Vehicle control apparatus and method thereof

Abstract

A vehicle control apparatus may include a light detection and ranging device (LiDAR) and a processor. According to the method, a processor may obtain a plurality of LiDAR data points by removing points having a particular height or greater from a point cloud corresponding to an external vehicle, may generate a bounding box based on contour points indicating a periphery of the external vehicle, and a final bounding box can be obtained by correcting the bounding box based on an angle between a first heading direction of the virtual box and a second heading direction of the bounding box exceeding a reference angle and based on a distance between a first position of the virtual box and a second position of the bounding box being less than or equal to a first reference distance.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims the benefit of Korean Patent Application No. 10-2023-0155741, filed on November 10, 2023, which is hereby incorporated herein by reference. Technical Field

[0003] The present disclosure relates to a vehicle device and a method thereof for identifying external objects using light detection and ranging (LiDAR). Background Art

[0004] Various studies are being conducted to assist the driving of a vehicle by recognizing external objects using various sensors.

[0005] In particular, when the vehicle is driven in a driving assistance device activation mode or an autonomous driving mode, external objects can be recognized by using LiDAR.

[0006] If an external vehicle is identified by using LiDAR, a virtual frame including the external vehicle and the side mirrors of the external vehicle may be generated, and a heading direction of the virtual frame may be identified by using the virtual frame including the side mirrors. If the heading direction of the virtual frame is identified by using the virtual frame including the side mirrors, the heading direction of the virtual frame is erroneously identified due to the side mirrors, and thus may be identified as an external vehicle cutting in that draws the virtual frame.

[0007] If it is recognized that an external vehicle cuts in the drawn virtual frame, the driving route of the vehicle can be changed, or the speed of the vehicle can be reduced. In order to correct an error in a vehicle control system including a vehicle control device, the driving route of the vehicle can be changed, or the speed of the vehicle can be reduced. Summary of the invention

[0008] The present disclosure relates to an apparatus for controlling a vehicle and a method thereof, and more particularly, to a technology for recognizing an external object by using Light Detection and Ranging (LiDAR).

[0009] Some embodiments of the present disclosure can solve the above-mentioned problems in the prior art, while the advantages achieved by the prior art can remain unchanged.

[0010] An embodiment of the present disclosure provides a vehicle control apparatus and method thereof, which generates a bounding box obtained by excluding a portion corresponding to a side mirror of an external vehicle.

[0011] An embodiment of the present disclosure provides a vehicle control apparatus and method thereof, which accurately recognizes a heading direction of an external vehicle by generating a bounding box obtained by excluding a portion corresponding to a side-view mirror of the external vehicle.

[0012] An embodiment of the present disclosure provides a vehicle control apparatus and method thereof which accurately recognizes the type of an external vehicle by using information including a side-view mirror even if a bounding box obtained by excluding a portion corresponding to the side-view mirror of the external vehicle is generated.

[0013] The technical problems to be solved by some embodiments of the present disclosure are not necessarily limited to the above-mentioned problems, and some embodiments may solve other technical problems not mentioned herein. Those skilled in the art to which the present disclosure belongs may clearly understand these other technical problems through the following description.

[0014] According to an embodiment of the present disclosure, a vehicle control device may include a light detection and ranging (LiDAR) and a processor. The processor may obtain a plurality of points by removing points having a specific height or higher from the point cloud based on a point cloud corresponding to an external vehicle obtained by LiDAR, may generate a bounding box based on contour points indicating the periphery of the external vehicle among the plurality of points, and may obtain a final bounding box by correcting the bounding box based on the fact that an angle between a first heading direction of a virtual frame of the point cloud and a second heading direction of the bounding box exceeds a reference angle, and a distance between a first position of the virtual frame corresponding to a center of a rear surface of the external vehicle and a second position of the bounding box corresponding to a center of a rear surface of the external vehicle is less than or equal to a first reference distance.

[0015] In an embodiment, the processor may remove points having a specific height or higher from the point cloud corresponding to the external vehicle based on the distance between the vehicle and the external vehicle being less than or equal to the second reference distance.

[0016] In an embodiment, the specific height may include a first specific height and a second specific height exceeding the first specific height. The processor may identify a length of the point cloud in the direction of a first axis among the first axis, the second axis, and the third axis, may remove a first point identified at the first specific height or higher in the direction of the third axis based on the length of the point cloud within the first range, and may remove a second point identified at the second specific height or higher in the direction of the third axis based on the length of the point cloud within a second range larger than the first range.

[0017] In an embodiment, the processor may identify contour points on each of the plurality of layers formed in a direction of a third axis among the first axis, the second axis, and the third axis, and may generate a bounding box including the contour points identified on each of the plurality of layers.

[0018] In an embodiment, the processor may identify an array of contour points based on identifying the location of the point cloud, and may identify a first line segment of a bounding box corresponding to a side surface of the external vehicle based on identifying the location of the point cloud and the array of contour points.

[0019] In an embodiment, the processor can identify a first endpoint and a second endpoint that are not coupled with other contour points from the contour points, can identify a peak point located farthest from a line segment connecting the first endpoint and the second endpoint, can identify a second line segment connecting the peak point and the endpoints from the first endpoint and the second endpoint, the second line segment being included in the contour points corresponding to the side surface of the external vehicle, and can identify a representative point corresponding to the side surface of the external vehicle in an area different from an area between the first line segment and the second line segment.

[0020] In an embodiment, the processor may obtain a lateral position correction value of the bounding box based on a distance between the first line segment and an average value of coordinate values ​​of representative points in the direction of the second axis among the first axis, the second axis, and the third axis, and may obtain a final bounding box based on a difference between the lateral position correction value and a reference value being less than a threshold.

[0021] In an embodiment, the processor can identify an intermediate representative point among the representative points, can identify a first representative point and a second representative point from the representative points, which are included within a specific distance from the intermediate representative point and are farthest apart from the intermediate representative point, can identify a second heading direction based on the first representative point and the second representative point, and can obtain a final bounding box based on a difference between the first heading direction and the second heading direction exceeding a reference angle.

[0022] In an embodiment, the processor may assign a first identifier to the virtual box through the point cloud, and may assign a second identifier to the final bounding box, the second identifier indicating that the final bounding box is generated by the virtual box assigned the first identifier.

[0023] In an embodiment, the processor may identify the type of the external vehicle based on the virtual box to which the first identifier is assigned, and may track the driving route of the external vehicle based on the final bounding box to which the second identifier is assigned.

[0024] According to an embodiment of the present disclosure, a vehicle control method may include: based on a point cloud corresponding to an external vehicle obtained through LiDAR, obtaining multiple points by removing points with a specific height or higher from the point cloud, generating a bounding box based on contour points indicating the periphery of the external vehicle among the multiple points, and obtaining a final bounding box by correcting the bounding box based on the following facts: the angle between a first heading direction of a virtual frame of the point cloud and a second heading direction of the bounding box exceeds a reference angle, and the distance between a first position of the virtual frame corresponding to the center of the rear surface of the external vehicle and a second position of the bounding box corresponding to the center of the rear surface of the external vehicle is less than or equal to a first reference distance.

[0025] According to an embodiment, the vehicle control method may further include removing points having a certain height or higher from the point cloud corresponding to the external vehicle based on the distance between the vehicle and the external vehicle being less than or equal to the second reference distance.

[0026] In an embodiment, the specific height may include a first specific height and a second specific height exceeding the first specific height. The vehicle control method may also include identifying a length of the point cloud in the direction of a first axis among the first axis, the second axis, and the third axis, removing a first point identified at a first specific height or higher in the direction of the third axis based on the length of the point cloud within the first range, and removing a second point identified at a second specific height or higher in the direction of the third axis based on the length of the point cloud within a second range larger than the first range.

[0027] According to an embodiment, the vehicle control method may further include identifying contour points on each of a plurality of layers formed in a direction of a third axis among the first axis, the second axis, and the third axis, and generating a bounding box including the contour points identified on each of the plurality of layers.

[0028] According to an embodiment, the vehicle control method may further include identifying an array of contour points based on the position of the identified point cloud, and identifying a first line segment of a bounding box corresponding to a side surface of the external vehicle based on the position of the identified point cloud and the array of contour points.

[0029] According to an embodiment, the vehicle control method may also include identifying a first endpoint and a second endpoint that are not coupled with other contour points from the contour points, identifying a peak point located at a position farthest from a line segment connecting the first endpoint and the second endpoint, identifying a second line segment connecting the peak point and the endpoints from the first endpoint and the second endpoint, the second line segment being included in the contour points corresponding to the side surface of the external vehicle, and identifying a representative point corresponding to the side surface of the external vehicle in an area different from the area between the first line segment and the second line segment.

[0030] According to an embodiment, the vehicle control method may further include: obtaining a lateral position correction value of the bounding box based on a distance between the first line segment and an average value of coordinate values ​​of representative points in the direction of the second axis among the first axis, the second axis, and the third axis, and obtaining a final bounding box based on a difference between the lateral position correction value and a reference value being less than a threshold.

[0031] According to an embodiment, the vehicle control method may also include identifying an intermediate representative point among the representative points, identifying a first representative point and a second representative point from the representative points, wherein the first representative point is included within a specific distance from the intermediate representative point and is farthest away from the intermediate representative point, identifying a second heading direction based on the first representative point and the second representative point, and obtaining a final bounding box based on the difference between the first heading direction and the second heading direction exceeding a reference angle.

[0032] According to an embodiment, the vehicle control method may further include assigning a first identifier to the virtual box through the point cloud, and assigning a second identifier to the final bounding box, the second identifier indicating that the final bounding box is generated by the virtual box to which the first identifier is assigned.

[0033] According to an embodiment, the vehicle control method may further include identifying a type of the external vehicle based on the virtual box to which the first identifier is assigned, and tracking a driving route of the external vehicle based on a final bounding box to which the second identifier is assigned. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The above and other features and advantages of the present disclosure will become more apparent from the following detailed description taken in conjunction with the accompanying drawings, in which:

[0035] Figure 1 An example of a block diagram showing a vehicle control device according to an embodiment of the present disclosure;

[0036] Figure 2 is a diagram showing an example of comparing an angle between a first heading direction of a virtual frame and a second heading direction of a bounding box according to an embodiment of the present disclosure;

[0037] Figure 3A is a diagram showing an example of removing points according to the position of an external vehicle according to an embodiment of the present disclosure;

[0038] Figure 3B is a diagram showing an example of removing points according to a distance between a vehicle and an external vehicle according to an embodiment of the present disclosure;

[0039] Figure 3C is a diagram showing an example of removing points according to the type of external vehicle according to an embodiment of the present disclosure;

[0040] Figure 4is a diagram showing an example of removing a vehicle control device having a certain height or higher according to an embodiment of the present disclosure;

[0041] Figure 5 is a diagram showing an example of identifying a line segment of a bounding box corresponding to a side surface of an external vehicle based on a contour point array according to an embodiment of the present disclosure;

[0042] Figure 6 is a diagram showing an example of identifying a representative point representing a side surface of an external vehicle according to an embodiment of the present disclosure;

[0043] Figure 7 is a diagram showing an example of determining whether to generate a final bounding box based on a lateral position of a bounding box in an embodiment of the present disclosure;

[0044] Figure 8 is a diagram showing an example of identifying a heading direction based on a representative point according to an embodiment of the present disclosure;

[0045] Fig. 9 is a diagram showing an example of using a virtual box and a bounding box according to an embodiment of the present disclosure;

[0046] Fig.10 is a diagram showing an example of a flowchart associated with a vehicle control method according to an embodiment of the present disclosure;

[0047] Fig.11 is a diagram showing an example of the result of applying an embodiment of the present disclosure; and

[0048] Fig.12 is a diagram showing a computing system associated with a vehicle control apparatus or a vehicle control method according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0049] Hereinafter, some embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. By adding reference numerals to the components of each figure, it can be noted that the same components include the same reference numerals even if they are also indicated on another figure. In addition, when describing some embodiments of the present disclosure, if detailed descriptions associated with well-known functions or configurations may make the subject matter of the present disclosure unnecessarily obscure, these detailed descriptions may be omitted.

[0050] When describing elements of the embodiments of the present disclosure, the terms "first", "second", "A", "B", "(a), "(b)", etc. may be used herein. The terms may only be used to distinguish one element from another, but may not necessarily limit the corresponding elements, regardless of the nature, order or priority of the corresponding elements. In addition, unless otherwise defined, the terms used herein, including technical and scientific terms, may be interpreted as customary in the art to which the present disclosure belongs. It can be understood that the terms used herein may be interpreted as including meanings consistent with their meanings in the context of the present disclosure and the related art.

[0051] In the following, reference will be made to Figures 1 to 12 Various embodiments of the present disclosure are described in detail.

[0052] Figure 1 An example of a block diagram of a vehicle control device according to an embodiment of the present disclosure is shown.

[0053] refer to Figure 1 The vehicle control device 100 according to the example of the present disclosure may be implemented inside or outside the vehicle, and some of the components included in the vehicle control device 100 may be implemented inside or outside the vehicle. For example, the vehicle control device 100 may be integrated with an internal control unit of the vehicle, and may be implemented with a separate device to be coupled with the control unit of the vehicle through a separate connection. For example, the vehicle control device 100 may also include Figure 1 Components not shown.

[0054] The vehicle control device 100 according to the embodiment may include a processor 110 and a LiDAR 120, either or both of which may be plural or may include multiple components thereof. The processor 110 or the LiDAR 120 may be electrically and / or operably coupled to each other through electronic components including a communication bus.

[0055] Hereinafter, the operably coupled pieces of hardware may include direct and / or indirect connections between the pieces of hardware by wire and / or wirelessly, such that a second piece of hardware may be controlled by a first piece of hardware among the pieces of hardware.

[0056] Although various blocks are shown, embodiments are not necessarily limited thereto. Figure 1 Some of the multiple hardware in the vehicle control device 100 may be included in a single integrated circuit including a system on a chip (SoC). The type and / or number of hardware included in the vehicle control device 100 is not limited to Figure 1 For example, the vehicle control device 100 may only include Figure 1 Some of the multiple hardware shown.

[0057] The vehicle control device 100 according to the embodiment may include hardware for processing data based on one or more instructions. The hardware for processing data may include a processor 110. For example, the hardware for processing data may include an arithmetic and logic unit (ALU), a floating point unit (FPU), a field programmable gate array (FPGA), a central processing unit (CPU) and / or an application processor (AP). The processor 110 may include a structure of a single-core processor, or may include a structure of a multi-core processor including, for example, a dual-core, quad-core, hexa-core or octa-core.

[0058] The LiDAR 120 included in the vehicle control apparatus 100 according to the embodiment may obtain a data set from identifying objects around the vehicle control apparatus 100. For example, based on a pulse laser signal emitted from the LiDAR 120 that is reflected and returned by the surrounding objects, the LiDAR 120 may identify at least one of the position of the surrounding objects, the moving direction of the surrounding objects, the speed of the surrounding objects, or any combination thereof.

[0059] For example, based on the pulsed laser signal reflected from the surrounding objects, the LiDAR 120 can obtain a data set for expressing the external objects in the space defined by the first axis, the second axis, and the third axis. For example, each of the data sets can correspond to each frame.

[0060] For example, the first axis may include an x-axis. For example, the second axis may include a y-axis. For example, the third axis may include a z-axis. For example, the first axis, the second axis, and the third axis may be perpendicular to each other and may intersect each other based on an origin. The first axis, the second axis, and the third axis are not limited to the above examples. In the following, for ease of description, the first axis is described as the x-axis; the second axis is described as the y-axis; and the third axis is described as the z-axis.

[0061] For example, based on receiving the pulsed laser signal at a specified period, the LiDAR 120 may obtain a data set including a plurality of points in space formed by an x-axis, a y-axis, and a z-axis.

[0062] The processor 110 included in the vehicle control device 100 according to the embodiment may emit light from the vehicle by using the LiDAR 120. For example, the LiDAR 120 may receive the light emitted from the vehicle. For example, the processor 110 may recognize at least one of the position, speed, moving direction, or any combination thereof of surrounding objects based on the time required to transmit the light emitted from the vehicle and / or the time required to receive the light emitted from the vehicle.

[0063] For example, the processor 110 can obtain a data set including multiple points based on the time required to emit light from the vehicle and the time required to receive the light emitted from the vehicle. The processor 110 can obtain a data set for expressing multiple points in a three-dimensional virtual coordinate system including an x-axis, a y-axis, and a z-axis.

[0064] In an embodiment, the processor 110 may obtain a point cloud corresponding to an external vehicle through the LiDAR 120. For example, the point cloud may be obtained by performing clustering based on identifying each of a plurality of points obtained by the LiDAR 120 at a specific distance. For example, each of the plurality of points identified at the specific distance may include a distance between the plurality of points that is less than the specific distance.

[0065] For example, a point cloud may include a set of points used to generate a virtual box representing an external object used to identify contour points.

[0066] In an embodiment, the processor 110 may remove points having a specific height or higher from the point cloud based on obtaining a point cloud corresponding to an external vehicle through the LiDAR 120. For example, the processor 110 may obtain a plurality of points based on obtaining a point cloud through the LiDAR 120 and removing points having a specific height or higher from the point cloud.

[0067] For example, the processor 110 may obtain a plurality of points by removing points having a specific height or higher from the point cloud based on a point cloud corresponding to an external vehicle driving on a lane different from a lane in which the vehicle is driving obtained through the LiDAR 120 .

[0068] In an embodiment, the processor 110 may identify a contour point indicating the periphery of the external vehicle among a plurality of points. For example, a contour point may be identified on each of the layers formed based on the x-axis, the y-axis, and the z-axis among the z-axis.

[0069] For example, the contour point may be obtained based on a representative point included in a point cloud on each of the layers formed based on the x-axis, the y-axis, and the z-axis. For example, the representative point may include all and / or part of the points located outside of the plurality of points included in the point cloud. For example, the point cloud may be obtained by performing clustering based on recognizing that the distances between the plurality of points obtained by the LiDAR 120 are within a specific distance.

[0070] In an embodiment, the processor 110 may generate a bounding box based on contour points in the plurality of points indicating the periphery of the external vehicle. For example, the bounding box may include the external vehicle within the frame.

[0071] In an embodiment, the processor 110 may identify a first heading direction of the virtual frame through the point cloud. The processor 110 may identify a second heading direction of the bounding box. The processor 110 may determine whether an angle between the first heading direction of the virtual frame and the second heading direction of the bounding box in the point cloud is less than or equal to a reference angle.

[0072] In an embodiment, the processor 110 may identify a first position of a virtual box corresponding to the center of the rear surface of the external vehicle. The processor 110 may identify a second position of a bounding box corresponding to the center of the rear surface of the external vehicle. For example, the processor 110 may identify a distance between the first position of the virtual box corresponding to the center of the rear surface of the external vehicle and the second position of the bounding box corresponding to the center of the rear surface of the external vehicle. For example, the processor 110 may determine whether the distance between the first position and the second position is less than or equal to a first reference distance.

[0073] In an embodiment, the processor 110 can obtain a final bounding box, which is obtained by correcting the bounding box based on that an angle between a first heading direction of the virtual frame of the point cloud and a second heading direction of the bounding box exceeds a reference angle, and a distance between a first position of the virtual frame corresponding to the center of the rear surface of the external vehicle and a second position of the bounding box corresponding to the center of the rear surface of the external vehicle is less than or equal to a first reference distance.

[0074] In an embodiment, the processor 110 may remove points having a specific height or higher from the point cloud corresponding to the external vehicle based on the distance between the vehicle and the external vehicle being less than or equal to the second reference distance. For example, the processor 110 may identify the distance between the line segment corresponding to the front surface of the vehicle and the line segment corresponding to the rear surface of the external vehicle. The processor 110 may remove points having a specific height or higher from the point cloud corresponding to the external vehicle based on the distance between the line segment corresponding to the front surface of the vehicle and the line segment corresponding to the rear surface of the external vehicle being less than or equal to the second reference distance.

[0075] For example, points having a certain height or higher may include points corresponding to the side mirrors of the external vehicle. The processor 110 may accurately identify the heading direction of the virtual box, bounding box, and / or final bounding box corresponding to the external vehicle by removing the points corresponding to the side mirrors of the external vehicle.

[0076] In an embodiment, the processor 110 may obtain a bounding box by removing points having a specific height or higher from the point cloud corresponding to the external vehicle based on the distance between the line segment corresponding to the front surface of the vehicle and the line segment corresponding to the rear surface of the external vehicle being less than or equal to the second reference distance.

[0077] In an embodiment, the processor 110 may identify the length of the point cloud in the direction of the first axis among the first axis, the second axis, and the third axis. For example, the first axis may include an x-axis. For example, the second axis may include a y-axis. For example, the third axis may include a z-axis.

[0078] For example, the specific height may include a first specific height and / or a second specific height. For example, the second specific height may exceed the first specific height.

[0079] In an embodiment, the processor 110 may remove the first point identified at the first specific height or higher in the third axis direction within the first range based on the length of the point cloud.

[0080] In an embodiment, the processor 110 may remove the second point identified at the second specific height or higher in the third axis direction based on the length of the point cloud being within a second range greater than the first range.

[0081] For example, the length of the point cloud within the first range may include a case where the external vehicle is a passenger car. For example, the length of the point cloud within the second range may include a case where the external vehicle is a large vehicle including at least one of a truck, a bus, or any combination thereof.

[0082] In an embodiment, the processor 110 may identify contour points on each of the plurality of layers formed by the first axis, the second axis, and the third axis in the third axis direction. The processor 110 may generate a bounding box including the contour points identified on each of the plurality of layers.

[0083] In an embodiment, the processor 110 may identify an array of contour points based on the position of the identified point cloud.The processor 110 may identify a first line segment of a bounding box corresponding to a side surface of the external vehicle based on the position of the identified point cloud and / or the array of contour points.

[0084] In an embodiment, the processor 110 may identify a first endpoint and / or a second endpoint that is not coupled with other contour points from the contour points. The processor 110 may identify a peak point located farthest from a line segment connecting the first endpoint and the second endpoint.

[0085] The processor 110 may identify a second line segment connecting the peak point and the endpoint from the first endpoint and the second endpoint, the second line segment being included in the contour point corresponding to the side surface of the external vehicle. The processor 110 may identify a representative point corresponding to the side surface of the external vehicle in an area different from the area between the first line segment and the second line segment.

[0086] In an embodiment, the processor 110 may obtain an average value of coordinate values ​​of the representative points in the direction of the second axis among the first axis, the second axis, and the third axis. The processor 110 may obtain a lateral position correction value of the bounding box based on a distance between the first line segment and the average value of coordinate values ​​of the representative points in the direction of the second axis among the first axis, the second axis, and the third axis.

[0087] The processor 110 may obtain a final bounding box obtained by correcting the bounding box based on the difference between the lateral position correction value and the reference value being less than a threshold value.

[0088] In an embodiment, the processor 110 may identify an intermediate representative point among the representative points. The processor 110 may identify a first representative point and a second representative point that are farthest from the intermediate representative point from the representative points included in a specific distance. The processor 110 may identify a second heading direction of the bounding box based on the first representative point and the second representative point. For example, the processor 110 may identify a second heading direction of the bounding box based on a direction extending from the first representative point to the second representative point.

[0089] The processor 110 may obtain a final bounding box obtained by correcting the bounding box based on a difference between the first heading direction of the virtual frame and the second heading direction of the bounding box exceeding a reference angle.

[0090] In an embodiment, the processor 110 may assign a first identifier to the virtual box through the point cloud. The processor 110 may assign a second identifier to the final bounding box, the second identifier indicating that the final bounding box is generated by the virtual box assigned the first identifier.

[0091] In an embodiment, the processor 110 may identify the type of the external vehicle based on the virtual box to which the first identifier is assigned. The processor 110 may track the driving route of the external vehicle based on the final bounding box to which the second identifier is assigned.

[0092] In an embodiment, the processor 110 may output a virtual box and a final bounding box. For example, the processor 110 may output a virtual box and a final bounding box generated from a point cloud corresponding to an external vehicle. For example, the processor 110 may assist the operation of a vehicle including the vehicle control device 100 based on the final bounding box and the virtual box obtained from the point cloud corresponding to the external vehicle.

[0093] Figure 2 An example of comparing an angle between a first heading direction of a virtual box and a second heading direction of a bounding box according to an embodiment of the present disclosure is shown.

[0094] refer to Figure 2 , according to the vehicle control device of the embodiment (for example, Figure 1The processor of the vehicle control device 100 (e.g., the processor 110 in 1) can be detected by LiDAR (e.g., Figure 1 The virtual frame 211 corresponding to the external vehicle is obtained by using the LiDAR 120 in the image processing unit 100. For example, the virtual frame 211 may be generated based on a point cloud corresponding to the external vehicle among a plurality of points.

[0095] In an embodiment, the processor may identify the first heading direction 213 of the virtual frame 211. For example, the first heading direction 213 of the virtual frame 211 may be formed as a direction from the center of the rear surface of the external vehicle toward the front surface of the external vehicle.

[0096] In an embodiment, the processor may generate bounding box 221. For example, the processor may generate bounding box 221 based on removing points having a certain height or higher from the point cloud. The processor may identify second heading direction 223 in bounding box 221.

[0097] In an embodiment, the processor may identify an angle 231 between the first heading direction 213 of the virtual frame 211 and the second heading direction 223 of the bounding box 221. The processor may obtain a final bounding box based on the angle 231 between the first heading direction 213 of the virtual frame 211 and the second heading direction 223 of the bounding box 221 exceeding the reference angle, and the final bounding box may be obtained by correcting the bounding box 221.

[0098] As described above, the processor of the vehicle control apparatus according to the embodiment may obtain a final bounding box representing an external vehicle by obtaining a final bounding box based on the angle 231 between the first heading direction 213 of the virtual frame 211 and the second heading direction 223 of the bounding box 221 .

[0099] Figure 3A An example of removing points according to the position of an external vehicle in an embodiment of the present disclosure is shown.

[0100] refer to Figure 3A , according to the vehicle control device of the embodiment (for example, Figure 1 A processor (eg, Figure 1 The processor 110 in the embodiment can identify the lateral position of the external vehicle. For example, the processor can identify the lateral position of the external vehicle based on the vehicle 311.

[0101] The processor can be based on the LiDAR (e.g. Figure 1 The lateral position of the external vehicle is identified by using a point cloud corresponding to the external vehicle obtained by the LiDAR 120 in the image processing unit.

[0102] For example, the processor may identify the coordinate values ​​of the point cloud corresponding to the external vehicle 321. The processor may identify the middle value in the y-axis direction in the coordinate values ​​of the point cloud corresponding to the external vehicle 321. For example, the processor may perform an operation of removing the points corresponding to the side mirror 321 of the external vehicle based on the fact that the middle value in the y-axis direction in the coordinate values ​​of the point cloud corresponding to the external vehicle 321 is smaller than the coordinate range corresponding to the road on which the vehicle 311 is driving. For example, the operation of removing the points corresponding to the side mirror of the external vehicle 321 may include an operation of removing points having a specific height or higher from the point cloud corresponding to the external vehicle 321.

[0103] For example, the processor may identify the coordinate values ​​of the point cloud corresponding to the external vehicle 323. The processor may identify the middle value in the y-axis direction in the coordinate values ​​of the point cloud corresponding to the external vehicle 323. For example, the processor may perform an operation of removing the points corresponding to the side mirror 323 of the external vehicle based on the fact that the middle value in the y-axis direction in the coordinate values ​​of the point cloud corresponding to the external vehicle 323 is greater than the coordinate range corresponding to the road on which the vehicle 311 is driving. For example, the operation of removing the points corresponding to the side mirror of the external vehicle 323 may include an operation of removing points having a specific height or higher from the point cloud corresponding to the external vehicle 323.

[0104] As described above, the processor of the vehicle control device according to the embodiment may not perform the operation of removing points corresponding to the side-view mirrors of external vehicles recognized on all roads, but may remove points corresponding to the side-view mirrors of external vehicles (e.g., external vehicle 321 and / or external vehicle 323) driven on roads different from the road on which the vehicle is driven, thereby reducing the load of the processor.

[0105] Figure 3B An example of removing points according to the distance between the vehicle and the external vehicle in the embodiment of the present disclosure is shown.

[0106] refer to Figure 3B , according to the vehicle control device of the embodiment (for example, Figure 1 A processor (eg, Figure 1 The processor 110 in the embodiment may be based on the LiDAR (e.g., Figure 1 The distance between vehicle 331 and an external vehicle (eg, external vehicle 341 and / or external vehicle 343) is identified using a plurality of points obtained by LiDAR 120 in the vehicle.

[0107] In an embodiment, the processor may identify a line segment including the center of the rear surface of the external vehicle 341 and parallel to the y-axis. The processor may identify a distance 333 between a line segment including the center of the rear surface of the external vehicle 341 and parallel to the y-axis and a line segment corresponding to the front surface of the vehicle 331.

[0108] In an embodiment, the processor may remove points having a certain height or higher from the point cloud corresponding to the external vehicle 341 based on the distance 333 between a line segment including the center of the rear surface of the external vehicle 341 and parallel to the y-axis and a line segment corresponding to the front surface of the vehicle 331 being less than or equal to a reference distance 335.

[0109] In an embodiment, the processor may identify a line segment that includes the center of the rear surface of the external vehicle 343 and is parallel to the y-axis. The processor may identify a distance 337 between a line segment that includes the center of the rear surface of the external vehicle 343 and is parallel to the y-axis and a line segment that corresponds to the front surface of the vehicle 331.

[0110] In an embodiment, the processor may identify a line segment that includes the center of the rear surface of the external vehicle 343 and is parallel to the y-axis. The processor may generate a virtual box and / or a bounding box by using a point cloud corresponding to the external vehicle 343 based on the distance 337 between the line segment that includes the center of the rear surface of the external vehicle 343 and is parallel to the y-axis and the line segment 331 corresponding to the front surface of the vehicle exceeding the reference distance 335.

[0111] As described above, the processor of the vehicle control device according to the embodiment can remove points corresponding to the side-view mirror of the external vehicle based on the distance between the vehicle 331 and the external vehicle (e.g., the external vehicle 341 and / or the external vehicle 343). The processor can remove points corresponding to the side-view mirror of the external vehicle based on the distance between the vehicle 331 and the external vehicle (e.g., the external vehicle 341 and / or the external vehicle 343), thereby reducing the load of the processor.

[0112] Figure 3C An example of removing points according to the type of external vehicles in the embodiment of the present disclosure is shown.

[0113] refer to Figure 3C , according to the vehicle control device of the embodiment (for example, Figure 1 A processor (eg, Figure 1 The processor 110 in FIG. 1 may be configured to detect the presence of a LiDAR (eg, Figure 1 The vehicle control device is included in the vehicle 351.

[0114] For example, the processor may estimate the type of external vehicle based on the length of the point cloud.

[0115] In an embodiment, the processor may identify a length 373 of the point cloud corresponding to the external vehicle 371. For example, the processor may identify a length 373 of the point cloud corresponding to the external vehicle 371 in the x-axis direction.

[0116] In an embodiment, the processor may identify that the length 373 of the point cloud corresponding to the external vehicle 371 is included in the first range. The processor may remove the first point identified at the first specific height or higher from the point cloud corresponding to the external vehicle 371 based on the length 373 of the point cloud corresponding to the external vehicle 371 included in the first range.

[0117] In an embodiment, the processor may generate a bounding box based on the point cloud from which the first point was removed.

[0118] For example, the length 373 of the point cloud included in the first range may indicate that the type of the external vehicle 371 is the first type including a passenger car.

[0119] In an embodiment, the processor may identify a length 363 of the point cloud corresponding to the external vehicle 361. For example, the processor may identify a length 363 of the point cloud corresponding to the external vehicle 361 in the x-axis direction.

[0120] In an embodiment, the processor may identify that the length 363 of the point cloud corresponding to the external vehicle 361 is included in a second range larger than the first range. The processor may remove a second point identified at a second specific height or higher that exceeds the first specific height from the point cloud corresponding to the external vehicle 361 based on the length 363 of the point cloud corresponding to the external vehicle 361 being included in the second range larger than the first range.

[0121] In an embodiment, the processor may generate a bounding box based on the point cloud from which the second point is removed.

[0122] For example, the length 363 of the point cloud included in the second range may indicate that the type of the external vehicle 361 is the second type including at least one of a truck, a bus, or any combination thereof.

[0123] As described above, the processor of the vehicle control device according to the embodiment can remove points having a specific height or higher based on the length of the point cloud corresponding to the external vehicle (e.g., the external vehicle 361 and / or the external vehicle 371). The processor can remove points corresponding to the side-view mirror of the external vehicle by removing points at different specific heights according to the size of the external vehicle.

[0124] Figure 4 An example in which a vehicle control device at a point having a certain height or higher is removed in the embodiment of the present disclosure is shown.

[0125] refer to Figure 4, according to the vehicle control device of the embodiment (for example, Figure 1 A processor (eg, Figure 1 The processor 110 in the embodiment of the present invention can obtain a point cloud corresponding to an external vehicle. For example, the processor can obtain a point cloud corresponding to an external vehicle driving on a road different from the road on which the vehicle is driving.

[0126] In an embodiment, the processor may identify a specific height 411 in the direction of the z-axis among the x-axis, the y-axis, and the z-axis.

[0127] For example, the processor may remove points 421 identified at a certain height 411 or higher based on obtaining a point cloud corresponding to an external vehicle. Figure 4 In the example of FIG. 4 , a point 421 corresponding to a side-view mirror is shown, but the embodiment is not limited thereto.

[0128] For example, the processor may remove only the points 421 corresponding to the side-view mirrors of the external vehicle from the point cloud corresponding to the external vehicle, or may remove all points identified at a certain height 411 or higher.

[0129] Figure 4 The example shows a point cloud expressed on a plane formed by the y-axis and the z-axis, but the embodiment is not limited thereto. For example, the processor may remove a point 421 identified at a specific height 411 or higher from the point cloud expressed on the plane formed by the x-axis and the z-axis. For example, the processor may remove a point 421 identified at a specific height 411 or higher from the point cloud expressed in a space formed by the x-axis, the y-axis, and the z-axis.

[0130] In an embodiment, the processor may generate a bounding box based on the point cloud, removing points 421 identified at a particular altitude 411 or higher from the point cloud.

[0131] As described above, the processor of the vehicle control device according to the embodiment can generate a bounding box corresponding to the external vehicle by using the point cloud based on removing the point 421 identified at the specific height 411 or higher, from which the point 421 is removed. The processor can accurately identify the position of the bounding box corresponding to the external vehicle and / or the heading direction of the bounding box by generating the bounding box based on the point cloud, from which the point 421 identified at the specific height 411 or higher is removed.

[0132] Figure 5 An example of identifying line segments of a bounding box corresponding to a side surface of an external vehicle based on an array of contour points in an embodiment of the present disclosure is shown.

[0133] refer to Figure 5 , included in a vehicle control device according to an embodiment (eg, Figure 1A processor (eg, Figure 1 The processor 110 in can identify the location of external vehicles based on the vehicle 511.

[0134] For example, the left front of the vehicle 511 may include quadrant I of a two-dimensional (2D) virtual coordinate system formed based on the vehicle 511. For example, the right front of the vehicle 511 may include quadrant IV of the 2D virtual coordinate system formed based on the vehicle 511.

[0135] For example, the processor may identify an array of contour points corresponding to the periphery of the external vehicle 521 in front of the left side of the vehicle 511. For example, the processor may identify a line segment corresponding to the side surface of the external vehicle 521 based on the array of contour points corresponding to the periphery of the external vehicle 521 identified as the first shape.

[0136] For example, the processor may identify an array of contour points corresponding to the periphery of the external vehicle 523 in front of the left side of the vehicle 511. For example, the processor may identify a line segment corresponding to the side surface of the external vehicle 523 based on the array of contour points corresponding to the periphery of the external vehicle 523 identified as the second shape.

[0137] For example, the processor may identify an array of contour points corresponding to the periphery of the external vehicle 531 on the same road as the vehicle 511. For example, the processor may identify a line segment corresponding to the side surface of the external vehicle 531 based on the array of contour points corresponding to the periphery of the external vehicle 531 identified as the third shape.

[0138] For example, the processor may identify an array of contour points corresponding to the periphery of the external vehicle 533 on the same road as the vehicle 511. For example, the processor may identify a line segment corresponding to the side surface of the external vehicle 533 based on the array of contour points corresponding to the periphery of the external vehicle 533 identified as the second shape.

[0139] For example, the processor may identify an array of contour points corresponding to the periphery of the external vehicle 541 right in front of the vehicle 511. For example, the processor may identify a line segment corresponding to the side surface of the external vehicle 541 based on the array of contour points corresponding to the periphery of the external vehicle 541 identified as the fourth shape.

[0140] For example, the processor may identify an array of contour points corresponding to the periphery of the external vehicle 543 right in front of the vehicle 511. For example, the processor may identify a line segment corresponding to the side surface of the external vehicle 543 based on the array of contour points corresponding to the periphery of the external vehicle 543 identified as the third shape.

[0141] In an embodiment, the processor may identify representative points representing the side surface of an external vehicle (eg, external vehicle 521 , external vehicle 523 , external vehicle 531 , external vehicle 533 , external vehicle 541 , and / or external vehicle 543 ).

[0142] Later on Figure 6 Identification of representative points representing the side surface of an external vehicle is described in detail.

[0143] Figure 6 An example of identifying a representative point representing a side surface of an external vehicle in the embodiment of the present disclosure is shown.

[0144] refer to Figure 6 , included in a vehicle control device according to an embodiment (eg, Figure 1 A processor (eg, Figure 1 The processor 110 in the example may identify contour points representing the periphery of an external vehicle from the point cloud.

[0145] Referring to the first example 601, in an embodiment, the processor may identify a first endpoint of the connection (eg, t 1 ) and a second endpoint (e.g. t 11 ) is the peak point at the farthest position of the line segment (for example, t 3 ). The processor may identify a point 611 located within a line segment connecting the second endpoint and the peak point. For example, the point 611 may be referred to as a representative point representing a side surface of an external vehicle. The point 611 located within the line segment connecting the second endpoint and the peak point may include a point identified in an area different from an area between a line segment corresponding to a side surface of a bounding box and / or a virtual box formed by a point cloud and a line segment connecting the second endpoint and the peak point.

[0146] Referring to the second example 603, in an embodiment, the processor may identify a layer among a plurality of layers formed in the z-axis direction, the layer including the longest reference line segment indicating a reference line segment (which indicates straightness) as the longest. For example, the reference line segment may be identified based on executing a convex hull algorithm.

[0147] In an embodiment, the processor may identify a point spaced apart from the longest reference line segment within a reference distance (eg, approximately 0.25 m). The processor may determine the point spaced apart from the longest reference line segment within the reference distance as a representative point representing the side surface of the external vehicle.

[0148] Based on performing the above operations, the processor can obtain the representative point 613 of the second example 603.

[0149] Figure 7 An example is shown in which whether to generate a final bounding box is determined based on the lateral position of the bounding box in an embodiment of the present disclosure.

[0150] refer to Figure 7 , according to the vehicle control device of the embodiment (for example, Figure 1 A processor (eg, Figure 1 The processor 110 in the embodiment may obtain the average horizontal axis value of the representative points. For example, the average horizontal axis value of the representative points may include the average value of the y coordinates of the representative points.

[0151] In an embodiment, the processor may identify a distance 715 between the average horizontal axis value of the representative point and a line segment of the bounding box 711 corresponding to the side surface of the external vehicle. For example, the distance 713 between the average horizontal axis value of the representative point and the line segment of the bounding box 711 corresponding to the side surface of the external vehicle may be referred to as a “lateral position correction value”.

[0152] In an embodiment, if the lateral position correction value is identified between 0 and the reference value, the processor may use the bounding box 711 as the final bounding box. For example, the reference value may be half the width of the bounding box 711.

[0153] In an embodiment, if no lateral position correction value is identified between 0 and the reference value, the processor may obtain the final bounding box by additionally correcting the bounding box 711 .

[0154] Figure 8 An example of identifying a heading direction based on a representative point in an embodiment of the present disclosure is shown.

[0155] refer to Figure 8 , according to the vehicle control device of the embodiment (for example, Figure 1 A processor (eg, Figure 1 The processor 110 in the embodiment may obtain a bounding box 811 corresponding to the external vehicle. The processor may select a middle area 821 as a high reliability interval among representative points corresponding to the side surface of the external vehicle.

[0156] For example, the middle area 821 may include an area within a specific distance from the middle representative point 823 among the representative points. For example, the specific distance may be determined according to the length of the external vehicle.

[0157] In an embodiment, the processor may identify a first representative point 825 closest to the front surface of the external vehicle from among the representative points included in the middle region 821. The processor may identify a second representative point 827 closest to the rear surface of the external vehicle from among the representative points included in the middle region 821.

[0158] The processor may identify a half-line from the second representative point 827 toward the first representative point 825. The processor may obtain a corrected heading direction 831 of the bounding box 811 based on the half-line from the second representative point 827 toward the first representative point 825.

[0159] In an embodiment, the processor may identify an angle difference between the corrected heading direction 831 of the bounding box 811 and the heading direction of the bounding box 811. The processor may correct the bounding box 811 based on the angle difference between the corrected heading direction 831 of the bounding box 811 and the heading direction of the bounding box 811 exceeding a threshold angle. For example, the processor may obtain a final bounding box obtained by correcting the bounding box 811.

[0160] In an embodiment, the processor may use the bounding box 811 as the final bounding box based on the angular difference between the corrected heading direction 831 of the bounding box 811 and the heading direction of the bounding box 811 being less than or equal to a threshold angle.

[0161] Fig. 9 An example of using a virtual box and a bounding box in an embodiment of the present disclosure is shown.

[0162] refer to Fig. 9 , according to the vehicle control device of the embodiment (for example, Figure 1 A processor (eg, Figure 1 The processor 110 in the embodiment may generate a virtual box 911 based on a point cloud corresponding to an external vehicle. The processor may generate a bounding box 913 based on removing at least a portion of the point cloud. For example, the bounding box 913 may include a final bounding box.

[0163] In an embodiment, the processor may assign a first identifier to the virtual frame 911 generated from the point cloud.

[0164] In an embodiment, the processor may assign a second identifier to the bounding box 913 , the second identifier indicating that the bounding box 913 is generated by the virtual box 911 to which the first identifier is assigned.

[0165] In an embodiment, the processor may identify the type of the external vehicle based on the virtual frame 911 to which the first identifier is assigned. For example, the processor may identify the type of the external vehicle based on the size of the virtual frame 911 to which the first identifier is assigned.

[0166] In an embodiment, the processor may track the driving route of the external vehicle based on the bounding box 913 to which the second identifier is assigned. For example, the processor may identify the rear surface center point of the bounding box 913 to which the second identifier is assigned and which corresponds to the rear surface center of the external vehicle from the bounding box 913 to which the second identifier is assigned. The processor may track the external vehicle based on the position of the rear surface center point.

[0167] As described above, the processor of the vehicle control device according to the embodiment can identify the type of the external vehicle by identifying the type of the external vehicle using the virtual frame 911, which is generated by using all the points included in the point cloud. In addition, the processor can accurately identify the position of the external vehicle and / or the driving direction of the external vehicle by tracking the external vehicle using the bounding box 913, which is generated by using a part of the point cloud from which the points corresponding to the part of the side view mirror are removed.

[0168] Fig.10 An example of a flowchart associated with a vehicle control method according to an embodiment of the present disclosure is shown.

[0169] In the following, it can be assumed that Figure 1 The vehicle control device 100 performs, for example, Fig.10 In addition, Fig.10 In the description, for example, operations described as being performed by a processor may be controlled by the processor 110 of the vehicle control device 100 .

[0170] Fig.10 At least one of the operations may be Figure 1 The vehicle control device 100 executes. Fig.10 Each of the operations in can be performed in sequence, but not necessarily in sequence. For example, the order of the operations can be changed, and at least two operations can be performed in parallel.

[0171] refer to Fig.10 In operation S1001, the vehicle control method according to the embodiment may include: Figure 1 The LiDAR 120 in the figure obtains a point cloud corresponding to an external vehicle, and an operation of obtaining a plurality of points by removing points having a specific height or higher from the point cloud.

[0172] The vehicle control method according to the embodiment may include an operation of removing points having a certain height or higher from a point cloud corresponding to the external vehicle based on a distance between the vehicle and the external vehicle being less than or equal to a second reference distance different from a first reference distance described later.

[0173] According to an embodiment, a vehicle control method may include identifying the length of a point cloud in the direction of a first axis among a first axis, a second axis, and a third axis, and removing a first point identified at a first specific height or higher in the direction of the third axis within a first range based on the length of the point cloud.

[0174] The vehicle control method according to the embodiment may include an operation of removing a second point identified at a second specific height or higher in the direction of the third axis line based on the length of the point cloud being within a second range greater than the first range.

[0175] In operation S1003 , the vehicle control method according to the embodiment may include an operation of generating a bounding box based on contour points indicating a periphery of the external vehicle among a plurality of points.

[0176] The vehicle control method according to the embodiment may include operations of identifying contour points on each of a plurality of layers formed in a direction of a third axis among the first axis, the second axis, and the third axis, and generating a bounding box including the contour points identified on each of the plurality of layers.

[0177] In operation S1005, the vehicle control method according to the embodiment may include an operation of obtaining a final bounding box, which is obtained by correcting the bounding box, wherein an angle between a first heading direction of a virtual frame based on the point cloud and a second heading direction of the bounding box exceeds a reference angle, and a distance between a first position of the virtual frame corresponding to the center of the rear surface of the external vehicle and a second position of the bounding box corresponding to the center of the rear surface of the external vehicle is less than or equal to a first reference distance.

[0178] The vehicle control method according to the embodiment may include an operation of identifying an array of contour points based on the position of the recognition point cloud, wherein the device recognizes the position of the point cloud and the array of contour points to identify a first line segment of a bounding box corresponding to a side surface of an external vehicle.

[0179] According to an embodiment, a vehicle control method may include the following operations: identifying a first endpoint and a second endpoint that are not coupled with other contour points from contour points, identifying a peak point located farthest from a line segment connecting the first endpoint and the second endpoint from the first endpoint and the second endpoint, identifying a second line segment connecting the peak point and the endpoint corresponding to the side surface of an external vehicle, and identifying a representative point corresponding to the side surface of the external vehicle in an area different from an area between the first line segment and the second line segment.

[0180] According to an embodiment, the vehicle control method may also include obtaining a lateral position correction value of the bounding box based on the distance between the first line segment and the average value of the coordinate values ​​of the representative points in the direction of the second axis among the first axis, the second axis and the third axis, the difference between the lateral position correction value of the device and the reference value being less than a threshold, and obtaining a final bounding box obtained by correcting the bounding box.

[0181] According to the embodiment, the vehicle control method may include the following operations: identifying a middle representative point among the representative points, identifying a first representative point and a second representative point from the representative points that are within a specific distance from the middle representative point and are farthest apart from the middle representative point, identifying a second heading direction based on the first representative point and the second representative point, and obtaining a final bounding box by using the device to obtain a final bounding box when the difference between the first heading direction and the second heading direction exceeds a reference angle.

[0182] The vehicle control method according to the embodiment may include an operation of assigning a first identifier to a virtual box through a point cloud, and assigning a second identifier to a final bounding box, the second identifier indicating that the final bounding box is generated by the virtual box to which the first identifier is assigned.

[0183] The vehicle control method according to the embodiment may include operations of identifying a type of the external vehicle based on a virtual box to which the first identifier is assigned, and tracking a driving route of the external vehicle based on a final bounding box to which the second identifier is assigned.

[0184] As described above, the vehicle control method according to the embodiment may assist the operation of a vehicle including a vehicle control apparatus based on a final bounding box and a virtual box obtained from a point cloud corresponding to an external vehicle.

[0185] Fig.11 An example of the result of applying the embodiment of the present disclosure is shown.

[0186] refer to Fig.11 , the virtual frame 1111 in the first example 1101 may include an example in which a point corresponding to a side-view mirror of an external vehicle is output without being removed.

[0187] The bounding box 1113 in the second example 1103 may include an example in which points corresponding to the side-view mirror of the external vehicle are output with the points removed.

[0188] As shown in the second example 1103, by outputting a bounding box 1113 based on removing points corresponding to the side mirrors, the driving direction of the external vehicle can be relatively accurately recognized.

[0189] The vehicle control device and / or the vehicle control method according to the embodiments of the present disclosure can relatively accurately identify the driving direction of an external vehicle, thereby assisting in stably operating a vehicle including the vehicle control device and / or a vehicle to which the vehicle control method is applied.

[0190] Fig.12 A computing system associated with a vehicle control device or a vehicle control method according to an embodiment of the present disclosure is shown.

[0191] refer to Fig.12 , the computing system 1000 may include at least one processor 1100, a memory 1300, a user interface input device 1400, a user interface output device 1500, a storage device 1600 and a network interface 1700 connected to each other via a bus 1200, and any combination or all of them may be multiple or may include multiple components thereof.

[0192] The processor 1100 may be a central processing unit (CPU) or a semiconductor device that processes instructions stored in the memory 1300 and / or the storage device 1600. The memory 1300 and the storage device 1600 may include various types of volatile or non-volatile storage media. For example, the memory 1300 may include a ROM (Read Only Memory) 1310 and a RAM (Random Access Memory) 1320.

[0193] Therefore, the process of the method or algorithm described in the embodiments of the present disclosure can be directly implemented by hardware, software modules or combinations thereof executed by the processor 1100. The software module can reside in a storage medium (i.e., memory 1300 and / or storage device 1600), such as, for example, RAM, flash memory, ROM, EPROM, EEPROM, register, hard disk, solid state drive (SSD), removable disk or CD-ROM. An exemplary storage medium can be coupled to the processor 1100, and the processor 1100 can read information from the storage medium and can write information in the storage medium. In another method, the storage medium can be integrated with the processor 1100. The processor 1100 and the storage medium can reside in an application specific integrated circuit (ASIC). The ASIC can reside in a user terminal. In another method, the processor 1100 and the storage medium can reside in a user terminal as a separate component.

[0194] Although the present disclosure has been described above with reference to some example embodiments and the accompanying drawings, the present disclosure is not necessarily limited thereto but various modifications and changes may be made by those skilled in the art without departing from the spirit and scope of the present disclosure according to the appended claims.

[0195] Therefore, the exemplary embodiments of the present disclosure are provided to explain the spirit and scope of the present disclosure, but not necessarily to limit them, so that the spirit and scope of the present disclosure are not necessarily limited by the exemplary embodiments. The scope of the present disclosure can be interpreted based on the appended claims, and technical ideas within the scope equivalent to the claims can be included within the scope of the present disclosure.

[0196] Some embodiments may generate a bounding box obtained by excluding a portion corresponding to a side-view mirror of an external vehicle.

[0197] Furthermore, some embodiments may accurately identify the heading direction of the external vehicle by generating a bounding box obtained by excluding a portion corresponding to a side-view mirror of the external vehicle.

[0198] Furthermore, some embodiments may accurately identify the type of an external vehicle by identifying the type of the external vehicle using information including the side-view mirrors even if a bounding box obtained by excluding a portion corresponding to the side-view mirror of the external vehicle is generated.

[0199] Various advantages can be understood directly or indirectly from the present disclosure.

Claims

1. A vehicle control device for a first vehicle, the vehicle control device comprising: Light detection and ranging device LiDAR; processor; as well as a memory coupled to the processor and storing instructions that, when executed by the processor, cause the processor to: Based on obtaining a point cloud corresponding to an external vehicle from the LiDAR, obtaining a plurality of points by removing a first set of points having a selected height or higher from the point cloud; generating a bounding box based on the contour points of the plurality of points indicating a periphery of the external vehicle; as well as A final bounding box is obtained by correcting the boundary based on that an angle between a first heading direction of a virtual frame of the point cloud and a second heading direction of the bounding box exceeds a reference angle, and based on that a travel distance between a first position of the virtual frame corresponding to a center of a rear surface of the external vehicle and a second position of the bounding box corresponding to a center of the rear surface of the external vehicle is less than or equal to a first reference distance. 2 . The apparatus of claim 1 , wherein the instructions further cause the processor to: remove the first set of points from the point cloud based on a vehicle distance between the first vehicle and the external vehicle being less than or equal to a second reference distance.

3. The apparatus of claim 1 , wherein the selected height comprises a first selected height and a second selected height exceeding the first selected height, and The instructions further cause the processor to: identifying a length of the point cloud in a first direction of the first axis among the first axis, the second axis, and the third axis; removing a first subset of the points identified at the first selected altitude or higher in a third direction of the third axis based on the length of the point cloud being within a first range; and Based on the length of the point cloud being within a second range greater than the first range, a second subset of the points identified at the second selected altitude or higher is removed in the third direction of the third axis.

4. The apparatus of claim 1 , wherein the instructions further cause the processor to: identifying a contour point on each of a plurality of layers formed in a third direction of the third axis among the first axis, the second axis, and the third axis; and The bounding box is generated, the bounding box including the contour points identified on each of the layers.

5. The apparatus of claim 1 , wherein the instructions further cause the processor to: identifying the array of contour points based on identifying the locations of the point cloud; and A first line segment of the bounding box corresponding to a side surface of the external vehicle is identified based on the position and the array of contour points.

6. The apparatus of claim 5, wherein the instructions further cause the processor to: identifying a first endpoint and a second endpoint from the contour points, wherein each of the first endpoint and the second endpoint is not coupled to other contour points from the contour points; identifying a peak point located farthest from a line segment connecting the first endpoint and the second endpoint; identifying a second line segment connecting the peak point and the first endpoint or the second endpoint, wherein the second line segment is included in a contour subset of contour points corresponding to the side surface of the external vehicle; as well as A representative point corresponding to the side surface of the external vehicle is identified in a first area different from a second area between the first line segment and the second line segment.

7. The apparatus of claim 6, wherein the instructions further cause the processor to: obtaining a lateral position correction value of the bounding box based on a correction distance between the first line segment and an average value of coordinate values ​​of the representative point in a second direction of the second axis among the first axis, the second axis, and the third axis; and The final bounding box is obtained based on that a difference between the lateral position correction value and a reference value is less than a threshold.

8. The apparatus of claim 6, wherein the instructions further cause the processor to: identifying an intermediate representative point among the representative points; identifying a first representative point and a second representative point from the representative points, the representative points being included within a selected distance from the intermediate representative point and being most spaced apart from the intermediate representative point; identifying the second heading direction based on the first representative point and the second representative point; as well as The final bounding box is obtained based on a difference between the first heading direction and the second heading direction exceeding the reference angle.

9. The apparatus of claim 1 , wherein the instructions further cause the processor to: assigning a first identifier to the virtual frame; and A second identifier is assigned to the final bounding box, the second identifier indicating that the final bounding box is generated by the virtual box to which the first identifier is assigned.

10. The apparatus of claim 9, wherein the instructions further cause the processor to: identifying a type of the external vehicle based on assigning the first identifier to the virtual frame; and The driving route of the external vehicle is tracked based on the final bounding box assigned the second identifier.

11. A vehicle control method, comprising: Based on obtaining a point cloud corresponding to the external vehicle from a light detection and ranging device (LiDAR) of the first vehicle, obtaining a plurality of points by removing a first group of points having a selected height or higher from the point cloud; generating a bounding box based on the contour points of the plurality of points indicating a periphery of the external vehicle; as well as A final bounding box is obtained by correcting the bounding box based on that an angle between a first heading direction of a virtual box of the point cloud and a second heading direction of the bounding box exceeds a reference angle, and based on that a travel distance between a first position of the virtual box corresponding to a center of a rear surface of the external vehicle and a second position of the bounding box corresponding to the center of the rear surface of the external vehicle is less than or equal to a first reference distance. 12 . The method of claim 11 , further comprising removing the first set of points from the point cloud based on a vehicle distance between the first vehicle and the external vehicle being less than or equal to a second reference distance.

13. The method of claim 11, wherein the selected height comprises a first selected height and a second selected height exceeding the first selected height, and the method further comprises: identifying a length of the point cloud in a first direction of the first axis among the first axis, the second axis, and the third axis; removing a first subset of the points identified at the first selected altitude or higher in a third direction of the third axis based on the length of the point cloud being within a first range; as well as Based on the length of the point cloud being within a second range greater than the first range, a second subset of the points identified at the second selected altitude or higher is removed in the third direction of the third axis.

14. The method according to claim 11, further comprising: identifying a contour point on each of a plurality of layers formed in a third direction of the third axis among the first axis, the second axis, and the third axis; as well as The bounding box is generated, the bounding box including the contour points identified on each of the layers.

15. The method according to claim 11, further comprising: identifying the array of contour points based on identifying the locations of the point cloud; as well as A first line segment of the bounding box corresponding to a side surface of the external vehicle is identified based on the position and the array of contour points.

16. The method according to claim 15, further comprising: identifying a first endpoint and a second endpoint from the contour points, wherein each of the first endpoint and the second endpoint is not coupled to other contour points from the contour points; identifying a peak point located farthest from a line segment connecting the first endpoint and the second endpoint; identifying a second line segment connecting the peak point and the first endpoint or the second endpoint, wherein the second line segment is included in a contour subset of contour points corresponding to the side surface of the external vehicle; as well as A representative point corresponding to the side surface of the external vehicle is identified in a first area different from a second area between the first line segment and the second line segment.

17. The method according to claim 16, further comprising: obtaining a lateral position correction value of the bounding box based on a correction distance between the first line segment and an average value of coordinate values ​​of the representative point in a second direction of the second axis among the first axis, the second axis, and the third axis; as well as The final bounding box is obtained based on that a difference between the lateral position correction value and a reference value is less than a threshold.

18. The method according to claim 16, further comprising: identifying an intermediate representative point among the representative points; identifying a first representative point and a second representative point from the representative points, the representative points being included within a selected distance from the intermediate representative point and being most spaced apart from the intermediate representative point; identifying the second heading direction based on the first representative point and the second representative point; as well as The final bounding box is obtained based on a difference between the first heading direction and the second heading direction exceeding the reference angle.

19. The method according to claim 11, further comprising: assigning a first identifier to the virtual frame; as well as A second identifier is assigned to the final bounding box, the second identifier indicating that the final bounding box is generated by the virtual box assigned the first identifier.

20. The method according to claim 19, further comprising: identifying a type of the external vehicle based on the virtual frame to which the first identifier is assigned; as well as A driving route of the external vehicle is tracked based on the final bounding box assigned the second identifier.

Images