CN110717007A - Map data positioning system and method applying roadside feature identification - Google Patents
Map data positioning system and method applying roadside feature identification Download PDFInfo
- Publication number
- CN110717007A CN110717007A CN201910977908.0A CN201910977908A CN110717007A CN 110717007 A CN110717007 A CN 110717007A CN 201910977908 A CN201910977908 A CN 201910977908A CN 110717007 A CN110717007 A CN 110717007A
- Authority
- CN
- China
- Prior art keywords
- roadside
- positioning
- map
- mobile carrier
- road
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- 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
Abstract
The invention provides a map data positioning system and method applying roadside feature identification, which are used for measuring by looking down a road and establishing a road image map comprising a plurality of feature points; detecting the surrounding driving environment when the mobile carrier moves to obtain a point cloud picture, identifying whether the characteristic points are included or not, filtering the dynamic object, and establishing a positioning map data according to the road image map, the residual characteristic points in the point cloud picture and the set characteristic attributes of the plurality of road side characteristic points; when a moving carrier runs, at least two roadside characteristic points in front are judged according to the positioning diagram data and are used as reference points to calculate the course angle of the moving carrier, and then the position of the moving carrier is calculated. The positioning map established by the invention has the advantages of low data quantity, low operation complexity, high reliability and the like, and can be used for the automatic driving mobile carrier to estimate the high-precision position.
Description
Technical Field
The present invention relates to positioning technologies, and more particularly, to a system and method for positioning image data by using roadside feature recognition.
Background
An autonomous vehicle (abbreviated as autonomous vehicle) is also called as an unmanned vehicle, can sense the surrounding environment and navigation without manual operation, and can sense the surrounding environment by technologies such as radar, optical radar (Lidar), satellite navigation and computer vision. Advanced control systems can convert sensed data into appropriate navigation paths, obstacles, and associated signs.
Common positioning methods for self-driving include triangulation, simultaneous localization and Mapping (SLAM), Tag (Tag) and Fingerprint-Based Mapping. The triangulation location method needs to measure the distances between a target object and three known position reference points and solve the intersection point of a circle with the three reference points as the circle center, but has the defects that more than three reference points are needed, no course information exists, and the location precision is low; the synchronous positioning and map construction positioning method scans a driving path point cloud picture by a radar, estimates the position of the vehicle by a point cloud comparison method, however, the time consumption is very long for establishing the point cloud picture, the data amount is large, about 150MB data amount is needed in 1 kilometer, the positioning cannot be performed in an environment with few point cloud characteristics, and the absolute course of the vehicle is corrected by a Differential Global Positioning System (DGPS) and a vehicle steering dynamic model; the label positioning method uses the principle of trigonometric function, scans the label of a known point by an optical radar, and then reversely deduces the position of the vehicle, for example, if the coordinate of a known bus stop board is (x, y), the distance between the vehicle and the bus stop board is d, and the included angle is theta, the position of the vehicle is (x-dsin theta, y-dcos theta), but the technology also needs to correct the absolute course of the vehicle by a Differential Global Positioning System (DGPS) and a vehicle steering dynamic model, and the label is difficult to be established and is easy to be shielded by road trees, pedestrians or other obstacles; the map positioning method based on the fingerprint firstly scans a driving path point cloud picture by an optical radar from a first vehicle, and a second vehicle compares the point cloud picture to estimate the position of the vehicle, but the time for establishing the point cloud picture is consumed, although the data amount is less than that of a synchronous positioning and map construction positioning method, the data needs encoding calculation in a grid-by-grid manner, the calculation amount is larger, and the problem that the positioning cannot be performed under the environment with less point cloud characteristics is also solved.
Disclosure of Invention
Therefore, the present invention provides a map data positioning system and method using roadside feature identification, which effectively solve the above problems, and the specific architecture and implementation thereof are described in detail below:
the invention mainly aims to provide a map data positioning system and method applying roadside feature identification, which are used for obtaining a road image map for overlooking a road from the upper part of the road and a point cloud map of a driving environment from a plane respectively, quickly distinguishing a road space and a roadside space from the road image map by utilizing an information space nesting technology, obtaining spatial information of a set object type, filtering out unnecessary dynamic objects, reserving static objects which can be used as roadside feature points, and establishing positioning map data with high precision and small data amount.
Another objective of the present invention is to provide a system and method for positioning road data by road side feature recognition, wherein an aerial camera is used to obtain a road image map, and a high-resolution camera is used to obtain a high-precision road map with low cost.
The present invention further provides a system and a method for positioning map data by using roadside feature identification, which further use the roadside feature points as reference points to calculate the course angle of the mobile carrier, thereby more accurately positioning the position of the mobile carrier.
To achieve the above object, the present invention provides a method for positioning image data by applying roadside feature identification, comprising: measuring by using at least one first detector for overlooking a road to establish a road image map, wherein the road image map comprises a plurality of feature points; installing at least one second detector on at least one mobile carrier, detecting the surrounding driving environment when the mobile carrier travels to obtain a point cloud picture, identifying whether the point cloud picture comprises the characteristic points, filtering at least one dynamic object in the characteristic points, and establishing a positioning map data according to the road image map, the residual characteristic points in the point cloud picture and the characteristic attributes of a plurality of roadside characteristic points; storing the positioning map data in a mobile carrier, scanning a road ahead by using a map data positioning system in the mobile carrier when the mobile carrier runs, judging at least two roadside characteristic points ahead according to the positioning map data, and calculating a course angle of the mobile carrier as a reference point; and calculating the position of the mobile carrier by utilizing the course angle of the mobile carrier and the at least two reference points.
According to the embodiment of the invention, the method for establishing the positioning map data further comprises the following steps: superposing the road image map and the point cloud picture to identify a road space and at least one road side space; filtering the dynamic objects in the feature points, and reserving a plurality of static objects as the roadside feature points; setting the characteristic attributes of the roadside characteristic points; and establishing the positioning map data according to an overlay of the road image map and the point cloud map, the roadside feature points and the feature attributes.
In summary, the roadside space divides the sidewalk, the bicycle lane and/or the building into a first roadside space and a second roadside space from inside to outside. The characteristic attributes include latitude and longitude coordinates, shape, size, and height.
According to the embodiment of the invention, the mobile carrier collects roadside images during driving, identifies at least one target object from the roadside images, and judges whether the target object is the roadside feature point or not according to the feature attributes in the positioning map data.
The invention also provides a map information positioning system, which is arranged in an on-vehicle system of a mobile carrier and used for positioning the mobile carrier by using the positioning map information established by the method, and the map information positioning system comprises: a database for storing the positioning map data, wherein the positioning map data comprises a plurality of roadside feature points and a plurality of feature attributes of the roadside feature points; a road side feature identification module, which scans the front of the road and judges at least two road side feature points according with the feature attributes according to the positioning diagram; a course angle estimation module of the mobile carrier, which uses at least two roadside characteristic points as reference points to calculate a course angle of the mobile carrier; and the mobile carrier position estimation module is used for calculating the position of the mobile carrier by utilizing the course angle of the mobile carrier and the at least two reference points.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a flow chart of a graph resource positioning method using roadside feature identification according to the present invention;
FIG. 2 is a detailed flowchart of the present invention for establishing positioning data;
FIGS. 3A to 3D are schematic views illustrating a process of establishing a positioning map according to the present invention;
FIG. 4 is a block diagram of a positioning system of the present invention;
FIG. 5 is a flow chart of the present invention for identifying roadside feature points using positioning map data;
FIG. 6 is a schematic diagram of calculating the heading angle and position of the mobile carrier according to the present invention.
10 road space, 12 first road side space, 14 second road side space, 20 environment detection device, 22 map data positioning system, 222 database, 224 road side feature identification module, 226 mobile carrier course angle estimation module, 228 mobile carrier position estimation module.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
The invention provides a map data positioning system and method applying roadside feature identification, which collects a high-precision road image map from the air, then is overlapped into a cloud point map around the running of a mobile carrier, quickly positions out the area of a road and a roadside, classifies dynamic objects and static objects in the image, deletes the dynamic objects and only reserves the static objects, can greatly reduce the data amount of positioning map data, can calculate the position by only two reference points, does not need to adopt a triangular positioning method, greatly reduces the operation complexity, can reach the accuracy of a common point when applied to the positioning of an automatically-driven mobile carrier, and obviously ensures the accuracy and the safety of an automatically-driven vehicle when compared with the accuracy error of the common satellite positioning within an acceptable range of 1-2 meters.
Referring to fig. 1, a flowchart of a map data positioning method applying roadside feature identification according to the present invention mainly includes four steps, step S10 is first to establish a positioning map data for a mobile vehicle (e.g., an autonomous vehicle); step S12, when the mobile vehicle actually runs, identifying roadside feature points; step S14 starts to correct the position of the mobile vehicle, estimates the heading angle of the mobile vehicle, and step S16 calculates the position of the mobile vehicle. The detailed process is as follows.
FIG. 2 is a detailed flow chart of the present invention for establishing positioning data. Firstly, step S102 is to use at least one first detector to look down the road from the top of the road for measurement, and establish a road image map, where the first detector may be an aircraft equipped with an image acquisition device, such as an aerial camera, an unmanned aerial vehicle, a remote control plane, and the like, and the image acquisition device is a camera or a video camera, and a high-precision image can be acquired as long as the image acquisition device with high resolution is installed on the aircraft, so that the road image map includes a plurality of feature points, such as dynamic objects, such as vehicles, pedestrians, and the like, and static objects, such as traffic lights, stop boards, signboards, buildings, traffic signs, and the like, and the determination of the dynamic objects presets that the vehicles on the road space, the pedestrians, and the moving objects on the roadside space are dynamic objects, and deletes the vehicles, the pedestrians, and; step S104, at least one second detector is arranged on at least one mobile carrier, the second detector can be an optical radar (Lidar) or a camera, the camera can generate a three-dimensional image by utilizing a three-dimensional image technology, the mobile carrier can be an automobile, when the mobile carrier moves, the second detector detects the driving environment around the mobile carrier, point clouds are established on the surface of the scanned object, the point clouds are used for representing the surface shape of the object, a more accurate model can be established by the point clouds with higher density, a deep and three-dimensional point cloud image (point cloud) is obtained, and the included information is geometric information of the object and whether the geometric information includes the characteristic points or not is identified; then, as shown in step S106, the road image map and the point cloud map are superimposed by means of information space nesting, and a road space and a road side space are identified and classified, wherein the road side space is defined widely, and a sidewalk, a bicycle lane and/or a building can be divided into a first road side space and a second road side space from inside to outside; in step S107, the dynamic objects in the feature points are filtered, only the static objects are retained as the roadside feature points, in step S108, feature attributes of a plurality of roadside feature points are set, including longitude and latitude coordinates, shapes, sizes, heights and the like of the roadside feature points, and finally, in step S109, a positioning map resource is established according to the superposition map of the road image map and the point cloud map, the remaining roadside feature points (static objects) in the map and the feature attributes of the roadside feature points.
When there is no static object in the road side space, representing no road side feature point, the road side space can be directly deleted, and only the road space is left, so as to reduce the data amount of the positioning map data.
Please refer to fig. 3A to fig. 3D, which are schematic diagrams illustrating a process of establishing a positioning map according to the present invention. Fig. 3A is a high-precision road image map taken from above, which shows that parts are roads and parts are not roads (such as buildings, parks, parking lots, etc.) from above, and fig. 3B is a 3D point cloud map detected and described by a mobile carrier, from which characteristic points such as roads, vehicles, pedestrians, buildings, traffic lights, stop boards, signboards, traffic signs, etc. can be identified through the position of the mobile carrier and the geometric spatial information of the high-precision roads; after the point cloud map of fig. 3B is overlapped with the road image map of fig. 3A, the overlay of fig. 3C is obtained, and the road space 10 and at least one road side space 12, 14 are classified on the overlay, for example, the first road side space 12 is a bicycle dedicated road, the second road side space 14 is a pedestrian road, or the first road side space 12 is a pedestrian road, and the second road side space 14 is a building or a building, when the positioning map is made, since dynamic objects such as vehicles and pedestrians cannot be used as road side feature points, the dynamic objects are deleted, and if the second road side space 14 has no static objects, the road side space can also be deleted. The finally created positioning map is shown in fig. 3D, the roadside feature points in the road space include traffic lights, and the roadside feature points in the road space include landmarks such as buildings, towers, and traffic signs, but this is only one embodiment, and all the objects that are featured and can be used as landmarks or feature points can be used as roadside feature points, such as signs of convenience stores or fast food restaurants, signs of gas stations, and the like.
The feature attributes of the roadside feature points are set according to different objects, such as the size, height and shape of a red street lamp, the size, height and shape of a bus stop board, the size, height and shape of a shop sign, and the like, and are recorded in the positioning map data one by one.
After the positioning diagram data is established, the positioning diagram data can be stored in a diagram data positioning system of the cloud platform or the mobile carrier, and the diagram data positioning system can update the latest information from the cloud periodically. The map information positioning system can be arranged in an on-board system of the mobile carrier and outputs the position information of the mobile carrier after operation. As shown in fig. 4, the architecture diagram of the positioning system 22 of the present invention includes a database 222, a roadside feature identification module 224, a mobile carrier course angle estimation module 226 and a mobile carrier position estimation module 228, wherein the database 222 stores positioning diagram data, and the positioning diagram data includes a plurality of roadside feature points and a plurality of feature attributes of the roadside feature points; the environmental detection device 20 arranged on the mobile carrier scans the road ahead, and transmits the scanning result to the roadside feature identification module 224, and the roadside feature identification module 224 judges whether feature points meeting the feature attributes exist in the scanned image according to the positioning diagram data, and if at least two feature points meeting the feature attributes exist, the feature points are used as reference points; the mobile carrier course angle estimation module 226 calculates a mobile carrier course angle of the mobile carrier by using the reference point; the mobile carrier position estimation module 228 calculates the position of the mobile carrier by using the heading angle of the mobile carrier and the reference point.
In step S12 of fig. 1, a detailed flowchart of identifying roadside features when the mobile vehicle is traveling is shown in fig. 5, where the environment detection device 20 installed on the mobile vehicle may be a camera, a video camera, or an optical radar, collects roadside images during traveling, and uses a processor of the on-board system to identify at least one target object by using an image identification processing technique, and determines whether the target object is a roadside feature point by using feature attributes in the positioning map data, and the determination method includes: step S122 determines whether the target object conforms to the size of the roadside feature point, if so, then step S124 determines whether the target object conforms to the shape of the roadside feature point, if so, then step S126 determines whether the target object conforms to the height of the roadside feature point, if so, then step S128 determines that the target object conforms to a certain roadside feature point, such as a traffic light; otherwise, if any of the above determinations is negative, it represents that the target object does not belong to any roadside feature point, and the determination is immediately ended in step S129.
When the heading direction of the mobile vehicle is not parallel to the road, the position of the mobile vehicle in the next second is far away from the position where the vehicle is moving forward, so in the present invention, for precise positioning, a technique for calculating the heading angle of the mobile vehicle is added as described in step S14 of fig. 1, and fig. 6 is a schematic diagram of calculating the heading angle and position of the mobile vehicle in the present invention. When the mobile carrier runs, a processor of the vehicle-mounted system judges at least two road side characteristic points in front according to the positioning diagram and calculates a course angle of the mobile carrier as a reference point. Suppose the coordinates of the mobile carrier are (x)v,yv) The coordinates of the roadside feature points are (x)1,y1) Then, then
xv1＝x1-R1sin(θv+φ1)＝x1-R1sinθvcosφ1-R1cosθvsinφ1＝x1-(R1cosφ1)α-(R1sinφ1)β
yv1＝y1-R1cos(θv+φ1)＝y1-R1cosθvcosφ1+R1sinθvsinφ1＝y1+(R1sinφ1)α-(R1cosφ1)β
Wherein α ═ sin θv，β＝cosθv。
Similarly, the coordinate of another roadside feature point is (x)0,y0) Then, the coordinates of the mobile carrier are calculated as follows: x is the number ofv0＝x0-(R0cosφ0)α-(R0sinφ0)β
yv0＝y0-(R0sinφ0)α-(R0cosφ0)β
Due to xv0＝xv1And y isv0＝yv1In combination with the above formula, can be described as Y ═ HX, where
X＝[α β]T，
Y＝[x0-x1y0-y1]TAnd is and
thus obtaining X ═ H-1Y。
X is abovev0＝xv1And y isv0＝yv1Will solve for theta firstvAnd obtaining an included angle between the vehicle head and the straight line, namely the course angle of the moving carrier. By the method, only two roadside feature points are needed to be used as reference points, and the position of the mobile carrier can be calculated without obtaining three reference points as in a triangulation method.
Then, the position of the mobile carrier is calculated as described in step S16 in fig. 1. Calculating the position of the mobile carrier according to the at least two mobile carriers derived from the at least two reference points as follows:
in summary, the image data positioning system and method using roadside feature identification provided by the present invention collect high-precision road image maps by using low-cost aerial photography, superimpose the information space with the point cloud images made by the surrounding road environment collected during traveling, classify the road space and the roadside space, dynamic objects and static objects, and delete the dynamic objects and the roadside space without any object, thereby greatly reducing the data amount.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and application ranges. In view of the above, the present disclosure should not be construed as limiting the invention.
Claims (15)
1. A map resource positioning method applying roadside feature identification is characterized by comprising the following steps:
measuring by using at least one first detector for overlooking a road to establish a road image map, wherein the road image map comprises a plurality of feature points;
installing at least one second detector on at least one mobile carrier, detecting the surrounding driving environment when the mobile carrier travels to obtain a point cloud picture, identifying whether the point cloud picture comprises the characteristic points or not, filtering at least one dynamic object in the characteristic points, and establishing a positioning map data according to the road image map, the residual characteristic points in the point cloud picture and the set characteristic attributes of a plurality of roadside characteristic points;
storing the positioning map data in the mobile carrier, scanning a road ahead by using a map data positioning system in the mobile carrier when the mobile carrier runs, judging at least two roadside feature points according to the positioning map data, and calculating a course angle of the mobile carrier as a reference point;
and calculating the position of the mobile carrier by utilizing the course angle of the mobile carrier and the at least two reference points.
2. The method of claim 1, wherein the first detector is an aircraft with an image capture device.
3. The map resource positioning method applying roadside feature recognition according to claim 2, wherein the aircraft is an aerial camera, an unmanned aerial vehicle or a remote control plane.
4. The method of claim 1, wherein the second detector is an optical radar Lidar, a laser, a camera, or a sonar.
5. The method of claim 1, wherein the method further comprises the steps of:
superposing the road image map and the point cloud picture to identify a road space and at least one road side space;
filtering the dynamic objects in the feature points, and reserving a plurality of static objects as the roadside feature points;
setting the characteristic attributes of the roadside characteristic points;
and establishing the positioning map data according to an overlay of the road image map and the point cloud map, the roadside feature points and the feature attributes.
6. The method of claim 5, wherein the feature points include a series of dynamic objects such as vehicles and pedestrians, and a series of static objects such as traffic lights, stop boards, signs, buildings, and traffic signs.
7. The method of claim 5, wherein the roadside space divides the sidewalk, the bicycle lane and/or the building into a first roadside space and a second roadside space from inside to outside.
8. The map asset location method applying roadside feature recognition according to claim 5, wherein the feature attributes include latitude and longitude coordinates, shape, size, and height.
9. The method of claim 8, wherein the mobile vehicle collects roadside images during driving, identifies at least one target object from the roadside images, and determines whether the target object is the roadside feature point according to the feature attributes in the positioning map.
10. The method of claim 1, wherein the positioning map is stored on a cloud platform or a map positioning system of the mobile vehicle, the map positioning system being located in an onboard system of the mobile vehicle.
11. A map data positioning system is arranged in an on-board system of a mobile carrier and carries out positioning on the mobile carrier by utilizing the positioning map data established by a request item 1, and is characterized by comprising:
a database for storing the positioning map data, wherein the positioning map data comprises a plurality of roadside feature points and a plurality of feature attributes of the roadside feature points;
a road side feature identification module, which scans the front of the road and judges at least two road side feature points according with the feature attributes according to the positioning diagram;
a course angle estimation module of the mobile carrier, which uses at least two roadside characteristic points as reference points to calculate a course angle of the mobile carrier;
and the mobile carrier position estimation module is used for calculating the position of the mobile carrier by utilizing the course angle of the mobile carrier and the at least two reference points.
12. The map data positioning system of claim 11, wherein the roadside features comprise a series of static objects such as traffic lights, stop boards, signs, buildings, traffic signs.
13. The map asset location system of claim 11, wherein the characteristic attributes comprise longitude and latitude coordinates, shape, size and height.
14. The map data positioning system of claim 11, wherein the mobile vehicle comprises an environment detection device for scanning images of a road ahead.
15. The map resource location system of claim 14, wherein the environment detection device is a camera, video camera, or optical radar.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910977908.0A CN110717007A (en) | 2019-10-15 | 2019-10-15 | Map data positioning system and method applying roadside feature identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910977908.0A CN110717007A (en) | 2019-10-15 | 2019-10-15 | Map data positioning system and method applying roadside feature identification |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110717007A true CN110717007A (en) | 2020-01-21 |
Family
ID=69211666
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910977908.0A Pending CN110717007A (en) | 2019-10-15 | 2019-10-15 | Map data positioning system and method applying roadside feature identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110717007A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115390116A (en) * | 2022-09-09 | 2022-11-25 | 紫清智行科技(北京)有限公司 | Dynamic mapping method and device based on roadside image recognition and satellite image |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108151729A (en) * | 2017-12-12 | 2018-06-12 | 财团法人车辆研究测试中心 | Image positioning method and its image positioning apparatus |
| CN108196535A (en) * | 2017-12-12 | 2018-06-22 | 清华大学苏州汽车研究院（吴江） | Automated driving system based on enhancing study and Multi-sensor Fusion |
| CN108303721A (en) * | 2018-02-12 | 2018-07-20 | 北京经纬恒润科技有限公司 | A kind of vehicle positioning method and system |
| CN109583409A (en) * | 2018-12-07 | 2019-04-05 | 电子科技大学 | A kind of intelligent vehicle localization method and system towards cognitive map |
| CN109791052A (en) * | 2016-09-28 | 2019-05-21 | 通腾全球信息公司 | For generate and using locating reference datum method and system |
| EP3516422A1 (en) * | 2016-09-29 | 2019-07-31 | The Charles Stark Draper Laboratory, Inc. | Autonomous vehicle: vehicle localization |
-
2019
- 2019-10-15 CN CN201910977908.0A patent/CN110717007A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109791052A (en) * | 2016-09-28 | 2019-05-21 | 通腾全球信息公司 | For generate and using locating reference datum method and system |
| EP3516422A1 (en) * | 2016-09-29 | 2019-07-31 | The Charles Stark Draper Laboratory, Inc. | Autonomous vehicle: vehicle localization |
| CN108151729A (en) * | 2017-12-12 | 2018-06-12 | 财团法人车辆研究测试中心 | Image positioning method and its image positioning apparatus |
| CN108196535A (en) * | 2017-12-12 | 2018-06-22 | 清华大学苏州汽车研究院（吴江） | Automated driving system based on enhancing study and Multi-sensor Fusion |
| CN108303721A (en) * | 2018-02-12 | 2018-07-20 | 北京经纬恒润科技有限公司 | A kind of vehicle positioning method and system |
| CN109583409A (en) * | 2018-12-07 | 2019-04-05 | 电子科技大学 | A kind of intelligent vehicle localization method and system towards cognitive map |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115390116A (en) * | 2022-09-09 | 2022-11-25 | 紫清智行科技(北京)有限公司 | Dynamic mapping method and device based on roadside image recognition and satellite image |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11755024B2 (en) | Navigation by augmented path prediction | |
| US11781870B2 (en) | Crowd sourcing data for autonomous vehicle navigation | |
| KR102503388B1 (en) | Object avoidance method during autonomous navigation | |
| US11874119B2 (en) | Traffic boundary mapping | |
| JP7090597B2 (en) | Methods and systems for generating and using location reference data | |
| RU2668459C1 (en) | Position evaluation device and method | |
| JP6714688B2 (en) | System and method for matching road data objects to generate and update an accurate road database | |
| Schreiber et al. | Laneloc: Lane marking based localization using highly accurate maps | |
| CN111856491B (en) | Method and apparatus for determining geographic position and orientation of a vehicle | |
| US10127461B2 (en) | Visual odometry for low illumination conditions using fixed light sources | |
| US20220282989A1 (en) | Fully aligned junctions | |
| CN111551958A (en) | Mining area unmanned high-precision map manufacturing method | |
| US20120327188A1 (en) | Vehicle-Mounted Environment Recognition Apparatus and Vehicle-Mounted Environment Recognition System | |
| US20220035378A1 (en) | Image segmentation | |
| US20210180958A1 (en) | Graphic information positioning system for recognizing roadside features and method using the same | |
| CN113743171A (en) | Target detection method and device | |
| Moras et al. | Drivable space characterization using automotive lidar and georeferenced map information | |
| US20190293444A1 (en) | Lane level accuracy using vision of roadway lights and particle filter | |
| CN110717007A (en) | Map data positioning system and method applying roadside feature identification | |
| US20200020126A1 (en) | Host vehicle position estimation device | |
| TW202115616A (en) | Map data positioning system and method using roadside feature recognition having the advantages of low data volume, low computational complexity, high reliability | |
| Fuerstenberg et al. | Feature-level map building and object recognition for intersection safety applications | |
| Meguro et al. | Automatic Orthographic Road Image Generation Using in Vehicle Sensors for ADAS | |
| CN113390422B (en) | Automobile positioning method and device and computer storage medium | |
| KR102603877B1 (en) | Precise Vehicle Positioning Method and 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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200121 |
|
| WD01 | Invention patent application deemed withdrawn after publication |