CN113295175A - Map data correction method and device - Google Patents
Map data correction method and device Download PDFInfo
- Publication number
- CN113295175A CN113295175A CN202110484869.8A CN202110484869A CN113295175A CN 113295175 A CN113295175 A CN 113295175A CN 202110484869 A CN202110484869 A CN 202110484869A CN 113295175 A CN113295175 A CN 113295175A
- Authority
- CN
- China
- Prior art keywords
- map data
- determining
- sampling point
- sampling
- vector
- 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
- 238000000034 method Methods 0.000 title claims abstract description 73
- 238000012937 correction Methods 0.000 title claims abstract description 16
- 238000005070 sampling Methods 0.000 claims abstract description 175
- 230000000007 visual effect Effects 0.000 claims abstract description 70
- 230000008569 process Effects 0.000 claims abstract description 33
- 238000004590 computer program Methods 0.000 claims description 16
- 230000004048 modification Effects 0.000 claims description 12
- 238000012986 modification Methods 0.000 claims description 12
- 238000003860 storage Methods 0.000 claims description 6
- 238000010586 diagram Methods 0.000 description 10
- 238000013507 mapping Methods 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 238000012952 Resampling Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004040 coloring Methods 0.000 description 1
- 238000013524 data verification Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000002715 modification method Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 230000016776 visual perception Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/28—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
- G01C21/30—Map- or contour-matching
- G01C21/32—Structuring or formatting of map data
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C25/00—Manufacturing, calibrating, cleaning, or repairing instruments or devices referred to in the other groups of this subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
Landscapes
- Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Manufacturing & Machinery (AREA)
- Instructional Devices (AREA)
Abstract
The embodiment of the invention provides a method and a device for correcting map data, wherein the method comprises the following steps: acquiring first map data constructed by the vehicle based on visual data acquired in the driving process and second map data constructed by the vehicle based on laser data acquired in the driving process; sampling in the first map data, determining a first sampling point, and determining a second sampling point related to the first sampling point in the second map data; and determining error information of the first map data according to the first sampling point and the second sampling point, and correcting the first map data according to the error information. According to the embodiment of the invention, the purpose that the error is accurately counted through the alignment of the first map data and the second map data is realized, and the error is fed back to the first map for correction, so that the visual map is optimized.
Description
Technical Field
The invention relates to the technical field of vehicles, in particular to a method and a device for correcting map data.
Background
In the vehicle driving process, the image of the surrounding environment can be collected through the camera of the vehicle body, and then the visual map of the vehicle driving environment can be constructed through the collected image, and a driver can obtain more efficient and convenient driving guide through the visual map.
However, when the vehicle-mounted camera shoots an image, the edge of the camera is greatly distorted, and the distortion changes along with the change of shooting distance, so that the accuracy of the constructed visual map is affected.
Meanwhile, the visual map is mainly built based on the Bayesian theory, and different area updating parameters are optimized, so that an efficient method cannot be found to count the map building precision to feed back the map building algorithm, and the generated visual map is insufficient in precision.
Disclosure of Invention
In view of the above, a method and apparatus for map data modification is proposed to overcome the above problems or at least partially solve the above problems, comprising:
a method of map data modification, the method comprising:
acquiring first map data constructed by the vehicle based on visual data acquired in the driving process and second map data constructed by the vehicle based on laser data acquired in the driving process;
sampling in the first map data, determining a first sampling point, and determining a second sampling point associated with the first sampling point in the second map data;
and determining error information of the first map data according to the first sampling point and the second sampling point, and correcting the first map data according to the error information.
Optionally, the sampling in the first map data and determining a first sampling point include:
determining a visual center point of the vehicle in first map data;
determining one or more sampling rays passing through the visual center point;
and determining a first sampling point according to the sampling ray.
Optionally, the determining a first sampling point according to the sampling ray includes:
determining, in the first map data, one or more candidate obstacle points through which the sampled ray passes;
determining a first sampling point among the one or more candidate obstacle points.
Optionally, the determining error information of the first map data according to the first sampling point and the second sampling point includes:
determining a first vector generated by the visual central point and the first sampling point and a second vector generated by the visual central point and the second sampling point;
error information of the first map data is determined from the first vector and the second vector.
Optionally, the determining error information of the determined first map data according to the first vector and the second vector includes:
determining a target distance of the first sampling point and the second sampling point;
determining a vector length difference of the first vector and the second vector, and an arc length between the first vector and the second vector;
and determining error information of the first map data according to the target distance, the vector length difference and the arc length.
Optionally, the first map data includes a first time stamp, the second map data includes a second time stamp, and before the sampling in the first map data, the method further includes:
aligning the first map data and the second map data according to the first timestamp and the second timestamp;
and converting the coordinate system of the second map data according to the coordinate system of the first map data.
Optionally, the angles between the plurality of sampled rays are equal.
An apparatus for map data modification, the apparatus comprising:
the map building module is used for obtaining first map data built by the vehicle based on visual data collected in the driving process and second map data built by the vehicle based on laser data collected in the driving process;
the sampling point determining module is used for sampling in the first map data, determining a first sampling point and determining a second sampling point related to the first sampling point in the second map data;
and the error correction module is used for determining the error information of the first map data according to the first sampling point and the second sampling point and correcting the first map data according to the error information.
A vehicle comprising a processor, a memory and a computer program stored on the memory and operable on the processor, the computer program when executed by the processor implementing a method of map data correction 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 map data modification as described above.
The embodiment of the invention has the following advantages:
according to the embodiment of the invention, the first map data constructed by the vehicle based on the visual data acquired in the driving process and the second map data constructed by the vehicle based on the laser data acquired in the driving process are acquired, sampling is carried out in the first map data, the first sampling point is determined, the second sampling point related to the first sampling point is determined in the second map data, the error information of the first map data is determined according to the first sampling point and the second sampling point, the first map data is corrected according to the error information, the aim of aligning the first map data and the second map data is achieved, the error is accurately counted, the error is fed back to the first map for correction, and the visual map is optimized.
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. 1 is a flowchart illustrating steps of a method for modifying map data according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating steps of another method for map data modification according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an apparatus for correcting map data 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. 1, a flowchart illustrating steps of a method for correcting map data according to an embodiment of the present invention is shown, which may specifically include the following steps:
in the driving process of a vehicle, visual data and laser data can be collected through vehicle-mounted equipment, wherein the vehicle-mounted equipment can be sensor equipment such as a camera and a laser radar. For example, visual data may be collected by a camera of the vehicle body, while laser data may be collected by a lidar of the vehicle body.
After the vehicle travels for a period of time, first map data can be constructed in real time based on the collected visual data, meanwhile, second map data can be constructed in real time based on the collected laser data, the first map data and the second map data constructed in real time are stored at the vehicle end or the cloud end, and when a preset trigger event is detected, the latest first map data and the latest second map data can be acquired from the vehicle end or the cloud end.
The preset trigger event may be an event that a user starts first map data correction, an event that a user starts first map data error statistics, an event that the first map data is periodically and automatically corrected, and the like.
In an example, a container may be provided for storing visual data and laser data collected during the driving process of the vehicle, the size of the container may be adjusted according to the user's requirement, and when the container is stored to a preset capacity, the first map data and the second map data may be triggered to start to be constructed.
Then, with the continuous update of the visual data and the laser data, a map construction period can be set, so that a map can be constructed according to a preset period.
102, sampling in the first map data, determining a first sampling point, and determining a second sampling point associated with the first sampling point in the second map data;
after the first map data and the second map data are obtained, sampling can be performed in the first map data, a first sampling point is determined, and a second sampling point associated with the first sampling point is determined in the second map data, wherein the first sampling point and the second sampling point are map points corresponding to a certain position in reality in the first map data and the second map data respectively.
In one example, the first sampling point may be an obstacle point closest to the vehicle, which has the greatest influence on the travel trajectory of the vehicle. When the accuracy of the first map data is low, the error of the first map data at the sampling point may be large, and thus, the vehicle is liable to be involved in an accident while traveling according to the first map data.
By calculating the error for the first sampling point, at least the error at the sampling point in the first map data can be corrected, thereby ensuring the safety of the vehicle.
In an embodiment of the present invention, the first map data includes a first timestamp, the second map data includes a second timestamp, and before step 102, the method may further include the following steps:
step S101, aligning the first map data and the second map data according to the first time stamp and the second time stamp;
in practical applications, the first map data and the second map data respectively construct a map, which may cause the coordinate systems of the two maps to be different, and thus, error calculation is not convenient to be directly performed.
In the step of collecting the visual data, each frame of visual data may include visual point coordinate data in visual sensor coordinates and a corresponding timestamp, so that, after the visual data is constructed into first map data, the obtained first map data may include the first timestamp; in the collected laser data, the laser data may include data that is coordinates of a laser point in a laser sensor coordinate system, and a corresponding time stamp, so that, after the laser data is constructed into the second map data, the acquired second map data may include the second time stamp.
After the first timestamp and the second timestamp are obtained, a corresponding relationship between the first timestamp and the second timestamp may be determined, so as to align the first map data and the second map data.
In an example, the first timestamp can be a timestamp associated with the current odometer, a corresponding first timestamp can be found from the second timestamp, and the other timestamps can be interpolated for the odometer based on the already corresponding timestamp.
For example, the odometer interpolation process: in the second map data, the odometer position corresponding to the timestamp 6 point is 0km as the starting point, the odometer position corresponding to the timestamp 7 point is 1km as the starting point, and if the speed of the vehicle is 1km/h, the timestamp of the second map data is 6: 30 deg., so the odometer location at the second map data should be exactly 0.5 km.
And step S102, converting the coordinate system of the second map data according to the coordinate system of the first map data.
After the map data are aligned, the coordinate system of the second map data may be transformed according to the coordinate system of the first map data, so that the coordinate systems of the first map data and the transformed second map data are consistent. Thereby facilitating subsequent sampling and calculating errors in the sampled data.
After the map data are respectively sampled, the error information of the first map data can be determined through the first sampling point and the second sampling point, so that the first map data can be corrected according to the error information, and the first map data with higher precision can be obtained.
Because the edge distortion is serious when the camera collects the visual data, the precision of the first map data can change along with the distance and the angle, and the laser data has the advantage of stable direction, thereby taking the second map data as true value data, calculating the error information of the first map data,
in an example, after determining the error information, it may be determined whether the error information is within a preset error range, and when it is determined that the error information is within the preset error range, it may be determined that the first sampling point matches the second sampling point.
The method comprises the steps of determining error information of a plurality of sampling points on first map data and second map data, determining a plurality of first sampling points which can be matched, in the first map data, connecting or coloring the matched first sampling points, and displaying the first map data, wherein the more the first sampling points which can be matched in the first map data, the higher the precision of the first map data can be determined.
By performing statistical analysis on the error, the accuracy of the first map data can be determined, and when the accuracy is low, the adjustment parameter of the first map data is determined according to the error information, wherein the adjustment parameter may be an adjustment parameter associated with a mapping algorithm in the first map data.
After the parameters are adjusted, the first map data may be corrected according to the adjusted parameters, so as to obtain the corrected first map data. Specifically, the first map data may be reconstructed in accordance with the adjustment parameter.
After the corrected first map data is obtained, the steps can be repeated, the error and the precision of the corrected first map data are calculated, whether the precision of the corrected first map data meets the preset requirement or not is determined, when the precision meets the preset requirement, the first map data is output, and when the precision does not meet the preset requirement, the correction is continued until the corrected first map data meets the preset requirement.
By resampling the laser mapping, the visual perception mapping evaluation index close to the vehicle body end can be optimized, and the mapping result is fed back to the mapping algorithm, so that the visual map is continuously optimized.
In one example, the difference of the algorithm-constructed map may also be caused by internal and external parameters of the installation positions of the perception cameras at different azimuth angles of different vehicles, the models of the cameras, engineering installation errors and the like.
In order to avoid the difference of the algorithm in map construction, the map can be sampled by regions, specifically, the specific steps of determining the first sampling point and the second sampling point are as follows:
step S11, determining a visual center point in the first map data;
step S12, constructing a plurality of fan-shaped areas by taking the visual central point as an origin;
step S13, equally dividing each sector area to obtain a plurality of sub-areas;
step S14, sampling in each sub-region, determining a first sample point, and determining a second sample point associated with the first sample point in the second map data.
In practical application, in order to avoid camera errors, a visual center point of first map data can be used as an origin to construct sector areas in different directions, the sector areas are divided equidistantly to obtain a plurality of sub-areas, each divided sub-area is sampled respectively to determine a first sampling point, and then a second sampling point associated with the first sampling point can be determined in second map data, so that error information of the first map data can be determined according to the first sampling point and the second sampling point, an adjustment parameter of the first map data can be determined according to the error information, the first map data can be corrected according to the adjustment parameter, and finally the high-precision first map data can be obtained.
In the embodiment of the invention, by acquiring first map data constructed by a vehicle based on visual data acquired in the driving process and second map data constructed by the vehicle based on laser data acquired in the driving process, sampling is carried out in the first map data, a first sampling point and a sampling point are determined, a second sampling point associated with the first sampling point is determined in the second map data, error information of the first map data is determined according to the first sampling point and the second sampling point, the first map data is corrected according to the error information, the aim of accurately counting errors by aligning the first map data with the second map data is realized, the errors are fed back to the first map for correction, and the visual map is optimized.
Referring to fig. 2, a flowchart illustrating steps of another map data modification method according to an embodiment of the present invention is shown, which may specifically include the following steps:
after the first map data and the second map data are obtained, in the first map data, the relation between the vehicle body pose and the map is that the center point of the vehicle head is in the center of the visual map, so that the visual center point of the vehicle, namely the center point of the vehicle head, can be determined in the first map data.
in one embodiment of the present invention, the angles between the plurality of sampled rays are equal.
After the visual center point is determined, one or more sampling rays passing through the visual center point can be determined around the visual center point, so that sampling can be performed along the periphery of the vehicle, and the sampling point close to the vehicle body end is determined.
When a plurality of rays exist, angles among the plurality of sampling rays can be equal, so that the sampling rays can be ensured to completely cover the surrounding environment of the vehicle, and the density of the sampling rays can be correspondingly adjusted according to the resolution of the grid map when the sampling rays are determined.
And 204, determining a first sampling point according to the sampling ray, and determining a second sampling point associated with the first sampling point in the second map data.
After the sampling ray is determined, sampling points may be determined along the sampling ray. The second map data is constructed by laser data, and when a sampling point is selected, an obstacle point on a sampling ray can be selected as the sampling point. In other embodiments, the map feature point on the sampling ray may also be selected as the first sampling point.
After the first sample points are determined, second sample points associated with the first sample points may also be determined in the second map data.
In an embodiment of the present invention, the determining a first sampling point according to the sampling ray includes:
determining, in the first map data, one or more candidate obstacle points through which the sampled ray passes; determining a first sampling point among the one or more candidate obstacle points.
In practical application, the process of determining the first sampling point is as follows:
in the first map data, the sampling ray may pass through one or more obstacle points, and in the second map data, the obstacle points determined under the laser data are relatively accurate, so that the first sampling point may be determined among the one or more obstacle points on the sampling ray.
In one example, an obstacle point closest to the visual center point may be determined among the plurality of obstacle points, and the point may be taken as a first sampling point, which is a perceived obstacle closest to the vehicle body in the surrounding environment of the vehicle.
In an embodiment of the present invention, the determining error information of the first map data according to the first sample point and the second sample point includes:
step S01, determining a first vector generated by the visual central point and the first sampling point, and a second vector generated by the visual central point and the second sampling point;
after the visual center point is determined, the first sampling point and the second sampling point may respectively form a first vector and a second vector with the visual center point, where the first vector may be a vector from the visual center point to the first sampling point, and the second vector may be a vector from the visual center point to the second sampling point.
Step S02, determining error information of the first map data according to the first vector and the second vector.
After determining the first vector and the second vector, a degree of matching between the visual point of the first map data and the true point in the second map data may be determined according to the first vector and the second vector, so that error information of the first map data may be determined.
In an embodiment of the present invention, the determining the error information of the determined first map data according to the first vector and the second vector includes:
determining a target distance of the first sampling point and the second sampling point; determining a vector length difference of the first vector and the second vector, and an arc length between the first vector and the second vector; and determining error information of the first map data according to the target distance, the vector length difference and the arc length.
In practical application, the first sampling point, the second sampling point and the visual center point can form a closed area, the first map data error is calculated, and the nearest real-valued laser point can be well matched through visual observation and actual data verification.
In the error calculation, three important parameters need to be determined: (1) a target distance of the first sampling point and the second sampling point; (2) a vector length difference of the first vector and the second vector; (3) the arc length between the first vector and the second vector, i.e. the arc length between the first sampling point and the second sampling point.
After the target distance, the vector length difference and the arc length are determined, the values of the target distance, the vector difference and the arc length are added to obtain an error value of the first map data, the error value is compared with a preset error range, when the error is within the preset error range, the fact that the visual point of the first map data is matched with the laser point of the second map data can be determined, the accuracy of the first map data is determined according to a matching result, when the accuracy of the first map data is too low, the first map data can be corrected according to the counted error, and the first map data with higher accuracy is obtained.
In the embodiment of the invention, by acquiring first map data constructed by a vehicle based on visual data acquired in the driving process and second map data constructed by the vehicle based on laser data acquired in the driving process, determining a visual center point of the vehicle in the first map data, determining one or more sampling rays passing through the visual center point, determining a first sampling point according to the sampling rays, determining a second sampling point associated with the first sampling point in the second map data, determining error information of the first map data according to the first sampling point and the second sampling point, and correcting the first map data according to the error information, the aim of accurately counting errors by the first map data and the second map data is realized, and the errors are fed back to the first map for correction, and optimizing the visual map.
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 in accordance with the embodiments of the present 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 device for correcting map data according to an embodiment of the present invention is shown, which may specifically include the following modules:
the map construction module 301 is configured to obtain first map data constructed by the vehicle based on visual data acquired in a driving process and second map data constructed by the vehicle based on laser data acquired in the driving process;
a sampling point determining module 302, configured to sample in the first map data, determine a first sampling point, and determine a second sampling point associated with the first sampling point in the second map data;
an error correction module 303, configured to determine error information of the first map data according to the first sample data and the second sample data, and correct the first map data according to the error information.
In an embodiment of the present invention, the sampling point determining module 302 may include:
the visual center point determining submodule is used for determining the visual center point of the vehicle in the first map data;
a sampled ray determination submodule for determining one or more sampled rays passing through the visual center point;
and the sampling point determination sub-module is used for determining a first sampling point according to the sampling ray.
In an embodiment of the present invention, the sampling point determination sub-module may include:
a candidate obstacle point determination unit configured to determine one or more candidate obstacle points through which the sampling ray passes in the first map data;
and the sampling point determining unit is used for determining a first sampling point in the one or more candidate obstacle points.
In an embodiment of the present invention, the error correction module 303 may include:
the vector generation sub-module is used for determining a first vector generated by the visual central point and the first sampling point and a second vector generated by the visual central point and the second sampling point;
and the error information determining submodule is used for determining the error information of the first map data according to the first vector and the second vector.
In an embodiment of the present invention, the error information determining sub-module may include:
a target distance determination unit for determining a target distance of the first sampling point and the second sampling point;
a vector length difference and arc length determination unit for determining a vector length difference of the first vector and the second vector and an arc length between the first vector and the second vector;
and the error determining unit is used for determining the error information of the first map data according to the target distance, the vector length difference and the arc length.
In an embodiment of the present invention, the apparatus further includes:
a timestamp alignment module for aligning the first map data and the second map data according to the first timestamp and the second timestamp;
and the coordinate system conversion module is used for converting the coordinate system of the second map data according to the coordinate system of the first map data.
In one embodiment of the present invention, the angles between the plurality of sampled rays are equal.
In the embodiment of the invention, the method comprises the steps of acquiring first map data constructed by a vehicle based on visual data acquired in the driving process and second map data constructed by the vehicle based on laser data acquired in the driving process, sampling in the first map data, determining a first sampling point, determining a second sampling point associated with the first sampling point in the second map data, determining error information of the first map data according to the first sampling point and the second sampling point, and correcting the first map data according to the error information, so that the aim matching of the first map data and the second map data is realized, the error is accurately counted, the error is fed back to a first map for correction, and the visual map is optimized.
An embodiment of the present invention also provides a vehicle, which may include a processor, a memory, and a computer program stored on the memory and capable of running on the processor, wherein the computer program, when executed by the processor, implements the map data correction method as described 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 above map data correction 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 map data modification provided above are described in detail, and the principle and the implementation of the present invention are explained in detail by applying specific examples, and the above description of the embodiments is only used to help understanding the method and the core idea 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 (10)
1. A method of map data modification, the method comprising:
acquiring first map data constructed by the vehicle based on visual data acquired in the driving process and second map data constructed by the vehicle based on laser data acquired in the driving process;
sampling in the first map data, determining a first sampling point, and determining a second sampling point associated with the first sampling point in the second map data;
and determining error information of the first map data according to the first sampling point and the second sampling point, and correcting the first map data according to the error information.
2. The method of claim 1, wherein sampling in the first map data to determine a first sample point comprises:
determining a visual center point of the vehicle in first map data;
determining one or more sampling rays passing through the visual center point;
and determining a first sampling point according to the sampling ray.
3. The method of claim 2, wherein determining a first sample point from the sampled ray comprises:
determining, in the first map data, one or more candidate obstacle points through which the sampled ray passes;
determining a first sampling point among the one or more candidate obstacle points.
4. The method of claim 2 or 3, wherein determining error information for the first map data from the first and second sample points comprises:
determining a first vector generated by the visual central point and the first sampling point and a second vector generated by the visual central point and the second sampling point;
error information of the first map data is determined from the first vector and the second vector.
5. The method of claim 4, wherein determining the error information for the determined first map data based on the first vector and the second vector comprises:
determining a target distance of the first sampling point and the second sampling point;
determining a vector length difference of the first vector and the second vector, and an arc length between the first vector and the second vector;
and determining error information of the first map data according to the target distance, the vector length difference and the arc length.
6. The method of claim 1, wherein the first map data includes a first timestamp and the second map data includes a second timestamp, and further comprising, prior to said sampling in the first map data:
aligning the first map data and the second map data according to the first timestamp and the second timestamp;
and converting the coordinate system of the second map data according to the coordinate system of the first map data.
7. The method of claim 2, wherein the angles between the plurality of sampled rays are equal.
8. An apparatus for map data modification, the apparatus comprising:
the map building module is used for obtaining first map data built by the vehicle based on visual data collected in the driving process and second map data built by the vehicle based on laser data collected in the driving process;
the sampling point determining module is used for sampling in the first map data, determining a first sampling point and determining a second sampling point related to the first sampling point in the second map data;
and the error correction module is used for determining the error information of the first map data according to the first sampling point and the second sampling point and correcting the first map data according to the error information.
9. A vehicle comprising a processor, a memory and a computer program stored on the memory and executable on the processor, the computer program, when executed by the processor, implementing a method of map data modification as claimed in any one of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out a method of map data modification according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110484869.8A CN113295175A (en) | 2021-04-30 | 2021-04-30 | Map data correction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110484869.8A CN113295175A (en) | 2021-04-30 | 2021-04-30 | Map data correction method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113295175A true CN113295175A (en) | 2021-08-24 |
Family
ID=77320716
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110484869.8A Pending CN113295175A (en) | 2021-04-30 | 2021-04-30 | Map data correction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113295175A (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108337915A (en) * | 2017-12-29 | 2018-07-27 | 深圳前海达闼云端智能科技有限公司 | Three-dimensional builds drawing method, device, system, high in the clouds platform, electronic equipment and computer program product |
| CN108958266A (en) * | 2018-08-09 | 2018-12-07 | 北京智行者科技有限公司 | A kind of map datum acquisition methods |
| CN109084786A (en) * | 2018-08-09 | 2018-12-25 | 北京智行者科技有限公司 | A kind of processing method of map datum |
| CN109783593A (en) * | 2018-12-27 | 2019-05-21 | 驭势科技（北京）有限公司 | A kind of map updating system can be used for automatic Pilot and method |
| KR20190131402A (en) * | 2018-05-16 | 2019-11-26 | 주식회사 유진로봇 | Moving Object and Hybrid Sensor with Camera and Lidar |
| US20200124421A1 (en) * | 2018-10-19 | 2020-04-23 | Samsung Electronics Co., Ltd. | Method and apparatus for estimating position |
| US20200158869A1 (en) * | 2018-11-19 | 2020-05-21 | Elmira Amirloo Abolfathi | System, device and method of generating a high resolution and high accuracy point cloud |
| CN111590595A (en) * | 2020-06-30 | 2020-08-28 | 深圳市银星智能科技股份有限公司 | Positioning method and device, mobile robot and storage medium |
| CN111735439A (en) * | 2019-03-22 | 2020-10-02 | 北京京东尚科信息技术有限公司 | Map construction method, map construction device and computer-readable storage medium |
| CN111736613A (en) * | 2020-07-22 | 2020-10-02 | 上海康莫巴智能科技有限公司 | Intelligent driving control method, device and system and storage medium |
| CN112213738A (en) * | 2020-09-28 | 2021-01-12 | 劢微机器人科技(深圳)有限公司 | Map construction method, device and equipment for automated guided vehicle and storage medium |
-
2021
- 2021-04-30 CN CN202110484869.8A patent/CN113295175A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108337915A (en) * | 2017-12-29 | 2018-07-27 | 深圳前海达闼云端智能科技有限公司 | Three-dimensional builds drawing method, device, system, high in the clouds platform, electronic equipment and computer program product |
| KR20190131402A (en) * | 2018-05-16 | 2019-11-26 | 주식회사 유진로봇 | Moving Object and Hybrid Sensor with Camera and Lidar |
| CN108958266A (en) * | 2018-08-09 | 2018-12-07 | 北京智行者科技有限公司 | A kind of map datum acquisition methods |
| CN109084786A (en) * | 2018-08-09 | 2018-12-25 | 北京智行者科技有限公司 | A kind of processing method of map datum |
| US20200124421A1 (en) * | 2018-10-19 | 2020-04-23 | Samsung Electronics Co., Ltd. | Method and apparatus for estimating position |
| US20200158869A1 (en) * | 2018-11-19 | 2020-05-21 | Elmira Amirloo Abolfathi | System, device and method of generating a high resolution and high accuracy point cloud |
| CN109783593A (en) * | 2018-12-27 | 2019-05-21 | 驭势科技（北京）有限公司 | A kind of map updating system can be used for automatic Pilot and method |
| CN111735439A (en) * | 2019-03-22 | 2020-10-02 | 北京京东尚科信息技术有限公司 | Map construction method, map construction device and computer-readable storage medium |
| CN111590595A (en) * | 2020-06-30 | 2020-08-28 | 深圳市银星智能科技股份有限公司 | Positioning method and device, mobile robot and storage medium |
| CN111736613A (en) * | 2020-07-22 | 2020-10-02 | 上海康莫巴智能科技有限公司 | Intelligent driving control method, device and system and storage medium |
| CN112213738A (en) * | 2020-09-28 | 2021-01-12 | 劢微机器人科技(深圳)有限公司 | Map construction method, device and equipment for automated guided vehicle and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| RU2727164C1 (en) | Method and apparatus for correcting map data | |
| JP6026295B2 (en) | Curve shape modeling apparatus, method, and in-vehicle navigation apparatus | |
| DE102017218249A1 (en) | System and method for detecting the position of a vehicle | |
| CN110617821B (en) | Positioning method, positioning device and storage medium | |
| WO2020154366A1 (en) | Generation of structured map data from vehicle sensors and camera arrays | |
| US20110307204A1 (en) | Velocity measuring device and method for correcting measured velocity | |
| CN104677361B (en) | A kind of method of comprehensive location | |
| CN112154445A (en) | Method and device for determining lane line in high-precision map | |
| CN112835019A (en) | Vehicle sensor calibration method and device, vehicle and storage medium | |
| CN107764273B (en) | Vehicle navigation positioning method and system | |
| CN111982132B (en) | Data processing method, device and storage medium | |
| CN115456898A (en) | Method and device for building image of parking lot, vehicle and storage medium | |
| US11908206B2 (en) | Compensation for vertical road curvature in road geometry estimation | |
| CN113295175A (en) | Map data correction method and device | |
| CN112284402B (en) | Vehicle positioning method and device | |
| CN112330977B (en) | Automatic parking method and device | |
| CN111435565A (en) | Road traffic state detection method, road traffic state detection device, electronic equipment and storage medium | |
| CN116295508A (en) | Road side sensor calibration method, device and system based on high-precision map | |
| CN114755663A (en) | External reference calibration method and device for vehicle sensor and computer readable storage medium | |
| CN114358038A (en) | Two-dimensional code coordinate calibration method and device based on vehicle high-precision positioning | |
| CN115841514A (en) | Automatic parking method, device and equipment | |
| EP4296711A1 (en) | Automatic extrinsic calibration and calibration validation of different sensor modalities, e.g camera, radar and lidar sensors | |
| CN114663458B (en) | Dynamic calibration method, dynamic calibration device, driving state detection method, driving state detection medium and driving state detection equipment | |
| CN115205828B (en) | Vehicle positioning method and device, vehicle control unit and readable storage medium | |
| CN114413890A (en) | Vehicle track generation method, vehicle track generation device, electronic device, 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 |