KR101878685B1 - System and method for positioning vehicle using local dynamic map - Google Patents

System and method for positioning vehicle using local dynamic map Download PDF

Info

Publication number
KR101878685B1
KR101878685B1 KR1020160016299A KR20160016299A KR101878685B1 KR 101878685 B1 KR101878685 B1 KR 101878685B1 KR 1020160016299 A KR1020160016299 A KR 1020160016299A KR 20160016299 A KR20160016299 A KR 20160016299A KR 101878685 B1 KR101878685 B1 KR 101878685B1
Authority
KR
South Korea
Prior art keywords
vehicle
information
landmark
detected
positioning
Prior art date
Application number
KR1020160016299A
Other languages
Korean (ko)
Other versions
KR20170094947A (en
Inventor
윤지훈
Original Assignee
서울과학기술대학교 산학협력단
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 서울과학기술대학교 산학협력단 filed Critical 서울과학기술대학교 산학협력단
Priority to KR1020160016299A priority Critical patent/KR101878685B1/en
Publication of KR20170094947A publication Critical patent/KR20170094947A/en
Application granted granted Critical
Publication of KR101878685B1 publication Critical patent/KR101878685B1/en

Links

Images

Classifications

    • 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
    • G01S19/01—Satellite radio beacon positioning systems transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
    • G01S19/03—Cooperating elements; Interaction or communication between different cooperating elements or between cooperating elements and receivers
    • 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
    • G06K9/00798—
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes

Abstract

A vehicle positioning system of the present invention includes a GPS receiver installed in a vehicle for receiving a Global Positioning System (GPS) signal, a map information receiving module for receiving map information corresponding to a current vehicle position from the server by the GPS signal, An image processing module for detecting landmark information included in the map information in real time using a camera installed in a vehicle and an image photographed by the camera; And a positioning module for calculating the current position of the vehicle using distance information between the vehicle and the landmark and angle information between the vehicle and the landmark.
According to the present invention, there is an effect that the positioning error of the GPS can be improved by positioning the vehicle by fusing the map information.

Description

BACKGROUND OF THE INVENTION Field of the Invention The present invention relates to a vehicle positioning system and method using map information,

Field of the Invention [0002] The present invention relates to a technique for positioning a vehicle, and more particularly, to a high precision positioning technique for an autonomous vehicle by fusing GPS and map information.

Generally, the error range measured by GPS (Global Positioning System) is 5 ~ 15m, and errors up to 30m depending on wireless environment may appear. Therefore, it is difficult to apply it to vehicle safety technology requiring precise positioning have.

And, GPS technology can provide the absolute coordinates of the vehicle location at a relatively slow rate (e.g., 1 Hz), because GPS signals are not received properly due to buildings and tunnels, In case of forming, an error may occur, and such a region may be referred to as a shaded area of the GPS. While the vehicle is passing through the shaded area, the accuracy of the GPS can be significantly reduced.

To overcome the disadvantages of GPS, it is possible to combine a GPS-based inertial navigation system with GPS to measure the relative vehicle condition.

The Inertial Navigation System (INS) measures the relative position of a vehicle by estimating the state and movement path of the vehicle by combining vehicle sensors such as a vehicle traveling system, a steering wheel encoder, an accelerometer, and a gyroscope .

INS is advantageous in that it does not have a shadow area because it is not affected by the surrounding terrain by using the vehicle sensor and outputs information at a relatively high speed (for example, about 50 Hz). However, unlike GPS, which generates absolute coordinates and does not accumulate errors even after a long period of operation, INS has the disadvantage of accumulating sensor errors over time. Therefore, by combining INS with GPS, it is possible to estimate the position information in the shaded area of GPS through INS, and the cumulative error of INS can be corrected by GPS to generate position information with high accuracy regardless of region.

However, there is a problem that the GPS calculation coordinate itself used as a reference for such fusion-based positioning has a large error. For this purpose, a technique for improving the accuracy of the GPS itself has been proposed, and it is possible to reduce errors up to several centimeters. However, since the satellite reception environment between the receiver and the reference station must be similar, To the extent possible. Therefore, there is a need for a method that can reduce the GPS positioning error in a wider variety of environments.

Korean Patent Publication No. 10-2005-0005115

SUMMARY OF THE INVENTION It is an object of the present invention to provide a system and method for realizing precise vehicle positioning using less hardware than a positioning error improvement technique using an existing inertial navigation system have.

The objects of the present invention are not limited to the above-mentioned objects, and other objects not mentioned can be clearly understood by those skilled in the art from the following description.

According to another aspect of the present invention, there is provided a vehicle positioning system including: a GPS receiver installed in a vehicle for receiving a Global Positioning System (GPS) signal; map information corresponding to a current location of the vehicle, An image processing module for detecting landmark information included in the map information in real time using an image photographed by the camera and a camera installed in the vehicle, And a positioning module for calculating the current position of the vehicle using the distance information between the vehicle and the landmark and the angle information between the vehicle and the landmark in the detected landmark information.

The image processing module senses the lane using the image photographed by the camera, and when the coordinate of the road in the direction of the vehicle is x coordinate, the positioning module determines that the current vehicle is located at the lane And the x-coordinate can be calculated using the lane information indicating how far from the center of the lane is located.

When both the distance information and the angle information for the detected landmark are extracted, the positioning module can calculate the position of the vehicle using the distance information, the angle information, and the lane information.

When there are two or more detected landmarks, the positioning module can calculate the final position of the vehicle by averaging the calculated position of the vehicle from each landmark.

When only the distance information for the detected landmark is extracted, the positioning module can calculate the final position of the vehicle by combining the distance information and the lane information.

When the detected landmarks are two or more, and the coordinate with respect to the road direction in which the vehicle is running is y coordinate, the positioning module can calculate the final position of the vehicle by averaging the y coordinate obtained from each landmark.

When only the angle information for the detected landmark is extracted, the positioning module can calculate the final position of the vehicle by combining the angle information and the lane information.

When there are two or more detected landmarks, the positioning module can calculate the final position of the vehicle by averaging the y coordinates obtained from each landmark.

When the distance information and the angle information of the landmark detected by the image processing module can not be extracted, the positioning module tracks the landmark through the camera and detects the angle of view when the landmark is just before departing from the camera viewing angle It is possible to estimate the angle information with respect to the landmark from the value and calculate the position of the vehicle from the estimated angle information.

If the distance information and the angle information of the landmark detected by the image processing module can not be extracted, the positioning module calculates the distance from the current position of the vehicle to the position of the vehicle Can be estimated.

The vehicle positioning system further includes a speed measurement module for measuring the speed of the vehicle. When the landmark that can be detected by the camera is missing, the positioning module assumes a virtual landmark, The position of the vehicle can be estimated.

The map information receiving module may receive LDM (Local Dynamic Map) information from a server.

In a vehicle positioning method in a vehicle positioning system for calculating a position of a vehicle in which a camera is installed, a GPS receiver for receiving a Global Positioning System (GPS) signal of the present invention, Receiving landmark information included in the map information in real time using an image photographed by the camera, receiving image information of the detected landmark from the server, And a positioning step of calculating the current position of the vehicle by using the distance information between the vehicle and the landmark and the angle information between the vehicle and the landmark in the information.

The lane detecting unit detects the lane by using the image photographed by the camera in the image processing step and uses the lane information indicating that the current vehicle is located at the lane of the lane of the road and how far the lane is from the center of the lane The x-coordinate of the vehicle can be calculated.

When both the distance information and the angle information for the detected landmark are extracted, the positioning step can calculate the position of the vehicle using the distance information, the angle information, and the lane information.

When there are two or more detected landmarks, the positioning step can calculate the final position of the vehicle by averaging the calculated position of the vehicle from each landmark.

When only the distance information for the detected landmark is extracted, the positioning step may calculate the final position of the vehicle by combining the distance information and the lane information.

When there are two or more detected landmarks, the positioning step can calculate the final position of the vehicle by averaging the y coordinates obtained from each landmark.

If only the angle information for the detected landmark is extracted, the positioning step may calculate the final position of the vehicle by combining the angle information and the lane information.

When there are two or more detected landmarks, the positioning step can calculate the final position of the vehicle by averaging the y coordinates obtained from each landmark.

Wherein when the distance information and the angle information for the landmark detected in the image processing step can not be extracted, the positioning step traces the landmark through the camera to determine a viewing angle when the landmark is just before departing from the camera viewing angle It is possible to estimate the angle information with respect to the landmark from the value and calculate the position of the vehicle from the estimated angle information.

If it is not possible to extract the distance information and the angle information of the landmark detected in the image processing step, the positioning step determines the position of the vehicle based on the maximum distance that the camera can sense and the position information of the currently detected landmark Can be estimated.

And a speed measuring step for measuring the speed of the vehicle, wherein when the landmark that can be detected by the camera is missing, the positioning step assumes a virtual landmark, The position can be estimated.

In the map information receiving step, LDM (Local Dynamic Map) information can be received from the server.

According to the present invention, there is an effect that the positioning error of the GPS can be improved by positioning the vehicle by fusing the map information.

In addition, according to the present invention, by implementing a vehicle positioning system using a camera installed in a vehicle for autonomous travel, fewer hardware is used than a technique for positioning a vehicle using an inertial navigation system including a conventional inertial sensor, The cost can be reduced.

1 is a block diagram showing the configuration of a vehicle positioning system according to an embodiment of the present invention.
2 is an exemplary diagram for explaining the extraction of distance and angle information from a landmark in a vehicle positioning system according to an embodiment of the present invention.
3 is an exemplary view for explaining the extraction of angle information of a landmark from camera viewing angle information in a vehicle positioning system according to an embodiment of the present invention.
4 is an exemplary diagram for explaining the extraction of the angle information of the landmark from the maximum detectable distance information and the vehicle speed information of the camera in the vehicle positioning system according to the embodiment of the present invention.
5 is a flowchart showing a vehicle positioning method according to an embodiment of the present invention.

While the invention is susceptible to various modifications and alternative forms, specific embodiments thereof are shown by way of example in the drawings and will herein be described in detail. It should be understood, however, that the invention is not intended to be limited to the particular embodiments, but includes all modifications, equivalents, and alternatives falling within the spirit and scope of the invention.

The terminology used in this application is used only to describe a specific embodiment and is not intended to limit the invention. The singular expressions include plural expressions unless the context clearly dictates otherwise. In the present application, the terms "comprises" or "having" and the like are used to specify that there is a feature, a number, a step, an operation, an element, a component or a combination thereof described in the specification, But do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, or combinations thereof.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Terms such as those defined in commonly used dictionaries are to be interpreted as having a meaning consistent with the contextual meaning of the related art and are to be interpreted in an ideal or overly formal sense unless expressly defined in the present application Do not.

In the following description of the present invention with reference to the accompanying drawings, the same components are denoted by the same reference numerals regardless of the reference numerals, and redundant explanations thereof will be omitted. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. In the following description, well-known functions or constructions are not described in detail since they would obscure the invention in unnecessary detail.

1 is a block diagram showing the configuration of a vehicle positioning system according to an embodiment of the present invention.

1, the vehicle positioning system of the present invention includes a GPS receiver 110, an LDM receiving module 120, a camera 130, an image processing module 140, a velocity measurement module 150, a positioning module 160, .

The GPS receiver 110 is installed in the vehicle and receives GPS (Global Positioning System) signals.

The map information receiving module 120 receives the map information corresponding to the current location of the vehicle from the server by the GPS signal. In an embodiment of the present invention, the map information receiving module 120 may receive LDM (Local Dynamic Map) information from a server.

The camera 130 is installed in the vehicle, and can photograph the front side or the rear side.

The image processing module 140 performs image processing for detecting landmark information included in the map information in real time using the image photographed by the camera 130.

The speed measurement module 150 serves to measure the speed of the vehicle.

The positioning module 160 calculates the current position of the vehicle using the distance information between the vehicle and the landmark and the angle information between the vehicle and the landmark in the landmark information detected by the image processing module 140. [

In the present invention, the image processing module 140 detects the lane using the image captured by the camera 130, and the positioning module 160 determines that the current vehicle is located at the lane of the road, The x-coordinate of the vehicle can be calculated using lane information indicating whether or not the vehicle is off.

When both the distance information and the angle information for the detected landmark are extracted, the positioning module 160 calculates the position of the vehicle using the distance information, the angle information, and the lane information. At this time, when there are two or more detected landmarks, the positioning module 160 calculates the final position of the vehicle by averaging the positions of the vehicles calculated from the respective landmarks.

In the present invention, when only the distance information on the detected landmark is extracted, the positioning module 160 can calculate the final position of the vehicle by combining the distance information and the lane information. At this time, when there are two or more detected landmarks, the positioning module 160 can calculate the final position of the vehicle by averaging the y coordinates obtained from each landmark.

In the present invention, when only the angle information about the detected landmark is extracted, the positioning module 160 can calculate the final position of the vehicle by combining the angle information and the lane information. At this time, when there are two or more detected landmarks, the positioning module 160 can calculate the final position of the vehicle by averaging the y coordinates obtained from each landmark.

In the present invention, when the distance information and the angle information for the landmark detected by the image processing module 140 can not be extracted, the positioning module 160 tracks the landmark through the camera 130, It is possible to estimate the angle information with respect to the landmark from the viewing angle value just before departing from the viewing angle of the vehicle and calculate the position of the vehicle from the estimated angle information.

If the distance information and the angle information for the landmark detected by the image processing module 140 can not be extracted, the positioning module 160 calculates the distance that the camera 130 can sense, The position of the vehicle can be estimated from the position information of the mark. At this time, when there is no landmark that can be detected by the camera 130, the positioning module 160 assumes a virtual landmark and can estimate the position of the vehicle using the speed information of the vehicle.

5 is a flowchart showing a vehicle positioning method according to an embodiment of the present invention.

5, a vehicle positioning method in a vehicle positioning system according to an exemplary embodiment of the present invention includes a map information receiving step (S510) of receiving map information corresponding to a current vehicle position from a server according to a received GPS signal, . In an embodiment of the present invention, the map information receiving step (S510) may receive LDM (Local Dynamic Map) information from a server.

Then, an image processing step (S520) of detecting landmark information included in the map information in real time using the image photographed by the camera 130 is performed.

Then, in the detected landmark information, a positioning step (S530) of calculating the current position of the vehicle using the distance information between the vehicle and the landmark and the angle information between the vehicle and the landmark is performed.

In the image processing step (S520), the lane is detected using the image photographed by the camera (130), and in the positioning step (S530), the current vehicle is located on the lane of the road and how far from the center of the lane The x-coordinate of the vehicle can be calculated using the lane information represented by the lane information.

When both the distance information and the angle information for the landmark detected in the present invention are extracted, the positioning step S530 can calculate the position of the vehicle using the distance information, the angle information, and the lane information. At this time, when there are two or more detected landmarks, the positioning step 160 can calculate the final position of the vehicle by averaging the positions of the vehicles calculated from the respective landmarks.

When only the distance information for the detected landmark is extracted in the present invention, the positioning step S530 may calculate the final position of the vehicle by combining the distance information and the lane information. At this time, when there are two or more detected landmarks, the positioning step (S530) can calculate the final position of the vehicle by averaging the y coordinates obtained from each landmark.

In the present invention, when only the angle information about the detected landmark is extracted, the positioning step S530 may calculate the final position of the vehicle by combining the angle information and the lane information. At this time, when there are two or more detected landmarks, the positioning step (S530) can calculate the final position of the vehicle by averaging the y coordinates obtained from each landmark.

In the present invention, if the distance information and angle information for the landmark detected in the image processing step S520 can not be extracted, the positioning step S530 tracks the landmark through the camera 130, It is possible to estimate the angle information with respect to the landmark from the viewing angle value just before departing from the viewing angle of the vehicle and calculate the position of the vehicle from the estimated angle information.

In the present invention, if the distance information and angle information for the landmark detected in the image processing step (S520) can not be extracted, the positioning step (S530) determines the maximum distance that the camera can detect, The position of the vehicle can be estimated from the position information.

In one embodiment of the present invention, the vehicle positioning method further includes a speed measuring step for measuring the speed of the vehicle, and when the landmark that can be detected by the camera 130 is missing, the positioning step S530 includes: It is possible to estimate the position of the vehicle by using the speed information of the vehicle, assuming a mark.

Now, a process of extracting landmark information through image processing in the vehicle positioning system of the present invention will be described.

2 is an exemplary diagram for explaining the extraction of distance and angle information from a landmark in a vehicle positioning system according to an embodiment of the present invention.

Referring to FIG. 2, the vehicle downloads a local dynamic map (LDM) in a certain area from the server through the LDM receiving module 120 based on the coordinate value received by the GPS receiver 110.

The downloaded LDM contains coordinate information of a landmark existing around the vehicle. A landmark is an object that can be detected through image processing, and may include a sign, a road structure, a building, and the like.

Then, the vehicle senses the landmark in real time using the camera 130 mounted. 2, distance information between the vehicle and the landmark, and angle information between the vehicle and the landmark can be obtained together with the distinction of the landmark.

In Fig. 2, three landmarks a, b, and c are illustrated, and distance information and angle information for each landmark are shown.

In the present invention, due to the limitations of image processing, the vehicle may not extract both the distance and angle information, extract only one of them, or extract both of the detected landmarks. Further, the information to be extracted may be different for each landmark to be sensed, or may be determined for each vehicle to the limit of the image processing software.

Further, the vehicle senses the lane using the mounted camera 130, calculates the x-coordinate of the vehicle in such a manner as to detect the lane on which the vehicle is presently present and how much the lane is offset from the center of the lane It is possible.

2, the position coordinate of the landmark a is (x a , y a ), the position coordinate of the landmark b is (x b , y b ), the position coordinate of the landmark c is x c , y c ).

Then, the distance between the vehicle and the landmark a r a d, and d the distance between the vehicle and landmark b b r d, and the distance between the vehicle and landmark c r c.

Then, the angle between the vehicle and a landmark of a θ d, and the angle d between the vehicle and landmark θ b b d, and the angle between the vehicle and landmark c θ c.

In the present invention, a vehicle positioning method for various cases according to the landmark extraction information range is proposed, and a detailed description of each case will be given below.

First, it is the case that both the distance and the angle information of the detected landmark are extracted.

When both the distance and the angle information of the detected landmark are extracted, the position of the current vehicle can be calculated from this. At this time, when a plurality of landmarks are detected, a final position is determined by averaging the calculated positions from the landmarks.

As shown in FIG. 2, when the landmarks a, b, and c are detected, the position of the vehicle can be calculated from the extraction information of each landmark according to the following equation.

Figure 112016014090500-pat00001

Then, the position of the final vehicle in the positioning module 160 can be calculated according to the following equation.

Figure 112016014090500-pat00002

Alternatively, in another embodiment of the present invention, when the x coordinate x lane of the vehicle is obtained by the lane detection method, since the obtained x coordinate is four, the position of the vehicle can be calculated as the following equation.

Figure 112016014090500-pat00003

If only the landmark a is detected, (x a , y a ) becomes the final position. In the present invention, the final position of the vehicle can be calculated through a process of re-fusion with the position obtained through the GPS receiver 110. [

Second, only the detected distance information of the landmark is extracted.

When only the distance information of the detected landmark is extracted, when there is only one landmark, the position is determined by combining with the lane information. In FIG. 2, when only the landmark a is detected and only the distance information is extracted from the landmark a, the position (x, y) of the vehicle has a relationship as shown in the following equation.

Figure 112016014090500-pat00004

Since x = x lane from the lane information,

Figure 112018020557552-pat00005
.

When an image is obtained from the front camera in the camera, the coordinates of the final position of the vehicle can be expressed by the following equation.

Figure 112016014090500-pat00006

Alternatively, when an image is obtained by a rear camera in the camera, the coordinates of the final position of the vehicle may be expressed by the following equation.

Figure 112016014090500-pat00007

When a plurality of landmarks are detected, the y coordinates obtained from each landmark are averaged to determine the final position.

Third, it is the case that only the detected angle information of the landmark is extracted.

When only the detected landmark angle information is extracted, when there is only one landmark, the position is determined in combination with the lane information. In FIG. 2, when only the landmark a is detected and only angle information is extracted from the landmark a, the position (x, y) of the vehicle has a relationship as shown in the following equation.

Figure 112016014090500-pat00008

Since x = x lane from the lane information, the final position coordinates of the vehicle can be calculated by the following equation.

Figure 112016014090500-pat00009

When a plurality of landmarks are detected, the y coordinates obtained from each landmark are averaged to determine the final position.

Fourth, when the additional information of the landmark detected through the image processing can not be extracted, the viewing angle of the camera is used.

In this case, the landmark is traced and the angle information of the landmark is estimated from the angle of view angle just before the landmark disappears from the viewing angle of the camera 130, and the positioning is performed therefrom.

3 is an exemplary view for explaining the extraction of angle information of a landmark from camera viewing angle information in a vehicle positioning system according to an embodiment of the present invention.

As shown in FIG. 3, when the viewing angle of the camera is? Cam , the angle of the landmark a immediately before the landmark a disappears from the camera viewing angle becomes? / 2 +? Cam / 2. The final position of the vehicle can be calculated by substituting it into the positioning method when only the angle information of the landmark is extracted.

Fifth, when the additional information of the landmark detected through the image processing can not be extracted, the maximum sensing distance of the camera is used.

If the additional information of the detected landmark can not be extracted through the image processing, the approximate position of the vehicle can be calculated from the distance that the camera 130 can detect maximum and the currently detected landmark position information.

4 is an exemplary diagram for explaining the extraction of the angle information of the landmark from the maximum detectable distance information and the vehicle speed information of the camera in the vehicle positioning system according to the embodiment of the present invention.

When the landmarks a, b, and c are detected in the camera in FIGS. 3 and 4, the position of the vehicle can be estimated as shown in the following equation.

Figure 112016014090500-pat00010

In this case, when the image is acquired by the front camera, the y coordinate value of the landmark is located in front of the vehicle, and correction is required.

As shown in FIG. 3, assuming an area where a landmark can be detected by a front camera, a distance from the vehicle to the farthest part of the area is denoted as d cam , and a blind spot Let d blind be the maximum distance from the vehicle. Assuming that the landmarks are uniformly distributed on average, the average y-coordinate of the landmarks detected in the landmark detection area is (d cam -d blind ) / 2 from the position of the vehicle. Therefore, a correction value to which a constant value is added by (d cam -d blind ) / 2 is subtracted from the y coordinate calculated averaged from the detected landmarks.

On the other hand, assuming that the landmark is uniformly distributed on the left and right sides of the vehicle, the x coordinate value does not use the correction value since the average is the x coordinate of the vehicle.

Sixth, there is a case where the vehicle speed information (v x (τ), υ y (τ)) according to the time τ can be known. In this case, even if the landmark disappears in the field of view, it can be utilized continuously for calculating the vehicle position. For example, if the landmark a disappears at time ta in the visual field, the imaginary landmark a 'is assumed, and the coordinates thereof are estimated at time t as shown in the following equation.

Figure 112016014090500-pat00011

Assuming that the landmarks b and c remain at the viewing angle of the camera 130, the position of the vehicle considering the virtual landmark a 'is estimated as shown in the following equation.

Figure 112016014090500-pat00012

In the present invention, the virtual landmark may be considered only for a certain period of time after the landmark disappears from the field of view, or may be weighted differently between the virtual landmark and the landmark in the visual field as shown in the following equation.

Figure 112016014090500-pat00013

In Equation (12),? () Is? (0) = 1,

Figure 112016014090500-pat00014
In weight function. Examples of ω () are functions such as the following equations.

Figure 112016014090500-pat00015

Here, a, b, and T are constants that can be set according to the environment.

Seventh, the information that can be extracted for each detected landmark is different.

For example, the distance information and angle information are extracted from the landmark a, the distance information is extracted from the b, and the information extraction from the c fails.

In this case, in this case, the coordinates are calculated by applying the above-described methods according to the types of information extracted from the landmarks, and finally the final coordinates are calculated by fusing them.

delete

delete

delete

delete

While the present invention has been described with reference to several preferred embodiments, these embodiments are illustrative and not restrictive. It will be understood by those skilled in the art that various changes and modifications may be made therein without departing from the spirit of the invention and the scope of the appended claims.

110 GPS Receiver 120 LDM Receiving Module
130 Camera 140 Image processing module
150 Speed measurement module 160 Position module

Claims (24)

A GPS receiver installed in the vehicle for receiving GPS (Global Positioning System) signals;
A map information receiving module for receiving map information corresponding to a current vehicle position from the server by the GPS signal;
A camera installed in the vehicle;
An image processing module for detecting landmark information included in the map information in real time using an image photographed by the camera;
A positioning module for calculating a current position of the vehicle using the landmark information detected by the image processing module; And
A speed measuring module for measuring the speed of the vehicle,
Wherein the landmark information detected by the image processing module includes at least one of distance information between the vehicle and the landmark and angle information between the vehicle and the landmark,
Wherein the image processing module detects a lane using an image photographed by the camera,
When the coordinates of the road in the direction perpendicular to the road in which the vehicle is traveling is the x coordinate, the positioning module calculates the distance between the current lane of the road and the lane information indicating how far the current lane is from the center of the lane Calculates coordinates,
If the distance information and the angle information of the landmark detected by the image processing module can not be extracted, the positioning module calculates the distance from the current position of the vehicle to the position of the vehicle Respectively,
Wherein when the landmark that can be detected by the camera is missing, the positioning module assumes a virtual landmark and estimates the position of the vehicle using the speed information of the vehicle.
delete The method according to claim 1,
When both the distance information and the angle information for the detected landmark are extracted,
Wherein the positioning module calculates the position of the vehicle using the distance information, the angle information, and the lane information.
The method of claim 3,
If there are two or more detected landmarks,
Wherein the positioning module calculates the final position of the vehicle by averaging the position of the vehicle calculated from each landmark.
The method according to claim 1,
If only the distance information for the detected landmark is extracted,
And the positioning module calculates the final position of the vehicle by combining the distance information and the lane information.
The method of claim 5,
If there are two or more detected landmarks,
And the y coordinate is a y coordinate of a road in which the vehicle is traveling, the positioning module calculates the final position of the vehicle by averaging the y coordinate obtained from each landmark.
The method according to claim 1,
If only the angular information about the detected landmark is extracted,
And the positioning module calculates the final position of the vehicle by combining the angle information and the lane information.
The method of claim 7,
If there are two or more detected landmarks,
And the y coordinate is a y coordinate of a road in which the vehicle is traveling, the positioning module calculates the final position of the vehicle by averaging the y coordinate obtained from each landmark.
The method according to claim 1,
When the distance information and angle information of the landmark detected by the image processing module can not be extracted,
The positioning module tracks the landmark through the camera, estimates angle information for the landmark from the viewing angle value when the landmark is just before departing from the viewing angle of the camera, and calculates the position of the vehicle from the estimated angle information Wherein the vehicle positioning system comprises:
delete delete The method according to claim 1,
Wherein the map information receiving module receives LDM (Local Dynamic Map) information from a server.
A GPS receiver for receiving GPS (Global Positioning System) signals, and a vehicle positioning method in a vehicle positioning system for calculating the position of a vehicle in which a camera is installed,
A map information receiving step of receiving map information corresponding to a current vehicle position from a server by a received GPS signal;
A speed measuring step for measuring the speed of the vehicle;
An image processing step of detecting landmark information included in the map information in real time using an image photographed by the camera; And
And a positioning step of calculating a current position of the vehicle using the detected landmark information,
Wherein the landmark information detected in the image processing step includes at least one of distance information between the vehicle and the landmark and angle information between the vehicle and the landmark,
The lane detecting means detects the lane using the image photographed by the camera in the image processing step,
Wherein when the coordinates of the road in the direction perpendicular to the road of the vehicle is x coordinate, the lane information indicating the current vehicle is located at the lane of the road and the distance from the center of the lane is used as x Calculates coordinates,
If it is not possible to extract the distance information and the angle information of the landmark detected in the image processing step, the positioning step determines the position of the vehicle based on the maximum distance that the camera can sense and the position information of the currently detected landmark Respectively,
Wherein when the landmark that can be detected by the camera is missing, the positioning step assumes a virtual landmark and estimates the position of the vehicle using the speed information of the vehicle.
delete 14. The method of claim 13,
When both the distance information and the angle information for the detected landmark are extracted,
Wherein the positioning step calculates the position of the vehicle using the distance information, the angle information, and the lane information.
16. The method of claim 15,
If there are two or more detected landmarks,
Wherein said positioning step calculates the final position of the vehicle by averaging the position of the vehicle calculated from each landmark.
18. The method of claim 16,
If only the distance information for the detected landmark is extracted,
Wherein the positioning step calculates the final position of the vehicle by combining the distance information and the lane information.
18. The method of claim 17,
If there are two or more detected landmarks,
Wherein the positioning step calculates the final position of the vehicle by averaging the y coordinate obtained from each landmark, when the coordinate of the road direction in which the vehicle is traveling is the y coordinate.
14. The method of claim 13,
If only the angular information about the detected landmark is extracted,
Wherein the positioning step combines the angle information and the lane information to calculate a final position of the vehicle.
The method of claim 19,
If there are two or more detected landmarks,
Wherein the positioning step calculates the final position of the vehicle by averaging the y coordinate obtained from each landmark, when the coordinate of the road direction in which the vehicle is traveling is the y coordinate.
14. The method of claim 13,
When the distance information and angle information for the landmark detected in the image processing step can not be extracted,
The positioning step tracks the landmark through the camera to estimate the angle information for the landmark from the viewing angle value when the landmark is just before departing from the viewing angle of the camera and calculates the position of the vehicle from the estimated angle information Wherein the vehicle positioning method comprises the steps of:
delete delete 14. The method of claim 13,
Wherein the map information receiving step receives LDM (Local Dynamic Map) information from a server.

KR1020160016299A 2016-02-12 2016-02-12 System and method for positioning vehicle using local dynamic map KR101878685B1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020160016299A KR101878685B1 (en) 2016-02-12 2016-02-12 System and method for positioning vehicle using local dynamic map

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020160016299A KR101878685B1 (en) 2016-02-12 2016-02-12 System and method for positioning vehicle using local dynamic map

Publications (2)

Publication Number Publication Date
KR20170094947A KR20170094947A (en) 2017-08-22
KR101878685B1 true KR101878685B1 (en) 2018-07-16

Family

ID=59757996

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020160016299A KR101878685B1 (en) 2016-02-12 2016-02-12 System and method for positioning vehicle using local dynamic map

Country Status (1)

Country Link
KR (1) KR101878685B1 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20210396527A1 (en) * 2019-03-07 2021-12-23 Sk Telecom Co., Ltd. Apparatus and method for determining of correction information of vehicle sensor

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102030693B1 (en) * 2017-09-01 2019-10-10 엘지전자 주식회사 Vehicle control method
KR102418048B1 (en) * 2017-11-30 2022-07-07 현대오토에버 주식회사 Downtown 3d map implementation apparatus, system and method thereof
KR102420476B1 (en) * 2018-05-25 2022-07-13 에스케이텔레콤 주식회사 Apparatus and method for estimating location of vehicle and computer recordable medium storing computer program thereof
KR102627453B1 (en) * 2018-10-17 2024-01-19 삼성전자주식회사 Method and device to estimate position
US10650548B1 (en) * 2019-01-30 2020-05-12 StradVision, Inc. Method and device for localization of autonomous vehicle for route planning by using attention-driven landmark detection
KR102296168B1 (en) * 2019-12-17 2021-08-31 주식회사 와이즈인포텍 Positioning method and an electronic device
KR20240020032A (en) * 2022-08-05 2024-02-14 김재한 A method and system for creating a landmark map using a live map

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100723834B1 (en) * 2005-06-17 2007-05-31 한국전자통신연구원 Method and apparatus for compensating for car position in car navigation system
KR20070064052A (en) * 2005-12-16 2007-06-20 주식회사 대우일렉트로닉스 Car navigation device having map matching function
JP2012127896A (en) * 2010-12-17 2012-07-05 Kumamoto Univ Mobile object position measurement device
KR20140078158A (en) * 2012-12-17 2014-06-25 주식회사 만도 Deadreckoning-based navigation system using camera and control method thereof
KR20150019085A (en) * 2013-08-12 2015-02-25 재단법인대구경북과학기술원 Position Measuring System and the Method
KR20160002178A (en) * 2014-06-30 2016-01-07 현대자동차주식회사 Apparatus and method for self-localization of vehicle

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20050005115A (en) 2003-07-03 2005-01-13 주식회사 우리기술 Method of localization of guide mobile robot using image of panning/tilting camera and photo detector sensor and ir beacon

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100723834B1 (en) * 2005-06-17 2007-05-31 한국전자통신연구원 Method and apparatus for compensating for car position in car navigation system
KR20070064052A (en) * 2005-12-16 2007-06-20 주식회사 대우일렉트로닉스 Car navigation device having map matching function
JP2012127896A (en) * 2010-12-17 2012-07-05 Kumamoto Univ Mobile object position measurement device
KR20140078158A (en) * 2012-12-17 2014-06-25 주식회사 만도 Deadreckoning-based navigation system using camera and control method thereof
KR20150019085A (en) * 2013-08-12 2015-02-25 재단법인대구경북과학기술원 Position Measuring System and the Method
KR20160002178A (en) * 2014-06-30 2016-01-07 현대자동차주식회사 Apparatus and method for self-localization of vehicle

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20210396527A1 (en) * 2019-03-07 2021-12-23 Sk Telecom Co., Ltd. Apparatus and method for determining of correction information of vehicle sensor

Also Published As

Publication number Publication date
KR20170094947A (en) 2017-08-22

Similar Documents

Publication Publication Date Title
KR101878685B1 (en) System and method for positioning vehicle using local dynamic map
CN106289275B (en) Unit and method for improving positioning accuracy
US10788830B2 (en) Systems and methods for determining a vehicle position
Rose et al. An integrated vehicle navigation system utilizing lane-detection and lateral position estimation systems in difficult environments for GPS
US11193782B2 (en) Vehicle position estimation apparatus
KR101241171B1 (en) Method for correcting gps position information by image sensor
CN107735692B (en) Method and device for locating a vehicle
KR101209062B1 (en) Gps correction system using image recognition information and its method
JP5747787B2 (en) Lane recognition device
US20150025786A1 (en) Method And Device For Determining The Speed And/Or Position Of A Vehicle
KR101454153B1 (en) Navigation system for unmanned ground vehicle by sensor fusion with virtual lane
TWI522258B (en) Based on electronic map, global navigation satellite system and vehicle motion detection technology Lane identification method
US20120330527A1 (en) Drive assist system and wireless communication device for vehicle
KR102331312B1 (en) 3D vehicular navigation system using vehicular internal sensor, camera, and GNSS terminal
JP2009074859A (en) Motion measuring device and position measuring device
US20190346273A1 (en) Host vehicle position estimation device
JP6806891B2 (en) Information processing equipment, control methods, programs and storage media
JP6569572B2 (en) Vehicle position determination device
KR100525517B1 (en) Car navigation system and control method thereof
KR20160120467A (en) Azimuth correction apparatus and method of 2-dimensional radar for vehicle
WO2019046504A1 (en) Lane marker signal improvement through mapped geo-referenced boundaries
JP6916705B2 (en) Self-driving vehicle position detector
JP2018017668A (en) Information processing device and information processing program
US20200020126A1 (en) Host vehicle position estimation device
WO2020230314A1 (en) Self-positioning correction method and self-positioning correction device

Legal Events

Date Code Title Description
A201 Request for examination
E902 Notification of reason for refusal
E701 Decision to grant or registration of patent right
GRNT Written decision to grant