CN112733078A - Method and device for smoothly connecting multiple lines among multiple road segments of crowdsourced data - Google Patents

Method and device for smoothly connecting multiple lines among multiple road segments of crowdsourced data Download PDF

Info

Publication number
CN112733078A
CN112733078A CN202011594172.8A CN202011594172A CN112733078A CN 112733078 A CN112733078 A CN 112733078A CN 202011594172 A CN202011594172 A CN 202011594172A CN 112733078 A CN112733078 A CN 112733078A
Authority
CN
China
Prior art keywords
line
vector
point
point deviation
calculating
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
Application number
CN202011594172.8A
Other languages
Chinese (zh)
Other versions
CN112733078B (en
Inventor
朱紫威
秦峰
王军
尹玉成
罗跃军
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Heading Data Intelligence Co Ltd
Original Assignee
Heading Data Intelligence Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Heading Data Intelligence Co Ltd filed Critical Heading Data Intelligence Co Ltd
Priority to CN202011594172.8A priority Critical patent/CN112733078B/en
Publication of CN112733078A publication Critical patent/CN112733078A/en
Application granted granted Critical
Publication of CN112733078B publication Critical patent/CN112733078B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/17—Function evaluation by approximation methods, e.g. inter- or extrapolation, smoothing, least mean square method
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Mathematical Analysis (AREA)
  • Computational Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Algebra (AREA)
  • Databases & Information Systems (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Image Processing (AREA)

Abstract

The invention relates to a smooth connection method and a smooth connection device among multiple lines among multiple road segments of crowdsourced data, which are used for acquiring corresponding line segments L in two sections of front and back sections which are directly connected1And a line segment L2Calculating to obtain a line segment L1And a line segment L2Is fitted to the output line L0(ii) a Calculating a first point deviation vector
Figure DDA0002869448520000011
And tail point deviation vector
Figure DDA0002869448520000012
According to the initial point deviation vector
Figure DDA0002869448520000013
Tail point deviation vector
Figure DDA00028694485200000110
And the fitting output line L0Number of on-line points N0Calculating a first point deviation coefficient vector
Figure DDA0002869448520000014
And tail point deviation coefficient vector
Figure DDA0002869448520000015
According to the initial point deviation vector
Figure DDA0002869448520000016
Tail point deviation vector
Figure DDA0002869448520000017
First point deviation coefficient vector
Figure DDA0002869448520000018
And tail point deviation coefficient vector
Figure DDA0002869448520000019
Calculating a translation matrix; obtaining an output line L according to the translation of the translation matrixout(ii) a The same line in the two sections is smooth and continuous, and the precision of the result line in the two road segments is improved to a certain extent on the basis of smoothness.

Description

Method and device for smoothly connecting multiple lines among multiple road segments of crowdsourced data
Technical Field
The invention relates to the field of high-precision maps, in particular to a smooth connection method and device among multiple lines among multiple road segments of crowdsourcing data.
Background
When the crowd-sourced lane line data is used for fusing lane line acquisition data of urban roads, lane line classification in segments is required to be performed on the lane line data using divided roads and segments, the lines of the same type are fused, the fusion result lines between the segments are connected, and when the lines are directly connected, the situation that the connection positions of the segments and the lines which can be connected with the segments are not smooth and continuous still exists, so that a method for smoothing the direct connection is required.
Disclosure of Invention
The invention provides a smooth connection method and a smooth connection device among multiple lines among multiple road segments of crowdsourcing data, aiming at the technical problems in the prior art, and solving the problems in the prior art.
The technical scheme for solving the technical problems is as follows: a method for smooth inter-multi-lane connection between multi-lane segments of crowd-sourced data, comprising:
step 1, acquiring corresponding line segment L in front and back sections which are directly connected1And a line segment L2And calculating to obtain the line segment L1And a line segment L2Is fitted to the output line L0；
Step 2, calculating a first point deviation vector
Figure BDA0002869448500000011
And tail point deviation vector
Figure BDA0002869448500000012
Step 3, according to the initial point deviation vector
Figure BDA0002869448500000013
Tail point deviation vector
Figure BDA0002869448500000014
And the fitting output line L0Number of on-line points N0Calculating a first point deviation coefficient vector
Figure BDA0002869448500000015
And tail point deviation coefficient vector
Figure BDA0002869448500000016
Step 4, according to the initial point deviation vector
Figure BDA0002869448500000017
Tail point deviation vector
Figure BDA0002869448500000018
First point deviation coefficient vector
Figure BDA0002869448500000021
And tail point deviation coefficient vector
Figure BDA0002869448500000022
Calculating a translation matrix; obtaining an output line L according to the translation of the translation matrixout。
A smooth inter-lane connection apparatus between multipath segments for crowdsourcing data, comprising: the device comprises a fit line output module, a deviation vector calculation module, a deviation coefficient vector calculation module and a smooth line output module;
the fit line output module is used for acquiring the corresponding line segment L in the front and the rear sections which are directly connected1And a line segment L2And calculating to obtain the line segment L1And a line segment L2Is fitted to the output line L0；
The deviation vector calculation module is used for calculating a first point deviation vector
Figure BDA0002869448500000023
And tail point deviation vector
Figure BDA0002869448500000024
The deviation coefficient vector calculation module is used for calculating the deviation vector according to the initial point
Figure BDA0002869448500000025
Tail point deviation vector
Figure BDA0002869448500000026
And the fitting output line L0Number of on-line points N0Calculating a first point deviation coefficient vector
Figure BDA0002869448500000027
And tail point deviation coefficient vector
Figure BDA0002869448500000028
The smooth line output module is used for outputting the first point deviation vector
Figure BDA0002869448500000029
Tail point deviation vector
Figure BDA00028694485000000210
First point deviation coefficient vector
Figure BDA00028694485000000211
And tail point deviation coefficient vector
Figure BDA00028694485000000212
Calculating a translation matrix; obtaining an output line L according to the translation of the translation matrixout。
The invention has the beneficial effects that: using the result of direct connection as input, calculating a fitting line, and obtaining a deviation vector through the difference between an input line and the fitting line; and then, a deviation coefficient is obtained by using a linear interpolation or non-linear interpolation method, a translation matrix is obtained from the deviation vector and the deviation coefficient, translation is carried out through the translation matrix, and finally an output result line is obtained, so that the road segments are segmented, the road linear point classification is carried out on the segmented road segments, the segmentation is carried out, the segmentation is fused, and after the direct connection judgment is carried out between the segments, the same line in the two segments is smooth and continuous, and the precision of the result line in the two road segments is improved to a certain extent on the basis of smoothness.
On the basis of the technical scheme, the invention can be further improved as follows.
Further, the fitting output line L is obtained in the step 10The process comprises the following steps:
segment L of the line1And line segment L2The point set is used as input fusion input, an optimization problem is established by using an optimization fusion method of measuring data of the same lane line in crowdsourcing data road segments, modeling is carried out on each shape point data in the input point set, a minimization problem is solved to obtain an output line equation, and the initial point of output is L1Starting point of (2), ending point of outputIs the line segment L2And make the number of output points N0＝N1+N2Obtaining the fitting output line L0＝{Pi(xi,yi,zi,dxi,dyi,dzi|i＝1,2,…,N0)}；
Wherein, PiTo form an output line L0I is a point number, each line point PiAccording to the fitting output line L0The order of the above is from small to large, N1Is the line segment L1Number of points on the line, N2Is the line segment L2The number of the upper line points.
Further, the head point deviation vector and the tail point deviation vector in step 2 are:
translation vector
Figure BDA0002869448500000031
Wherein, Pi|i＝0Is the fitting output line L0The first point of (a) is that,
Figure BDA00028694485000000315
is the fitting output line L0Tail point of (D), Pj|j＝0Is the line segment L1The first point of (a) is that,
Figure BDA00028694485000000316
is the line segment L2The tail point of (1).
Further, in step 3, the initial point deviation coefficient vector
Figure BDA0002869448500000032
The tail point deviation coefficient vector is
Figure BDA0002869448500000033
In the formula (I), the compound is shown in the specification,
Figure BDA0002869448500000034
represents the vector
Figure BDA0002869448500000035
All elements are arranged in reverse order;
Figure BDA0002869448500000036
Figure BDA0002869448500000037
wherein n is2＝(N0-1)2,
Figure BDA0002869448500000038
Figure BDA0002869448500000039
The expression in line (s, e, n) is that s and e are uniformly contained from value s to e and n values are taken as n values to form a column vector in sequence.
Further, the translation matrix in the step 4
Figure BDA00028694485000000310
Wherein the content of the first and second substances,
Figure BDA00028694485000000311
is composed of
Figure BDA00028694485000000312
The transposed vector of (a) is,
Figure BDA00028694485000000313
is composed of
Figure BDA00028694485000000314
The transposed vector of (1).
Further, the step 4 comprises:
obtaining a position matrix P according to the translation matrix, and obtaining an output line L by translating according to the position matrix Pout＝{Po(xo,yo,zo,dxo,dyo,dzo)|o＝1,2,…,N0}；
Wherein the positionMatrix P is N in total0Row 3 and column, where the ith row element is the line point PiThree-dimensional coordinate position of (a); (x)o,yo,zo) The values of the three elements of the o-th row of the matrix P + S; performing center difference on the matrix P + S according to rows, and obtaining a matrix D (dx) by using a forward or backward difference method on the boundaryo,dyo,dzo) Is row o of the matrix D.
The beneficial effect of adopting the further scheme is that: the method takes the smoothness and the precision and the shape of the front and rear fused lines into consideration, avoids the loss of the smoothness or the precision and the shape caused by using a direct weighted average or a fitting smoothing method, and performs targeted level difference according to the difference between the fused line results of the front and rear segments, thereby further improving the overall precision.
Drawings
Fig. 1 is a flowchart of a method for smooth inter-multi-channel connection between multi-channel segments of crowdsourced data according to an embodiment of the present invention;
FIG. 2 is a block diagram illustrating an embodiment of a smooth connection apparatus for multiple channels between multiple channel segments for crowdsourcing data according to the present invention;
fig. 3 is a schematic physical structure diagram of an electronic device according to an embodiment of the present invention.
In the drawings, the components represented by the respective reference numerals are listed below:
101. the device comprises a fitting line output module 102, a deviation vector calculation module 103, a deviation coefficient vector calculation module 104, a smooth line output module 201, a processor 202, a communication interface 203, a memory 204 and a communication bus.
Detailed Description
The principles and features of this invention are described below in conjunction with the following drawings, which are set forth by way of illustration only and are not intended to limit the scope of the invention.
When the crowd-sourced lane line data is used for fusing lane line acquisition data of urban roads, road segments are divided for the roads, the lane line data of each road segment is classified and fused, the segments are connected with the fusion result line, and after the lines are directly connected, the situation that the connection positions of the segments are not smooth and continuous can still exist between the lines which can be connected with the segments, so that the embodiment of the invention provides a method for smoothing direct connection.
Fig. 1 is a flowchart illustrating a method for smoothly connecting multiple channels among multiple channel segments of crowdsourced data according to an embodiment of the present invention, as can be seen from fig. 1, the method includes:
step 1, acquiring corresponding line segment L in front and back sections which are directly connected1And a line segment L2Calculating to obtain a line segment L1And a line segment L2Is fitted to the output line L0。
L1＝{Pj(xj,yj,zj,dxj,dyj,dzj)|j＝0,1,…,N1},L2＝{Pk(xk,yk,zk,dxk,dyk,dzk)|k＝0,1,…,N2In which P isj,PkAre formed into line segments L1Or L2The six-dimensional point is called a line point in the embodiment of the invention, the tangent vector is approximated by the central difference of the point coordinates or directly calculated by using a curve equation, and the subscript j, k expresses the point sequence number and is arranged from small to large according to the line point sequence on the line.
Step 2, calculating a first point deviation vector
Figure BDA0002869448500000051
And tail point deviation vector
Figure BDA0002869448500000052
Step 3, according to the initial point deviation vector
Figure BDA0002869448500000053
Tail point deviation vector
Figure BDA0002869448500000054
And the fitting output line L0Number of on-line points N0Calculating a first point deviation coefficient vector
Figure BDA0002869448500000055
And tail point deviation coefficient vector
Figure BDA0002869448500000056
Step 4, according to the initial point deviation vector
Figure BDA0002869448500000057
Tail point deviation vector
Figure BDA0002869448500000058
First point deviation coefficient vector
Figure BDA0002869448500000059
And tail point deviation coefficient vector
Figure BDA00028694485000000510
Calculating a translation matrix; obtaining an output line L according to the translation of the translation matrixout。
The invention provides a smooth connection method among multiple lines among multiple channel segments of crowdsourcing data, which uses the result of direct connection as input, calculates a fit line, and obtains a deviation vector through the difference between an input line and the fit line; and then, a deviation coefficient is obtained by using a linear interpolation or non-linear interpolation method, a translation matrix is obtained from the deviation vector and the deviation coefficient, translation is carried out through the translation matrix, and finally an output result line is obtained, so that the road segments are segmented, the road linear point classification is carried out on the segmented road segments, the segmentation is carried out, the segmentation is fused, and after the direct connection judgment is carried out between the segments, the same line in the two segments is smooth and continuous, and the precision of the result line in the two road segments is improved to a certain extent on the basis of smoothness.
Example 1
Embodiment 1 of the present invention is an embodiment of a method for smoothly connecting multiple channels among multiple channel segments of crowdsourcing data, and as can be seen from fig. 1, the embodiment includes:
step 1, acquiring corresponding line segment L in front and back sections which are directly connected1And a line segment L2Calculating to obtain a line segment L1And a line segment L2Is fitted to the output line L0。
Preferably, a fitting output line L is obtained0The process comprises the following steps:
segment L1And line segment L2The point set is used as input fusion input, an optimization problem is established by using an optimization fusion method of measuring data of the same lane line in crowdsourcing data road segments, modeling is carried out on each shape point data in the input point set, a minimization problem is solved to obtain an output line equation, and the initial point of output is L1The starting point of (2) and the ending point of the output being a line segment L2And make the number of output points N0＝N1+N2To obtain a fitting output line L0＝{Pi(xi,yi,zi,dxi,dyi,dzi|i＝1,2,…,N0)}。
Wherein, PiTo form an output line L0I is a point number, each line point PiOn-line fitting output line L0The order of the above is from small to large, N1Is a line segment L1Number of points on the line, N2Is a line segment L2The number of the upper line points.
Step 2, calculating a first point deviation vector
Figure BDA0002869448500000061
And tail point deviation vector
Figure BDA0002869448500000062
Preferably, the head-to-tail deviation vector is: translation vector
Figure BDA0002869448500000063
Figure BDA0002869448500000064
Wherein, Pi|i＝0Output line L for fitting0The first point of (a) is that,
Figure BDA0002869448500000065
output line L for fitting0Tail point of (D), Pj|j＝0Is a line segment L1The first point of (a) is that,
Figure BDA0002869448500000066
is a line segment L2The tail point of (1). Vector quantity
Figure BDA0002869448500000067
And vector
Figure BDA0002869448500000068
Is a column vector.
Step 3, according to the initial point deviation vector
Figure BDA0002869448500000069
Tail point deviation vector
Figure BDA00028694485000000610
And the fitting output line L0Number of on-line points N0Calculating a first point deviation coefficient vector
Figure BDA00028694485000000611
And tail point deviation coefficient vector
Figure BDA00028694485000000612
Preferably, the first and second liquid crystal materials are,
Figure BDA00028694485000000613
the expression in line (s, e, n) is that s and e are uniformly contained from value s to e and n values are taken as n values to form a column vector in sequence.
Finally, the initial point deviation coefficient vector is obtained as
Figure BDA00028694485000000614
The tail point deviation coefficient vector is
Figure BDA00028694485000000615
In the formula (I), the compound is shown in the specification,
Figure BDA00028694485000000616
represents the vector
Figure BDA00028694485000000617
All elements are arranged in reverse order;
Figure BDA00028694485000000618
Figure BDA00028694485000000619
wherein n is2＝(N0-1)2,
Figure BDA00028694485000000620
Figure BDA00028694485000000621
Step 4, according to the initial point deviation vector
Figure BDA00028694485000000622
Tail point deviation vector
Figure BDA00028694485000000623
First point deviation coefficient vector
Figure BDA00028694485000000624
And tail point deviation coefficient vector
Figure BDA0002869448500000071
Calculating a translation matrix; obtaining an output line L according to the translation of the translation matrixout。
Preferably, the translation matrix
Figure BDA0002869448500000072
Wherein the content of the first and second substances,
Figure BDA0002869448500000073
is composed of
Figure BDA0002869448500000074
The transposed vector of (a) is,
Figure BDA0002869448500000075
is composed of
Figure BDA0002869448500000076
The transposed vector of (1).
Figure BDA0002869448500000077
And
Figure BDA0002869448500000078
is a vector of the columns and is,
Figure BDA0002869448500000079
and
Figure BDA00028694485000000710
is a vector of the rows and the columns,
Figure BDA00028694485000000711
and
Figure BDA00028694485000000712
the matrix multiplication is performed in such a way that,
Figure BDA00028694485000000713
and
Figure BDA00028694485000000714
and performing matrix multiplication, and adding the result matrixes obtained by the two matrix multiplications to obtain a translation matrix.
Preferably, the step 4 comprises: obtaining a position matrix P according to the translation matrix, and obtaining an output line L by translating according to the position matrix Pout＝{Po(xo,yo,zo,dxo,dyo,dzo)|o＝1,2,…,N0}。
Wherein the position matrix P has N0Row 3 and column, where the ith row element is the line point PiThree-dimensional coordinate position of (a); (x)o,yo,zo) The values of the three elements of the o-th row of the matrix P + S; performing center difference on the matrix P + S according to rows, and obtaining a matrix D (dx) by using a forward or backward difference method on the boundaryo,dyo,dzo) Row o of matrix D.
Example 2
Embodiment 2 of the present invention is an embodiment of a smooth connection device for multiple lines between multiple channel segments for crowdsourcing data according to the present invention, and as shown in fig. 2, is a block diagram of an embodiment of a smooth connection device for multiple lines between multiple channel segments for crowdsourcing data according to the present invention, as can be seen from fig. 2, the device includes: a fit line output module 101, a deviation vector calculation module 102, a deviation coefficient vector calculation module 103 and a smooth line output module 104.
A fit line output module 101 for obtaining the corresponding line segment L in the two directly connected front and back segments1And a line segment L2Calculating to obtain a line segment L1And a line segment L2Is fitted to the output line L0。
A deviation vector calculation module 102 for calculating a first point deviation vector
Figure BDA00028694485000000715
And tail point deviation vector
Figure BDA00028694485000000716
A deviation coefficient vector calculation module 103 for calculating a deviation vector according to the initial point
Figure BDA00028694485000000717
Tail point deviation vector
Figure BDA00028694485000000718
And fitting outputLine L0Number of on-line points N0Calculating a first point deviation coefficient vector
Figure BDA00028694485000000719
And tail point deviation coefficient vector
Figure BDA00028694485000000720
A smooth line output module 104 for outputting a vector according to the head point deviation
Figure BDA00028694485000000721
Tail point deviation vector
Figure BDA00028694485000000722
First point deviation coefficient vector
Figure BDA00028694485000000723
And tail point deviation coefficient vector
Figure BDA00028694485000000724
Calculating a translation matrix; obtaining an output line L according to the translation of the translation matrixout。
Fig. 3 is a schematic entity structure diagram of an electronic device according to an embodiment of the present invention, and as shown in fig. 3, the electronic device may include: the system comprises a processor 201, a communication interface 202, a memory 203 and a communication bus 204, wherein the processor 201, the communication interface 202 and the memory 203 are communicated with each other through the communication bus 204. The processor 201 may call a computer program stored on the memory 203 and executable on the processor 201 to perform the method for smooth connection between multiple channels among multiple channel segments of crowdsourced data provided by the above embodiments, for example, including: step 1, acquiring corresponding line segment L in front and back sections which are directly connected1And a line segment L2Calculating to obtain a line segment L1And a line segment L2Is fitted to the output line L0(ii) a Step 2, calculating a first point deviation vector
Figure BDA0002869448500000081
Deviation from tail point(Vector)
Figure BDA0002869448500000082
Step 3, according to the initial point deviation vector
Figure BDA0002869448500000083
Tail point deviation vector
Figure BDA0002869448500000084
And the fitting output line L0Number of on-line points N0Calculating a first point deviation coefficient vector
Figure BDA0002869448500000085
And tail point deviation coefficient vector
Figure BDA0002869448500000086
Step 4, according to the initial point deviation vector
Figure BDA0002869448500000087
Tail point deviation vector
Figure BDA0002869448500000088
First point deviation coefficient vector
Figure BDA0002869448500000089
And tail point deviation coefficient vector
Figure BDA00028694485000000810
Calculating a translation matrix; obtaining an output line L according to the translation of the translation matrixout。
An embodiment of the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program is implemented to, when executed by a processor, perform a method for smoothly connecting multiple channels among multiple channel segments of crowdsourcing data, where the method includes: step 1, acquiring corresponding line segment L in front and back sections which are directly connected1And a line segment L2Calculating to obtain a line segment L1And a line segment L2Is fitted to the output line L0(ii) a Step 2, calculate the headPoint deviation vector
Figure BDA00028694485000000811
And tail point deviation vector
Figure BDA00028694485000000812
Step 3, according to the initial point deviation vector
Figure BDA00028694485000000813
Tail point deviation vector
Figure BDA00028694485000000814
And the fitting output line L0Number of on-line points N0Calculating a first point deviation coefficient vector
Figure BDA00028694485000000815
And tail point deviation coefficient vector
Figure BDA00028694485000000816
Step 4, according to the initial point deviation vector
Figure BDA00028694485000000817
Tail point deviation vector
Figure BDA00028694485000000818
First point deviation coefficient vector
Figure BDA00028694485000000819
And tail point deviation coefficient vector
Figure BDA00028694485000000820
Calculating a translation matrix; obtaining an output line L according to the translation of the translation matrixout。
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.

Claims (9)

1. A method for smooth inter-lane connections between multipath segments of crowd-sourced data, the method comprising:
step 1, acquiring corresponding line segment L in front and back sections which are directly connected1And a line segment L2And calculating to obtain the line segment L1And a line segment L2Is fitted to the output line L0；
Step 2, calculating a first point deviation vector
Figure FDA0002869448490000011
And tail point deviation vector
Figure FDA0002869448490000012
Step 3, according to the initial point deviation vector
Figure FDA0002869448490000013
Tail point deviation vector
Figure FDA0002869448490000014
And the fitting output line L0Number of on-line points N0Calculating a first point deviation coefficient vector
Figure FDA0002869448490000015
And tail point deviation coefficient vector
Figure FDA0002869448490000016
Step 4, according to the initial point deviation vector
Figure FDA0002869448490000017
Tail point deviation vector
Figure FDA0002869448490000018
First point deviation coefficient vector
Figure FDA0002869448490000019
And tail point deviation coefficient vector
Figure FDA00028694484900000110
Calculating a translation matrix; obtaining an output line L according to the translation of the translation matrixout。
2. The method of claim 1 wherein said fitting output line L is obtained in step 10The process comprises the following steps:
segment L of the line1And line segment L2The point set is used as input fusion input, an optimization problem is established by using an optimization fusion method of measuring data of the same lane line in crowdsourcing data road segments, modeling is carried out on each shape point data in the input point set, a minimization problem is solved to obtain an output line equation, and the initial point of output is L1The end point of the output is made to be the line segment L2And make the number of output points N0＝N1+N2Obtaining the fitting output line L0＝{Pi(xi，yi，zi，dxi，dyi，dzi|i＝1，2，…，N0)}；
Wherein, PiTo form an output line L0I is a point number, each line point PiAccording to the fitting output line L0The order of the above is from small to large, N1Is the line segment L1Number of points on the line, N2Is the line segment L2The number of the upper line points.
3. The method of claim 1, wherein the head and tail bias vectors of step 2 are:
translation vector
Figure FDA00028694484900000111
Wherein, Pi|i＝0Is the fitting output line L0The first point of (a) is that,
Figure FDA00028694484900000112
is the fitting output line L0Tail point of (D), Pj|j＝0Is the line segment L1The first point of (a) is that,
Figure FDA0002869448490000021
is the line segment L2The tail point of (1).
4. The method of claim 3, wherein in step 3, the initial point bias coefficient vector
Figure FDA0002869448490000022
The tail point deviation coefficient vector is
Figure FDA0002869448490000023
In the formula (I), the compound is shown in the specification,
Figure FDA0002869448490000024
represents the vector
Figure FDA00028694484900000219
All elements are arranged in reverse order;
Figure FDA0002869448490000025
Figure FDA0002869448490000026
wherein the content of the first and second substances,
Figure FDA0002869448490000027
Figure FDA0002869448490000028
the expression in line (s, e, n) is that s and e are uniformly contained from value s to e and n values are taken as n values to form a column vector in sequence.
5. The method of claim 1, wherein the translation matrix in step 4
Figure FDA0002869448490000029
Wherein the content of the first and second substances,
Figure FDA00028694484900000210
is composed of
Figure FDA00028694484900000211
The transposed vector of (a) is,
Figure FDA00028694484900000212
is composed of
Figure FDA00028694484900000213
The transposed vector of (1).
6. The method of claim 1, wherein the step 4 comprises:
obtaining a position matrix P according to the translation matrix, and obtaining an output line L by translating according to the position matrix Pout＝{Po(xo，yo，zo，dxo，dyo，dzo)|o＝1，2，…，N0}；
Wherein the position matrix P is N in total0Row 3 and column, where the ith row element is the line point PiThree-dimensional coordinate position of (a); (x)o，yo，zo) The values of the three elements of the o-th row of the matrix P + S; performing center difference on the matrix P + S according to rows, and obtaining a matrix D (dx) by using a forward or backward difference method on the boundaryo，dyo，dzo) Is row o of the matrix D.
7. An apparatus for smoothly connecting between a plurality of lines between a plurality of road segments for crowdsourcing data, the apparatus comprising: the device comprises a fit line output module, a deviation vector calculation module, a deviation coefficient vector calculation module and a smooth line output module;
the fit line output module is used for acquiring the corresponding line segment L in the front and the rear sections which are directly connected1And a line segment L2And calculating to obtain the line segment L1And a line segment L2Is fitted to the output line L0；
The deviation vector calculation module is used for calculating a first point deviation vector
Figure FDA00028694484900000214
And tail point deviation vector
Figure FDA00028694484900000215
The deviation coefficient vector calculation module is used for calculating the deviation vector according to the initial point
Figure FDA00028694484900000216
Tail point deviation vector
Figure FDA00028694484900000217
And the fitting output line L0Number of on-line points N0Calculating a first point deviation coefficient vector
Figure FDA00028694484900000218
And tail point deviation coefficient vector
Figure FDA0002869448490000031
The smooth line output module is used for outputting the first point deviation vector
Figure FDA0002869448490000032
Tail point deviation vector
Figure FDA0002869448490000033
First point deviation coefficient vector
Figure FDA0002869448490000034
And tail point deviation coefficient vector
Figure FDA0002869448490000035
Calculating a translation matrix; obtaining an output line L according to the translation of the translation matrixout。
8. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements the steps of the method for smooth connection between multiple channels between multiple channel segments of crowdsourced data as recited in any one of claims 1 to 6.
9. A non-transitory computer readable storage medium, having stored thereon a computer program, which when executed by a processor, performs the steps of the method for smooth inter-multipath connection between multipath segments of crowd-sourced data as claimed in any one of claims 1 to 6.
CN202011594172.8A 2020-12-29 2020-12-29 Method and device for smooth connection among multiple paths of fragments of crowdsourcing data Active CN112733078B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011594172.8A CN112733078B (en) 2020-12-29 2020-12-29 Method and device for smooth connection among multiple paths of fragments of crowdsourcing data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011594172.8A CN112733078B (en) 2020-12-29 2020-12-29 Method and device for smooth connection among multiple paths of fragments of crowdsourcing data

Publications (2)

Publication Number Publication Date
CN112733078A true CN112733078A (en) 2021-04-30
CN112733078B CN112733078B (en) 2023-10-10

Family

ID=75607537

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011594172.8A Active CN112733078B (en) 2020-12-29 2020-12-29 Method and device for smooth connection among multiple paths of fragments of crowdsourcing data

Country Status (1)

Country Link
CN (1) CN112733078B (en)

Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105957342A (en) * 2016-05-30 2016-09-21 武汉大学 Lane-level road mapping method and system based on crowdsourcing space-time big data
US20190101610A1 (en) * 2017-09-29 2019-04-04 Siemens Healthcare Gmbh Phase deviation acquisition method and system, and phase calibration method and system
CN110414387A (en) * 2019-07-12 2019-11-05 武汉理工大学 A kind of lane line multi-task learning detection method based on lane segmentation
CN111209805A (en) * 2019-12-24 2020-05-29 武汉中海庭数据技术有限公司 Rapid fusion optimization method for multi-channel segment data of lane line crowdsourcing data
CN111222418A (en) * 2019-12-24 2020-06-02 武汉中海庭数据技术有限公司 Crowdsourcing data rapid fusion optimization method for multiple road segments of lane line
CN111222405A (en) * 2019-11-15 2020-06-02 北京邮电大学 Lane line detection method and device, electronic device and readable storage medium
CN111611958A (en) * 2020-05-28 2020-09-01 武汉四维图新科技有限公司 Method, device and equipment for determining lane line shape in crowdsourcing data
CN111696059A (en) * 2020-05-28 2020-09-22 武汉中海庭数据技术有限公司 Lane line smooth connection processing method and device
CN111708856A (en) * 2020-06-03 2020-09-25 武汉中海庭数据技术有限公司 Crowdsourcing data segmentation fusion method of lane line based on reinforcement learning
EP3739293A1 (en) * 2019-05-14 2020-11-18 HERE Global B.V. Method and apparatus for providing lane connectivity data for an intersection
CN112069280A (en) * 2020-09-04 2020-12-11 中国平安财产保险股份有限公司 Road data processing method, device, equipment and storage medium

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105957342A (en) * 2016-05-30 2016-09-21 武汉大学 Lane-level road mapping method and system based on crowdsourcing space-time big data
US20190101610A1 (en) * 2017-09-29 2019-04-04 Siemens Healthcare Gmbh Phase deviation acquisition method and system, and phase calibration method and system
EP3739293A1 (en) * 2019-05-14 2020-11-18 HERE Global B.V. Method and apparatus for providing lane connectivity data for an intersection
CN110414387A (en) * 2019-07-12 2019-11-05 武汉理工大学 A kind of lane line multi-task learning detection method based on lane segmentation
CN111222405A (en) * 2019-11-15 2020-06-02 北京邮电大学 Lane line detection method and device, electronic device and readable storage medium
CN111209805A (en) * 2019-12-24 2020-05-29 武汉中海庭数据技术有限公司 Rapid fusion optimization method for multi-channel segment data of lane line crowdsourcing data
CN111222418A (en) * 2019-12-24 2020-06-02 武汉中海庭数据技术有限公司 Crowdsourcing data rapid fusion optimization method for multiple road segments of lane line
CN111611958A (en) * 2020-05-28 2020-09-01 武汉四维图新科技有限公司 Method, device and equipment for determining lane line shape in crowdsourcing data
CN111696059A (en) * 2020-05-28 2020-09-22 武汉中海庭数据技术有限公司 Lane line smooth connection processing method and device
CN111708856A (en) * 2020-06-03 2020-09-25 武汉中海庭数据技术有限公司 Crowdsourcing data segmentation fusion method of lane line based on reinforcement learning
CN112069280A (en) * 2020-09-04 2020-12-11 中国平安财产保险股份有限公司 Road data processing method, device, equipment and storage medium

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
尤中桐;王太勇;刘清建;辛全琦;: "一种基于最小二乘法的离散点螺旋线式拟合算法", 中国机械工程, no. 20, pages 2502 - 2506 *
王东波;黄鹤;王欣宇;: "基于道路边线GPS原始数据的曲率评估方法", 北京测绘, no. 1, pages 44 - 48 *

Also Published As

Publication number Publication date
CN112733078B (en) 2023-10-10

Similar Documents

Publication Publication Date Title
CN109308459B (en) Gesture estimation method based on finger attention model and key point topology model
CN111179314A (en) Target tracking method based on residual dense twin network
CN110246181B (en) Anchor point-based attitude estimation model training method, attitude estimation method and system
CN107886477A (en) Unmanned neutral body vision merges antidote with low line beam laser radar
CN113822284B (en) RGBD image semantic segmentation method based on boundary attention
CN112560684B (en) Lane line detection method, lane line detection device, electronic equipment, storage medium and vehicle
CN103778598B (en) Disparity map ameliorative way and device
CN111860276B (en) Human body key point detection method, device, network equipment and storage medium
WO2021115061A1 (en) Image segmentation method and apparatus, and server
CN112907573B (en) Depth completion method based on 3D convolution
CN105654460A (en) Point cloud splicing system and method
CN110645996B (en) Method and system for extracting perception data
CN111009179B (en) Method and device for determining denudation thickness
Zhou et al. PADENet: An efficient and robust panoramic monocular depth estimation network for outdoor scenes
CN112733078A (en) Method and device for smoothly connecting multiple lines among multiple road segments of crowdsourced data
CN107730543B (en) Rapid iterative computation method for semi-dense stereo matching
CN117635444A (en) Depth completion method, device and equipment based on radiation difference and space distance
CN113505885A (en) Training method of monocular depth estimation network based on preset loss function
CN109816710B (en) Parallax calculation method for binocular vision system with high precision and no smear
US20210397953A1 (en) Deep neural network operation method and apparatus
WO2016026064A1 (en) A method and a system for estimating facial landmarks for face image
WO2020232666A1 (en) Image processing method, terminal, system, and computer readable storage medium
CN106651950B (en) Single-camera pose estimation method based on quadratic curve perspective projection invariance
WO2022017129A1 (en) Target object detection method and apparatus, electronic device, and storage medium
CN113112523B (en) Target tracking method and device based on anchor-free twin network

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant