CN115046562B - Low-cost high-precision automatic driving automobile positioning method - Google Patents
Low-cost high-precision automatic driving automobile positioning method Download PDFInfo
- Publication number
- CN115046562B CN115046562B CN202210393023.8A CN202210393023A CN115046562B CN 115046562 B CN115046562 B CN 115046562B CN 202210393023 A CN202210393023 A CN 202210393023A CN 115046562 B CN115046562 B CN 115046562B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- module
- position information
- information
- 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
- 238000000034 method Methods 0.000 title claims abstract description 36
- 239000003550 marker Substances 0.000 claims abstract description 56
- 238000012545 processing Methods 0.000 claims description 16
- 238000000605 extraction Methods 0.000 claims description 6
- 238000003709 image segmentation Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000007613 environmental effect Effects 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000010365 information processing Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
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
- G01C21/34—Route searching; Route guidance
- G01C21/3407—Route searching; Route guidance specially adapted for specific applications
- G01C21/343—Calculating itineraries, i.e. routes leading from a starting point to a series of categorical destinations using a global route restraint, round trips, touristic trips
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
- G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/42—Determining position
- G01S19/48—Determining position by combining or switching between position solutions derived from the satellite radio beacon positioning system and position solutions derived from a further system
- G01S19/485—Determining position by combining or switching between position solutions derived from the satellite radio beacon positioning system and position solutions derived from a further system whereby the further system is an optical system or imaging system
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Computer Networks & Wireless Communication (AREA)
- Navigation (AREA)
- Traffic Control Systems (AREA)
Abstract
According to the low-cost high-precision automatic driving automobile positioning method, the vehicle-mounted camera module is used for identifying the driving road and the environmental marker of the automobile, the relative transverse and longitudinal position relation between the camera and the lane line and the environmental marker is calculated, the general satellite positioning vehicle-mounted terminal module is used for finding the approximate position of the automobile to be positioned, the range of the automobile is determined in the high-precision map, the lane line and the environmental marker collected by the vehicle-mounted camera module are matched with the position relation of the high-precision map, high-precision positioning information of the automobile to be positioned can be obtained, and compared with the prior art, the positioning precision of the automobile to be positioned is greatly improved.
Description
Technical Field
The invention relates to the technical field of intelligent traffic control, in particular to a low-cost high-precision automatic driving automobile positioning method.
Background
With the rapid development of intelligent automobile and road cooperative technology, intelligent automobile technology is continuously innovated, and automatic driving technology is rapidly advancing to the industrialization direction. Under the industrialization requirement, the automatic driving system has high requirement on high-precision positioning, and has centimeter-level precision and better reliability. However, the high-precision positioning system currently applied to the automatic driving automobile is generally a combined application of satellite positioning and a high-precision map, the positioning precision is up to 30-50 cm, and the positioning reliability is not high. Although satellites can provide high-precision positioning service, the cost is extremely high, and meanwhile, because the automatic driving automobile uses positioning information in real time in the running process, signals provided by the existing high-precision positioning service cannot be stably transmitted in all driving environments, and the requirements on the stability and safety of positioning of the automatic driving automobile are not met.
Disclosure of Invention
In order to solve the problem that a positioning system of an automatic driving automobile in the prior art is not suitable for industrialization in terms of precision, reliability or cost, the invention provides a method for identifying illegal vehicles at fixed points, which can realize high-precision positioning of the automatic driving automobile based on lower cost, provides high-precision, stable and reliable centimeter-level position information for the automatic driving system, and is suitable for industrialized application.
The technical scheme of the invention is as follows: a low cost high precision autopilot vehicle positioning method comprising: installing a positioning system on a vehicle to be positioned, the positioning system comprising: the positioning system is characterized by also comprising a position calculation module;
The vehicle-mounted camera module is arranged at a front windshield of a vehicle and comprises: an image acquisition function and an image processing function;
the high-precision map module provides accurate position information of the vehicle and driving environment markers for the system;
the common satellite positioning vehicle-mounted terminal module receives satellite positioning information, calculates the current position of the vehicle to be positioned and outputs position information; the common satellite positioning vehicle-mounted terminal module provides inaccurate position information of the vehicle;
After the inaccurate positioning information acquired by the common satellite positioning vehicle-mounted terminal module is input into the high-precision map module, the high-precision map module invokes the position information of traffic control equipment in front of the vehicle to be positioned; the traffic control device location information includes: lane line position information and position information of a road environment marker including: road indication signs, light poles, traffic light poles and traffic sign signs for the direction of travel of the vehicle;
The vehicle-mounted camera module matches the identified markers in the effective identification distance with the outputted road environment marker position information identified by the high-precision map module to obtain the precise environment information of the vehicle to be positioned; the accurate environment information includes: accurate position information of the lane line position and accurate position information of the road environment marker;
The position calculation module calculates the transverse distance between the vehicle to be positioned and the lane line and the longitudinal distance between the vehicle to be positioned and the road environment marker according to the accurate environment information output by the vehicle-mounted camera module;
And calculating the current accurate position information of the vehicle to be positioned by taking the lane line output by the high-precision map module as a vehicle transverse reference standard and taking the distance between the road environment marker in the vehicle driving direction and the vehicle longitudinal direction as a longitudinal reference standard and combining the distances between the vehicle to be positioned and the road environment marker and the lane line to finish the high-precision positioning of the vehicle to be positioned.
It is further characterized by:
In the position calculation module, the process of calculating the current accurate position information of the vehicle to be positioned comprises the following steps:
a1: according to the acquisition precision of the camera, setting the LA meter in front of the central axis of the camera as an acquisition reference point;
a2: calculating position information OA (xA, yA) of the vehicle to be positioned through a lane central line of a lane where the vehicle to be positioned is positioned;
setting: on the point of the acquired datum point, the transverse distance between the central axis of the camera and the central line of the lane where the vehicle to be positioned is a;
in the vehicle driving direction, the included angle between the central axis of the camera and the central line of the lane where the vehicle to be positioned is located is as follows: beta
In the vehicle running direction, the intersection point of the central axis of the camera and the central line of the lane where the vehicle to be positioned is located is: oa (xa, ya)
Then there are:
xA＝xa+(a*arcsinβ+LA)sinβ
yA＝ya+(a*arcsinβ+LA)cosβ
a3: acquiring the distance between the vehicle to be positioned and each road environment marker based on the vehicle-mounted camera module;
setting N road environment markers in total;
The distance between the camera in the vehicle-mounted camera module and the marker i is as follows: l i;
a4: obtaining the position information O' i(x′i,y′i of the vehicle to be positioned according to the accurate position information of Li and the road environment marker;
Connecting the road environment marker with a vehicle to be positioned as an endpoint to obtain a line segment L;
establish, the contained angle between camera axis and the line segment L is: alpha;
the coordinates of the road environment markers acquired by the vehicle-mounted camera module are O i(xi,yi);
Then there are:
x′i＝xi+Lisinα
y′i＝yi+Licosα
a6: the current accurate position information O (x, y) of the vehicle to be positioned is:
x＝(xA+x1+...+xi)/(i+1)
y＝(yA+y1+...+yi)/(i+1)；
In the calculation process of the current accurate position information of the vehicle to be positioned, the value of a is 10;
In the calculation process of the current accurate position information of the vehicle to be positioned, i is 1;
The vehicle-mounted camera module shoots an environment image of a path of a vehicle in real time, and completes extraction of a vehicle running environment marker based on an image processing function; the image processing function includes: image preprocessing, ROI region identification, image segmentation, feature point extraction and feature classification; the image information data output by the vehicle-mounted camera module comprises: the method comprises the steps of (1) module environment marker images and semantic information;
the vehicle-mounted camera module sends the image information data to the position calculation module through a special bus to perform feature point matching and accurate position calculation of the vehicle;
the image acquisition and processing time of the vehicle-mounted camera module is less than or equal to 50ms, and the output frequency of the output image and semantic information is more than or equal to 20Hz;
The vehicle position accuracy output by the common satellite positioning vehicle-mounted terminal module is 10m; the error of the accurate position information provided by the high-precision map module is less than or equal to 5cm;
after the inaccurate positioning information acquired by the common satellite positioning vehicle-mounted terminal module is input into the high-precision map module, the high-precision map module is used for acquiring the position information of the traffic control equipment with the radius of 150 meters and the vehicle to be positioned as the center in real time.
The invention provides a low-cost high-precision automatic driving automobile positioning method, which adopts a vehicle-mounted camera module to identify a vehicle driving road and an environment marker, calculates to obtain a relative transverse and longitudinal position relation between a camera and a lane line and the environment marker, utilizes a common satellite positioning vehicle-mounted terminal module to find the approximate position of a vehicle to be positioned, determines the range of the vehicle in a high-precision map, and matches the lane line and the environment marker acquired by the vehicle-mounted camera module with the position relation of the high-precision map, so that the high-precision positioning information of the vehicle to be positioned can be obtained, and compared with the prior art, the positioning precision of the vehicle to be positioned is greatly improved; the method utilizes the camera module, the high-precision map module and the common satellite positioning module which are usually carried by the automatic driving automobile, improves the positioning precision and reliability of the automatic driving automobile under the condition of not adding other high-cost sensors (such as a laser radar, a millimeter wave radar and the like), and realizes the low-cost high-precision positioning of the automatic driving automobile.
Drawings
FIG. 1 is a schematic diagram of a positioning system framework of an autopilot positioning method;
FIG. 2 is a schematic diagram of the location of a positioning system installed on a vehicle to be positioned;
fig. 3 is a schematic diagram of a method for calculating a lateral distance between a vehicle to be positioned and a lane line.
Detailed Description
As shown in fig. 1, the present invention includes a low-cost high-precision automatic driving car positioning method, which includes: installing a positioning system on a vehicle to be positioned, the positioning system comprising: the system comprises a vehicle-mounted camera module 1, a high-precision map module, a common satellite positioning vehicle-mounted terminal module 2 and a calculation module.
In specific implementation, as shown in fig. 2, the vehicle-mounted camera module 1 is mounted at a middle upper position of a front windshield of a vehicle, and the common satellite positioning vehicle-mounted terminal module 2 can be reused for a satellite positioning system commonly mounted in an automobile in the prior art. The high-precision map module is generally a common module of an automatic driving automobile, is realized based on the prior art, and is generally installed inside an automobile instrument desk. The position calculation module may be integrated with the in-vehicle camera module 1, or may be a separate module, mounted inside the vehicle instrument desk, or integrated into other in-vehicle modules in the vehicle instrument desk.
The common satellite positioning vehicle-mounted terminal module 2 receives satellite positioning information, calculates the current position of the vehicle to be positioned and outputs position information; the normal satellite positioning in-vehicle terminal module 2 provides inaccurate position information of the vehicle.
The common satellite positioning vehicle-mounted terminal module 2 is used for multiplexing a satellite positioning system which is usually carried by an automobile and is generally composed of a satellite signal receiving antenna 2-1 and a satellite signal processing sub-module 2-2, wherein the satellite signal receiving antenna 2-1 is generally integrated with other wireless communication antennas, the common satellite positioning vehicle-mounted terminal module 2 is generally integrated with a vehicle instrument system, and the satellite signal processing sub-module 2-2 is arranged in a vehicle instrument desk. The satellite signal receiving antenna 2-1 receives positioning information sent by a satellite positioning system, performs information processing and calculation through the satellite signal processing sub-module 2-2 to obtain position information (longitude and latitude coordinates), and performs data transmission through a vehicle bus. The position information data of the vehicle to be positioned, which is acquired by the common satellite positioning vehicle-mounted terminal module 2, is continuously updated in real time, and in a common urban road, the update frequency is ensured to be more than or equal to 20Hz, and the position error is generally about 10 meters, so that the requirements can be met.
The high-precision map module provides accurate position information of the vehicle and the driving environment marker for the system, and the position error is less than or equal to 5 cm.
After the inaccurate positioning information acquired by the general satellite positioning vehicle-mounted terminal module 2 is input into the high-precision map module, the high-precision map module invokes the position information of the traffic control equipment in front of the vehicle to be positioned, and the specific invoking range is determined by the acquisition range of the camera in the vehicle-mounted camera module 1, and the accuracy of the calculation result cannot be ensured because the data of the high-precision map module is required to be matched with the data acquired by the vehicle-mounted camera module 1.
The traffic management and control equipment position information includes: lane line position information and position information of a road environment marker including: road indication signs, light poles, traffic light poles and traffic sign signs for the direction of travel of the vehicle.
In this embodiment, after the non-precise positioning information obtained by the general satellite positioning vehicle-mounted terminal module 2 is input into the high-precision map module, the high-precision map module retrieves the position information of the traffic control device with the radius of 150 meters and the vehicle to be positioned as the center in real time. The data output by the high-precision map module comprises semantic and image information such as lane lines, road indication signs, lamp poles, traffic sign signs and the like. The marker information around the vehicle to be positioned, which is output by the high-precision map module, is continuously updated in real time, the updating frequency is more than or equal to 20Hz, the updating frequency of the marker information is kept to be the same as or higher than the updating frequency of the positioning information provided by the common satellite positioning vehicle-mounted terminal module 2, and the accuracy of the calculation result is ensured. And the surrounding environment marker information of the vehicle to be positioned is sent to a position calculation module through a special bus to perform feature point matching and accurate position calculation of the vehicle.
Theoretically, the map in the high-precision map module can provide infinite marker position information, and the system also needs information of the long-distance markers to improve positioning precision and reliability. However, in practical application, the computing and storage capabilities of the map module are considered first. The marker information in the longer distance range can cause information delay, limited by the calculation and storage capabilities of the high-precision map module. Second, the computing and storage capabilities of the location calculation module are considered. As the distance range increases, the markers generally increase in quantity, the information provided to the location calculation unit increases in quantity, stress is placed on the calculation and storage capabilities of the location calculation unit, and the calculation delay time may not meet the requirements of the automatic driving system. Finally, the effective recognition range of the camera module is also considered. The effective recognition range of the camera module in the prior art is that the recognition range of the target distance can be calculated, and is generally within 170 m. In the method, the markers in the effective recognition distance of the vehicle-mounted camera module 1 are required to be matched with the markers of the map module, so that the information range of the map module is limited by the effective recognition range of the camera module. Therefore, in the present method, the marker information providing range of the high-precision map module is determined as: the radius of 150 meters centered on the vehicle to be positioned ranges from 150m. The method not only can meet the requirement of automobile positioning precision, but also can ensure that the calculation speed can meet the time limit requirement of automatic driving automobile positioning.
The in-vehicle camera module 1 includes: an image acquisition function and an image processing function. The vehicle-mounted camera module 1 matches the identified markers in the effective identification distance with the outputted road environment marker position information identified by the high-precision map module to obtain the accurate environment information of the vehicle to be positioned; the accurate environmental information includes: accurate position information of the lane line position and accurate position information of the road environment marker.
The vehicle-mounted camera module 1 shoots an environment image of a path of a vehicle in real time, and completes extraction of a vehicle running environment marker based on an image processing function; the image processing function includes: image preprocessing, ROI region identification, image segmentation, feature point extraction and feature classification; the image information data output from the in-vehicle camera module 1 includes: the module environment marker image and semantic information.
The vehicle-mounted camera module 1 sends image information data to the position calculation module through a special bus to perform feature point matching and accurate position calculation of the vehicle. In this example, the time for acquiring and processing the image of the vehicle-mounted camera module 1 is less than or equal to 50ms, the requirement of the driving speed of the vehicle on the urban road is met, the output frequency of the output image and semantic information is more than or equal to 20Hz, the update frequency of the position information provided by the common satellite positioning vehicle-mounted terminal module 2 is kept the same as or higher than the update frequency of the positioning information, and the accuracy of the calculation result is ensured.
In specific implementation, the vehicle-mounted camera module 1 is implemented based on the existing vehicle-mounted camera module with computing capability, and can have both an image acquisition function and an image processing function. Such as: cameras such as Mobileye EyeQ, and MFC535 of contental.
The position calculation module calculates the transverse distance between the vehicle to be positioned and the lane line and the longitudinal distance between the vehicle to be positioned and the lane line according to the accurate environment information output by the vehicle-mounted camera module 1, takes the lane line output by the high-precision map module as a transverse reference standard of the vehicle, takes the longitudinal distance between the lane line and the vehicle in the running direction of the vehicle as a longitudinal reference standard, combines the distance between the vehicle to be positioned and the lane line, calculates the current accurate position information of the vehicle to be positioned, and completes the high-precision positioning of the vehicle to be positioned.
In the position calculation module, surrounding environment marker information of a locating point in the high-precision map is obtained through a special bus, an image output by the camera module and the camera environment marker information are obtained through the special bus, the two types of environment marker information are matched, namely the environment marker information of two sources is overlapped, and the marker information is confirmed to come from the same marker.
In the position calculation module, the process of calculating the current accurate position information of the vehicle to be positioned comprises the following steps:
a1: according to the acquisition precision of the camera, setting the LA meter in front of the central axis of the camera as an acquisition datum point;
a2: calculating position information OA (xA, yA) of the vehicle to be positioned through a lane central line of a lane where the vehicle to be positioned is positioned;
Setting: on the point of the acquired datum point, the transverse distance between the central axis of the camera and the central line of the lane where the vehicle to be positioned is a;
In the vehicle driving direction, the included angle between the central axis of the camera and the central line of the lane where the vehicle to be positioned is located is as follows: beta
In the vehicle driving direction, the intersection point of the central axis of the camera and the central line of the lane where the vehicle to be positioned is located is: oa (xa, ya)
Then there are:
xA＝xa+(a*arcsinβ+LA)sinβ
yA＝ya+(a*arcsinβ+LA)cosβ
a3: acquiring the distance between a vehicle to be positioned and each road environment marker based on the vehicle-mounted camera module;
setting N road environment markers in total;
The distance between the camera in the vehicle-mounted camera module and the marker i is as follows: l i;
a4: obtaining the position information O' i(x′i,y′i of the vehicle to be positioned according to the accurate position information of the Li and the road environment marker;
Connecting a road environment marker with a vehicle to be positioned as an endpoint to obtain a line segment L;
establish, the contained angle between camera axis and the line segment L is: alpha;
the coordinates of the road environment markers collected by the vehicle-mounted camera module are O i(xi,yi);
Then there are:
x′i＝xi+Lisinα
y′i＝yi+Licosα
a6: the current accurate position information O (x, y) of the vehicle to be positioned is:
x＝(xA+x1+...+xi)/(i+1)
y＝(yA+y1+...+yi)/(i+1)。
As shown in fig. 3, the distance L between the camera and the road environment marker and the angle information α between the central axis of the camera and the road environment marker are acquired by the vehicle-mounted camera module 1. From the L and α values and the position information of the road environment markers, the position O' (x, y) of the vehicle can be calculated. The location information O1 (x 1,y1) of the road environment markers can be acquired by the high-precision map module. Because a picture usually has a plurality of markers, a plurality of vehicle position information can be calculated and obtained, unreasonable data is filtered through information processing, and the average value of the rest position information (longitude and latitude) is taken to obtain the final vehicle position information. In addition, lane information, such as a second left lane, in which the vehicle is located, can be acquired through the image. The position information of the lane center line position can be obtained through the map module, and the included angle beta between the camera and the lane center line, namely the included angle between the optical axis of the camera and the lane center line, can be obtained through the camera picture.
In the embodiment, based on the acquisition precision of the vehicle-mounted camera module 1, in the calculation process of the current accurate position information of the vehicle to be positioned, the value of a is 10; in the calculation process of the current accurate position information of the vehicle to be positioned, the value of i is 1. In urban roads, accurate positioning of the vehicle to be positioned can be achieved through the transverse distance between the vehicle to be positioned and the lane lines and the distance between the vehicle to be positioned and any road environment marker.
The length, a, angle α, β of the line segment L in fig. 3 can be directly obtained from the output information of the vehicle-mounted camera, and most of the camera modules used in the existing intelligent automobiles have such information calculating and outputting functions. Coordinates O 1(x1,y1), oa (xa, ya) can be obtained from the high-precision map module output information. In this embodiment, only 1 road environment marker is selected to participate in the calculation, i.e., i=1.
Let the length of line segment L be L 1, then there are:
By O 1(x1,y1) calculates the coordinates of the vehicle to be positioned as O ' (x ', y '):
x’＝x1+L1sinα
y’＝y1+L1cosα
The coordinates of the vehicle to be positioned are calculated as OA (xA, yA) by Oa (xA, yA)
xA＝xa+(a*arcsinβ+10)sinβ
yA＝ya+(a*arcsinβ+10)cosβ
And finally, taking an average value of the results of the two calculations as a vehicle coordinate O (x, y), namely:
In actual use, the road environment markers are missing due to various reasons, and any one of the existing available road environment markers is used for calculation together with the coordinates of the lane lines, so that the positioning accuracy requirement can be met; if the calculation of the coordinates of the vehicle by the lane center line fails, one of the road environment markers that can be acquired is used as the coordinates of the vehicle O (x, y). In the method, the value of a front part a of the vehicle to be positioned is designated, the included angle beta between the central line of the lane where the vehicle to be positioned is acquired through the vehicle-mounted camera module 1, then the intersection point of the central axis of the camera and the central line of the lane where the vehicle to be positioned is found to be Oa, the coordinates OA of the vehicle to be positioned are calculated through the Oa on the central line of the lane, and the calculation of the coordinates OA is very low in acquisition failure probability unless the positioning system is damaged, so that the success rate of positioning the automatic driving vehicle based on the method is greatly improved.
In specific application, the position calculation module can be integrated in other calculation units of the vehicle, such as an automatic driving calculation unit, so that the development and measurement cost of the system is reduced, and meanwhile, the whole system can realize low-cost and high-precision positioning of the automatic driving automobile.
After the technical scheme of the invention is used, the vehicle-mounted camera module 1, the high-precision map module, the common satellite positioning vehicle-mounted terminal module 2 and the position calculation module are adopted to combine the image position information with the high-precision map, and the high-precision position information is obtained through calculation, so that the centimeter-level high-precision positioning system of the automatic driving automobile is constructed, and the high-precision stable and reliable position information is provided for the automatic driving automobile.
Claims (7)
1. A low cost high precision autopilot vehicle positioning method comprising: installing a positioning system on a vehicle to be positioned, the positioning system comprising: the positioning system is characterized by also comprising a position calculation module;
The vehicle-mounted camera module is arranged at a front windshield of a vehicle and comprises: an image acquisition function and an image processing function;
the high-precision map module provides accurate position information of the vehicle and driving environment markers for the system;
the common satellite positioning vehicle-mounted terminal module receives satellite positioning information, calculates the current position of the vehicle to be positioned and outputs position information; the common satellite positioning vehicle-mounted terminal module provides inaccurate position information of the vehicle;
After the inaccurate positioning information acquired by the common satellite positioning vehicle-mounted terminal module is input into the high-precision map module, the high-precision map module invokes the position information of traffic control equipment in front of the vehicle to be positioned; the traffic control device location information includes: lane line position information and position information of a road environment marker including: road indication signs, light poles, traffic light poles and traffic sign signs for the direction of travel of the vehicle;
The vehicle-mounted camera module matches the identified markers in the effective identification distance with the outputted road environment marker position information identified by the high-precision map module to obtain the precise environment information of the vehicle to be positioned; the accurate environment information includes: accurate position information of the lane line position and accurate position information of the road environment marker;
The position calculation module calculates the transverse distance between the vehicle to be positioned and the lane line and the longitudinal distance between the vehicle to be positioned and the road environment marker according to the accurate environment information output by the vehicle-mounted camera module;
taking a lane line output by the high-precision map module as a vehicle transverse reference standard, taking the distance between a road environment marker in the vehicle driving direction and a vehicle longitudinal direction as a longitudinal reference standard, and combining the distances between the vehicle to be positioned and the road environment marker and the lane line to calculate and obtain the current accurate position information of the vehicle to be positioned, thereby completing the high-precision positioning of the vehicle to be positioned;
In the position calculation module, the process of calculating the current accurate position information of the vehicle to be positioned comprises the following steps:
a1: according to the acquisition precision of the camera, setting the LA meter in front of the central axis of the camera as an acquisition reference point;
a2: calculating position information OA (xA, yA) of the vehicle to be positioned through a lane central line of a lane where the vehicle to be positioned is positioned;
setting: on the point of the acquired datum point, the transverse distance between the central axis of the camera and the central line of the lane where the vehicle to be positioned is a; in the vehicle driving direction, the included angle between the central axis of the camera and the central line of the lane where the vehicle to be positioned is located is as follows: the beta-form of the beta-form,
In the vehicle running direction, the intersection point of the central axis of the camera and the central line of the lane where the vehicle to be positioned is located is: oa (xa, ya), then there are:
xA＝xa+(a*arcsinβ+LA)sinβ，
yA＝ya+(a*arcsinβ+LA)cosβ；
a3: acquiring the distance between the vehicle to be positioned and each road environment marker based on the vehicle-mounted camera module;
setting N road environment markers in total;
The distance between the camera in the vehicle-mounted camera module and the marker i is as follows: l i;
a4: obtaining the position information O' i(x'i,y'i of the vehicle to be positioned according to the L i and the accurate position information of the road environment marker;
Connecting the road environment marker with a vehicle to be positioned as an endpoint to obtain a line segment L;
establish, the contained angle between camera axis and the line segment L is: alpha;
the coordinates of the road environment markers acquired by the vehicle-mounted camera module are O i(xi,yi);
Then there are:
xi′＝xi+Li sinα，
yi′＝yi+Li cosα；
a6: the current accurate position information O (x, y) of the vehicle to be positioned is:
x＝(xA+x1+...+xi)/(i+1)，
y＝(yA+y1+...+yi)/(i+1)。
2. The low-cost high-precision automatic driving automobile positioning method according to claim 1, characterized by comprising the following steps: in the calculation process of the current accurate position information of the vehicle to be positioned, the value of a is 10.
3. The low-cost high-precision automatic driving automobile positioning method according to claim 1, characterized by comprising the following steps: in the calculation process of the current accurate position information of the vehicle to be positioned, the value of i is 1.
4. The low-cost high-precision automatic driving automobile positioning method according to claim 1, characterized by comprising the following steps: the vehicle-mounted camera module shoots an environment image of a path of a vehicle in real time, and completes extraction of a vehicle running environment marker based on an image processing function; the image processing function includes: image preprocessing, ROI region identification, image segmentation, feature point extraction and feature classification; the image information data output by the vehicle-mounted camera module comprises: the method comprises the steps of (1) module environment marker images and semantic information;
And the vehicle-mounted camera module sends the image information data to the position calculation module through a special bus to perform feature point matching and accurate position calculation of the vehicle.
5. The low-cost high-precision automatic driving automobile positioning method according to claim 4, wherein the method comprises the following steps of: the image acquisition and processing time of the vehicle-mounted camera module is less than or equal to 50ms, and the output frequency of the output image and semantic information is more than or equal to 20Hz.
6. The low-cost high-precision automatic driving automobile positioning method according to claim 1, characterized by comprising the following steps: the vehicle position accuracy output by the common satellite positioning vehicle-mounted terminal module is 10m; and the error of the accurate position information provided by the high-precision map module is less than or equal to 5cm.
7. The low-cost high-precision automatic driving automobile positioning method according to claim 1, characterized by comprising the following steps: after the inaccurate positioning information acquired by the common satellite positioning vehicle-mounted terminal module is input into the high-precision map module, the high-precision map module is used for acquiring the position information of the traffic control equipment with the radius of 150 meters and the vehicle to be positioned as the center in real time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210393023.8A CN115046562B (en) | 2022-04-15 | 2022-04-15 | Low-cost high-precision automatic driving automobile positioning method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210393023.8A CN115046562B (en) | 2022-04-15 | 2022-04-15 | Low-cost high-precision automatic driving automobile positioning method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115046562A CN115046562A (en) | 2022-09-13 |
| CN115046562B true CN115046562B (en) | 2024-05-07 |
Family
ID=83158192
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210393023.8A Active CN115046562B (en) | 2022-04-15 | 2022-04-15 | Low-cost high-precision automatic driving automobile positioning method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115046562B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116215564A (en) * | 2023-05-10 | 2023-06-06 | 禾多科技（北京）有限公司 | Man-machine interaction intelligent driving system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109815300A (en) * | 2018-12-13 | 2019-05-28 | 北京邮电大学 | A kind of vehicle positioning method |
| CN112683260A (en) * | 2020-10-30 | 2021-04-20 | 东风汽车集团有限公司 | High-precision map and V2X-based integrated navigation positioning precision improving system and method |
| CN113566817A (en) * | 2021-07-23 | 2021-10-29 | 北京经纬恒润科技股份有限公司 | Vehicle positioning method and device |
| KR20220035641A (en) * | 2020-09-14 | 2022-03-22 | 한국교통대학교산학협력단 | System for improving GPS accuracy using HD map and camera information |
-
2022
- 2022-04-15 CN CN202210393023.8A patent/CN115046562B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109815300A (en) * | 2018-12-13 | 2019-05-28 | 北京邮电大学 | A kind of vehicle positioning method |
| KR20220035641A (en) * | 2020-09-14 | 2022-03-22 | 한국교통대학교산학협력단 | System for improving GPS accuracy using HD map and camera information |
| CN112683260A (en) * | 2020-10-30 | 2021-04-20 | 东风汽车集团有限公司 | High-precision map and V2X-based integrated navigation positioning precision improving system and method |
| CN113566817A (en) * | 2021-07-23 | 2021-10-29 | 北京经纬恒润科技股份有限公司 | Vehicle positioning method and device |
Non-Patent Citations (1)
| Title |
|---|
| 视觉辅助驾驶系统多维度道路建模及车辆定位优化;蒋如意;CNKI博士学位论文电子期刊;20150515;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115046562A (en) | 2022-09-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107389064B (en) | Unmanned vehicle lane change control method based on inertial navigation | |
| CN111770451B (en) | Road vehicle positioning and sensing method and device based on vehicle-road cooperation | |
| US9915539B2 (en) | Intelligent video navigation for automobiles | |
| US20190294898A1 (en) | Localization by vision | |
| US11686582B2 (en) | Sensor plausibility using GPS road information | |
| CN111380542B (en) | Vehicle positioning and navigation method and device and related system | |
| US20170016740A1 (en) | Method and apparatus for determining a vehicle ego-position | |
| CN111507129B (en) | Lane-level positioning method and system, computer equipment, vehicle and storage medium | |
| US10458805B2 (en) | Driver assistance system for a motor vehicle | |
| US11869251B2 (en) | Driving support method and driving support device | |
| CN113885062A (en) | Data acquisition and fusion equipment, method and system based on V2X | |
| US11410429B2 (en) | Image collection system, image collection method, image collection device, recording medium, and vehicle communication device | |
| CN111522003A (en) | Vehicle positioning method and system, computer equipment, vehicle and storage medium | |
| US20220035036A1 (en) | Method and apparatus for positioning movable device, and movable device | |
| CN115046562B (en) | Low-cost high-precision automatic driving automobile positioning method | |
| CN113175938A (en) | Vehicle positioning enhancement system and method based on high-precision map | |
| CN113029187A (en) | Lane-level navigation method and system fusing ADAS fine perception data | |
| US11680818B2 (en) | System and method for updating and sharing crossroad dynamic map data | |
| US11187815B2 (en) | Method of determining location of vehicle, apparatus for determining location, and system for controlling driving | |
| CN110784680B (en) | Vehicle positioning method and device, vehicle and storage medium | |
| CN112150576A (en) | High-precision vector map acquisition system and method | |
| CN113312403B (en) | Map acquisition method and device, electronic equipment and storage medium | |
| WO2015016406A1 (en) | System and method for correcting absolute positioning of vehicle | |
| CN115427760A (en) | Method and device for determining the position of a vehicle in a road network | |
| CN114821531A (en) | Lane line recognition image display system based on electronic outside rear-view mirror ADAS |
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 |