OBJECT DETECTION DEVICE AND METHOD

Abstract

An object detection device includes a sensor (e.g., LIDAR) and a processor. The processor may obtain at least one point representing an external environment of a vehicle via the sensor and determine a plurality of waypoints representing positions on a ground. The plurality of waypoints may correspond to a path along which the vehicle is expected to move. The processor may further classify each waypoint of the plurality of waypoints into at least one of a plurality of groups based on a distance between the vehicle and a position on the ground of each waypoint of the plurality of waypoints, determine a representative point for each group of the plurality of groups, determine a road profile including at least one of ground elevation information or ground contour information, and output a signal connected to the autonomous driving control of the vehicle.

Description

REFERENCE TO RELATED APPLICATION

[0001] This application claims priority to Korean Patent Application No. 10-2024-0001034, filed on January 3, 2024, with the Korean Intellectual Property Office, the entire contents of which are incorporated by reference into this application. TECHNICAL FIELD

[0002] The present disclosure relates to an object recognition apparatus and method, and more particularly to a technology for identifying ground height information based on information obtained via a light detection and ranging device (LIDAR). BACKGROUND

[0003] For autonomous vehicles and vehicles equipped with a driver assistance system, environmental awareness technology is essential to avoid obstacles and detect hazards.

[0004] A vehicle can obtain information about its surroundings through one or more sensors, such as a LIDAR, a radar and a camera.

[0005] If only one camera is used to obtain information about the vehicle's surroundings, the accuracy of the surrounding height information may be below a reference value. In particular, driving comfort and stability can be improved if the accuracy of the height information of the ground on which the vehicle is traveling also improves. This is because vehicle control can be assisted by the height information of the ground.

[0006] Accordingly, a technology for identifying ground elevation information by a LIDAR may be beneficial for improving the elevation information of the environment. SUMMARY

[0007] The present disclosure has been made to solve the above-mentioned problems encountered in the prior art while maintaining the advantages achieved by the prior art.

[0008] One aspect of the present disclosure provides an object detection apparatus and method for identifying ground elevation information for a path a host vehicle is expected to travel via a LIDAR.

[0009] One aspect of the present disclosure provides an object detection apparatus and method for improving the accuracy of elevation information by identifying, via a LIDAR, elevation information of the ground for a path on which a host vehicle is expected to travel.

[0010] One aspect of the present disclosure provides an object detection apparatus and method for improving driving stability by improving the accuracy of ground height information for a path on which a host vehicle is expected to travel when there is a road surface defect.

[0011] One aspect of the present disclosure provides an object detection apparatus and method for enhancing the driving experience by improving the accuracy of ground elevation information for a path on which a host vehicle is expected to travel.

[0012] One aspect of the present disclosure provides an object detection apparatus and method for obtaining ground elevation information for a path on which a host vehicle robust to noise is expected to travel.

[0013] One aspect of the present disclosure provides an object recognition apparatus and method for identifying a confidence level of points corresponding to the ground.

[0014] The technical problems to be solved by the present disclosure are not limited to the above-mentioned problems, and any other technical problems not mentioned here will be clearly understood by those skilled in the art to which the present disclosure relates from the following description.

[0015] According to one or more embodiments of the present disclosure, an apparatus may comprise: a sensor; and a processor. The processor may be configured to: obtain, via the sensor, at least one point representing an external environment of a vehicle; determine, among the at least one point, a plurality of waypoints representing positions on a ground. The plurality of waypoints may correspond to a path along which the vehicle is expected to travel.The processor may be further configured to: classify each waypoint of the plurality of waypoints into at least one group of a plurality of groups based on a distance between the vehicle and a position of each waypoint of the plurality of waypoints on the ground; determine a representative point for each group of the plurality of groups based on a position of each classified waypoint in a group of the plurality of groups that corresponds to the representative point; determine a road profile comprising at least one of elevation information of the ground or contour information of the ground based on an interpolation between representative points of two adjacent groups of the plurality of groups; and output a signal associated with an autonomous driving controller of the vehicle based on the determined road profile.

[0016] The processor may be configured to determine the plurality of waypoints by: determining an object type corresponding to each of the at least one point representing the external environment of the vehicle; and determining the plurality of waypoints based on the object type and a position of the object.

[0017] The at least one point may be included in the input data of an artificial neural network (ANN). The processor may be configured to determine the object type by determining the object type based on output data from the ANN.

[0018] The processor may be further configured to determine a confidence level of the representative point for each group of the plurality of groups based on at least one of: an object type corresponding to classified waypoints included in a group corresponding to the representative point, a set of the classified waypoints included in the group corresponding to the representative point, or an altitude of the classified waypoints included in the group corresponding to the representative point.

[0019] A first representative point corresponding to a first group that has more than a certain amount of classified waypoints may have a higher confidence level than a second representative point corresponding to a second group that has fewer than the certain amount of classified waypoints. A third representative point corresponding to a third group may have a higher confidence level than a fourth representative point corresponding to a fourth group. A maximum elevation value of classified waypoints in the third group may not be greater than an average elevation value of the classified waypoints contained in the third group by at least a certain amount. A maximum value of classified waypoints in the fourth group may be greater than an average elevation of the classified waypoints contained in the fourth group by at least the certain amount.

[0020] The processor may be configured to classify each point of the plurality of waypoints by: classifying a first waypoint of the plurality of waypoints into a first group based on a first distance from a first position on the ground corresponding to the first waypoint to the vehicle satisfying a first distance range; and classifying a second waypoint of the plurality of waypoints into a second group based on a second distance from a second position on the ground corresponding to the second waypoint to the vehicle satisfying a second distance range different from the first distance range.

[0021] The processor may be further configured to: determine an expected trajectory of two front wheels with respect to a direction of travel based on a steering angle of the vehicle; and determine the path based on the expected trajectory.

[0022] The processor may be configured to determine the representative point for each group of the plurality of groups by determining the representative point based on at least one of the following: an average longitudinal position of one or more waypoints of the plurality of waypoints classified into a group corresponding to the representative point; and an average lateral position of the one or more waypoints classified into the group corresponding to the representative point; or an average altitude of the one or more waypoints classified into the group corresponding to the representative point,

[0023] The path can have a certain length.

[0024] The processor may be configured to determine the representative point for each group of the plurality of groups by determining the representative point based on a set of classified waypoints included in the group corresponding to the representative point that is greater than a threshold set.

[0025] According to one or more embodiments of the present disclosure, a method may include: obtaining at least one point representing an external environment of a vehicle via a sensor; determining a plurality of waypoints representing positions on a ground below the at least one point. The plurality of waypoints may correspond to a path the vehicle is expected to travel.The method may further comprise: classifying each waypoint of the plurality of waypoints into at least one group of a plurality of groups based on a distance between the vehicle and a position of each waypoint of the plurality of waypoints on the ground; determining a representative point for each group of the plurality of groups based on a position of each classified waypoint in a group of the plurality of groups that corresponds to the representative point; determining a road profile including at least one of elevation information of the ground and contour information of the ground based on an interpolation between representative points of two adjacent groups of the plurality of groups; and outputting a signal associated with the autonomous driving controller of the vehicle based on the determined road profile.

[0026] Determining the plurality of waypoints may include: determining an object type corresponding to each of the at least one point representing the external environment of the vehicle; and determining the plurality of waypoints based on the object type and a position of the object.

[0027] The at least one point may be contained in the input data of an artificial neural network (ANN). Determining the object type may include determining the object type based on output data from the ANN.

[0028] The method may comprise: determining a confidence level of the representative point for each group of the plurality of groups based on at least one of the following: an object type corresponding to classified waypoints included in a group corresponding to the representative point, a set of the classified waypoints included in the group corresponding to the representative point, or an altitude of the classified waypoints included in the group corresponding to the representative point.

[0029] A first representative point corresponding to a first group that has more than a certain amount of classified waypoints may have a higher confidence level than a second representative point corresponding to a second group that has fewer than the certain amount of classified waypoints. A third representative point corresponding to a third group may have a higher confidence level than a fourth representative point corresponding to a fourth group. A maximum elevation value of classified waypoints in the third group may not be greater than an average elevation value of the classified waypoints contained in the third group by at least a certain amount. A maximum value of classified waypoints in the fourth group may be greater than an average elevation of the classified waypoints contained in the fourth group by at least the certain amount.

[0030] Classifying each point of the plurality of waypoints may include: classifying a first waypoint of the plurality of waypoints into a first group based on a first distance from a first position on the ground corresponding to the first waypoint to the vehicle satisfying a first distance range; and classifying a second waypoint of the plurality of waypoints into a second group based on a second distance from a second position on the ground corresponding to the second waypoint to the vehicle satisfying a second distance range different from the first distance range.

[0031] The method may further comprise: determining an expected trajectory of two front wheels with respect to a direction of travel based on a steering angle of the vehicle; and determining the path based on the expected trajectory.

[0032] Determining the representative point for each group of the plurality of groups may include determining the representative point based on at least one of the following: an average longitudinal position of one or more waypoints of the plurality of waypoints classified into a group corresponding to the representative point; and an average lateral position of the one or more waypoints classified into the group corresponding to the representative point; or an average elevation of the one or more waypoints classified into the group corresponding to the representative point.

[0033] The path can have a certain length.

[0034] Determining the representative point for each group of the plurality of groups may include: determining the representative point based on a set of classified waypoints included in the group corresponding to the representative point that is greater than a threshold set. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The above and other objects, features and advantages of the present disclosure will become more apparent from the following detailed description taken in conjunction with the accompanying drawings: Fig. 1 is a block diagram showing a configuration of an object recognition device according to an embodiment of the present disclosure; Fig. 2 shows an example of determining a road profile by a sensor (e.g., LIDAR) in an object detection device or an object detection method according to an embodiment of the present disclosure; Fig. 3 illustrates a flowchart of operations of an object detection device for identifying a confidence level and obtaining a road profile in the object detection device or an object detection method according to an embodiment of the present disclosure; Fig. 4 illustrates another flowchart of the operation of an object detection device for identifying a confidence level and obtaining a road profile in an object detection device or an object detection method according to an embodiment of the present disclosure; Fig. 5 shows an example of a path on which a host vehicle is to travel in an object recognition device or an object recognition method according to an embodiment of the present disclosure; Fig. 6 shows an example of a representative point identified from classified points in an object recognition device or method according to an embodiment of the present disclosure; Fig. 7 illustrates a flowchart of the operation of an object detection device for obtaining a road profile in an object detection device or an object detection method according to an embodiment of the present disclosure; Fig. 8 illustrates a flowchart of the operation of an object recognition device for assigning a confidence level to a representative point in an object recognition device or an object recognition method according to an embodiment of the present disclosure; Fig. 9 illustrates diagrams for deriving criteria for assigning a confidence level in an object recognition apparatus or method according to an embodiment of the present disclosure; Fig. 10 illustrates an example of a road profile according to an embodiment of the present disclosure; and Fig. 11 illustrates a computing system related to an object recognition device or method according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0036] Below, some embodiments of the present disclosure will be described in detail with reference to the exemplary drawings. When adding reference numerals to the components of each drawing, it should be noted that the identical or equivalent component is identified by the same number even if it is shown in other drawings. Furthermore, in describing the embodiment of the present disclosure, a detailed description of well-known features or functions is excluded in order not to unnecessarily obscure the essence of the present disclosure.

[0037] When describing the components of the embodiment according to the present disclosure, terms such as "first," "second," "A," "B," (a), (b), and the like may be used. These terms are used solely to distinguish one component from another, and the terms do not limit the type, sequence, or order of the individual components. Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure relates.Terms defined in a commonly used dictionary shall be construed to have the same meaning as the contextual meanings in the relevant field of art and shall not be construed to have an ideal or overly formal meaning unless they are clearly defined as such in the present application.

[0038] Furthermore, in the present disclosure, the terms "greater than" or "less than" may be used to indicate whether a particular condition is met or satisfied, but they are used only to provide examples and do not exclude "greater than or equal to" or "less than or equal to." A condition indicating "greater than or equal to" may be replaced with "greater than," a condition indicating "less than or equal to" may be replaced with "less than," and a condition indicating "greater than or equal to and less than" may be replaced with "greater than and less than or equal to." Furthermore, "A" to "B" means at least one of the elements from A (inclusive of A) to B (inclusive of B).

[0039] Hereinafter, embodiments of the present disclosure will be described with reference to the Fig. 1 to 11 are described in detail.

[0040] Fig. 1 is a block diagram showing a configuration of an object recognition device according to an embodiment of the present disclosure.

[0041] With reference to Fig. 1, an object detection device 101 may include a sensor (e.g., LIDAR) 103 and a processor 105.

[0042] The sensor (e.g., LIDAR) 103 and the processor 105 may be electronically and / or operably coupled to each other by an electronic component, such as a communication bus.

[0043] According to one embodiment, the combination of hardware parts may hereinafter mean a direct or indirect connection between the hardware parts, which is established in a wired or wireless manner, such that the first hardware of the hardware parts is controlled by the second hardware of the hardware parts. The type and / or number (e.g., quantity) of the hardware included in the object recognition device 101 is not limited to the Fig. 1. For example, the object recognition device 101 may only use some of the Fig. 1 hardware components shown.

[0044] According to one embodiment, the processor 105 of the object recognition device 101 may identify an external environment of a host vehicle based on the sensor (e.g., LIDAR) 103. For example, the processor 105 of the object recognition device 101 may obtain at least one point representing the external environment (e.g., ground, road, sidewalk, parking lot) from the sensor (e.g., LIDAR) 103.

[0045] According to one embodiment, the processor 105 of the object recognition device 101 may identify the type of object corresponding to each of the points contained in at least one point representing the external environment of the host vehicle. For example, an object may represent an external environment. For example, object types may include ground, sidewalk, road, and parking lot.

[0046] According to one embodiment, the processor 105 of the object recognition device 101 may determine the type of object corresponding to each of the points included in the output data of an artificial neural network (ANN) based on each of the points included in at least one point representing the external environment of the host vehicle included in the input data of the artificial neural network.

[0047] According to one embodiment, the processor 105 of the object recognition device 101 may identify a path (e.g., an expected trajectory) along which the two preceding wheels (e.g., two front wheels of a forward-moving vehicle or two rear wheels of a backward-moving vehicle) are expected to move (e.g., travel) with respect to the direction of travel (e.g., a direction of travel) based on the steering angle of the host vehicle, and identify a path along which the host vehicle is expected to move based on the path along which the two wheels are expected to move.

[0048] According to one embodiment, the processor 105 of the object recognition device 101 may identify a waypoint, which is a point included in the path along which the host vehicle is expected to travel and which represents the ground (e.g., terrain) beneath the at least one point, based on the type of object and the position of the object. For example, the ground (e.g., the ground) may include surfaces on which the host vehicle may travel, such as sidewalks, roads, and parking lots.

[0049] According to one embodiment, the processor 105 of the object recognition device 101 may classify the waypoint into at least one group according to the distance between the host vehicle and the ground corresponding to the waypoint.

[0050] According to one embodiment, the processor 105 of the object recognition device 101 may classify a first waypoint into a first group if the distance between the host vehicle and the ground corresponding to the first waypoint included in the waypoint satisfies a first distance range.

[0051] According to one embodiment, the distance between the host vehicle and the ground corresponding to the first waypoint may include a distance from the ground corresponding to the first waypoint to the center of the bumper of the host vehicle, but the embodiment of the present disclosure is not limited thereto. According to another embodiment, a point on the host vehicle serving as a reference for a distance from the first waypoint to the host vehicle may include a point other than the center of the bumper.

[0052] According to one embodiment, the processor 105 of the object recognition device 101 may classify a second waypoint into a second group instead of the first group based on the fact that the distance between the host vehicle and the ground corresponding to the second waypoint included in the waypoint does not satisfy the first distance range and satisfies a second distance range different from the first distance range.

[0053] According to one embodiment, the distance between the host vehicle and the ground corresponding to the second waypoint may include a distance from the ground corresponding to the second waypoint to the center of the bumper of the host vehicle, but the embodiment of the present disclosure is not limited thereto. According to another embodiment, a point on the host vehicle serving as a reference for a distance from the second waypoint to the host vehicle may include a point other than the center of the bumper.

[0054] According to one embodiment, the processor 105 of the object recognition device 101 may identify a representative point for each group based on the position of a classified point that is a waypoint classified into each of the groups included in at least one group.

[0055] For example, the longitudinal position of a representative point corresponding to a particular group may include the average value of the longitudinal positions of classified points included in the particular group. For example, the lateral position of a representative point corresponding to a particular group may include the average value of the lateral positions of classified points included in the particular group. For example, the elevation of a representative point corresponding to a particular group may include the average value of the elevations of classified points included in the particular group.

[0056] According to one embodiment, when the number (e.g., amount) of classified points included in a particular group is greater than a threshold number, the processor 105 of the object recognition device 101 may identify a representative point corresponding to the particular group according to the positions of the classified points included in the particular group.

[0057] If the number of classified points included in a specific group is not greater than the threshold number, the processor 105 of the object recognition device 101 cannot identify a representative point corresponding to the specific group. This is because the points are determined to be unreliable if the number of points is equal to or less than the threshold number.

[0058] According to one embodiment, the processor 105 of the object recognition device 101 may obtain a road profile representing at least one of the following information: ground elevation information for a path along which the host vehicle is expected to travel, or contour information (e.g., shape) of the ground for the path along which the host vehicle is expected to move, or any combination thereof, based on performing interpolation between representative points corresponding to two adjacent groups separated by a distance from the ground corresponding to the representative point to the host vehicle. For example, the road profile may represent elevation information of the path along which the host vehicle is expected to move.

[0059] Fig. 2 shows an example of the generation of a road profile by a sensor (e.g., LIDAR) in an object detection device or an object detection method according to an embodiment of the present disclosure.

[0060] With reference to Fig. 2, in a first situation 201, the ground level of a first section 203 on a path on which a carrier vehicle is expected to travel may be less than or equal to a certain height.

[0061] In a second situation 211, the ground height of a second section 213 of the path on which the carrier vehicle is expected to travel may be greater than a certain height.

[0062] According to one embodiment, in the first situation 201, the first portion 203 may represent a flat ground that does not include a speed bump, although a road surface marking indicating a speed bump is displayed.

[0063] A speed bump is a structure installed to prevent vehicles from overspeeding and improve traffic safety on roads or parking lots. It can be installed in a protruding shape on the road surface. Road surface markings indicating the speed bump can be painted on the speed bump. The road surface markings indicating the speed bump can mainly be expressed as white and yellow lines.

[0064] In the first situation 201, it may be difficult for the processor of an existing object detection device to determine the ground structure for the first section 203 using a camera because the marking of the speed bump and the actual ground structure do not match. Since the processor of the object detection device according to one embodiment determines the ground structure using a sensor (e.g., LIDAR), the processor of the object detection device can detect that a speed bump is not included in the first section 203. The processor of the object detection device according to one embodiment can detect that the height of the first section 203 is identical to the height of the road on which the host vehicle is traveling.

[0065] According to one embodiment, in the second situation 211, the second section 213 may not contain a pavement marking indicating a speed bump, but the ground including the speed bump may appear. In other words, the second section 213 may contain a speed bump whose color has been lost.

[0066] In the second situation 211, it may be difficult for the processor of an existing object detection device to detect the speed bump contained in the second section 213 through a camera because the marking of the ground and the actual structure of the ground do not match. Since the processor of the object detection device according to one embodiment determines the structure of the ground through a sensor (e.g., LIDAR), the processor of the object detection device can detect that a speed bump is contained in the second section 213. The processor of the object detection device according to one embodiment can detect that the height of the second section 213 is higher than the height of the road on which the host vehicle is traveling.

[0067] The processor of the object detection device according to one embodiment can improve driving stability by improving the accuracy of road profiles according to ground structures that differ from painted markings or road surface defects. Road surface defects may include raised obstacles, such as speed bumps, or embedded obstacles, such as potholes.

[0068] Fig. 3 illustrates a flowchart of the operation of an object detection device for identifying a confidence level and obtaining a road profile in the object detection device or an object detection method according to an embodiment of the present disclosure.

[0069] In the following, it is assumed that the processor 105 of the object recognition device 101 of Fig. 1 the process of Fig. 3. In addition, the description of Fig. 3 the operations described as being performed by the processor of the object recognition device are understood to be controlled by the processor 105 of the object recognition device 101.

[0070] With reference to Fig. 3, in a first operation 301, the processor of an object recognition device according to an embodiment may identify the type of object corresponding to a point and identify a path along which a host vehicle is expected to move.

[0071] According to one embodiment, the type of object corresponding to a point may include ground, sidewalks, roads, and parking lots.

[0072] According to one embodiment, the processor of the object recognition device can identify a path (e.g., an expected trajectory) along which the two leading wheels (e.g., two front wheels of a forward-moving vehicle or two rear wheels of a backward-moving vehicle) are expected to move (e.g., travel) with respect to the direction of travel (e.g., a direction of motion), based on the steering angle of the host vehicle. The processor of the object recognition device can identify the path along which the host vehicle is expected to move based on the path along which the two wheels are expected to move.

[0073] According to one embodiment, the processor of the object recognition device may identify a waypoint that is a point among points representing the ground and included in a path along which the host vehicle is expected to move.

[0074] In a second operation 303, the processor of the object recognition device according to one embodiment may identify a representative point of each group and a confidence level of the representative point according to information about classified points included in each group.

[0075] According to one embodiment, the processor of the object recognition device may classify waypoints into at least one group according to the distance from the ground corresponding to the waypoint to the host vehicle to identify the representative point and the confidence level of the representative point.

[0076] According to one embodiment, the processor of the object recognition device may identify a representative point for each group based on the position of a classified point that is a waypoint classified into each of the groups included in at least one group.

[0077] For example, the processor of the object recognition device may classify a classified point into at least one group according to a distance from the ground corresponding to the classified point to the host vehicle.

[0078] According to one embodiment, the processor of the object recognition device may identify a confidence level of the representative point corresponding to each group based on at least one of the following information: the type of object corresponding to classified points included in each group, the number of classified points included in each group, or the height of the classified points included in each group, or any combination thereof. A method for determining a confidence level is described below with reference to Fig. 9 described.

[0079] In a third operation 305, the processor of the object recognition device may obtain a road profile by interpolation according to one embodiment.

[0080] According to one embodiment, the processor of the object recognition device may obtain a road profile indicating at least one of the following information: ground elevation information for a path on which the host vehicle is expected to travel, or contour information (e.g., shape) of the ground for the path on which the host vehicle is expected to move, or any combination thereof, based on performing an interpolation between representative points corresponding to two adjacent groups separated by a distance from the ground corresponding to the representative points to the host vehicle.

[0081] Interpolation may refer to identifying a function value for a third variable that is between a first variable value and a second variable value based on a function value for the first variable value and a function value for the second variable value.

[0082] According to one embodiment, the processor of the object recognition device may estimate the height of the ground between the position of the ground corresponding to a first representative point and the position of the ground corresponding to a second representative point by interpolation.

[0083] Fig. 4 illustrates another flowchart of the operation of an object detection device for identifying a confidence level and obtaining a road profile in an object detection device or an object detection method according to an embodiment of the present disclosure.

[0084] In the following, it is assumed that the processor 105 of the object recognition device 101 of Fig. 1 the process of Fig. 4. In addition, the description of Fig. 4 the operations described as being performed by the processor of the object recognition device are understood to be controlled by the processor 105 of the object recognition device 101.

[0085] In relation to Fig. 4, according to one embodiment, the processor of the object recognition device may identify the type of object corresponding to a point in a first operation 401.

[0086] In a second operation 403, according to one embodiment, the processor of the object recognition device may identify a path a host vehicle is expected to travel based on a path two wheels are expected to travel. According to one embodiment, the first operation 401 may be performed before the second operation 403 or after the second operation 403 has been performed.

[0087] In a third operation 405, according to one embodiment, the processor of the object recognition device may generate a raster map based on a path the host vehicle is expected to travel. According to one embodiment, the raster map may include a plurality of rasters separated according to the distance from the ground corresponding to a point to the host vehicle. Each raster included in the plurality of rasters may correspond to each group.

[0088] In a fourth operation 407, the processor of the object recognition device may obtain a representative point for each group based on the raster map, according to one embodiment.

[0089] In a fifth operation 409, the processor of the object recognition device may identify the confidence level of the representative point according to one embodiment.

[0090] In a sixth operation 411, the processor of the object recognition device may obtain a road profile by interpolation according to one embodiment.

[0091] According to one embodiment, the road profile may represent at least one of the following information: ground elevation information for a path on which the host vehicle is expected to travel, or ground contour information (e.g., shape) for the path on which the host vehicle is expected to travel, or any combination thereof.

[0092] Fig. 5 shows an example of a path on which a host vehicle is expected to travel in an object recognition device or method according to an embodiment of the present disclosure.

[0093] With reference to Fig. 5, a first display 501 may include points representing an external environment. A second display 503 may include points representing an external environment that is different from the external environment included in the first display 501. The external environment may include roads, vehicles, and trees. Points representing a road may be included within points representing the ground.

[0094] A first sensor (e.g., LIDAR) display 511 may include points representing the ground and a path a host vehicle is expected to travel on a straight path. A second sensor (e.g., LIDAR) display 513 may include points representing the ground and a path a vehicle is expected to travel on a curved path.

[0095] According to one embodiment, a path identified based on the steering angle of the host vehicle may be displayed on the first sensor (e.g., LIDAR) display 511 when the steering wheel of the host vehicle is not operated.

[0096] According to one embodiment, a path identified based on the steering angle of the host vehicle may be displayed on the second sensor (e.g., LIDAR) display 513 when the steering wheel of the host vehicle is operated to the left with respect to the host vehicle.

[0097] Fig. 6 shows an example of a representative point identified from classified points in an object recognition apparatus or method according to an embodiment of the present disclosure.

[0098] With reference to Fig. 6, a first raster map 601 may include waypoints classified according to a distance between the host vehicle and the ground corresponding to the waypoints. The first raster map 601 may include a first preliminary raster 603, at least one raster 605, and a second preliminary raster 607. A second raster map 611 may include the same waypoints as the first raster map 601. The second raster map 611 may include representative points each corresponding to the rasters identified from the first raster map 601. A first diagram 621 may display representative points identified from the second raster map 611 according to elevation. A second diagram 623 may include interpolation points generated by interpolation between the representative points displayed in the first diagram 621.The interpolation points can represent ground elevation information for the path along which the host vehicle is expected to move.

[0099] According to one embodiment, the processor of the object recognition device may generate a raster map identified according to the path along which the host vehicle is expected to move. The processor of the object recognition device may map waypoints representing the ground and included in the path along which the host vehicle is expected to move onto a raster map.

[0100] The first preliminary grid 603 and the second preliminary grid 607 can be reserved for performing an interpolation. Due to the characteristics of a sensor (e.g., LIDAR), it may happen that a grid contained in at least one grid 605 does not contain a waypoint. In this case, the processor of the object detection device can save a preliminary grid to perform an interpolation. The size of the first preliminary grid 603 and the size of the second preliminary grid 607 can be set to a size that allows waypoints contained in at least one layer to be obtained.

[0101] According to one embodiment, the horizontal axis (e.g., l) of the first raster map 601, the horizontal axis (e.g., l) of the second raster map 611, the horizontal axis (e.g., l) of the first diagram 621, and the horizontal axis (e.g., l) of the second diagram 623 may represent a distance between the host vehicle and the ground corresponding to the grid. The vertical axis (e.g., y) of the first raster map 601 and the vertical axis (e.g., y) of the second raster map 611 may represent a distance between the host vehicle and a representative point or an interpolation point. The vertical axis of the first diagram 621 and the vertical axis of the second diagram 623 may represent the elevation of the ground corresponding to the representative point or the interpolation point.

[0102] According to one embodiment, in the first grid map 601, the horizontal length of at least one grid 605 may relate to the length of a path along which the host vehicle is expected to travel. The path along which the host vehicle is expected to travel may have a specific length.

[0103] According to one embodiment, the processor of the object recognition device may identify a representative point (e.g., a fixed point) in the second grid map 611 for each group corresponding to each grid based on the positions of classified points, based on the number of classified points included in each group being greater than a threshold number. This is because the points may be caused by noise if the number of classified points included in the grid is less than or equal to the threshold number.

[0104] The longitudinal position of a representative point corresponding to each group can be identified based on the average value of the longitudinal positions of the classified points included in each group. The lateral position of the representative point corresponding to each group can be identified based on the average value of the lateral positions of the classified points included in each group. The altitude of the representative point can be identified based on the average value of the altitudes of the classified points classified into each group.

[0105] According to one embodiment, the processor of the object recognition device may display the height of a point in the first graph 621 corresponding to a distance from the ground that corresponds to the representative point from the host vehicle. Referring to the first graph 621, it can be seen that the height of the ground increases with increasing distance from the host vehicle.

[0106] In the second graph 623, the processor of the object detection device can estimate height information on the ground that does not correspond to the representative points by performing interpolation between the representative points for each group. The interpolation may be performed because a classified point may not exist in the grid, as points may be lost due to the characteristics of the sensor (e.g., LIDAR), and the lateral resolution may be lower than the longitudinal resolution.

[0107] Fig. 7 shows a flowchart of the operation of an object detection device for obtaining a road profile in an object detection device or an object detection method according to an embodiment of the present disclosure.

[0108] In the following, it is assumed that the processor 105 of the object recognition device 101 of Fig. 1 the process of Fig. 7. Also, in the description of Fig. 7 the operations described as being performed by the processor of the object recognition device are understood to be controlled by the processor 105 of the object recognition device 101.

[0109] With reference to Fig. 7, according to one embodiment, in a first operation 701, the processor of the object recognition device may obtain at least one point representing an external environment of the host vehicle through a sensor (e.g., LIDAR).

[0110] In a second operation 703, the processor of the object recognition device according to one embodiment may identify a waypoint, which is a point representing the ground and is included in a path along which the host vehicle is expected to travel, from the at least one point.

[0111] In a third operation 705, according to one embodiment, the processor of the object recognition device may classify the waypoint into at least one group according to a distance between the host vehicle and the ground corresponding to the waypoint.

[0112] In a fourth operation 707, according to one embodiment, the processor of the object recognition device may identify a representative point for each group based on the location of a classified point that is a waypoint classified into each of the groups included in at least one group.

[0113] In a fifth operation 709, according to one embodiment, the processor of the object recognition device may perform interpolation between representative points corresponding to two adjacent groups separated according to a distance between the host vehicle and the ground corresponding to each of the representative points.

[0114] In a sixth operation 711, according to one embodiment, the processor of the object recognition device may obtain at least one of a road profile representing at least one of ground elevation information or ground contour information (e.g., shape), or any combination thereof. The ground elevation information may represent ground elevation information for a path along which the host vehicle is expected to travel. The ground contour (e.g., shape) information may represent ground contour (e.g., shape) information for the path along which the host vehicle is expected to travel.

[0115] Fig. 8 illustrates a flowchart of the operation of an object recognition device for assigning a confidence level to a representative point in an object recognition device or an object recognition method according to an embodiment of the present disclosure.

[0116] In the following, it is assumed that the processor 105 of the object recognition device 101 of Fig. 1 the process of Fig. 8. In addition, the description of Fig. 8, the operations described as being performed by the processor of the object recognition device are understood to be controlled by the processor 105 of the object recognition device 101.

[0117] With reference to Fig. 8, according to one embodiment, the processor of the object recognition device may identify a confidence level of a representative point corresponding to each group based on at least one of the following: the type of an object corresponding to classified points included in each group, the number of classified points included in each group, or the height of classified points included in each group, or any combination thereof.

[0118] The processor of the object detection device according to one embodiment may obtain a road profile based on the classified points obtained via the sensor (e.g., LIDAR) and assign a confidence level to the classified points included in each group based on the road profile. The processor of the object detection device according to one embodiment may assign a confidence level to a classified point when the confidence level is classified into a certain number of levels (e.g., five levels). For example, a confidence level in the absence of a road surface defect or obstacle may be greater than a confidence level in the presence of a road surface defect or obstacle on the ground. For example, a confidence level (e.g.,about 15 points) when the height of the classified points in the group is evenly distributed and the ground is represented by all classified points in the group, it may be greater than a confidence level (e.g. about 0 points) when the height of the classified points in the group is unevenly distributed and classified points representing a stationary object (e.g. a building) are included in the group.

[0119] In a first operation 801, according to one embodiment, the processor of the object recognition device may determine whether only points representing the ground are identified. If only points representing the ground are identified, the processor of the object recognition device may perform a second operation 803. If only points representing the ground are not identified, the processor of the object recognition device may perform a third operation 805.

[0120] According to one embodiment, the points representing the ground may include points representing a roadway, points representing a sidewalk, points representing a parking lot, and points corresponding to a part of the ground.

[0121] In a third operation 805, the processor of the object recognition device may determine whether the points representing the ground are identified. If the points representing the ground are identified, the processor of the object recognition device may perform a fourth operation 807. If the points representing the ground are not identified, the processor of the object recognition device may perform a fifth operation 809.

[0122] According to one embodiment, the confidence level (e.g., a confidence score) of a representative point corresponding to a particular group when the number of classified points included in the particular group is greater than a certain number may be identified as greater than the confidence level of a representative point corresponding to the particular group when the number of classified points included in the particular group is less than or equal to the certain number. In other words, the higher the confidence level can be, the more (i.e., a higher number) of classified points are included in the group.

[0123] In the fifth operation 809, the processor may assign a confidence level of zero to the object recognition device according to one embodiment.

[0124] In the fourth operation 807, according to one embodiment, the processor of the object recognition device may identify whether the ratio of the number of points representing the ground to the total number of points is greater than a specified ratio. If the ratio of the number of points representing the ground to the total number of points is greater than the specified ratio, the processor of the object recognition device may perform a sixth operation 817. If the ratio of the number of points representing the ground to the total number of points is less than or equal to the specified ratio, the processor of the object recognition device may perform a seventh operation 819.

[0125] According to one embodiment, the processor of the object recognition device can recognize that the confidence level of the representative point corresponding to the specific group is smaller than a certain difference when a value obtained by subtracting the average value of the height represented by the classified points in the specific group from the maximum value of the height represented by the classified points in the specific group is greater than a certain difference. In other words, the lower the confidence level of a representative point can be, the greater the difference between the maximum value of the height and the average value of the height.

[0126] In the seventh operation 819, the processor may assign a confidence level of 3 to the object recognition device according to one embodiment.

[0127] In the sixth operation 817, according to one embodiment, the processor of the object recognition device may identify whether a value obtained by subtracting the average value of the height of the classified points in the specific group from the maximum value of the height of the classified points in the specific group is greater than the specified difference. If the value obtained by subtracting the average value of the height of the classified points in the specific group from the maximum value of the height of the classified points in the specific group is less than or equal to the specified difference, the processor of the object recognition device may perform an eighth operation.When the value obtained by subtracting the average value of the height of the classified points in the specific group from the maximum value of the height of the classified points in the specific group is greater than the specified difference, the processor of the object recognition device may execute the seventh operation 819.

[0128] In the eighth operation 821, the processor may assign a confidence level of 7 to the object recognition device according to one embodiment.

[0129] In the second operation 803, according to one embodiment, the processor of the object recognition device may identify whether the number of points is greater than a certain number. If the number of points is greater than the certain number, the processor of the object recognition device may perform a ninth operation 811. If the number of points is less than or equal to the certain number, the processor of the object recognition device may perform a tenth operation 813.

[0130] In the tenth operation 813, the processor may assign a confidence level of 11 to the object recognition device according to one embodiment.

[0131] In the ninth operation 811, according to one embodiment, the processor of the object recognition device may identify whether a ratio of the number of points representing roads to the total number of points is greater than a specified ratio. If the ratio of the number of points representing roads to the total number of points is greater than the specified ratio, the processor of the object recognition device may perform an eleventh operation 815. If the ratio of the number of points representing roads to the total number of points is less than or equal to the specified ratio, the processor of the object recognition device may perform the tenth operation 813.

[0132] In the eleventh operation 815, the processor may assign a confidence level of 15 to the object recognition device according to one embodiment.

[0133] Fig. 9 illustrates diagrams for deriving criteria for assigning a confidence level in an object recognition apparatus or method according to an embodiment of the present disclosure.

[0134] With reference to Fig. 9, a first graph 901 may display the number of groups based on a value obtained by subtracting an average height value represented by classified points in a group from the maximum height value represented by the classified points in the group. The classified points represented in the first graph 901 may be obtained in accordance with a flat ground whose height is within a certain range.

[0135] A second diagram 911 may display the number of groups corresponding to the number of classified points representing the ground included in the group. The classified points representing the second diagram 911 may display points obtained in accordance with a curved ground whose height is outside the specified range.

[0136] According to one embodiment, in the first diagram 901, in the case of a group according to classified points included in correspondence with the flat ground whose height is within the specified range, the number of groups having a value obtained by subtracting the average value of the height in the group from the maximum value of the height in the group may decrease rapidly after a specified difference (e.g., about 0.05 meters).

[0137] Therefore, the processor of the object recognition device can identify whether a classified point included in the group corresponds to the flat ground based on the value obtained by subtracting the average height value from the maximum height value in the group and the specified difference. For example, the sixth process 817 of Fig. 8 reference may be made.

[0138] In other words, the processor of the object recognition device according to one embodiment can identify a confidence level (e.g., about 3) of a representative point corresponding to a specific group when the value obtained by subtracting the average value of the height represented by classified points included in the specific group from the maximum value of the height represented by the classified points in the specific group is greater than a certain difference (e.g., about 0.05 meters), as less than a confidence level (e.g., about 7) of the representative point corresponding to the specific group when the value obtained by subtracting the average value from the maximum value is less than or equal to the certain difference.

[0139] According to one embodiment, in the second diagram 911, the number of groups corresponding to the number of classified points included in groups representing the ground may decrease rapidly after a certain number (e.g., 8). The classified points representing the second diagram 911 may be obtained in accordance with a curved ground.

[0140] The processor of the object recognition device may determine whether points included in a group correspond to a curved ground based on the number of classified points representing the ground included in the group and the determined number. For example, the second operation 803 of Fig. 8 reference may be made.

[0141] In other words, a confidence level (e.g., about 15) of a representative point corresponding to the specific group when the number of classified points included in the specific group is greater than the certain number (e.g., about 8) can be considered greater than a confidence level (e.g., about 11) of a representative point corresponding to the specific group when the number of classified points included in the specific group is less than or equal to the certain number.

[0142] Fig. 10 shows an example of a road profile according to an embodiment of the present disclosure.

[0143] With reference to Fig. 10, a first display 1001 may display an indication identified via a sensor (e.g., LIDAR) when a speed bump is included in a path a host vehicle is expected to travel. A first image 1003 may display an indication identified via a camera when a speed bump is included in the path the host vehicle is expected to travel. The path the host vehicle is expected to travel may include a first road profile 1005 for a predicted left wheel path and a second road profile 1007 for a predicted right wheel path.

[0144] According to one embodiment, a processor of the object detection device may identify a portion corresponding to the speed bump based on the first road profile 1005 and the second road profile 1007.

[0145] A second display 1011 may display an indication identified via a sensor (e.g., LIDAR) when a ramp is included in the path the host vehicle is expected to travel. A second image 1013 may display an indication identified via a camera when a ramp is included in the path the host vehicle is expected to travel. The path the host vehicle is expected to travel may include a third road profile 1015 for a predicted left wheel path and a fourth road profile 1017 for a predicted right wheel path.

[0146] According to one embodiment, a processor of the object recognition device may identify a section corresponding to the ramp based on the third road profile 1015 and the fourth road file 1017.

[0147] Fig. 11 illustrates a computing system associated with an object recognition apparatus or method according to an embodiment of the present disclosure.

[0148] With reference to Fig. 11, a computing system 1100 may include at least a processor 1110, a memory 1130, a user interface input device 1140, a user interface output device 1150, a memory 1160, and a network interface 1170 interconnected via a bus 1120.

[0149] Processor 1110 may be a central processing unit (CPU) or a semiconductor device that processes instructions stored in memory 1130 and / or storage 1160. Memory 1130 and storage 1160 may include various types of volatile or non-volatile storage media. For example, memory 1130 may include a ROM (Read Only Memory) 1131 and a RAM (Random Access Memory) 1132.

[0150] Thus, the operations of the method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware or a software module executed by processor 1110, or a combination thereof. The software module may be located on a storage medium (i.e., memory 1130 and / or storage 1160), such as RAM, flash memory, ROM, EPROM, EEPROM, register, hard disk, removable disk, and CD-ROM.

[0151] The example storage medium may be coupled to processor 1110, and processor 1110 may read information from the storage medium and record information to the storage medium. Alternatively, the storage medium may be integrated with processor 1110. The processor and storage medium may be located within an application-specific integrated circuit (ASIC). The ASIC may be located within a user terminal. Alternatively, the processor and storage medium may be located as separate components within the user terminal.

[0152] The above description is merely illustrative of the technical idea of the present disclosure, and various modifications and variations may be made without departing from the essential features of the present disclosure by those skilled in the art to which the present disclosure relates.

[0153] Accordingly, the embodiment disclosed in the present disclosure is not intended to limit the technical idea of the present disclosure, but to describe the present disclosure, and the scope of the technical idea of the present disclosure is not limited by the embodiment. The scope of the present disclosure should be interpreted by the following claims, and all technical ideas within the scope that correspond to them should be considered to be included in the scope of the present disclosure.

[0154] The present technology can use a sensor (e.g. LIDAR) to determine ground elevation information for a path on which a carrier vehicle is expected to travel.

[0155] Furthermore, the present technology can improve the accuracy of elevation information by using a sensor (e.g., LIDAR) to determine ground elevation information for a path on which a host vehicle is expected to travel.

[0156] Furthermore, the present technology can improve driving stability by improving the accuracy of ground elevation information for a path on which a host vehicle is expected to travel, even if there is a defect in the road surface.

[0157] Furthermore, the present technology can enhance the driving experience by improving the accuracy of ground elevation information for a path on which a host vehicle is expected to travel.

[0158] Furthermore, the present technology can obtain ground elevation information that is robust to noise.

[0159] Furthermore, the present technology can identify a degree of confidence of points corresponding to the ground.

[0160] In addition, various effects may be provided which are understood directly or indirectly through the disclosure.

[0161] Although the present disclosure has been described with reference to exemplary embodiments and the accompanying drawings, the present disclosure is not limited thereto, but may be variously modified and changed by those skilled in the art to which the present disclosure relates without departing from the spirit and scope of the present disclosure as claimed in the following claims. QUOTES CONTAINED IN THE DESCRIPTION

[0000] This list of documents submitted by the applicant was generated automatically and is included solely for the convenience of the reader. This list is not part of the German patent or utility model application. The DPMA assumes no liability for any errors or omissions. Cited patent literature

[0000] KR 10-2024-0001034

[0001]

Claims

[1] a device comprising: a sensor; and a processor that is configured: to detect at least one point representing an external environment of a vehicle via the sensor; to determine under the at least one point a plurality of waypoints representing positions on a ground, wherein the plurality of waypoints correspond to a path along which the vehicle is expected to move; classify each waypoint of the plurality of waypoints into at least one group of a plurality of groups based on a distance between the vehicle and a position of each waypoint of the plurality of waypoints on the ground; determine a representative point for each group of the plurality of groups based on a position of each classified waypoint in a group of the plurality of groups corresponding to the representative point; to determine a road profile based on an interpolation between representative points of two adjacent groups of the plurality of groups, which includes at least one of elevation information of the ground or Contour information of the ground; and output a signal based on the determined road profile that is linked to the autonomous driving control of the vehicle. [2] The apparatus of claim 1, wherein the processor is configured to determine the plurality of waypoints by: Determining an object type corresponding to each of the at least one points representing the external environment of the vehicle; and Determining the plurality of waypoints based on the object type and a position of the object. [3] The apparatus of claim 2, wherein the at least one point is contained in input data of an artificial neural network (ANN), and wherein the processor is configured to determine the object type by: Determine the object type based on ANN output data. [4] The apparatus of claim 1, wherein the processor is further configured to determine a confidence level of the representative point for each group of the plurality of groups based on at least one of: an object type corresponding to classified waypoints included in a group corresponding to the representative point, a set of the classified waypoints included in the group corresponding to the representative point, or an altitude of the classified waypoints included in the group corresponding to the representative point. [5] The apparatus of claim 1, wherein a first representative point corresponding to a first group having more than a certain amount of classified waypoints has a higher degree of confidence than a second representative point corresponding to a second group having fewer than the certain amount of classified waypoints, and wherein a third representative point corresponding to a third group has a higher degree of confidence than a fourth representative point corresponding to a fourth group, wherein a maximum altitude value of classified waypoints in the third group is not greater by at least a certain amount than an average altitude value of the classified waypoints included in the third group is greater by at least a certain amount,and wherein a maximum value of classified waypoints in the fourth group is greater than an average height of the classified waypoints included in the fourth group by at least the determined amount. [6] The apparatus of claim 1, wherein the processor is configured to classify each point of the plurality of waypoints by: Classifying a first waypoint of the plurality of waypoints into a first group based on a first distance from a first position on the ground, corresponding to the first waypoint to the vehicle that satisfies a first distance range; and Classifying a second waypoint of the plurality of waypoints into a second group based on a second distance from a second position on the ground, corresponding to the second waypoint to the vehicle that satisfies a second distance range that is different from the first distance range. [7] The apparatus of claim 1, wherein the processor is further configured to determine an expected trajectory of two front wheels with respect to a direction of travel based on a steering angle of the vehicle; and to determine the path based on the expected trajectory. [8] The apparatus of claim 1, wherein the processor is configured to determine the representative point for each group of the plurality of groups by: determines the representative point on the basis of at least one of the following: an average longitudinal position of one or more waypoints of the plurality of waypoints classified into a group corresponding to the representative point; and an average transverse position of the one or more waypoints classified in the group corresponding to the representative point, or an average altitude of the one or more waypoints classified in the group corresponding to the representative point. [9] Device according to claim 1, wherein the path has a certain length. [10] The apparatus of claim 1, wherein the processor is configured to determine the representative point for each group of the plurality of groups by determining the representative point based on a set of classified waypoints included in the group corresponding to the representative point that is greater than a threshold set. [11] Procedure comprising: Obtaining at least one point representing an external environment of a vehicle via a sensor; Determining a plurality of waypoints representing positions on a ground below the at least one point, the plurality of waypoints corresponding to a path along which the vehicle is expected to move; Classifying each waypoint of the plurality of waypoints into at least one group of a plurality of groups based on a distance between the vehicle and a position of each waypoint of the plurality of waypoints on the ground; Determining a representative point for each group of the plurality of groups based on a position of each classified waypoint in a group of the plurality of groups corresponding to the representative point; Determining a road profile based on an interpolation between representative points of two adjacent groups of the plurality of groups, wherein the road profile includes at least one of ground elevation information or ground contour information; and outputting a signal associated with the autonomous driving controller of the vehicle based on the determined road profile. [12] The method of claim 11, wherein determining the plurality of waypoints comprises: Determining an object type corresponding to each of the at least one point representing the external environment of the vehicle; and Determining the plurality of waypoints based on the object type and a position of the object. [13] The method of claim 12, wherein the at least one point is included in the input data of an artificial neural network (ANN), and wherein determining the object type comprises: Determine the object type based on ANN output data. [14] The method of claim 11, further comprising: Determining a confidence level of the representative point for each group of the plurality of groups based on at least one of: an object type corresponding to classified waypoints included in a group corresponding to the representative point, a set of the classified waypoints included in the group corresponding to the representative point, or an altitude of the classified waypoints included in the group corresponding to the representative point. [15] The method of claim 11, wherein a first representative point corresponding to a first group having more than a certain number of classified waypoints has a higher degree of confidence than a second representative point corresponding to a second group having fewer than the certain number of classified waypoints, and wherein a third representative point corresponding to a third group has a higher degree of confidence than a fourth representative point corresponding to a fourth group, wherein a maximum altitude value of classified waypoints in the third group is not greater by at least a certain amount than an average altitude value of the classified waypoints included in the third group is greater by at least a certain amount,and wherein a maximum value of classified waypoints in the fourth group is at least the specified amount greater than an average altitude of the classified waypoints included in the fourth group. [16] The method of claim 11, wherein classifying each point of the plurality of waypoints comprises: Classifying a first waypoint of the plurality of waypoints into a first group based on a first distance from a first position on the ground corresponding to the first waypoint to the vehicle satisfying a first distance range; and Classifying a second waypoint of the plurality of waypoints into a second group based on a second distance from a second position on the ground corresponding to the second waypoint to the vehicle satisfying a second distance range different from the first distance range. [17] The method of claim 11, further comprising: Determining an expected trajectory of two front wheels with respect to a direction of travel based on a steering angle of the vehicle; and Determine the path based on the expected trajectory. [18] The method of claim 11, wherein determining the representative point for each group of the plurality of groups comprises: Determining the representative point based on at least one of: an average longitudinal position of one or more waypoints of the plurality of waypoints classified into a group corresponding to the representative point; and an average transverse position of the one or more waypoints classified in the group corresponding to the representative point, or an average altitude of the one or more waypoints classified in the group corresponding to the representative point. [19] The method of claim 11, wherein the path has a certain length. [20] The method of claim 11, wherein determining the representative point for each group of the plurality of groups comprises: Determining the representative point based on a set of classified waypoints included in the group corresponding to the representative point that is greater than a threshold set.

Images