CN114120279A - Traffic signboard updating method, system, electronic equipment and storage medium - Google Patents
Traffic signboard updating method, system, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN114120279A CN114120279A CN202111422396.5A CN202111422396A CN114120279A CN 114120279 A CN114120279 A CN 114120279A CN 202111422396 A CN202111422396 A CN 202111422396A CN 114120279 A CN114120279 A CN 114120279A
- Authority
- CN
- China
- Prior art keywords
- traffic signboard
- traffic
- map
- updating
- signboard
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/251—Fusion techniques of input or preprocessed data
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a method, a system, electronic equipment and a storage medium for updating a traffic signboard, wherein the method comprises the following steps: segmenting traffic signboard semantic features in each frame of image data based on a deep learning semantic segmentation network, and extracting a traffic signboard outline area; based on the pose information and the camera internal and external parameters, projecting the traffic signboard space area in the high-precision MAP HD MAP to an image coordinate system; carrying out global similarity matching on the traffic signboard area under an image coordinate system; carrying out difference analysis on the matching result of the traffic signboard to acquire addition and deletion attribute information of the image data relative to HD MAP data; and updating the traffic signboard data in the HD MAP library based on the addition and deletion attribute information. The invention reduces human intervention by means of an image deep learning technology, improves the efficiency of updating traffic signboard elements of a high-precision map, and has low cost and higher updating efficiency compared with an extraction method for manufacturing the high-precision map.
Description
Technical Field
The invention relates to the field of high-precision map making, in particular to a method and a system for updating a traffic signboard, electronic equipment and a storage medium.
Background
The automatic driving high-precision map is used as an indispensable important component of an automatic driving vehicle, and provides favorable support for vehicle positioning, path planning, vehicle energy conservation and the like. In order to ensure the freshness of the high-precision map, under the condition of meeting the precision requirement, how to update the map with low cost and high efficiency becomes the key for ensuring the effectiveness of the map and having competitiveness. The automatic driving high-precision map updating has the following characteristics: 1) the automatic driving high-precision map is different from the traditional navigation map, contains three-dimensional information and has higher precision requirement; 2) the high-precision map is a lane-level map; 3) the map information is richer and the updating difficulty is higher. In summary, the updating process of the automatic driving high-precision map needs to ensure high precision and high efficiency.
Disclosure of Invention
The invention provides a traffic signboard updating method, a traffic signboard updating system, electronic equipment and a storage medium, aiming at the technical problems in the prior art.
According to a first aspect of the present invention, there is provided a traffic signboard updating method including: segmenting traffic signboard semantic features in each frame of image data based on a deep learning semantic segmentation network, and extracting a traffic signboard outline area; based on the pose information and the camera internal and external parameters, projecting the traffic signboard space area in the high-precision MAP HD MAP to an image coordinate system; carrying out global similarity matching on the traffic signboard outline region extracted from the image data and the traffic signboard region projected from the HD MAP data under an image coordinate system to obtain a traffic signboard matching result; performing difference analysis on the traffic signboard matching result to acquire addition and deletion attribute information of the image data relative to HD MAP data; and updating the traffic signboard data in the HD MAP library based on the addition and deletion attribute information.
On the basis of the technical scheme, the invention can be improved as follows.
Optionally, the deep learning semantic segmentation network is configured to segment semantic features of the traffic signboard in each frame of image data and extract a traffic signboard contour region, where the segmentation comprises: initializing the first frame of image data based on the pose data comprising the GNSS information.
Optionally, initializing the first frame of image data based on the pose data containing the GNSS information, and then: and detecting the traffic signboard elements in each frame of image data based on a deep learning target detection network, and acquiring a target rectangular frame comprising the traffic signboard.
Optionally, the segmenting the semantic features of the traffic signboard in each frame of image data based on the deep learning semantic segmentation network, and extracting the contour region of the traffic signboard includes: segmenting semantic features of traffic signboard, upright stanchion and lane line elements in each frame of image data based on a deep learning semantic segmentation network; according to the semantic features of the traffic signboard, the upright post and the lane line element, extracting the outer contour of the traffic signboard and extracting the skeleton line of the lane line and the upright post respectively to obtain the contour area of the traffic signboard.
Optionally, the initializing the first frame of image data based on the pose data including GNSS information, and then optimizing the pose information includes: and optimizing the pose information by taking the odometer information, the IMU inertial navigation data and the GPS track data as input, and acquiring the optimized pose information.
Optionally, the add/delete attribute information includes a traffic signboard profile that needs to be added/deleted, and correspondingly, the update of the traffic signboard data in the HD MAP library is performed based on the add/delete attribute information, including: acquiring a traffic signboard target rectangular frame corresponding to a traffic signboard outline area needing to be added and deleted; and updating the traffic signboard data in the HP MAP base based on the traffic signboard target rectangular frame.
According to a second aspect of the present invention, there is provided a traffic signboard updating system including: the extraction module is used for segmenting the semantic features of the traffic signboard in each frame of image data based on the deep learning semantic segmentation network and extracting the outline area of the traffic signboard; the projection module is used for projecting the space area of the traffic signboard in the high-precision MAP HD MAP to an image coordinate system based on the pose information and the camera internal and external parameters; the matching module is used for carrying out global similarity matching on the traffic signboard outline region extracted from the image data and the traffic signboard region projected from the HD MAP data under the image coordinate system to obtain a traffic signboard matching result; the difference analysis module is used for carrying out difference analysis on the matching result of the traffic signboard to acquire addition and deletion attribute information of the image data relative to the HD MAP data; and the updating module is used for updating the traffic signboard data in the HD MAP base based on the addition and deletion attribute information.
According to a third aspect of the present invention, there is provided an electronic device comprising a memory, a processor for implementing the steps of the traffic sign updating method when executing a computer management-like program stored in the memory.
According to a fourth aspect of the present invention, there is provided a computer-readable storage medium having stored thereon a computer management-like program, which when executed by a processor, performs the steps of the traffic signboard updating method.
The invention provides a traffic signboard updating method, a system, electronic equipment and a storage medium, which take a forward-looking image, IMU information, odometer information, a GPS track and HD MAP as main data sources, extract traffic signboard element form points from image data by means of a traffic signboard reasoning result of an image deep learning technology, match the HD MAP traffic signboard elements with the traffic signboard result extracted from the image by means of internal and external parameters and track data, obtain a difference analysis result, and update the result with high efficiency. The invention reduces human intervention by means of an image deep learning technology, improves the efficiency of updating traffic signboard elements of a high-precision map, and has low cost and higher updating efficiency compared with an extraction method for manufacturing the high-precision map.
Drawings
FIG. 1 is a flow chart of a method for updating a traffic signboard according to the present invention;
FIG. 2 is an overall flow chart of a traffic sign update method;
FIG. 3 is a schematic structural diagram of a traffic signboard updating system provided by the present invention;
FIG. 4 is a schematic diagram of a hardware structure of a possible electronic device provided in the present invention;
fig. 5 is a schematic diagram of a hardware structure of a possible computer-readable storage medium according to the present invention.
Detailed Description
The following detailed description of embodiments of the present invention is provided in connection with the accompanying drawings and examples. The following examples are intended to illustrate the invention but are not intended to limit the scope of the invention.
In the updating process of the automatic driving high-precision map, the efficiency can be improved by means of deep learning from the aspect of reducing human intervention in the aspect of improving the efficiency. The technology of deep learning in the aspect of image processing is mature, but the image can only express two-dimensional information, and the two-dimensional information of the image can be matched with the three-dimensional information of the HD MAP by means of the multi-source data fusion technology. In the aspect of improving the precision, the precision improvement can be realized by adopting multiple means of continuous image frame tracking, pose graph optimization and GPS (global positioning system) deviation correction, and the influence of factors such as low single image quality and GPS signal lock losing on the precision is reduced.
Example one
A traffic signboard updating method, referring to fig. 1, the traffic signboard updating method mainly comprises the following steps:
s1, segmenting the semantic features of the traffic signboard in each frame of image data based on the deep learning semantic segmentation network, and extracting the outline area of the traffic signboard.
As an embodiment, the deep learning semantic segmentation network is used for segmenting traffic signboard semantic features in each frame of image data and extracting traffic signboard contour regions, and the method comprises the following steps: initializing the first frame of image data based on the pose data comprising the GNSS information.
As an embodiment, the initializing the first frame of image data based on the pose data containing GNSS information then includes: and detecting the traffic signboard elements in each frame of image data based on a deep learning target detection network, and acquiring a target rectangular frame comprising the traffic signboard.
It should be noted that the data used in the present invention includes a forward-looking image, camera internal and external parameters, high-precision MAP HD MAP data, GPS track data, IMU inertial navigation data, and odometer information. The vehicle is provided with a camera, a Global Positioning System (GPS), an inertial navigation unit (IMU) and a milemeter respectively in the driving process, and image data, GPS track data, IMU inertial navigation data and milemeter information in the driving process of the vehicle are acquired respectively.
The coordinate system of the HD MAP data is an absolute coordinate system, and if the vision 2D perception result is associated with the HD MAP element, the position and posture data containing GNSS information is needed to initialize the first frame of image data, so that the reliability of the initial position information of the camera is ensured, and the matching operation at the later stage is facilitated.
After the pose information is initialized, the semantic features of the signboard, the upright post and the lane line element in each frame of image are segmented by utilizing a deep learning semantic segmentation network (such as BiseNet). The semantic features of the signboard, the upright rod and the lane line elements in the image are obtained in the step, a data basis is provided for subsequent pose optimization, a semantic segmentation technology is added to the device, the influence of pose graph optimization residual errors on matching accuracy is reduced, the matching accuracy in the step six is facilitated, and the robustness of the device is improved.
And respectively extracting the outer contour of the traffic signboard and the skeleton lines of the lane lines and the upright poles according to the obtained semantic segmentation result to obtain the contour area of the traffic signboard. The semantic features of the three elements are abstracted according to the expression forms of the signboard, the lane line and the upright rod, and the consistency of the data features of different sources of different elements is ensured as much as possible.
The traffic signboard semantic features in the image data are extracted by using a deep learning semantic segmentation network, and meanwhile, traffic signboard elements in each frame of image data are detected by using a deep learning target detection network, so that a target rectangular frame comprising the traffic signboard is obtained.
Specifically, a deep learning target detection network (such as YOLO) is used to detect the traffic signboard elements in each frame of image, and the traffic signboard elements are output as a target rectangular frame including the traffic signboard. The basic data of the traffic signboard used for matching is generated in the step, only the image is used as input data, the equipment cost is low, and the efficiency is high by adopting a front-edge image depth learning technology.
And S2, projecting the space area of the traffic signboard in the HD MAP of the high-precision MAP to an image coordinate system based on the pose information and the internal and external parameters of the camera.
It can be understood that in the vehicle running process, the pose is also changed, in order to avoid the occurrence of a large offset error in the camera position caused by the loss of lock of the GPS signal and further cause processing abnormity, the pose image is optimized by taking the odometer information, the IMU inertial navigation data and the GPS track data as input, and the reliability of the pose information of each frame of image is improved. Specifically, when the GPS fails, missing GPS trajectory data may be resolved according to the IMU information and the odometry information, and the attitude information is optimized.
And projecting the traffic signboard space area in the HD MAP data of the high-precision MAP to an image coordinate system based on the optimized pose information and the camera internal and external parameters to obtain the traffic signboard area under the image coordinate system.
And S3, carrying out global similarity matching on the traffic signboard outline region extracted from the image data and the traffic signboard region projected from the HD MAP data under the image coordinate system to obtain a traffic signboard matching result.
And carrying out global similarity matching on the traffic signboard outline region extracted from the image data and the traffic signboard region projected from the HD MAP data under an image coordinate system to obtain a traffic signboard matching result.
And S4, performing difference analysis on the traffic signboard matching result to acquire addition and deletion attribute information of the image data relative to the HD MAP data.
It can be understood that, after the image data is used as one data source and the high-precision MAP HD MAP is used as another data source, and the traffic signboard regions in the two data sources are globally matched, the step S4 performs difference analysis on the matching result of the traffic signboards of the two data sources obtained in the step S3, so as to obtain the add-drop attribute information, where the add-drop attribute information includes the traffic signboard contour region where the image data needs to be added and dropped relative to the HD MAP data.
And S5, updating the traffic signboard data in the HD MAP library based on the addition and deletion attribute information.
As an embodiment, updating the traffic signboard data in the HD MAP library based on the addition/deletion attribute information includes: acquiring a traffic signboard target rectangular frame corresponding to a traffic signboard outline area needing to be added and deleted; and updating the traffic signboard data in the HP MAP base based on the traffic signboard target rectangular frame.
It can be understood that the traffic signboard matching result is subjected to differentiation analysis to obtain the addition and deletion attribute information, namely the traffic signboard area where the image data needs to be added and deleted relative to the HD MAP data.
And finding a corresponding target rectangular frame comprising the traffic signboard according to the traffic signboard outline area needing to be added and deleted, and performing addition and deletion updating operation on the traffic signboard data in the HD MAP database based on the target rectangular frame of the traffic signboard, namely realizing the updating of the traffic signboard in the HA MAP data according to the image data.
Example two
A traffic signboard updating method, referring to fig. 2, for image data, a target rectangular frame of a traffic signboard is detected from the image data based on a deep learning target detection network, semantic features of the traffic signboard are extracted from the image data based on a deep learning semantic segmentation network, and a traffic signboard outline area is extracted.
And resolving the pose information based on the camera internal and external parameters, the GPS information, the IMU inertial navigation information and the odometer information, and projecting the traffic signboard space region in the HD MAP data to an image coordinate system based on the pose information to obtain the traffic signboard region under the image coordinate system.
And carrying out global similarity matching on the traffic signboard outline region extracted from the image data and the traffic signboard region projected by the HD MAP data to obtain a traffic signboard matching result.
And performing differentiation analysis on the matching result of the traffic signboard to acquire the addition and deletion attribute information, wherein the addition and deletion attribute information comprises a traffic signboard outline area of which the image data needs to be added and deleted relative to the HD MAP data. And based on the traffic sign outline area needing to be added and deleted, finding a corresponding traffic sign target rectangular frame, and based on the traffic sign target rectangular frame needing to be added and deleted, adding and deleting the traffic sign data in the HD MAP library and updating.
EXAMPLE III
A traffic signboard updating system, referring to fig. 3, includes an extracting module 301, a projecting module 302, a matching module 303, a difference analyzing module 304 and an updating module 305, wherein:
the extraction module 301 is configured to segment traffic signboard semantic features in each frame of image data based on a deep learning semantic segmentation network, and extract a traffic signboard outline region; the projection module 302 is used for projecting the space area of the traffic signboard in the high-precision MAP HD MAP to an image coordinate system based on the pose information and the camera internal and external parameters; the matching module 303 is configured to perform global similarity matching on the traffic signboard contour region extracted from the image data and the traffic signboard region projected from the HD MAP data in the image coordinate system to obtain a traffic signboard matching result; a difference analysis module 304, configured to perform difference analysis on the traffic signboard matching result, and obtain addition/deletion attribute information of the image data relative to the HD MAP data; an updating module 305, configured to update the traffic signboard data in the HD MAP library based on the add/delete attribute information.
It can be understood that the traffic signboard updating system provided by the present invention corresponds to the traffic signboard updating method provided by each of the foregoing embodiments, and the related technical features of the traffic signboard updating system may refer to the related technical features of the traffic signboard updating method, and are not described herein again.
Example four
Referring to fig. 4, fig. 4 is a schematic view of an embodiment of an electronic device according to an embodiment of the invention. As shown in fig. 4, an embodiment of the present invention provides an electronic device, which includes a memory 410, a processor 420, and a computer program 411 stored in the memory 410 and executable on the processor 420, and when the processor 420 executes the computer program 411, the following steps are implemented: segmenting traffic signboard semantic features in each frame of image data based on a deep learning semantic segmentation network, and extracting a traffic signboard outline area; based on the pose information and the camera internal and external parameters, projecting the traffic signboard space area in the high-precision MAP HD MAP to an image coordinate system; carrying out global similarity matching on the traffic signboard outline region extracted from the image data and the traffic signboard region projected from the HD MAP data under an image coordinate system to obtain a traffic signboard matching result; carrying out difference analysis on the matching result of the traffic signboard to acquire addition and deletion attribute information of the image data relative to HD MAP data; and updating the traffic signboard data in the HD MAP library based on the addition and deletion attribute information.
EXAMPLE five
Referring to fig. 5, fig. 5 is a schematic diagram of an embodiment of a computer-readable storage medium according to the present invention. As shown in fig. 5, the present embodiment provides a computer-readable storage medium 500 having a computer program 511 stored thereon, the computer program 511 implementing the following steps when executed by a processor: segmenting traffic signboard semantic features in each frame of image data based on a deep learning semantic segmentation network, and extracting a traffic signboard outline area; based on the pose information and the camera internal and external parameters, projecting the traffic signboard space area in the high-precision MAP HD MAP to an image coordinate system; carrying out global similarity matching on the traffic signboard outline region extracted from the image data and the traffic signboard region projected from the HD MAP data under an image coordinate system to obtain a traffic signboard matching result; carrying out difference analysis on the matching result of the traffic signboard to acquire addition and deletion attribute information of the image data relative to HD MAP data; and updating the traffic signboard data in the HD MAP library based on the addition and deletion attribute information.
Compared with the prior art, the traffic signboard updating method, the traffic signboard updating system, the electronic device and the storage medium provided by the embodiment of the invention have the following advantages:
(1) instead of using only a deep learning target detection mode, a multi-mode of deep learning target detection and semantic segmentation target is adopted to improve matching accuracy.
(2) Does not depend on laser radar data and has low cost.
(3) And by adopting an image deep learning technology, the updating efficiency is greatly improved.
It should be noted that, in the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to relevant descriptions of other embodiments for parts that are not described in detail in a certain embodiment.
As will be appreciated by one skilled in the art, 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 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 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. 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 invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (9)
1. A traffic signboard updating method is characterized by comprising the following steps:
segmenting traffic signboard semantic features in each frame of image data based on a deep learning semantic segmentation network, and extracting a traffic signboard outline area;
based on the pose information and the camera internal and external parameters, projecting the traffic signboard space area in the high-precision MAP HD MAP to an image coordinate system;
carrying out global similarity matching on the traffic signboard outline region extracted from the image data and the traffic signboard region projected from the HD MAP data under an image coordinate system to obtain a traffic signboard matching result;
performing difference analysis on the traffic signboard matching result to acquire addition and deletion attribute information of the image data relative to HD MAP data;
and updating the traffic signboard data in the HD MAP library based on the addition and deletion attribute information.
2. The method for updating the traffic signboard of claim 1, wherein the deep learning semantic segmentation network is used for segmenting the semantic features of the traffic signboard in each frame of image data and extracting the contour region of the traffic signboard, and the method comprises the following steps:
initializing the first frame of image data based on the pose data comprising the GNSS information.
3. The method for updating a traffic signboard of claim 2, wherein the initializing a first frame of image data based on pose data including GNSS information comprises:
and detecting the traffic signboard elements in each frame of image data based on a deep learning target detection network, and acquiring a target rectangular frame comprising the traffic signboard.
4. The method for updating the traffic signboard of claim 1, wherein the segmenting the semantic features of the traffic signboard in each frame of image data based on the deep learning semantic segmentation network and extracting the contour region of the traffic signboard comprises:
segmenting semantic features of traffic signboard, upright stanchion and lane line elements in each frame of image data based on a deep learning semantic segmentation network;
according to the semantic features of the traffic signboard, the upright post and the lane line element, extracting the outer contour of the traffic signboard and extracting the skeleton line of the lane line and the upright post respectively to obtain the contour area of the traffic signboard.
5. The method for updating a traffic signboard of claim 2, wherein the initializing the first frame of image data based on the pose data containing GNSS information further comprises optimizing the pose information, comprising:
and optimizing the pose information by taking the odometer information, the IMU inertial navigation data and the GPS track data as input, and acquiring the optimized pose information.
6. The method for updating a traffic signboard of claim 3, wherein the addition/deletion attribute information includes a traffic signboard profile region to be added/deleted, and accordingly, the updating of the traffic signboard data in the HD MAP library based on the addition/deletion attribute information includes:
acquiring a traffic signboard target rectangular frame corresponding to a traffic signboard outline area needing to be added and deleted;
and updating the traffic signboard data in the HP MAP base based on the traffic signboard target rectangular frame.
7. A traffic sign update system, comprising:
the extraction module is used for segmenting the semantic features of the traffic signboard in each frame of image data based on the deep learning semantic segmentation network and extracting the outline area of the traffic signboard;
the projection module is used for projecting the space area of the traffic signboard in the high-precision MAP HD MAP to an image coordinate system based on the pose information and the camera internal and external parameters;
the matching module is used for carrying out global similarity matching on the traffic signboard outline region extracted from the image data and the traffic signboard region projected from the HD MAP data under the image coordinate system to obtain a traffic signboard matching result;
the difference analysis module is used for carrying out difference analysis on the matching result of the traffic signboard to acquire addition and deletion attribute information of the image data relative to the HD MAP data;
and the updating module is used for updating the traffic signboard data in the HD MAP base based on the addition and deletion attribute information.
8. An electronic device comprising a memory, a processor for implementing the steps of the traffic sign updating method according to any one of claims 1-6 when executing a computer management like program stored in the memory.
9. A computer-readable storage medium, having stored thereon a computer management-like program, which when executed by a processor, carries out the steps of the traffic sign updating method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111422396.5A CN114120279A (en) | 2021-11-26 | 2021-11-26 | Traffic signboard updating method, system, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111422396.5A CN114120279A (en) | 2021-11-26 | 2021-11-26 | Traffic signboard updating method, system, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114120279A true CN114120279A (en) | 2022-03-01 |
Family
ID=80370226
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111422396.5A Pending CN114120279A (en) | 2021-11-26 | 2021-11-26 | Traffic signboard updating method, system, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114120279A (en) |
-
2021
- 2021-11-26 CN CN202111422396.5A patent/CN114120279A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108765487B (en) | Method, device, equipment and computer readable storage medium for reconstructing three-dimensional scene | |
| CN114236552B (en) | Repositioning method and repositioning system based on laser radar | |
| CN107167826B (en) | Vehicle longitudinal positioning system and method based on variable grid image feature detection in automatic driving | |
| CN108829116B (en) | Barrier-avoiding method and equipment based on monocular cam | |
| KR102206834B1 (en) | Method and system for detecting changes in road-layout information | |
| CN111830953A (en) | Vehicle self-positioning method, device and system | |
| WO2021254019A1 (en) | Method, device and system for cooperatively constructing point cloud map | |
| CN111508258A (en) | Positioning method and device | |
| EP4194807A1 (en) | High-precision map construction method and apparatus, electronic device, and storage medium | |
| Wu et al. | Hierarchical partial matching and segmentation of interacting cells | |
| CN112923938B (en) | Map optimization method, device, storage medium and system | |
| CN112837241A (en) | Method and device for removing image-building ghost and storage medium | |
| CN114111817B (en) | Vehicle positioning method and system based on SLAM map and high-precision map matching | |
| CN114120279A (en) | Traffic signboard updating method, system, electronic equipment and storage medium | |
| WO2020118623A1 (en) | Method and system for generating an environment model for positioning | |
| KR101962388B1 (en) | Method and System for Automatically Generating Satellite Image Map | |
| Wong et al. | Single camera vehicle localization using feature scale tracklets | |
| US11580666B2 (en) | Localization and mapping method and moving apparatus | |
| Li et al. | RF-LOAM: Robust and Fast LiDAR Odometry and Mapping in Urban Dynamic Environment | |
| CN114791936A (en) | Storage, efficient editing and calling method for passable area of unmanned vehicle | |
| CN114116749A (en) | Road marking updating method, system, electronic equipment and storage medium | |
| CN114140770A (en) | Automatic dynamic target identification method | |
| CN113516664B (en) | Visual SLAM method based on semantic segmentation dynamic points | |
| CN114155509A (en) | Method and system for extracting passable road area | |
| CN113551678B (en) | Method for constructing map, method for constructing high-precision map and mobile device |
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 |