CN117009368A - High-precision map updating method and device based on point cloud, vehicle and medium - Google Patents
High-precision map updating method and device based on point cloud, vehicle and medium Download PDFInfo
- Publication number
- CN117009368A CN117009368A CN202311204590.5A CN202311204590A CN117009368A CN 117009368 A CN117009368 A CN 117009368A CN 202311204590 A CN202311204590 A CN 202311204590A CN 117009368 A CN117009368 A CN 117009368A
- Authority
- CN
- China
- Prior art keywords
- map
- point cloud
- preset
- data
- precision
- 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 33
- 238000012545 processing Methods 0.000 claims description 18
- 238000004422 calculation algorithm Methods 0.000 claims description 17
- 238000013135 deep learning Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 7
- 230000008859 change Effects 0.000 abstract description 5
- 238000004891 communication Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 5
- 238000010276 construction Methods 0.000 description 3
- 238000002372 labelling Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
Classifications
-
- 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
- G06F16/23—Updating
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- Instructional Devices (AREA)
Abstract
The application relates to the field of high-precision maps, in particular to a high-precision map updating method, device, vehicle and medium based on point cloud. The method comprises the following steps: acquiring point cloud data, pose data and image data of the current position of the vehicle; obtaining a local point cloud map according to the pose data and a preset point cloud map, and obtaining an optimal matching pose result meeting a preset precision condition according to the local point cloud map and the point cloud data; and updating the current local high-precision map according to the image data based on the optimal matching pose result. Therefore, the local high-definition map is updated through the point cloud data, the pose data and the image data, the problems that in the current updating mode, the global consistency of the high-definition map is reduced, the elements of the high-definition map are suddenly changed and the like due to error change caused by acquisition of multiple vehicles or acquisition of a single vehicle in the same road section data are solved, and meanwhile, the elements in the high-definition map are automatically updated without dislocation, map blurring or overlapping.
Description
Technical Field
The application relates to the field of high-precision maps, in particular to a high-precision map updating method, device, vehicle and medium based on point cloud.
Background
The high-precision map is also called as a high-precision map, has accurate vehicle position information and rich road element data information, and can help vehicles to predict complex road surface information such as gradient, curvature, heading and the like, so that potential driving risks are better avoided. Compared with a common electronic map, the high-precision map has larger data specification, so that higher processing performance and processing efficiency are required during updating to ensure timeliness, accuracy and reliability.
In the related art, the use and update of a high-definition map is generally achieved by collecting road section data through a vehicle sensor.
However, when the same road section in the method is acquired by the same vehicle for multiple times or acquired by different vehicles in turn, the detected map elements are misplaced due to sensor errors and noise, and if the acquired data is directly updated into the map, the global consistency of the high-precision map is reduced, so that the situation that the high-precision map elements are suddenly changed is needed to be solved.
Disclosure of Invention
The application provides a point cloud-based high-precision map updating method, a point cloud-based high-precision map updating device, a point cloud-based high-precision map updating vehicle and a point cloud-based high-precision map medium, which are used for solving the problems that in the current updating mode, the global consistency of a high-precision map is reduced, the elements of the high-precision map are suddenly changed, and the like caused by error changes of data acquired by a plurality of vehicles or data acquired by a single vehicle for many times, so that the elements in the high-precision map are automatically updated, and meanwhile, the conditions of dislocation, map blurring or overlapping are avoided.
In order to achieve the above objective, an embodiment of a first aspect of the present application provides a method for updating a high-precision map based on a point cloud, including the following steps:
acquiring point cloud data, pose data and image data of the current position of the vehicle;
obtaining a local point cloud map according to the pose data and a preset point cloud map, and obtaining an optimal matching pose result meeting a preset precision condition according to the local point cloud map and the point cloud data; and
and updating the current local high-precision map according to the image data based on the optimal matching pose result.
According to an embodiment of the present application, the obtaining the local point cloud map according to the pose data and the preset point cloud map includes:
acquiring a key frame sequence in the preset point cloud map, wherein the key frame sequence comprises the number and the pose of each key frame;
constructing a Kd tree according to the key frame sequence, and determining a key frame number with the minimum position distance from the pose data from the Kd tree;
and according to the first preset frame number data of the minimum key frame number in the first direction and the second preset frame number data of the minimum key frame number in the second direction, the local point cloud map is obtained by splicing.
According to an embodiment of the present application, the obtaining the optimal matching pose result satisfying the preset precision condition according to the local point cloud map and the point cloud data includes:
optimizing the point cloud data by utilizing a preset ICP (Iterative Closest Point, nearest point iteration) algorithm based on the local point cloud map to obtain the optimal matching pose result and a matching score corresponding to the optimal matching pose result;
and if the matching score is greater than or equal to a preset score, judging that the optimal matching pose result meets the preset precision condition.
According to one embodiment of the present application, after obtaining the optimal matching pose result and the matching score corresponding to the optimal matching pose result, the method further includes:
and if the matching score is smaller than the preset score, judging that the optimal matching pose result does not meet the preset precision condition, and stopping updating the current local high-precision map.
According to one embodiment of the present application, the updating the current local high-precision map according to the image data based on the optimal matching pose result includes:
processing the current frame image by using a preset deep learning algorithm to obtain a plurality of map elements;
taking any map element of the map elements as a current map element, and judging whether a target map element corresponding to the current map element exists in the current local high-precision map;
if the target map element corresponding to the current map element does not exist in the current local high-precision map, adding the current map element to the current local high-precision map, otherwise, replacing the current map element with the target map element when the matching score of the current map element is larger than the matching score of the target map element, and not updating the current local high-precision map when the matching score of the current map element is smaller than or equal to the matching score of the target map element; until the plurality of map elements is traversed.
According to the high-precision map updating method based on the point cloud, which is provided by the embodiment of the application, the local point cloud map is obtained according to the pose data of the current position of the vehicle and the preset point cloud map, and the optimal matching pose result meeting the preset precision condition is obtained according to the local point cloud map and the point cloud data of the current position of the vehicle; and updating the current local high-precision map according to the image data based on the optimal matching pose result. Therefore, the local high-definition map is updated through the point cloud data, the pose data and the image data, the problems that the global consistency of the high-definition map is reduced, the elements of the high-definition map are suddenly changed and the like caused by error change of the same road section data acquired by a plurality of vehicles or acquired by a single vehicle for a plurality of times in the current updating mode are solved, the automatic updating of the elements in the high-definition map is realized, and meanwhile, the conditions of dislocation, map blurring or overlapping are avoided
In order to achieve the above object, a second aspect of the present application provides a high-precision map updating device based on a point cloud, including:
the acquisition module is used for acquiring point cloud data, pose data and image data of the current position of the vehicle;
the processing module is used for obtaining a local point cloud map according to the pose data and a preset point cloud map, and obtaining an optimal matching pose result meeting a preset precision condition according to the local point cloud map and the point cloud data; and
and the updating module is used for updating the current local high-precision map according to the image data based on the optimal matching pose result.
According to one embodiment of the application, the processing module comprises:
the acquisition unit is used for acquiring a key frame sequence in the preset point cloud map, wherein the key frame sequence comprises the number and the pose of each key frame;
the construction unit is used for constructing a Kd tree according to the key frame sequence and determining a key frame number with the minimum position distance from the pose data from the Kd tree;
and the splicing unit is used for splicing the first preset frame number data of the minimum key frame number in the first direction and the second preset frame number data of the minimum key frame number in the second direction to obtain the local point cloud map.
According to one embodiment of the application, the processing module comprises:
the optimization unit is used for optimizing the point cloud data by utilizing a preset ICP algorithm based on the local point cloud map to obtain the optimal matching pose result and a matching score corresponding to the optimal matching pose result;
and the judging unit is used for judging that the optimal matching pose result meets the preset precision condition when the matching score is larger than or equal to a preset score.
According to an embodiment of the present application, after obtaining the optimal matching pose result and the matching score corresponding to the optimal matching pose result, the optimizing unit is further configured to:
and if the matching score is smaller than the preset score, judging that the optimal matching pose result does not meet the preset precision condition, and stopping updating the current local high-precision map.
According to one embodiment of the present application, the update module is specifically configured to:
processing the current frame image by using a preset deep learning algorithm to obtain a plurality of map elements;
taking any map element of the map elements as a current map element, and judging whether a target map element corresponding to the current map element exists in the current local high-precision map;
if the target map element corresponding to the current map element does not exist in the current local high-precision map, adding the current map element to the current local high-precision map, otherwise, replacing the current map element with the target map element when the matching score of the current map element is larger than the matching score of the target map element, and not updating the current local high-precision map when the matching score of the current map element is smaller than or equal to the matching score of the target map element; until the plurality of map elements is traversed.
According to the high-precision map updating device based on the point cloud, which is provided by the embodiment of the application, the local point cloud map is obtained according to the pose data of the current position of the vehicle and the preset point cloud map, and the optimal matching pose result meeting the preset precision condition is obtained according to the local point cloud map and the point cloud data of the current position of the vehicle; and updating the current local high-precision map according to the image data based on the optimal matching pose result. Therefore, the local high-definition map is updated through the point cloud data, the pose data and the image data, the problems that in the current updating mode, the global consistency of the high-definition map is reduced, the elements of the high-definition map are suddenly changed and the like due to error change caused by acquisition of multiple vehicles or acquisition of a single vehicle in the same road section data are solved, and meanwhile, the elements in the high-definition map are automatically updated without dislocation, map blurring or overlapping.
To achieve the above object, an embodiment of a third aspect of the present application provides a vehicle, including: the system comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the high-precision map updating method based on the point cloud.
To achieve the above object, a fourth aspect of the present application provides a computer storage medium having a computer program stored thereon, the program being executed by a processor to implement the high-precision map updating method based on point cloud as described in the above embodiment.
Additional aspects and advantages of the application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the application.
Drawings
The foregoing and/or additional aspects and advantages of the application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:
fig. 1 is a flowchart of a high-precision map updating method based on point cloud according to an embodiment of the present application;
fig. 2 is a schematic diagram of a correspondence relationship between data of a point cloud map and a high-precision map according to an embodiment of the present application;
FIG. 3 is a data flow diagram of a local high-precision map update according to one embodiment of the application;
fig. 4 is a flowchart of a high-precision map updating method based on a point cloud according to another embodiment of the present application;
fig. 5 is a block schematic diagram of a high-precision map updating apparatus based on a point cloud according to an embodiment of the present application;
fig. 6 is a schematic structural view of a vehicle according to an embodiment of the present application.
Detailed Description
Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative and intended to explain the present application and should not be construed as limiting the application.
The high-precision map updating method, device, vehicle and medium based on the point cloud according to the embodiment of the application are described below with reference to the accompanying drawings, and the high-precision map updating method based on the point cloud according to the embodiment of the application is described first with reference to the accompanying drawings.
Fig. 1 is a flowchart of a high-precision map updating method based on a point cloud according to an embodiment of the present application.
As shown in fig. 1, the high-precision map updating method based on the point cloud comprises the following steps:
in step S101, point cloud data, pose data, and image data of the current position of the vehicle are acquired.
The method comprises the steps that point cloud data can be acquired through a laser radar, a laser radar system scans the ground to obtain three-dimensional coordinates of ground reflection points, each ground reflection point is distributed in a three-dimensional space in a point mode according to the three-dimensional coordinates, the point cloud data refer to a set of scanning points in a three-dimensional coordinate system; the pose data can be obtained through a position sensor; image data (e.g., lane lines, traffic signs, etc.) may be acquired by an image sensor.
In step S102, a local point cloud map is obtained according to the pose data and a preset point cloud map, and an optimal matching pose result satisfying a preset precision condition is obtained according to the local point cloud map and the point cloud data.
The point cloud map is map information acquired through sensors such as radar and the like, is stored in the form of point cloud data and is used for describing a three-dimensional model of an object and an environment on the ground, and the preset point cloud map is a global point cloud map updated last time.
It can be understood that the vehicle-mounted laser radar has higher measurement precision, larger measurement range and higher precision of point cloud matching without being influenced by illumination factors, so that based on a complete global point cloud map, the follow-up local high-precision map updating is more accurate and reliable.
Further, in some embodiments, obtaining a local point cloud map according to the pose data and a preset point cloud map includes: acquiring a key frame sequence in a preset point cloud map, wherein the key frame sequence comprises the number and the pose of each key frame; constructing a Kd tree according to the key frame sequence, and determining a key frame number with the minimum position distance from pose data from the Kd tree; and splicing the first preset frame number data with the minimum key frame number in the first direction and the second preset frame number data with the minimum key frame number in the second direction to obtain the local point cloud map.
The first preset frame number and the second preset frame number may be preset by a person skilled in the art, may be obtained through limited experiments, or may be obtained through limited computer simulation, and are not particularly limited herein.
Specifically, the embodiment of the application can obtain a key frame sequence in a preset point Cloud map through a SLAM (Simultaneous Localization And Mapping) immediate positioning and map construction) algorithm, wherein the key frame sequence comprises the number and the corresponding Pose of each key frame and can be expressed as { (cloud1, pose 1) (cloud2, pose 2), (Cloudm, posem) }, cloudm represents the number of the mth key frame, posem represents the Pose of the mth key frame, after obtaining the key frame sequence, a data structure for dividing a K-dimensional data space can be constructed according to the key frame sequence, and the minimum key frame number is marked in a first preset frame number (calibratable, such as m frame number) in a first direction (such as the front) and a second preset frame number (such as the rear) in a second direction (such as the front) from the Kd tree according to the Pose data acquired in the step S101, so that the local map data can be obtained.
Further, in some embodiments, obtaining an optimal matching pose result satisfying a preset precision condition according to the local point cloud map and the point cloud data includes: optimizing point cloud data by utilizing a preset ICP algorithm based on the local point cloud map to obtain an optimal matching pose result and a matching score corresponding to the optimal matching pose result; and if the matching score is greater than or equal to the preset score, judging that the optimal matching pose result meets the preset precision condition.
Specifically, the embodiment of the application can optimize the point cloud data acquired in the step S101 through a preset ICP algorithm based on the local point cloud map, that is, correct according to the point cloud data and the local point cloud map, obtain an optimized optimal matching pose result and a matching score corresponding to the optimal matching pose result, and when the matching score is greater than or equal to a preset score, determine that the optimal matching pose result meets a preset precision condition, and can continue to perform subsequent updating operation on the current local high-precision map.
In step S103, the current local high-precision map is updated according to the image data based on the best matching pose result.
Further, in some embodiments, updating the current local high-precision map according to the image data based on the best matching pose result includes: processing the current frame image by using a preset deep learning algorithm to obtain a plurality of map elements; taking any one of the map elements as a current map element, and judging whether a target map element corresponding to the current map element exists in the current local high-precision map; if the target map element corresponding to the current map element does not exist in the current local high-precision map, adding the current map element to the current local high-precision map, otherwise, replacing the current map element with the target map element when the matching score of the current map element is greater than the matching score of the target map element, and not updating the current local high-precision map when the matching score of the current map element is less than or equal to the matching score of the target map element; until a plurality of map elements is traversed.
The current local high-precision map can extract road and environment elements (such as lane lines, traffic marks and the like) from single point cloud data or multiple fused point cloud data through a preset deep learning algorithm, the types, positions and shapes of the elements are stored, and then the local high-precision map is obtained by manually labeling or automatically labeling based on the local point cloud map.
Specifically, the embodiment of the application can process the current frame image data through a preset deep learning algorithm to obtain a plurality of map elements, select any map element from the plurality of map elements as the current map element Mi, and judge whether a target map element Oj corresponding to the current map element Mi exists in the current local high-precision map according to the position of the current map element Mi. If the target map element Oj corresponding to the current map element Mi does not exist in the current local high-precision map, the current map element Mi can be added to the current local high-precision map; if the corresponding target map element Oj exists in the current local high-precision map, the matching scores of the current map element Mi and the corresponding target map element Oj need to be compared, if the matching score of the current map element Mi is larger than the matching score of the corresponding target map element Oj, the corresponding target map element Oj is replaced by the current map element Mi, and if the matching score of the current map element Mi is smaller than or equal to the matching score of the corresponding target map element Oj, the current local high-precision map is not updated, and each map element is traversed according to the logic.
Further, in some embodiments, after obtaining the best matching pose result and the matching score corresponding to the best matching pose result, further includes: if the matching score is smaller than the preset score, judging that the optimal matching pose result does not meet the preset precision condition, and stopping updating the current local high-precision map.
It can be understood that after the best matching pose result and the matching score corresponding to the best matching pose result are obtained, if the matching score is not within a reasonable range, that is, the matching score is smaller than the preset score, it is determined that the best matching pose result does not meet the preset precision condition, the point cloud data obtained in the step S101 can be directly discarded, and the update of the current local high-precision map is stopped.
It should be noted that, as shown in fig. 2, the local point cloud map corresponding to the current local high-precision map needs to be complete, that is, each map element in the current local high-precision map can find a corresponding key frame in the local point cloud map, and the same key frame may correspond to different map elements.
Further, as shown in fig. 3, fig. 3 is a data flow chart of updating the current high-precision map, and the point cloud data and the pose data obtained in step S101 are matched with a preset point cloud map to obtain an optimal matching pose result relative to the preset point cloud map, which is equivalent to conversion from a global position coordinate system to a local coordinate system; the point cloud data and the image data acquired in the step S101 can be used for extracting a plurality of map elements (such as lane lines, traffic marks, etc.) through a preset deep learning algorithm; and updating the current local high-precision map based on the optimal matching pose result and according to map elements in the image data.
In order to facilitate the person skilled in the art to further understand the high-precision map updating method based on the point cloud according to the embodiment of the present application, the following is further described with reference to fig. 4.
As shown in fig. 4, a high-precision map updating method based on a point cloud according to another embodiment of the present application includes the following steps:
step S401, acquiring point cloud data, pose data, and graphic data.
Step S402, searching a key frame number with the smallest distance from pose data in a preset point cloud map, and splicing key frame data of m frames in the front-back direction of the smallest key frame number to obtain a local point cloud map.
Step S403, the point cloud data and the local point cloud map obtain the optimal matching pose result and the matching score corresponding to the optimal matching pose result through an ICP algorithm, and if the matching score is smaller than a preset score, updating is terminated.
Step S404, traversing the map elements Mi obtained from the current frame image.
Step S405, judging whether a target map element Oj corresponding to Mi exists in the current local high-precision map according to the position of Mi. If so, execute step S406; otherwise, step S409 is performed.
In step S406, it is determined whether the matching score of Mi is greater than the matching score of Oj. If yes, go to step S407; otherwise, step S408 is performed.
Step S407, deleting Oj, and replacing Mi to the current local high-precision map.
Step S408, the current local high-precision map is not updated.
Step S409, adding Mi to the current local high-precision map, and simultaneously recording the matching score and key frame number of Mi.
According to the high-precision map updating method based on the point cloud, which is provided by the embodiment of the application, the local point cloud map is obtained according to the pose data of the current position of the vehicle and the preset point cloud map, and the optimal matching pose result meeting the preset precision condition is obtained according to the local point cloud map and the point cloud data of the current position of the vehicle; and updating the current local high-precision map according to the image data based on the optimal matching pose result. Therefore, the local high-definition map is updated through the point cloud data, the pose data and the image data, the problems that in the current updating mode, the global consistency of the high-definition map is reduced, the elements of the high-definition map are suddenly changed and the like due to error change caused by acquisition of multiple vehicles or acquisition of a single vehicle in the same road section data are solved, and meanwhile, the elements in the high-definition map are automatically updated without dislocation, map blurring or overlapping.
Next, a high-precision map updating device based on point cloud according to an embodiment of the present application will be described with reference to the accompanying drawings.
Fig. 5 is a block schematic diagram of a high-precision map updating apparatus based on a point cloud according to an embodiment of the present application.
As shown in fig. 5, the high-precision map updating apparatus 10 based on the point cloud includes: an acquisition module 100, a processing module 200 and an update module 300.
The acquiring module 100 is configured to acquire point cloud data, pose data and image data of a current position of the vehicle;
the processing module 200 is configured to obtain a local point cloud map according to the pose data and a preset point cloud map, and obtain an optimal matching pose result that meets a preset precision condition according to the local point cloud map and the point cloud data; and
and the updating module 300 is used for updating the current local high-precision map according to the image data based on the optimal matching pose result.
Further, in some embodiments, the processing module 200 includes:
the acquisition unit is used for acquiring a key frame sequence in a preset point cloud map, wherein the key frame sequence comprises the number and the pose of each key frame;
the construction unit is used for constructing a Kd tree according to the key frame sequence and determining a key frame number with the minimum position distance from pose data from the Kd tree;
and the splicing unit is used for splicing the first preset frame number data in the first direction according to the minimum key frame number and the second preset frame number data in the second direction according to the minimum key frame number to obtain the local point cloud map.
Further, in some embodiments, the processing module 200 includes:
the optimizing unit is used for optimizing the point cloud data by utilizing a preset ICP algorithm based on the local point cloud map to obtain an optimal matching pose result and a matching score corresponding to the optimal matching pose result;
and the judging unit is used for judging that the optimal matching pose result meets the preset precision condition when the matching score is larger than or equal to the preset score.
Further, in some embodiments, after obtaining the best matching pose result and the matching score corresponding to the best matching pose result, the optimizing unit is further configured to:
if the matching score is smaller than the preset score, judging that the optimal matching pose result does not meet the preset precision condition, and stopping updating the current local high-precision map.
Further, in some embodiments, the update module 300 is specifically configured to:
processing the current frame image by using a preset deep learning algorithm to obtain a plurality of map elements;
taking any one of the map elements as a current map element, and judging whether a target map element corresponding to the current map element exists in the current local high-precision map;
if the target map element corresponding to the current map element does not exist in the current local high-precision map, adding the current map element to the current local high-precision map, otherwise, replacing the current map element with the target map element when the matching score of the current map element is greater than the matching score of the target map element, and not updating the current local high-precision map when the matching score of the current map element is less than or equal to the matching score of the target map element; until a plurality of map elements is traversed.
It should be noted that the foregoing explanation of the embodiment of the point cloud based high-precision map updating method is also applicable to the point cloud based high-precision map updating device of the embodiment, and will not be repeated herein.
According to the high-precision map updating device based on the point cloud, which is provided by the embodiment of the application, the local point cloud map is obtained according to the pose data of the current position of the vehicle and the preset point cloud map, and the optimal matching pose result meeting the preset precision condition is obtained according to the local point cloud map and the point cloud data of the current position of the vehicle; and updating the current local high-precision map according to the image data based on the optimal matching pose result. Therefore, the local high-definition map is updated through the point cloud data, the pose data and the image data, the problems that in the current updating mode, the global consistency of the high-definition map is reduced, the elements of the high-definition map are suddenly changed and the like due to error change caused by acquisition of multiple vehicles or acquisition of a single vehicle in the same road section data are solved, and meanwhile, the elements in the high-definition map are automatically updated without dislocation, map blurring or overlapping.
Fig. 6 is a schematic structural diagram of a vehicle according to an embodiment of the present application. The vehicle may include:
a memory 601, a processor 602, and a computer program stored on the memory 601 and executable on the processor 602.
The processor 602 implements the high-precision map updating method based on the point cloud provided in the above embodiment when executing the program.
Further, the vehicle further includes:
a communication interface 603 for communication between the memory 601 and the processor 602.
A memory 601 for storing a computer program executable on the processor 602.
The memory 601 may include a high-speed RAM (Random Access Memory ) memory, and may also include a nonvolatile memory, such as at least one disk memory.
If the memory 601, the processor 602, and the communication interface 603 are implemented independently, the communication interface 603, the memory 601, and the processor 602 may be connected to each other through a bus and perform communication with each other. The bus may be an ISA (Industry Standard Architecture ) bus, a PCI (Peripheral Component, external device interconnect) bus, or EISA (Extended Industry Standard Architecture ) bus, among others. The buses may be divided into address buses, data buses, control buses, etc. For ease of illustration, only one thick line is shown in fig. 6, but not only one bus or one type of bus.
Alternatively, in a specific implementation, if the memory 601, the processor 602, and the communication interface 603 are integrated on a chip, the memory 601, the processor 602, and the communication interface 603 may perform communication with each other through internal interfaces.
The processor 602 may be a CPU (Central Processing Unit ) or ASIC (Application Specific Integrated Circuit, application specific integrated circuit) or one or more integrated circuits configured to implement embodiments of the present application.
The embodiment of the application also provides a computer readable storage medium, on which a computer program is stored, which when being executed by a processor, implements the high-precision map updating method based on the point cloud.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present application, the meaning of "plurality" means at least two, for example, two, three, etc., unless specifically defined otherwise.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
While embodiments of the present application have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the application, and that variations, modifications, alternatives and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the application.
Claims (10)
1. The high-precision map updating method based on the point cloud is characterized by comprising the following steps of:
acquiring point cloud data, pose data and image data of the current position of the vehicle;
obtaining a local point cloud map according to the pose data and a preset point cloud map, and obtaining an optimal matching pose result meeting a preset precision condition according to the local point cloud map and the point cloud data; and
and updating the current local high-precision map according to the image data based on the optimal matching pose result.
2. The method according to claim 1, wherein the obtaining the local point cloud map from the pose data and the preset point cloud map includes:
acquiring a key frame sequence in the preset point cloud map, wherein the key frame sequence comprises the number and the pose of each key frame;
constructing a Kd tree according to the key frame sequence, and determining a key frame number with the minimum position distance from the pose data from the Kd tree;
and according to the first preset frame number data of the minimum key frame number in the first direction and the second preset frame number data of the minimum key frame number in the second direction, the local point cloud map is obtained by splicing.
3. The method according to claim 1, wherein the obtaining the optimal matching pose result satisfying the preset precision condition according to the local point cloud map and the point cloud data includes:
optimizing the point cloud data by utilizing a preset nearest point iterative ICP algorithm based on the local point cloud map to obtain the optimal matching pose result and a matching score corresponding to the optimal matching pose result;
and if the matching score is greater than or equal to a preset score, judging that the optimal matching pose result meets the preset precision condition.
4. The method of claim 3, further comprising, after obtaining the optimal matching pose result and the matching score corresponding to the optimal matching pose result:
and if the matching score is smaller than the preset score, judging that the optimal matching pose result does not meet the preset precision condition, and stopping updating the current local high-precision map.
5. The method of claim 1, wherein updating the current local high-precision map from the image data based on the optimal matching pose result comprises:
processing the current frame image by using a preset deep learning algorithm to obtain a plurality of map elements;
taking any map element of the map elements as a current map element, and judging whether a target map element corresponding to the current map element exists in the current local high-precision map;
if the target map element corresponding to the current map element does not exist in the current local high-precision map, adding the current map element to the current local high-precision map, otherwise, replacing the current map element with the target map element when the matching score of the current map element is larger than the matching score of the target map element, and not updating the current local high-precision map when the matching score of the current map element is smaller than or equal to the matching score of the target map element; until the plurality of map elements is traversed.
6. A high-precision map updating device based on a point cloud, comprising:
the acquisition module is used for acquiring point cloud data, pose data and image data of the current position of the vehicle;
the processing module is used for obtaining a local point cloud map according to the pose data and a preset point cloud map, and obtaining an optimal matching pose result meeting a preset precision condition according to the local point cloud map and the point cloud data; and
and the updating module is used for updating the current local high-precision map according to the image data based on the optimal matching pose result.
7. The apparatus of claim 6, wherein the processing module is specifically configured to:
acquiring a key frame sequence in the preset point cloud map, wherein the key frame sequence comprises the number and the pose of each key frame;
constructing a Kd tree according to the key frame sequence, and determining a key frame number with the minimum position distance from the pose data from the Kd tree;
and according to the first preset frame number data of the minimum key frame number in the first direction and the second preset frame number data of the minimum key frame number in the second direction, the local point cloud map is obtained by splicing.
8. The apparatus of claim 6, wherein the processing module is specifically configured to:
optimizing the point cloud data by utilizing a preset ICP algorithm based on the local point cloud map to obtain the optimal matching pose result and a matching score corresponding to the optimal matching pose result;
and if the matching score is greater than or equal to a preset score, judging that the optimal matching pose result meets the preset precision condition.
9. A vehicle, characterized by comprising: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor executing the program to implement the point cloud based high-precision map updating method of any of claims 1-5.
10. A computer-readable storage medium, on which a computer program is stored, characterized in that the program is executed by a processor for implementing the point cloud based high-precision map updating method according to any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311204590.5A CN117009368A (en) | 2023-09-18 | 2023-09-18 | High-precision map updating method and device based on point cloud, vehicle and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311204590.5A CN117009368A (en) | 2023-09-18 | 2023-09-18 | High-precision map updating method and device based on point cloud, vehicle and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117009368A true CN117009368A (en) | 2023-11-07 |
Family
ID=88562032
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311204590.5A Pending CN117009368A (en) | 2023-09-18 | 2023-09-18 | High-precision map updating method and device based on point cloud, vehicle and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117009368A (en) |
-
2023
- 2023-09-18 CN CN202311204590.5A patent/CN117009368A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11030803B2 (en) | Method and apparatus for generating raster map | |
| CN112667837A (en) | Automatic image data labeling method and device | |
| CN112086010B (en) | Map generation method, map generation device, map generation equipment and storage medium | |
| CN111982532B (en) | Automatic parking performance testing method | |
| US11926339B2 (en) | Method for constructing driving coordinate system, and application thereof | |
| JP2022528301A (en) | Calibration method, positioning method, equipment, electronic devices and storage media | |
| EP3875905B1 (en) | Method, device and medium for detecting environmental change | |
| EP3633551A1 (en) | Obstacle distribution simulation method, device and terminal based on a probability graph | |
| JP2020134198A (en) | Controlling map information evaluation device, controlling map information evaluation method and control program | |
| JP2008020225A (en) | Self position estimation program, self position estimation method and self position estimation apparatus | |
| EP3620962A1 (en) | Method, device and terminal for simulating a distribution of obstacles | |
| CN113566817B (en) | Vehicle positioning method and device | |
| US20210089506A1 (en) | Method and device for creating a localization map | |
| CN116380088B (en) | Vehicle positioning method and device, vehicle and storage medium | |
| CN117009368A (en) | High-precision map updating method and device based on point cloud, vehicle and medium | |
| CN116343148A (en) | Lane line detection method, device, vehicle and storage medium | |
| CN116383321A (en) | Decision environment construction method, device, vehicle and storage medium | |
| CN116134488A (en) | Point cloud labeling method, point cloud labeling device, computer equipment and storage medium | |
| US20240077316A1 (en) | Lane detection system and vehicle equipped with the same | |
| US20230280165A1 (en) | Methods for processing map, and vehicle | |
| CN117553775A (en) | Automatic map generation method and device, electronic equipment and storage medium | |
| CN114359872A (en) | Lane positioning method and device and electronic equipment | |
| CN116698053A (en) | Method, device and medium for matching high-precision map with traditional navigation path | |
| CN116597730A (en) | Lane recognition data merging method and system | |
| CN114219834A (en) | Method and device for updating traffic marker in high-precision map and electronic equipment |
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 |