Vehicle control apparatus and method thereof

Abstract

The invention relates to a vehicle control device and a method thereof. The vehicle control device comprises a laser radar and a processor, wherein the laser radar obtains a plurality of first points corresponding to an external vehicle; wherein the processor is configured to: identify, within a space formed by the first axis, the second axis, and the third axis, whether a distribution of first contour points included in a first virtual frame generated by the first plurality of points in a plane formed by the first axis and the second axis is one of specified shapes; identifying, among first contour points included in the first virtual frame and included in each of a first plurality of layers formed in the third axis direction, a local minimum contour point for each of the first plurality of layers, based on which a set of contour points including a global minimum contour point is identified; generating a second virtual frame based on second contour points obtained by excluding the contour point set from the first contour points; and performing a validity check on the second virtual frame.

Description

Technical Field

[0001] The present invention relates to a vehicle control device and a method thereof, and more particularly, to a technology for identifying external objects using a laser radar. Background Art

[0002] In order to assist the driving of the vehicle, various studies are being conducted to recognize external objects using various sensors.

[0003] In particular, when the vehicle is operating in a driver assistance device activation mode or an autonomous driving mode, a laser radar (LiDAR, light detection and ranging) can be used to identify external objects.

[0004] When an external vehicle is recognized using a laser radar, noise may be generated by external objects adjacent to the external vehicle (e.g., lane markings, curbs, road reflectors (cat's eyes), or protruding objects). During the formation of a virtual frame for outputting an external vehicle, the noise recognized together with the external vehicle may be recognized as a point corresponding to the external vehicle.

[0005] When a single virtual frame is generated based on external vehicles and noise, errors in the direction or speed of the virtual frame may cause errors in the vehicle control system including the vehicle control device of the vehicle, so this problem needs to be solved. Summary of the invention

[0006] An embodiment of the present invention is directed to a vehicle control device and method thereof, which generates a virtual frame by removing points corresponding to noise, thereby improving the position accuracy of an external vehicle.

[0007] An embodiment of the present invention is directed to a vehicle control device and method thereof, which generates a virtual frame by removing points corresponding to noise, thereby improving the accuracy of at least one of the longitudinal speed, the lateral speed, or any combination thereof of an external vehicle.

[0008] An embodiment of the present invention is directed to a vehicle control device and method thereof, which generates a virtual frame by removing points corresponding to noise, thereby stably outputting a traveling direction of a virtual frame corresponding to an external vehicle.

[0009] The technical problems of the present invention are not limited to the technical problems mentioned above, and other technical problems not mentioned can be clearly understood by relevant persons in the relevant field from the following description.

[0010] The vehicle control device according to an embodiment of the present invention may include: a laser radar (LiDAR, light detection and ranging) that obtains a first plurality of points corresponding to an external vehicle; and a processor; wherein the processor is configured to: in a space formed by a first axis, a second axis, and a third axis, identify whether the distribution of first contour points included in a first virtual frame generated by the first plurality of points in a surface formed by the first axis and the second axis is one of specified shapes; among the first contour points included in the first virtual frame and included in each of the first plurality of layers formed along the third axis direction, identify a local minimum contour point for each of the first plurality of layers, based on which, identify a global minimum contour point. a contour point set of contour points of the first virtual frame, wherein the local minimum contour point has the minimum length between a reference line segment and the first contour point among the line segments forming the first virtual frame, and the global minimum contour point is one of the local minimum contour points and has the minimum length between the local minimum contour point and the reference line segment; generating a second virtual frame based on a second contour point obtained by excluding the contour point set from the first contour point; and performing a validity check on the second virtual frame based on at least one of a difference between a first width of the first virtual frame and a second width of the second virtual frame, a difference between a first number of the first contour points included in the first virtual frame whose distribution is recognized as one of the specified shapes and a second number of the second contour points included in the second virtual frame whose distribution is recognized as one of the specified shapes, a difference between the number of the first plurality of points included in the first virtual frame and the number of the second plurality of points included in the second virtual frame, or any combination thereof. The reference line segment may include a line segment corresponding to the rear surface or side of the external vehicle among the line segments forming the first virtual frame.

[0011] In one embodiment, the processor is configured to: output the second virtual frame based on identifying that the second virtual frame is valid through the validity check; and output the first virtual frame based on identifying that the second virtual frame is invalid through the validity check.

[0012] In one embodiment, the processor is configured to: based on identifying that the distribution of the first contour points included in the first virtual frame is a first shape among the specified shapes, identify a line segment of the first virtual frame corresponding to the rear surface of the external vehicle as a reference line segment, and based on the width of the first virtual frame exceeding a first reference width and the length of the first virtual frame exceeding a first reference length, identify each of the local minimum contour points in each layer of the first plurality of layers.

[0013] The vehicle control device according to an embodiment may further include a memory, and the processor may store relevant information of the layer in which the global minimum contour point is identified among the first plurality of layers in the memory.

[0014] In one embodiment, the processor is configured to: based on the distance between each of the local minimum contour points included in each layer of the first plurality of layers and the reference line segment exceeding a first reference distance, and based on the minimum value in the third axis direction being identified in the second contour points, set the layer including the minimum value in the third axis direction as the minimum layer, thereby forming a second plurality of layers different from the first plurality of layers, and generate the second virtual frame based on the second contour points included in the second plurality of layers.

[0015] In one embodiment, the processor is configured to: in a case where the distribution of the first contour points included in the first virtual frame is identified as a second shape different from the first shape in the specified shape, in each layer of the first plurality of layers, identify a partial shape included in the second shape based on the distance between a line segment connecting the minimum and maximum values ​​in the second axis direction of the first contour points and each first contour point being within a reference distance, and identify a layer including the partial shape in the first plurality of layers.

[0016] In one embodiment, the reference line segment may include a first reference line segment, and the processor is configured to: in at least one layer including the partial shape, among the line segments corresponding to the side of the external vehicle and forming the first virtual frame, identify the line segment with the largest distance from the point forming the partial shape as the first reference line segment; in at least one layer in the first plurality of layers in which the partial shape is not identified, identify the smallest first distance between each first contour point and the first reference line segment, and the smallest second distance between each first contour point and a second reference line segment facing the first reference line segment among the line segments forming the first virtual frame; based on identifying that the first distance is smaller than the second distance, identify the global minimum contour point forming the first distance; based on identifying the global minimum contour point, obtain the contour point set including the global minimum contour point; based on obtaining the second contour point obtained by excluding the contour point set from the first contour point, identify the minimum value in the third axis direction among the second contour points; set the layer including the minimum value in the third axis direction as the minimum layer to form a second plurality of layers different from the first plurality of layers.

[0017] According to one embodiment, the vehicle control device may also include a memory, and the processor is configured to: identify, among the first plurality of points, the distance between a lane line point included in a lane line frame and assigned a first identifier representing a lane line and the reference line segment; identify an invalid frame assigned a second identifier indicating that the distribution of the first contour point is not one of the specified shapes; and store in the memory at least one of a second contour point obtained by excluding at least a portion of the first contour point overlapping with the lane line point from the first contour point, a second contour point obtained by excluding invalid points included in the invalid frame from the first contour point, or any combination thereof.

[0018] In one embodiment, the processor is configured to: based on identifying the minimum value of the third axis direction in the second contour point, set the layer including the minimum value in the third axis direction as the minimum layer to form a second plurality of layers different from the first plurality of layers; and generate the second virtual frame based on the second contour points included in the second plurality of layers.

[0019] In one embodiment, the processor may identify that the second virtual frame is valid based on the following conditions: the difference between the first width of the first virtual frame and the second width of the second virtual frame is greater than a second reference width; a second number of the distribution of the second contour points included in the second virtual frame is identified as one of the specified shapes is greater than or equal to a first number of the distribution of the first contour points included in the first virtual frame is identified as one of the specified shapes; the difference between the number of the first plurality of points included in the first virtual frame and the number of the second plurality of points included in the second virtual frame is less than a reference ratio.

[0020] According to an embodiment, a vehicle control method may include the following operations: in a space formed by a first axis, a second axis, and a third axis, based on obtaining a first plurality of points corresponding to an external vehicle through a laser radar (LiDAR), identifying whether the distribution of first contour points included in a first virtual frame generated by the first plurality of points in a surface formed by the first axis and the second axis is one of specified shapes; among the first contour points included in the first virtual frame and in each of the first plurality of layers formed along the third axis, identifying a local minimum contour point for each of the first plurality of layers, based on which, identifying a global minimum contour point. a contour point set of contour points of the first virtual frame, wherein the local minimum contour point has the minimum length between a reference line segment and the first contour point among the line segments forming the first virtual frame, and the global minimum contour point is one of the local minimum contour points and has the minimum length between the local minimum contour point and the reference line segment; generating a second virtual frame based on a second contour point obtained by excluding the contour point set from the first contour point; and performing a validity check on the second virtual frame based on at least one of a difference between a first width of the first virtual frame and a second width of the second virtual frame, a difference between a first number of the first contour points included in the first virtual frame whose distribution is recognized as one of the specified shapes and a second number of the second contour points included in the second virtual frame whose distribution is recognized as one of the specified shapes, a difference between the number of the first plurality of points included in the first virtual frame and the number of the second plurality of points included in the second virtual frame, or any combination thereof. The reference line segment may include a line segment corresponding to the rear surface or the side surface of the external vehicle among the line segments forming the first virtual frame.

[0021] The vehicle control method according to an embodiment may include the following operations: outputting the second virtual frame based on identifying that the second virtual frame is valid through the validity check; and outputting the first virtual frame based on identifying that the second virtual frame is invalid through the validity check.

[0022] According to one embodiment, the vehicle control method may include the following operations: based on identifying that the distribution of the first contour points included in the first virtual frame is a first shape among the specified shapes, a line segment of the first virtual frame corresponding to the rear surface of the external vehicle is identified as a reference line segment; based on the width of the first virtual frame exceeding a first reference width and the length of the first virtual frame exceeding a first reference length, in each layer of the first plurality of layers, each point in each of the local minimum contour points is identified.

[0023] The vehicle control method according to an embodiment may include the following operation: storing relevant information of the layer in which the global minimum contour point is identified among the first plurality of layers in a memory.

[0024] According to one embodiment, the vehicle control method may include the following operations: based on the distance between each of the local minimum contour points included in each layer of the first plurality of layers and the reference line segment exceeding the first reference distance, and based on the minimum value in the third axis direction being identified in the second contour points, setting the layer including the minimum value in the third axis direction as the minimum layer, thereby forming a second plurality of layers different from the first plurality of layers; based on the second contour points included in the second plurality of layers, generating the second virtual frame.

[0025] According to one embodiment, the vehicle control method may include the following operations: when the distribution of the first contour points included in the first virtual frame is identified as a second shape different from the first shape in the specified shape, in each layer of the first multiple layers, based on identifying that the distance between a line segment connecting the minimum and maximum values ​​in the second axis direction of the first contour points and each of the first contour points is within a reference distance, a partial shape included in the second shape is identified; and among the first multiple layers, a layer including the partial shape is identified.

[0026] In one embodiment, the reference line segment may include a first reference line segment, and the vehicle control method may include the following operations: in at least one layer including the partial shape, among the line segments corresponding to the side of the external vehicle and forming the first virtual frame, identifying the line segment with the largest distance from the point forming the partial shape as the first reference line segment; in at least one layer among the first plurality of layers in which the partial shape is not identified, identifying the smallest first distance between each of the first contour points and the first reference line segment, and the smallest second distance between each of the first contour points and a second reference line segment facing the first reference line segment among the line segments forming the first virtual frame; based on identifying that the first distance is smaller than the second distance, identifying the global minimum contour point forming the first distance; based on identifying the global minimum contour point, obtaining the contour point set including the global minimum contour point; based on obtaining the second contour point obtained by excluding the contour point set from the first contour point, identifying the minimum value in the third axis direction among the second contour points; setting the layer including the minimum value in the third axis direction as the minimum layer to form a second plurality of layers different from the first plurality of layers.

[0027] According to one embodiment, the vehicle control method may include the following operations: among the first plurality of points, identifying the distance between a lane line point included in a lane line frame and assigned a first identifier representing a lane line and the reference line segment; identifying an invalid box assigned a second identifier indicating that the distribution of the first contour point is not one of the specified shapes; and storing in the memory at least one of a second contour point obtained by excluding at least a portion of the first contour point overlapping with the lane line point from the first contour point, a second contour point obtained by excluding invalid points included in the invalid box from the first contour point, or any combination thereof.

[0028] According to one embodiment, the vehicle control method may include: based on identifying the minimum value of the third axis direction in the second contour point, setting the layer including the minimum value of the third axis direction as the minimum layer to form a second plurality of layers different from the first plurality of layers; based on the second contour points included in the second plurality of layers, generating the second virtual frame.

[0029] According to one embodiment, the vehicle control method may include an operation of identifying the second virtual frame as valid based on the following conditions: the difference between the first width of the first virtual frame and the second width of the second virtual frame is greater than a second reference width; the second number of the distribution of the second contour points included in the second virtual frame is greater than or equal to the first number of the distribution of the first contour points included in the first virtual frame is greater than or equal to the first number of the distribution of the first contour points included in the first virtual frame is greater than or equal to the first number of the distribution of the first contour points included in the first virtual frame is greater than or equal to the first number of the distribution of the first plurality of points included in the first virtual frame; the difference between the number of the first plurality of points included in the first virtual frame and the number of the second plurality of points included in the second virtual frame is less than a reference ratio.

[0030] This technology can generate a virtual frame by removing points corresponding to noise, thereby improving the position accuracy of external vehicles.

[0031] In addition, the present technology may generate a virtual frame by removing points corresponding to noise, thereby improving the accuracy of at least one of the longitudinal speed, the lateral speed, or any combination thereof of the external vehicle.

[0032] In addition, the present technology can generate a virtual frame by removing points corresponding to noise, thereby stably outputting the traveling direction of the virtual frame corresponding to the external vehicle.

[0033] Furthermore, various effects directly or indirectly grasped by this document can be provided. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 An example of a block diagram of a vehicle control device according to an embodiment of the present invention is shown.

[0035] Figure 2 An example of the shape of the recognition portion in one embodiment of the present invention is shown.

[0036] Figure 3 An example of obtaining a contour point set in an embodiment of the present invention is shown.

[0037] Figure 4 An example of obtaining a contour point set in an embodiment of the present invention is shown.

[0038] Figure 5 An example related to an invalid frame in an embodiment of the present invention is shown.

[0039] Figure 6 An example related to a lane wireframe in an embodiment of the present invention is shown.

[0040] Figure 7 An example of forming a second plurality of layers including second contour points in one embodiment of the present invention is shown.

[0041] Figure 8 An example related to a flowchart of a vehicle control method according to an embodiment of the present invention is shown.

[0042] Fig. 9 An example related to a flowchart of a vehicle control method according to an embodiment of the present invention is shown.

[0043] Fig.10 An example of the result of applying the present invention is shown.

[0044] Fig.11 An example of the result of applying the present invention is shown.

[0045] Fig.12 A computing system related to a vehicle control device or a vehicle control method according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0046] The following is a detailed description of some embodiments of the present invention through exemplary drawings. In assigning reference numerals to the constituent elements of each figure, it should be noted that the same reference numerals are attached to the same elements as much as possible even if they are shown in different figures. In addition, in describing the embodiments of the present invention, if it is determined that the specific description of the relevant known structure or function will hinder the understanding of the embodiments of the present invention, its detailed description will be omitted.

[0047] In describing the elements of the embodiments of the present invention, the terms such as first, second, A, B, (a), (b) etc. may be used. Such terms are only used to distinguish the element from other elements, and the nature, order or sequence of the corresponding elements are not limited by the terms. In addition, unless a different definition is made, all terms (including technical or scientific terms) used in this document have the same meaning as generally understood by technicians in the technical field to which the present invention belongs. Terms that are the same as those defined in commonly used dictionaries should be interpreted as having the same meaning as that in the context of the relevant technology, and should not be interpreted as having an idealized or overly formalized meaning, unless such a meaning is clearly defined in this application.

[0048] Refer to the following Figures 1 to 12 , specifically describe the embodiments of the present invention.

[0049] Figure 1 An example of a block diagram of a vehicle control device according to an embodiment of the present invention is shown.

[0050] Reference Figure 1 The vehicle control device 100 according to an embodiment of the present invention can be implemented inside or outside the vehicle, and part of the components included in the vehicle control device 100 can be implemented inside or outside the vehicle. In this case, the vehicle control device 100 can be formed in an integrated manner with the internal control unit of the vehicle, or it can be implemented as an independent device and connected to the control unit of the vehicle by means of another connection mechanism. For example, the vehicle control device 100 can also include Figure 1 Other components not shown.

[0051] Reference Figure 1 According to an embodiment, the vehicle control device 100 may include a processor 110 and a laser radar 120. According to an embodiment, the vehicle control device 100 may further include a memory 130. The processor 110, the laser radar 120 or the memory 130 may be electrically and / or operably coupled with each other by means of an electronic component including a communication bus.

[0052] The so-called hardware being operably combined below may include a direct connection and / or an indirect connection between hardware being established in a wired and / or wireless manner so that the second hardware in the hardware is controlled by the first hardware.

[0053] Although shown in different blocks, the embodiments are not limited thereto. Figure 1Part of the hardware of the vehicle control device 100 may be included in a single integrated circuit (SIC) including a system on a chip (SoC). The type and / or quantity of the 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 Part of the hardware shown.

[0054] The vehicle control device 100 according to an embodiment may include hardware for processing data based on one or more instructions. The hardware for processing data may include a processor 110 .

[0055] For example, hardware for processing more than one 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 have a single-core processor structure, or a multi-core processor structure including a dual core, a quad core, a hexa core or an octa core.

[0056] The laser radar 120 of the vehicle control device 100 according to an embodiment can obtain a data set for identifying objects around the vehicle including the vehicle control device 100. For example, the laser radar 120 can identify at least one of the position, movement direction, speed, or any combination thereof of the surrounding objects based on the reflection of the pulsed laser signal emitted from the laser radar 120 by the surrounding objects.

[0057] For example, the laser radar 120 may obtain a data set including multiple points in a space formed by a first axis, a second axis, and a third axis based on a pulsed laser signal reflected from surrounding objects. For example, the laser radar 120 may obtain a data set including multiple points in a space formed by a first axis, a second axis, and a third axis based on receiving a pulsed laser signal at every specified period. 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. However, the first axis, the second axis, and / or the third axis are not limited to the above examples.

[0058] The processor 110 of the vehicle control device 100 according to an embodiment may emit light from the vehicle using the laser radar 120. For example, the processor 110 may receive the light emitted from the vehicle. For example, the processor 110 may recognize at least one of the position, speed, and movement direction of surrounding objects, or any combination thereof, based on the emission time of the light emitted from the vehicle and the time when the light emitted from the vehicle is received.

[0059] For example, the processor 110 may obtain a data set including multiple points based on the emission time of the light emitted from the vehicle and the time of receiving the light emitted from the vehicle. The processor 110 may obtain a data set representing multiple points in a three-dimensional virtual coordinate system including a first axis, a second axis, and a third axis.

[0060] The processor 110 included in the vehicle control device 100 according to one embodiment may obtain a first plurality of points corresponding to an external vehicle through the laser radar 120 .

[0061] In one embodiment, the processor 110 can identify whether the distribution of first contour points included in the first virtual frame generated by the first plurality of points in the surface formed by the first axis and the second axis is one of the specified shapes in the space formed by the first axis, the second axis and the third axis.

[0062] 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 specified shape may include a first shape and a second shape. For example, the first shape may include an L-shape. For example, the second shape may include an I-shape. For example, the first contour point may be included in the first plurality of points.

[0063] In one embodiment, the processor 110 may identify a first plurality of layers included in the first virtual frame and formed along the third axis direction. The processor 110 may identify a local minimum contour point for each of the first plurality of layers among first contour points included in the first virtual frame and included in each of the first plurality of layers formed along the third axis direction, and based on this, identify a contour point set including a global minimum contour point, wherein the local minimum contour point has a minimum length between a reference line segment in line segments forming the first virtual frame and the first contour point, and the global minimum contour point is one of the local minimum contour points and has a minimum length between the local minimum contour point and the reference line segment.

[0064] For example, the reference line segment may include a line segment corresponding to the rear surface or the side surface of the external vehicle among the line segments forming the first virtual frame.

[0065] In one embodiment, the processor 110 may exclude a set of contour points including a global minimum contour point from the first contour points. The processor 110 may identify a second contour point obtained by excluding the set of contour points including the global minimum contour point from the first contour points. The processor 110 may generate a second virtual frame based on the second contour point obtained by excluding the set of contour points including the global minimum contour point from the first contour points.

[0066] In one embodiment, the processor 110 may perform a validity check on the second virtual frame based on at least one of a difference between a first width of the first virtual frame and a second width of the second virtual frame, a difference between a first number of first contour points included in the first virtual frame whose distribution is identified as one of the specified shapes and a second number of second contour points included in the second virtual frame whose distribution is identified as one of the specified shapes, a difference between a first plurality of points included in the first virtual frame and a second plurality of points included in the second virtual frame, or any combination thereof.

[0067] In one embodiment, the processor 110 may identify whether the difference between the first width of the first virtual frame and the second width of the second virtual frame is greater than or equal to the second reference width. The processor 110 may identify whether the second number of the distribution of the second contour points included in the second virtual frame is identified as one of the specified shapes is greater than or equal to the first number of the distribution of the first contour points included in the first virtual frame is identified as one of the specified shapes. The processor 110 may identify whether the difference between the number of the first plurality of points included in the first virtual frame and the number of the second plurality of points included in the second virtual frame is less than or equal to the reference ratio.

[0068] In one embodiment, the processor 110 may identify that the second virtual frame is valid based on the following conditions: the difference between the first width of the first virtual frame and the second width of the second virtual frame is greater than the second reference width; the distribution of second contour points included in the second virtual frame is identified as a second number of one of the specified shapes, which is greater than the first number of first contour points included in the first virtual frame; the difference between the number of a first plurality of points included in the first virtual frame and the number of a second plurality of points included in the second virtual frame is less than a reference ratio.

[0069] In one embodiment, the processor 110 may identify that the second virtual frame is invalid based on the following conditions: the difference between the first width of the first virtual frame and the second width of the second virtual frame is less than the second reference width, or the second number of second contour points included in the second virtual frame that are identified as one of the specified shapes is less than the first number of first contour points included in the first virtual frame that are identified as one of the specified shapes, or the difference between the number of a first plurality of points included in the first virtual frame and the number of a second plurality of points included in the second virtual frame exceeds a reference ratio.

[0070] In one embodiment, the processor 110 may output the second virtual frame based on recognizing that the second virtual frame is valid through the validity check. In one embodiment, the processor 110 may output the first virtual frame based on recognizing that the second virtual frame is invalid through the validity check.

[0071] Hereinafter, an example of obtaining the second virtual frame based on the distribution of the first contour points included in the first virtual frame being recognized as a first shape (for example, L-shape) among the specified shapes will be described.

[0072] In one embodiment, the processor 110 may identify a line segment of the first virtual frame corresponding to the rear surface of the external vehicle as a reference line segment based on the distribution of the first contour points included in the first virtual frame being identified as the first shape in the specified shape. For example, the processor 110 may set the line segment of the first virtual frame corresponding to the rear surface of the external vehicle as the reference line segment.

[0073] In one embodiment, the processor 110 may identify at least one of the width of the first virtual frame, the length of the first virtual frame, or any combination thereof. For example, the processor 110 may identify each local minimum contour point in each layer of the first plurality of layers based on the width of the first virtual frame exceeding the first reference width and the length of the first virtual frame exceeding the first reference length.

[0074] In one embodiment, the processor 110 may identify, among the local minimum contour points, a global minimum contour point having a minimum length between the reference line segment and each local minimum contour.

[0075] In one embodiment, the processor 110 may identify a layer including a global minimum contour point. The processor 110 may store information related to the layer in the first plurality of layers where the global minimum contour point is identified in the memory 130. For example, the information related to the layer in which the global minimum contour point is identified may include the number of the layer in the first plurality of layers where the global minimum contour point is identified.

[0076] In one embodiment, the processor 110 may identify each local minimum contour point included in each layer of the first plurality of layers. The processor 110 may identify whether the distance between each local minimum contour point included in each layer of the first plurality of layers and the reference line segment exceeds the first reference distance. The processor 110 may identify the minimum value in the third axis direction in the second contour point based on the distance between each local minimum contour point included in each layer of the first plurality of layers and the reference line segment exceeding the first reference distance. For example, the minimum value in the third axis direction may include the coordinate of the global minimum contour point in the third axis direction.

[0077] In one embodiment, the processor 110 may set the layer including the minimum value in the third axis direction as the minimum layer based on identifying the minimum value in the third axis direction in the second contour point, thereby forming a second plurality of layers different from the first plurality of layers. For example, the processor 110 may use the minimum value in the third axis direction as a reference to form the second plurality of layers.

[0078] In an embodiment, the processor 110 may generate a second virtual frame based on second contour points included in the second plurality of layers.

[0079] In one embodiment, the processor 110 may perform a validity check on the second virtual frame generated based on the second contour points. The processor 110 may output the second virtual frame or the first virtual frame based on the validity check result of the second virtual frame.

[0080] Hereinafter, an example of obtaining the second virtual frame based on the distribution of the first contour points included in the first virtual frame being recognized as a second shape (for example, I-shape) among the specified shapes will be described.

[0081] In one embodiment, the processor 110 may recognize that the distribution of the first contour points included in the first virtual frame is a second shape (eg, I-shape) different from the first shape (eg, L-shape) in a specified shape (eg, L-shape or I-shape).

[0082] In one embodiment, the processor 110 may identify the minimum and maximum values ​​of the first contour points in the second axis direction in each layer of the first plurality of layers. The processor 110 may identify the distance between a line segment connecting the minimum and maximum values ​​of the first contour points in the second axis direction and each first contour point in each layer of the first plurality of layers.

[0083] In one embodiment, the processor can identify a partial shape (e.g., an I'-shape) included in the second shape based on identifying in each layer of the first plurality of layers that a line segment connecting the minimum and maximum values ​​of the first contour points in the second axis direction is within a reference distance from each first contour point.

[0084] In an embodiment, the processor 110 may identify a layer including a partial shape included in the second shape based on performing an operation of identifying a partial shape included in the second shape in each layer of the first plurality of layers.

[0085] In one embodiment, the processor 110 may identify a reference line segment corresponding to the side of the external vehicle. The side of the external vehicle includes a left side and a right side, and thus is described below as a first reference line segment and a second reference line segment.

[0086] In an embodiment, the processor 110 may identify a first line segment and a second line segment corresponding to a side of the external vehicle in at least one of the layers including the partial shape.

[0087] The processor 110 may identify a first length between the first line segment and a first point corresponding to a minimum value in a second axis direction forming a partial shape. The processor 110 may identify a second length between the first line segment and a second point corresponding to a maximum value in a second axis direction forming a partial shape.

[0088] The processor 110 may identify a relatively smaller first minimum length among the first length and the second length.

[0089] The processor 110 may identify a third length between the second line segment and the first point corresponding to the minimum value in the second axis direction forming the partial shape. The processor 110 may identify a fourth length between the second line segment and the second point corresponding to the maximum value in the second axis direction forming the partial shape.

[0090] The processor 110 may identify a relatively smaller second minimum length among the third length and the fourth length.

[0091] In one embodiment, the processor 110 may compare the first minimum length with the second minimum length. For example, the processor 110 may identify a relatively smaller length between the first minimum length and the second minimum length. In one embodiment, the processor 110 may identify a line segment that forms a relatively smaller length between the first minimum length and the second minimum length. The processor 110 may set the line segment that forms the relatively smaller length between the first minimum length and the second minimum length as a first reference line segment.

[0092] In one embodiment, the processor 110 may identify at least one layer in the first plurality of layers where no partial shape is identified. The processor 110 may identify a distance between the first reference line segment and each first contour point in at least one layer in the first plurality of layers where no partial shape is identified.

[0093] The processor 110 may identify a third point in the first contour points corresponding to the minimum value in the second axis direction in at least one layer in the first plurality of layers where no partial shape is recognized. The processor 110 may identify a fourth point in the first contour points corresponding to the maximum value in the second axis direction in at least one layer in the first plurality of layers where no partial shape is recognized.

[0094] In one embodiment, the processor 110 may identify a second reference line segment that forms the first virtual frame and is opposite to the first reference line segment. In one embodiment, the processor 110 may identify a fifth length between the first reference line segment and the third point. The processor 110 may identify a sixth length between the first reference line segment and the fourth point. The processor 110 may identify a seventh length between the second reference line segment and the third point. The processor 110 may identify an eighth length between the second reference line segment and the fourth point.

[0095] In one embodiment, the processor 110 may identify the smallest length among the fifth length, the sixth length, the seventh length, and the eighth length, and identify whether the line segment forming the smallest length among the fifth length, the sixth length, the seventh length, and the eighth length is the first reference line segment. The processor 110 may identify the point forming the smallest length among the fifth length, the sixth length, the seventh length, and the eighth length as the global minimum contour point based on the line segment forming the smallest length among the fifth length, the sixth length, the seventh length, and the eighth length being the first reference line segment. The processor 110 may identify a contour point set including the global minimum contour point. The processor 110 may obtain a second contour point obtained from the first contour point excluding the contour point set including the global minimum contour point based on identifying the contour point set including the global minimum contour point.

[0096] The processor 110 may generate a second virtual frame based on the obtained second contour points.

[0097] To summarize, in one embodiment, the processor 110 may identify (or set) as a first reference line segment, in at least one layer among the layers including the partial shape, a line segment having the largest distance from a point forming the partial shape among the line segments corresponding to the external vehicle side and forming a first virtual frame.

[0098] The processor 110 can identify, in at least one layer among the first multiple layers in which no partial shape is recognized, a first distance that is the shortest among the distances between each first contour point and the first reference line segment, and a second distance that is the shortest among the distances between each first contour point and the second reference line segment that is opposite to the first reference line segment and that forms the first virtual frame.

[0099] The processor 110 may compare the first distance with the second distance. The processor 110 may identify whether the first distance is less than the second distance. The processor 110 may identify the global minimum contour point forming the first distance based on identifying that the first distance is less than the second distance. The processor 110 may obtain a contour point set including the global minimum contour point based on identifying the global minimum contour point.

[0100] The processor 110 may identify the minimum value of the third axis direction in the second contour point based on obtaining the second contour point obtained by excluding the contour point set from the first contour point. The processor 110 may set the layer including the minimum value of the third axis direction as the minimum layer, forming a second plurality of layers different from the first plurality of layers.

[0101] In an embodiment, the processor 110 may generate a second virtual frame based on second contour points included in the second plurality of layers.

[0102] In one embodiment, the processor 110 may identify, from among the first plurality of points, a distance between a lane line point included in a lane line frame and assigned a first identifier representing a lane line and a reference line segment (eg, a first reference line segment).

[0103] The processor 110 may identify an invalid box assigned with a second identifier indicating that the distribution of the first contour points is not one of the specified shapes (eg, L-shape or I-shape).

[0104] The processor 110 may store at least one of the second contour points obtained by excluding at least a portion of the first contour points overlapping the lane line points from the first contour points, the second contour points obtained by excluding the invalid points included in the invalid box from the first contour points, or any combination thereof in the memory 130.

[0105] In one embodiment, the processor 110 may set the layer including the minimum value in the third axis direction as the minimum layer based on identifying the minimum value in the third axis direction in the second contour points. The processor 110 sets the layer including the minimum value in the third axis direction as the minimum layer based on identifying the minimum value in the third axis direction in the second contour points, thereby forming a second plurality of layers different from the first plurality of layers.

[0106] In an embodiment, the processor 110 may generate a second virtual frame based on second contour points included in the second plurality of layers.

[0107] Figure 2 An example of the shape of the recognition portion in one embodiment of the present invention is shown.

[0108] Reference Figure 2 , according to a vehicle control device of an embodiment (for example: Figure 1 A processor of the vehicle control device 100 (for example: Figure 1 The processor 110) can identify contour points arranged into a second shape in the specified shape among the plurality of points, the second shape being different from the first shape.

[0109] Figure 2The content described in may include operations performed by a processor in each of the multiple layers.

[0110] Figure 2 The first example 201 may include an example for identifying a partial shape in a second shape. Figure 2 The second example 203 may include an example of identifying the length of a line segment based on a coordinate in a second axis direction among a first axis, a second axis, and a third axis in a contour point.

[0111] For example, the first shape may include an L-shape. For example, the L-shape may include that the arrangement of the contour points is an L-shaped arrangement. For example, the second shape may include an I-shape. For example, the I-shape may include that the arrangement of the contour points is an I-shaped arrangement.

[0112] Reference Figure 2 In a first example 201, in one embodiment, the processor may identify a distribution characteristic of contour points forming the second shape. For example, the processor may identify a parallel distribution graph of contour points forming the second shape.

[0113] The processor may identify a first point 211 and a second point 213. For example, the length between the first point 211 and the second point 213 may be less than the width corresponding to the lane (e.g., about 4 m). For example, the first point 211 and the second point 213 may include a laser radar (e.g., Figure 1 The laser radar 120 of the embodiment of the present invention can be used to identify a portion of the multiple points. For example, the first point 211 can correspond to the minimum value of the second axis direction among the first axis, the second axis, and the third axis. For example, the second point 213 can correspond to the maximum value of the second axis direction among the first axis, the second axis, and the third axis.

[0114] In one embodiment, the processor may identify a line segment 215 connecting the first point 211 and the second point 213. The processor may identify a distance between the line segment 215 and each of the contour points 231, 233, 235.

[0115] For example, the processor may identify the distance between the line segment 215 and each of the contour points 231 , 233 , 235 based on the following Math Formula 1.

[0116]

Mathematical formula 1

[0117]

[0118] In Mathematical Formula 1, d may be the distance between the line segment 215 and each of the contour points 231, 233, 235. 1 and (-1) may be values ​​related to the slope of line segment 215. For example, the slope of line segment 215 may be x jIt can be the coordinate of one of the contour points 231, 233, 235 in the first axis direction. j It can be the coordinate of one of the contour points 231, 233, 235 in the second axis direction. 2 It can be the intercept of the line segment 215 in the second axis direction.

[0119] In one embodiment, the processor may identify the contour points located in the first area 221 or the second area 223 based on the distances between the line segment 215 and each of the contour points 231, 233, 235. For example, the first area 221 may include an area within a first specified distance (e.g., about 0.025 m) from the line segment 215. For example, the second area 223 may include an area within a second specified distance (e.g., about 0.05 m) from the line segment 215 beyond the first specified distance. For example, the third area may include an area outside the second area 223.

[0120] Reference Figure 2 In the second example 203, in one embodiment, the processor may identify, among the contour points, a point 241 corresponding to the minimum value in the second axis direction of the first axis, the second axis, and the third axis, and a point 242 corresponding to the maximum value in the second axis direction. For example, the processor may perform the selection based on the fact that the distance between the point 241 corresponding to the minimum value in the second axis direction and the point 242 corresponding to the maximum value in the second axis direction is less than the width corresponding to the lane (e.g., about 4 m). Figure 2 The first example 201 describes an operation of analyzing the distribution characteristics of the contour points forming the second shape.

[0121] Figure 3 An example of obtaining a contour point set in an embodiment of the present invention is shown.

[0122] Reference Figure 3 , according to a vehicle control device of an embodiment (for example: Figure 1 A processor (for example: Figure 1 The processor 110) can identify the contour points included in multiple layers 301, 302, 303, 304, 305, and 306.

[0123] For example, the processor may identify a virtual box including a plurality of layers of a specified number (e.g., about 6) or more and a first shape among the specified shapes being identified as a specified number (e.g., about 2) or more. The processor may identify a size of a virtual box including a plurality of layers of a specified number (e.g., about 6) or more and a first shape among the specified shapes being identified as a specified number (e.g., about 2) or more. For example, the processor may identify a minimum distance between a bottom edge of the virtual box and a contour point based on a width of the virtual box exceeding a reference width (e.g., about 1.5 m) and a length of the virtual box exceeding a reference length (e.g., about 1.5 m).

[0124] For example, the processor may identify, among the contour points identified in the first layer 301 , a first point 331 having a minimum distance from the bottom edge 321 of the virtual frame 311 .

[0125] For example, the processor may identify, among the contour points identified in the second layer 302 , a second point 332 having a minimum distance 342 from the bottom edge 321 of the virtual frame 311 .

[0126] For example, the processor may identify, among the contour points identified in the third layer 303 , a third point 333 having a minimum distance 352 from the bottom edge 321 of the virtual frame 311 .

[0127] For example, the processor may identify, among the contour points identified in the fourth layer 304 , a fourth point 334 having a minimum distance 362 from the bottom edge 321 of the virtual frame 311 .

[0128] For example, the processor may identify, among the contour points identified in the fifth layer 305 , a fifth point 335 having a minimum distance 372 from the bottom edge 321 of the virtual frame 311 .

[0129] For example, the processor may identify, among the contour points identified in the sixth layer 306 , a sixth point 336 having a minimum distance 382 from the bottom edge 321 of the virtual frame 311 .

[0130] In one embodiment, the processor may identify points 331 , 332 , 333 , 334 , 335 , 336 having a minimum distance from a bottom edge 321 of the virtual frame 311 among contour points included in the virtual frame 311 within the first plurality of layers included in the virtual frame 311 .

[0131] For example, the processor may identify the first point 331 having the smallest distance from the bottom edge 321 of the virtual frame 311 among the points 331, 332, 333, 334, 335, 336 having the smallest distance from the bottom edge 321 of the virtual frame 311 based on identifying the points 331, 332, 333, 334, 335, 336 having the smallest distance from the bottom edge 321 of the virtual frame 311 within the first plurality of layers included in the virtual frame 311. For example, the processor may identify a set of contour points including the first point 331. For example, the set of contour points including the first point 331 may include noise.

[0132] In one embodiment, the processor may store information related to the first layer 301 including the first point 331 in the memory (for example: Figure 1 For example, the processor may store the identifier assigned to the first layer 301 in the memory.

[0133] In one embodiment, the processor may identify a set of contour points identified in a height region including the first layer 301, the first layer 301 including the first point 331. For example, the height region may include a region based on a third axis among the first axis, the second axis, and the third axis. For example, the processor may generate a virtual frame different from the virtual frame 311 based on excluding the set of contour points identified in the height region from the contour points included in the virtual frame 311. For example, the virtual frame 311 may be referred to as a first virtual frame, and a virtual frame different from the virtual frame 311 may be referred to as a second virtual frame.

[0134] Based on excluding the contour points set identified in the height area from the contour points included in the virtual frame 311, the content of the virtual frame different from the virtual frame 311 is generated. Figures 7 and 8 Described in.

[0135] Figure 4 An example of obtaining a contour point set in an embodiment of the present invention is shown.

[0136] Reference Figure 4 , according to a vehicle control device of an embodiment (for example: Figure 1 A processor (for example: Figure 1 The processor 110 of the embodiment may identify the reference line segment based on the distribution of the contour points included in the virtual frame 410 as a second shape different from the first shape in the specified shape. For example, the processor may perform operations related to the following first example 401 in each layer including contour points having a partial shape distribution included in the second shape.

[0137] Reference Figure 4 In the first example 401, in one embodiment, the processor may identify line segments 411 and 413 corresponding to the side of the external vehicle among the line segments forming the virtual frame 410. The processor may identify, among the contour points included in the virtual frame 410, a first point 415 having a minimum value in the second axis direction of the first axis, the second axis, and the third axis from the line segments 411 and 413 and a second point (417) having a maximum value in the second axis direction.

[0138] Referring to the first operation 401-1 of the first example 401, the processor may identify a first length 421 between the first line segment 411 and the first point 415. The processor may identify a second length 422 between the first line segment 411 and the second point 417.

[0139] The processor may identify a third length 431 between the second line segment 413 and the second point 417. The processor may identify a fourth length 432 between the second line segment 413 and the first point 415.

[0140] Referring to the second operation 401-2 of the first example 401, the processor may identify the relatively smaller first length 421 among the first length 421 and the second length 422. The processor may identify the relatively smaller third length 431 among the third length 431 and the fourth length 432.

[0141] Referring to the third operation 401-3 of the first example 401, the processor may identify the relatively larger third length 431 between the first length 421 and the third length 431. The processor may identify the second line segment 413 used to obtain the third length 431 as a reference line segment based on identifying the relatively larger third length 431 between the first length 421 and the third length 431. For example, the processor may set the second line segment 413 used to obtain the third length 431 as a reference line segment.

[0142] Figure 4 The second example 403 may include an example of identifying a contour point set including second contour points to be excluded from the first contour points using the reference line segment identified in the first example 401 .

[0143] In one embodiment, the processor may perform the following operations in the first virtual frame 460 in each layer different from the layer in which the partial shape included in the second shape is recognized.

[0144] Referring to the first operation 403 - 1 of the second example 403 , in one embodiment, the processor may identify, among the line segments forming the virtual frame, a first line segment 461 and a second line segment 462 corresponding to the side surface of the vehicle.

[0145] The processor may identify a first point 463 having a minimum value in the second axis direction and a second point 464 having a maximum value in the second axis direction, among points included in one of the layers different from the layer in which the partial shape included in the second shape is identified.

[0146] In one embodiment, the processor may identify the length between the first point 463 and the second point 464. The processor may identify the ratio between the width of the virtual frame 460 and the length of the line segment connecting the first point 463 and the second point 464 based on identifying the width of the virtual frame 460 and the length of the line segment connecting the first point 463 and the second point 464. The processor performs the following operation based on the ratio between the length of the line segment connecting the first point 463 and the second point 464 and the width of the virtual frame 460 being less than a specified ratio (e.g., about 30%).

[0147] The processor may identify a first length 471 between the first point 463 having a minimum value in the second axis direction and the first line segment 461. The processor may identify a second length 472 between the second point 464 having a maximum value in the second axis direction and the first line segment 461.

[0148] The processor may identify a third length 481 between the second point 464 having the maximum value in the second axis direction and the second line segment 462. The processor may identify a fourth length 482 between the first point 463 having the minimum value in the second axis direction and the second line segment 462.

[0149] Referring to the second operation 403-2 of the second example 403, in one embodiment, the processor may identify a relatively smaller length in the first length 471 and the second length 472 based on identifying the first length 471 and the second length 472. For example, the processor may identify a relatively smaller first length 471 in the first length 471 and the second length 472 based on identifying the first length 471 and the second length 472.

[0150] In one embodiment, the processor may identify a relatively smaller length between the third length 481 and the fourth length 482 based on identifying the third length 481 and the fourth length 482. For example, the processor may identify the relatively smaller third length 481 between the third length 481 and the fourth length 482.

[0151] Referring to the third operation 403-3 of the second example 403, in one embodiment, the processor may identify a relatively smaller length in the first length 471 and the third length 481 based on identifying the first length 471 and the third length 481. The processor may identify a relatively smaller third length 481 in the first length 471 and the third length 481.

[0152] The processor may identify the line segment and point used to obtain the third length 481 based on identifying the third length 481. For example, the processor may identify the second line segment 462 used to obtain the third length 481 and the second point 464 having the maximum value. The processor may identify whether the second line segment 462 used to obtain the third length 481 is a reference line segment.

[0153] For example, the processor may identify whether the second line segment 462 is Figure 4 The processor may assign an identifier to the contour point set identified in the corresponding layer based on the second line segment 462 being the reference line segment. For example, the processor may remove the contour point set to which the identifier is assigned to the contour point set identified in the corresponding layer based on the second line segment 462 being the reference line segment. For another example, the processor may exclude the contour point set to which the identifier is assigned from the first contour points included in the first virtual frame 460 based on the second line segment 462 being the reference line segment.

[0154] In one embodiment, the processor may obtain the second contour points by excluding the contour point set assigned the identifier to the contour point set identified in the corresponding layer from the first contour points included in the first virtual frame 460. The processor may generate the second virtual frame based on the obtained second contour points.

[0155] Figure 5 An example related to an invalid box in an embodiment of the present invention is shown.

[0156] Reference Figure 5 , according to a vehicle control device of an embodiment (for example: Figure 1 A processor (for example: Figure 1 The processor 110) can identify a virtual frame corresponding to an external vehicle in front of the vehicle 500.

[0157] In one embodiment, the processor may identify the distribution of the first contour points included in the virtual frame. For example, the processor may identify the arrangement of the first contour points included in the virtual frame.

[0158] In one embodiment, the processor may identify the distribution of the first contour points as one of the first type 501, the second type 502, the third type 503, and the fourth type 504. For example, the processor may assign an identifier based on the distribution of the first contour points being identified as a specified type among the first type 501, the second type 502, the third type 503, and the fourth type 504.

[0159] For example, Figure 5 The types specified in can include non Figure 1 One of the specified shapes described in .

[0160] In one embodiment, the processor may identify that the distribution of the first contour points included in the virtual frame is the second type 502 or the third type 503. The processor may identify the virtual frame including the distribution of the first contour points of the second type 502 or the third type 503 as an invalid frame based on that the distribution of the first contour points is the second type 502 or the third type 503.

[0161] The processor may not output a virtual box identified as an invalid box, or remove a layer including the distribution of the second type 502 or the third type 503 .

[0162] The second type 502 or the third type 503 is a type that cannot be identified in front of the vehicle 500, so the processor can be identified as the second type 502 or the third type 503 based on the distribution of the first contour points, and interrupt the tracking of the virtual box including the distribution of the first contour points of the second type 502 or the third type 503.

[0163] Figure 6 An example related to a lane wireframe in an embodiment of the present invention is shown.

[0164] Reference Figure 6 According to an embodiment of the vehicle control device (eg: Figure 1 A processor (eg, Figure 1 The processor 110 can identify the lane line point included in the lane line frame 611 and assigned a first identifier representing the lane line.

[0165] For example, the processor may identify a lane line frame 611 at least a portion of which is included in the virtual frame 610. The processor may identify lane line points included in the lane line frame 611 at least a portion of which is included in the virtual frame 610.

[0166] The processor may exclude lane line points included in lane line frame 611 from the first contour points, and at least a portion of lane line frame 611 is included in virtual frame 610. The processor may obtain second contour points based on excluding lane line points included in lane line frame 611 from the first contour points, wherein at least a portion of lane line frame 611 is included in virtual frame 610.

[0167] In one embodiment, the processor may use the obtained second contour points to generate a second virtual frame 620. The processor may output the generated second virtual frame 620, or assign the second virtual frame 620 to an external vehicle.

[0168] Figure 7An example of forming a second plurality of layers including second contour points in one embodiment of the present invention is shown.

[0169] Figure 7 An example of a contour point identified on a surface including a first axis, a second axis, and a third axis may be included. A vehicle control device according to an embodiment (e.g.: Figure 1 A processor of the vehicle control device 100 (for example: Figure 1 The processor 110 of the embodiment may identify the first contour point 710 included in the virtual frame. For example, the processor may identify the first contour point 710 spaced apart from the ground 700.

[0170] The processor may identify a point 715 having a minimum value in the third axis direction among the first contour points 710 based on the identification of the first contour point 710 .

[0171] For example, the processor may identify a layer 713 that includes a point 715 having a minimum value in the third axis direction. Figure 3 to Figure 4 The operation in is used to identify the point 715 having the minimum value in the third axis direction.

[0172] The processor may sample first contour points corresponding to the external object. The processor may identify whether the sampled first contour points satisfy at least one condition related to a convex hull, an angle, a minimum length, a maximum length, or any combination thereof.

[0173] The processor may identify the reliability of the first contour point that satisfies at least one condition related to a modified convex hull, an angle, a minimum length, a maximum length, or any combination thereof. For example, the processor may identify the reliability of the first contour point based on tracking a virtual box including the first contour point.

[0174] In one embodiment, the processor may identify the distribution (or arrangement) of the first contour points. The processor may identify whether the distribution of the first contour points forms a specified shape (e.g., an L-shape or an I-shape). The processor may identify the direction of travel based on forming the specified shape and based on at least one of a pixel map, a sampling angle, or any combination thereof.

[0175] For example, the pixel distribution map may include a distribution map showing the distribution of the first contour points. For example, the sampling angle may include an angle between reference points in the first contour points. For example, the reference point may include at least one of a minimum value in the first axis direction, a maximum value in the first axis direction, a minimum value in the second axis direction, a maximum value in the second axis direction, or any combination thereof.

[0176] In one embodiment, the processor may re-identify the reliability and the travel direction of the first contour point. For example, the processor may identify the travel direction based on at least one of the pixel distribution map, the sampling angle, or any combination thereof, and based thereon, re-identify at least one of the reliability, the travel direction, or any combination thereof of the first contour point. For example, the processor may perform the above operation again for a second check.

[0177] In one embodiment, the processor may identify the virtual frame including the first contour points and the order of the first contour points based on the reliability of re-recognizing the first contour points and the traveling direction. The virtual frame including the first contour points may be referred to as a meta-object for tracking an external object.

[0178] In one embodiment, the processor may perform an operation to remove noise included in the generated meta-object. For example, the noise may include Figure 3 to Figure 4 The processor may obtain a second contour point based on removing noise. The processor may perform the following steps again based on obtaining the second contour point. Figure 7 The operations described in .

[0179] The following reference Figure 8 , a vehicle control method according to another embodiment of the present invention is described in detail. Figure 8 An example related to a flowchart of a vehicle control method according to an embodiment of the present invention is shown.

[0180] The following assumptions Figure 1 The vehicle control device 100 executes Figure 8 In addition, Figure 8 The operations described as being executed by a processor in the description may be understood to be controlled by the processor 110 of the vehicle control device 100 .

[0181] In operation S801, a vehicle control method according to an embodiment may include the following operations: using a laser radar (e.g.: Figure 1 The laser radar 120 of the vehicle may obtain a plurality of points corresponding to the external object. For example, the vehicle control method may include performing a sampling operation on the obtained plurality of points.

[0182] In operation S803 , the vehicle control method according to an embodiment may include an operation of extracting points satisfying conditions related to at least one of a modified convex hull, an angle, a minimum length, a maximum length, or any combination thereof.

[0183] For example, the modified convex hull may include obtaining a minimum convex polygon including the plurality of points. For example, the modified convex hull may include obtaining a convex polygon including all line segments connecting all of the plurality of points. For example, the angle may include an angle between line segments connecting each of the plurality of points. For example, the minimum length may include a minimum length among the lengths of the line segments connecting each of the plurality of points. For example, the maximum length may include a maximum length among the lengths of the line segments connecting each of the plurality of points.

[0184] In operation S805 , the vehicle control method according to an embodiment may include operations of identifying the reliability of the points extracted in operation S803 , and assigning shapes to the extracted points.

[0185] For example, the vehicle control method may include the following operations: identifying the reliability of the extracted points based on tracking external objects related to the extracted points. For example, the vehicle control method may include the following operations: identifying the distribution of the extracted points. For example, the vehicle control method may assign a shape to the extracted points based on identifying the distribution of the extracted points. For example, the shape may include Figure 1 The specified shape (for example, L-shape or I-shape) described in .

[0186] In operation S807 , the vehicle control method according to an embodiment may include the following operation: extracting a traveling direction based on at least one of a pixel distribution map, a sampling angle, or any combination thereof.

[0187] For example, the pixel distribution map may include a distribution map showing the distribution of the first contour points. For example, the sampling angle may include an angle between reference points in the first contour points. For example, the reference point may include at least one of a minimum value in the first axis direction, a maximum value in the first axis direction, a minimum value in the second axis direction, a maximum value in the second axis direction, or any combination thereof.

[0188] In operation S809 , the vehicle control method according to an embodiment may include operations of calculating the reliability of the first contour point and extracting the traveling direction again.

[0189] In operation S811, the vehicle control method according to an embodiment may include the following operation: determining a point sequence for generating a virtual frame. For example, the vehicle control method may include the following operation: determining the sequence for the first contour point.

[0190] For example, the vehicle control method may include the following operations: determining the order of the first contour points in a counterclockwise direction starting from the minimum value in the second axis direction, and assigning identifiers to the first contour points according to the determined order. For example, the vehicle control method may include the following operations: assigning an identifier indicating the order of the first contour points to each first contour point.

[0191] In operation S813, the vehicle control method according to an embodiment may include an operation of generating a meta-object. For example, the vehicle control method may include an operation of generating a meta-object based on assigning an identifier representing the sequence of the first contour points to each point in the first contour points. For example, the meta-object may include a virtual frame for tracking an external object.

[0192] In operation S815, the vehicle control method according to an embodiment may include: removing noise points. For example, the vehicle control method may include the following operations: using Figure 3 to Figure 4 The operation described in the embodiment of the present invention is used to identify a set of contour points including noise points. For example, the vehicle control method can obtain the second contour points based on removing the identified noise points.

[0193] In one embodiment, the vehicle control method may repeatedly perform operations S801 to S815 or end based on obtaining the second contour point.

[0194] The following reference Fig. 9 , a vehicle control method according to another embodiment of the present invention is described in detail. Fig. 9 An example related to a flowchart of a vehicle control method according to an embodiment of the present invention is shown.

[0195] The following assumptions Figure 1 The vehicle control device 100 executes Fig. 9 In addition, Fig. 9 In the description, the operations described as being executed by the processor can be understood as being controlled by the processor 110 of the vehicle control device 100.

[0196] Reference Fig. 9 In operation S901, a vehicle control method according to an embodiment may include the following operation: in a space formed by a first axis, a second axis, and a third axis, identifying whether the distribution of first contour points included in a first virtual frame generated by a first plurality of points in a surface formed by the first axis and the second axis is one of the specified shapes.

[0197] In operation S903, a vehicle control method according to an embodiment may include the following operations: among first contour points included in a first virtual frame and included in each of a first plurality of layers formed along a third axis direction, a local minimum contour point is identified for each of the first plurality of layers, and based on this, a contour point set including a global minimum contour point is identified; wherein the local minimum contour point has a minimum length between a reference line segment in a line segment forming the first virtual frame and the first contour point, and the global minimum contour point is one of the local minimum contour points and has a minimum length between the local minimum contour point and the reference line segment.

[0198] For example, the reference line segment may include a line segment corresponding to the rear surface of the external vehicle or the side surface of the external vehicle among the line segments forming the first virtual frame.

[0199] The vehicle control method according to an embodiment may include the following operations: based on the distribution of the first contour points included in the first virtual frame being identified as the first shape in the specified shape, a line segment of the first virtual frame corresponding to the rear surface of the external vehicle is identified (or set) as a reference line segment. The vehicle control method may include the following operations: based on the width of the first virtual frame exceeding the first reference width and the length of the first virtual frame exceeding the first reference length, each local minimum contour point is identified in each layer of the first plurality of layers.

[0200] The vehicle control method according to an embodiment may include the following operations: storing information related to the layer in the first plurality of layers where the global minimum contour point is identified in a memory (for example: Figure 1 Memory 130).

[0201] The vehicle control method according to an embodiment may include the following operations: based on the distance between each local minimum contour point included in each layer of the first plurality of layers and the reference line segment exceeding the first reference distance, and based on the minimum value in the third axis direction being identified in the second contour point, setting the layer including the minimum value in the third axis direction as the minimum layer, and setting a second plurality of layers different from the first plurality of layers. The vehicle control method may include the following operations: generating a second virtual frame based on the second contour points included in the second plurality of layers.

[0202] The vehicle control method according to an embodiment may include the following operation: recognizing that distribution of first contour points included in the first virtual frame is a second shape different from the first shape among designated shapes.

[0203] The vehicle control method may include the following operation: when the distribution of the first contour points included in the first virtual frame is a second shape different from the first shape in the specified shape, based on identifying that the distance between a line segment connecting the minimum value and the maximum value in the second axis direction of the first contour points in each layer of the first plurality of layers and each first contour point is within a reference distance, a partial shape included in the second shape is identified. The vehicle control method may include the following operation: identifying a layer including the partial shape in the first plurality of layers.

[0204] The vehicle control method according to an embodiment may include the following operations: in at least one of the layers including the partial shape, a line segment corresponding to the side of the external vehicle and forming the first virtual frame, which has the largest distance from the point forming the partial shape, is identified as a first reference line segment. The vehicle control method may include the following operations: in at least one layer in the first plurality of layers in which the partial shape is not identified, a first distance that is the smallest among the distances from each first contour point to the first reference line segment, and a second distance that is the smallest among the distances from each first contour point to the second reference line segment that is opposite to the first reference line segment among the line segments forming the first virtual frame, is identified.

[0205] The vehicle control method may include the following operations: based on the first distance being identified as being smaller than the second distance, identifying a global minimum contour point forming the first distance. The vehicle control method may include the following operations: based on identifying the global minimum contour point, obtaining a contour point set including the global minimum contour point. The vehicle control method may include the following operations: based on obtaining a second contour point obtained by excluding the contour point set from the first contour point, identifying a minimum value in the third axis direction in the second contour point. The vehicle control method may include the following operations: setting a layer including the minimum value in the third axis direction as a minimum layer, forming a second plurality of layers different from the first plurality of layers.

[0206] The vehicle control method according to an embodiment may include the following operations: among the first plurality of points, identifying the distance between a lane line point included in a lane line frame and assigned a first identifier representing a lane line and a reference line segment. The vehicle control method may include the following operations: identifying an invalid frame assigned a second identifier representing that the distribution of the first contour points is not one of the specified shapes.

[0207] According to one embodiment, a vehicle control method may include the following operations: storing in a memory at least one of a second contour point obtained by excluding at least a portion of the first contour point overlapping with the lane line point from the first contour point, a second contour point obtained by excluding invalid points included in an invalid box from the first contour point, or any combination thereof.

[0208] The vehicle control method according to an embodiment may include the following operations: based on identifying a minimum value in the third axis direction in the second contour points, setting a layer including the minimum value in the third axis direction as a minimum layer, thereby forming a second plurality of layers different from the first plurality of layers. The vehicle control method may include the following operations: based on the second contour points included in the second plurality of layers, generating a second virtual frame.

[0209] In operation S905 , the vehicle control method according to an embodiment may include the following operation: generating a second virtual frame based on second contour points obtained by excluding the contour point set from the first contour points.

[0210] In operation S907, a vehicle control method according to an embodiment may include the following operations: performing a validity check on the second virtual frame based on at least one of a difference between a first width of the first virtual frame and a second width of the second virtual frame, a difference between a first number of first contour points included in the first virtual frame whose distribution is identified as one of the specified shapes and a second number of second contour points included in the second virtual frame whose distribution is identified as one of the specified shapes, a difference between a first plurality of points included in the first virtual frame and a second plurality of points included in the second virtual frame, or any combination thereof.

[0211] The vehicle control method according to an embodiment may include the following operation: outputting the second virtual frame based on recognizing that the second virtual frame is valid through the validity check. The vehicle control method according to an embodiment may include the following operation: outputting the first virtual frame based on recognizing that the second virtual frame is invalid through the validity check.

[0212] According to one embodiment, a vehicle control method may include an operation that is identified as valid for a second virtual frame based on the following conditions: a difference between a first width of the first virtual frame and a second width of the second virtual frame is greater than a second reference width; a second number of second contour points included in the second virtual frame are identified as one of the specified shapes, which is greater than a first number of first contour points included in the first virtual frame; and a difference between a first plurality of points included in the first virtual frame and a second plurality of points included in the second virtual frame is less than a reference ratio.

[0213] Fig.10 An example of the result after applying the present invention is shown.

[0214] Fig.10 The first example 1001 may include an example to which the present technology is not applied. Fig.10 The second example 1003 may include an example to which the present technology is applied.

[0215] Reference Fig.10In the first example 1001, due to noise, the size of the virtual box 1005 will be output larger than Fig.10 The size of the virtual frame 1007 of the second example 1003 is relatively larger.

[0216] in addition, Fig.10 The first graph 1011 , the second graph 1013 , the third graph 1015 , and the fourth graph 1017 may include speed-related graphs before and after the application of the present technology.

[0217] For example, Fig.10 The first graph 1011 may include an example related to the longitudinal velocity of the external vehicle. Fig.10 The first graph 1011 may be a graph showing that the longitudinal speed output of the external vehicle is unstable before the present technology is applied, while the longitudinal speed output of the external vehicle is stable after the present technology is applied.

[0218] For example, Fig.10 The second graph 1013 may include an example related to the lateral velocity of the external vehicle. Fig.10 The second graph 1013 may be a graph showing that the lateral velocity output of the external vehicle is unstable before the present technology is applied, while the lateral velocity output of the external vehicle is stable after the present technology is applied.

[0219] For example, Fig.10 The third graph 1015 may include an example relating to the relative longitudinal speed of the external vehicle and the host vehicle. Fig.10 The third graph 1015 may be a graph showing that the relative longitudinal speed output between the external vehicle and the own vehicle is unstable before the application of the present technology, while the relative longitudinal speed output between the external vehicle and the own vehicle is relatively stable after the application of the present technology.

[0220] For example, Fig.10 The fourth graph 1017 may include an example related to the relative lateral speed of the external vehicle and the host vehicle. Fig.10 The fourth graph 1017 may be a graph showing that the relative lateral velocity output between the external vehicle and the vehicle is unstable before the application of the present technology, while the relative lateral velocity output between the external vehicle and the vehicle is relatively stable after the application of the present technology.

[0221] Fig.11 An example of the result of applying the present invention is shown.

[0222] Fig.11 The first diagram 1100 may include an example related to the direction of travel of a meta-object. Fig.11The second chart 1110 may include an example related to the traveling direction of the tracking object. For example, the meta object may include a virtual box before the output virtual box. For example, the tracking object may include the output virtual box.

[0223] In the first diagram 1100, a first line 1101 may include the direction of travel of the meta-objects before the present technique is applied. A second line 1103 may include the direction of travel of the meta-objects after the present technique is applied.

[0224] Referring to the first graph 1100 , the first graph 1100 may be a graph showing that the traveling direction output of the meta-object after applying the present technology is relatively stable.

[0225] In the second graph 1110, a third line 1111 may include the traveling direction of the tracked object before the present technology is applied. A fourth line 1113 may include the traveling direction of the tracked object after the present technology is applied.

[0226] Referring to the second graph 1110 , the second graph 1110 may be a graph showing that the output of the traveling direction of the tracked object after applying the present technology is relatively stable.

[0227] Fig.12 A computing system related to a vehicle control device or a vehicle control method according to an embodiment of the present invention is shown.

[0228] Reference 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 via a bus 1200 .

[0229] The processor 1100 may be a central processing unit (CPU) or a semiconductor device that processes commands stored in the memory 1300 and / or the storage device 1600. The memory 1300 and the storage device 1600 may include various volatile or non-volatile storage media. For example, the memory 1300 may include a read-only memory (ROM) and a random access memory (RAM).

[0230] Therefore, the steps of the methods or algorithms described with respect to the embodiments disclosed in this specification may be directly implemented by hardware, software modules, or a combination of both executed by the processor 1100. The software modules may also reside in a storage medium (i.e., the memory 1300 and / or the storage device 1600) such as RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, removable disk, CD-ROM.

[0231] As an example, the storage medium can be combined with the processor 1100, and the processor 1100 can read information from the storage medium and record the information in the storage medium. As another method, the storage medium can also be integrated with the processor 1100. The processor and the storage medium can also reside in an application specific integrated circuit (ASIC). The ASIC can also reside in a user terminal. As another method, the processor and the storage medium can also reside in a user terminal as independent components.

[0232] The above description is merely an exemplary description of the technical concept of the present invention. Those skilled in the art to which the present invention belongs may make various modifications and variations without departing from the essential characteristics of the present invention.

[0233] Therefore, the embodiments disclosed in the present invention are intended to illustrate rather than limit the technical ideas of the present invention, and the scope of the technical ideas of the present invention is not limited by such embodiments. The protection scope of the present invention should be interpreted according to the claims, and all technical ideas within the equivalent scope should be interpreted as included in the scope of rights of the present invention.

Claims

1. A vehicle control device, comprising: a laser radar that obtains a first plurality of points corresponding to an external vehicle; as well as processor; Wherein, the processor is configured as follows: In a space formed by a first axis, a second axis, and a third axis, identifying whether distribution of first contour points included in a first virtual frame generated by the first plurality of points in a plane formed by the first axis and the second axis is one of specified shapes, identifying a local minimum contour point for each of the first plurality of layers among the first contour points included in the first virtual frame and included in each of the first plurality of layers formed along the third axis direction, and based on this, identifying a contour point set including a global minimum contour point, wherein the local minimum contour point has a minimum length between a reference line segment among line segments forming the first virtual frame and the first contour point, and the global minimum contour point is one of the local minimum contour points and has a minimum length between the local minimum contour point and the reference line segment, generating a second virtual frame based on second contour points obtained by excluding the contour point set from the first contour points, and performing a validity check on the second virtual frame based on at least one of a difference between a first width of the first virtual frame and a second width of the second virtual frame, a difference between a first number of the first contour points included in the first virtual frame whose distribution is recognized as one of the specified shapes and a second number of the second contour points included in the second virtual frame whose distribution is recognized as one of the specified shapes, a difference between a number of the first plurality of points included in the first virtual frame and a number of the second plurality of points included in the second virtual frame, or any combination thereof; The reference line segments include line segments corresponding to the rear surface or the side surface of the external vehicle among the line segments forming the first virtual frame.

2. The vehicle control device according to claim 1, wherein: The processor is configured as follows: outputting the second virtual frame based on recognizing that the second virtual frame is valid through the validity check, Based on recognizing that the second virtual frame is invalid through the validity check, the first virtual frame is output.

3. The vehicle control device according to claim 1, wherein: The processor is configured as follows: identifying, based on recognizing that the distribution of the first contour points included in the first virtual frame is a first shape among the designated shapes, a line segment of the first virtual frame corresponding to the rear surface of the external vehicle as a reference line segment, Based on the width of the first virtual frame exceeding a first reference width and the length of the first virtual frame exceeding a first reference length, each of the local minimum contour points is identified in each layer of the first plurality of layers.

4. The vehicle control device according to claim 3, wherein: Also includes a memory; and The processor is configured as follows: The information related to the layer of the first plurality of layers in which the global minimum contour point is identified is stored in the memory.

5. The vehicle control device according to claim 3, wherein: The processor is configured as follows: Based on the distance between each of the local minimum contour points included in each layer of the first plurality of layers and the reference line segment exceeding a first reference distance, and based on the minimum value in the third axis direction being identified in the second contour points, setting the layer including the minimum value in the third axis direction as the minimum layer, thereby forming a second plurality of layers different from the first plurality of layers, The second virtual frame is generated based on the second contour points included in the second plurality of layers.

6. The vehicle control device according to claim 1, wherein: The processor is configured as follows: In a case where the distribution of the first contour points included in the first virtual frame is recognized as a second shape different from the first shape among the specified shapes, In each of the first plurality of layers, a partial shape included in the second shape is identified based on identifying that a distance between a line segment connecting a minimum value and a maximum value in a second axis direction of the first contour points and each first contour point is within a reference distance, And among the first plurality of layers, a layer including the partial shape is identified.

7. The vehicle control device according to claim 6, wherein: The reference line segment comprises a first reference line segment; The processor is configured as follows: in at least one of the layers including the partial shape, identifying, among the line segments corresponding to the side of the external vehicle and forming the first virtual frame, a line segment having a maximum distance from a point forming the partial shape as the first reference line segment, In at least one layer in the first plurality of layers in which the partial shape is not identified, a first distance that is the shortest among distances between each first contour point and the first reference line segment, and a second distance that is the shortest among distances between each first contour point and a second reference line segment that is opposite to the first reference line segment and that forms the first virtual frame are identified, Based on identifying that the first distance is less than the second distance, identifying the global minimum contour point that forms the first distance, Based on identifying the global minimum contour point, obtaining the contour point set including the global minimum contour point, Based on obtaining the second contour point obtained by excluding the contour point set from the first contour point, identifying the minimum value of the third axis direction in the second contour point, A layer including the minimum value in the third axis direction is set as a minimum layer, and a second plurality of layers different from the first plurality of layers is formed.

8. The vehicle control device according to claim 6, wherein: Also includes a memory; and The processor is configured as follows: identifying, among the first plurality of points, a distance between a lane line point included in a lane line frame and assigned a first identifier representing a lane line and the reference line segment, identifying an invalid box assigned with a second identifier indicating that the distribution of the first contour points is not one of the specified shapes, At least one of a second contour point obtained by excluding at least a part of the first contour points overlapping the lane line point from the first contour points, a second contour point obtained by excluding invalid points included in the invalid box from the first contour points, or any combination thereof is stored in the memory.

9. The vehicle control device according to claim 8, wherein: The processor is configured as follows: Based on identifying the minimum value in the third axis direction in the second contour points, setting the layer including the minimum value in the third axis direction as the minimum layer to form a second plurality of layers different from the first plurality of layers, The second virtual frame is generated based on the second contour points included in the second plurality of layers.

10. The vehicle control device according to claim 1, wherein: The processor is configured to identify that the second virtual frame is valid based on the following conditions: a difference between the first width of the first virtual frame and the second width of the second virtual frame is greater than or equal to a second reference width, a second number of the distribution of the second contour points included in the second virtual frame that is recognized as one of the specified shapes is greater than or equal to a first number of the distribution of the first contour points included in the first virtual frame that is recognized as one of the specified shapes, A difference between the number of the first plurality of dots included in the first virtual frame and the number of the second plurality of dots included in the second virtual frame is less than a reference ratio.

11. A vehicle control method, comprising: In a space formed by a first axis, a second axis, and a third axis, based on a first plurality of points corresponding to an external vehicle obtained by a laser radar, identifying whether distribution of first contour points included in a first virtual frame generated by the first plurality of points in a plane formed by the first axis and the second axis is one of specified shapes; identifying a local minimum contour point for each of the first plurality of layers among the first contour points included in the first virtual frame and included in each of the first plurality of layers formed along the third axis direction, and based on this, identifying a contour point set including a global minimum contour point, wherein the local minimum contour point has a minimum length between a reference line segment among line segments forming the first virtual frame and the first contour point, and the global minimum contour point is one of the local minimum contour points and has a minimum length between the local minimum contour point and the reference line segment; generating a second virtual frame based on second contour points obtained by excluding the contour point set from the first contour points; and performing a validity check on the second virtual frame based on at least one of a difference between a first width of the first virtual frame and a second width of the second virtual frame, a difference between a first number of the first contour points included in the first virtual frame whose distribution is recognized as one of the specified shapes and a second number of the second contour points included in the second virtual frame whose distribution is recognized as one of the specified shapes, a difference between a number of the first plurality of points included in the first virtual frame and a number of the second plurality of points included in the second virtual frame, or any combination thereof; The reference line segments include line segments corresponding to the rear surface or the side surface of the external vehicle among the line segments forming the first virtual frame.

12. The vehicle control method according to claim 11, wherein: The vehicle control method comprises: outputting the second virtual frame based on recognizing that the second virtual frame is valid through the validity check; Based on recognizing that the second virtual frame is invalid through the validity check, the first virtual frame is output.

13. The vehicle control method according to claim 11, wherein: The vehicle control method comprises: identifying, based on recognizing that the distribution of the first contour points included in the first virtual frame is a first shape among the designated shapes, a line segment of the first virtual frame corresponding to the rear surface of the external vehicle as a reference line segment; Based on the width of the first virtual frame exceeding a first reference width and the length of the first virtual frame exceeding a first reference length, each of the local minimum contour points is identified in each layer of the first plurality of layers.

14. The vehicle control method according to claim 13, wherein: The vehicle control method comprises: The information related to the layer of the first plurality of layers in which the global minimum contour point is identified is stored in a memory.

15. The vehicle control method according to claim 13, wherein: The vehicle control method comprises: Based on the distance between each of the local minimum contour points included in each layer of the first plurality of layers and the reference line segment exceeding a first reference distance, and based on the minimum value in the third axis direction being identified in the second contour points, setting a layer including the minimum value in the third axis direction as a minimum layer, thereby forming a second plurality of layers different from the first plurality of layers; The second virtual frame is generated based on the second contour points included in the second plurality of layers.

16. The vehicle control method according to claim 11, wherein: The vehicle control method comprises: In a case where the distribution of the first contour points included in the first virtual frame is recognized as a second shape different from the first shape among the specified shapes, identifying, in each of the first plurality of layers, a partial shape included in the second shape based on identifying that a distance between a line segment connecting a minimum value and a maximum value in a second axis direction of the first contour points and each of the first contour points is within a reference distance; Among the first plurality of layers, a layer comprising the partial shape is identified.

17. The vehicle control method according to claim 16, wherein: The reference line segment comprises a first reference line segment; and The vehicle control method comprises: in at least one of the layers including the partial shape, identifying, among line segments corresponding to the side of the external vehicle and forming the first virtual frame, a line segment having a maximum distance from a point forming the partial shape as the first reference line segment; In at least one layer in the first plurality of layers in which the partial shape is not identified, identifying a first distance that is the shortest among distances between each of the first contour points and the first reference line segment, and a second distance that is the shortest among distances between each of the first contour points and a second reference line segment that is opposite to the first reference line segment among line segments forming the first virtual frame; Based on identifying that the first distance is less than the second distance, identifying the global minimum contour point that forms the first distance; Based on identifying the global minimum contour point, obtaining the contour point set including the global minimum contour point; Based on obtaining the second contour points obtained by excluding the contour point set from the first contour points, identifying the minimum value of the third axis direction in the second contour points; A layer including the minimum value in the third axis direction is set as a minimum layer, and a second plurality of layers different from the first plurality of layers is formed.

18. The vehicle control method according to claim 16, wherein: The vehicle control method comprises: identifying, among the first plurality of points, a distance between a lane line point included in a lane line frame and assigned a first identifier representing a lane line and the reference line segment; identifying an invalid box assigned with a second identifier indicating that the distribution of the first contour points is not one of the specified shapes; At least one of the second contour points obtained by excluding at least a part of the first contour points overlapping the lane line points from the first contour points, the second contour points obtained by excluding invalid points included in the invalid box from the first contour points, or any combination thereof is stored in the memory.

19. The vehicle control method according to claim 18, wherein: The vehicle control method comprises: Based on identifying the minimum value in the third axis direction in the second contour points, setting a layer including the minimum value in the third axis direction as a minimum layer to form a second plurality of layers different from the first plurality of layers; The second virtual frame is generated based on the second contour points included in the second plurality of layers.

20. The vehicle control method according to claim 11, wherein: The vehicle control method includes identifying that the second virtual frame is valid based on the following conditions: a difference between the first width of the first virtual frame and the second width of the second virtual frame is greater than or equal to a second reference width, the second number of the distribution of the second contour points included in the second virtual frame that is recognized as one of the specified shapes is greater than or equal to the first number of the distribution of the first contour points included in the first virtual frame that is recognized as one of the specified shapes, A difference between the number of the first plurality of dots included in the first virtual frame and the number of the second plurality of dots included in the second virtual frame is less than a reference ratio.

Images