CN114359870A - Data processing method and device - Google Patents
Data processing method and device Download PDFInfo
- Publication number
- CN114359870A CN114359870A CN202111681866.XA CN202111681866A CN114359870A CN 114359870 A CN114359870 A CN 114359870A CN 202111681866 A CN202111681866 A CN 202111681866A CN 114359870 A CN114359870 A CN 114359870A
- Authority
- CN
- China
- Prior art keywords
- data
- lane line
- line data
- type sequence
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 9
- 239000012634 fragment Substances 0.000 claims abstract description 94
- 238000000034 method Methods 0.000 claims abstract description 62
- 238000012545 processing Methods 0.000 claims abstract description 33
- 230000008569 process Effects 0.000 claims abstract description 27
- 238000013467 fragmentation Methods 0.000 claims abstract description 21
- 238000006062 fragmentation reaction Methods 0.000 claims abstract description 21
- 238000004590 computer program Methods 0.000 claims description 16
- 230000004927 fusion Effects 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 6
- 238000010586 diagram Methods 0.000 description 13
- 230000007613 environmental effect Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000013507 mapping Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000013016 damping Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
Images
Landscapes
- Traffic Control Systems (AREA)
Abstract
The embodiment of the invention provides a data processing method and device, which are applied to a cloud, wherein the method comprises the following steps: acquiring target lane line data acquired and uploaded by a plurality of vehicles in the driving process; slicing the target lane line data to obtain sliced data of the target lane line data; determining type sequence data corresponding to lane line segments in the fragment data; and aligning the target lane line data based on the type sequence data. By the embodiment of the invention, the lane line data are subjected to fragmentation processing, and the lane lines are matched and aligned according to the type sequence of the fragments, so that the matching and aligning efficiency is greatly improved compared with the mode of directly matching and aligning the lane line data.
Description
Technical Field
The present invention relates to the field of map processing technologies, and in particular, to a data processing method and apparatus.
Background
In the automatic driving process of the vehicle, the accurate map can better assist automatic driving, and in order to generate the accurate map, a large amount of driving data collected by multiple vehicles can be processed to obtain a crowdsourcing map.
In practical applications, the navigation and localization of each vehicle can only maintain local characteristics due to different sensor accuracies, global consistency of the algorithm, and some inherent limitations (such as high-precision maps that are deflected). Thus, even if there is a necessary offset between different vehicles with respect to the data reported on the road. In the process of generating the crowdsourcing map, the vehicle data needs to be matched and aligned, so that an accurate crowdsourcing map is obtained.
The alignment and fusion between the vehicle data are directly determined by the matching effectiveness, and a successful matching party without failure can exert the characteristic of mass data of a crowdsourcing scheme.
Disclosure of Invention
In view of the above, it is proposed to provide a method and apparatus for data processing that overcomes or at least partially solves the above mentioned problems, comprising:
a data processing method is applied to a cloud end, and comprises the following steps:
acquiring target lane line data acquired and uploaded by a plurality of vehicles in the driving process;
slicing the target lane line data to obtain sliced data of the target lane line data;
determining type sequence data corresponding to lane line segments in the fragment data;
and aligning the target lane line data based on the type sequence data.
Optionally, said aligning the target lane line data based on the type sequence data comprises
Determining lane line quantity data corresponding to lane line segments in the segment data;
according to the lane line number data, grouping the target lane line data to obtain a first lane line group and a second lane line group, wherein the lane line number of the first lane line data in the first lane line group is larger than the lane line number of the second lane line data in the second lane line group;
aligning the first lane line data according to the type sequence data;
and aligning the second lane line data with the aligned first lane line data according to the type sequence data.
Optionally, the aligning the first lane line data according to the type sequence data includes:
in the first lane line group, determining first segment offset data corresponding to a plurality of first segment data matched with any two first lane line data according to the type sequence data;
determining first lane line offset data of any two first lane line data based on the first fragmentation offset data;
and aligning the first lane line data according to the first lane line offset data.
Optionally, the aligning the second lane line data with the aligned first lane line data according to the type sequence data includes:
determining third lane line data in the aligned first lane line data;
according to the type sequence data, second fragmentation offset data corresponding to a plurality of second fragmentation data matched with the third lane line data are determined;
determining second lane line offset data of the second lane line data and the third lane line data based on the second fragmentation offset data;
and aligning the second lane line data according to the second lane line offset data.
Optionally, the determining, according to the type sequence data, first segment offset data corresponding to a plurality of first segment data matched between any two first lane line data includes:
determining a plurality of first fragment data matched with any two first lane line data according to the type sequence data;
determining first position information of each first sliced data;
based on the first location information, first tile offset data between the matching first tile data is determined.
Optionally, the determining, according to the type sequence data, second fragmentation offset data corresponding to a plurality of second fragmentation data in which the second lane line data matches the third lane line data includes:
determining a plurality of second fragment data of which the second lane line data are matched with the third lane line data according to the type sequence data;
determining second position information of each second sliced data;
second tile offset data between the matched second tile data is determined based on the second location information.
Optionally, before slicing the target lane line data, the method further includes:
determining third position information of the target lane line data;
and denoising the target lane line data according to the third position information.
Optionally, the method further comprises:
and performing lane line fusion based on the aligned target lane line data to obtain the target crowdsourcing map.
A data processing device is applied to a cloud end and comprises:
the target lane line data acquisition module is used for acquiring target lane line data acquired and uploaded by a plurality of vehicles in the driving process;
the fragment processing module is used for carrying out fragment processing on the target lane line data to obtain fragment data of the target lane line data;
the type sequence determining module is used for determining type sequence data corresponding to the lane line segment in the fragment data;
and the lane line alignment module is used for aligning the target lane line data based on the type sequence data.
A server comprising a processor, a memory and a computer program stored on the memory and capable of running on the processor, the computer program, when executed by the processor, implementing a method of data processing as described above.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method of data processing as described above.
The embodiment of the invention has the following advantages:
according to the embodiment of the invention, the target lane line data acquired and uploaded by a plurality of vehicles in the driving process is acquired, and then the target lane line data can be sliced to obtain the fragment data of the target lane line data, so that the type sequence data corresponding to the lane line fragments in the fragment data can be determined, and the target lane line data can be aligned based on the type sequence data, so that the lane line data can be sliced, the lane lines can be aligned according to the fragment type sequence, and compared with the direct alignment of the lane line data, the efficiency of alignment is greatly improved.
Drawings
In order to more clearly illustrate the technical solution of the present invention, the drawings needed to be used in the description of the present invention will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
FIG. 1a is a flow chart illustrating steps of a method for data processing according to an embodiment of the present invention;
fig. 1b is a schematic diagram of fragmented data according to an embodiment of the present invention;
FIG. 1c is a schematic diagram of a process for constructing a crowd-sourced map according to an embodiment of the present invention;
FIG. 2a is a flow chart illustrating steps of another method for data processing according to an embodiment of the present invention;
FIG. 2b is a schematic diagram of a lane line alignment process according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a data processing apparatus according to an embodiment of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below. It is to be understood that the embodiments described are only a few embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1a, a flowchart illustrating steps of a data processing method according to an embodiment of the present invention is shown, and applied to a cloud, the method may specifically include the following steps:
the vehicle can acquire environmental data near the vehicle through a sensor of the vehicle during driving, such as lane line data, damping belt data, obstacle data (such as walls, roadblocks and the like), intersection data and the like. After the environmental data is acquired, a map may be constructed based on the environmental data.
In practical application, the sensor of the vehicle may have the problems of insufficient accuracy and the like, and environmental data acquired by one vehicle is single, so that errors are easy to occur, and a complete map is difficult to construct.
In order to construct an accurate map, data acquired by a plurality of vehicles in the driving process are uploaded to a cloud for processing, and the data uploaded by the vehicles can include target lane line data.
The target lane line data can be generated based on image data collected by a plurality of cameras of a vehicle body in the driving process of the vehicle, specifically, the vehicle can acquire a plurality of image data collected by the plurality of cameras, and then can perform splicing processing on the plurality of image data to obtain the target image data, so that the lane line data is extracted from the target image data.
In one example, after the vehicle obtains the lane line data, the lane line data may be denoised to remove too short and bent lane lines, and the lane lines with good shapes are obtained by screening.
Specifically, the lane line data acquired by the vehicle may be composed of a plurality of coordinate points, and it is determined whether the lane line has a bend according to the coordinate points, and then the bent lane line is removed, and the length of the lane line is determined according to the coordinate points, and then the lane line having the length smaller than the preset length may be removed.
By preprocessing the lane line data uploaded to the cloud, the cloud can obtain the lane line data subjected to denoising, and the lane line data processing efficiency of the cloud is improved.
In an example, the vehicle may periodically upload lane line data to update the lane line data in the cloud; the vehicle can also be provided with a preset triggering uploading event, when the vehicle detects the preset triggering uploading event, the vehicle uploads the acquired lane line data to the cloud, wherein the triggering uploading event can be an event aiming at the power-off of the vehicle, namely, when the vehicle powers off every time, the lane line data acquired in the driving process are uploaded to the cloud. It should be noted that, in the embodiment of the present invention, an event triggering upload may be set according to actual needs, and is not limited to the above example.
102, slicing the target lane line data to obtain sliced data of the target lane line data;
after the target lane line data are acquired at the cloud end, the target lane line data of each vehicle can be respectively sliced according to the advancing direction of the vehicle and preset step length, the segmented data of the target lane line data can be obtained, and lane line segments can be included in the segmented data.
In an embodiment of the present invention, before step 102, the method may further include:
determining third position information of the target lane line data; and denoising the target lane line data according to the third position information.
In practical application, the vehicle can upload the target lane line data collected during driving process to the cloud end, and the target lane line data may include bent or too short lane line data,
specifically, the target lane line data that the high in the clouds was received can comprise a plurality of coordinate points to whether can confirm the lane line according to the coordinate point and buckle, and confirm the length of lane line according to the coordinate point, and then can remove the lane line that lane line length is less than preset length.
103, determining type sequence data corresponding to the lane line segments in the fragmented data;
after the fragment data is obtained, lane line fragments may be included in the fragment data, the lane line fragments may include a plurality of lane lines, and the type sequence data may be obtained according to the lane line type and the lane line logical position (geometric position) of each lane line.
As shown in fig. 1b, the lane line data is processed in a segmented manner, and 3 dashed boxes in the figure indicate three segmented data in the lane line data, where the vehicle moves forward from left to right, and the number 1 indicates a solid line and 0 indicates a dashed line.
The fragment data of the leftmost dashed frame contains 4 lane lines, and the types of the lane lines are respectively from top to bottom: solid line, dotted line, dashed line, solid line, so that the type sequence of the sliced data may be 1001.
The fragment data of the middle dotted frame comprises 4 lane lines, and the types of the lane lines are respectively from top to bottom: solid line, dotted line, dashed line, solid line, so that the type sequence of the sliced data may be 1001.
The rightmost fragment data comprises 4 lane lines, and the types of the lane lines are respectively from top to bottom: solid line, so that the type sequence of the sliced data may be 1111.
And 104, aligning the target lane line data based on the type sequence data.
After the type sequence data of each piece of data is obtained, the target lane line data can be aligned in a matching manner according to the type sequence data.
In an embodiment of the present invention, the method further includes:
and performing lane line fusion based on the aligned target lane line data to obtain the target crowdsourcing map.
In practical application, after the target lane line data are aligned, lane line fusion can be performed, that is, a plurality of lane lines are fused into one lane line, so that target crowdsourcing map data can be obtained,
as shown in fig. 1c, the first state is a plurality of lane line data collected from top to bottom; the second state is obtained by aligning the lane line data of a plurality of vehicles; the third state is that a plurality of aligned lane lines are fused into one lane line; and the fourth state is that the connection relation is established between the lane lines, and finally, the roads in the crowdsourcing map are formed.
In an example, after the target lane line data are aligned, the position relationship of the lane line and the type of the lane line may be combined, a cluster of the lane line is obtained through clustering, and then the lane line connection relationship is extracted and calculated, so as to complete the map building.
In an example, a distributed parallel mapping may be adopted, that is, the cloud performs mapping on different areas respectively, and then the built maps are pieced together to obtain a global map. Specifically, the corresponding relationship between the middle lane lines of the two high-precision maps can be obtained by searching and matching, after optimization and alignment are performed, the geometric information of the lane lines can be re-extracted or the result of one of the two map building can be selected according to specific requirements to process the overlapping part of the two maps, and finally, the connection relationship of the lane lines is updated.
The cloud end can also establish an initial map, and then update the map of the initial map according to data uploaded by the vehicle at different time intervals.
In the embodiment of the invention, the target lane line data acquired and uploaded by a plurality of vehicles in the driving process is acquired, and then the target lane line data can be sliced to obtain the fragment data of the target lane line data, so that the type sequence data corresponding to the lane line fragments in the fragment data can be determined, and the target lane line data can be aligned based on the type sequence data, thereby realizing the purpose of greatly improving the efficiency of matching and aligning by carrying out fragment processing on the lane line data and carrying out matching and aligning of lane lines according to the type sequence of the fragment compared with the direct matching and aligning of the lane line data.
Referring to fig. 2a, a flowchart illustrating steps of another data processing method according to an embodiment of the present invention is shown, and the method is applied to a cloud, and specifically includes the following steps:
after the fragment data is obtained, lane line number data in the fragment data may be determined for lane line segments in the fragment data.
Step 204 may occur after step 202, may be concurrent with step 203, or may occur before or after step 203.
after the lane line quantity data is obtained, when the number of lane lines of a certain vehicle is large, matching is easy to perform, so that target lane line data can be grouped according to the number of lane lines of the fragment data contained in each vehicle, lane line data of which the number is greater than or equal to the preset number in the target lane line data is drawn to the first lane line group, and lane line data of which the number is less than the preset number in the target lane line data is drawn to the first lane line group.
In one example, the continuity of the lane lines also has an effect on lane line matching. After the cloud obtains the lane line quantity data, whether the lane line of each vehicle is lane line data with good continuity (namely the continuity of the front lane and the rear lane) can be determined according to the lane line quantity data, and the lane line data with good continuity can be drawn to the first lane line data.
after the first lane line group and the second lane line group are divided, the first lane line data in the first lane line group are lane lines with a large number and good continuity, and lane line matching is easy to perform, so that the first lane line data can be aligned according to type sequence data.
In an embodiment of the present invention, step 206 may include the following sub-steps:
a substep 2061 of determining, in the first lane line group, first segment offset data corresponding to a plurality of first segment data matched with any two pieces of first lane line data, based on the type sequence data;
in practical application, the cloud can be completely matched with the first lane line data in the first lane line group, that is, the lane line data of any vehicle in the first lane line group is respectively matched and aligned with the lane line data of other vehicles.
Specifically, in the first lane line group, lane line data of two vehicles are determined, first fragment data of the lane line is further determined, the first fragment data is matched according to type sequence data, the two matched first fragment data are further determined, first fragment offset data of the two first fragment data are determined, and first fragment offset data corresponding to all the first fragment data in the lane line data are calculated according to the method.
In an embodiment of the present invention, sub-step 2062 may comprise the following sub-steps:
a substep S21 of determining a plurality of first segment data matching any two first lane line data based on the type sequence data;
in practical application, the type sequence data may be used to determine whether the segments of lane line data of two vehicles match, and when matching is performed, not only matching between the segment data but also matching relationship between lane lines included in the segment data is performed, so that the first segment data matching any two first lane line data may be determined according to the type sequence data.
A substep S22 of determining first location information of each first sliced data;
after determining the matching first sliced data, first location information of each first sliced data may be determined, and the first location information may be location information of each lane line in the sliced data, which may be represented by a coordinate point.
The sub-step S23, based on the first position information, determines first slice offset data between the matched first slice data.
After the first position information is obtained, first fragment offset data between the matched first fragment data can be determined, wherein the first fragment offset data is an offset which can enable the two matched first fragment data to achieve optimal alignment, namely the two first fragment data are offset according to the first fragment offset data, and lane line data in the two first fragment data can achieve maximum superposition.
Substep 2062, determining first lane line offset data of any two first lane line data based on the first segment offset data;
after the first fragment offset data of the matched first fragment data is obtained, the lane line offset data of the two lane line data, namely the first lane line offset data, can be calculated according to the first fragment offset data, and when the two lane line data are offset according to the first lane line offset data, the lane lines can be superposed to the maximum extent.
And a substep 2063 of aligning the first lane line data according to the first lane line offset data.
And after the first lane line offset data is obtained, carrying out offset processing on the first lane line data according to the first lane line offset data, so that the first lane lines in the first lane line group are aligned.
And step 207, aligning the second lane line data with the aligned first lane line data according to the type sequence data.
After aligning the first lane line data in the first lane line group, the second lane line data may be aligned with the aligned first lane line data according to the type sequence data, so that all the lane line data are aligned.
In an embodiment of the present invention, step 207 may comprise the following sub-steps:
substep 2071, determining third lane line data in the aligned first lane line data;
in practical application, the first lane line data have many matching elements and are easy to match, so that complete matching can be performed, the number of lane lines of the second lane line data is small, the continuity is poor, and matching is not easy to perform, so that the aligned first lane line data can be used as more reliable lane line data, and the second lane line data and the reliable first lane line data are aligned.
In the alignment process, a complete matching mode is not needed, a preset number of first lane line data can be selected from the aligned first lane line data to serve as reliable lane line data used for matching with the second lane line data, and the selected data is third lane line data.
A substep 2072 of determining second fragmentation offset data corresponding to a plurality of second fragmentation data in which the second lane line data matches the third lane line data, according to the type sequence data;
after the third lane line data is determined, the second fragment data of the third lane line data and the second lane line data can be determined, the second fragment data can be matched according to the type sequence data, two matched second fragment data are determined, the second fragment offset data of the two second fragment data are determined, and the second fragment offset data corresponding to all the second fragment data in the lane line data are calculated according to the method.
In an embodiment of the present invention, sub-step 2072 may comprise:
a substep S24 of determining a plurality of second segment data in which the second lane line data matches the third lane line data, based on the type-series data;
in practical applications, the type sequence data may be used to determine whether the segments of lane line data of two vehicles match, and when matching, not only matching between the segment data but also matching relationship between lane lines included in the segment data is performed. Thus, from the type-sequential data, the second segment data in which the second lane line data matches the third lane line data can be determined.
A substep S25 of determining second location information of each second sliced data;
after determining the matching second sliced data, second position information of each second sliced data may be determined, and the second position information may be position information of each lane line in the sliced data, which may be represented by a coordinate point.
And a sub-step S26 of determining second slice offset data between the matched second slice data based on the second position information.
After the second position information is obtained, second fragment offset data between the matched second fragment data can be determined, wherein the second fragment offset data is an offset which can enable the two matched second fragment data to achieve optimal alignment, namely the two second fragment data are offset according to the second fragment offset data, and lane line data in the two second fragment data can be enabled to achieve maximum coincidence.
Substep 2073, determining second lane line offset data of the second lane line data and the third lane line data based on the second sliced offset data;
after the second fragment offset data of the matched second fragment data is obtained, the lane line offset data of the two lane line data, namely the second lane line offset data, can be calculated according to the second fragment offset data, and when the two lane line data are offset according to the second lane line offset data, the lane lines can be superposed to the maximum extent.
Substep 2074 aligns the second lane line data according to the second lane line offset data.
And after the second lane line offset data is obtained, performing offset processing on the second lane line data according to the second lane line offset data to align a second lane line in the second lane line group with the first lane line, so that all lane lines are aligned.
Fig. 2b shows the process of aligning two lane lines, and the matching alignment of three groups of patch data is shown in the figure.
In the first group, the type sequence of the lane line segment on the left side is 1001 on the left side, and the type sequence on the right side is 001, so that it can be determined that the lane lines 2-4 of the lane line segment data on the left side are respectively aligned with the lane lines 1-3 on the right side.
In the second group, the sequence of the left-side fragment data is 1001, and the type sequence of the right-side fragment data is 1001, so that the 1 st lane line to the 4 th lane line in the left-side fragment data is aligned with the 1 st lane line to the 4 th lane line in the right-side fragment data respectively.
In the third group, the type sequence of the left-side fragment data is 111, and the type of the right-side fragment data is 1111, so that two alignment modes exist, wherein the first mode is that the 1 st to 3 rd lane lines of the left-side fragment data correspond to the 1 st to 3 rd lane lines of the right-side fragment data; secondly, the 1 st to 3 rd lane lines of the left-side fragment data are aligned with the 2 nd to 4 th lane lines of the right-side fragment data, and then the alignment mode can be further determined through lane line data (for example, offset data of lane lines is obtained through coordinate positions, and an alignment mode with small offset is selected).
In the embodiment of the invention, the target lane line data acquired and uploaded by a plurality of vehicles in the driving process is acquired, and then the target lane line data can be sliced to obtain the fragment data of the target lane line data, so that the type sequence data corresponding to the lane line fragments in the fragment data can be determined, the lane line number data corresponding to the lane line fragments in the fragment data can be determined, the target lane line data can be grouped according to the lane line number data to obtain the first lane line group and the second lane line group, so that the first lane line data can be aligned according to the type sequence data, and further, the second lane line data and the aligned first lane line data can be aligned according to the type sequence data, so that the lane line grouping through the fragment data is realized, the alignment is carried out according to the grouping of the type sequences, compared with the direct matching alignment of the lane line data, the efficiency of the matching alignment is greatly improved, and the accuracy and the rapidity of the matching are ensured simultaneously by grouping processing.
It should be noted that for simplicity of description, the method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present invention is not limited by the illustrated order of acts, as some steps may occur in other orders or concurrently depending on the embodiment of the invention. Further, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred and that no particular act is required to implement the invention.
Referring to fig. 3, a schematic structural diagram of a data processing apparatus according to an embodiment of the present invention is shown, and the data processing apparatus is applied to a cloud, and specifically includes the following modules:
the target lane line data acquisition module 301 is configured to acquire target lane line data acquired and uploaded by multiple vehicles in a driving process;
the fragment processing module 302 is configured to perform fragment processing on the target lane line data to obtain fragment data of the target lane line data;
a type sequence determining module 303, configured to determine type sequence data corresponding to the lane line segment in the segment data;
a lane line alignment module 304, configured to align the target lane line data based on the type sequence data.
In an embodiment of the present invention, the lane line alignment module 304 may include:
the lane line number determining submodule is used for determining lane line number data corresponding to lane line segments in the fragment data;
the lane line grouping submodule is used for grouping the target lane line data according to the lane line quantity data to obtain a first lane line group and a second lane line group, wherein the number of lane lines of the first lane line data in the first lane line group is larger than that of the second lane line data in the second lane line group;
the first lane line alignment sub-module is used for aligning the first lane line data according to the type sequence data;
and the second lane line alignment submodule is used for aligning the second lane line data with the aligned first lane line data according to the type sequence data.
In an embodiment of the present invention, the first lane line alignment sub-module may include:
a first fragmentation offset determination unit, configured to determine, in the first lane line group, first fragmentation offset data corresponding to a plurality of first fragmentation data matched by any two pieces of first lane line data according to the type sequence data;
a first lane line offset determination unit configured to determine first lane line offset data of any two first lane line data based on the first segment offset data;
and the first alignment unit is used for aligning the first lane line data according to the first lane line offset data.
In an embodiment of the present invention, the second lane alignment sub-module may include:
a third lane line determining unit, configured to determine third lane line data in the aligned first lane line data;
a second fragmentation offset determination unit, configured to determine, according to the type sequence data, second fragmentation offset data corresponding to a plurality of second fragmentation data in which the second lane line data matches the third lane line data;
a second lane line offset determination unit configured to determine second lane line offset data of the second lane line data and the third lane line data based on the second sliced offset data;
and the second alignment unit is used for aligning the second lane line data according to the second lane line offset data.
In an embodiment of the present invention, the first tile offset determining unit may include:
a first segment determining subunit, configured to determine, according to the type sequence data, a plurality of first segment data in which any two first lane line data match;
a first position determination subunit operable to determine first position information of each of the first sliced data;
a first slice offset determination subunit configured to determine first slice offset data between the matched first slice data based on the first position information.
In an embodiment of the present invention, the second tile offset determining unit may include:
a second segment determining subunit, configured to determine, according to the type sequence data, a plurality of second segment data in which the second lane line data matches the third lane line data;
a second position determination subunit operable to determine second position information of each of the second sliced data;
a second slice offset determination subunit configured to determine second slice offset data between the matched second slice data based on the second position information.
In an embodiment of the present invention, the method further includes:
the lane position information determining module is used for determining third position information of the target lane line data;
and the denoising module is used for denoising the target lane line data according to the third position information.
In an embodiment of the present invention, the apparatus further includes:
and the crowdsourcing map generation module is used for carrying out lane line fusion based on the aligned target lane line data to obtain a target crowdsourcing map.
According to the embodiment of the invention, the target lane line data acquired and uploaded by a plurality of vehicles in the driving process is acquired, and then the target lane line data can be sliced to obtain the fragment data of the target lane line data, so that the type sequence data corresponding to the lane line fragments in the fragment data can be determined, and the target lane line data can be aligned based on the type sequence data, so that the lane line data can be sliced, the lane lines can be aligned according to the fragment type sequence, and compared with the direct alignment of the lane line data, the efficiency of alignment is greatly improved.
An embodiment of the present invention also provides a server, which may include a processor, a memory, and a computer program stored on the memory and capable of running on the processor, and when executed by the processor, the computer program implements the method for processing data as above.
An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the steps of the above data processing method.
For the device embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment.
The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing terminal to cause a series of operational steps to be performed on the computer or other programmable terminal to produce a computer implemented process such that the instructions which execute on the computer or other programmable terminal provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications of these embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the embodiments of the invention.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or terminal that comprises the element.
The method and apparatus for data processing provided above are described in detail, and a specific example is applied herein to illustrate the principles and embodiments of the present invention, and the above description of the embodiment is only used to help understand the method and core ideas of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (11)
1. A data processing method is applied to a cloud end, and comprises the following steps:
acquiring target lane line data acquired and uploaded by a plurality of vehicles in the driving process;
slicing the target lane line data to obtain sliced data of the target lane line data;
determining type sequence data corresponding to lane line segments in the fragment data;
and aligning the target lane line data based on the type sequence data.
2. The method of claim 1, wherein aligning the target lane line data based on the type sequence data comprises
Determining lane line quantity data corresponding to lane line segments in the segment data;
according to the lane line number data, grouping the target lane line data to obtain a first lane line group and a second lane line group, wherein the lane line number of the first lane line data in the first lane line group is larger than the lane line number of the second lane line data in the second lane line group;
aligning the first lane line data according to the type sequence data;
and aligning the second lane line data with the aligned first lane line data according to the type sequence data.
3. The method of claim 2, wherein said aligning said first lane line data according to said type sequence data comprises:
in the first lane line group, determining first segment offset data corresponding to a plurality of first segment data matched with any two first lane line data according to the type sequence data;
determining first lane line offset data of any two first lane line data based on the first fragmentation offset data;
and aligning the first lane line data according to the first lane line offset data.
4. The method of claim 2, wherein aligning the second lane line data with the aligned first lane line data according to the type sequence data comprises:
determining third lane line data in the aligned first lane line data;
according to the type sequence data, second fragmentation offset data corresponding to a plurality of second fragmentation data matched with the third lane line data are determined;
determining second lane line offset data of the second lane line data and the third lane line data based on the second fragmentation offset data;
and aligning the second lane line data according to the second lane line offset data.
5. The method of claim 3, wherein the determining, from the type sequence data, first segment offset data corresponding to a plurality of first segment data matched with any two first lane line data comprises:
determining a plurality of first fragment data matched with any two first lane line data according to the type sequence data;
determining first position information of each first sliced data;
based on the first location information, first tile offset data between the matching first tile data is determined.
6. The method according to claim 4, wherein the determining, according to the type sequence data, second fragmentation offset data corresponding to a plurality of second fragmentation data in which the second lane line data matches the third lane line data includes:
determining a plurality of second fragment data of which the second lane line data are matched with the third lane line data according to the type sequence data;
determining second position information of each second sliced data;
second tile offset data between the matched second tile data is determined based on the second location information.
7. The method of any one of claims 1 to 6, further comprising, prior to slicing the target lane line data:
determining third position information of the target lane line data;
and denoising the target lane line data according to the third position information.
8. The method of any of claims 1 to 6, further comprising:
and performing lane line fusion based on the aligned target lane line data to obtain the target crowdsourcing map.
9. An apparatus for data processing, applied to a cloud, the apparatus comprising:
the target lane line data acquisition module is used for acquiring target lane line data acquired and uploaded by a plurality of vehicles in the driving process;
the fragment processing module is used for carrying out fragment processing on the target lane line data to obtain fragment data of the target lane line data;
the type sequence determining module is used for determining type sequence data corresponding to the lane line segment in the fragment data;
and the lane line alignment module is used for aligning the target lane line data based on the type sequence data.
10. A server comprising a processor, a memory and a computer program stored on the memory and capable of running on the processor, the computer program, when executed by the processor, implementing a method of data processing according to any one of claims 1 to 8.
11. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out a method of data processing according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111681866.XA CN114359870A (en) | 2021-12-27 | 2021-12-27 | Data processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111681866.XA CN114359870A (en) | 2021-12-27 | 2021-12-27 | Data processing method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114359870A true CN114359870A (en) | 2022-04-15 |
Family
ID=81106102
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111681866.XA Pending CN114359870A (en) | 2021-12-27 | 2021-12-27 | Data processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114359870A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117058647A (en) * | 2023-10-13 | 2023-11-14 | 腾讯科技（深圳）有限公司 | Lane line processing method, device and equipment and computer storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| US20200355506A1 (en) * | 2018-02-01 | 2020-11-12 | Denso Corporation | Image data generation device for vehicle, travel trajectory data generation system, and storage medium |
| CN112363192A (en) * | 2020-09-29 | 2021-02-12 | 蘑菇车联信息科技有限公司 | Lane positioning method and device, vehicle, electronic equipment and storage medium |
| CN112835363A (en) * | 2020-12-29 | 2021-05-25 | 武汉中海庭数据技术有限公司 | Method and device for controlling flow of large-range crowdsourcing map lane line data fusion |
| CN112985404A (en) * | 2021-02-09 | 2021-06-18 | 广州小鹏自动驾驶科技有限公司 | Method, device, equipment and medium for generating crowdsourcing map of parking lot |
| CN113435427A (en) * | 2021-08-27 | 2021-09-24 | 湖北亿咖通科技有限公司 | Method and device for aggregating lane lines |
-
2021
- 2021-12-27 CN CN202111681866.XA patent/CN114359870A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200355506A1 (en) * | 2018-02-01 | 2020-11-12 | Denso Corporation | Image data generation device for vehicle, travel trajectory data generation system, and 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 |
| CN112363192A (en) * | 2020-09-29 | 2021-02-12 | 蘑菇车联信息科技有限公司 | Lane positioning method and device, vehicle, electronic equipment and storage medium |
| CN112835363A (en) * | 2020-12-29 | 2021-05-25 | 武汉中海庭数据技术有限公司 | Method and device for controlling flow of large-range crowdsourcing map lane line data fusion |
| CN112985404A (en) * | 2021-02-09 | 2021-06-18 | 广州小鹏自动驾驶科技有限公司 | Method, device, equipment and medium for generating crowdsourcing map of parking lot |
| CN113435427A (en) * | 2021-08-27 | 2021-09-24 | 湖北亿咖通科技有限公司 | Method and device for aggregating lane lines |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117058647A (en) * | 2023-10-13 | 2023-11-14 | 腾讯科技（深圳）有限公司 | Lane line processing method, device and equipment and computer storage medium |
| CN117058647B (en) * | 2023-10-13 | 2024-01-23 | 腾讯科技（深圳）有限公司 | Lane line processing method, device and equipment and computer storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3505869B1 (en) | Method, apparatus, and computer readable storage medium for updating electronic map | |
| US11094198B2 (en) | Lane determination method, device and storage medium | |
| CN108334523B (en) | Road scene map construction method and device | |
| JP2015148601A (en) | System and method for mapping, localization and pose correction | |
| CN111830953A (en) | Vehicle self-positioning method, device and system | |
| CN116255992A (en) | Method and device for simultaneously positioning and mapping | |
| CN109313809B (en) | Image matching method, device and storage medium | |
| WO2024012212A1 (en) | Environmental perception method, domain controller, storage medium, and vehicle | |
| CN114111775B (en) | Multi-sensor fusion positioning method and device, storage medium and electronic equipment | |
| CN111274847A (en) | Positioning method | |
| CN114372068A (en) | Map updating method and map updating device | |
| CN109059946B (en) | Vehicle route acquisition method, storage medium, and electronic device | |
| CN114359870A (en) | Data processing method and device | |
| CN111337039B (en) | Map data acquisition method, device and system for congested road section and storage medium | |
| CN114234986A (en) | Map data processing method and device | |
| CN113448973B (en) | Map data updating method, server, vehicle machine and storage medium | |
| CN114111817A (en) | Vehicle positioning method and system based on SLAM map and high-precision map matching | |
| CN114018240A (en) | Map data processing method and device | |
| CN114485689B (en) | Road segment segmentation method and device for constructing high-precision map by utilizing crowdsourcing data | |
| CN117726533B (en) | Edge splicing processing method and related device | |
| CN111461982B (en) | Method and apparatus for splice point cloud | |
| CN111829537B (en) | Vehicle positioning method and device | |
| CN117078566B (en) | Map data processing method and related equipment | |
| CN114359872A (en) | Lane positioning method and device and electronic equipment | |
| CN114120279A (en) | Traffic signboard updating method, system, electronic equipment and storage medium |
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 |