KR20220115176A - System for improving GPS accuracy using HD map and camera information - Google Patents

Abstract

The present invention relates to a system for improving GPS accuracy using a HD map and a camera. According to the present invention, the present invention can greatly enhance location accuracy even when using a low-priced GPS module having a high error rate by correcting GPS coordinate information by using the camera and the HD map, so it is possible to put commercialization of autonomous driving vehicles forward.

Description

Positioning accuracy improvement system using a precision map and camera {System for improving GPS accuracy using HD map and camera information}

The present invention relates to a system for improving positioning accuracy using a precision map and camera information, and more particularly, to a technology capable of correcting a positioning error of a low-cost GPS.

In the field of smart cars or autonomous vehicles, a technology that accurately identifies (location) the location of one's own vehicle is essential.

GNSS is the most widely used positioning system. GNSS (Global Navigation Satellite System) is a generic term for a system that provides information on the position, altitude, and speed of an object on the ground using satellites, and the US Global Positioning System (GPS) is a representative example.

In the case of a widely distributed low-cost GPS, it is sufficient to determine the direction or location of a vehicle, and on which road it is currently located. However, in the case of low-cost GPS, an error of about 1.5 meters occurs, and when the signal reception environment is not good, such as in a downtown area or a mountainous area with many high-rise buildings, a large error of more than 7 meters may occur. That is, as shown in FIG. 1 , when the vehicle 10 is driving along the center in both lanes LL and RL, the actual position 11R of the vehicle is any one point among the center lines of the lanes LL and RL, In many cases, the GPS coordinates 11G obtained through the GPS module are not the location of the center line of the lane.

Therefore, it is difficult to use low-cost GPS in an autonomous driving environment. To this end, there are cases where autonomous vehicle technology is demonstrated after an expensive GPS module with high location accuracy is mounted.

Meanwhile, as a prior art related to positioning of a vehicle, there is Republic of Korea Patent No. 10-1752342 (June 23, 2017, 'vehicle positioning method') and the like.

The present invention has been devised to solve the problems of the prior art as described above, and by correcting coordinate information obtained from a low-cost GPS using a camera and a precision map that photograph the surroundings of the vehicle, the location accuracy in an autonomous vehicle environment is improved. Its purpose is to provide technology that can improve it.

Positioning accuracy improvement system according to the present invention for achieving the above object, a camera for acquiring image information around the vehicle; GPS module for acquiring GPS coordinate information; and a position correcting means for correcting the GPS coordinate information obtained from the GPS module using the precise map data and the image information obtained from the camera. a driving route calculation unit for calculating a driving route equation expressing a centerline calculator for calculating a centerline equation including centerline coordinates closest to the GPS coordinates obtained from the GPS module among the centerline coordinates of the precision map data stored in the precision map DB; a correction information generating unit for generating correction information by moving the driving path equation and the center line equation to be close to each other on the same relative coordinate system; and a location updater configured to generate updated GPS coordinates by reflecting the correction information generated by the correction information generator to the GPS coordinates.

Here, the correction information generating unit integrates the driving route equation and the center line equation into one relative coordinate system, moves the center line equation in parallel to the origin of the relative coordinate system based on arbitrary coordinates on the center line equation, and then moves in parallel By repeating the process of calculating the difference between the center line equation and the driving route equation a certain number of times, extracting the coordinates on the center line with the minimum difference in the integral difference, and moving the extracted coordinates on the center line in parallel to the origin of the relative coordinate system. can be determined as the correction information.

According to the present invention, even if a low-cost GPS module is mounted, it is possible to improve location accuracy by correcting errors in GPS coordinates using a camera and precision map data. Therefore, it is possible to accelerate the commercialization of autonomous vehicles by improving location accuracy at a low price in the field of autonomous vehicles.

1 is a view for explaining an example in which an error in GPS coordinates obtained from a GPS module of a vehicle while driving occurs;
2 is a block diagram illustrating a system for improving positioning accuracy according to an embodiment of the present invention;
3 is a flowchart for explaining a method for improving positioning accuracy according to an embodiment of the present invention;
4 and 5 are diagrams for explaining an example of calculating a driving route equation by analyzing image information captured by a camera.
6 and 7 are diagrams for explaining an example of calculating a centerline equation through a precision map.
Fig. 8 is a view showing a travel route equation and a center line equation on the same relative coordinate system;
9 and 10 are diagrams for explaining and comparing the difference value of the integral difference between the parallel-moved center line equation and the driving path equation when the coordinates on different center lines are moved in parallel to the origin of the relative coordinate system.

Hereinafter, preferred embodiments of the present invention will be described with reference to the accompanying drawings. However, some components irrelevant to the gist of the present invention will be omitted or compressed, but the omitted configuration is not necessarily a configuration that is not necessary in the present invention, and it will be used in combination by those of ordinary skill in the art to which the present invention belongs. can

2 is a block diagram illustrating a system for improving positioning accuracy according to an embodiment of the present invention. As shown in FIG. 2 , the positioning accuracy improvement system 100 according to an embodiment of the present invention includes a camera 110 , a GPS module 120 , and a position correction means 130 . The positioning accuracy improvement system 100 dealt with in the present invention can perform various functions necessary for autonomous driving, such as determining the exact location of the own vehicle 10, predicting a driving route, or tracking the movement of surrounding vehicles. have. However, FIG. 2 shows only the components necessary to improve the positioning accuracy of the low-cost GPS module 120 . In addition, each component of the positioning accuracy improvement system 100 is mounted on the vehicle 10 , and each component may be integrated as a hardware configuration or may be configured as individual hardware and may be interlocked with each other. In addition, some components of the positioning accuracy improvement system 100 may be designed in software.

The camera 110 is provided to acquire image information by photographing the surroundings of the vehicle 10 . For example, the camera 110 may include a plurality of cameras 110 for photographing the front, rear, and side images of the vehicle 10 , but in the present invention, only the camera 110 for photographing the front image will be described.

The GPS module 120 is provided to obtain GPS coordinate information by receiving a GPS signal through a satellite and processing the data. The coordinate information obtained through the GPS module 120 includes a longitude value and a latitude value, and may further include altitude information according to implementation.

The GPS module 120 used in the positioning accuracy improvement system 100 according to an embodiment of the present invention is a low-cost product, and thus the obtained coordinate information 11G may have an error. Of course, even if there is some error, it is possible to determine which lane on which road is being driven.

The position correction means 130 uses the image information and the precision map data acquired from the camera 110 to correct the error of the coordinate information 11G acquired from the GPS module 120 to update the coordinate information of the GPS signal. prepared for The position correcting means 130 includes a driving route calculating unit 131 , a centerline calculating unit 132 , a correction information generating unit 133 , a position updating unit 134 , and a precision map DB 135 .

The driving route calculation unit 131 is provided to analyze the image information obtained from the camera 110 to calculate an equation expressing the traveling path of the vehicle as a curve, that is, a driving path equation. A detailed description of calculating the driving path equation in the driving path calculating unit 131 will be dealt with again below.

The centerline calculation unit 132 is provided to extract specific data through the precision map data stored in the precision map DB 135 and calculate a centerline equation by using the extracted data. The detailed process of calculating the centerline equation in the centerline calculating unit 132 will be discussed again below.

The correction information generating unit 133 uses the driving path equation calculated by the driving path calculating unit 131 and the center line equation calculated by the center line calculating unit 132, and coordinate information 11G of the GPS module 120 in which the error occurred. ) is provided to generate a correction value to be corrected, that is, correction information (Δx, Δy). A detailed process of generating the correction information in the correction information generating unit 133 will be discussed again below.

The position update unit 134 updates the coordinate information of the GPS signal obtained from the GPS module 120 by using the correction information generated by the correction information generation unit 133 . That is, the correct coordinate information is output by reflecting the correction information to the wrong coordinate information.

The precision map DB 135 is a database storing precision map data. The precise map can be expressed in detail down to the lane level, and further includes detailed information such as the center line of the lane, traffic lights, signs, road markings, road facilities, and buildings. The precision video image stored in the precision map DB 135 is a form in which numerous points are gathered, and each point has absolute coordinates such as latitude and longitude.

The positioning accuracy improvement system 100 described above will be further detailed from the description of the positioning accuracy improvement method which will be described with reference to FIG. 3 .

3 is a flowchart for explaining a method for improving positioning accuracy according to an embodiment of the present invention. That is, in the positioning accuracy improvement system 100 shown in FIG. 2 , the position correction means 130 includes the error obtained from the GPS module 120 using the image information and the precision map data acquired from the camera 110 . The information is about the process of updating the correct coordinate information.

First, the camera 110 acquires image information by photographing the surroundings of the vehicle 10 <S305>. One camera 110 may be provided to sequentially photograph the front, side, and rear of the vehicle 10, and a plurality of cameras 110 for photographing various directions may be provided, but in the present invention, the camera 110 It is assumed that the forward image is being acquired in a fixed manner.

Thereafter, the driving path calculating unit 131 analyzes the image information captured by the camera 110 to calculate a driving path equation expressing the shape of the road ahead of the vehicle 10 as an equation <S310>. The process of calculating the driving route equation will be described with reference to FIGS. 4 and 5 .

First, as shown in FIG. 4 , the driving route calculating unit 131 analyzes the image captured by the camera 110 to obtain curve information on the left lane LL and the right lane RL with the vehicle 10 as the origin. It is expressed as a cubic equation in a relative coordinate system with For example, the cubic equation y _L for the left lane LL may be expressed as follows.

[Equation 1]

y _L =f _L (x)=C _0L +C _1L x+C _2L x ² +C _3L x ³

And the cubic equation y _R for the right lane RL may be expressed as follows.

[Equation 2]

y _R =f _R (x)=C _0R +C _1R x+C _2R x ² +C _3R x ³

Thereafter, the driving path calculating unit 131 uses the equation (y _L ) for the left lane (LL) and the equation (y _R ) for the right lane (RL) to the driving path (DL) passing through the center between the two curves. A cubic equation for , that is, a driving path equation is calculated. For example, the driving route equation (y _C ) may be expressed as follows.

[Equation 3]

y _C =f _C (x)=C _0C +C _1C x+C _2C x ² +C _3C x ³

After analyzing the image captured by the camera 110 to calculate a cubic equation for the left lane LL and a cubic equation for the right lane RL, Since the algorithm for calculating the displayed driving path equation (y _C ) is a known technique, a detailed algorithm description will be omitted.

Referring to FIG. 5 , the driving path equation y _C calculated by the driving path calculating unit 131 passes through the origin on the relative coordinate system with the vehicle 10 as the origin. In other words, if the autonomous vehicle is designed to drive along the center of both lanes, and driving is performed normally based on this, it is natural that the driving path equation (y _C ) passes through the origin in the relative coordinate system.

When the driving path calculation unit 131 calculates the driving path equation (y _C ) by analyzing the image information of the camera 110 <S310>, the GPS module 120 acquires GPS coordinates <S315>.

In order to realize autonomous driving, it is necessary to check accurate GPS coordinates in real time in order to confirm the current location of the vehicle 10 . However, since the GPS module 120 applied in the present invention is a low-cost type, the obtained GPS coordinate information may have an error. That is, referring to FIG. 1 , the location according to the GPS coordinate information is indicated by reference numeral 11G, which is adjacent to the location 11R of the actual vehicle 10, but is displayed at a different location due to an error. In order to correct this, in the present invention, the positioning accuracy improvement process is performed.

That is, referring to FIG. 6 , the center line calculation unit 132 calculates a center line equation including the center line coordinates closest to the GPS coordinates 11G among the center line (CL) coordinates of the precision map data stored in the precision map DB 135. . As described above, the precise map DB 135 stores detailed coordinate information of lanes, traffic lights, signs, road marks, road facilities, buildings, etc., and also includes information on the center line (CL) between the lanes. have.

Therefore, when the centerline calculating unit 132 extracts the closest centerline coordinates to the GPS coordinates 11G, a predetermined number of front and rear coordinates on the centerline CL including the extracted centerline coordinates can be confirmed, and the predetermined number of coordinates If the equation for the connecting curve is calculated, it becomes the centerline equation (y _M ).

At this time, the center line equation (y _M ) calculated by the center line calculator 132 has the GPS coordinates 11G obtained from the GPS module 120 as the origin, and the coordinates included in the center line CL have latitude and longitude. Since it consists of absolute coordinates, the expression expressing the curve connecting the coordinates on the center line CL is displayed on the absolute coordinate system with the GPS coordinates 11G as the origin. Therefore, the center line calculation unit 132 converts the center line equation (y _M ) on the absolute coordinate system into the relative coordinate system. Since the algorithm for converting a curve formula in the absolute coordinate system based on latitude and longitude into a relative coordinate system is a known technology, a detailed description thereof will be omitted. The center line equation (y _M ) converted into the relative coordinate system can be confirmed through FIG. 7 , and the center line equation (y _M ) can be expressed as follows.

[Equation 4]

y _M =f _M (x)=C _0M +C _1M x+C _2M x ² +C _3M x ³

On the other hand, even if there is an error in the coordinate information 11G obtained from the GPS module 120 as shown in FIGS. 6 and 7 , assuming that the actual vehicle 10 is driving normally along the center of both lanes, the center line The curve CL and the centerline equation y _M expressed as an equation do not pass through the origin on the coordinate system with the GPS coordinates 11G as the origin. If the curve CL for the center line equation y _M in the coordinate system of FIG. 7 passes through the origin, this means that there is no error in the GPS coordinates 11G obtained from the GPS module 120 . However, in an actual situation, the center line equation (y _M ) does not pass through the origin as shown in FIG. 7 due to the error of the GPS coordinates.

The driving path equation (y _C =f _C (x)) is calculated in the driving path calculation unit 131 <S310>, and the center line equation (y _M =f _M (x)) is calculated in the center line calculation unit 132< When S320>, the correction information generating unit 133 generates correction information using the driving path equation and the center line equation.

Specifically, the correction information generating unit 133 displays the driving route equation fc(x) and the centerline equation f _M (x) in one relative coordinate system as shown in FIG. 8 <S325>. That is, when the driving route equation shown in FIG. 5 and the center line equation shown in FIG. 7 are combined into one relative coordinate system, two different curves are displayed on one relative coordinate system as shown in FIG. 8 .

As can be seen from FIG. 8 , the driving path equation fc(x) is a curve passing through the origin, and the centerline equation f _M (x) does not pass through the origin. At this time, the driving path equation fc(x) represents the path the vehicle 10 should travel based on the image captured by the camera 110, and the centerline equation f _M (x)) even if there is an error. It is a curve with respect to the center line CL extracted from the vicinity of the GPS coordinates 11G, and this center line CL curve also represents a path along which the vehicle 10 travels.

That is, although the two curves appear to be different in FIG. 8, the shapes of the two curves will be almost identical. Therefore, if any one point located on the centerline equation (f _M (x)) is moved in parallel to the origin on the relative coordinate system, the curve represented by the driving path equation (fc(x)) and the curve represented by the centerline equation (f _M (x)) will overlap almost coincidentally. However, it is not clear which point should be translated to the origin in the centerline equation (f _M (x)). To this end, the correction information generating unit 133 performs the following process.

First, the correction information generator 133 extracts arbitrary coordinates on the center line CL expressed by the center line equation f _M (x), and calculates the center line equation f _M (x) based on the extracted arbitrary coordinates. It moves in parallel to the origin of the relative coordinate system. Thereafter, a difference value of the integral difference between the parallel-moved center line equation and the driving path equation is calculated <S330>. The correction information generating unit 133 repeats the parallel movement to the origin for various coordinates in the center line equation (f _M (x)) and calculating the definite integral difference value several times, Extract <S335>.

The process of calculating the integral difference value between the centerline equation and the driving route equation after moving specific coordinates in the centerline equation (f _M (x)) in parallel to the origin is described with reference to FIGS. 9 and 10 as follows. First, suppose that A and B are extracted as arbitrary coordinates on the centerline equation (f _M (x)) in FIG. 8 .

9 shows the driving path equation (f _C (x)) displayed on the relative coordinate system when an arbitrary coordinate B in the center line equation (f _M (x)) is moved in parallel to the origin, and the center line equation (f _MB (x)) is shown.

If the indefinite integral of the driving path equation (f _C (x)) is F _C (x), the definite integral with the lower end as b and the upper end as b is expressed as follows.

[Equation 5]

Also, when an arbitrary coordinate B in the centerline equation (f _M (x)) is translated to the origin, if the indefinite integral of the translated center line equation f _MB (x) is F _MB (x), the lower end is b, The definite integral with the upper end of b is expressed as follows.

[Equation 6]

The result of Equation 5 above represents the area of sections a and b formed by the x-axis and the driving path equation f _C (x) in the relative coordinate system of FIG. 9, and the result of Equation 6 is x in the relative coordinate system of FIG. It represents the area of sections a and b formed by the centerline equation f _MB (x) moved parallel to the axis.

In order for the correction information generating unit 133 to calculate the integral difference value, Equation 6 is subtracted from Equation 5, and an absolute value is taken to obtain a positive value indicating an area.

That is, in FIG. 9 , the area of sections a and b between f _C (x) and f _MB (x) may be expressed by the following equation.

[Equation 7]

In the same way, when an arbitrary coordinate A in the center line equation (f _M (x)) in FIG. 8 is moved in parallel to the origin, the driving path equation (f _C (x)) displayed on the relative coordinate system and the parallel shifted center line equation (f _MA (x)) is shown in FIG.

When an arbitrary coordinate A in the center line equation (f _M (x)) is translated to the origin, if the indefinite integral of the translated center line equation f _MA (x) is F _MA (x), the lower end is b, and the upper end is The definite integral with b is expressed as follows.

[Equation 8]

The result of Equation 8 above represents the area of sections a and b formed by the center line equation f _MA (x) moved parallel to the x-axis on the relative coordinate system of FIG. 10 .

Accordingly, in FIG. 10 , the area of sections a and b between f _C (x) and f _MA (x) may be expressed as follows.

[Equation 9]

The result of Equation 7 showing the area of sections a and b between f _C (x) and f _MB (x), and Equation 9 representing the areas of sections a and b between f _C (x) and f _MA (x) As can be compared through FIGS. 9 and 10, the result of Equation 9 (the result of FIG. 10) is smaller. That is, in the centerline equation (f _M (x)), when an arbitrary coordinate A is translated to the origin, the equation f _MA (x) is translated, and when B is translated to the origin, the equation f _MB (x) This means that it overlaps more closely with the driving path equation f _C (x).

If the result of calculating the differential difference between the centerline equation and the driving route equation after moving an arbitrary coordinate A in the centerline equation (f _M (x)) in parallel is the minimum value, the correction information generating unit is located on the center line where the difference value of the integral difference is the minimum. Coordinates, that is, the coordinates of A are extracted <S335>, and a value for moving the extracted coordinates A on the center line in parallel to the origin of the relative coordinate system is determined as the correction information (Δx, Δy) <S340>.

When the correction information generation unit 133 generates the correction information, the position update unit 134 reflects the generated correction information to the GPS coordinate information to update the position information <S345>. That is, the updated GPS coordinate information is calculated by reflecting the correction information (Δx, Δy) in the GPS coordinates 11G, and the updated GPS coordinate information is output so that it can be used in a configuration necessary for autonomous driving. Of course, whether to add or subtract the correction information (Δx, Δy) to the error GPS coordinates 11G can be appropriately modified according to the design.

Based on the example of FIG. 6 , the updated GPS coordinates will be the coordinates of 11R, or coordinates that are close to the coordinates of 11R.

On the other hand, in the above description, after extracting arbitrary coordinates from the center line equation (f _M (x)) and moving them in parallel to the origin of the relative coordinate system, the result of calculating the difference between the central line equation and the travel path equation that was moved in parallel is the minimum value. It has been explained that we need to find the coordinates that become this. At this time, the error of the GPS coordinates 11G will not be as large as 1.5m. Therefore, when extracting arbitrary coordinates from the centerline equation (f _M (x)), the value of x is determined based on (0, y) in the 1.5 m front (positive) section and the rear (negative) 1.5 m section. A method of extracting coordinates while increasing or decreasing at intervals of 1 cm or 5 cm may be applied. In this case, if arbitrary coordinates are taken at 1cm intervals in the entire 3m section, 300 sampling times are required, and if arbitrary coordinates are taken at 5cm intervals, 60 samplings are required. Therefore, when sampling arbitrary coordinates in the centerline equation, an appropriate section and interval can be set according to the performance of the system, and the accuracy of positioning improvement can also vary according to the set sampling section and interval.

As described in detail above, according to the present invention, even if the low-cost GPS module 120 is mounted, the error of the GPS coordinates can be corrected by using the camera 110 and precision map data to increase the location accuracy. Therefore, it is possible to accelerate the commercialization of autonomous vehicles by improving location accuracy at a low price in the field of autonomous vehicles.

The above-described preferred embodiments of the present invention have been disclosed for the purpose of illustration, and those skilled in the art with common knowledge about the present invention will be able to make various modifications, changes and additions within the spirit and scope of the present invention, such modifications, changes and additions are to be considered as falling within the scope of the claims of the present invention.

10: vehicle
100: positioning accuracy improvement system
110: camera
120: GPS module
130: position correction means
131: driving route calculation unit
132: center line calculation unit
133: correction information generation unit
134: location update unit
135: precision map DB

Claims (2)

a camera for acquiring image information around the vehicle;
GPS module for acquiring GPS coordinate information; and
Position correction means for correcting the GPS coordinate information obtained from the GPS module using the precision map data and the image information obtained from the camera; including;
The position correction means,
a driving path calculator for calculating a driving path equation representing the driving path of the vehicle through the image information;
a centerline calculator for calculating a centerline equation including centerline coordinates closest to the GPS coordinates obtained from the GPS module among the centerline coordinates of the precision map data stored in the precision map DB;
a correction information generating unit for generating correction information by moving the driving path equation and the center line equation to be close to each other on the same relative coordinate system; and
and a position update unit generating updated GPS coordinates by reflecting the correction information generated by the correction information generating unit to the GPS coordinates.
According to claim 1,
The correction information generating unit integrates the driving route equation and the center line equation into one relative coordinate system, moves the center line equation in parallel to the origin of the relative coordinate system based on arbitrary coordinates on the center line equation, and then moves the center line in parallel The process of calculating the difference between the equation and the driving route equation is repeated a certain number of times to extract the coordinates on the center line with the minimum difference in the integral difference, and to correct the value of moving the extracted coordinates on the center line to the origin of the relative coordinate system in parallel Positioning accuracy improvement system, characterized in that determined by information.

Images