CN113129438B - Method and device for improving precision of lane line and readable storage medium - Google Patents
Method and device for improving precision of lane line and readable storage medium Download PDFInfo
- Publication number
- CN113129438B CN113129438B CN202010042198.5A CN202010042198A CN113129438B CN 113129438 B CN113129438 B CN 113129438B CN 202010042198 A CN202010042198 A CN 202010042198A CN 113129438 B CN113129438 B CN 113129438B
- Authority
- CN
- China
- Prior art keywords
- track
- acquisition
- point
- lane line
- coordinates
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/05—Geographic models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T19/00—Manipulating 3D models or images for computer graphics
- G06T19/20—Editing of 3D images, e.g. changing shapes or colours, aligning objects or positioning parts
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/04—Indexing scheme for image data processing or generation, in general involving 3D image data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2219/00—Indexing scheme for manipulating 3D models or images for computer graphics
- G06T2219/20—Indexing scheme for editing of 3D models
- G06T2219/2021—Shape modification
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- Computer Graphics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Architecture (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Image Processing (AREA)
Abstract
The embodiment of the invention provides a method and a device for improving the precision of lane lines and a readable storage medium, wherein the method comprises the following steps: acquiring a first acquisition track and a second acquisition track corresponding to the same position range and a lane line corresponding to the first acquisition track, wherein the precision of the second acquisition track is higher than that of the first acquisition track; determining a first track point corresponding to the shape point from the first acquisition track according to the coordinates of the shape point of the lane line; determining a second track point corresponding to the first track point from the second acquisition track; and correcting the coordinates of the shape point according to the coordinate offset of the first track point and the second track point. The embodiment of the invention can efficiently and accurately correct the lane line.
Description
Technical Field
The embodiment of the invention relates to the technical field of map data, in particular to a method and a device for improving the precision of lane lines and a readable storage medium.
Background
The manufacturing of the high-precision map data mainly comprises an outside industry data acquisition stage and an inside industry data processing stage; in the field data acquisition stage, field personnel can acquire point cloud data through a high-precision acquisition vehicle, in the field data processing stage, the field personnel can identify the point cloud data by utilizing an identification algorithm, and the high-precision map data can be manufactured by assisting in manually correcting an identification result.
The manufacture of the lane line is an important task for manufacturing high-precision map data, after the precision of the point cloud data is improved, the phenomenon that the originally manufactured lane line cannot be matched with the point cloud data after the precision is improved exists, so that how to provide a scheme for improving the precision of the lane line, so that the precision of the lane line is improved by efficiently correcting the lane line, and the problem to be solved by the person skilled in the art is urgent.
Disclosure of Invention
In view of the above, the embodiments of the present invention provide a method and apparatus for improving the accuracy of a lane line, and a readable storage medium, so as to efficiently correct the lane line and improve the accuracy of the lane line.
In order to achieve the above object, the embodiment of the present invention provides the following technical solutions:
a method for improving the precision of a lane line comprises the following steps:
acquiring a first acquisition track, a second acquisition track and a lane line which are obtained based on the same acquisition track; the lane line corresponds to the first acquisition track, and the precision of the second acquisition track is higher than that of the first acquisition track;
and correcting the coordinates of the shape points of the lane lines according to the coordinate offset of the corresponding track points in the first acquisition track and the second acquisition track.
Optionally, the correcting the coordinates of the shape point of the lane line according to the coordinate offset of the corresponding track point in the first acquisition track and the second acquisition track includes:
determining a first track point corresponding to the shape point from the first acquisition track according to the coordinates of the shape point of the lane line;
determining a second track point corresponding to the first track point from the second acquisition track;
and correcting the coordinates of the shape point according to the coordinate offset of the first track point and the second track point.
Optionally, the determining, according to the coordinates of the shape point of the lane line, a first track point corresponding to the shape point from the first acquisition track includes:
and determining a nearest track point which is within a preset distance with the coordinates of the shape point of the lane line from the first acquisition track, and determining the nearest track point as a first track point corresponding to the shape point.
Optionally, the determining, from the first collected track, a nearest track point with coordinates of the shape point of the lane line within a predetermined distance includes:
judging whether track points of the first acquisition track exist within a preset distance of the coordinates of the shape points according to the coordinates of the shape points of the lane lines and the coordinates of the track points of the first acquisition track; if so, determining the nearest track point closest to the shape point from the track points of the first acquisition track.
Optionally, the method further comprises:
and if the track point of the first acquisition track does not exist within the preset distance of the coordinates of the shape point, canceling correction of the coordinates of the shape point of the lane line.
Optionally, the determining, from the second acquisition track, a second track point corresponding to the first track point includes:
and determining a second track point corresponding to the acquisition time from the second acquisition track according to the acquisition time of the first track point.
Optionally, the first acquisition track is obtained by calculating the same acquisition track based on a first track calculation algorithm; the lane lines are determined based on the point cloud data corresponding to the first acquisition track; the second acquisition track is obtained by calculating the same acquisition track based on a second track calculation algorithm; the accuracy of the second trajectory calculation algorithm is higher than the accuracy of the first calculation algorithm.
Optionally, the correcting the coordinates of the shape point according to the coordinate offsets of the first track point and the second track point includes:
determining longitude coordinate offset, latitude coordinate offset and elevation coordinate offset of the first track point and the second track point respectively;
and adding the longitude coordinate offset to the current longitude coordinate of the shape point, adding the latitude coordinate offset to the current latitude coordinate, and adding the elevation coordinate offset to the current elevation coordinate to obtain the corrected coordinate of the shape point.
The embodiment of the invention also provides a device for improving the precision of the lane line, which comprises the following steps:
the data acquisition module is used for acquiring a first acquisition track, a second acquisition track and a lane line which are acquired based on the same acquisition track; the lane line corresponds to the first acquisition track, and the precision of the second acquisition track is higher than that of the first acquisition track;
and the correction module is used for correcting the coordinates of the shape points of the lane lines according to the coordinate offset of the corresponding track points in the first acquisition track and the second acquisition track.
The embodiment of the invention also provides a readable storage medium which stores a program for executing the lane line precision improving method.
According to the method for improving the precision of the lane line, when the coordinates of the lane line need to be corrected, the first acquisition track, the second acquisition track and the lane line which are obtained based on the same acquisition track can be obtained; the lane line corresponds to the first acquisition track, and the precision of the second acquisition track is higher than that of the first acquisition track; and correcting the coordinates of the shape points of the lane lines according to the coordinate offset of the corresponding track points in the first acquisition track and the second acquisition track. Because the coordinate relation between the acquisition track and the corresponding lane line is unchanged when the precision of the acquisition track changes, the embodiment of the invention can carry out coordinate correction on the shape point in the lane line corresponding to the first acquisition track based on the coordinate offset of the corresponding track point in the first acquisition track and the second acquisition track, so that the coordinate of the shape point after the correction of the lane line is matched with the point cloud data corresponding to the second acquisition track with improved precision, the process of reconstructing map data based on the point cloud data with improved precision is avoided, and the efficient and accurate correction of the coordinate of the lane line can be realized.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present application, and that other drawings may be obtained according to the provided drawings without inventive effort to a person skilled in the art.
FIG. 1 is a flowchart of a method for improving accuracy of lane lines according to an embodiment of the present invention;
FIG. 2 is a flowchart of a method for correcting coordinates of a shape point according to an embodiment of the present invention;
FIG. 3 is another flowchart of a method for improving accuracy of lane lines according to an embodiment of the present invention;
FIG. 4 is an exemplary diagram of trace points corresponding to shape points;
FIG. 5 is a flowchart of a method for improving accuracy of lane lines according to an embodiment of the present invention;
FIG. 6 is a diagram of an application example provided in an embodiment of the present invention;
FIG. 7 is a block diagram of a lane line accuracy improving apparatus according to an embodiment of the present invention;
FIG. 8 is a block diagram of a computing device provided by the present invention.
Detailed Description
Along with the continuous improvement of the precision requirement of the high-precision map data, the precision requirement of the high-precision map data which is particularly suitable for unmanned requirements is higher and higher, when the acquisition track of the high-precision acquisition vehicle is obtained by resolving through a track resolving algorithm with higher precision, in order to meet the continuous improvement of the precision requirement of the high-precision map data, the acquisition track with higher precision can be obtained by resolving through the track resolving algorithm with higher precision, and correspondingly, the precision of the point cloud data corresponding to the acquisition track is also improved; for example, the point cloud coordinates of the point cloud data are derived from the acquisition track coordinates of the high-precision acquisition vehicle acquisition point cloud data, and the accuracy of the point cloud data is correspondingly improved after the accuracy of the acquisition track is improved by utilizing a track resolving algorithm with higher accuracy; the precision of the point cloud data is improved, so that the coordinates of the lane lines in the originally manufactured high-precision map data cannot be matched with the point cloud data with the precision improved, and the coordinates of the lane lines are required to be corrected at the moment so as to improve the precision of the lane lines.
At present, high-precision map data are manufactured again based on the point cloud data with improved precision, so that coordinates of lane lines in the reproduced high-precision map data are matched with the point cloud data with improved precision, namely, the coordinates of the lane lines are corrected by reproducing the high-precision map data, so that the precision of the lane lines is improved; however, the method is based on the point cloud data with improved precision, and the correction efficiency of the lane lines is lower on the basis of reconstructing high-precision map data.
Based on the above, the embodiment of the invention provides a method and a device for improving the precision of a lane line and a readable storage medium, so as to efficiently correct the lane line and improve the precision of the lane line. The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As an optional implementation of the disclosure of the embodiment of the present invention, fig. 1 shows an optional flow of a method for improving accuracy of a lane line provided by the embodiment of the present invention, where the method for improving accuracy of a lane line may be executed by a computing device having a data processing capability; alternatively, the computing device may be implemented by a server (e.g., a single server, or a server group formed by multiple servers), or may be implemented by a terminal; in one example, the computing device may be a computing device used in an in-house data processing stage of high-precision map data production;
referring to fig. 1, the method for improving the accuracy of a lane line according to the embodiment of the present invention may include:
s10, acquiring a first acquisition track, a second acquisition track and a lane line which are obtained based on the same acquisition track; the lane line corresponds to the first acquisition track, and the precision of the second acquisition track is higher than that of the first acquisition track.
In the embodiment of the invention, the first acquisition track and the second acquisition track are obtained based on the same acquisition track, the first acquisition track can be the acquisition track of the point cloud data before precision improvement, the second acquisition track can be the acquisition track of the point cloud data after precision improvement, namely the first acquisition track and the second acquisition track are the acquisition tracks of the point cloud data before and after precision improvement, and the precision of the second acquisition track is higher than that of the first acquisition track.
The first acquisition track and the second acquisition track can be understood as being based on the same acquisition track, wherein the first acquisition track and the second acquisition track are derived from the same running track of the high-definition acquisition vehicle acquisition point cloud data and are obtained by resolving through a track resolving algorithm with different accuracies; the accuracy of the trajectory solution algorithm used by the second acquisition trajectory is higher than the accuracy of the trajectory solution algorithm used by the first acquisition trajectory. Optionally, the first acquisition track and the second acquisition track may be obtained by using a track resolving algorithm before and after precision improvement to resolve the same acquisition track (such as a running track) of the high-precision acquisition vehicle acquisition point cloud data; for example, the first acquisition track may be obtained by resolving the same acquisition track of the point cloud data acquired by the high-precision acquisition vehicle by using a first track resolving algorithm before precision improvement, and the first acquisition track may have corresponding point cloud data, for example, the point cloud coordinates of the corresponding point cloud data may be determined based on the coordinates of the first acquisition track; when the accuracy of the track resolving algorithm is improved and a second track resolving algorithm with higher accuracy is provided, the same acquisition track can be resolved by using the second track resolving algorithm to obtain a second acquisition track with higher accuracy in order to meet the accuracy improving requirement of the high-accuracy map data, and the second acquisition track with higher accuracy can be provided with corresponding point cloud data with higher accuracy, such as point cloud coordinates of the point cloud data with higher accuracy can be determined based on the second acquisition track with higher accuracy; at this time, the coordinates of the lane lines in the high-precision map data which are manufactured based on the first acquisition track cannot be matched with the point cloud data with improved accuracy, and the coordinates of the lane lines need to be corrected so as to improve the accuracy of the lane lines.
It can be seen that the first acquisition track and the second acquisition track are derived from the same acquisition track of the high-definition acquisition vehicle, and optionally, the first acquisition track can be obtained by calculating the same acquisition track based on a first track calculation algorithm with lower precision, and the second acquisition track can be obtained by calculating the same acquisition track based on a second track calculation algorithm with higher precision. Taking the example that the high-precision acquisition vehicle acquires data on the road S on 1 month and 2 days as the example, the embodiment of the invention can firstly use a first track resolving algorithm (such as an ephemeris resolving algorithm) to resolve the acquisition track of the high-precision acquisition vehicle on the road S on 1 month and 2 days to obtain a first acquisition track, and make high-precision map data based on the point cloud data corresponding to the first acquisition track; when the track resolving algorithm is improved in technology and a second track resolving algorithm with higher precision exists (for example, when a thousand base station resolving algorithm with higher precision than the ephemeris resolving algorithm exists), the embodiment of the invention can use the second track resolving algorithm to resolve the acquisition track of the high-precision acquisition vehicle on the road S for 1 month and 2 days to obtain the second acquisition track with higher precision; at this time, the coordinate change of the second acquisition track will bring about the change of the point cloud coordinate of the point cloud data, and the coordinate of the lane line of the originally manufactured high-precision map data cannot be matched with the point cloud data corresponding to the second acquisition track, so that the coordinate of the lane line needs to be corrected to improve the precision of the lane line.
In order to correct a lane line, the embodiment of the invention can acquire a first acquisition track, a second acquisition track and a lane line which are obtained based on the same acquisition track, wherein the lane line corresponds to the first acquisition track, and the precision of the second acquisition track is higher than that of the first acquisition track. The lane line corresponds to the first acquisition track and can be regarded as being processed and manufactured based on the first acquisition track and the point cloud data corresponding to the first acquisition track, namely the lane line is the lane line in the high-precision map data before the precision is improved; optionally, the embodiment of the invention can acquire the lane line corresponding to the first acquisition track from a production library, and the production library can store map elements of the high-precision map data manufactured based on the first acquisition track before precision improvement and corresponding point cloud data.
And S11, correcting coordinates of the shape points of the lane lines according to the coordinate offset of the corresponding track points in the first acquisition track and the second acquisition track.
The first acquisition track and the second acquisition track are derived from the same acquisition track of the high-definition acquisition vehicle acquisition point cloud data, the lane line corresponds to the first acquisition track, and although the accuracy of the first acquisition track and the accuracy of the second acquisition track are different, the coordinate correspondence between the first acquisition track and the second acquisition track and the lane line is unchanged, namely the coordinate relationship between the first acquisition track and the lane line is equivalent to the coordinate relationship between the second acquisition track and the corresponding lane line; meanwhile, the coordinate deviation of corresponding track points in the first acquisition track and the second acquisition track can be represented, and the coordinate difference of the track points of the same acquisition track before and after the precision is improved; based on the above, the embodiment of the invention can correct the coordinates of the shape points of the lane lines before the precision is improved by utilizing the coordinate deviation of the corresponding track points in the first acquisition track and the second acquisition track, so that the coordinates of the shape points of the corrected lane lines are matched with the second acquisition track after the precision is improved.
According to the method for improving the precision of the lane line, when the coordinates of the lane line need to be corrected, the first acquisition track, the second acquisition track and the lane line which are obtained based on the same acquisition track can be obtained; the lane line corresponds to the first acquisition track, and the precision of the second acquisition track is higher than that of the first acquisition track; and correcting the coordinates of the shape points of the lane lines according to the coordinate offset of the corresponding track points in the first acquisition track and the second acquisition track. Because the coordinate relation between the acquisition track and the corresponding lane line is unchanged when the precision of the acquisition track changes, the embodiment of the invention can carry out coordinate correction on the shape point in the lane line corresponding to the first acquisition track based on the coordinate offset of the corresponding track point in the first acquisition track and the second acquisition track, so that the coordinate of the shape point after the correction of the lane line is matched with the point cloud data corresponding to the second acquisition track with improved precision, the process of reconstructing map data based on the point cloud data with improved precision is avoided, and the efficient and accurate correction of the coordinate of the lane line can be realized.
In an alternative implementation, the implementation of step S11 shown in fig. 1 may include, as shown in fig. 2:
and step S111, determining a first track point corresponding to the shape point from the first acquisition track according to the coordinates of the shape point of the lane line.
The embodiment of the invention can determine the corresponding track point from the first acquisition track before the precision is improved by utilizing the coordinates of the shape point of the lane line before the precision is improved, so as to obtain the first track point; and then correcting the coordinates of the shape points of the lane lines by utilizing the coordinate changes of the corresponding track points in the second acquisition track and the first acquisition track.
In an alternative implementation, the first track point corresponding to the shape point in the first acquisition track may be a nearest track point in the first acquisition track, where the coordinates of the shape point of the lane line are within a predetermined distance.
And step S112, determining a second track point corresponding to the first track point from the second acquisition track.
Optionally, the first acquisition track and the second acquisition track originate from the same acquisition track of the high-definition acquisition vehicle, so that the acquisition time of corresponding track points in the first acquisition track and the second acquisition track is the same;
for example, the acquisition time of the first track point in the first acquisition track is 11 minutes 11 seconds of 11 points on 1 month 1 day 1 in 2018, so that the embodiment of the invention can determine the track point with the acquisition time of 11 minutes 11 seconds of 11 points on 1 month 1 day 1 from the second acquisition track to obtain the second track point; the embodiment of the invention can refer to the track points with the same acquisition time points in the first acquisition track and the second acquisition track as the same-name track points.
Step S113, correcting coordinates of the shape point according to the coordinate offsets of the first track point and the second track point.
Because the coordinate relation between the acquisition track and the corresponding lane line is unchanged, the coordinate offset of the same-name track points in the first acquisition track and the second acquisition track can be regarded as the coordinate offset of the shape points of the lane line corresponding to the first acquisition track and the lane line corresponding to the second acquisition track; the embodiment of the invention can carry out coordinate correction on the corresponding shape point in the lane line corresponding to the first acquisition track based on the coordinate offset of the corresponding track point in the first acquisition track and the second acquisition track, so that the coordinates of the shape point after the lane line correction are matched with the second acquisition track with improved precision, and the coordinates of the lane line can be corrected efficiently and accurately.
In an alternative implementation, the lane line may have a plurality of shape points, where there may be a shape point that needs to be corrected or a shape point that does not need to be corrected, so in the embodiment of the present invention, the shape point that needs to be corrected in the lane line may be determined according to the coordinates of the shape point of the lane line and the coordinates of the track point in the first acquisition track, and then coordinate correction is performed on the shape point that needs to be corrected; optionally, fig. 3 shows another flowchart of a method for improving accuracy of a lane line according to an embodiment of the present invention, and referring to fig. 3, the flowchart may include:
step S20, acquiring a first acquisition track, a second acquisition track and a lane line which are obtained based on the same acquisition track; the lane line corresponds to the first acquisition track, and the precision of the second acquisition track is higher than that of the first acquisition track.
Alternatively, the description of step S20 may refer to the previous step S10, and will not be repeated here.
And step S21, judging whether track points of the first acquisition track exist within a preset distance of the coordinates of the shape points according to the coordinates of the shape points of the lane lines and the coordinates of the track points of the first acquisition track, if not, executing step S22, and if so, executing step S23.
Optionally, for each shape point in the lane line corresponding to the first acquisition track, the embodiment of the invention can determine whether the track point of the first acquisition track exists within a predetermined distance of the coordinates of the shape point, so as to determine whether the coordinates of the shape point need to be corrected; if the track point of the first acquisition track does not exist within the preset distance of the coordinate of a certain shape point in the lane line, the embodiment of the invention considers that the coordinate of the shape point does not need to be corrected, and the flow can be ended; if the track point of the first acquisition track exists within a preset distance of the coordinate of a certain shape point in the lane line, the embodiment of the invention can consider that the coordinate of the shape point needs to be corrected.
Optionally, according to the embodiment of the invention, whether the track point of the first acquisition track exists in the preset distance of the coordinates of the shape point of the lane line or not can be judged according to the coordinates of the shape point of the lane line and the coordinates of the track point of the first acquisition track in a coordinate distance matching mode.
Step S22, ending the flow.
When the track point of the first acquisition track does not exist within the preset distance of the coordinates of the shape point, the embodiment of the invention can cancel correction of the coordinates of the shape point and end the flow.
And S23, determining the nearest track point which is nearest to the shape point in the first acquisition track as a first track point which corresponds to the shape point in the first acquisition track.
When the track point of the first acquisition track exists within the preset distance of the coordinates of the shape point of the lane line, the embodiment of the invention can consider that the coordinates of the shape point need to be corrected, and the embodiment of the invention can determine the track point closest to the shape point in the first acquisition track as the first track point corresponding to the shape point in the first acquisition track; that is, the first track point corresponding to the shape point in the first acquisition track may be the nearest track point in the first acquisition track, where the coordinates of the shape point of the lane line are within a predetermined distance.
For example, as shown in fig. 4, taking a lane line as an example, for a shape point A1 on the lane line, the embodiment of the present invention may determine, as a first track point corresponding to the shape point A1 in a first acquisition track, a nearest track point B1 in the first acquisition track having a distance within 30 meters from the shape point A1; it should be noted that, the specific value of the predetermined distance may be set according to the actual situation, which is only illustrated here.
And step S24, determining a second track point corresponding to the acquisition time from the second acquisition track according to the acquisition time of the first track point.
After a first track point corresponding to a shape point to be corrected is determined from a first acquisition track, the embodiment of the invention can acquire the acquisition time and coordinates of the first track point; based on the principle that the coordinate relation between the acquisition track and the corresponding lane line is unchanged, the embodiment of the invention can determine the same-name track point of the first track point from the second acquisition track with improved precision according to the acquisition time of the first track point, namely, determine the second track point corresponding to the first track point in the acquisition time from the second acquisition track, so that the coordinate correction can be carried out on the shape point based on the coordinate deviation amount of the second track point and the first track point belonging to the same-name track point.
And S25, correcting the coordinates of the shape points according to the coordinate offset of the first track points and the second track points.
The lane line is required to be matched with the point cloud data based on the product requirement of the high-precision map data, and the point cloud coordinates of the point cloud data are derived from the coordinates of the acquisition tracks, so that the coordinate offset of the acquisition tracks before and after the precision is improved can be regarded as the point cloud coordinate offset of the point cloud data before and after the precision is improved, that is, when the precision of the acquisition tracks is changed, the coordinate relation between the acquisition tracks and the corresponding lane lines is unchanged, and therefore the lane line precision correction method and the lane line precision correction device can correct the coordinates of the corresponding shape points in the lane lines before the precision is improved according to the coordinate offset of the corresponding track points in the first acquisition tracks and the second acquisition tracks before and after the precision is improved, and therefore the lane line precision is improved.
Optionally, the embodiment of the present invention may add the current coordinate of the shape point to the coordinate offset to obtain the corrected coordinate of the shape point.
As an alternative implementation of the disclosure of the embodiment of the present invention, the embodiment of the present invention may use an XYZ coordinate system to represent coordinates, where X represents longitude, Y represents latitude, and Z represents elevation, that is, the embodiment of the present invention may use a combination of longitude, latitude, and elevation to represent coordinates of a shape point and coordinates of a track point; optionally, fig. 5 shows a further flowchart of a method for improving accuracy of a lane line according to an embodiment of the present invention, and referring to fig. 5, the flowchart may include:
step S30, acquiring a first acquisition track, a second acquisition track and a lane line which are obtained based on the same acquisition track; the lane line corresponds to the first acquisition track, and the precision of the second acquisition track is higher than that of the first acquisition track.
Alternatively, the description of step S30 may refer to the previous step S10, and will not be repeated here.
And S31, judging whether the track point of the first acquisition track exists within a preset distance of the coordinates of the shape point of the lane line and the coordinates of the track point of the first acquisition track in a coordinate system established based on longitude, latitude and elevation, if not, executing the step S32, and if so, executing the step S33.
The coordinates of the shape points and the coordinates of the track points can be represented by longitude coordinates, latitude coordinates and elevation coordinates, namely, the coordinates of any shape point are represented as (X, Y, Z), X represents longitude, Y represents latitude, Z represents elevation;
after the coordinate system of XYZ is established, for any shape point of the lane line, the embodiment of the invention can judge whether the track point of the first acquisition track exists within the preset distance of the coordinate of the shape point according to the coordinate of the shape point of the lane line and the coordinate of the track point of the first acquisition track; if not, the embodiment of the invention considers that the coordinates of the shape point do not need to be corrected, and the flow can be ended; if yes, the embodiment of the invention can consider that the coordinates of the shape point need to be corrected.
Step S32, ending the flow.
And step S33, determining the nearest track point which is nearest to the shape point in the first acquisition track as a first track point which corresponds to the shape point in the first acquisition track.
And step S34, determining a second track point corresponding to the acquisition time from the second acquisition track according to the acquisition time of the first track point.
In the implementation of the invention, the track points in the first acquisition track and the second acquisition track have information such as acquisition time and coordinates. For example, after determining the acquisition time T1 and the coordinates (X1, Y1, Z1) of the first track point, the embodiment of the present invention may determine, according to the acquisition time T1 of the first track point, a second track point corresponding to the acquisition time T1 from the second acquisition track, and obtain the coordinates (X1 ', Y1', Z1 ') of the second track point.
And step S35, determining the longitude coordinate offset, the latitude coordinate offset and the elevation coordinate offset of the first track point and the second track point respectively.
For example, taking the coordinates of the first track point as (X1, Y1, Z1) and the coordinates of the second track point as (X1 ', Y1', Z1 '), the coordinate offset (X1-X1', Y1-Y1', Z1-Z1') can be calculated.
Step S36, adding the longitude coordinate offset to the current longitude coordinate of the shape point, adding the latitude coordinate offset to the current latitude coordinate, and adding the elevation coordinate offset to the current elevation coordinate to obtain the corrected coordinate of the shape point.
Taking the coordinates of the shape point as (X, Y, Z) as an example, the coordinates after shape point correction according to the embodiment of the present invention may be: (X+ (X1-X1 '), Y+ (Y1-Y1 '), Z+ (Z1-Z1 ')).
As an application example, as shown in fig. 6, an acquisition track 1 is an acquisition track obtained by resolving an acquisition track of a high-precision acquisition vehicle on a road S by a first track resolving algorithm, track points on the acquisition track 1 have information such as acquisition time and coordinates, high-precision map data can be manufactured based on point cloud data corresponding to the acquisition track 1, and a lane line a shown in fig. 6 is a lane line on the road S in the manufactured high-precision map data;
along with the improvement of the precision of the track resolving algorithm, when a second track resolving algorithm with higher precision exists, the embodiment of the invention can resolve the acquisition track of the high-precision acquisition vehicle on the road S based on the second track resolving algorithm with higher precision to obtain an acquisition track 2; the track points on the acquisition track 2 have information such as acquisition time and coordinates, the coordinates of the track points on the acquisition track 2 are higher in precision than the coordinates of the track points on the acquisition track 1, but the acquisition time of the track points on the acquisition track 2 and the acquisition time of the track points on the acquisition track 1 are corresponding to the acquisition time of the acquisition track of the high-precision acquisition vehicle on the road S;
it can be understood that the point cloud data corresponding to the acquisition track 2 with improved precision is not matched with the coordinates of the manufactured lane line A, and the coordinates of the lane line A need to be corrected in order to improve the precision of the high-precision map data; the traditional correction mode is based on the point cloud data corresponding to the acquisition track 2 after the precision is improved, and the high-precision map data is reproduced, so that the coordinates of the lane line A are corrected in the process of reproducing the high-precision map data, but the mode is definitely low in efficiency;
in order to achieve efficient correction of coordinates of a lane line, after the acquisition track 2 is calculated based on the second track algorithm, for any shape point A1 on the lane line a, the embodiment of the invention can determine the nearest track point 11, which is within a predetermined distance from the coordinates of the shape point A1, in the acquisition track 1, that is, the track point 11 is the track point corresponding to the shape point A1 in the acquisition track 1;
therefore, according to the acquisition time T of the track point 11, the track point 12 with the same acquisition time T is determined from the acquisition track 2, and the same-name track points 11 and 12 in the acquisition track 1 and the acquisition track 2 are determined; the track points 12 in the acquisition track 2 can be regarded as track points corresponding to the shape points A1 after the precision is improved;
further, the coordinate offset of the track point 11 and the track point 12 is calculated, and the coordinate of the shape point A1 is added with the coordinate offset to realize the coordinate correction of the shape point A1;
by the mode, the coordinates of each shape point in the lane line A are corrected, and the coordinates of the lane line can be corrected efficiently and accurately.
The method for improving the precision of the lane line provided by the embodiment of the invention can improve the precision of the lane line by efficiently correcting the coordinates of the lane line in the manufactured high-precision map data after the precision of the point cloud data is improved.
The foregoing describes several embodiments of the present invention, and the various alternatives presented by the various embodiments may be combined, cross-referenced, with each other without conflict, extending beyond what is possible embodiments, all of which are considered to be embodiments of the present invention disclosed and disclosed.
The following describes the lane line accuracy improving device provided by the embodiment of the present invention, and the lane line accuracy improving device described below may be considered as a functional module required to be set for implementing the lane line accuracy improving method provided by the embodiment of the present invention. The contents of the accuracy improving apparatus for lane lines described below may be referred to in correspondence with the contents of the accuracy improving method for lane lines described above.
Fig. 7 is a block diagram of a lane line accuracy improving apparatus according to an embodiment of the present invention, and referring to fig. 7, the lane line accuracy improving apparatus according to an embodiment of the present invention may include:
the data acquisition module 100 is configured to acquire a first acquisition track, a second acquisition track and a lane line, which are acquired based on the same acquisition track; the lane line corresponds to the first acquisition track, and the precision of the second acquisition track is higher than that of the first acquisition track;
and the correction module 200 is configured to correct coordinates of the shape point of the lane line according to the coordinate offsets of the corresponding track points in the first acquisition track and the second acquisition track.
Optionally, the correction module 200 is configured to correct coordinates of the shape point of the lane line according to the coordinate offset of the corresponding track point in the first acquisition track and the second acquisition track, and includes:
determining a first track point corresponding to the shape point from the first acquisition track according to the coordinates of the shape point of the lane line;
determining a second track point corresponding to the first track point from the second acquisition track;
and correcting the coordinates of the shape point according to the coordinate offset of the first track point and the second track point.
The correction module 200, configured to determine, from the first acquisition trajectory, a first trajectory point corresponding to the shape point according to coordinates of the shape point of the lane line, may specifically include:
and determining a nearest track point which is within a preset distance with the coordinates of the shape point of the lane line from the first acquisition track, and determining the nearest track point as a first track point corresponding to the shape point.
Optionally, the correction module 200 is configured to determine, from the first collected track, a nearest track point that is within a predetermined distance from the coordinates of the shape point of the lane line, where the nearest track point includes:
judging whether track points of the first acquisition track exist within a preset distance of the coordinates of the shape points according to the coordinates of the shape points of the lane lines and the coordinates of the track points of the first acquisition track; if so, determining the nearest track point closest to the shape point from the track points of the first acquisition track.
Optionally, the device for improving the accuracy of the lane line provided by the embodiment of the invention is further used for:
and if the track point of the first acquisition track does not exist within the preset distance of the coordinates of the shape point, canceling correction of the coordinates of the shape point of the lane line.
Optionally, the correction module 200, configured to determine, from the second acquired track, a second track point corresponding to the first track point includes:
and determining a second track point corresponding to the acquisition time from the second acquisition track according to the acquisition time of the first track point.
Optionally, the first acquisition track is obtained by calculating the same acquisition track based on a first track calculation algorithm; the lane lines are determined based on the point cloud data corresponding to the first acquisition track; the second acquisition track is obtained by calculating the same acquisition track based on a second track calculation algorithm; the accuracy of the second trajectory calculation algorithm is higher than the accuracy of the first calculation algorithm.
Optionally, the correcting module 200 is configured to correct the coordinates of the shape point according to the coordinate offsets of the first track point and the second track point, where the correcting module includes:
determining longitude coordinate offset, latitude coordinate offset and elevation coordinate offset of the first track point and the second track point respectively;
and adding the longitude coordinate offset to the current longitude coordinate of the shape point, adding the latitude coordinate offset to the current latitude coordinate, and adding the elevation coordinate offset to the current elevation coordinate to obtain the corrected coordinate of the shape point.
According to the lane line precision lifting device provided by the embodiment of the invention, the coordinates of the shape points corresponding to the lane line corresponding to the first acquisition track can be corrected based on the coordinate offset of the corresponding track points in the first acquisition track and the second acquisition track, so that the coordinates of the corrected shape points of the lane line are matched with the point cloud data corresponding to the second acquisition track with the precision, the process of reconstructing map data based on the point cloud data with the precision is avoided, and the coordinates of the lane line can be corrected efficiently and accurately.
The embodiment of the invention also provides a computing device, and the lane line precision improving device can be loaded on the computing device in a program form; in an alternative implementation, fig. 8 illustrates an alternative block diagram of a computing device provided by the present invention, and referring to fig. 8, the computing device may include: at least one processor 10, at least one communication interface 20, at least one memory 30 and at least one communication bus 40;
in the embodiment of the present invention, the number of the processor 10, the communication interface 20, the memory 30 and the communication bus 40 is at least one, and the processor 10, the communication interface 20 and the memory 30 complete the communication with each other through the communication bus 40;
alternatively, the communication interface 20 may be an interface of a communication module, such as an interface of a GSM module;
the processor 10 may be a central processing unit CPU, or a specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement embodiments of the present invention.
The memory 30 may comprise high-speed RAM memory or may further comprise non-volatile memory (non-volatile memory), such as at least one disk memory.
The memory 30 stores a program, and the processor 10 calls the program stored in the memory 30 to execute the lane line accuracy improving method according to the embodiment of the present invention.
Further, the embodiment of the invention also provides a readable storage medium, which can store a program for executing the lane line precision improving method provided by the embodiment of the invention;
wherein, the program can be specifically used for:
acquiring a first acquisition track, a second acquisition track and a lane line which are obtained based on the same acquisition track; the lane line corresponds to the first acquisition track, and the precision of the second acquisition track is higher than that of the first acquisition track;
and correcting the coordinates of the shape points of the lane lines according to the coordinate offset of the corresponding track points in the first acquisition track and the second acquisition track.
Although the embodiments of the present invention are disclosed above, the present invention is not limited thereto. Various changes and modifications may be made by one skilled in the art without departing from the spirit and scope of the invention, and the scope of the invention should be assessed accordingly to that of the appended claims.
Claims (10)
1. A method for improving the precision of a lane line comprises the following steps:
acquiring a first acquisition track, a second acquisition track and a lane line which are obtained based on the same acquisition track; the lane line corresponds to the first acquisition track, and the precision of the second acquisition track is higher than that of the first acquisition track; the acquisition time of corresponding track points in the first acquisition track and the second acquisition track is the same;
and correcting the coordinates of the shape points of the lane lines according to the coordinate offset of the corresponding track points in the first acquisition track and the second acquisition track.
2. The method for improving the precision of the lane line according to claim 1, wherein the correcting the coordinates of the shape point of the lane line according to the coordinate offsets of the corresponding track points in the first acquisition track and the second acquisition track comprises:
determining a first track point corresponding to the shape point from the first acquisition track according to the coordinates of the shape point of the lane line;
determining a second track point corresponding to the first track point from the second acquisition track;
and correcting the coordinates of the shape point according to the coordinate offset of the first track point and the second track point.
3. The method for improving the accuracy of a lane line according to claim 2, wherein the determining a first track point corresponding to the shape point from the first acquisition track according to the coordinates of the shape point of the lane line comprises:
and determining a nearest track point which is within a preset distance with the coordinates of the shape point of the lane line from the first acquisition track, and determining the nearest track point as a first track point corresponding to the shape point.
4. The accuracy improving method of a lane line according to claim 3, wherein the determining, from the first acquisition trajectory, a nearest trajectory point within a predetermined distance from coordinates of a shape point of the lane line includes:
judging whether track points of the first acquisition track exist within a preset distance of the coordinates of the shape points according to the coordinates of the shape points of the lane lines and the coordinates of the track points of the first acquisition track; if so, determining the nearest track point closest to the shape point from the track points of the first acquisition track.
5. The method for improving the accuracy of a lane line according to claim 4, further comprising:
and if the track point of the first acquisition track does not exist within the preset distance of the coordinates of the shape point, canceling correction of the coordinates of the shape point of the lane line.
6. The method for improving the accuracy of the lane line according to any one of claims 2 to 5, wherein the determining a second track point corresponding to the first track point from the second acquisition track includes:
and determining a second track point corresponding to the acquisition time from the second acquisition track according to the acquisition time of the first track point.
7. The method for improving the accuracy of the lane line according to claim 1, wherein the first acquisition track is obtained by calculating the same acquisition track based on a first track calculation algorithm; the lane lines are determined based on the point cloud data corresponding to the first acquisition track; the second acquisition track is obtained by calculating the same acquisition track based on a second track calculation algorithm; the accuracy of the second trajectory calculation algorithm is higher than the accuracy of the first trajectory calculation algorithm.
8. The method for improving the accuracy of the lane line according to claim 2, wherein correcting the coordinates of the shape point according to the coordinate offsets of the first and second track points comprises:
determining longitude coordinate offset, latitude coordinate offset and elevation coordinate offset of the first track point and the second track point respectively;
and adding the longitude coordinate offset to the current longitude coordinate of the shape point, adding the latitude coordinate offset to the current latitude coordinate, and adding the elevation coordinate offset to the current elevation coordinate to obtain the corrected coordinate of the shape point.
9. An accuracy improving device of lane line, comprising:
the data acquisition module is used for acquiring a first acquisition track, a second acquisition track and a lane line which are acquired based on the same acquisition track; the lane line corresponds to the first acquisition track, and the precision of the second acquisition track is higher than that of the first acquisition track; the acquisition time of corresponding track points in the first acquisition track and the second acquisition track is the same;
and the correction module is used for correcting the coordinates of the shape points of the lane lines according to the coordinate offset of the corresponding track points in the first acquisition track and the second acquisition track.
10. A readable storage medium storing a program that executes the accuracy improvement method of a lane line according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010042198.5A CN113129438B (en) | 2020-01-15 | 2020-01-15 | Method and device for improving precision of lane line and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010042198.5A CN113129438B (en) | 2020-01-15 | 2020-01-15 | Method and device for improving precision of lane line and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113129438A CN113129438A (en) | 2021-07-16 |
| CN113129438B true CN113129438B (en) | 2023-06-23 |
Family
ID=76771361
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010042198.5A Active CN113129438B (en) | 2020-01-15 | 2020-01-15 | Method and device for improving precision of lane line and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113129438B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116793369B (en) * | 2023-02-10 | 2024-03-08 | 北京斯年智驾科技有限公司 | Path planning method, device, equipment and computer readable storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101719042A (en) * | 2010-01-14 | 2010-06-02 | 广东威创视讯科技股份有限公司 | Method for improving scanning speed of infrared touch screen |
| JP2012208525A (en) * | 2012-07-17 | 2012-10-25 | Toyota Central R&D Labs Inc | Stationary object map generation device |
| CN106570446A (en) * | 2015-10-12 | 2017-04-19 | 腾讯科技（深圳）有限公司 | Lane line extraction method and device |
| CN108036794A (en) * | 2017-11-24 | 2018-05-15 | 华域汽车系统股份有限公司 | A kind of high accuracy map generation system and generation method |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6524892B2 (en) * | 2015-11-13 | 2019-06-05 | 株式会社デンソー | Roadway information generation system for vehicles |
| CN106525057A (en) * | 2016-10-26 | 2017-03-22 | 陈曦 | Generation system for high-precision road map |
| US10296812B2 (en) * | 2017-01-04 | 2019-05-21 | Qualcomm Incorporated | Systems and methods for mapping based on multi-journey data |
| CN109425350A (en) * | 2017-08-24 | 2019-03-05 | 阿里巴巴集团控股有限公司 | Road positioning, road switching deciding method, device, equipment and storage medium |
| CN108279670B (en) * | 2017-12-29 | 2021-12-10 | 百度在线网络技术（北京）有限公司 | Method, apparatus and computer readable medium for adjusting point cloud data acquisition trajectory |
-
2020
- 2020-01-15 CN CN202010042198.5A patent/CN113129438B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101719042A (en) * | 2010-01-14 | 2010-06-02 | 广东威创视讯科技股份有限公司 | Method for improving scanning speed of infrared touch screen |
| JP2012208525A (en) * | 2012-07-17 | 2012-10-25 | Toyota Central R&D Labs Inc | Stationary object map generation device |
| CN106570446A (en) * | 2015-10-12 | 2017-04-19 | 腾讯科技（深圳）有限公司 | Lane line extraction method and device |
| CN108036794A (en) * | 2017-11-24 | 2018-05-15 | 华域汽车系统股份有限公司 | A kind of high accuracy map generation system and generation method |
Non-Patent Citations (1)
| Title |
|---|
| 基于GPS时空轨迹的路网拓扑自动变化检测;唐炉亮等;《武汉大学学报(信息科学版) 》;第42卷(第10期);1381-1386页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113129438A (en) | 2021-07-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106767851B (en) | The collected tracing point of positioning system is matched to the method and device thereof of map | |
| CN111856521B (en) | Data processing method, device, electronic equipment and storage medium | |
| JP6302848B2 (en) | Map generation system and map generation method | |
| CN112747755B (en) | Method and device for determining road route, readable storage medium and map updating system | |
| CN107784012A (en) | A kind of update method and device of numerical map point of interest | |
| CN113587945B (en) | Vehicle driving route correction method and system under condition of road network data loss | |
| CN111750882B (en) | Method and device for correcting vehicle pose during initialization of navigation map | |
| CN113706592A (en) | Method and device for correcting positioning information, electronic equipment and storage medium | |
| CN113393519B (en) | Laser point cloud data processing method, device and equipment | |
| CN109214314B (en) | Automatic fusion matching algorithm for lane lines | |
| CN114241049B (en) | Vehicle posture determination method and device | |
| CN111488414A (en) | Road task matching method, device and equipment | |
| CN112347210B (en) | Lane center line bending error correction method and system for medium-precision map | |
| CN113129438B (en) | Method and device for improving precision of lane line and readable storage medium | |
| CN111858785A (en) | Method, device and system for matching discrete elements of map and storage medium | |
| CN111832597B (en) | Method and device for judging vehicle type | |
| CN109916417B (en) | Map establishing method, map establishing device, computer equipment and storage medium thereof | |
| CN109754630B (en) | Method and device for determining vehicle operation line | |
| CN110926498A (en) | Vehicle mileage compensation method, device, computer equipment and program product | |
| CN110334174B (en) | POS data deviation rectifying method and system | |
| CN111737237B (en) | Missing milepost data generation method, device, equipment and storage medium | |
| CN113554712A (en) | Registration method and device of automatic driving vehicle, electronic equipment and vehicle | |
| US11796342B2 (en) | Production of digital road maps by crowdsourcing | |
| CN111858624B (en) | Vehicle usage status updating method and device | |
| CN118670422A (en) | Drift correction method and device of inertial measurement unit based on piecewise compensation |
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 |