KR20170015754A - Vehicle Location Method of Skyline - Google Patents

Abstract

The present invention relates to a method of positioning a vehicle using a skyline, and more particularly, to a method of positioning a vehicle using a camera of the vehicle when the vehicle is traveling in an area where a skyline is formed by a structure such as a large- A second step of extracting a precise map data corresponding to the image of the skyline, a third step of separating a sky object and a structure object from the image of the skyline, A fourth step of aligning the accurate map data to the image of the object and the structure object, and a fifth step of positioning the vehicle, so as to smoothly drive the vehicle or to measure the vehicle position and lane level without receiving GPS signals. Thereby providing an effect of enabling autonomous driving.

Description

Vehicle Location Method of Skyline < RTI ID = 0.0 >

The present invention relates to a method of positioning a vehicle using a skyline, and more particularly, to a method of positioning a vehicle by photographing a skyline with an upper mounted camera when the vehicle is traveling in an area where GPS reception by a structure around the road is difficult, Which is located at the current lane position, through the comparison with the accurate map data.

Generally, a navigation system (a navigation system) that performs positioning by using a GPS receiver communicates with at least three GPS satellites, calculates the communication distance and communication time with each satellite, accurately grasps its current position The present position of the vehicle thus identified is displayed on an electronic map stored in the database, and the driver can go to the desired location by referring to the current position.

Such a GPS receiver has an advantage that it can easily grasp the current position of the vehicle with accuracy.

However, the method using the GPS satellites may cause a communication difficulty region due to one or more of the three GPS satellites due to the high-rise buildings, high-rise buildings or other high-rise buildings in the urban area of a metropolis.

In addition, due to the inaccuracy of the GPS satellite signal due to the high-rise buildings and high structures in the urban center, the navigation system using the satellite communication may cause an error. When the vehicle is operated automatically or unmanned, The method of operating by satellite may be dangerous.

Therefore, there is a need for a method of locating the vehicle position and lane using only the skyline, which is the sky boundary between all the structures that obstruct or restrict the reception of GPS signals.

As a conventional technique for solving the above-mentioned problems, Korean Patent Laid-Open Publication No. 10-2004-0049765 discloses a method for identifying the current position of a running vehicle using identifiable terrain information around the running vehicle, A driving device is known.

However, according to the conventional technique, the current position of the vehicle is precisely three-dimensionally set by using traffic signs, lanes, positional relationship between the vehicle and the landmark, and traffic signals around the vehicle during driving or driving. The present invention provides a method and system for enabling automatic operation of a vehicle, and it is understood that the present position of the vehicle is mainly determined by the three-dimensional traffic coordinates, and the vehicle is automatically operated by the current position information of the detected vehicle.

However, in the conventional technique described above, when the three-dimensional traffic coordinates are grasped by the sensor, the position of the vehicle can be grasped, but there is a limit in grasping the position of the accurate lane, and the positional relationship between the vehicle and the property is complex, There is a problem with this.

In addition, the above-described conventional technique uses the skyline of the building to determine the current position of the vehicle when the vehicle is traveling in a region where the skyline is formed by a building forest or a GPS non- However, there are many differences from the technique of positioning to the lane level.

SUMMARY OF THE INVENTION The present invention has been made in order to solve the above-mentioned problems of the conventional art, and it is an object of the present invention to provide a vehicle equipped with a camera capable of photographing the sky in the vertical direction from the ground in the upper part of the vehicle, There is provided a method of positioning a current position and a lane level by matching an image of a skyline taken by the camera with precision map data at the time of driving.

It is another object of the present invention to provide a system for solving the problem of difficulty in recognizing a position and a lane due to weak GPS signals when a vehicle is traveling in a region where GPS is not received.

In order to achieve the object of the present invention, when a vehicle is traveling in an area where a skyline is formed by a structure and GPS reception is obstructed, a video image of the skyline in a vertical direction on the ground A second step of searching for and acquiring accurate map data matching the video image of the skyline photographed in the first step using navigation installed in the vehicle, A third step of separating a sky object and a structure object image from a video image of the captured skyline, a third step of separating the sky object and the structure object image from the sky object and the image of the structure object, A fourth step in which the information is matched, the structure object is matched with the information of the structure, Been by matching information of the stage 4 is accomplished through what is made of a fifth step of positioning the current position of the vehicle and the lane-level periodically.

Therefore, the positioning method of the vehicle using the skyline of the present invention solves the problem that it is difficult to grasp the current position of the vehicle in a region where GPS reception is difficult due to the building forest or structure of a large city, .

In addition, the present invention utilizes only the communication means of the camera and the navigation without using various sensors, and provides the cost reduction effect of the system by setting the active positioning period.

In addition, the present invention provides an effect of acquiring the position of the vehicle by precise map data when the GPS signal reception is obstructed by the structure forming the skyline.

1 is a flowchart showing a flow of a positioning method of a vehicle using a skyline according to the present invention,
2 is a diagram illustrating an example of photographing a building skyline using a camera in a GPS non-receiving building forest according to an embodiment of the present invention,
3 is an exemplary view showing an example of a skyline distinguished according to the position of a vehicle according to an embodiment of the present invention;
FIG. 4A is a block diagram illustrating the precision map data of an intersection matching the skyline image of an intersection according to an embodiment of the present invention,
FIG. 4B is a diagram showing the accuracy map data in the straight line corresponding to the skyline image in the straight line according to the embodiment of the present invention,
5 is an exemplary diagram illustrating lane level positioning through a building skyline in accordance with an embodiment of the present invention.

The terms and words used in the present specification and claims should not be construed as limited to ordinary or dictionary terms and the inventor may appropriately define the concept of the term in order to best describe its invention It should be construed as meaning and concept consistent with the technical idea of the present invention.

Therefore, the embodiments described in the present specification and the configurations shown in the drawings are merely the most preferred embodiments of the present invention and are not intended to represent all of the technical ideas of the present invention. Therefore, various equivalents It should be understood that water and variations may be present.

The present invention is based on the fact that, when a vehicle is traveling on a road in which a skyline is formed by a building forest or a structure that is difficult to receive GPS, the shape of the sky on the skyline is similar to that of a ground including a road surface excluding a building or a structure And to provide a technique of determining the current position of the vehicle and positioning it to the lane level of the vehicle.

Generally, the skyline generally refers to a line connecting a boundary point where a building such as a high-rise building, which mainly appears in a central densely populated area of a large city, meets sky. In the present invention, Is interpreted to mean the boundary between the sky and all structures that obstruct or restrict the reception of GPS signals when they are viewed from the vehicle in the sky vertically.

Hereinafter, a method of positioning a vehicle using a skyline in a building forest, such as in an urban central business district according to an embodiment of the present invention, will be described in detail.

1 is a flowchart showing a flow of a positioning method of a vehicle using a skyline according to the present invention.

As shown in the drawing, the present invention includes a first step (S100) of photographing a video image of a skyline using a camera of the vehicle, a second step (S200) of searching and extracting precise map data matching the image of the skyline, A third step S300 of separating the sky object and the structure object from the image of the skyline, a fourth step S400 of matching the accurate map data to the sky object and the image of the structure object, And the fifth step S500.

The first step S100 is a step of photographing an image of a skyline in a vertical direction on the ground using a camera located on the upper part of the vehicle. It shows an example of shooting a building skyline using a camera.

At this time, the camera preferably utilizes a wide angle lens having a sufficiently large angle. Or a fisheye lens which can take a picture with a square angle exceeding 180 degrees. This is to provide an effect that a wide angle can be photographed in a narrow space when utilizing the wide angle lens and a wide area where a focused object is widened by using a deep object depth, so that every corner of the screen is clearly captured.

The skyline image photographed by the camera is transmitted to navigation located inside the vehicle using either a wired or wireless communication scheme.

The navigation system of the present invention basically includes a general navigation function, and includes communication means for interlocking with the camera, interlocking with an external network, and built-in software for processing a video image to inform the user of positional positioning and positional information A navigation device of a vehicle.

3 is an exemplary view showing an example of a skyline distinguished according to the position of a vehicle according to an embodiment of the present invention.

The image of the skyline in the building forest, like the city, shows that the skyline of the intersection and the skyline characteristic of the straight road are distinguished.

The second step (S200) searches the network server for the precision map data matching the video image of the skyline photographed in the first step (S100) using the communication means of the navigation installed in the vehicle and acquires .

At this time, the precision map data is data generated by a high-precision map construction vehicle that acquires position information on the road and its surroundings through a LiDAR (Light Detection And Ranging), a camera, a GPS and other sensors, Shape and lane of a building, and map data that is previously constructed and stored on a network server by mapping information of a structure such as the building and coordinates of a lane.

In addition, the precision map data may further include aerial map data in which aerial photographs are taken vertically at a predetermined height in the direction of the ground, and the shapes of buildings and roads appear.

FIG. 4A is an exemplary view showing that a skyline image of an intersection and an accurate map data of an intersection coincide with each other according to an embodiment of the present invention, and FIG. 4B is an example of precision map data coinciding with a skyline image of a straight road Show.

The third step S300 is a step of separating the sky object and the structure object image from the image of the skyline photographed in the first step S100. An algorithm for separating objects from video images used in MPEG (Moving Picture Experts Group) or JPEG (Joint Photographic Coding Experts Group) is used.

At this time, it can be seen that the sky object is an area on the space recognized as a virtual road on the video image of the captured skyline, and is a region capable of positioning at the lane level according to the center position of the camera focus.

In addition, the structure object of the present invention can be used to receive GPS signals such as a streetlight, an illuminated light, a roadside or signboard, and a roadway of a double road as well as a skyscraper or a building other than the sky object, It means the area of all things that can interfere.

Since the structures are preliminarily stored on the precise map data, they can match the position coordinates according to the precise map data.

Therefore, in the fourth step S400, the sky object is matched with the road name and the lane information by the precise map data on the image of the sky object and the structure object, and the information of the building or the structure is registered in the structure object Is a losing step.

The fifth step S500 is a step of periodically positioning the direction, the position, and the driving lane level of the vehicle according to the matched information of the fourth step S400.

5 is a diagram illustrating an example of lane-level positioning through a skyline according to an exemplary embodiment of the present invention. As shown in FIG. 5, it is shown that the lane level can be positioned on the sky object according to the center position of the camera focus.

In the fifth step S500, the positioning cycle is lengthened by a predetermined time at a point where the change of the road shape is small by referring to the precision map data, and the positioning period is shortened by a predetermined time at the point where the change of the road shape is large It is possible to operate the system with low power to reduce the load on the CPU.

In another embodiment of the present invention, when the upper part is viewed from the lower road of the double bridge or the double elevated road where GPS is not received, the boundary shape along the skyline of the upper structure can be compared with the structure information on the precise map data, The position and the lane level of the vehicle can be determined by using the sky object and the structure object on both sides of the road as described above.

In another embodiment of the present invention, the sky line of the skyline, which is seen through the roadside trees even when driving in an area where GPS is not received, is closely packed with roads on both sides of the road, The position of the vehicle and the lane level can be determined.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is clearly understood that the same is by way of illustration and example only and is not to be taken by way of limitation, Various changes and modifications will be possible.

Claims (7)

When the vehicle is traveling in an area where the skyline is formed by the structure and GPS reception is obstructed,
A first step of acquiring a video image of a skyline in a vertical direction on the ground using a camera located at an upper portion of the vehicle;
A second step of searching and acquiring accurate map data corresponding to a video image of the skyline photographed in the first step using navigation installed in the vehicle;
A third step of separating a sky object and a structure object image from a video image of the skyline photographed in the first step;
A fourth step of matching the road name and the lane information to the sky object by the precise map data on the image of the sky object and the structure object in the third step and the information on the structure is matched to the structure object, ; And
And a fifth step of periodically locating the current position and the lane level of the vehicle according to the matched information of the fourth step.
The method according to claim 1,
Wherein the camera is a wide-angle lens or a fisheye lens capable of photographing with an angle of more than 180 degrees.
The method according to claim 1,
The precision map data is map data that includes image information about the shape of the skyline by the structure and is previously constructed and stored on the network server by mapping the information about the structure and the road with the coordinate position. A method of positioning a vehicle using a skyline.
The method of claim 3,
Wherein the precision map data further includes aerial map data obtained by aerial photographing at a predetermined height vertically in the direction of the ground.
The method according to claim 1,
Wherein the sky object is a spatial image area recognized as an imaginary road on the image of the skyline, and is an area in which the lane level positioning is possible according to the center position of the camera focus.
The method according to claim 1,
The structure object is an area including a structure around the road that can obstruct the reception of GPS signals on the image of the skyline, and is an object capable of matching information of the structure according to the precise map data. A method of positioning a vehicle using a skyline.
The method according to claim 1,
The positioning period is lengthened by a predetermined time at a point within a certain range of change of the road shape with reference to the precision map data, and the positioning period is shortened by a predetermined time at a point where the change of the road shape exceeds a certain range. A method of positioning a vehicle using the method.

Images