KR102520189B1 - Method and system for generating high-definition map based on aerial images captured from unmanned air vehicle or aircraft - Google Patents

Abstract

A reference shape is selected from a first aerial image capturing the target area from a first viewpoint looking at the target area, and a reference shape is obtained from a second aerial image capturing the target area from a second viewpoint different from the first aerial image. A corresponding corresponding figure is identified, and the 3D position (elevation or 3D position including the altitude) of the reference figure is determined by matching the reference figure and the corresponding figure, and the determined 3D position is used for the target area. A method for generating an HD map is provided.

Description

Method and system for generating HD maps based on aerial images taken by unmanned aerial vehicles or aircrafts

Embodiments relate to a method for generating a high definition (HD) map based on aerial images, wherein the 3D position (e.g., altitude) of a point within a corresponding region is based on aerial images taken of the same target region from different viewpoints. or a 3D location including altitude) to a method for generating an HD map of a target area.

An HD (High Definition) map is a high-precision map used in fields such as autonomous driving, and is a map with higher accuracy than conventional maps. For example, the HD map may include information on the surrounding environment of the target area, such as roads, topography height, and curvature, implemented in 3D, and may have an accuracy of 10 times or more than conventional maps. The HD map may have an error of less than 10 cm, for example.

The HD map may be generated based on data collected from a Mobile Mapping System (MMS) vehicle traveling on the road or data measured on the ground. However, according to this, HD maps are accompanied by errors due to location errors or sea level errors of the GPS installed in the MMS, and since large-scale survey data are required, the accompanying costs are also excessive.

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

Korean Patent Publication No. 10-2020-0094644 (published on August 7, 2020) is a 3D space using depth prediction information for each object and class information for each object obtained through V2X information convergence technology. A learning method and a learning device for updating an HD map by reconstruction are disclosed.

The information described above is for illustrative purposes only and may include material that does not form part of the prior art.

According to an embodiment, 3D positions (elevation or 3D positions including elevations) 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 of generating an HD map of a target area based on a 3D location may be provided.

In one embodiment, a reference figure selected from a first aerial image capturing the target area from a first viewpoint looking at the target area and a second aerial image capturing the target area from a second viewpoint different from the first aerial image By matching the corresponding figure identified in the image, a tool for determining the 3D position (elevation or 3D position including altitude) of the reference figure can be provided.

In one aspect, in the method for generating a high definition (HD) map based on an aerial image, performed by a computer system, a first image of a target region is obtained from a first viewpoint looking at the target region. Selecting a reference figure from an aerial image; Identifying a corresponding figure corresponding to the reference figure in a second aerial image obtained by capturing the target area at a second viewpoint different from the first aerial image; A method for generating an HD map is provided, comprising determining the 3D position of the reference figure by matching the corresponding figures with each other and generating an HD map for the target region using the determined 3D position. do.

The determining may include the 3D position and direction of the camera capturing the first aerial image corresponding to the first viewpoint, and the 3D position of the camera capturing the second aerial image corresponding to the second viewpoint. and a three-dimensional position including the altitude 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 one of the facilities included in the target area of the first aerial image, or connects the vertex and another vertex of the one facility or a vertex of another facility among the facilities. It can contain a single line, the baseline.

The selecting includes selecting a reference facility 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; The identifying step may include identifying a corresponding line corresponding to the guide line in the second aerial image as the corresponding figure;

The determining step may include determining the 3D position of the guide line by matching the guide line with the corresponding line, and determining whether the guide line and the reference facility intersect based on the 3D position of the guide line. It may include determining the 3-dimensional position of the point.

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

In the selecting step, a line connecting vertices of reference facilities among facilities included in the target area of the first aerial image is selected as the reference line, and in the identifying step, the reference line in the second aerial image is selected. In the step of identifying and determining a corresponding line corresponding to as the corresponding figure, the 3D 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 determining a 3D location of the reference facility and determining a 3D location of at least one neighboring facility around the reference facility based on the 3D location of the reference facility. can include more.

The step of determining the 3D position of the surrounding facility may include adjusting an altitude value corresponding to the 3D position of the reference facility according to a gradient existing between the reference facility and the surrounding facility, and the adjusted altitude. The method may include determining a 3D location of the surrounding facility based on the value.

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

The method for generating the HD map further includes determining a 3D location of a facility in the target area including the reference figure based on the determined 3D location, wherein the 3D location of the facility is determined by the determined 3D location. It may be determined by calculating the 3D positions of points constituting the facility according to interpolation based on the 3D position of the reference figure.

The determining may include projecting the first aerial image including the selected reference figure or the selected reference figure onto the second aerial image; Moving the reference figure so that the identified corresponding figure matches, and determining an altitude value of the reference figure corresponding to the matching of the identified corresponding figure and the reference figure as a 3D position of the reference figure. can do.

The determining may include outputting an altitude value corresponding to a position moved as the reference figure is moved, and the altitude value output when the identified corresponding figure matches the reference figure is the reference figure. It can be determined by the 3D position of the figure.

The reference figure to be moved 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 3D location. Further steps may be included.

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 included in a memory, wherein the at least one processor is configured to, when viewing the target region, the target region at a first point of view. A reference figure is selected from a first aerial image taken, and a corresponding figure corresponding to the reference figure is identified in a second aerial image taken of the target area at a second viewpoint different from the first aerial image. and determining the 3D position of the reference figure by matching the reference figure and the corresponding figure with each other, and generating an HD map of the target region using the determined 3D position.

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

By utilizing aerial images of a target area taken from different viewpoints, it is possible to accurately determine a 3D position including an altitude of a facility that is obscured by a specific aerial image.

1 is a diagram of determining a 3D location (elevation or a 3D location including elevation) of facilities included in a target area based on aerial images taken of the same target area from different viewpoints, according to an embodiment. and how to create an HD map.
2 is a block diagram illustrating the structure of a computer system generating an HD map based on aerial images, according to an exemplary embodiment.
3 is a diagram of determining a 3D position (elevation or a 3D position including elevation) of facilities included in a target area based on aerial images of the same target area taken at different viewpoints, according to an embodiment. and a flow chart showing a method for generating an HD map.
4 and 5 show a 3D view of a reference facility by selecting a guideline from a first aerial photograph and determining a 3D position (elevation or a 3D position including altitude) of the guideline according to an example. It is a flow chart showing how to determine a position (altitude or a 3-dimensional position including altitude).
6 is a flowchart illustrating a method of determining a 3D position (an altitude or a 3D position including an altitude) of a nearby facility based on an altitude of a reference facility, according to an example.
7 is a method for determining a 3D position (elevation or a 3D position including altitude) of a reference figure by matching a reference figure selected from a first aerial image with a corresponding figure identified from a second aerial image according to an example. Here is a flow chart showing the method.
8 illustrates a method of generating a DSM and a DEM of a target region according to a determined altitude, and further generating a vertical ortho image of the target region, according to an example.
9 is a method for determining a 3D position (elevation or a 3D position including altitude) of a reference figure by matching a reference figure selected from a first aerial image with a corresponding figure identified from a second aerial image according to an example. indicate the way
10 illustrates a 3D location (elevation) of a reference facility by selecting a guideline from a first aerial photograph and determining a 3D location (3D location including elevation or elevation) of the guideline according to an example. or a three-dimensional position including altitude).
11 is a flowchart illustrating a method of determining a 3D location (an elevation or a 3D location including an elevation) of a nearby facility based on an elevation 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.

"Elevation" and "determination of altitude" described in the drawings and detailed descriptions to be described later may be replaced with "3-dimensional position" and "determination of 3-dimensional position".

1 is a diagram of determining a 3D location (elevation or a 3D location including elevation) of facilities included in a target area based on aerial images taken of the same target area from different viewpoints, according to an embodiment. and how to create an HD map.

Referring to FIG. 1 , a method of creating a high definition (HD) map 50 for a target area 30 corresponding to at least a part of a target area will be described. The HD map 50 is a high-precision map, and may have higher accuracy than existing maps. For example, in the HD map 50 , surrounding environment information of the target region 30 , such as roads, topography height, and curvature, may be 3-dimensionally implemented. That is, information on facilities included in the target area 30 may be 3-dimensionally implemented on the HD map 50 . The facility included in the target area 30 may include, for example, a road, a center line included (drawn) on the road, and a lane included (drawn) on the road. 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 constructing 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 in which the target area 30 is captured, and the facilities within the target area 30 3D locations (elevation or 3D locations including elevations) of the facilities may be determined, and an HD map 50 for the target area 30 may be generated based on the determined 3D locations of facilities.

The "altitude" of a facility (or point) can be its elevation or elevation. Alternatively, "altitude" may represent the absolute height of a corresponding facility (or a specific point). Alternatively, “altitude” may indicate depth information of a corresponding facility (or a specific point) with respect to a predetermined criterion. At this time, the reference may be the sea level or the ground.

The 3D location of a specific point described in the present disclosure may mean the altitude of the specific point or a 3D location including the altitude of the specific point (eg, 3D coordinates including altitude and horizontal coordinates). .

The computer system 100 generates a first aerial image 10 capturing the target area 30 and a second aerial image 20 capturing the target area 30 from a different viewpoint from the first aerial image 10. A 3D position or altitude associated with the target area 30 (ie, a 3D position or altitude of a facility (or a specific point) included in the target area 30) can be determined using the . The first aerial image 10 and the second aerial image 20 may be matched images. That is, the first aerial image 10 and the second aerial image 20 may be images whose attitude is determined. In the present disclosure, “video” may include a picture or image.

The first aerial image 10 and the second aerial image 20 are images captured by an unmanned air vehicle such as a drone or an aircraft (for land-surface capture) flying over a target area including the target area 30, or the captured image It may be a matched 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, and calculates the exact 3-dimensional position of the corresponding point. can be specified. As an example, the computer system 100 may specify the exact three-dimensional location of a point using triangulation.

The 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 manner to a point in the target area 30. It is possible to determine a 3-dimensional position (altitude or a 3-dimensional position including altitude) for

For a more specific method for the computer system 100 to determine the 3D location (elevation or 3D location including the elevation) of a point in the target area 30, refer to FIGS. 2 to 11 to be described later. explained in more detail.

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

The computer system 100 performing the method of determining the 3D location of the target area 30 and generating the HD map 50 according to the situation according to the embodiments to be described later is a 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 for an area 30 and generating an HD map 50 . These programs may be loaded into the computer system 100 .

The computer system 100 may be a client terminal used by a user to process a job for generating the HD map 50 . The computer system 100 may be an electronic device capable of installing and executing a program that performs a method of determining a 3D position and generating an HD map 50. For example, the computer system 100 may be a personal computer (PC), a laptop computer, a laptop computer, a smart phone, a tablet, an Internet Of Things device, or a 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-perishable 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 separate 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 recording medium readable by a separate computer 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, software components may be loaded into the memory 110 through the communication interface 130 rather than a computer-readable recording medium. For example, software components may be loaded into memory 110 of computer system 100 based on a computer program installed by files received over network 160 .

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

Communication interface 130 may provide functionality for computer system 100 to communicate with other devices via network 160 . For example, a request, command, data, file, etc. generated according to a program code stored in a recording device such as the memory 110 by the processor 120 of the computer system 100 is transferred to a network ( 160) to other devices. Conversely, signals, commands, data, files, etc. from other devices may be received into the computer system 100 via the communication interface 130 of the computer system 100 via the network 160 . Signals, commands, data, etc. received through the communication interface 130 may be transmitted to the processor 120 or memory 110, and files, etc. may be stored in the computer system 100. permanent storage).

The communication method through the communication interface 130 is not limited, and the network 160 may include a communication network (eg, mobile communication network, wired Internet, wireless Internet, broadcasting network) as well as a communication method utilizing 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). , one or more arbitrary networks such as the Internet. In addition, the network 160 may include any one or more of network topologies 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. Not limited.

The input/output interface 140 may be a means for interface with the input/output device 150 . For example, the input device may include devices such as a microphone, keyboard, camera, or mouse, and the output device may include devices such as a display and a speaker. As another example, the input/output interface 140 may be a means for 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 elements than those of FIG. 2 . However, most of the prior art elements need not be shown explicitly. For example, the computer system 100 may be implemented to include at least some of the aforementioned input/output devices 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 determines the 3D position (elevation or 3D position including altitude) of facilities included in the target area 30 based on the aerial images 10 and 20 to be described later. ), and to perform 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 job for generating the HD map 50 . That is, based on the aerial images 10 and 20 to be described later, the 3D location (elevation or 3D location including elevation) of the facilities included in the target area 30 is determined, and the HD map 50 Steps for performing the method of generating ) may be performed by the computer system 100, which is a server communicating with the client terminal.

Alternatively, the 3D location (elevation or 3D location including elevation) of the 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 at least some of the steps for performing the method of generating the server are performed.

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 explained by the action of

In the above, since the technical features described above with reference to FIG. 1 can be applied to FIG. 2 as they are, duplicate descriptions will be omitted.

3 is a diagram of determining a 3D position (elevation or a 3D position including elevation) of facilities included in a target area based on aerial images of the same target area taken at different viewpoints, according to an embodiment. and a flow chart showing a method for generating an HD map.

In operation 310 , the computer system 100 may obtain a first aerial image 10 of the target area 30 . The first aerial image 10 may be an image captured by an unmanned air vehicle such as a drone or an aircraft (for land-based imaging) flying over a target area including the target area 30 , or an image in which the captured images are matched. For example, the first aerial image 10 may be an image in which a posture is determined as a matched image. For example, the first aerial image 10 may correspond to an image obtained by photographing the ground surface in a vertical direction. Alternatively, the first aerial image 10 may correspond to an image captured vertically or in an arbitrary direction (ie, from a viewpoint) in which an operator identifies a target area or is easy to work with.

The computer system 100 may obtain the first aerial image 10 by loading the previously stored first aerial image 10 . A drone or an unmanned aerial vehicle flying over a target may photograph the target with a predetermined degree of overlap, and the first aerial image 10 may be determined according to matching of images having this degree of overlap. The first aerial image 10 may be a photograph of the target region 30 from a first viewpoint viewing the target region 30 vertically (as much as possible) among images of the target region 30 captured. there is. In other words, the first aerial image 10 may be obtained by photographing the target region 30 most vertically among images of the target region 30 .

In step 320, the computer system 100 may select a reference shape from the first aerial image 10 in which the target area 30 is photographed from the first viewpoint looking at the target area 30. For example, the user may use a tool for determining the 3D position (e.g., the 3D position (elevation or 3D position including the altitude) of the reference figure) in the target area 30 of the first aerial image 10 displayed on the screen. ) may select a reference figure through a user interface provided by the user, 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 points, lines, and planes (closed curves or polygons) selected within the target area 30 . Within the target region 30, a reference figure may be a target for determining an altitude 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, and/or/in addition, 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 (drawn) on the road, and a lane included (drawn) on the road. 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 obtain a second aerial image 20 of the target area 30 . As for the second aerial image 20 and the acquisition of the second aerial image 20, similar descriptions to those described above for the first aerial image 10 can be applied as they are, and duplicate descriptions will be omitted. However, the second aerial image 20 may be obtained by capturing the target area 30 at a second viewpoint different from that of the first aerial image 10 . In other words, the first aerial image 10 and the second aerial image 20 may be images with different viewpoints. For example, while the first aerial image 10 captures the target area 30 vertically (or most vertically), the second aerial image 20 captures the target area 30 at an angle other than vertical. may have been filmed with

The computer system 100 may obtain 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 shape is selected from the first aerial image 10, the computer system 100 may automatically search for and load a suitable second aerial image 20. there is. For example, the computer system 100 compares the coordinate values included in the first aerial image 10 and the second aerial image 20, which are matched images (or the coordinate values of the selected reference figure and the second aerial image 20). Based on the comparison of coordinate values of ), the second aerial image 20 obtained by capturing the same target region 30 as the first aerial image 10 may be searched for and loaded.

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 may be displayed as the main on the screen. can At this time, 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 converts the first aerial image 10 from the second aerial image 20 obtained by capturing the target area 30 from a second viewpoint different from the first aerial image 10. A corresponding figure corresponding to the selected reference figure can 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 .

Corresponding figures may be automatically identified in 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 matched images, include Comparison of coordinate values Based on the comparison between the shape (shape or color, etc.) of the reference figure 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 of the second aerial image. For example, the user compares the first aerial image 10 and the second aerial image 20 displayed on the screen and recognizes a portion of the second aerial image 20 corresponding to the reference figure of the first aerial image 10. and select it as a corresponding figure, and the computer system 100 can identify the corresponding figure according to the input from the user.

The corresponding figure may include at least one of a line and a face (closed curve or polygon) according to the corresponding reference figure. The corresponding figure and the reference figure may be compared to determine a 3D location (altitude value).

The first viewpoint is based on the 3D position (eg, 3D coordinates (x, y, z)) of the camera that captured the first aerial image 10 and the shooting direction (photography angle (yaw, roll, pitch) of the camera). can include Similarly, the second viewpoint is based on the 3D position (eg, 3D coordinates (x, y, z)) of the camera that captured the second aerial image 20 and the shooting direction (photography angle of the camera (yaw, yaw, 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 to each other so that the 3D position of the reference figure (elevation or elevation) 3D position) can be determined.

Below, a method for determining the 3D position (altitude or 3D position including altitude) of the reference figure by matching the reference figure of the first aerial image 10 and the corresponding figure of the second aerial image 20 with each other. explain 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 a reference figure and a corresponding figure corresponding thereto, it is possible to specify an accurate 3-dimensional location of a corresponding region (ie, reference figure). For example, the computer system 100 may use triangulation to specify the exact three-dimensional location of a point. In addition, the computer system 100 calculates the altitude (height) of a specific point based on aerial photographs, or calculates the altitude of a point for plotting a contour line, in a manner similar to that in the target area 30. A 3D position (altitude or a 3D position including altitude) with respect to a reference figure may be determined.

For example, the computer system 100 determines (according to the image matching process) the 3D position and direction of a camera that has captured the first aerial image 10 corresponding to the first viewpoint, which is a known value, and the second viewpoint. The 3D position of a point in the target area common to the first aerial image 10 and the second aerial image 20 based on the 3D position and the shooting direction of the camera that captured the second aerial image 20 corresponding to can decide In determining the 3D position, focal distance information and principal point information of the camera may be further used as information of the camera.

When the 3D position (x, y, z) of the camera that captured the first aerial image 10 and the second aerial image 20 and its shooting direction (yaw, roll, pitch) are determined through the registration process, respectively , two line segments facing a point commonly included in each image can be determined, and the 3D position of the point can be determined by calculating the intersection of these line segments.

The capture altitude of the first aerial image 10 and the capture altitude of the second aerial image 20 may be the same. According to the above method, 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, the computer system 100 converts the reference figure and the corresponding figure to each other. By matching, the 3D position (altitude or 3D position including altitude) of the reference figure can be determined. "Matching" of the reference figure and the corresponding figure determines the comparison between the first aerial image 10 and the second aerial image 20 and/or the above-mentioned 3-dimensional position (altitude or 3-dimensional position including altitude) ( It may mean encompassing operations for calculation).

Alternatively, the computer system 100 may set the parallax between the first viewpoint of the first aerial image 10 and the second viewpoint of the second aerial image 20 (eg, the 3D position of the camera indicated by the first viewpoint and the second viewpoint). The 3D position of the reference figure (elevation or 3-dimensional position including altitude) can be determined. That is, the computer system 100 can match (match) the reference figure and the corresponding figure, and accurately specify the 3-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 matched images, and as described above, each image may include the 3D position of the camera from which the image was captured and the photographing direction (expression). can In other words, the first aerial image 10 and the second aerial image 20 are information about viewpoints at which the images were captured, respectively, and 3D coordinate information and rotation information of the camera at the point where the images were captured ( camera yaw, roll, pitch, etc.).

Specifically, the computer system 100 captures the 3D position and shooting direction of the camera that captures the first aerial image 10 corresponding to the first viewpoint, and captures the second aerial image 20 corresponding to the second viewpoint. The 3D position and photographing direction of the camera, the first angle with respect to the reference figure from the first viewpoint (ie, the 3D position of the camera that captured the first aerial image 10), and the second viewpoint (ie, the second aerial image 10) The 3D position including the altitude of the reference figure may be determined according to the triangulation method based on the second angle with respect to the corresponding figure from the 3D position of the camera capturing the image 20 .

According to the above method, 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, the computer system 100 converts the reference figure and the corresponding figure to each other. By matching (matching), the 3D position (altitude or 3D position including altitude) of the reference figure can be determined according to the triangulation method.

The computer system 100 may determine the 3D location of the facility in the target area 30 including the reference figure based on the 3D location (elevation or 3D location including the elevation) determined in step 350. there is. The 3D location of the facility is calculated by calculating the 3D location of points constituting the facility (for example, points between vertices and points between corners) according to interpolation based on the 3D location of the determined reference figure. can be determined by

Meanwhile, when a preset reference altitude is used, the computer system 100 may determine the 3D 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) of a point in the first aerial image 10 or the second aerial image 20 . Alternatively, the reference altitude may be a reference altitude value set in a program (e.g., the tool described above) used to determine the 3D position (elevation or 3D position including the altitude) of the reference figure and generate the HD map. . The reference altitude is a surrounding 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 the 3D position and shooting direction of a camera that captures the first aerial image 10 corresponding to the first viewpoint, a first angle with respect to a reference figure from the first viewpoint, and a preset reference. Based on the altitude, the altitude of the reference figure can be determined. Also, the computer system 100 may determine the 3D position of the reference figure by determining horizontal coordinates of the reference figure based on the determined altitude.

The 3D position of the reference figure determined (by triangulation or the like) described above may include not only the altitude of the reference figure but also the horizontal coordinates. In other words, in the embodiment, the 3D position of the reference figure is determined using an aerial image in which the 3D position and shooting direction of the camera that has taken the image are determined. can be determined

In step 360 , the computer system 100 may generate the HD map 50 of the target area 30 using the 3D position of the reference figure determined in step 350 . That is, the computer system 100 may specify the exact altitude (height) of the facilities included in the target area 30 by step 350, and use this as height information on the facilities on the HD map ( 50) can be created. For example, in the embodiment, the HD map 50 including facilities such as lanes determined by connecting the determined altitude values may be generated. In generating the HD map 50, information included in the aforementioned aerial images may be further used.

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

According to the embodiment, since the heights of facilities such as center lines or lanes within the target area 30 can be accurately specified, the HD map 50 accurately reflecting the height information of these facilities 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 facilities that are not visible (by street trees, vehicles, shadows, etc.) It can be accurately characterized using other aerial images.

Since the technical features described above with reference to FIGS. 1 and 2 may be applied to FIG. 3 as they are, duplicate descriptions will be omitted.

4 and 5 show a 3D view of a reference facility by selecting a guideline from a first aerial photograph and determining a 3D position (elevation or a 3D position including altitude) of the guideline according to an example. It is a flow chart showing how to determine a position (altitude or a 3-dimensional position including altitude).

Referring to FIGS. 4 and 5 , a method of determining a 3D location (elevation or 3D location including elevation) of a facility corresponding to a standard facility within the target area 30 will be described in more detail.

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

At step 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 guideline intersecting the reference facility (eg, through a user interface provided by a tool) in the target area 30 displayed on the screen, and in response to an input from the user Accordingly, the computer system 100 may select a guideline.

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 a vertex of one facility and another vertex of the corresponding facility or a vertex of another facility among the facilities.

The computer system 100 may determine the 3D location (elevation or 3D location including the elevation) of the guide line, which is a reference figure.

At this time, in step 340 described above, 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 with the corresponding line of the second aerial image 20, thereby matching the guide line's 3D position (elevation or height). 3D position) can be determined. The method for determining the 3-dimensional position (elevation or 3-dimensional position including altitude) of the guideline is applied as it is to the method for determining the 3-dimensional position (elevation or 3-dimensional position including altitude) of the reference figure described above. Therefore, redundant descriptions are omitted.

In step 520, the computer system 100 determines a 3D location (elevation or a 3D location including elevation) of a point where the guideline and the reference facility intersect based on the determined 3D location of the guideline. can For example, the computer system 100 may determine the altitude of a point where the guide line and the reference facility intersect with the same altitude value as the determined altitude of the guide line. Alternatively, the computer system 100 may determine the altitude of a point where the guideline and the reference facility intersect according to interpolation when the altitudes at both end points of the guideline are different.

As the altitude determination method for the guideline is used in steps 510 and 520, facilities that do not include vertices (ie, matching between the first aerial image 10 and the second aerial image 20 are difficult) The altitude or three-dimensional position of the object can also be accurately determined.

As an 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 two lanes located around the center line.

In this regard, FIG. 10 shows, according to an example, selecting guide lines 1020-1 to 1020-3 from the first aerial photograph 10, and 3D positions of the guide lines 1020-1 to 1020-3 ( A method of determining the 3D location (altitude or 3D location including the elevation) of a reference facility by determining the elevation or the 3D location including the elevation) is shown.

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

According to 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. Computer system 100 may use the elevation values for these determined intersecting points to interpolate to determine the three-dimensional location (elevation or three-dimensional location including elevation) of the remaining points of centerline 1010. there is.

The user may select (i.e., draw) the center line 1010 from the first aerial image 1000 displayed on the screen using the tool described above, and then 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 3D position.

Meanwhile, in the loaded second aerial image 20, corresponding lines corresponding to each of the guidelines 1020-1 to 1020-3 and objects 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 3-dimensional position (elevation or 3-dimensional position including the altitude) of the guide lines 1020-1 to 1020-3 can be determined.

Meanwhile, an example of determining the 3D location (elevation or 3D location including elevation) of a reference facility without using a guideline will be described below. When the reference facility is a facility including vertex(s), the 3D position of the reference facility can be accurately determined without using a guideline.

That is, in the above-described step 320, the computer system 100 draws a line connecting vertices of reference facilities among facilities included in the target area 30 of the first aerial image 10 (to the aforementioned reference figure). corresponding) can be selected as the baseline. In step 340 described above, 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 the above-described step 350, the computer system 100 may determine the 3D position (elevation or a 3D position including the altitude) of the reference line by matching the reference line with the corresponding line. A 3D location of the reference facility may be determined based on the determined 3D location of the reference line.

Thus, depending on the characteristics of the facility (e.g., whether or not it includes vertices) to determine the three-dimensional location (elevation or three-dimensional location including elevation), using or without guidelines, the facility The 3D position of can be determined.

Since the technical features described above with reference to FIGS. 1 to 3 may be applied to FIGS. 4, 5, and 10 as they are, duplicate descriptions will be omitted.

6 is a flowchart illustrating a method of determining a 3D position (an altitude or a 3D position including an altitude) of a nearby 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, a method for determining the 3D location (elevation or 3D location including elevation) of a nearby facility is described. explain about

As in step 352 shown in FIG. 3, computer system 100 determines (according to methods described above with reference to FIGS. dimension) can be determined.

As in step 354, the computer system 100 may determine a 3D location (elevation or a 3D location including elevation) of at least one neighboring facility around the reference facility based on the 3D location of the reference facility. there is.

For example, the reference facility may be a center line of a road within the target area 30, and the surrounding facility may be each of lanes located around the center line. Alternatively, the surrounding facilities may include facilities around the reference facility and at least partially hidden from the aerial image.

If 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 above-described tool), the altitude of the surrounding facility may be determined to be the same as that of the reference facility. For example, it may be assumed that the center line and lanes on both sides have the same altitude. At this time, if the altitudes are the same, the 3D position of the surrounding facility can be determined simply by specifying the location of the surrounding facility in the first aerial image 10, and the figure transferred to the second aerial image 20 If (a figure corresponding to a nearby facility) and the location of the nearby facility displayed on the second aerial image 20 coincide, additional positioning in the second aerial image 20 is not required. If the location of the figure transferred to the second aerial image 20 and the corresponding nearby facility displayed on the second aerial image 20 do not match, the position of the figure transferred from the second aerial image 20 is changed to the second aerial image ( 20) By adjusting the location of the facility above, the altitude of the facility corresponding to the transferred figure can be determined.

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

In step 620, the computer system 100 may determine a 3D location (elevation or a 3D location including the elevation) of a nearby facility based on the adjusted altitude value. Adjustment of the altitude value corresponding to the gradient may be performed according to a user's input to the user interface provided through the above-described tool. Also, the computer system 100 may automatically adjust the altitude value according to known topographical information of the target area 30 .

In this regard, FIG. 11 is a flowchart illustrating a method of determining a 3D location (elevation or a 3D location including elevation) of a nearby facility based on a 3D location 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 lines. Meanwhile, the lane 1110 is a facility located around the center line 1010 and may correspond to the aforementioned surrounding facilities.

The computer system 100 may determine the altitude of the lane 1110 as being equal to the altitude of the center line 1010 assuming that there is no gradient in the case of the 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 a user or terrain information.

Accordingly, in the embodiment, the 3D location of the surrounding facility can be easily determined only by determining the 3D location of the reference facility.

Since the technical features described above with reference to FIGS. 1 to 5 and 10 may be applied to FIGS. 6 and 11 as they are, duplicate descriptions are omitted.

7 is a method for determining a 3D position (elevation or a 3D position including altitude) of a reference figure by matching a reference figure selected from a first aerial image with a corresponding figure identified from a second aerial image according to an example. Here is a flow chart showing the method.

Referring to FIG. 7 , by matching the reference figure of the first aerial image 10 and the corresponding figure of the second aerial image 20 using the above-described tool, the 3D position of the reference figure (elevation or elevation) A method for determining a 3D position) will be described.

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

In step 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 a layer of the first aerial image 10 or a layer of a reference figure onto the second aerial image 20 . The layer of the reference figure may be created when the reference figure of the first aerial image 10 is selected.

In step 720, the computer system 100 may move the reference figure so that the transferred reference figure matches the corresponding figure identified in the second aerial image 20. The reference figure to be moved 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 the computer system 100 may move according to an input from the user. ) may move the reference figure on the second aerial image 20.

In operation 740, the computer system 100 may determine an altitude value of the corresponding reference figure as the altitude of the reference figure when the corresponding figure on the second aerial image 20 matches the moving reference figure. For example, in step 730, the computer system 100 may move the reference figure (according to step 720), output an altitude value corresponding to the moved position, and when the corresponding figure and the reference figure match. The altitude value displayed at the time can 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 3D position of the reference figure including the elevation and horizontal coordinates may be determined.

In this regard, FIG. 9 is a 3D position (elevation or 3D position including altitude) is determined.

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

The computer system 100 may determine a 3D position (elevation or a 3D position including altitude) at each of positions 920 - 1 to 4 and 915 of the reference figure 905 that has been transferred. 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 is generated at each position. It is possible to determine the 3-dimensional position (altitude or 3-dimensional position including altitude) of . Since the above-described method can be applied as it is to the method of determining the 3D location (elevation or 3D location including the elevation) of the reference figure 905, duplicate descriptions will be omitted.

Accordingly, as shown, the computer system 100 outputs an altitude value of the reference figure 905 at each position as the transferred reference figure 905 moves through the positions 920-1 to 4 and 915. can do. That is, as the position of the reference figure 905 moves 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.

While the user moves the transferred reference figure 905 between positions 920-1 to 4 and 915, the altitude value (ie, height 22.7m) at the position 915 that exactly matches the corresponding figure is 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) at what height). Accordingly, the computer system 100 may determine the altitude value at the location 915 as the altitude value of the reference figure 905 .

As described above, by determining the altitude value of the figure 905 using the user interface of the tool, the location 915 where the reference figure 905 and the corresponding figure match can be intuitively grasped, and thus, Determination of the 3D position including the altitude of the reference figure 905 can also be conveniently performed.

Since the technical features described above with reference to FIGS. 1 to 6, 10 and 11 may be applied to FIGS. 7 and 9 as they are, duplicate descriptions will be omitted.

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

As described above, according to the embodiment, the HD map 50 for the target area 30 based on (matched) aerial images can be directly generated without performing a process of generating a DSM or DEM separately. there is.

At step 810, computer system 100 uses the determined elevation relative to target area 30 to generate a digital surface model (DSM) and digital elevation model (Digital Elevation) for target area 30. At least one of Model; DEM) can be created. In other words, the computer system 100 does not determine the 3-dimensional position (elevation or 3-dimensional position including elevation) of the target area 30 based on the DSM or DEM, but the 3-dimensional position of the target area 30. may be determined first, and a DSM and/or a DEM may 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 a vertical orthographic image of the target region 30 based on the aerial images.

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

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

Since the technical features described above with reference to FIGS. 1 to 7 and 9 to 11 may be applied to FIG. 8 as they are, duplicate descriptions are omitted.

The devices described above may be implemented as hardware components, software components, and/or a combination of hardware components and software components. For example, devices and components described in the embodiments 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 PLU (programmable logic unit). logic unit), microprocessor, or any other device capable of executing and responding to instructions. The processing device may run an operating system (OS) and one or more software applications running on the operating system. A processing device may also access, store, manipulate, process, and generate data in response to execution of software. For convenience of understanding, there are cases in which one processing device is used, but those skilled in the art will understand that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that it can include. For example, a processing device may include a plurality of processors or a processor and a controller. Other processing configurations are also possible, such as parallel processors.

Software may include a computer program, code, instructions, or a combination of one or more of the foregoing, which configures a processing device to operate as desired or processes independently or collectively. The device can be commanded. The software and/or data may be embodied in any tangible machine, component, physical device, computer storage medium or device to be interpreted by or to provide instructions or data to a processing device. there is. Software may be distributed on networked computer systems and stored or executed in a distributed manner. Software and data may be stored on one or more computer readable 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 on a computer readable medium. In this case, the medium may continuously store a program executable by a computer or 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 combined hardware, but is not limited to a medium directly connected to a certain computer system, and may be distributed on a network. Examples of the medium include magnetic media such as hard disks, floppy disks and magnetic tapes, optical recording media such as CD-ROM and DVD, magneto-optical media such as floptical disks, and ROM, RAM, flash memory, etc. configured to store program instructions. In addition, examples of other media include recording media or storage media managed by an app store that distributes applications, a site that supplies or distributes various other software, and a server.

As described above, although the embodiments have been described with limited examples and drawings, those skilled in the art can make various modifications and variations from the above description. For example, the described techniques may be performed in an order different from the method described, and/or components of the described system, structure, device, circuit, etc. may be combined or combined in a different form than the method described, or other components may be used. Or even if it is replaced or substituted by equivalents, appropriate results can be achieved.

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

Claims (18)

A method for generating a high definition (HD) map based on an aerial image, performed by a computer system,
Selecting a reference shape from a first aerial image of a target area captured at a first viewpoint looking at the target area, based on a user's input through a tool for 3D location determination of the target area ;
identifying a corresponding figure corresponding to the reference figure in a second aerial image obtained by capturing the target region at a second viewpoint different from the first aerial image;
determining a 3D 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 3D position;
including,
The selection step is
Based on the input from the user through the tool, a vertex of any one of the facilities among the facilities included in the target area of the first aerial image and intersecting a point on a reference facility and the facilities Selecting a guide line connecting vertices of other facilities among the reference figures
including,
The identification step is
Identifying a corresponding line corresponding to the guide line in the second aerial image 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 the 3D location of a point on the reference facility where the guideline and the reference facility intersect based on the 3D location of the guideline
Including, how to create an HD map. According to claim 1,
The determining step is
The 3D position and photographing direction of the camera capturing the first aerial image corresponding to the first viewpoint, the 3D position and photographing direction of the camera capturing the second aerial image corresponding to the second viewpoint, An HD map for determining a three-dimensional position including the altitude of the reference figure according to a triangulation method based on a first angle with respect to the reference figure from a first viewpoint and a second angle with respect to the corresponding figure from the second viewpoint. How to create. According to claim 1,
The method of generating an HD map, wherein the reference facility does not include vertices. delete According to claim 1,
The method of claim 1 , wherein the reference facility is a center line of a road in the target area, and the guide line is a line connecting vertices of each lane of two lanes located around the center line. delete According to claim 1,
determining the 3D location of the reference facility; and
Determining the 3D position of at least one neighboring facility around the reference facility based on the 3D location of the reference facility
Further comprising a method for generating an HD map. According to claim 7,
Determining the 3D location of the surrounding facilities,
adjusting an altitude value corresponding to a 3D position of the reference facility according to a gradient existing between the reference facility and the neighboring facilities; and
Determining the 3D location of the surrounding facility based on the adjusted altitude value
Including, how to create an HD map. According to claim 7,
The method of claim 1 , wherein the reference facility is a center line of a road in the target area, and the surrounding facility is each of lanes located around the center line. According to claim 1,
Determining a 3D location of a facility in the target area including at least a part of the reference figure based on the determined 3D location
Including more,
The 3D location of a facility including at least a part of the reference figure is determined by calculating the 3D location of points constituting the facility according to interpolation based on the determined 3D position of the reference figure, using an HD map. How to create. A method for generating a high definition (HD) map based on an aerial image, performed by a computer system,
Selecting a reference shape from a first aerial image of a target region captured at a first viewpoint looking at the target region, based on a user input through a tool for determining a 3D location of the target region ;
identifying a corresponding figure corresponding to the reference figure in a second aerial image obtained by capturing the target region at a second viewpoint different from the first aerial image;
determining a 3D 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 3D position;
including,
The determining step is
Projecting the first aerial image including the selected reference figure or the selected reference figure onto the second aerial image;
moving the reference figure so that the transferred reference figure matches the identified corresponding figure in the second aerial image based on an input for moving the transcribed reference figure from the user through the tool; and
Determining an altitude value of the reference figure corresponding to when the identified corresponding figure matches the reference figure as a 3D position of the reference figure
Including, how to create an HD map. According to claim 11,
The determining step is
Outputting, through the tool, an altitude value corresponding to a position where the reference figure is moved when the reference figure is moved according to an input for moving the reference figure from the user.
including,
The method of generating an HD map, wherein an altitude value output when the identified corresponding figure matches the reference figure is determined as a 3-dimensional position of the reference figure. According to 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 3-dimensional position;
Further comprising a method for generating an HD map. According to claim 14,
generating a true ortho image of the target region based on the generated DSM and DEM;
Further comprising a method for generating an HD map. A computer program stored in a non-transitory computer readable recording medium to execute the method of any one of claims 1 to 3, 5, and 7 to 15 in the computer system. A non-transitory computer readable recording medium in which a program for executing the method of any one of claims 1 to 3, 5, and 7 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,
Based on a user's input through a tool for determining the 3D location of the target region, a reference figure is selected from a first aerial image obtained by capturing the target region at a first viewpoint looking at the target region, and the first A corresponding figure corresponding to the reference figure is identified in a second aerial image obtained by capturing the target area from a second viewpoint different from the aerial image, and the reference figure and the corresponding figure are matched with each other to obtain the reference figure. determining a 3D location, and generating an HD map for the target area using the determined 3D location;
In selecting the reference figure,
Based on the input from the user through the tool, a vertex of any one of the facilities among the facilities included in the target area of the first aerial image and intersecting a point on the reference facility and the facilities Select a guideline connecting the vertices of other facilities as the reference figure,
In identifying the corresponding figure,
Identifying a corresponding line corresponding to the guide line in the second aerial image as the corresponding figure;
In determining the 3-dimensional position of the reference figure,
By matching the guide line and the corresponding line, the three-dimensional position of the guide line is determined,
Based on the three-dimensional location of the guide line, determine the three-dimensional location of a point on the reference facility where the guide line and the reference facility intersect.

Images