determined in S22
Fruit is modified, and obtains the road of revised crossing streetscape point association.
S24, according to the Streetscape picture at described streetscape point, identify road both sides that described streetscape point associates are whether
There is parking stall.
Exemplary, determining that described streetscape point after the road of association, identifies institute in the road network of described basis
State streetscape point association road both sides whether there is parking stall before, it is also possible to including: along described basis road
The road comprised in net, the streetscape associating described road clicks on row filter.Concrete, determine that streetscape point closes
After the road of connection, along every road according to certain distance length, extraction streetscape point is as sampled point (ginseng
Examine Fig. 2 c), the spacing distance of sampled point is the shortest, and follow-up parking stall data precision is the highest, but parking space number evidence
Procurement cost the highest, preferably control same link grade road on collection point uniform.
The technical scheme that the present embodiment provides, by according to the direction of traffic at streetscape point, streetscape point and coupling
Rule, primarily determines that streetscape point road of association in the road network of basis, true according to streetscape point and initial matching degree
Determine the offset vector of streetscape point, and based on offset vector, crossing streetscape is clicked on line displacement process, offset
Streetscape point, and by skew streetscape point road of association in the road network of basis, revise crossing streetscape point on basis road
The road of association in net, improves the accuracy of the road of crossing streetscape point association, so improve follow-up really
Whether the road both sides of fixed crossing streetscape point association exist the accuracy on parking stall, i.e. compared to existing skill
Art not only increases parking stall recognition efficiency, also improves the accuracy that parking stall identifies.
Exemplary, region, described wheelpath crossing is based on what described offset vector determined.Such as, may be used
By will be centered by wheelpath cross point, radius be that the default value times region of offset vector mould length is defined as
Region, wheelpath crossing.Default value is not especially limited by the present embodiment, if default value can be 1.5.
Exemplary, according to the direction of traffic at described skew streetscape point, described skew streetscape point and described
Join rule, revise crossing streetscape point road of association in the road network of described basis, may include that according to described
Direction of traffic at skew streetscape point, described skew streetscape point and described matched rule, determine described skew street
Skew matching degree between the road comprised in sight spot and described basis road network；According to described skew matching degree,
Revise described crossing streetscape point road of association in the road network of described basis.
Concrete, calculate skew streetscape point to the distance between the road comprised in the road network of basis, and calculate
Offset the differential seat angle of the road comprised in the direction of traffic at streetscape point and basis road network, advise according to coupling subsequently
Then, offset distance corresponding to streetscape point and differential seat angle, determine the road comprised in skew streetscape point and basis road network
Skew matching degree between road, as the skew between the road comprised in crossing streetscape point and basis road network
Degree of joining, and preliminary path adaptation result based on skew matching degree correction crossing streetscape point, after being revised
Crossing streetscape point described basis road network in association road.
Exemplary, according to the coupling rule of the direction of traffic at the streetscape point obtained, described streetscape point and setting
Then, calculate the initial matching degree of the road comprised in described streetscape point and described basis road network, may include that
Calculate the distance between the road comprised in the streetscape point obtained and basis road network；
Calculate the differential seat angle between the road comprised in the direction of traffic at streetscape point and described basis road network；
According to the matched rule of distance, differential seat angle and the setting of the association of described streetscape point, determine described streetscape point
Initial matching degree with the road comprised in the road network of described basis.
Embodiment three
Fig. 3 is the structure chart identifying device on a kind of parking stall that the embodiment of the present invention three provides.This device one
As can be integrated in map application server, and the device of the present embodiment be generally applicable to identify electronic chart
The situation of middle road both sides parking space information.See Fig. 3, the identification device on the parking stall that the present embodiment provides
Concrete structure is as follows:
Streetscape Point matching module 31, for according to the streetscape point obtained, direction of traffic at described streetscape point and
The matched rule set, mates described streetscape point with the road comprised in the road network of basis, determines described
Streetscape point is the road of association in the road network of described basis；
Parking stall identification module 32, for according to the Streetscape picture at described streetscape point, identifies described streetscape point
Whether the road both sides of association exist parking stall.
Exemplary, streetscape Point matching module 31 may include that
Initial matching degree computing unit, for according to the direction of traffic at the streetscape point obtained, described streetscape point
With the matched rule set, calculate the initial matching of the road comprised in described streetscape point and described basis road network
Degree；
According to described initial matching degree, initial road matching unit, for determining that described streetscape point is on described basis
The road of association in road network；
Skew streetscape point determines unit, for according to the road comprised in described streetscape point, described basis road network
With described initial matching degree, the crossing streetscape comprised is clicked on line displacement process in region, wheelpath crossing,
Obtain offseting streetscape point；
Road amending unit, for according to the direction of traffic at described skew streetscape point, described skew streetscape point
With described matched rule, revise crossing streetscape point road of association in the road network of described basis.
Exemplary, skew streetscape point determines that unit may include that
Offset vector determines subelement, for according to the road comprised in described streetscape point, described basis road network
With described initial matching degree, determine the offset vector of described streetscape point and described basis road network；
Skew streetscape point determines subelement, for according to described offset vector, in region, wheelpath crossing
The crossing streetscape comprised clicks on line displacement and processes, and obtains offseting streetscape point.
Exemplary, offset vector determines that subelement specifically may be used for:
According to described streetscape point-rendering wheelpath, determine wheelpath cross point；
According to the initial matching degree of road comprised in described wheelpath cross point and described basis road network, from
The road junction comprised in the road network of described basis determines the lane departure that described wheelpath cross point associates
Point；
By being pointed to the vector of described lane departure point by described wheelpath cross point, it is defined as described streetscape point
Offset vector with described basis road network.
Exemplary, region, described wheelpath crossing is based on what described offset vector determined.
Exemplary, road amending unit may include that
Skew matching degree subelement, for according to the driving at described skew streetscape point, described skew streetscape point
Direction and described matched rule, determine between the road comprised in described skew streetscape point and described basis road network
Skew matching degree；
Road correction subelement, for according to described skew matching degree, revises described crossing streetscape point described
The road of association in the road network of basis.
Exemplary, this device can also include:
Streetscape point screening module, for determine described streetscape point described basis road network in association road it
After, before identifying whether the road both sides that described streetscape point associates exist parking stall, along described basis road network
In the road that comprises, the streetscape associating described road clicks on row filter.
Exemplary, this device can also include:
Lay-by forms module, for according to the Streetscape picture at described streetscape point, identifies that described streetscape point closes
After whether the road both sides of connection exist parking stall, continuous print parking stall, linking-up road both sides, form lay-by.
Exemplary, initial matching degree computing unit may include that
Distance computation subunit, between the road comprised in the streetscape point calculating acquisition and basis road network
Distance；
Differential seat angle computation subunit, comprises in the road network of described basis for calculating the direction of traffic at streetscape point
Road between differential seat angle；
Initial matching degree computation subunit, for distance, differential seat angle and setting according to the association of described streetscape point
Matched rule, determine the initial matching degree of road comprised in described streetscape point and described basis road network.
The identification device on the parking stall that the present embodiment provides, the parking stall provided with any embodiment of the present invention
Recognition methods belong to same inventive concept, the knowledge on the parking stall that any embodiment of the present invention is provided can be performed
Other method, possesses the corresponding functional module of recognition methods and the beneficial effect performing parking stall.Not in this enforcement
The ins and outs of detailed description in example, can be found in the recognition methods on the parking stall that any embodiment of the present invention provides.
Note, above are only presently preferred embodiments of the present invention and institute's application technology principle.Those skilled in the art
It will be appreciated that the invention is not restricted to specific embodiment described here, can enter for a person skilled in the art
Row various obvious changes, readjust and substitute without departing from protection scope of the present invention.Therefore, though
So by above example, the present invention is described in further detail, but the present invention be not limited only to
Upper embodiment, without departing from the inventive concept, it is also possible to include other Equivalent embodiments more,
And the scope of the present invention is determined by scope of the appended claims.
Claims (18)
1. the recognition methods on a parking stall, it is characterised in that including:
According to the direction of traffic at the streetscape point obtained, described streetscape point and the matched rule of setting, by described
Streetscape point mates with the road comprised in the road network of basis, determines that described streetscape point is in the road network of described basis
The road of association；
According to the Streetscape picture at described streetscape point, identify whether the road both sides that described streetscape point associates exist
Parking stall.
Method the most according to claim 1, it is characterised in that according to the streetscape point obtained, described street
Direction of traffic at sight spot and the matched rule of setting, the road that will comprise in described streetscape point and basis road network
Mate, determine described streetscape point road of association in the road network of described basis, including:
According to the direction of traffic at the streetscape point obtained, described streetscape point and the matched rule of setting, calculate institute
State the initial matching degree of the road comprised in streetscape point and described basis road network, and according to described initial matching degree
Determine described streetscape point road of association in the road network of described basis；
According to the road comprised in described streetscape point, described basis road network and described initial matching degree, to driving
The crossing streetscape comprised in region, track crossing clicks on line displacement and processes, and obtains offseting streetscape point；
According to the direction of traffic at described skew streetscape point, described skew streetscape point and described matched rule, repair
Positive crossing streetscape point is the road of association in the road network of described basis.
Method the most according to claim 2, it is characterised in that according to described streetscape point, described basis
The road comprised in road network and described initial matching degree, to the crossing streetscape comprised in region, wheelpath crossing
Click on line displacement to process, obtain offseting streetscape point, including:
According to the road comprised in described streetscape point, described basis road network and described initial matching degree, determine institute
State the offset vector of streetscape point and described basis road network；
According to described offset vector, the crossing streetscape comprised in region, wheelpath crossing is clicked at line displacement
Reason, obtains offseting streetscape point.
Method the most according to claim 3, it is characterised in that according to described streetscape point, described basis
The road comprised in road network and described initial matching degree, determine the skew of described streetscape point and described basis road network
Vector, including:
According to described streetscape point-rendering wheelpath, determine wheelpath cross point；
According to the initial matching degree of road comprised in described wheelpath cross point and described basis road network, from
The road junction comprised in the road network of described basis determines the lane departure that described wheelpath cross point associates
Point；
By being pointed to the vector of described lane departure point by described wheelpath cross point, it is defined as described streetscape point
Offset vector with described basis road network.
Method the most according to claim 3, it is characterised in that region, described wheelpath crossing is to depend on
Determine according to described offset vector.
Method the most according to claim 2, it is characterised in that according to described skew streetscape point, described
Direction of traffic at skew streetscape point and described matched rule, revise crossing streetscape point in the road network of described basis
The road of association, including:
According to the direction of traffic at described skew streetscape point, described skew streetscape point and described matched rule, really
Skew matching degree between the road comprised in fixed described skew streetscape point and described basis road network；
According to described skew matching degree, revise described crossing streetscape point road of association in the road network of described basis.
Method the most according to claim 1, it is characterised in that determining that described streetscape point is at described base
In plinth road network association road after, identify the road both sides that described streetscape point associates whether exist parking stall it
Before, also include:
The road comprised in the road network of described basis, the streetscape associating described road clicks on row filter.
Method the most according to claim 1, it is characterised in that according to the streetscape figure at described streetscape point
Sheet, after identifying whether the road both sides that described streetscape point associates exist parking stall, also includes:
Continuous print parking stall, linking-up road both sides, forms lay-by.
Method the most according to claim 2, it is characterised in that according to the streetscape point obtained, described street
Direction of traffic at sight spot and the matched rule of setting, calculate described streetscape point and comprise in the road network of described basis
The initial matching degree of road, including:
Calculate the distance between the road comprised in the streetscape point obtained and basis road network；
Calculate the differential seat angle between the road comprised in the direction of traffic at streetscape point and described basis road network；
According to the matched rule of distance, differential seat angle and the setting of the association of described streetscape point, determine described streetscape point
Initial matching degree with the road comprised in the road network of described basis.
10. the identification device on a parking stall, it is characterised in that including:
Streetscape Point matching module, is used for the direction of traffic at according to the streetscape point obtained, described streetscape point and sets
Fixed matched rule, mates described streetscape point with the road comprised in the road network of basis, determines described street
Sight spot is the road of association in the road network of described basis；
Parking stall identification module, for according to the Streetscape picture at described streetscape point, identifies that described streetscape point closes
Whether the road both sides of connection exist parking stall.
11. devices according to claim 10, it is characterised in that streetscape Point matching module includes:
Initial matching degree computing unit, for according to the direction of traffic at the streetscape point obtained, described streetscape point
With the matched rule set, calculate the initial matching of the road comprised in described streetscape point and described basis road network
Degree；
According to described initial matching degree, initial road matching unit, for determining that described streetscape point is on described basis
The road of association in road network；
Skew streetscape point determines unit, for according to the road comprised in described streetscape point, described basis road network
With described initial matching degree, the crossing streetscape comprised is clicked on line displacement process in region, wheelpath crossing,
Obtain offseting streetscape point；
Road amending unit, for according to the direction of traffic at described skew streetscape point, described skew streetscape point
With described matched rule, revise crossing streetscape point road of association in the road network of described basis.
12. devices according to claim 11, it is characterised in that skew streetscape point determines that unit includes:
Offset vector determines subelement, for according to the road comprised in described streetscape point, described basis road network
With described initial matching degree, determine the offset vector of described streetscape point and described basis road network；
Skew streetscape point determines subelement, for according to described offset vector, in region, wheelpath crossing
The crossing streetscape comprised clicks on line displacement and processes, and obtains offseting streetscape point.
13. devices according to claim 12, it is characterised in that offset vector determines that subelement is concrete
For:
According to described streetscape point-rendering wheelpath, determine wheelpath cross point；
According to the initial matching degree of road comprised in described wheelpath cross point and described basis road network, from
The road junction comprised in the road network of described basis determines the lane departure that described wheelpath cross point associates
Point；
By being pointed to the vector of described lane departure point by described wheelpath cross point, it is defined as described streetscape point
Offset vector with described basis road network.
14. devices according to claim 12, it is characterised in that region, described wheelpath crossing is
Determine according to described offset vector.
15. devices according to claim 11, it is characterised in that road amending unit includes:
Skew matching degree subelement, for according to the driving at described skew streetscape point, described skew streetscape point
Direction and described matched rule, determine between the road comprised in described skew streetscape point and described basis road network
Skew matching degree；
Road correction subelement, for according to described skew matching degree, revises described crossing streetscape point described
The road of association in the road network of basis.
16. devices according to claim 10, it is characterised in that also include:
Streetscape point screening module, for determine described streetscape point described basis road network in association road it
After, before identifying whether the road both sides that described streetscape point associates exist parking stall, along described basis road network
In the road that comprises, the streetscape associating described road clicks on row filter.
17. devices according to claim 10, it is characterised in that also include:
Lay-by forms module, for according to the Streetscape picture at described streetscape point, identifies that described streetscape point closes
After whether the road both sides of connection exist parking stall, continuous print parking stall, linking-up road both sides, form lay-by.
18. devices according to claim 11, it is characterised in that initial matching degree computing unit includes:
Distance computation subunit, between the road comprised in the streetscape point calculating acquisition and basis road network
Distance；
Differential seat angle computation subunit, comprises in the road network of described basis for calculating the direction of traffic at streetscape point
Road between differential seat angle；
Initial matching degree computation subunit, for distance, differential seat angle and setting according to the association of described streetscape point
Matched rule, determine the initial matching degree of road comprised in described streetscape point and described basis road network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610282333.7A CN105957393B (en) | 2016-04-29 | 2016-04-29 | A kind of recognition methods on parking stall and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610282333.7A CN105957393B (en) | 2016-04-29 | 2016-04-29 | A kind of recognition methods on parking stall and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105957393A true CN105957393A (en) | 2016-09-21 |
| CN105957393B CN105957393B (en) | 2019-11-12 |
Family
ID=56913421
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610282333.7A Active CN105957393B (en) | 2016-04-29 | 2016-04-29 | A kind of recognition methods on parking stall and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105957393B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106767854A (en) * | 2016-11-07 | 2017-05-31 | 纵目科技（上海）股份有限公司 | mobile device, garage map forming method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104376007A (en) * | 2013-08-14 | 2015-02-25 | 高德软件有限公司 | POI (point of interest) street view image displaying method and device |
| CN104916163A (en) * | 2015-06-29 | 2015-09-16 | 惠州华阳通用电子有限公司 | Parking space detection method |
| CN104933409A (en) * | 2015-06-12 | 2015-09-23 | 北京理工大学 | Parking space identification method based on point and line features of panoramic image |
| JP2016016681A (en) * | 2014-07-04 | 2016-02-01 | クラリオン株式会社 | Parking frame recognition device |
-
2016
- 2016-04-29 CN CN201610282333.7A patent/CN105957393B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104376007A (en) * | 2013-08-14 | 2015-02-25 | 高德软件有限公司 | POI (point of interest) street view image displaying method and device |
| JP2016016681A (en) * | 2014-07-04 | 2016-02-01 | クラリオン株式会社 | Parking frame recognition device |
| CN104933409A (en) * | 2015-06-12 | 2015-09-23 | 北京理工大学 | Parking space identification method based on point and line features of panoramic image |
| CN104916163A (en) * | 2015-06-29 | 2015-09-16 | 惠州华阳通用电子有限公司 | Parking space detection method |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106767854A (en) * | 2016-11-07 | 2017-05-31 | 纵目科技（上海）股份有限公司 | mobile device, garage map forming method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105957393B (en) | 2019-11-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210004017A1 (en) | Using high definition maps for generating synthetic sensor data for autonomous vehicles | |
| US20210004363A1 (en) | Updating high definition maps based on age of maps | |
| US11988518B2 (en) | Updating high definition maps based on lane closure and lane opening | |
| US11738770B2 (en) | Determination of lane connectivity at traffic intersections for high definition maps | |
| US20220121550A1 (en) | Autonomous Vehicle Testing Systems and Methods | |
| Autey et al. | Safety evaluation of right-turn smart channels using automated traffic conflict analysis | |
| CN110796714B (en) | Map construction method, device, terminal and computer readable storage medium | |
| JP5661782B2 (en) | Additional map generation, refinement and expansion using GPS trajectories | |
| WO2015051718A1 (en) | Dynamic track navigation method and cloud platform | |
| US20210229280A1 (en) | Positioning method and device, path determination method and device, robot and storage medium | |
| CN111174799A (en) | Map construction method and device, computer readable medium and terminal equipment | |
| WO2018126228A1 (en) | Sign and lane creation for high definition maps used for autonomous vehicles | |
| CN107228677A (en) | Driftage recognition methods and device | |
| CN111325788B (en) | Building height determination method based on street view picture | |
| CN113409459B (en) | Method, device and equipment for producing high-precision map and computer storage medium | |
| CN110379168A (en) | A kind of vehicular traffic information acquisition method based on Mask R-CNN | |
| WO2021036243A1 (en) | Method and apparatus for recognizing lane, and computing device | |
| CN114116927A (en) | Roundabout road identification method and device, electronic equipment and storage medium | |
| CN112446915A (en) | Picture-establishing method and device based on image group | |
| CN105865482A (en) | Map navigation method and apparatus | |
| CN105957393A (en) | Parking space identification method and device | |
| CN112833891A (en) | Road data and lane-level map data fusion method based on satellite film recognition | |
| CN112651991A (en) | Visual positioning method, device and computer system | |
| CN116148890A (en) | High-precision map lane planning method, system, electronic equipment and storage medium | |
| CN101533567B (en) | Method for identifying intersection between air traffic control area and airway section and device thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |