CN114111817B - Vehicle positioning method and system based on SLAM map and high-precision map matching - Google Patents
Vehicle positioning method and system based on SLAM map and high-precision map matching Download PDFInfo
- Publication number
- CN114111817B CN114111817B CN202111385621.2A CN202111385621A CN114111817B CN 114111817 B CN114111817 B CN 114111817B CN 202111385621 A CN202111385621 A CN 202111385621A CN 114111817 B CN114111817 B CN 114111817B
- Authority
- CN
- China
- Prior art keywords
- map
- vehicle
- slam
- slam map
- 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.)
- Active
Links
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
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
- G01C21/3804—Creation or updating of map data
- G01C21/3807—Creation or updating of map data characterised by the type of data
- G01C21/3815—Road data
-
- 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
- G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
- G01C21/3804—Creation or updating of map data
- G01C21/3833—Creation or updating of map data characterised by the source of data
- G01C21/3841—Data obtained from two or more sources, e.g. probe vehicles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/32—Indexing scheme for image data processing or generation, in general involving image mosaicing
-
- 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)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Automation & Control Theory (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Image Analysis (AREA)
- Navigation (AREA)
Abstract
The invention provides a vehicle positioning method and a system based on SLAM map and high-precision map matching, which are characterized in that a visual SLAM map is constructed in real time, semantic segmentation is carried out by utilizing a deep learning technology, element information in a scene is extracted, point sets formed by SLAM map elements are registered by the same type of map element point sets in the high-precision map, and the positioning of a vehicle in the high-precision map is obtained through a registration result. The scheme has the following advantages: (1) independent of GNSS signals; (2) global positioning information may be output; (3) The SLAM map does not need to be constructed and stored in advance, and only depends on a high-precision map which is usually contained in an automatic driving vehicle, so that the practicability is higher; (4) Compared with the traditional 'visual feature point-SLAM map feature point' matching mode, the 'SLAM map element-high-precision map element' matching mode is used, more matching elements are used, and the success rate is higher.
Description
Technical Field
The invention relates to the technical field of vehicle positioning, in particular to a vehicle positioning method and system based on SLAM map and high-precision map matching.
Background
With the development of autopilot technology, the demand for high-precision and high-robustness positioning systems for autopilot vehicles is increasing. At present, the positioning mode of a vehicle mainly depends on a GNSS system (Global Navigation Satellite System, global satellite navigation system), inertial navigation and an odometer, the GNSS system cannot accurately position in the scenes of no signals or serious shielding such as tunnels, mountain areas and urban roads, the accumulated errors exist in the calculation results of the inertial navigation and the odometer, and the deviation is larger and larger under the condition of no external signal correction. Therefore, there is a need for a positioning system independent of GNSS signals, which solves the problem of high accuracy positioning in the above scenario. A positioning method based on a SLAM map is proposed in (publication No. CN 201811472195.4) a positioning method based on a SLAM map, in which a local SLAM map is established, and the continuity of vehicle positioning is ensured by means of relative positioning of a vehicle in the local map. A similar positioning method is used by the "high-precision positioning method and system based on shared SLAM map" (publication No. cn20191019444. X), except that the used SLAM map is a shared SLAM map acquired by a network. ORB-SLAM-based high-precision vehicle positioning method (publication No. CN 201910075818.2) performs vehicle matching positioning by constructing an SLAM visual map and feature points in advance and then performing vehicle matching positioning by the feature points.
The above methods are all actually adopted in a manner of constructing a SLAM map and then positioning in the SLAM map, and the main limitation is that:
(1) The SLAM map is a local relative relation map, does not contain world coordinate information, and the positioning result is also relative information, so that the position of the vehicle in the real world cannot be clearly known;
(2) The matching positioning in the SLAM map depends on visual feature points of single-frame or multi-frame images, and cannot accurately position when feature points in a scene are scarce.
Disclosure of Invention
The invention aims to solve the technical problems that in the prior art, global world coordinates cannot be obtained when a local SLAM map is established to position a vehicle, positioning is unreliable due to excessively depending on visual feature points, and the like.
The invention provides a vehicle positioning method based on SLAM map and high-precision map matching, which comprises the following steps:
s1, constructing a visual SLAM map according to an original uncorrected vehicle track and a visual image;
s2, carrying out semantic segmentation on the SLAM map through a deep learning algorithm to generate map element information of different categories;
s3, extracting SLAM map element information and high-precision map element information in a certain range near the vehicle according to the current position of the vehicle;
s4, registering the SLAM map element point set and the high-precision map element point set by using a classical ICP (Iterative Closest Point) point set registration algorithm;
s5, converting the uncorrected vehicle track through the translation parameters and the rotation parameters which are output by registration, so as to obtain the corrected vehicle track, and finishing one-time accurate positioning of the vehicle.
Preferably, the S1 specifically includes: and calculating the vehicle track through an inertia device, and constructing the SLAM map in real time by the vehicle track and the visual image.
Preferably, the inertial device is one or a combination of accelerometers, gyroscopes or odometers.
Preferably, the S1 specifically includes: through the relative relation between the pre-calibrated camera and the vehicle, the coordinate information of the image in the camera is obtained in real time, the visual image is obtained by splicing multiple frames of images, and then the vehicle track and the visual image are fused to construct the SLAM map in real time.
Preferably, the estimated starting position of the vehicle track in S1 is a memory position of the last positioning or a position before the GNSS lock is lost.
Preferably, the semantic segmentation in S2 specifically includes: and splicing and clustering similar point sets in the SLAM map to obtain map element information of different categories, wherein the map element information consists of element categories and point set coordinates, and the map element categories comprise, but are not limited to, lane lines, traffic lights, traffic signs, ground text arrows and stop lines.
Preferably, the S4 specifically includes: the iterative processes of searching the closest point, generating a matched point set, obtaining transformation parameters by least square and updating the point set to be matched are adopted for registration, and the search of registration objects is only carried out in map elements of the same category.
The invention also provides a system for realizing the vehicle positioning method based on SLAM map and high-precision map matching, which comprises the following steps:
the SLAM map construction module is used for constructing a visual SLAM map according to the original uncorrected vehicle track and the visual image;
the SLAM map element generation module is used for carrying out semantic segmentation on the SLAM map through a deep learning algorithm to generate map element information of different categories;
the SLAM map and high-precision map extraction module is used for extracting SLAM map element information and high-precision map element information in a certain range near the vehicle according to the current position of the vehicle;
the SLAM map and high-precision map registration module is used for registering the SLAM map element point set and the high-precision map element point set by using a classical ICP (Iterative Closest Point) point set registration algorithm;
and the vehicle track correction module is used for transforming the uncorrected vehicle track through the translation parameters and the rotation parameters which are output by registration, so as to obtain the corrected vehicle track and finish one-time accurate positioning of the vehicle.
The invention also provides an electronic device, which comprises a memory and a processor, wherein the processor is used for realizing the steps of the vehicle positioning method based on SLAM map and high-precision map matching when executing the computer management program stored in the memory.
The present invention also provides a computer-readable storage medium having stored thereon a computer management class program which, when executed by a processor, implements the steps of a method for locating a vehicle based on a SLAM map matching a high-precision map.
The beneficial effects are that: according to the vehicle positioning method and system based on SLAM map and high-precision map matching, the visual SLAM map is built in real time, the deep learning technology is utilized for semantic segmentation, element information in a scene including but not limited to lane lines, traffic lights, traffic signs, ground text arrows and stop lines is extracted, point sets formed by SLAM map elements are registered with the same type map element point sets in the high-precision map, and the positioning of the vehicle in the high-precision map is obtained through registration results. The process is similar to that of human eyes for observing and identifying the environment in front of the vehicle, and then searching for a scene similar to the observed result in the high-precision map, so that the position information of the current vehicle is obtained. The scheme uses the existing SLAM mapping technology and the deep learning semantic segmentation technology, and performs positioning by registering a visual perception local map and a high-precision map, so that the method has the following advantages: (1) independent of GNSS signals; (2) global positioning information may be output; (3) The SLAM map does not need to be constructed and stored in advance, and only depends on a high-precision map which is usually contained in an automatic driving vehicle, so that the practicability is higher; (4) Compared with the traditional 'visual feature point-SLAM map feature point' matching mode, the 'SLAM map element-high-precision map element' matching mode is used, more matching elements are used, and the success rate is higher.
Drawings
FIG. 1 is a flow chart of a vehicle positioning method based on SLAM map and high-precision map matching provided by the invention;
fig. 2 is a schematic hardware structure of one possible electronic device according to the present invention;
FIG. 3 is a schematic diagram of a possible hardware configuration of a computer readable storage medium according to the present invention;
fig. 4 is a schematic frame diagram of a vehicle positioning system based on matching of a SLAM map and a high-precision map.
Detailed Description
The following describes in further detail the embodiments of the present invention with reference to the drawings and examples. The following examples are illustrative of the invention and are not intended to limit the scope of the invention.
As shown in fig. 1, the embodiment of the invention provides a vehicle positioning method based on matching of a SLAM map and a high-precision map, which comprises the following steps:
s1, constructing a visual SLAM map according to the original uncorrected vehicle track and the visual image. And calculating a vehicle track by an inertial device, and constructing an SLAM map in real time by the vehicle track and the visual image. The inertial device can be one or more of an accelerometer, a gyroscope, an odometer and the like, and the track reckoning initial position is a memory position of the last positioning or a position before GNSS unlocking.
Through calibrating the relative relation between the camera and the vehicle in advance, the coordinate information of the image in the camera can be obtained in real time, and the SLAM map is constructed by splicing multiple frames of images in real time, wherein the SLAM map comprises a large number of unclassified point set coordinates. The relative relationship between the point set in the SLAM map and the vehicle track is kept unchanged, and since the vehicle track is uncorrected, the point set in the SLAM map is likewise uncorrected.
S2, carrying out semantic segmentation on the SLAM map through a deep learning algorithm to generate map element information of different categories. The semantic segmentation comprises the steps of splicing and clustering similar point sets in the SLAM map, identifying the types of the similar point sets, and obtaining various map element information, wherein the map element information comprises element categories and point set coordinates, and the map element categories comprise, but are not limited to, lane lines, traffic lights, traffic signs, ground text arrows and stop lines.
S3, extracting SLAM map element information and high-precision map element information in a certain range near the vehicle according to the current position of the vehicle. In a specific implementation scenario, according to the current position (not corrected) of the vehicle, the SLAM map element information and the high-precision map element information in a certain range near the vehicle are extracted, the range value is selected mainly considering the calculation amount and real-time performance of subsequent matching, the typical value is 500-1000 m, the high-precision map is used as the matching object of the SLAM map, the extraction range of the high-precision map is larger than that of the SLAM map, the value is selected mainly considering the error value possibly generated by track estimation of an inertial device, and the typical value is 50-200 m.
S4, performing registration of the SLAM map element point set and the high-precision map element point set by using a classical ICP (Iterative Closest Point) point set registration algorithm. Specifically, a classical ICP point set registration algorithm is utilized to register the SLAM map element point set and the high-precision map element point set, the essence of the ICP algorithm is an iterative process of searching the nearest point, generating a pairing point set, obtaining a transformation parameter by least square, updating the point set to be matched, in order to reduce the probability of mismatching, the searching of a registration object is only carried out in the same category of elements, the iteration stopping condition of registration can be the appointed iteration times, or the distance between the transformed SLAM map element point set and the high-precision map element point set is smaller than an appointed threshold, and the output result of registration is a translation+rotation parameter of the SLAM map from an initial state to a final alignment state.
S5, converting the uncorrected vehicle track through the translation parameters and the rotation parameters which are output by registration, so as to obtain the corrected vehicle track, and finishing one-time accurate positioning of the vehicle. Because the SLAM map is constructed by using the vehicle track, the uncorrected vehicle track is transformed by the translation parameter and the rotation parameter which are registered and output, and the corrected vehicle track is obtained, so that the accurate positioning of the vehicle is completed once.
According to the scheme, a visual SLAM map is constructed in real time, semantic segmentation is performed by using a deep learning technology, element information in a scene including but not limited to lane lines, traffic lights, traffic signs, ground text arrows and stop lines is extracted, point sets formed by SLAM map elements are registered with similar map element point sets in a high-precision map, and the positioning of a vehicle in the high-precision map is obtained through registration results. The process is similar to that of human eyes for observing and identifying the environment in front of the vehicle, and then searching for a scene similar to the observed result in the high-precision map, so that the position information of the current vehicle is obtained.
The scheme uses the existing SLAM mapping technology and the deep learning semantic segmentation technology, and performs positioning by registering a visual perception local map and a high-precision map, so that the method has the following advantages: (1) independent of GNSS signals; (2) global positioning information may be output; (3) The SLAM map does not need to be constructed and stored in advance, and only depends on a high-precision map which is usually contained in an automatic driving vehicle, so that the practicability is higher; (4) Compared with the traditional 'visual feature point-SLAM map feature point' matching mode, the 'SLAM map element-high-precision map element' matching mode is used, more matching elements are used, and the success rate is higher.
Please refer to fig. 4, which is a system for a vehicle positioning method based on SLAM map and high-precision map matching, comprising:
the SLAM map construction module is used for constructing a visual SLAM map according to the original uncorrected vehicle track and the visual image;
the SLAM map element generation module is used for carrying out semantic segmentation on the SLAM map through a deep learning algorithm to generate map element information of different categories;
the SLAM map and high-precision map extraction module is used for extracting SLAM map element information and high-precision map element information in a certain range near the vehicle according to the current position of the vehicle;
the SLAM map and high-precision map registration module is used for registering the SLAM map element point set and the high-precision map element point set by using a classical ICP (Iterative Closest Point) point set registration algorithm;
and the vehicle track correction module is used for transforming the uncorrected vehicle track through the translation parameters and the rotation parameters which are output by registration, so as to obtain the corrected vehicle track and finish one-time accurate positioning of the vehicle.
All modules are executed in linkage to implement all the vehicle positioning methods based on SLAM map and high-precision map matching. And will not be described in detail herein.
Fig. 2 is a schematic diagram of an embodiment of an electronic device according to an embodiment of the present invention. As shown in fig. 2, an embodiment of the present invention provides an electronic device, including a memory 1310, a processor 1320, and a computer program 1311 stored in the memory 1310 and executable on the processor 1320, wherein the processor 1320 executes the computer program 1311 to implement the following steps:
s1, constructing a visual SLAM map according to an original uncorrected vehicle track and a visual image;
s2, carrying out semantic segmentation on the SLAM map through a deep learning algorithm to generate map element information of different categories;
s3, extracting SLAM map element information and high-precision map element information in a certain range near the vehicle according to the current position of the vehicle;
s4, registering the SLAM map element point set and the high-precision map element point set by using a classical ICP (Iterative Closest Point) point set registration algorithm;
s5, converting the uncorrected vehicle track through the translation parameters and the rotation parameters which are output by registration, so as to obtain the corrected vehicle track, and finishing one-time accurate positioning of the vehicle.
Fig. 3 is a schematic diagram of an embodiment of a computer readable storage medium according to the present invention. As shown in fig. 3, the present embodiment provides a computer-readable storage medium 1400 having stored thereon a computer program 1411, which computer program 1411, when executed by a processor, performs the steps of:
s1, constructing a visual SLAM map according to an original uncorrected vehicle track and a visual image;
s2, carrying out semantic segmentation on the SLAM map through a deep learning algorithm to generate map element information of different categories;
s3, extracting SLAM map element information and high-precision map element information in a certain range near the vehicle according to the current position of the vehicle;
s4, registering the SLAM map element point set and the high-precision map element point set by using a classical ICP (Iterative Closest Point) point set registration algorithm;
s5, converting the uncorrected vehicle track through the translation parameters and the rotation parameters which are output by registration, so as to obtain the corrected vehicle track, and finishing one-time accurate positioning of the vehicle.
In the foregoing embodiments, the descriptions of the embodiments are focused on, and for those portions of one embodiment that are not described in detail, reference may be made to the related descriptions of other embodiments.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, 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, 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.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations 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 computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, 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 apparatus 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 apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus 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 in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (6)
1. A vehicle positioning method based on SLAM map and high-precision map matching is characterized by comprising the following steps:
s1, constructing a visual SLAM map according to an original uncorrected vehicle track and a visual image, specifically, obtaining coordinate information of an image in a camera in real time by calibrating a relative relation between the camera and the vehicle in advance, splicing a plurality of frames of images to obtain the visual image, calculating the vehicle track through an inertial device, and fusing the vehicle track and the visual image to construct the SLAM map in real time;
s2, carrying out semantic segmentation on the SLAM map through a deep learning algorithm to generate map element information of different categories, specifically, splicing and clustering similar point sets in the SLAM map to obtain the map element information of different categories, wherein the map element information consists of element categories and point set coordinates, and the map element categories comprise, but are not limited to, lane lines, traffic lights, traffic cards, ground text arrows and stop lines;
s3, extracting SLAM map element information and high-precision map element information in a certain range near the vehicle according to the current position of the vehicle;
s4, performing registration of the SLAM map element point set and the high-precision map element point set by using a classical ICP (Iterative Closest Point) point set registration algorithm, specifically, performing registration by adopting an iterative process of searching the closest point, generating a pairing point set, acquiring transformation parameters by least square and updating the point set to be matched, and performing the search of registration objects only in map elements of the same category;
s5, converting the uncorrected vehicle track through the translation parameters and the rotation parameters which are output by registration, so as to obtain the corrected vehicle track, and finishing one-time accurate positioning of the vehicle.
2. The SLAM map and high-precision map matching-based vehicle positioning method of claim 1, wherein the inertial device is one or more of an accelerometer, a gyroscope, or an odometer.
3. The method for locating a vehicle based on SLAM map matching with high-precision map according to claim 1, wherein the estimated starting position of the vehicle track in S1 is a memory position of the last location or a position before the GNSS lock out.
4. A system for implementing the SLAM map-based high-precision map matching vehicle positioning method as claimed in any one of claims 1 to 3, characterized by comprising:
the SLAM map construction module is used for constructing a visual SLAM map according to the original uncorrected vehicle track and the visual image;
the SLAM map element generation module is used for carrying out semantic segmentation on the SLAM map through a deep learning algorithm to generate map element information of different categories;
the SLAM map and high-precision map extraction module is used for extracting SLAM map element information and high-precision map element information in a certain range near the vehicle according to the current position of the vehicle;
the SLAM map and high-precision map registration module is used for registering the SLAM map element point set and the high-precision map element point set by using a classical ICP (Iterative Closest Point) point set registration algorithm;
and the vehicle track correction module is used for transforming the uncorrected vehicle track through the translation parameters and the rotation parameters which are output by registration, so as to obtain the corrected vehicle track and finish one-time accurate positioning of the vehicle.
5. An electronic device comprising a memory, a processor for implementing the steps of the SLAM map-based high-precision map matching vehicle positioning method according to any one of claims 1-3 when executing a computer management class program stored in the memory.
6. A computer-readable storage medium, having stored thereon a computer management class program which, when executed by a processor, implements the steps of the SLAM map-and high-precision map-matching-based vehicle positioning method as recited in any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111385621.2A CN114111817B (en) | 2021-11-22 | 2021-11-22 | Vehicle positioning method and system based on SLAM map and high-precision map matching |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111385621.2A CN114111817B (en) | 2021-11-22 | 2021-11-22 | Vehicle positioning method and system based on SLAM map and high-precision map matching |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114111817A CN114111817A (en) | 2022-03-01 |
| CN114111817B true CN114111817B (en) | 2023-10-13 |
Family
ID=80439306
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111385621.2A Active CN114111817B (en) | 2021-11-22 | 2021-11-22 | Vehicle positioning method and system based on SLAM map and high-precision map matching |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114111817B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116202538B (en) * | 2023-05-05 | 2023-08-29 | 广州小鹏自动驾驶科技有限公司 | Map matching fusion method, device, equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111220164A (en) * | 2020-01-21 | 2020-06-02 | 北京百度网讯科技有限公司 | Positioning method, device, equipment and storage medium |
| CN111380542A (en) * | 2018-12-28 | 2020-07-07 | 沈阳美行科技有限公司 | Vehicle positioning and navigation method and device and related system |
| WO2020199565A1 (en) * | 2019-03-29 | 2020-10-08 | 魔门塔(苏州)科技有限公司 | Street lamp pole-based vehicle posture correction method and device |
| CN111750882A (en) * | 2019-03-29 | 2020-10-09 | 北京初速度科技有限公司 | Method and device for correcting vehicle pose during initialization of navigation map |
| CN111830953A (en) * | 2019-04-12 | 2020-10-27 | 北京四维图新科技股份有限公司 | Vehicle self-positioning method, device and system |
| WO2020237996A1 (en) * | 2019-05-30 | 2020-12-03 | 魔门塔(苏州)科技有限公司 | Vehicle pose correction method and device |
| WO2021073656A1 (en) * | 2019-10-16 | 2021-04-22 | 上海商汤临港智能科技有限公司 | Method for automatically labeling image data and device |
| CN113137973A (en) * | 2020-01-20 | 2021-07-20 | 北京初速度科技有限公司 | Image semantic feature point truth value determining method and device |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140323148A1 (en) * | 2013-04-30 | 2014-10-30 | Qualcomm Incorporated | Wide area localization from slam maps |
| KR20190121275A (en) * | 2019-10-07 | 2019-10-25 | 엘지전자 주식회사 | System, apparatus and method for indoor positioning |
| CN111274343B (en) * | 2020-01-20 | 2023-11-24 | 阿波罗智能技术(北京)有限公司 | Vehicle positioning method and device, electronic equipment and storage medium |
| CN111833717B (en) * | 2020-07-20 | 2022-04-15 | 阿波罗智联(北京)科技有限公司 | Method, device, equipment and storage medium for positioning vehicle |
-
2021
- 2021-11-22 CN CN202111385621.2A patent/CN114111817B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111380542A (en) * | 2018-12-28 | 2020-07-07 | 沈阳美行科技有限公司 | Vehicle positioning and navigation method and device and related system |
| WO2020199565A1 (en) * | 2019-03-29 | 2020-10-08 | 魔门塔(苏州)科技有限公司 | Street lamp pole-based vehicle posture correction method and device |
| CN111750882A (en) * | 2019-03-29 | 2020-10-09 | 北京初速度科技有限公司 | Method and device for correcting vehicle pose during initialization of navigation map |
| CN111750881A (en) * | 2019-03-29 | 2020-10-09 | 北京初速度科技有限公司 | Vehicle pose correction method and device based on light pole |
| CN111830953A (en) * | 2019-04-12 | 2020-10-27 | 北京四维图新科技股份有限公司 | Vehicle self-positioning method, device and system |
| WO2020237996A1 (en) * | 2019-05-30 | 2020-12-03 | 魔门塔(苏州)科技有限公司 | Vehicle pose correction method and device |
| WO2021073656A1 (en) * | 2019-10-16 | 2021-04-22 | 上海商汤临港智能科技有限公司 | Method for automatically labeling image data and device |
| CN113137973A (en) * | 2020-01-20 | 2021-07-20 | 北京初速度科技有限公司 | Image semantic feature point truth value determining method and device |
| CN111220164A (en) * | 2020-01-21 | 2020-06-02 | 北京百度网讯科技有限公司 | Positioning method, device, equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 预建高精度地图的封闭区域UGV自动驾驶导航定位;王一文;钱闯;唐健;温景仁;牛小骥;;测绘通报(01);第21-25页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114111817A (en) | 2022-03-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6812404B2 (en) | Methods, devices, computer-readable storage media, and computer programs for fusing point cloud data | |
| JP6595182B2 (en) | Systems and methods for mapping, locating, and attitude correction | |
| CN112734852B (en) | Robot mapping method and device and computing equipment | |
| CN111912416B (en) | Method, device and equipment for positioning equipment | |
| WO2020043081A1 (en) | Positioning technique | |
| CN114663852B (en) | Lane diagram construction method and device, electronic equipment and readable storage medium | |
| CN109214314B (en) | Automatic fusion matching algorithm for lane lines | |
| CN111508258A (en) | Positioning method and device | |
| CN114565863B (en) | Real-time generation method, device, medium and equipment for orthophoto of unmanned aerial vehicle image | |
| CN111008660A (en) | Semantic map generation method, device and system, storage medium and electronic equipment | |
| US20220398825A1 (en) | Method for generating 3d reference points in a map of a scene | |
| CN113223064B (en) | Visual inertial odometer scale estimation method and device | |
| CN114111817B (en) | Vehicle positioning method and system based on SLAM map and high-precision map matching | |
| CN115761164A (en) | Method and device for generating inverse perspective IPM image | |
| CN115344655A (en) | Method and device for finding change of feature element, and storage medium | |
| CN116958452A (en) | Three-dimensional reconstruction method and system | |
| CN110827340B (en) | Map updating method, device and storage medium | |
| CN115937449A (en) | High-precision map generation method and device, electronic equipment and storage medium | |
| WO2023283929A1 (en) | Method and apparatus for calibrating external parameters of binocular camera | |
| CN114332174A (en) | Track image alignment method and device, computer equipment and storage medium | |
| CN113034538B (en) | Pose tracking method and device of visual inertial navigation equipment and visual inertial navigation equipment | |
| Sun et al. | Accurate deep direct geo-localization from ground imagery and phone-grade gps | |
| CN115128655B (en) | Positioning method and device for automatic driving vehicle, electronic equipment and storage medium | |
| CN114972494B (en) | Map construction method and device for memorizing parking scene | |
| CN115205828B (en) | Vehicle positioning method and device, vehicle control unit and readable 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |