KR20220123901A - Method and system for generating HD maps based on aerial images taken by unmanned aerial vehicles or aircraft - Google Patents

Abstract

A reference figure is selected from the first aerial image obtained by photographing the target area at a first viewpoint looking at the target area, and the reference figure is added to the reference figure from the second aerial image obtained by photographing the target area at a second viewpoint different from the first aerial image. By identifying the corresponding corresponding figure, matching the reference figure and the corresponding figure with each other, the three-dimensional position (three-dimensional position including elevation or elevation) of the reference figure is determined, and the determined three-dimensional position is used for the target area A method for generating an HD map is provided.

Description

METHOD AND SYSTEM FOR GENERATING HIGH-DEFINITION MAP BASED ON AERIAL IMAGES CAPTURED FROM UNMANNED AIR VEHICLE OR AIRCRAFT

Embodiments relate to a method of generating a high definition (HD) map based on an aerial image, and a three-dimensional position (eg, altitude) of a point in the same target region based on aerial images taken from different viewpoints. or a method of generating an HD map for a target area by acquiring a three-dimensional position including elevation).

The HD (High Definition) map is a high-precision map used in the field of autonomous driving and the like, and has a higher accuracy than the existing map. For example, in such an HD map, information about the surrounding environment of a target area, such as a road, a terrain elevation, and a curvature, may be implemented in three dimensions, and may have an accuracy of 10 times or more than that of an existing map. The HD map may have an error of, for example, less than 10 cm.

The HD map may be generated based on data collected from a Mobile Mapping System (MMS) vehicle traveling on a road or data measured on the ground. However, according to this, the HD map accompanies an error due to a location error or elevation error of the GPS mounted on the MMS, and requires a large-scale survey data, and the accompanying cost is also excessive.

On the other hand, a True Ortho image is generated based on a digital surface model (DSM) and a digital elevation model (DEM) generated based on the registered aerial image, and Even in the case of a method of generating an HD map based on the DSM, there is a problem that errors generated in generating the DSM, DEM, and vertical orthogonal images are also reflected in the HD map.

Korean Patent Application Laid-Open No. 10-2020-0094644 (published on August 07, 2020) discloses a 3D space using depth prediction information for each object and class information for each object, obtained through V2X information fusion technology. Disclosed are a learning method and a learning apparatus for updating an HD map by rebuilding.

The information described above is for understanding only, and may include content that does not form a part of the prior art.

According to an embodiment, a three-dimensional position (a three-dimensional position including an altitude or an altitude) of facilities included in the target area may be determined based on aerial images taken of the same target area from different viewpoints, and the determined A method for generating an HD map for a target area based on a three-dimensional position may be provided.

According to an embodiment, a reference figure selected from a first aerial image obtained by photographing the target area from a first viewpoint looking at the target area and a second aerial image obtained by photographing the target area from a second viewpoint different from the first aerial image By matching the corresponding figure identified in the image, it is possible to provide a tool for determining a three-dimensional position (elevation or a three-dimensional position including elevation) of a reference figure.

In one aspect, in a method of generating a high definition (HD) map based on an aerial image performed by a computer system, a first photographing the target area from a first viewpoint looking at the target area selecting a reference figure from an aerial image; identifying a corresponding figure corresponding to the reference figure from a second aerial image obtained by photographing the target area at a second viewpoint different from the first aerial image; A method for generating an HD map is provided, comprising: determining a three-dimensional position of the reference figure by matching the corresponding figures with each other; and generating an HD map for the target area using the determined three-dimensional position do.

The determining may include a three-dimensional position and a shooting direction of the camera that captured the first aerial image corresponding to the first viewpoint, and a three-dimensional position of the camera that photographed the second aerial image corresponding to the second viewpoint. A three-dimensional position including the elevation of the reference figure according to a triangulation method based on a photographing direction, a first angle with respect to the reference figure from the first viewpoint, and a second angle with respect to the corresponding figure from the second viewpoint can decide

The reference figure includes a vertex of any one of the facilities included in the target area of the first aerial image, or connects the vertex to another vertex of the one facility or a vertex of another facility among the facilities One line, the baseline, may be included.

The selecting includes selecting a reference facility from among facilities included in the target area of the first aerial image and selecting the reference line as at least one guide line intersecting the reference facility, In the identifying, a corresponding line corresponding to the guide line in the second aerial image is identified as the corresponding figure,

The determining may include determining a three-dimensional position of the guide line by matching the guide line and the corresponding line, and based on the three-dimensional position of the guide line, the guide line and the reference facility intersect It may include determining the three-dimensional position of the point.

The reference facility may be a center line of a road within the target area, and the guide line may be a line connecting vertices of two lanes positioned around the center line.

The selecting may include selecting a line connecting vertices of a reference facility among facilities included in the target area of the first aerial image as the reference line, and the identifying may include selecting the reference line in the second aerial image. In the determining of a corresponding line corresponding to the corresponding figure, the three-dimensional position of the reference line may be determined by matching the reference line with the corresponding line.

The method for generating the HD map includes the steps of determining a three-dimensional location of the reference facility and determining the three-dimensional location of at least one surrounding facility around the reference facility based on the three-dimensional location of the reference facility. may include more.

The determining of the three-dimensional location of the surrounding facility may include adjusting an altitude value corresponding to the three-dimensional location of the reference facility according to a gradient existing between the reference facility and the surrounding facility, and the adjusted altitude It may include determining a three-dimensional position of the surrounding facility based on the value.

The reference facility may be a center line of a road within the target area, and the surrounding facility may be each of lanes positioned around the center line.

The method for generating the HD map further includes determining a three-dimensional location of a facility in the target area including the reference figure based on the determined three-dimensional location, wherein the three-dimensional location of the facility is determined by the determined three-dimensional location. It may be determined by calculating the three-dimensional positions of the points constituting the facility according to interpolaration based on the three-dimensional position of the reference figure.

The determining may include: projecting the first aerial image including the selected reference figure or the selected reference figure to the second aerial image; Moving the reference figure so that the identified corresponding figure matches, and determining an elevation value of the reference figure corresponding to when the identified corresponding figure matches the reference figure as a three-dimensional position of the reference figure can do.

The determining may include outputting an altitude value corresponding to a moved position as the reference figure is moved, and an altitude value output when the identified corresponding figure and the reference figure match is determined by the reference figure. It may be determined by the three-dimensional position of the figure.

The moved reference figure may be a layer corresponding to the reference figure.

The method for generating the HD map includes generating at least one of a digital surface model (DSM) and a digital elevation model (DEM) for the target area using the determined three-dimensional position. It may include further steps.

The method of generating the HD map may further include generating a true ortho image of the target region based on the generated DSM and DEM.

In another aspect, a computer system includes at least one processor configured to execute computer readable instructions contained in a memory, wherein the at least one processor is configured to: A reference figure is selected from the first aerial image obtained by photographing , and a corresponding figure corresponding to the reference figure is identified in the second aerial image obtained by photographing the target area from a second viewpoint different from the first aerial image. and determining a three-dimensional position of the reference figure by matching the reference figure and the corresponding figure with each other, and generating an HD map for the target area using the determined three-dimensional position.

From aerial images taken of the target area from different viewpoints, 3D location (3D location including elevation or elevation) 3D location (3D location including elevation or elevation) for facility(s) included in the aerial image dimensional position) can be determined to create an HD map of the target area without performing the process of creating a DSM or DEM. In addition, by using aerial images to generate HD maps, extensive surveying work or data acquisition through MMS vehicles may not be required.

By using aerial images of the target area from different viewpoints, it is possible to accurately determine a 3D location including an altitude even for a facility that is obscured from a specific aerial image.

1 is a diagram illustrating three-dimensional positions (three-dimensional positions including elevation or altitude) of facilities included in a target area based on aerial images captured from different viewpoints in the same target area, according to an exemplary embodiment; and how to create an HD map.
2 is a block diagram illustrating a structure of a computer system for generating an HD map based on aerial images, according to an embodiment.
3 is a diagram illustrating three-dimensional positions (three-dimensional positions including elevation or elevation) of facilities included in a target area determined based on aerial images obtained from different viewpoints of the same target area, according to an exemplary embodiment; and is a flowchart showing a method of generating an HD map.
4 and 5 are three-dimensional views of a reference facility through selecting a guide line from a first aerial photograph and determining a three-dimensional position (a three-dimensional position including an altitude or an altitude) of the guide line, according to an example; A flow chart showing a method for determining a location (elevation or a three-dimensional location that includes elevation).
6 is a flowchart illustrating a method of determining a three-dimensional position (a three-dimensional position including an altitude or an altitude) of a surrounding facility based on an altitude of a reference facility, according to an example.
7 is a method for determining a three-dimensional position (a three-dimensional position including an altitude or an altitude) of a reference figure by matching a reference figure selected from the first aerial image and a corresponding figure identified from the second aerial image, according to an example; A flowchart showing the method.
8 illustrates a method of generating a DSM and a DEM of a target area according to a determined altitude and further generating a vertical orthogonal image of the target area according to an example.
9 is a method for determining a three-dimensional position (three-dimensional position including elevation or altitude) of a reference figure by matching a reference figure selected in the first aerial image with a corresponding figure identified in the second aerial image, according to an example; indicates how.
10 is a three-dimensional position (altitude) of a reference facility through selecting a guide line from a first aerial photograph and determining a three-dimensional position (a three-dimensional position including an altitude or an altitude) of the guide line, according to an example; or a method of determining a three-dimensional position including elevation).
11 is a flowchart illustrating a method of determining a three-dimensional position (a three-dimensional position including an altitude or an altitude) of a surrounding facility based on an altitude of a reference facility, according to an example.

Hereinafter, embodiments will be described in detail with reference to the accompanying drawings. Like reference numerals in each figure indicate like elements.

In the drawings and detailed description to be described later, “altitude” and “determination of altitude” may be replaced with “three-dimensional position” and “determination of three-dimensional position”.

1 is a diagram illustrating three-dimensional positions (three-dimensional positions including elevation or altitude) of facilities included in a target area based on aerial images captured from different viewpoints in the same target area, according to an exemplary embodiment; and how to create an HD map.

A method of creating a high definition (HD) map 50 for the target area 30 corresponding to at least a part of the target area will be described with reference to FIG. 1 . The HD map 50 is a high-precision map, and may be a map having higher accuracy than a conventional map. For example, in the HD map 50 , as shown, surrounding environment information of the target area 30 such as roads, terrain elevations, and curvatures may be implemented in three dimensions. That is, in the HD map 50 , information on facilities included in the target area 30 may be implemented in three dimensions. The facilities included in the target area 30 may include, for example, a road, a center line included in the road (drawn), and a lane included in the road (drawn). The HD map 50 may include, for example, a map used when the autonomous vehicle autonomously drives the target area 30 .

The target area 30 may be an area distributed to workers for the construction of the HD map 50 .

In the embodiment, a computer system (hereinafter, a computer system 100 to be described later with reference to FIG. 2 ) uses the aerial images 10 and 20 obtained by photographing the target area 30 , and a facility in the target area 30 . It is possible to determine the three-dimensional position (altitude or three-dimensional position including the elevation) of the three-dimensional objects, and generate the HD map 50 for the target area 30 based on the three-dimensional positions of the determined facilities.

The "altitude" of a facility (or a specific point) may be an altitude or elevation. Alternatively, “altitude” may indicate the absolute height of a corresponding facility (or a specific point). Alternatively, “altitude” may indicate depth information with respect to a predetermined reference of a corresponding facility (or a specific point). In this case, the reference may be the sea level or the ground.

The three-dimensional position of a specific point described in the present disclosure may mean the elevation of the specific point, or a three-dimensional position including the elevation of the specific point (eg, three-dimensional coordinates including elevation and horizontal coordinates). .

The computer system 100 obtains the first aerial image 10 obtained by photographing the target area 30 and the second aerial image 20 obtained by photographing the target area 30 at a different viewpoint from the first aerial image 10 . It may be used to determine a three-dimensional position or altitude associated with the target area 30 (ie, a three-dimensional location or altitude of a facility (or a specific point) included in the target area 30 ). The first aerial image 10 and the second aerial image 20 may be registered images. That is, the first aerial image 10 and the second aerial image 20 may be images in which postures are determined. In the present disclosure, “image” may include an image or an image.

The first aerial image 10 and the second aerial image 20 are images captured by an unmanned aerial vehicle such as a drone flying over a target area including the target area 30 or an aircraft (for surface imaging) or the photographed image is It may be a registered image.

For example, the computer system 100 takes the same point in the target area 30 of the first aerial image 10 and the target area 30 of the second aerial image 20 to determine the exact three-dimensional position of the point. can be specified. In one example, the computer system 100 may use triangulation to determine the exact three-dimensional location of the point.

Computer system 100 calculates the altitude (height) of a particular point based on aerial photographs, or calculates the altitude of a point for plotting a contour line, in a similar way to the computer system 100 at a point in the target area 30. It is possible to determine a three-dimensional position (elevation or a three-dimensional position including elevation) for the .

For a more specific method for the computer system 100 to determine a three-dimensional position (a three-dimensional position including elevation or elevation) for a point in the target area 30, refer to FIGS. 2 to 11 to be described later. described in more detail.

2 is a block diagram illustrating a structure of a computer system for generating an HD map based on aerial images, according to an embodiment.

The computer system 100 for performing the method of determining the three-dimensional position of the target area 30 and generating the HD map 50 according to the situation according to the embodiments to be described later is the computer system having the structure shown in FIG. 2 . (100) can be implemented.

The computer system 100 may be a system for executing a program that performs a method of determining a three-dimensional position with respect to the region 30 and generating the HD map 50 . Such a program may be loaded into the computer system 100 .

The computer system 100 may be a client terminal used by a user to process a task for generating the HD map 50 . The computer system 100 may be an electronic device capable of installing and executing a program for performing a method of determining a three-dimensional position and generating the HD map 50 . For example, the computer system 100 is a personal computer (PC), a laptop computer, a laptop computer, a smart phone, a tablet, an Internet of Things (Internet Of Things) device, or a wearable computer (wearable computer). computer), etc.

As shown in FIG. 2 , the computer system 100 may include a memory 110 , a processor 120 , a communication interface 130 , and an input/output interface 140 as components.

The memory 110 is a computer-readable recording medium and may include a random access memory (RAM), a read only memory (ROM), and a permanent mass storage device such as a disk drive. Here, a non-volatile mass storage device such as a ROM and a disk drive may be included in the computer system 100 as a separate permanent storage device distinct from the memory 110 . Also, an operating system and at least one program code may be stored in the memory 110 . These software components may be loaded into the memory 110 from a computer-readable recording medium separate from the memory 110 . The separate computer-readable recording medium may include a computer-readable recording medium such as a floppy drive, a disk, a tape, a DVD/CD-ROM drive, and a memory card. In another embodiment, the software components may be loaded into the memory 110 through the communication interface 130 rather than the computer-readable recording medium. For example, the software components may be loaded into the memory 110 of the computer system 100 based on a computer program installed by files received over the network 160 .

The processor 120 may be configured to process instructions of a computer program by performing basic arithmetic, logic, and input/output operations. The instructions may be provided to the processor 120 by the memory 110 or the communication interface 130 . For example, the processor 120 may be configured to execute a received instruction according to a program code stored in a recording device such as the memory 110 .

The communication interface 130 may provide a function for the computer system 100 to communicate with other devices via the network 160 . For example, a request, command, data, file, etc. generated by the processor 120 of the computer system 100 according to a program code stored in a recording device such as the memory 110 is transmitted to the network ( 160) to other devices. Conversely, signals, commands, data, files, etc. from other devices may be received by the computer system 100 through the communication interface 130 of the computer system 100 via the network 160 . A signal, command, or data received through the communication interface 130 may be transferred to the processor 120 or the memory 110 , and the file may be a storage medium (described above) that the computer system 100 may further include. persistent storage).

A communication method through the communication interface 130 is not limited, and a communication method using a communication network (eg, a mobile communication network, a wired Internet, a wireless Internet, a broadcasting network) that the network 160 may include as well as a communication method using a short distance between devices Wired/wireless communication may be included. For example, the network 160 may include a personal area network (PAN), a local area network (LAN), a campus area network (CAN), a metropolitan area network (MAN), a wide area network (WAN), and a broadband network (BBN). , the Internet, and the like. In addition, the network 160 may include any one or more of a network topology including a bus network, a star network, a ring network, a mesh network, a star-bus network, a tree or a hierarchical network, and the like, such that not limited

The input/output interface 140 may be a means for an interface with the input/output device 150 . For example, the input device may include a device such as a microphone, keyboard, camera, or mouse, and the output device may include a device such as a display or speaker. As another example, the input/output interface 140 may be a means for an interface with a device in which functions for input and output are integrated into one, such as a touch screen. The input/output device 150 may be configured as one device with the computer system 100 .

Also, in other embodiments, computer system 100 may include fewer or more components than those of FIG. 2 . However, it is not necessary to clearly show most of the prior art components. For example, the computer system 100 may be implemented to include at least a portion of the above-described input/output device 150 or may further include other components such as a transceiver, a camera, various sensors, and a database.

The processor 120 of the computer system 100 performs a three-dimensional position (elevation or a three-dimensional position including an altitude) with respect to the facilities included in the target area 30 based on aerial images 10 and 20 to be described later. ) and performing the steps for performing a method of generating the HD map 50 .

Meanwhile, the computer system 100 may be a server that communicates with a client terminal used by a user who processes a task for generating the HD map 50 . That is, based on the aerial images 10 and 20 to be described later, 3D positions (3D positions including elevation or elevation) of facilities included in the target area 30 are determined, and the HD map 50 ) may be performed by the computer system 100, which is a server communicating with a client terminal.

Alternatively, a three-dimensional position (a three-dimensional position including an altitude or an altitude) of facilities included in the target area 30 is determined based on the aerial images 10 and 20 to be described later, and the HD map 50 ), the client terminal and the server may be configured such that only at least some of the steps for performing the method of generating are performed in the server.

In the detailed description to be described later, for convenience of description, it is described that the above steps are performed by the computer system 100 (which may correspond to either a server and/or a client terminal).

Meanwhile, an operation performed by the processor 120 or other components of the computer system 100 or an operation performed by an application/program executed by the processor 120 is performed by the computer system 100 for convenience of description. It can be described as an operation that becomes

As described above, the technical features described above with reference to FIG. 1 may be directly applied to FIG. 2 , and thus a redundant description will be omitted.

3 is a diagram illustrating three-dimensional positions (three-dimensional positions including elevation or elevation) of facilities included in a target area determined based on aerial images obtained from different viewpoints of the same target area, according to an exemplary embodiment; and is a flowchart showing a method of generating an HD map.

In operation 310 , the computer system 100 may acquire the first aerial image 10 obtained by photographing the target area 30 . The first aerial image 10 may be an image photographed by an unmanned aerial vehicle such as a drone flying over a target area including the target area 30 or an aircraft (for surface photographing) or an image obtained by matching the photographed image. For example, the first aerial image 10 may be an image in which a posture is determined as a registered image. For example, the first aerial image 10 may correspond to an image photographed in a vertical direction on the ground surface. Alternatively, the first aerial image 10 may correspond to an image photographed vertically or in an arbitrary direction (ie, at a viewpoint) in which an operator identifies a target area or an operation is easy.

The computer system 100 may acquire the first aerial image 10 by loading the pre-stored first aerial image 10 . A drone or unmanned aerial vehicle flying over a target may photograph the target with a predetermined degree of redundancy, and the first aerial image 10 may be determined according to matching of images having such overlap. The first aerial image 10 may be obtained by photographing the target area 30 from a first viewpoint that vertically views the target area 30 (as much as possible) among the images in which the target area 30 is captured. have. In other words, the first aerial image 10 may be the most vertical image of the target region 30 captured by the target region 30 .

In operation 320 , the computer system 100 may select a reference figure from the first aerial image 10 obtained by photographing the target area 30 at the first viewpoint looking at the target area 30 . For example, the user may use a tool for determining a three-dimensional position (e.g., a three-dimensional position (elevation or a three-dimensional position including an altitude) of a reference figure) in the target region 30 portion of the first aerial image 10 displayed on the screen. ) may select a reference figure), and the computer system 100 may select the reference figure according to an input from the user. The reference figure may include at least one of a point, a line, and a surface (closed curve or polygon) selected within the target area 30 . The reference figure in the target area 30 may be a target for determining an elevation value.

The reference figure may include a vertex of any one of the facilities included in the target area 30 of the first aerial image 10, or/additionally, the vertex and another vertex of the one facility or It may include a reference line that is a line connecting vertices of other facilities among the facilities. Each of the facilities included in the target area 30 may include, for example, a road, a center line included in the road (drawn), and a lane included in the road (drawn). Alternatively, the facility may be any feature included in the target area 30 .

The selected reference figure may be visually distinguished from other parts of the first aerial image 10 .

In operation 330 , the computer system 100 may acquire the second aerial image 20 obtained by photographing the target area 30 . Regarding the acquisition of the second aerial image 20 and the second aerial image 20 , a description similar to that described above with respect to the first aerial image 10 may be applied as it is, and thus a redundant description will be omitted. However, the second aerial image 20 may be a photograph of the target area 30 at a second viewpoint different from the first aerial image 10 . That is, the first aerial image 10 and the second aerial image 20 may be images from different viewpoints. For example, while the first aerial image 10 is obtained by photographing the target region 30 vertically (or closest to the vertical), the second aerial image 20 includes the target region 30 at an angle other than vertical. It may have been filmed with

The computer system 100 may acquire the second aerial image 20 by loading the pre-stored second aerial image 20 . At this time, when the first aerial image 10 is loaded or a reference figure is selected from the first aerial image 10 , the computer system 100 may automatically search for and load a suitable second aerial image 20 . have. For example, the computer system 100 compares coordinate values included in the first aerial image 10 and the second aerial image 20 that are, for example, matched images (or the coordinate values of the selected reference figure and the second aerial image 20 ). ), the second aerial image 20 obtained by photographing the same target area 30 as the first aerial image 10 may be searched and loaded based on the comparison of coordinate values of .

The second aerial image 20 may be plural. The second aerial image 20 may be displayed as a thumbnail when the first aerial image 10 is displayed as the main on the screen, and when the corresponding thumbnail is selected, the second aerial image 20 is displayed as the main on the screen. can In this case, the first aerial image 10 may be displayed as a thumbnail. Alternatively, the second aerial image 20 may be arranged on the screen in the same size as the first aerial image 10 .

The first aerial image 10 may correspond to a master image, and the second aerial image 20 may correspond to a slave image.

In step 340 , the computer system 100 performs the first aerial image 10 in the second aerial image 20 obtained by photographing the target area 30 at a second viewpoint different from the first aerial image 10 . A corresponding figure corresponding to the selected reference figure may be identified. The corresponding figure may be a part of the second aerial image 20 that matches the reference figure of the first aerial image 10 .

The corresponding figure may be automatically identified from the second aerial image 20 . For example, the computer system 100 compares the first aerial image 10 and the second aerial image 20 (for example, the first aerial image 10 and the second aerial image 20, which are registered images). Based on the comparison of the form (shape or color, etc.) of the comparison reference figure of the coordinate values and the second aerial image 20), a corresponding figure corresponding to the reference figure may be identified.

Alternatively, the corresponding figure may be identified according to a user's selection (eg, through a user interface provided by a tool) in the target area 30 portion of the second aerial image. For example, the user recognizes the portion of the second aerial image 20 corresponding to the reference figure of the first aerial image 10 by comparing the first aerial image 10 and the second aerial image 20 displayed on the screen. to select the corresponding figure, and the computer system 100 may identify the corresponding figure according to the input from the user.

The corresponding figure may include at least one of a line and a surface (closed curve or polygon) according to the corresponding reference figure. The corresponding figure may be compared to the reference figure to determine a three-dimensional position (altitude value).

The first point of view is a three-dimensional position (eg, three-dimensional coordinates (x, y, z)) and a shooting direction (a shooting angle of the camera (yaw, roll, pitch)) of the camera that has taken the first aerial image 10 may include Similarly, as for the second viewpoint, the second viewpoint is a three-dimensional position (eg, three-dimensional coordinates (x, y, z)) and a photographing direction (a photographing angle of the camera (yaw, roll, pitch)).

In step 350, the computer system 100 matches the reference figure of the first aerial image 10 and the corresponding figure of the second aerial image 20 with each other, so that the three-dimensional position (including elevation or elevation) of the reference figure is performed. 3D position) can be determined.

Below, a method of determining a three-dimensional position (a three-dimensional position including an altitude or an altitude) of a reference figure by matching a reference figure of the first aerial image 10 and a corresponding figure of the second aerial image 20 with each other will be described in more detail.

The computer system 100 corresponds to the same area in the target area 30 of the first aerial image 10 and the target area 30 of the second aerial image 20 (consisting of at least one of a point, a line, and a plane). ) by taking the reference figure and the corresponding figure thereto, the precise three-dimensional position of the corresponding area (ie, the reference figure) can be specified. For example, the computer system 100 may use triangulation to determine the exact three-dimensional location of the point. In addition, computer system 100 calculates the elevation (height) of a specific point based on aerial photographs, or calculates the elevation of a point for plotting a contour line, in a similar manner to the computer system 100 in the target area 30. A three-dimensional position (a three-dimensional position including an altitude or an altitude) with respect to the reference figure may be determined.

As an example, the computer system 100 may (according to the image registration process) the three-dimensional position and the shooting direction of the camera that captured the first aerial image 10 corresponding to the first viewpoint that has become a known value, and the second viewpoint. 3D position of a point of a common target area in the first aerial image 10 and the second aerial image 20 based on the 3D position and the shooting direction of the camera that has captured the second aerial image 20 corresponding to can be decided In determining the 3D position, focal length information and principal point information of the camera may be further used as information of the camera.

When the three-dimensional position (x, y, z) of the camera photographing the first aerial image 10 and the second aerial image 20 and the photographing direction (yaw, roll, pitch) are respectively determined through the registration process , two line segments looking at a point commonly included in each image may be determined, and a three-dimensional position of the point may be determined by calculating the intersection of these line segments.

The photographing altitude of the first aerial image 10 and the photographing altitude of the second aerial image 20 may be the same. According to the above method, the computer system 100 compares the reference figure and the corresponding figure to each other as the reference figure is selected from the first aerial image 10 and the corresponding corresponding figure is identified from the second aerial image 20 . By matching, a three-dimensional position (a three-dimensional position including an altitude or an altitude) of the reference figure can be determined. "Matching" of the reference figure and the corresponding figure is a comparison between the first aerial image 10 and the second aerial image 20 and/or determining the above-mentioned three-dimensional position (three-dimensional position including altitude or altitude) ( It may mean encompassing operations for calculation).

Alternatively, the computer system 100 may configure the parallax between the first viewpoint of the first aerial image 10 and the second viewpoint of the second aerial image 20 (eg, a three-dimensional position of the camera and the second viewpoint indicated by the first viewpoint). the three-dimensional position of the reference figure (altitude or 3D position including elevation) can be determined. That is, the computer system 100 may match (match) the reference figure and the corresponding figure, and accurately specify the three-dimensional position of the reference figure according to the triangulation method.

At this time, the first aerial image 10 and the second aerial image 20 are registered images, and as described above, each image includes the three-dimensional position and shooting direction (expression) of the camera where the image was captured. can In other words, the first aerial image 10 and the second aerial image 20 are information about a viewpoint at which the image was captured, respectively, and three-dimensional coordinate information and rotation information ( camera's yaw, roll, pitch, etc.).

Specifically, the computer system 100 captures the three-dimensional position and shooting direction of the camera that has captured the first aerial image 10 corresponding to the first viewpoint, and the second aerial image 20 corresponding to the second viewpoint. A three-dimensional position and a shooting direction of the camera, a first angle with respect to the reference figure from a first viewpoint (that is, a three-dimensional position of the camera photographing the first aerial image 10), and a second viewpoint (ie, a second aerial image) The three-dimensional position including the elevation of the reference figure may be determined according to a triangulation method based on a second angle with respect to the corresponding figure from the three-dimensional position of the camera that captured the image 20).

According to the above method, the computer system 100 compares the reference figure and the corresponding figure to each other as the reference figure is selected from the first aerial image 10 and the corresponding corresponding figure is identified from the second aerial image 20 . By matching (matching), the three-dimensional position (three-dimensional position including elevation or elevation) of the reference figure can be determined according to the triangulation method.

The computer system 100 may determine the three-dimensional position of the facility in the target area 30 including the reference figure based on the three-dimensional position (altitude or three-dimensional position including the altitude) determined in step 350 . have. The three-dimensional position of the facility is calculated according to interpolation based on the determined three-dimensional position of the reference figure. can be determined by

Meanwhile, when a preset reference altitude is used, the computer system 100 may determine the three-dimensional position of a point in the target area using only the first aerial image 10 (ie, one aerial image). The preset reference altitude may be an altitude value (eg, elevation) for a point in the first aerial image 10 or the second aerial image 20 . Alternatively, the reference elevation may be a reference elevation value set in a program (eg, the aforementioned tool) used to determine a three-dimensional position (a three-dimensional position including elevation or elevation) of a reference figure and generate an HD map. . The reference altitude is a peripheral altitude value associated with the first aerial image 10 or the second aerial image 20 , and the altitude determined in step 350 may be a value based on the reference altitude.

For example, the computer system 100 may include a three-dimensional position and a shooting direction of a camera that has captured the first aerial image 10 corresponding to the first viewpoint, a first angle with respect to the reference figure from the first viewpoint, and a preset reference. The elevation of the reference figure may be determined based on the elevation. Also, the computer system 100 may determine a three-dimensional position of the reference figure by determining horizontal coordinates for the reference figure based on the determined altitude.

The three-dimensional position of the reference figure determined above (by triangulation, etc.) may include not only the elevation of the reference figure, but also horizontal coordinates. In other words, in the embodiment, the three-dimensional position of the reference figure is determined using the aerial image in which the three-dimensional position and the shooting direction of the camera are determined. This three-dimensional position is determined with the horizontal coordinates at the same time as the height is determined. can be decided.

In step 360 , the computer system 100 may generate the HD map 50 for the target area 30 using the three-dimensional position of the reference figure determined in step 350 . That is, the computer system 100 may specify the correct altitude (height) for the facilities included in the target area 30 by step 350, and use this as height information for the facilities to obtain an HD map ( 50) can be created. For example, in the embodiment, the HD map 50 including facilities such as a lane determined by connecting the determined altitude values may be generated. In generating the HD map 50 , information included in the above-described aerial images may be further used.

Therefore, according to an embodiment, the HD map 50 for the target area 30 based on the (matched) aerial images may be directly generated without performing a process of separately generating a DSM or a DEM. Accordingly, through the embodiment, a problem of terrain distortion that may occur when the HD map 50 is generated based on DSM and DEM or a problem of height distortion of a facility obscured from an aerial photograph can be solved.

Through the embodiment, the height of facilities such as the center line or lane within the target area 30 can be precisely specified, and the HD map 50 in which height information about the facilities is accurately reflected can be generated.

In addition, by utilizing a plurality of aerial images (that is, aerial images taken from different viewpoints of the target area 30), the height of a facility that is not visible (by a roadside tree, vehicle, shadow, etc.) is also covered in one aerial image. It can be precisely specified using other aerial images.

As described above, the technical features described above with reference to FIGS. 1 and 2 can be applied to FIG. 3 as they are, and thus a redundant description will be omitted.

4 and 5 are three-dimensional views of a reference facility through selecting a guide line from a first aerial photograph and determining a three-dimensional position (a three-dimensional position including an altitude or an altitude) of the guide line, according to an example; A flow chart showing a method for determining a location (elevation or a three-dimensional location that includes elevation).

A method of determining a three-dimensional position (a three-dimensional position including an altitude or an altitude) with respect to a facility corresponding to a reference facility within the target area 30 will be described in more detail with reference to FIGS. 4 and 5 .

In operation 410 , the computer system 100 may select a reference facility from among facilities included in the target area 30 of the first aerial image 10 . For example, the user may select a reference facility (eg, via a user interface provided by a tool) in a portion of the target area 30 displayed on the screen, and according to an input from the user, the computer system 100 may facilities can be selected.

In operation 420 , the computer system 100 may select at least one guide line that intersects the reference facility. For example, the user may select at least one guide line intersecting the reference facility in the target area 30 portion displayed on the screen (eg, through a user interface provided by a tool), Accordingly, the computer system 100 may select a guide line.

Each of the selected 'guidelines' may correspond to the aforementioned reference figure. In other words, each of the guide lines may be the aforementioned reference line corresponding to a line connecting the vertex of one facility and the other vertex of the corresponding facility or the vertex of another facility among the facilities.

The computer system 100 may determine a three-dimensional position (a three-dimensional position including an altitude or an altitude) of a guide line that is a reference figure.

In this case, in the aforementioned step 340 , the computer system 100 may identify a corresponding line corresponding to the guide line in the second aerial image 20 as a corresponding figure.

In step 510 , the computer system 100 matches the guide line of the first aerial image 10 and the corresponding line of the second aerial image 20 , thereby providing a three-dimensional position (including elevation or elevation) of the guide line. 3D position) can be determined. The method of determining the three-dimensional position (three-dimensional position including elevation or elevation) of the guide line may be applied to the method of determining the three-dimensional position (three-dimensional position including elevation or elevation) of the reference figure described above. Therefore, redundant descriptions will be omitted.

In step 520 , the computer system 100 determines a three-dimensional position (a three-dimensional position including an altitude or an altitude) of a point where the guide line and the reference facility intersect based on the determined three-dimensional position of the guide line. can For example, the computer system 100 may determine the altitude of the point where the guide line and the reference facility intersect with the same altitude value as the determined altitude of the guide line. Alternatively, when the altitudes at both endpoints of the guide line are different, the computer system 100 may determine the altitude of the point where the guide line and the reference facility intersect according to interpolaration.

By using the altitude determination method for the guide line in steps 510 and 520, facilities that do not include vertices (that is, it is difficult to match between the first aerial image 10 and the second aerial image 20) The elevation or three-dimensional position of the can also be accurately determined.

For example, the aforementioned reference facility may be a center line of a road within the target area 30 , and the guide line may be a line connecting vertices of each of two lanes positioned around the center line.

In relation to this, FIG. 10 shows a selection of guide lines 1020-1 to 1020-3 from the first aerial photograph 10, according to an example, and three-dimensional positions of the guide lines 1020-1 to 1020-3 ( A method of determining a three-dimensional position (a three-dimensional position including an altitude or an altitude) of a reference facility through determining an altitude or a three-dimensional position including the altitude) is shown.

The center line 1010 shown in FIG. 10 may correspond to the aforementioned reference facility, and the guide lines 1020-1 to 1020-3 may correspond to the aforementioned guide line. As illustrated, each of the guide lines 1020-1 to 1020-3 intersects the center line 1010 and may be selected by connecting vertices of the lanes centered on the center line 1010.

According to the steps 510 and 520 , altitudes for points where the guide lines 1020-1 to 1020-3 and the center line 1010 intersect may be determined. The computer system 100 may use the elevation values for these determined intersecting points to determine, according to interpolation, the three-dimensional positions (three-dimensional positions including elevation or elevation) of the remaining points of the centerline 1010 . have.

The user may select (ie, draw) the center line 1010 from the first aerial image 1000 displayed on the screen by using the above-described tool, and then the guide line 1020 intersecting the center line 1010 -1 to 1020-3) can be selected. Each of these guide lines 1020-1 to 1020-3 may be selected as a reference figure to determine a three-dimensional position.

Meanwhile, in the loaded second aerial image 20 , a corresponding line corresponding to each of the guide lines 1020-1 to 1020-3 and an object corresponding to the center line 1010 may be identified, and the computer system 100 By matching the corresponding line with the guide lines 1020-1 to 1020-3, each of the three-dimensional positions (the three-dimensional positions including the altitude or the altitude) of the guide lines 1020-1 to 1020-3 may be determined.

Meanwhile, an example of determining a three-dimensional position (a three-dimensional position including an altitude or an altitude) of a reference facility without using a guide line will be described below. When the reference facility is a facility including vertex(s), the three-dimensional position of the reference facility may be accurately determined without using a guide line.

That is, in the above-described step 320, the computer system 100 draws a line connecting the vertices of the reference facility among the facilities included in the target area 30 of the first aerial image 10 (in the reference figure described above). applicable) can be selected as a baseline. In the aforementioned step 340 , the computer system 100 may identify a corresponding line corresponding to the reference line in the second aerial image 20 as a corresponding figure. In step 350 described above, the computer system 100 may determine a three-dimensional position (a three-dimensional position including an altitude or an altitude) of the reference line by matching the reference line with the corresponding line. The three-dimensional position of the reference facility may be determined based on the determined three-dimensional position of the reference line.

In this way, according to the characteristics of the facility (eg, whether it includes vertices or not) to determine the three-dimensional position (elevation or the three-dimensional position including the altitude), with or without the guide line, the facility The three-dimensional position of may be determined.

As described above, the technical features described above with reference to FIGS. 1 to 3 can be applied to FIGS. 4, 5, and 10 as they are, and thus overlapping descriptions will be omitted.

6 is a flowchart illustrating a method of determining a three-dimensional position (a three-dimensional position including an altitude or an altitude) of a surrounding facility based on an altitude of a reference facility, according to an example.

Below, with reference to steps 352 and 354 of FIG. 3 and steps 610 and 620 of FIG. 6 to determine the three-dimensional position (three-dimensional position including the altitude or altitude) of the surrounding facilities. explain about

As in step 352 illustrated in FIG. 3 , computer system 100 (according to the methods described above with reference to FIGS. 4, 5 and 10 ) provides a three-dimensional position (altitude or 3 including elevation) of the reference facility. position of the dimension) can be determined.

As in step 354, the computer system 100 may determine a three-dimensional position (a three-dimensional position including an altitude or an altitude) of at least one surrounding facility around the reference facility based on the three-dimensional position of the reference facility. have.

As an example, the reference facility may be a center line of a road within the target area 30 , and the surrounding facilities may be each of lanes positioned around the center line. Alternatively, the surrounding facility may include a facility at least partially obscured from the aerial image as a facility around the reference facility.

When it is assumed that there is no (slope) gradient between the reference facility and the surrounding facility (eg, when a related option is selected in the aforementioned tool), the elevation of the surrounding facility may be determined to be equal to the elevation of the reference facility. For example, it may be assumed that the center line and the lanes on both sides have the same elevation. At this time, if the altitudes are the same, the three-dimensional position of the surrounding facilities can be determined only by specifying the location of the corresponding surrounding facilities in the first aerial image 10 , and the figure transferred to the second aerial image 20 . If the (figure corresponding to the surrounding facility) and the location of the corresponding surrounding facility displayed on the second aerial image 20 match, additional location confirmation is not required in the second aerial image 20 . If the position of the figure transferred to the second aerial image 20 and the corresponding surrounding facilities displayed on the second aerial image 20 do not match, the position of the figure transferred from the second aerial image 20 is set to the second aerial image ( 20) By adjusting the location of the above facility, it is possible to determine the height of the facility corresponding to the transferred figure.

Meanwhile, in step 610 , the computer system 100 may adjust the altitude value corresponding to the altitude of the reference facility (which will be the altitude value of the surrounding facility) according to a gradient existing between the reference facility and the surrounding facility. .

In operation 620 , the computer system 100 may determine a three-dimensional position (a three-dimensional position including an altitude or an altitude) of a surrounding facility based on the adjusted altitude value. The adjustment of the altitude value corresponding to the gradient may be performed according to a user input to a user interface provided through the aforementioned tool. In addition, the computer system 100 may automatically adjust the altitude value according to known topographic information for the target area 30 .

In relation to this, FIG. 11 is a flowchart illustrating a method of determining a three-dimensional position (a three-dimensional position including an altitude or an altitude) of a surrounding facility based on a three-dimensional position of a reference facility, according to an example.

In the illustrated example, the center line 1010 may correspond to the aforementioned reference facility, and the guide lines 1020-1 to 1020-3 may correspond to the aforementioned guide line. Meanwhile, the lane 1110 is a facility located around the center line 1010 and may correspond to the aforementioned surrounding facilities.

Computer system 100 may determine the elevation of lane 1110 as equal to elevation of centerline 1010, assuming that there is no gradient in the case of a road. Alternatively, the computer system 100 may determine the altitude of the lane 1110 by adjusting the altitude of the center line 1010 according to a gradient set according to the user or terrain information.

Accordingly, in the embodiment, the three-dimensional position of the surrounding facilities can be easily determined only by determining the three-dimensional position of the reference facility.

As described above, the technical features described above with reference to FIGS. 1 to 5 and 10 can be applied to FIGS. 6 and 11 as they are, and thus a redundant description will be omitted.

7 is a method for determining a three-dimensional position (a three-dimensional position including an altitude or an altitude) of a reference figure by matching a reference figure selected from the first aerial image and a corresponding figure identified from the second aerial image, according to an example; A flowchart showing the method.

Referring to FIG. 7 , using the above-described tool, the reference figure of the first aerial image 10 and the corresponding figure of the second aerial image 20 are matched to match the three-dimensional position (including elevation or elevation) of the reference figure. A method of determining a three-dimensional position) will be described.

Steps 710 to 740 to be described later may be included in the aforementioned step 350 .

In operation 710 , the computer system 100 may project the first aerial image 10 including the reference figure or the reference figure onto the second aerial image 20 . For example, the computer system 100 may project the layer of the first aerial image 10 or the layer of the reference figure to the second aerial image 20 . The layer of the reference figure may be generated when the reference figure of the first aerial image 10 is selected.

In operation 720 , the computer system 100 may move the reference figure so that the transferred reference figure and the corresponding figure identified in the second aerial image 20 match. The moved reference figure may be a layer corresponding to the reference figure. For example, the user may move the layer of the reference figure transferred to the second aerial image 20 (eg, through a user interface provided by a tool), and according to an input from the user, the computer system 100 ) may move the reference figure on the second aerial image 20 .

In operation 740 , when the corresponding figure on the second aerial image 20 and the moving reference figure match, the computer system 100 may determine the elevation value of the corresponding reference figure as the altitude of the reference figure. For example, in step 730 , the computer system 100 may move the reference figure (according to step 720 ) and output an elevation value corresponding to the moved position, and the corresponding figure and the reference figure may match. The altitude value output at the time may be determined as the altitude of the reference figure. The output altitude value may be a height value with respect to the reference altitude. The horizontal coordinates of the reference figure may also be determined in a similar manner. Accordingly, the three-dimensional position of the reference figure including the elevation and horizontal coordinates may be determined.

In relation to this, FIG. 9 shows a three-dimensional position (altitude or height A method for determining a three-dimensional position (including elevation) is shown.

As illustrated, in the first aerial image 900 , a reference line corresponding to a lane may be identified as a reference figure 905 . The reference figure 905 (a layer of the reference figure 905) may be transferred to the second aerial image 910 . The user may move the layer of the transferred reference figure 905 between positions 920 - 1 to 4 (positions corresponding to the corresponding figure 915 ) through the user interface provided by the above-described tool.

The computer system 100 may determine a three-dimensional position (a three-dimensional position including an altitude or an altitude) at each of the positions 920 - 1 to 4 and 915 of the transferred reference figure 905 . In other words, the computer system 100 assumes that each position of the positions 920 - 1 to 4 and 915 is a position where the transferred reference figure 905 and the corresponding figure coincide, and the reference figure 905 at each position It is possible to determine the three-dimensional position of (elevation or three-dimensional position including elevation). Since the above-described method may be applied as it is to a method of determining a three-dimensional position (a three-dimensional position including an altitude or an altitude) of the reference figure 905 , a redundant description will be omitted.

Accordingly, as shown, the computer system 100 outputs the elevation value of the reference figure 905 at each position as the transferred reference figure 905 moves to the positions 920 - 1 to 4 and 915 . can do. That is, as the position of the reference figure 905 is moved along the epipolar of the corresponding figure in the second aerial image 910, the computer system 100 changes the height of the reference figure 905 accordingly. can be printed out.

The user moves the transferred reference figure 905 between positions 920 - 1 to 4 and 915 , and the elevation value (ie, height 22.7 m) at the position 915 exactly matching the corresponding figure is determined by the reference figure. It can be seen that it corresponds to 905 (that is, the user can easily identify whether the reference figure 905 and the corresponding figure match (match) when the height is set to a certain level). Accordingly, the computer system 100 may determine the elevation value at the location 915 as the elevation value of the reference figure 905 .

As described above, by being able to determine the elevation value of the figure 905 using the user interface of the tool, the position 915 at which the reference figure 905 and the corresponding figure match can be intuitively identified, thus, Determination of a three-dimensional position including the elevation of the reference figure 905 may also be conveniently performed.

As described above with reference to FIGS. 1 to 6 , 10 and 11 , the technical features described above may be applied to FIGS. 7 and 9 as they are, and thus a redundant description will be omitted.

8 illustrates a method of generating a DSM and a DEM of a target area according to a determined altitude and further generating a vertical orthogonal image of the target area according to an example.

As described above, through the embodiment, the HD map 50 for the target region 30 based on the (registered) aerial images can be directly generated without performing the process of separately generating the DSM or DEM. have.

In step 810 , the computer system 100 uses the determined elevation with respect to the target area 30 , a Digital Surface Model (DSM) and a Digital Elevation model for the target area 30 . Model; DEM) can be created. In other words, the computer system 100 does not determine the three-dimensional position (a three-dimensional position including elevation or elevation) of the target region 30 based on the DSM or DEM, but rather the three-dimensional position of the target region 30 . can be determined first and the DSM and/or DEM can be generated according to the determined altitude.

Also, in operation 820 , the computer system 100 may generate a true ortho image of the target region 30 based on the generated DSM and DEM. Accordingly, the computer system 100 may construct a 3D map based on the vertical orthographic image of the target area 30 based on the aerial images.

In order to generate the DSM, DEM, and vertical orthographic images of the target region 30 , information included in the above-described aerial images may need to be further used.

At least one of the DSM, DEM, and vertical orthographic images of the target area 30 may be generated by the computer system 100 according to a user's selection after elevations of the target area 30 are determined.

As described above with reference to FIGS. 1 to 7 and FIGS. 9 to 11 , the technical features described above can be applied to FIG. 8 as it is, and thus overlapping descriptions will be omitted.

The device described above may be implemented as a hardware component, a software component, and/or a combination of the hardware component and the software component. For example, the devices and components described in the embodiments may include a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), and a programmable logic unit (PLU). It may be implemented using one or more general purpose or special purpose computers, such as a logic unit, microprocessor, or any other device capable of executing and responding to instructions. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. The processing device may also access, store, manipulate, process, and generate data in response to execution of the software. For convenience of understanding, although one processing device is sometimes described as being used, one of ordinary skill in the art will recognize that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that may include For example, the processing device may include a plurality of processors or one processor and one controller. Other processing configurations are also possible, such as parallel processors.

The software may comprise a computer program, code, instructions, or a combination of one or more thereof, which configures a processing device to operate as desired or is independently or collectively processed You can command the device. The software and/or data may be embodied in any type of machine, component, physical device, computer storage medium or device for interpretation by or providing instructions or data to the processing device. have. The software may be distributed over networked computer systems and stored or executed in a distributed manner. Software and data may be stored in one or more computer-readable recording media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded in a computer-readable medium. In this case, the medium may be to continuously store the program executable by the computer, or to temporarily store the program for execution or download. In addition, the medium may be various recording means or storage means in the form of a single or several hardware combined, it is not limited to a medium directly connected to any computer system, and may exist distributed on a network. Examples of the medium include a hard disk, a magnetic medium such as a floppy disk and a magnetic tape, an optical recording medium such as CD-ROM and DVD, a magneto-optical medium such as a floppy disk, and those configured to store program instructions, including ROM, RAM, flash memory, and the like. In addition, examples of other media may include recording media or storage media managed by an app store that distributes applications, sites that supply or distribute other various software, and servers.

As described above, although the embodiments have been described with reference to the limited embodiments and drawings, various modifications and variations are possible by those skilled in the art from the above description. For example, the described techniques are performed in a different order than the described method, and/or the described components of the system, structure, apparatus, circuit, etc. are combined or combined in a different form than the described method, or other components Or substituted or substituted by equivalents may achieve an appropriate result.

Therefore, other implementations, other embodiments, and equivalents to the claims are also within the scope of the following claims.

Claims (18)

A method of generating an HD (High Definition) map based on an aerial image, performed by a computer system, the method comprising:
selecting a reference figure from a first aerial image obtained by photographing the target area at a first viewpoint looking at the target area;
identifying a corresponding figure corresponding to the reference figure in a second aerial image obtained by photographing the target area at a second viewpoint different from the first aerial image;
determining a three-dimensional position of the reference figure by matching the reference figure with the corresponding figure; and
generating an HD map for the target area using the determined three-dimensional position
A method of generating an HD map, comprising: According to claim 1,
The determining step is
The three-dimensional position and the photographing direction of the camera photographing the first aerial image corresponding to the first viewpoint, the three-dimensional position and photographing direction of the camera photographing the second aerial image corresponding to the second viewpoint, the second viewpoint An HD map that determines a three-dimensional position including the elevation of the reference figure according to triangulation based on a first angle with respect to the reference figure from a first point of view, and a second angle with respect to the corresponding figure from the second point of view. How to create. According to claim 1,
The reference figure includes a vertex of any one of the facilities included in the target area of the first aerial image, or
and a reference line that is a line connecting the vertex and another vertex of the one facility or a vertex of another facility among the facilities. 4. The method of claim 3,
The selecting step is
selecting a reference facility from among facilities included in the target area of the first aerial image; and
selecting the reference line as at least one guide line intersecting the reference facility;
including,
In the identifying, a corresponding line corresponding to the guide line in the second aerial image is identified as the corresponding figure,
The determining step is
determining a three-dimensional position of the guide line by matching the guide line with the corresponding line; and
Determining a three-dimensional position of a point where the guide line and the reference facility intersect based on the three-dimensional position of the guide line
A method of generating an HD map, comprising: 5. The method of claim 4,
The method of generating an HD map, wherein the reference facility is a centerline of a road in the target area, and the guide line is a line connecting vertices of each of the two lanes located around the centerline. 4. The method of claim 3,
In the selecting, a line connecting vertices of a reference facility among facilities included in the target area of the first aerial image is selected as the reference line,
In the identifying, a corresponding line corresponding to the reference line in the second aerial image is identified as the corresponding figure,
The determining includes determining a three-dimensional position of the reference line by matching the reference line with the corresponding line. 7. The method of claim 4 or 6,
determining a three-dimensional position of the reference facility; and
Determining a three-dimensional location of at least one surrounding facility around the reference facility based on the three-dimensional location of the reference facility
A method for generating an HD map, further comprising: 8. The method of claim 7,
The step of determining the three-dimensional location of the surrounding facilities,
adjusting an altitude value corresponding to a three-dimensional position of the reference facility according to a gradient existing between the reference facility and the surrounding facilities; and
Determining a three-dimensional position of the surrounding facilities based on the adjusted altitude value
A method of generating an HD map, comprising: 8. The method of claim 7,
The method of generating an HD map, wherein the reference facility is a centerline of a road within the target area, and the surrounding facility is each of the lanes positioned around the centerline. According to claim 1,
Determining a three-dimensional position of a facility in the target area including the reference figure based on the determined three-dimensional position
further comprising,
The three-dimensional position of the facility is determined by calculating the three-dimensional positions of points constituting the facility according to interpolaration based on the determined three-dimensional position of the reference figure. According to claim 1,
The determining step is
transferring the first aerial image including the selected reference figure or the selected reference figure to the second aerial image;
moving the reference figure so that the transferred reference figure and the identified corresponding figure in the second aerial image match; and
Determining an elevation value of the reference figure corresponding to when the identified corresponding figure matches the reference figure as a three-dimensional position of the reference figure
A method of generating an HD map, comprising: 12. The method of claim 11,
The determining step is
Outputting an altitude value corresponding to the moved position as the reference figure is moved
including,
The method of generating an HD map, wherein an elevation value output when the identified corresponding figure matches the reference figure is determined as a three-dimensional position of the reference figure. 12. The method of claim 11,
The method of generating an HD map, wherein the moved reference figure is a layer corresponding to the reference figure. According to claim 1,
generating at least one of a digital surface model (DSM) and a digital elevation model (DEM) for the target area using the determined three-dimensional position
A method for generating an HD map, further comprising: 15. The method of claim 14,
generating a true ortho image of the target region based on the generated DSM and DEM;
A method for generating an HD map, further comprising: A computer program stored in a non-transitory computer readable recording medium for executing the method of any one of claims 1 to 15 in the computer system. 16. A non-transitory computer-readable recording medium in which a program for executing the method of any one of claims 1 to 15 in the computer system is recorded. In a computer system,
at least one processor configured to execute computer readable instructions contained in memory
including,
the at least one processor,
A second aerial view in which a reference figure is selected from a first aerial image obtained by photographing the target area at a first viewpoint looking at the target area, and the target area is photographed from a second viewpoint different from the first aerial image A corresponding figure corresponding to the reference figure is identified in an image, the three-dimensional position of the reference figure is determined by matching the reference figure and the corresponding figure with each other, and the HD for the target area is performed using the determined three-dimensional position. A computer system that generates a map.

Images