CN112733078B - Method and device for smooth connection among multiple paths of fragments of crowdsourcing data - Google Patents
Method and device for smooth connection among multiple paths of fragments of crowdsourcing data Download PDFInfo
- Publication number
- CN112733078B CN112733078B CN202011594172.8A CN202011594172A CN112733078B CN 112733078 B CN112733078 B CN 112733078B CN 202011594172 A CN202011594172 A CN 202011594172A CN 112733078 B CN112733078 B CN 112733078B
- Authority
- CN
- China
- Prior art keywords
- line
- vector
- point
- output
- point deviation
- 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.)
- Active
Links
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)
- Pure & Applied Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Data Mining & Analysis (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 device between multiple lines of multi-path fragments of crowd-sourced data, which acquire corresponding line segments L in a front section and a rear section which are directly connected 1 And line segment L 2 Calculating to obtain a line segment L 1 And line segment L 2 Fitting output line L of (1) 0 The method comprises the steps of carrying out a first treatment on the surface of the Calculating a first-point deviation vectorAnd tail point deviation vectorAccording to the first-point deviation vectorTail point deviation vectorAnd fitting output line L 0 The number N of the upper line points 0 Calculating the first-point deviation coefficient vectorCoefficient vector of deviation from tail pointAccording to the first-point deviation vectorTail point deviation vectorFirst-point deviation coefficient vectorCoefficient vector of deviation from tail pointCalculating a translation matrix; obtaining an output line L according to translation of the translation matrix out The method comprises the steps of carrying out a first treatment on the surface of the 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 smooth basis.
Description
Technical Field
The invention relates to the field of high-precision maps, in particular to a method and a device for smoothly connecting 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 lines in the segments are required to be classified by using the lane line data of the divided roads and the segments, the similar lines are fused, fusion result lines between the segments are connected, and when the lines are directly connected, the condition that the connection part between the segments can be connected is not smooth and continuous is still likely to exist, so that a method for smoothing the direct connection is required.
Disclosure of Invention
Aiming at the technical problems in the prior art, the invention provides a smooth connection method and a device between multiple paths of fragments of crowdsourcing data, which solve the problems in the prior art.
The technical scheme for solving the technical problems is as follows: a method of smooth connection between multiple lines between multiple road segments of crowd-sourced data, comprising:
step 1, obtaining corresponding lines in a front section and a rear section which are directly connectedSegment L 1 And line segment L 2 Calculating to obtain the line segment L 1 And line segment L 2 Fitting output line L of (1) 0 ;
Step 2, calculating a head point deviation vectorAnd tail point deviation vector->
Step 3, according to the initial point deviation vectorTail point deviation vector->And the fitting output line L 0 The number N of the upper line points 0 Calculating the first-point deviation coefficient vector +.>And the tail point deviation coefficient vector->
Step 4, according to the initial point deviation vectorTail point deviation vector->First-point deviation coefficient vector->And the tail point deviation coefficient vector->Calculating a translation matrix; translating according to the translation matrix to obtain an output line L out 。
A smooth connection between multiple lines between multiple road segments of crowd-sourced data, comprising: the device comprises a fitting line output module, a deviation vector calculation module, a deviation coefficient vector calculation module and a smooth line output module;
the fitting line output module is used for obtaining the corresponding line segment L in the front and rear sections which are directly connected 1 And line segment L 2 Calculating to obtain the line segment L 1 And line segment L 2 Fitting output line L of (1) 0 ;
The deviation vector calculation module is used for calculating a head point deviation vectorAnd tail point deviation vector->
The deviation coefficient vector calculation module is used for calculating a deviation vector according to the initial pointTail point deviation vector->And the fitting output line L 0 The number N of the upper line points 0 Calculating the first-point deviation coefficient vector +.>And the tail point deviation coefficient vector->
The smooth line output module is used for outputting the initial point deviation vector according to the initial point deviation vectorTail point deviation vector->First-point deviation coefficient vector->And the tail point deviation coefficient vector->Calculating a translation matrix; translating according to the translation matrix to obtain an output line L out 。
The beneficial effects of the invention are as follows: using the direct connection result as input, calculating the fitting line, and obtaining a deviation vector through the difference between the input line and the fitting line; and obtaining a deviation coefficient by using a linear interpolation or nonlinear interpolation method, obtaining a translation matrix from the deviation vector and the deviation coefficient, translating through the translation matrix, and finally obtaining an output result line, so that the method realizes that after road segments are segmented, lane linear point classification is carried out on the segmented road segments, fusion is carried out on the segments, and after direct connection judgment is carried out between the segments, the same line in the two segments is smooth and continuous, and the accuracy of the result line in the two road segments is improved to a certain extent on the smooth basis.
On the basis of the technical scheme, the invention can be improved as follows.
Further, the fitting output line L is obtained in the step 1 0 The process of (1) comprises:
the line segment L 1 And line segment L 2 The method comprises the steps of taking a point set of an input fusion input, establishing an optimization problem by using an optimization fusion method of measurement data of the same lane line in a crowded data road segment, modeling each shape point data in the input point set, solving a minimization problem to obtain an output line equation, and enabling an output starting point to be L 1 Make the end point of the output be the line segment L 2 And make the number of output points N 0 =N 1 +N 2 Obtaining the fitting output line L 0 ={P i (x i ,y i ,z i ,dx i ,dy i ,dz i |i=1,2,…,N 0 )};
Wherein P is i To compose an output line L 0 I is the point number, each line point P i Is pressed on the fitting output line L 0 The sequence is arranged from small to large, N 1 For the line segment L 1 The number of the upper line points N 2 For the line segment L 2 The number of upper line points.
Further, in the step 2, the head point deviation vector and the tail point deviation vector are:
translation vector
Wherein P is i|i=0 For the fitting output line L 0 Is used for the first point of (a),for the fitting output line L 0 Tail point of P j|j=0 For the line segment L 1 Is the first point of->For the line segment L 2 Is a tail point of (c).
Further, in the step 3, a first-point deviation coefficient vectorThe tail point deviation coefficient vector is +.>
In the method, in the process of the invention,representing vectors +.>All elements are arranged in reverse order; />
Wherein n is 2 =(N 0 -1) 2 , The expression "line space (s, e, n)" means that the values s to e uniformly include s and e, and n values are sequentially formed into a column vector.
Further, the translation matrix in the step 4Wherein (1)>Is->Is used to determine the transposed vector of (c),is->Is a transposed vector of (a).
Further, the step 4 includes:
obtaining a position matrix P according to the translation matrix, and translating according to the position matrix P to obtain an output line L out ={P o (x o ,y o ,z o ,dx o ,dy o ,dz o )|o=1,2,…,N 0 };
Wherein the position matrix P is N in total 0 Row 3 column, where the i-th row element is line point P i Is defined by a three-dimensional coordinate position of (a); (x) o ,y o ,z o ) Values of three elements of the o-th row of the matrix p+s; the matrix P+S is differentiated according to the center of the row, the boundary uses forward or backward differential method to obtain matrix D, (dx) o ,dy o ,dz o ) Is thatThe o-th row of the matrix D.
The beneficial effects of adopting the further scheme are as follows: the method has the advantages that the smoothness and the precision and the shape of the front and rear fused lines are considered, the loss of the smoothness or the precision and the shape caused by using a direct weighted average or adopting a fitting smoothing method is avoided, and the targeted horizon is carried out through the difference between the front and rear fused line results, so that the overall precision is further improved.
Drawings
Fig. 1 is a flowchart of a method for smooth connection between multiple paths of fragments of crowd-sourced data according to an embodiment of the present invention;
FIG. 2 is a block diagram illustrating an embodiment of a smoothing connection apparatus between multiple fragments of crowd-sourced data according to the present invention;
fig. 3 is a schematic entity structure diagram of an electronic device according to an embodiment of the present invention.
In the drawings, the list of components represented by the various numbers is as follows:
101. fitting line output module 102, deviation vector calculation module 103, deviation coefficient vector calculation module 104, smooth line output module 201, processor 202, communication interface 203, memory 204 and communication bus.
Detailed Description
The principles and features of the present invention are described below with reference to the drawings, the examples are illustrated for the purpose of illustrating the invention and are not to be construed as limiting 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, lane line data are classified and fused for each road segment, fusion result lines between the segments are connected, and after the lines are directly connected, the situation that the connection positions are not smooth and continuous can still exist between the lines which can be connected between the segments is still caused.
Fig. 1 is a flowchart of a method for smoothing connection between multiple paths of fragments of crowd-sourced data according to an embodiment of the present invention, where fig. 1 shows that the method includes:
step 1, obtaining corresponding line segments L in a front section and a rear section which are directly connected 1 And line segment L 2 Calculating to obtain a line segment L 1 And line segment L 2 Fitting output line L of (1) 0 。
L 1 ={P j (x j ,y j ,z j ,dx j ,dy j ,dz j )|j=0,1,…,N 1 },L 2 ={P k (x k ,y k ,z k ,dx k ,dy k ,dz k )|k=0,1,…,N 2 }, wherein P j ,P k To form line segment L 1 Or L 2 The six-dimensional points are called line points in the embodiment of the invention, the tangent vector is calculated by the center difference approximation of the point coordinates or directly by using a curve equation, the subscripts j and k express the point serial numbers, and the line points are arranged from small to large according to the line-on-line point sequence.
Step 2, calculating a head point deviation vectorAnd tail point deviation vector->
Step 3, according to the initial point deviation vectorTail point deviation vector->And fitting output line L 0 The number N of the upper line points 0 Calculating the first-point deviation coefficient vector +.>And the tail point deviation coefficient vector->
Step 4, according to the initial point deviation vectorTail point deviation vector->First-point deviation coefficient vector->And the tail point deviation coefficient vector->Calculating a translation matrix; obtaining an output line L according to translation of the translation matrix out 。
The smooth connection method between the multiple paths of fragments of the crowdsourcing data uses the direct connection result as input, calculates the fitting line, and obtains the deviation vector through the difference between the input line and the fitting line; and obtaining a deviation coefficient by using a linear interpolation or nonlinear interpolation method, obtaining a translation matrix from the deviation vector and the deviation coefficient, translating through the translation matrix, and finally obtaining an output result line, so that the method realizes that after road segments are segmented, lane linear point classification is carried out on the segmented road segments, fusion is carried out on the segments, and after direct connection judgment is carried out between the segments, the same line in the two segments is smooth and continuous, and the accuracy of the result line in the two road segments is improved to a certain extent on the smooth basis.
Example 1
Embodiment 1 of the present invention provides an embodiment of a method for smoothing connection between multiple paths of fragments of crowd-sourced data, and as can be seen in fig. 1, the embodiment includes:
step 1, obtaining corresponding line segments L in a front section and a rear section which are directly connected 1 And line segment L 2 Calculating to obtain a line segment L 1 And line segment L 2 Fitting output line L of (1) 0 。
Preferably, a fitting output line L is obtained 0 The process of (1) comprises:
will segment L 1 And line segment L 2 The method comprises the steps of taking a point set of an input fusion input, establishing an optimization problem by using an optimization fusion method of measurement data of the same lane line in a crowded data road segment, modeling each shape point data in the input point set, solving a minimization problem to obtain an output line equation, and enabling an output starting point to be L 1 Make the end point of the output be line segment L 2 And make the number of output points N 0 =N 1 +N 2 Obtaining a fitting output line L 0 ={P i (x i ,y i ,z i ,dx i ,dy i ,dz i |i=1,2,…,N 0 )}。
Wherein P is i To compose an output line L 0 I is the point number, each line point P i Fitting output line L 0 The sequence is arranged from small to large, N 1 Is a line segment L 1 The number of the upper line points N 2 Is a line segment L 2 The number of upper line points.
Step 2, calculating a head point deviation vectorAnd tail point deviation vector->
Preferably, the head-to-tail point deviation vector is: translation vector
Wherein P is i|i=0 To fit an output line L 0 Is used for the first point of (a),to fit an output line L 0 Tail point of P j|j=0 Is a line segment L 1 Is the first point of->Is a line segment L 2 Is a tail point of (c). Vector->Vector->Is a column vector.
Step 3, according to the initial point deviation vectorTail point deviation vector->And fitting output line L 0 The number N of the upper line points 0 Calculating the first-point deviation coefficient vector +.>And the tail point deviation coefficient vector->
Preferably, the method comprises the steps of,the expression "line space (s, e, n)" means that the values s to e uniformly include s and e, and n values are sequentially formed into a column vector.
Finally, the first point deviation coefficient vector is obtained asThe tail point deviation coefficient vector is
In the method, in the process of the invention,representing vectors +.>All elements are arranged in reverse order; />
Wherein n is 2 =(N 0 -1) 2 ,
Step 4, according to the initial point deviation vectorTail point deviation vector->First-point deviation coefficient vector->And the tail point deviation coefficient vector->Calculating a translation matrix; obtaining an output line L according to translation of the translation matrix out 。
Preferably, the translation matrixWherein (1)>Is->Is the transposed vector of>Is->Is a transposed vector of (a).
And->For column vector, +.>And->For row vector +.>And->Perform matrix multiplication +.>And->And performing matrix multiplication, and adding the result matrixes obtained by the two matrix multiplication to obtain a translation matrix.
Preferably, the step 4 includes: obtaining a position matrix P according to the translation matrix, and translating according to the position matrix P to obtain an output line L out ={P o (x o ,y o ,z o ,dx o ,dy o ,dz o )|o=1,2,…,N 0 }。
Wherein the position matrix P is N in total 0 Row 3 column, where the i-th row element is line point P i Is defined by a three-dimensional coordinate position of (a); (x) o ,y o ,z o ) Values of three elements of the o-th row of the matrix p+s; the matrix P+S is differentiated according to the center of the row, the boundary uses forward or backward differential method to obtain matrix D, (dx) o ,dy o ,dz o ) Is the o-th row of matrix D.
Example 2
Embodiment 2 of the present invention is an embodiment of a smoothing connection device between multiple paths of fragments of crowd-sourced data, as shown in fig. 2, which is a block diagram of an embodiment of a smoothing connection device between multiple paths of fragments of crowd-sourced data, as shown in fig. 2, the device includes: the fitting line output module 101, the deviation vector calculation module 102, the deviation coefficient vector calculation module 103 and the smooth line output module 104.
A fitting line output module 101 for obtaining corresponding line segments L in the front and rear sections directly connected 1 And line segment L 2 Calculating to obtain a line segment L 1 And line segment L 2 Fitting output line L of (1) 0 。
A bias vector calculation module 102 for calculating a head point bias vectorAnd tail point deviation vector->
A deviation coefficient vector calculation module 103 for calculating a deviation vector according to the initial pointTail point deviation vector->And fitting output line L 0 The number N of the upper line points 0 Calculating the first-point deviation coefficient vector +.>And the tail point deviation coefficient vector->
A smooth line output module 104 for outputting a deviation vector according to the initial pointTail point deviation vector->First-point deviation coefficient vector->And the tail point deviation coefficient vector->Calculating a translation matrix; obtaining an output line L according to translation of the translation matrix out 。
Fig. 3 is a schematic physical structure diagram of an electronic device according to an embodiment of the present invention, where, as shown in fig. 3, the electronic device may include: the processor 201, the communication interface 202, the memory 203 and the communication bus 204, wherein the processor 201, the communication interface 202 and the memory 203 complete communication with each other through the communication bus 204. The processor 201 may invoke a computer program stored in the memory 203 and executable on the processor 201 to perform the method of smoothing connections between multiple tracks of fragments of crowd-sourced data provided by the embodiments described above, including, for example: step 1, obtaining corresponding line segments L in a front section and a rear section which are directly connected 1 And line segment L 2 Calculating to obtain a line segment L 1 And line segment L 2 Fitting output line L of (1) 0 The method comprises the steps of carrying out a first treatment on the surface of the Step 2, calculating a head point deviation vectorAnd tail point deviation vector->Step 3, according to the head point deviation vector +.>Tail point deviation vector->And fitting output line L 0 The number N of the upper line points 0 Calculating the first-point deviation coefficient vector +.>And the tail point deviation coefficient vector->Step 4, according to the head point deviation vector +.>Tail point deviation vector->First-point deviation coefficient vector->And the tail point deviation coefficient vector->Calculating a translation matrix; obtaining an output line L according to translation of the translation matrix out 。
The embodiments of the present invention also provide a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, is implemented to perform the method for smooth connection between multiple paths of multi-path segments of crowd-sourced data provided in the above embodiments, for example, including: step 1, obtaining corresponding line segments L in a front section and a rear section which are directly connected 1 And line segment L 2 Calculating to obtain a line segment L 1 And line segment L 2 Fitting output line L of (1) 0 The method comprises the steps of carrying out a first treatment on the surface of the Step 2, calculating a head point deviation vectorAnd tail point deviation vector->Step 3, according to the head point deviation vector +.>Tail point deviation vector->And fitting output line L 0 The number N of the upper line points 0 Calculating the first-point deviation coefficient vector +.>And the tail point deviation coefficient vector->Step 4, according to the head point deviation vector +.>Tail point deviation vector->First-point deviation coefficient vector->And the tail point deviation coefficient vector->Calculating a translation matrix; obtaining an output line L according to translation of the translation matrix out 。
The foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the invention are intended to be included within the scope of the invention.
Claims (5)
1. A method for smooth connection between multiple lines of multi-path segments of crowd-sourced data, the method comprising:
step 1, obtaining corresponding line segments L in a front section and a rear section which are directly connected 1 And line segment L 2 Calculating to obtain the line segment L 1 And line segment L 2 Fitting output line L of (1) 0 ;
Step 2, calculating a head point deviation vectorAnd tail point deviation vector->
Step 3, according to the initial point deviation vectorTail point deviation vector->And the fitting output line L 0 The number N of the upper line points 0 Calculating the first-point deviation coefficient vector +.>And the tail point deviation coefficient vector->
Step 4, according to the initial point deviation vectorTail point deviation vector->First-point deviation coefficient vector->And the tail point deviation coefficient vector->Calculating a translation matrix; translating according to the translation matrix to obtain an output line L out ;
The fitting output line L is obtained in the step 1 0 The process of (1) comprises:
the line segment L 1 And line segment L 2 The method comprises the steps of taking a point set of an input fusion input, establishing an optimization problem by using an optimization fusion method of measurement data of the same lane line in a crowded data road segment, modeling each shape point data in the input point set, solving a minimization problem to obtain an output line equation, and enabling an output starting point to be L 1 Make the end point of the output be the line segment L 2 And make the number of output points N 0 =N 1 +N 2 Obtaining the fitting output line L 0 ={P i (x i ,y i ,z i ,dx i ,dy i ,dz i |i=1,2,…,N 0 )};
Wherein P is i To compose an output line L 0 I is the point number, each line point P i Is pressed on the fitting output line L 0 The sequence is arranged from small to large, N 1 For the line segment L 1 The number of the upper line points N 2 For the line segment L 2 The number of the line-up points;
the head point deviation vector and the tail point deviation vector in the step 2 are as follows:
translation vector
Wherein P is i|i=0 For the fitting output line L 0 Is used for the first point of (a),for the fitting output line L 0 Tail point of P j|j=0 For the line segment L 1 Is the first point of->For the line segment L 2 Is a tail point of (2);
in the step 3, the first point deviation coefficient vectorThe tail point deviation coefficient vector is
In the method, in the process of the invention,representing vectors +.>All elements are arranged in reverse order; />
Wherein n is 2 =(N 0 -1) 2 , The linspace (s, e, n) represents that the values s to e uniformly contain s and e, n values are sequentially formed into a column vector;
the step 4 comprises the following steps:
obtaining a position matrix P according to the translation matrix, and translating according to the position matrix P to obtain an output line L out ={P o (x o ,y o ,z o ,dx o ,dy o ,dz o )|o=1,2,…,N 0 };
Wherein the position matrix P is N in total 0 Row 3 column, where the i-th row element is line point P i Is defined by a three-dimensional coordinate position of (a); (x) o ,y o ,z o ) Values of three elements of the o-th row of the matrix p+s; the matrix P+S is differentiated according to the center of the row, the boundary uses forward or backward differential method to obtain matrix D, (dx) o ,dy o ,dz o ) Is the o-th row of the matrix D.
2. The method according to claim 1, wherein the translation matrix in step 4Wherein (1)>Is->Is the transposed vector of>Is->Is a transposed vector of (a).
3. A smooth connection between multiple lines between multiple road segments of crowd-sourced data, the apparatus comprising: the device comprises a fitting line output module, a deviation vector calculation module, a deviation coefficient vector calculation module and a smooth line output module;
the fitting line output module is used for obtaining the corresponding line segment L in the front and rear sections which are directly connected 1 And line segment L 2 Calculating to obtain the line segment L 1 And line segment L 2 Fitting output line L of (1) 0 ;
The deviation vector calculation moduleBlock for calculating head point bias vectorAnd tail point deviation vector->
The deviation coefficient vector calculation module is used for calculating a deviation vector according to the initial pointTail point deviation vector->And the fitting output line L 0 The number N of the upper line points 0 Calculating the first-point deviation coefficient vector +.>And the tail point deviation coefficient vector->
The smooth line output module is used for outputting the initial point deviation vector according to the initial point deviation vectorTail point deviation vector->First-point deviation coefficient vector->And the tail point deviation coefficient vector->Calculating a translation matrix; translating according to the translation matrix to obtain an output line L out ;
The fitting line output module obtains the fitting output line L 0 The process of (1) comprises:
the line segment L 1 And line segment L 2 The method comprises the steps of taking a point set of an input fusion input, establishing an optimization problem by using an optimization fusion method of measurement data of the same lane line in a crowded data road segment, modeling each shape point data in the input point set, solving a minimization problem to obtain an output line equation, and enabling an output starting point to be L 1 Make the end point of the output be the line segment L 2 And make the number of output points N 0 =N 1 +N 2 Obtaining the fitting output line L 0 ={P i (x i ,y i ,z i ,dx i ,dy i ,dz i |i=1,2,…,N 0 )};
Wherein P is i To compose an output line L 0 I is the point number, each line point P i Is pressed on the fitting output line L 0 The sequence is arranged from small to large, N 1 For the line segment L 1 The number of the upper line points N 2 For the line segment L 2 The number of the line-up points;
the head point deviation vector and the tail point deviation vector in the deviation vector calculation module are as follows:
translation vector
Wherein P is i|i=0 For the fitting output line L 0 Is used for the first point of (a),for the fitting output line L 0 Tail point of P j|j=0 For the line segment L 1 Is the first point of->For the line segment L 2 Is a tail point of (2);
the coefficient of deviationIn the vector calculation module, the first point deviation coefficient vector The tail point deviation coefficient vector is +.>
In the method, in the process of the invention,representing vectors +.>All elements are arranged in reverse order; />
Wherein n is 2 =(N 0 -1) 2 , The linspace (s, e, n) represents that the values s to e uniformly contain s and e, n values are sequentially formed into a column vector;
the smooth line output module includes:
obtaining a position matrix P according to the translation matrix, and translating according to the position matrix P to obtain an output line L out ={P o (x o ,y o ,z o ,dx o ,dy o ,dz o )|o=1,2,…,N 0 };
Wherein the position matrix P is N in total 0 Row 3 column, where the i-th row element is line point P i Is defined by a three-dimensional coordinate position of (a); (x) o ,y o ,z o ) Values of three elements of the o-th row of the matrix p+s; the matrix P+S is differentiated according to the center of the row, the boundary uses forward or backward differential method to obtain matrix D, (dx) o ,dy o ,dz o ) Is the o-th row of the matrix D.
4. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor performs the steps of a method of smoothing connections between multiple fragments of crowd-sourced data according to any one of claims 1 to 2.
5. A non-transitory computer readable storage medium having stored thereon a computer program, which when executed by a processor, performs the steps of a method of smooth connection between multiple lines of multi-path segments of crowd-sourced data according to any one of claims 1 to 2.
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 CN112733078A (en) | 2021-04-30 |
CN112733078B true 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 (10)
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 |
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 |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109581254B (en) * | 2017-09-29 | 2021-07-30 | 西门子(深圳)磁共振有限公司 | Phase deviation obtaining method and system and phase calibration method and system |
-
2020
- 2020-12-29 CN CN202011594172.8A patent/CN112733078B/en active Active
Patent Citations (10)
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 |
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)
Title |
---|
一种基于最小二乘法的离散点螺旋线式拟合算法;尤中桐;王太勇;刘清建;辛全琦;;中国机械工程(第20期);2502-2506+2514 * |
基于道路边线GPS原始数据的曲率评估方法;王东波;黄鹤;王欣宇;;北京测绘(第S1期);44-48 * |
Also Published As
Publication number | Publication date |
---|---|
CN112733078A (en) | 2021-04-30 |
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 | |
CN109242903A (en) | Generation method, device, equipment and the storage medium of three-dimensional data | |
CN114782691A (en) | Robot target identification and motion detection method based on deep learning, storage medium and equipment | |
CN103778598B (en) | Disparity map ameliorative way and device | |
CN112183675B (en) | Tracking method for low-resolution target based on twin network | |
WO2021115061A1 (en) | Image segmentation method and apparatus, and server | |
CN105956074A (en) | Single image scene six-degree-of-freedom positioning method of adjacent pose fusion guidance | |
CN113191243B (en) | Human hand three-dimensional attitude estimation model establishment method based on camera distance and application thereof | |
CN112907573B (en) | Depth completion method based on 3D convolution | |
CN111105451A (en) | Driving scene binocular depth estimation method for overcoming occlusion effect | |
CN109446471A (en) | A kind of consideration fluid structurecoupling interface data transmission method of the load uncertainty based on Interpolation Property of Radial Basis Function | |
CN112733078B (en) | Method and device for smooth connection among multiple paths of fragments of crowdsourcing data | |
CN115063759B (en) | Three-dimensional lane line detection method, device, vehicle and storage medium | |
CN115447584A (en) | Method, device and equipment for determining lane center line and storage medium | |
CN108286957A (en) | A kind of Flatness error evaluation method of fast steady letter | |
CN113592958A (en) | Monocular vision based AUV docking station optical guiding method | |
CN111612912A (en) | Rapid three-dimensional reconstruction and optimization method based on Kinect2 camera face contour point cloud model | |
CN102708293B (en) | Registration method of electrode model and head model | |
CN112580744A (en) | Optimized fusion method for measuring data of same lane line in crowdsourced data road segment | |
CN115116019B (en) | Lane line processing method, device, equipment and storage medium | |
CN110473258A (en) | Monocular SLAM system initialization algorithm based on dotted line Unified frame | |
CN104091308A (en) | Polar line correction method for reducing image distortion | |
CN105741320B (en) | High-real-time machine vision motion analysis method |
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 |