DEVICE AND METHOD FOR DETECTING OBJECTS

Abstract

In an object detection device and an object detection method, the object detection device includes a LiDAR and a processor. The processor can detect a first point, a second point, a third point, and a fourth point; detect a first outer point and a second outer point; detect an angle between a line segment connecting the first outer point and the LiDAR and a line segment connecting the second outer point and the LiDAR; detect as an occluded object an object that is one of the first object and the second object when the angle is less than or equal to a threshold angle; and detect an object different from the object detected as an occluded object among the first object and the second object as an object that occludes the occluded object.

Description

BACKGROUND OF THE PRESENT DISCLOSURE Scope of the present disclosure

[0001] The present disclosure relates to an apparatus and method for object recognition, and more particularly to a technique for recognizing or determining properties of an object represented by a point cloud obtained by light detection and ranging (LiDAR). Description of the state of the art

[0002] In order for an autonomous vehicle or a vehicle with enabled driver assistance devices to adapt its path and avoid obstacles with minimal driver intervention, technology to sense the environment and distinguish obstacles is required.

[0003] A vehicle can obtain data from a Light Detection and Ranging (LiDAR) system that indicates the position of an object in the vehicle's surroundings. A distance from a LiDAR to an object can be determined by the interval between the time the laser is emitted by the LiDAR and the time the laser reflected from the object is received. A vehicle can determine the location of a point external to the object in a space where the vehicle is located based on the angle of the emitted laser and the distance to the object.

[0004] The autonomous vehicle or the vehicle with the driver assistance device activated can recognize the information of an object represented by the points based on the obtained position information of obtained points.

[0005] The information contained in this Background of the present disclosure is provided merely to facilitate understanding of the general background of the present disclosure and should not be construed as acknowledgment or indication that this information comprises prior art already known to those skilled in the art. SHORT SUMMARY

[0006] Various embodiments of the present disclosure are directed to providing an apparatus and method for object detection that can identify or detect whether an object represented by a point cloud is an object that occludes another object or an object that is occluded by another object.

[0007] Various aspects of the present disclosure are directed to providing an apparatus and method for object recognition to improve the accuracy of determining whether an object represented by a point cloud is an object occluding another object or an object occluded by another object by comparing reliability values ​​of a plurality of objects represented by a point cloud.

[0008] Various aspects of the present disclosure are directed to providing an apparatus and method for object detection to improve the accuracy of determining whether an object represented by a point cloud is an object occluding another object or an object occluded by another object by comparing distances from a LiDAR to exterior points of an object.

[0009] 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 a person skilled in the art to which the present disclosure relates from the following description.

[0010] According to one embodiment of the present disclosure, an object detection device may include a LiDAR and a processor.

[0011] According to an embodiment of the present disclosure, the processor may detect a first point that is a leftmost point, with respect to a host vehicle, in a point cloud obtained by the LiDAR and representing a first object, a second point that is a rightmost point, with respect to the host vehicle, in the point cloud representing the first object, a third point that is a leftmost point, with respect to the host vehicle, in a point cloud representing a second object, and a fourth point that is a rightmost point, with respect to the host vehicle, in the point cloud representing the second object, a first outer point that is closer to the second object, which is one of the first point and the second point, and a second outer point that is closer to the first object, which is one of the third point and the fourth point,detect an angle between a line segment connecting the first external point and the LiDAR and a line segment connecting the second external point and the LiDAR on the basis that the first external point and the second external point do not overlap each other, detect as an occluded object an object that is one of the first object and the second object, that corresponds to one of the first external point and the second external point, that forms a larger distance than a distance between the first external point and the LiDAR and a distance between the second external point and the LiDAR, if the angle is less than or equal to a threshold angle, and detect an object that is different from the object detected as the occluded object among the first object and the second object as an object that occludes the occluded object.

[0012] According to an embodiment of the present disclosure, the processor may assign a reliability to the first object and assign a reliability with a value different from the reliability assigned to the first object according to a distance between a straight line connecting the first point and the second point and the LiDAR and a distance between a straight line connecting the third point and the fourth point and the LiDAR, based on determining that the first external point and the second external point overlap each other. The reliability assigned to the first object and the reliability assigned to the second object may indicate whether a corresponding object is an object that occludes another object.

[0013] According to an embodiment of the present disclosure, the processor may identify a point cloud representing at least one of the first object and the second object identified in a plane formed by a first axis and a second axis among the first axis, the second axis, and a third axis, and detect whether the first external point and the second external point overlap each other based on determining that an azimuth angle of the first external point with respect to an origin corresponding to the LiDAR and the first axis is included in a range between an azimuth angle of the third point with respect to the origin and the first axis and an azimuth angle of the fourth point with respect to the origin and the first axis.

[0014] According to an embodiment of the present disclosure, the processor may detect a straight line passing through the first point and the second point according to coordinates of the first point and coordinates of the second point based on determining that the first outer point and the second outer point overlap each other, assign to the second object a reliability as large as a number of the third points or the fourth points included in an area to which the LiDAR belongs among two regions separated by the straight line, detect a straight line passing through the third point and the fourth point according to coordinates of the third point and coordinates of the fourth point, assign to the first object a reliability with a different value from the reliability assigned to the second object, which is as large as a number of the first points or the second points included in an area,to which the LiDAR belongs are encompassed by two areas separated by the straight line passing through the third point and the fourth point, and detect an object with a greater reliability value than an object obscuring another object by comparing a reliability value of the first object and a reliability value of the second object.

[0015] According to an embodiment of the present disclosure, the processor may recognize a first function, which is a function of a straight line passing through the first point and the second point, according to coordinates of the first point and coordinates of the second point based on determining that the first external point and the second external point overlap each other, assign to the second object a reliability as large as the number of the same signs as a sign of a value obtained by substituting coordinates of an origin corresponding to the LiDAR into the first function, a sign of a value obtained by substituting coordinates of the third point into the first function, and a sign of a value obtained by substituting coordinates of the fourth point into the first function, a second function,which is a function of a straight line passing through the third point and the fourth point, detect the first object according to the coordinates of the third point and the coordinates of the fourth point, assign the first object a reliability equal to the number of signs equal to the sign of a value obtained by substituting the coordinates of the origin corresponding to the LiDAR into the second function, the sign of a value obtained by substituting the coordinates of the first point into the second function, and the sign of a value obtained by substituting the coordinates of the second point into the second function, and detect an object with a greater reliability value than an object occluding another object by comparing the reliability value of the first object and the reliability value of the second object.

[0016] According to an embodiment of the present disclosure, the processor may detect a fan-shaped region having a point cloud included in a particular layer and representing the first object located on the leftmost with respect to the host vehicle and a point cloud included in the particular layer and representing the second object located on the rightmost with respect to the host vehicle, the fan-shaped region including a minimum central angle with respect to an origin corresponding to the LiDAR, and expand a region of the fan-shaped region by increasing the central angle of the fan-shaped region to include at least one point located outside the fan-shaped region based on determining that the at least one point of a point cloud included in a plurality of layers including the particular layer and representing the first object,and a point cloud included in the plurality of layers including the particular layer and representing the second object, located outside the fan-shaped area.

[0017] According to an embodiment of the present disclosure, the processor may detect a fan-shaped region having a point cloud representing the first object located at the far left of the host vehicle and a point cloud representing the second object located at the far right of the host vehicle, including a minimum center angle relative to an origin corresponding to the lidar, detect a fifth point located at the far left of the host vehicle in a point cloud representing a third object and a sixth point located at the far right of the host vehicle in a point cloud representing the third object, a left angle between a line segment representing a left boundary of the fan-shaped region and a line segment connecting the fifth point and the lidar, or a right angle between a line segment,representing a right boundary of the fan-shaped area, and a line segment connecting the sixth point and the LiDAR, and, based on the left angle or the right angle being less than or equal to a predetermined angle, detect the third object as being located at the left boundary or the right boundary.

[0018] According to an embodiment of the present disclosure, the processor may detect a point cloud representing the first object among the points included in a plurality of layers and detect a point cloud representing the second object among the points included in the plurality of layers.

[0019] According to an embodiment of the present disclosure, the processor may detect the first outer point and the second outer point based on an angle between a line segment connecting the first point and the LiDAR and a line segment connecting the third point and the LiDAR, an angle between the line segment connecting the first point and the LiDAR and a line segment connecting the fourth point and the LiDAR, an angle between a line segment connecting the second point and the LiDAR and the line segment connecting the third point and the LiDAR, and an angle between the line segment connecting the second point and the LiDAR and the line segment connecting the fourth point and the LiDAR.

[0020] According to an embodiment of the present disclosure, the processor may detect a fourth object occluded by at least one object and iteratively detect a fifth object occluded by the fourth object based on a table representing the occluded object and the occluding object and the at least one object located at the left or right boundary.

[0021] According to one aspect of the present disclosure, an object detection method includes identifying a first point that is a leftmost point with respect to a host vehicle in a point cloud obtained by a LiDAR and representing a first object, a second point that is a rightmost point with respect to the host vehicle in the point cloud representing the first object, a third point that is a leftmost point with respect to the host vehicle in a point cloud representing a second object, and a fourth point that is a rightmost point with respect to the host vehicle in the point cloud representing the second object, detecting a first outer point that is closer to the second object, which is one of the first point and the second point, and a second outer point that is closer to the first object,which is one of the third point and the fourth point, detecting an angle between a line segment connecting the first outer point and the LiDAR and a line segment connecting the second outer point and the LiDAR based on determining that the first outer point and the second outer point do not overlap each other, detecting an object that is one of the first object and the second object as an occluded object corresponding to one of the first outer point and the second outer point that forms a larger distance among a distance between the first outer point and the LiDAR and a distance between the second outer point and the LiDAR when the angle is less than or equal to a threshold angle, and detecting an object that is different from the object detected as an occluded object among the first object and the second object as an object that occludes the occluded object.

[0022] According to an embodiment of the present disclosure, the object detection method may further include assigning a reliability to the first object and assigning a reliability to the second object with a value different from the reliability assigned to the first object, according to a distance between a straight line connecting the first point and the second point and the LiDAR and a distance between a straight line connecting the third point and the fourth point and the LiDAR, based on determining that the first outer point and the second outer point overlap each other. The reliability assigned to the first object and the reliability assigned to the second object may indicate whether a corresponding object is an object that occludes another object.

[0023] According to an embodiment of the present disclosure, the object detection method may further include detecting a point cloud representing at least one of the first object and the second object detected in a plane formed by a first axis and a second axis among the first axis, the second axis, and a third axis, and detecting whether the first outer point and the second outer point overlap each other based on determining that an azimuth angle of the first outer point with respect to an origin corresponding to the LiDAR and the first axis is included in a range between an azimuth angle of the third point with respect to the origin and the first axis and an azimuth angle of the fourth point with respect to the origin and the first axis.

[0024] According to an embodiment of the present disclosure, the object detection method may further include detecting a straight line passing through the first point and the second point according to coordinates of the first point and coordinates of the second point based on determining that the first outer point and the second outer point overlap each other, assigning a reliability to the second object equal to a number of the third points or the fourth points included in an area to which the LiDAR belongs among two areas separated by the straight line, detecting a straight line passing through the third point and the fourth point according to coordinates of the third point and coordinates of the fourth point, assigning a reliability to the first object with a value different from the reliability equal to a number of the first points or the second points,which are included in an area to which the LiDAR belongs, among two areas separated by the straight line passing through the third point and the fourth point, and detecting an object with a greater reliability value than an object occluding another object by comparing a reliability value of the first object and a reliability value of the second object.

[0025] According to an embodiment of the present disclosure, the object detection method may further include detecting a first function that is a function of a straight line passing through the first point and the second point according to coordinates of the first point and coordinates of the second point based on determining that the first outer point and the second outer point overlap each other, assigning to the second object a reliability equal to a number of signs equal to a sign of a value obtained by substituting coordinates of an origin corresponding to the LiDAR into the first function, a sign of a value obtained by substituting coordinates of the third point into the first function, and a sign of a value obtained by substituting coordinates of the fourth point into the first function, detecting a second function,which is a function of a straight line passing through the third point and the fourth point, according to the coordinates of the third point and the coordinates of the fourth point, assigning a reliability to the first object equal to a number of signs equal to a sign of a value obtained by substituting the coordinates of the origin corresponding to the LiDAR into the second function, a sign of a value obtained by substituting the coordinates of the first point into the second function, and a sign of a value obtained by substituting the coordinates of the second point into the second function, and detecting an object with a greater reliability value than an object occluding another object by comparing a reliability value of the first object and a reliability value of the second object.

[0026] According to an embodiment of the present disclosure, the object detection method may further comprise detecting a fan-shaped region having a point cloud included in a particular layer and representing the first object located on the leftmost with respect to the host vehicle and a point cloud included in the particular layer and representing the second object located on the rightmost with respect to the host vehicle, the fan-shaped region including a minimum central angle with respect to an origin corresponding to the LiDAR, and expanding a region of the fan-shaped region by increasing the central angle of the fan-shaped region to include at least one point located outside the fan-shaped region based on determining that the at least one point of a point cloud,which is comprised in a plurality of layers including the specific layer and represents the first object, and a point cloud which is comprised in the plurality of layers including the specific layer and represents the second object, is located outside the fan-shaped area.

[0027] According to an embodiment of the present disclosure, the method of the object recognition device may further comprise detecting a fan-shaped region having a point cloud representing the first object located on the far left with respect to the host vehicle and a point cloud representing the second object located on the far right with respect to the host vehicle, with a minimum center angle with respect to an origin corresponding to the LiDAR, detecting a fifth point located on the far left with respect to the host vehicle in a point cloud representing a third object and a sixth point located on the far right with respect to the host vehicle in a point cloud representing the third object, detecting a left angle between a line segment representing a left boundary of the fan-shaped region and a line segment connecting the fifth point and the LiDAR,or a right angle between a line segment representing a right boundary of the fan-shaped region and a line segment connecting the sixth point and the LiDAR, and detecting the third object as being on the left boundary or as being on the right boundary based on the left angle or the right angle being less than or equal to a predetermined angle.

[0028] According to an embodiment of the present disclosure, detecting the first point, which is the leftmost point with respect to the host vehicle in the point cloud obtained by the LiDAR and representing the first object, the second point, which is the rightmost point with respect to the host vehicle in the point cloud representing the first object, the third point, which is the leftmost point with respect to the host vehicle in the point cloud representing the second object, and the fourth point, which is the rightmost point with respect to the host vehicle in the point cloud representing the second object, may include detecting a point cloud representing the first object among points included in a plurality of layers and detecting a point cloud representing the second object among points included in the plurality of layers.

[0029] According to an embodiment of the present disclosure, detecting the first outer point that is closer to the second object, which is one of the first point and the second point, and the second outer point that is closer to the first object, which is one of the third point and the fourth point, may detect the first outer point and the second outer point based on an angle between a line segment connecting the first point and the LiDAR and a line segment connecting the third point and the LiDAR, an angle between the line segment connecting the first point and the LiDAR and a line segment connecting the fourth point and the LiDAR, an angle between a line segment connecting the second point and the LiDAR and the line segment connecting the third point and the LiDAR, and an angle between the line segment connecting the second point and the LiDAR,and the line segment connecting the fourth point and the LiDAR.

[0030] According to an embodiment of the present disclosure, the method of the object recognition device may further comprise iteratively recognizing a fourth object occluded by at least one object and a fifth object occluded by the fourth object based on a table representing the occluded object and the occluding object and the at least one object located at the left boundary or at the right boundary.

[0031] The methods and apparatus of the present disclosure have additional features and advantages that will be apparent from the accompanying drawings incorporated herein and the following detailed description, which together serve to explain certain principles of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS Fig. 1 shows a block diagram illustrating an object recognition device according to an embodiment of the present disclosure. Fig. 2 shows a flowchart of an operation of an object recognition device for determining whether an object is an occluding object or an occluded object in the object recognition device or the object recognition method according to an embodiment of the present disclosure; Fig. 3 shows an example of external points that may overlap in an object recognition device or method according to an embodiment of the present disclosure; Fig. 4 is a flowchart illustrating an operation of an object recognition device for recognizing an object occluded by an object located at a left or right boundary based on a fan-shaped area in the object recognition device or the object recognition method according to an embodiment of the present disclosure; Fig. 5 shows an example of area expansion of a fan-shaped region performed based on external points in an object recognition device or method according to an embodiment of the present disclosure; Fig. 6 illustrates an example of determining whether an object occludes another object or is occluded by another object when external points do not overlap each other in an object recognition apparatus or an object recognition method according to an embodiment of the present disclosure; Fig. 7 illustrates an example of determining whether an object occludes another object or is occluded by another object when external points overlap each other in an object recognition apparatus or method according to an embodiment of the present disclosure; Fig. 8 shows another example of a determination for detecting whether an object occludes or is occluded by another object when external points overlap each other in an object detection apparatus or method according to an embodiment of the present disclosure; Fig. 9 illustrates an example of an iterative determination of whether an object occludes another object or is occluded by another object in an object recognition apparatus or method according to an embodiment of the present disclosure; Fig. 10 is a flowchart illustrating an operation of an object detection apparatus for detecting whether an object occludes another object or is occluded by another object when external points do not overlap, in the object detection apparatus or the object detection method according to an embodiment of the present disclosure; Fig. 11 shows an example of comparing the accuracy of a determination for an occluding object detected based on an existing object detection apparatus or method with the accuracy of a determination for an occluding object detected based on an object detection apparatus or method according to an embodiment of the present disclosure; Fig. 12 shows an example of a computational effort determined based on an existing object recognition device or an object recognition method and an example of a computational effort determined based on an object recognition device or an object recognition method according to an embodiment of the present disclosure; and Fig. 13 shows a determination system related to an object recognition device or an object recognition method according to an embodiment of the present disclosure.

[0032] It should be understood that the accompanying drawings are not necessarily to scale and present a somewhat simplified representation of various preferred features illustrative of the principles of the disclosure. The predetermined design features of the present disclosure as disclosed herein, including, for example, specific dimensions, orientations, positions, and shapes, will be determined in part by the particular application and environment of use.

[0033] In the figures, reference numerals refer to the same or equivalent portions of the present disclosure in the different figures of the drawing. DETAILED DESCRIPTION

[0034] Reference will now be made in detail to various embodiments of the present disclosure(s), examples of which are illustrated in the accompanying drawings and described below. Although the present disclosure(s) will be described in connection with embodiments of the present disclosure, it is to be understood that the present description is not intended to limit the present disclosure(s) to those embodiments of the present disclosure. On the contrary, the present disclosure(s) are intended to cover not only the embodiments of the present disclosure, but also various alternatives, modifications, equivalents, and other embodiments which may be included within the spirit and scope of the present disclosure as defined by the appended claims.

[0035] Hereinafter, various embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. When reference numerals are added to components in the drawings, it is understood that the same components will be denoted by the same reference numerals even though they are shown in different drawings. Furthermore, when describing the embodiments of the present disclosure, if it is determined that a detailed description of related known arrangements or configurations and functions might obscure the understanding of the embodiments of the present disclosure, a detailed description will be omitted.

[0036] In describing the components of the exemplary embodiment of the present disclosure, terms such as "first," "second," "A," "B," "(a)," "(b)," and the like may be used. Such terms may merely be used to distinguish one component from another, and such terms do not necessarily limit the nature, sequence, or order of the individual components. Unless otherwise defined, terms used herein, including technical or scientific terms, may have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.Such terms, as defined in a commonly used dictionary, may be interpreted to have the same meaning as the contextual meanings in the relevant art, and not to have ideal or overly formal meanings, unless clearly defined as such in the present application.

[0037] In addition, the terms “unit”, “device”, “element”, “body” or the like used below may indicate at least one shape structure or may indicate a unit of processing a function.

[0038] Furthermore, in the disclosures of the present disclosure, the terms "greater than" or "less than" may be used to indicate whether a particular condition is met or satisfied, but 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." In addition, "A" to "B" means at least one of the elements from A (inclusive of A) to B (inclusive of B).

[0039] In the following, various embodiments of the present disclosure are described with reference to the Fig. 1 to 13 described in detail.

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

[0041] With reference to Fig. 1, an object detection device 101 according to an embodiment of the present disclosure can be implemented within a vehicle. In the present case, the object detection device 101 can be formed integrally with internal control units of the vehicle or can be implemented as a separate device and connected to the control units of the vehicle by separate connection means.

[0042] With reference to Fig. 1, the object detection device 101 may include a LiDAR 103 and a processor 105.

[0043] According to an embodiment of the present disclosure, the processor 105 of the object recognition device 101 may obtain a point cloud representing an object by the LiDAR 103.

[0044] According to one embodiment of the present disclosure, the point cloud may represent a set of points corresponding to points of a portion of an object obtained by the LiDAR 103. Each point forming the point cloud may include position information of a corresponding point of the object.

[0045] According to one embodiment of the present disclosure, the processor 105 of the object recognition device 101 may recognize a plurality of objects based on the point cloud. The processor 105 of the object recognition device 101 may recognize a first point that is the leftmost point with respect to the host vehicle in a point cloud representing a first object and a second point that is the rightmost point with respect to the host vehicle in the point cloud representing the first object. The processor of the object recognition device may recognize a third point that is the leftmost point with respect to the host vehicle in a point cloud representing a second object and a fourth point that is the rightmost point with respect to the host vehicle in the point cloud representing the second object.

[0046] According to one embodiment of the present disclosure, the processor 105 of the object recognition device 101 may detect a first external point that is closer to the second object, which is one of the first point or the second point. The processor 105 of the object recognition device 101 may detect a second external point that is closer to the first object, which is one of the third point and the fourth point.

[0047] According to an embodiment of the present disclosure, the processor 105 of the object recognition device 101 may detect whether the first outer point and the second outer point overlap. A method for detecting whether a first outer point and a second outer point overlap is described with reference to Fig. 3 described.

[0048] When the first outer point and the second outer point overlap, the processor 105 of the object detection device 101 may identify the reliability of the first object and the reliability of the second object based on a distance from a straight line connecting the first point and the second point to the LiDAR 103 and a distance from a straight line connecting the third point and the fourth point to the LiDAR 103. For example, the processor of the object detection device may assign a lower reliability to an object corresponding to the straight line the larger the distances between the straight line and the LiDAR 103.

[0049] The processor 105 of the object recognition device 101 can recognize whether the first object is an object that occludes another object or whether the first object is an object that is occluded by another object based on the reliability assigned to the first object and the reliability assigned to the second object. The processor 105 of the object recognition device 101 can recognize whether the second object is an object that occludes another object or whether the second object is an object that is occluded by another object based on the reliability assigned to the first object and the reliability assigned to the second object. For example, an object with a higher reliability among the first object and the second object may be an object that occludes another object.

[0050] A method for detecting whether an object occludes another object or whether an object is occluded by another object when the first outer point and the second outer point overlap each other will be described below with reference to Fig. 7 and Fig. 8 described.

[0051] When the first outer point and the second outer point do not overlap, the processor 105 of the object detection device 101 can detect one of the first object and the second object as an occluding object and the other of the first object and the second object as an occluded object based on the distance between the first outer point and the LiDAR 103 and the distance between the second outer point and the LiDAR 103. A method for detecting whether an object occludes another object or whether an object is occluded by another object when the first outer point and the second outer point do not overlap will be described below with reference to Fig. 6 described.

[0052] According to an embodiment of the present disclosure, the processor 105 of the object recognition device 101 may store the ID of an object in a table showing an occluded object and an occluding object based on determining the object as an occluding object. The table showing an occluded object and an occluding object will be described below with reference to Fig. 9 described.

[0053] Fig. 2 shows a flowchart of an operation of an object recognition device for determining whether an object is an object that occludes another object or for determining whether an object is occluded by another object in an object recognition device or an object recognition method according to an embodiment of the present disclosure.

[0054] In the following, it is assumed that the object recognition device 101 of Fig. 1 the process of Fig. 2. In the description of Fig. 2, the operations described as being performed by the object recognition device can also be understood as being controlled by the processor 105 of the object recognition device 101.

[0055] With reference to Fig. 2, according to various embodiments of the present disclosure, the processor of the object recognition device may detect a first outer point and a second outer point in a first operation 201. To detect the first outer point and the second outer point, the processor of the object recognition device may detect a first point, a second point, a third point, and a fourth point.

[0056] In other words, the processor of the object recognition device may recognize a point cloud representing at least one of a first object and a second object detected in a plane formed by a first axis and a second axis below the first axis, the second axis, and a third axis. The first axis may be referred to as the x-axis. The second axis may be referred to as the y-axis. The third axis may be referred to as the z-axis.The processor of the object detection device may detect a first point that is the leftmost point, with respect to the host vehicle, in a point cloud obtained via the LiDAR and representing the first object, a second point that is the rightmost point, with respect to the host vehicle, in the point cloud representing the first object, a third point that is the leftmost point, with respect to the host vehicle, in a point cloud representing the second object, and a fourth point that is the rightmost point, with respect to the host vehicle, in the point cloud representing the second object.The processor of the object recognition device may recognize a first external point that is one of the first point and the second point that is near the second object, and a second external point that is one of the third point and the fourth point that is near the first object.

[0057] In a second operation 203, the processor of the object recognition device according to various embodiments of the present disclosure may detect whether the first outer point and the second outer point overlap. If the first outer point and the second outer point overlap, the processor of the object recognition device may perform a third operation 205. If the first outer point and the second outer point do not overlap, the processor of the object recognition device may perform a fourth operation 209.

[0058] The processor of the object recognition device may recognize that the first outer point and the second outer point overlap based on determining that the azimuth angle of the first outer point with respect to the origin and the first axis corresponding to the LiDAR is included in a range between the azimuth angle of the third point with respect to the origin and the first axis and the azimuth angle of the fourth point with respect to the origin and the first axis.

[0059] According to one embodiment of the present disclosure, the first axis may be referred to as the x-axis. The second axis may be referred to as the y-axis. The third axis may be referred to as the z-axis.

[0060] In a third operation 205, the processor of the object recognition device may assign a reliability to the first object and assign a reliability to the second object according to various embodiments of the present disclosure.

[0061] According to an embodiment of the present disclosure, the processor of the object recognition device may recognize a straight line passing through the first point and the second point according to the coordinates of the first point and the coordinates of the second point based on determining that the first outer point and the second outer point overlap each other. The processor of the object recognition device may assign to the second object a reliability corresponding to the number of the third points or the fourth points included in an area to which the LiDAR belongs among the two areas separated by the straight line passing through the first point and the second point. The processor of the object recognition device may recognize a straight line passing through the third point and the fourth point according to the coordinates of the third point and the coordinates of the fourth point.The processor of the object recognition device may assign to the first object a reliability comprising a value different from the reliability of the second object equal to the number of the first points or the second points included in an area to which the LiDAR belongs among the two areas separated by the straight line passing through the third point and the fourth point.

[0062] According to another embodiment of the present disclosure, the processor of the object recognition device may recognize a first function, which is the function of a straight line passing through the first point and the second point, according to the coordinates of the first point and the coordinates of the second point based on determining that the first outer point and the second outer point overlap each other.The processor of the object recognition device may assign to the second object a reliability equal to the number of times the sign of a value obtained by substituting the coordinates of the origin corresponding to the LiDAR into the first function is the same as the sign of a value obtained by substituting the coordinates of the third point into the first function, and the sign of a value obtained by substituting the coordinates of the fourth point into the first function. The processor of the object recognition device may recognize a second function, which is the function of a straight line passing through the third point and the fourth point, based on the coordinates of the third point and the coordinates of the fourth point.The processor of the object recognition device may assign to the first object a reliability as large as the number of the same signs as the sign of a value obtained by substituting the coordinates of the origin corresponding to the LiDAR into the second function, the sign of a value obtained by substituting the coordinates of the first point into the second function, and the sign of a value obtained by substituting the coordinates of the second point into the second function.

[0063] In a fifth operation 207, the processor of the object recognition device may be configured according to various embodiments of the present disclosure to determine an occluded object and an occluding object. The processor of the object recognition device may compare the reliability value of the first object and the reliability value of the second object and identify an object with a high reliability value as an object that occludes another object.

[0064] In a fourth operation 209, the processor of the object detection device according to various embodiments of the present disclosure may detect whether an angle between a line segment connecting the first outer point and the LiDAR and a line segment connecting the second outer point and the LiDAR is less than or equal to a threshold angle. If the angle between the line segment connecting the first outer point and the LiDAR and the line segment connecting the second outer point and the LiDAR is less than or equal to the threshold angle, the processor of the object detection device according to various embodiments of the present disclosure may perform a sixth operation 211.If the angle between the line segment connecting the first outer point and the LiDAR and the line segment connecting the second outer point and the LiDAR is greater than the threshold angle, the processor of the object detection device may perform a seventh operation 213 according to various embodiments of the present disclosure.

[0065] According to an embodiment of the present disclosure, the threshold angle may increase as the distance between the object and the LiDAR becomes shorter.

[0066] In the sixth operation 211, the processor of the object detection device according to various embodiments of the present disclosure may detect a distance between the first outer point and the LiDAR and a distance between the second outer point and the LiDAR.

[0067] In an eighth operation 215, the processor of the object recognition device according to various embodiments of the present disclosure may be configured to determine an occluding object and an occluded object.

[0068] The processor of the object detection device may detect as an occluded object an object that is one of the first object and the second object corresponding to one of the first outer point and the second outer point that forms a larger distance among a distance between the first outer point and the LiDAR and a distance between the second outer point and the LiDAR.

[0069] The processor of the object detection device may detect an object as an occluding object that is one of the first object and the second object, which corresponds to one of the first outer point and the second outer point that forms a shorter distance between a distance between the first outer point and the LiDAR and a distance between the second outer point and the LiDAR. This is because there is a high probability that an object close to the LiDAR will occlude an object far from the LiDAR.

[0070] In the seventh operation 213, the processor of the object recognition device according to various embodiments of the present disclosure cannot determine whether an object is an occluded object or an occluding object. This is because the first object does not occlude the second object and the second object does not occlude the first object.

[0071] In a ninth operation 217, the processor of the object detection device according to various embodiments of the present disclosure may be configured to operate the host vehicle based on an occluding object and an occluded object.

[0072] Fig. 3 shows an example of external points that may overlap in an object recognition device or method according to an embodiment of the present disclosure.

[0073] With reference to Fig. 3, in a first situation 301, the first outer point of a first object (e.g., point B in the first situation 301) and the second outer point of a second object (e.g., point C in the first situation 301) may overlap. In a second situation 311, the first outer point of the first object (e.g., point B in the second situation 311) and the second outer point of the second object (e.g., point C in the second situation 311) do not overlap.

[0074] According to an embodiment of the present disclosure, the processor of the object recognition device may recognize a point cloud representing at least one of a first object and a second object detected in a plane formed by the first axis and the second axis under the first axis, the second axis, and the third axis.

[0075] According to an embodiment of the present disclosure, the processor of the object recognition device may detect a first point (e.g., point A in the first situation 301 or point A in the second situation 311) that is the leftmost point with respect to a host vehicle in a point cloud obtained via a LiDAR and representing the first object, a second point (e.g., point B in the first situation 301 or point B in the second situation 311) that is the rightmost point with respect to the host vehicle in the point cloud representing the first object, a third point (e.g., point C in the first situation 301 or point C in the second situation 311) that is the leftmost point with respect to the host vehicle in a point cloud representing the second object, and a fourth point (e.g.,Point D in the first situation 301 or point D in the second situation 311), which is the rightmost point with respect to the host vehicle in the point cloud representing the second object.

[0076] According to an embodiment of the present disclosure, the processor of the object recognition device may recognize a first external point (e.g., point B in the first situation 301 or point B in the second situation 311), which is one of the first point and the second point located near the second object, and a second external point (e.g., point C in the first situation 301 or point C in the second situation 311), which is one of the third point and the fourth point located near the first object.

[0077] According to an embodiment of the present disclosure, the processor of the object recognition device may recognize that the azimuth angle of the first outer point (e.g., point B in the first situation 301) with respect to the origin corresponding to the LiDAR and the first axis is included in a range between the azimuth angle of the third point (e.g., point C in the first situation 301) with respect to the origin and the first axis and the azimuth angle of the fourth point (e.g., point D in the first situation 301) with respect to the origin and the first axis, to recognize that the first outer point (e.g., point B in the first situation 301) and the second outer point (e.g., point C in the first situation 301) overlap each other.

[0078] According to an embodiment of the present disclosure, the processor of the object recognition device may recognize that the azimuth angle of the first outer point (e.g., point B in the second situation 311) with respect to the origin corresponding to the LiDAR and the first axis is not included in the range between the azimuth angle of the third point (e.g., point C in the second situation 311) with respect to the origin and the first axis and the azimuth angle of the fourth point (e.g., point D in the second situation 311) with respect to the origin and the first axis, to recognize that the first outer point (e.g., point B in the second situation 311) and the second outer point (e.g., point C in the second situation 311) do not overlap.

[0079] According to an embodiment of the present disclosure, when the angle between the line segment connecting the first outer point (e.g., point B in the second situation 311) and the LiDAR and the line segment connecting the second outer point (e.g., point C in the second situation 311) and the LiDAR is less than or equal to a threshold angle, one of the first object and the second object may be detected as an occluded object, and the other object may be detected as an occluding object.

[0080] According to an embodiment of the present disclosure, a method of detecting an occluding object among the first object and the second object when the first outer point (e.g., point B in the first situation 301) and the second outer point (e.g., point C in the first situation 301) overlap each other may be different from a method of detecting an occluding object among the first object and the second object when the first outer point (e.g., point B in the second situation 311) and the second outer point (e.g., point C in the second situation 311) do not overlap each other.

[0081] Fig. 4 shows a flowchart of an operation of an object recognition device for recognizing an object occluded by an object located at a left or right boundary based on a fan-shaped area in an object recognition device or an object recognition method according to an embodiment of the present disclosure.

[0082] In the following, it is assumed that the object recognition device 101 of Fig. 1 the process of Fig. 4. In addition, the description of Fig. 4 Operations described as being performed by the object recognition device are understood to be controlled by the processor 105 of the object recognition device 101.

[0083] With reference to Fig. 4, the processor of the object recognition device according to various embodiments of the present disclosure may obtain a point cloud via a LiDAR in a first operation 401.

[0084] According to one embodiment of the present disclosure, the processor of the object detection device may detect a fan-shaped region including a point cloud included in a particular layer and representing a first object that is leftmost with respect to a host vehicle and a point cloud included in the particular layer and representing a second object that is rightmost with respect to the host vehicle, wherein the fan-shaped region includes the minimum central angle with respect to the origin corresponding to the LiDAR. The fan-shaped region may be detected based on the point cloud included in the particular layer.

[0085] In a second operation 403, the processor of the object recognition device may recognize a first point, a second point, a third point, a fourth point, a first outer point, and a second outer point according to various embodiments of the present disclosure.

[0086] According to one embodiment of the present disclosure, the processor of the object recognition device may recognize a point cloud representing the first object among points included in a plurality of layers including a specific layer (e.g., all layers including points representing an object). The processor of the object recognition device may recognize a point cloud representing the second object among points included in the plurality of layers including the specific layer.

[0087] According to an embodiment of the present disclosure, the processor of the object recognition device may recognize, as the first outer point and the second outer point, points that form two line segments that form the smallest angle among an angle between a line segment connecting the first point and the LiDAR and a line segment connecting the third point and the LiDAR, an angle between the line segment connecting the first point and the LiDAR and a line segment connecting the fourth point and the LiDAR, an angle between a line segment connecting the second point and the LiDAR and the line segment connecting the third point and the LiDAR, and an angle between the line segment connecting the second point and the LiDAR and the line segment connecting the fourth point and the LiDAR.

[0088] In a third operation 405, the processor of the object recognition device according to various embodiments of the present disclosure may expand the area of ​​the fan-shaped region.

[0089] The processor of the object recognition device may expand the area of ​​the fan-shaped region by increasing the central angle of the fan-shaped region to include at least one point located outside the fan-shaped region, based on determining that the at least one point is located outside the fan-shaped region, among a point cloud included in a plurality of layers including a specific layer and representing the first object, and a point cloud included in the plurality of layers including the specific layer and representing the second object.

[0090] In a fourth operation 407, the processor of the object detection device according to various embodiments of the present disclosure may detect whether a third object is located at a left or right boundary.

[0091] According to an embodiment of the present disclosure, the processor of the object recognition device may recognize a fifth point located on the far left with respect to the host vehicle in the point cloud representing the third object and a sixth point located on the far right with respect to the host vehicle in the point cloud representing the third object.

[0092] According to an embodiment of the present disclosure, the processor of the object detection device may detect a left angle between a line segment representing the left boundary of the fan-shaped area and a line segment connecting the fifth point and the LiDAR, or detect a right angle between a line segment representing the right boundary of the fan-shaped area and a line segment connecting the sixth point and the LiDAR.

[0093] According to an embodiment of the present disclosure, the processor of the object recognition device may recognize the third object as being located at the left boundary or the right boundary based on the left angle or the right angle being less than or equal to a predetermined angle.

[0094] According to an embodiment of the present disclosure, the processor of the object recognition device may store the ID of an object located at the left or right boundary in a table.

[0095] In a fifth operation 409, the processor of the object recognition device according to various embodiments of the present disclosure may recognize whether the first object or the second object is an occluding object or an occluded object.

[0096] According to an embodiment of the present disclosure, the processor of the object recognition device may differently perform a process of recognizing whether an object occludes another object or is occluded by another object when a first outer point and a second outer point overlap each other and a process of recognizing whether an object occludes another object or is occluded by another object when a first outer point and a second outer point do not overlap each other.

[0097] In a sixth operation 411, the processor of the object detection device according to various embodiments of the present disclosure may detect an object occluded by an object at the left boundary or at the right boundary and an object iteratively occluded.

[0098] According to an embodiment of the present disclosure, the processor of the object recognition device may detect a fourth object occluded by at least one object, and iteratively detect a fifth object occluded by the fourth object based on a table representing occluded objects and occluding objects and at least one object located at the left boundary or the right boundary.

[0099] For example, the processor of the object recognition device may recognize the fifth object occluded by the fourth object based on the table representing occluded objects and occluding objects.

[0100] In a seventh operation 413, the processor of the object detection device according to various embodiments of the present disclosure may operate the host vehicle based on an occluding object and an occluded object.

[0101] Fig. 5 shows an example of expanding the area of ​​a fan-shaped region performed based on external points in an object recognition apparatus or an object recognition method according to an embodiment of the present disclosure.

[0102] With reference to Fig. 5, in a first situation 501, the processor of the object detection device may detect, via a first LiDAR 503, a first point 511 that is the leftmost point with respect to a host vehicle in a point cloud 509 representing a first object 505 in the first situation 501. The processor of the object detection device may detect, via the first LiDAR 503, a second point that is the rightmost point with respect to the host vehicle in the point cloud 509 representing the first object 505 in the first situation 501.The processor of the object detection device can detect, via the first LiDAR 503, a third point that is the leftmost point with respect to the host vehicle in a point cloud representing a second object 507 in the first situation 501, and, via the LiDAR 503, a fourth point that is the rightmost point with respect to the host vehicle in the point cloud representing the second object 507 in the first situation 501.

[0103] In a second situation 513, the processor of the object recognition device may expand the area of ​​a fan-shaped region based on a point cloud representing a first object 517 in the second situation 513 and obtained via a second LiDAR 515 and a point cloud representing a second object 519 in the second situation 513 and obtained via the second LiDAR 515.

[0104] In the first situation 501, the processor of the object detection device may detect a first point that is the leftmost point with respect to the host vehicle in the point cloud obtained by the first LiDAR 503 and representing the first object 505 in the first situation 501, a second point that is the rightmost point with respect to the host vehicle in the point cloud representing the first object 505 in the first situation 501, a third point that is the leftmost point with respect to the host vehicle in the point cloud representing the second object 507 in the first situation 501, and a fourth point that is the rightmost point with respect to the host vehicle in the point cloud representing the second object 507 in the first situation 501. The first point, the second point, the third point, and the fourth point may be defined as a critical angle orvertex (Angular Critical Point - ACP), but the embodiments of the present disclosure are not limited thereto.

[0105] According to one embodiment of the present disclosure, the first point may include the largest azimuth angle with respect to the origin corresponding to the first LiDAR 503 and a first axis in the point cloud representing the first object 505 in the first situation 501. The second point may include the smallest azimuth angle with respect to the first axis in the point cloud representing the first object 505 in the first situation 501. The first axis may be referred to as the x-axis.

[0106] Furthermore, according to an embodiment of the present disclosure, the processor of the object detection device may detect a fan-shaped region comprising a point cloud included in a particular layer and representing the first object 505 in the first situation 501 that is leftmost with respect to the host vehicle, and a point cloud included in the particular layer and representing the second object 507 in the first situation 501 that is rightmost with respect to the host vehicle, wherein the fan-shaped region includes the minimum central angle with respect to the origin corresponding to the first LiDAR 503. The fan-shaped region may be detected based on the point cloud included in the particular layer.

[0107] In the second situation 513, the processor of the object recognition device may expand the area of ​​the fan-shaped region by increasing the central angle of the fan-shaped region to include at least one point located outside the fan-shaped region, based on determining that at least one point lies outside the fan-shaped region, among a point cloud included in a plurality of layers including a particular layer (e.g., all layers including points representing an object) and representing the first object 517 of the second situation 513, and a point cloud included in the plurality of layers including the particular layer and representing the second object 519 of the second situation 513.

[0108] According to an embodiment of the present disclosure, the second object 507 in the first situation 501 may move over time to the position of the second object 519 in the second situation 513.

[0109] Fig. 6 illustrates an example of determining whether an object occludes another object or is occluded by another object when external points do not overlap each other in an object recognition apparatus or an object recognition method according to an embodiment of the present disclosure.

[0110] With reference to Fig. 6, the processor of the object recognition device may, in a first situation 601, recognize a first object 605 of the first situation 601 and a second object 607 of the first situation 601 based on a point cloud obtained by a first LiDAR 603. The processor of the object recognition device may recognize that the second object 607 in the first situation 601 is located at the right boundary of a fan-shaped area.

[0111] In a second situation 611, the processor of the object detection device may detect a first object 615, a second object 617, and a third object 619 through a second LiDAR 613. The processor of the object detection device may detect an occluding object and an occluded object among the first object 615, the second object 617, and the third object 619.

[0112] According to an embodiment of the present disclosure, the processor of the object recognition device may recognize a fifth point that is the leftmost point with respect to the host vehicle in a point cloud representing the second object 607 in the first situation 601 and a sixth point that is the rightmost point with respect to the host vehicle in the point cloud representing the second object 607 in the first situation 601.

[0113] According to an embodiment of the present disclosure, the processor of the object detection device may detect a left angle between a line segment representing the left boundary of the fan-shaped area and a line segment connecting the fifth point and the first LiDAR 603, or a right angle between a line segment representing the right boundary of the fan-shaped area and a line segment connecting the sixth point and the first LiDAR 603.

[0114] According to one embodiment of the present disclosure, the processor of the object recognition device may detect that the second object 607 is not located at the left boundary in the first situation 601 based on the left angle being greater than or equal to a predetermined angle. The processor of the object recognition device may detect that the second object 607 is located at the right boundary in the first situation 601 based on the right angle being less than or equal to the predetermined angle.

[0115] According to one embodiment of the present disclosure, the processor of the object recognition device may store the ID of the second object 607 of the first situation 601 located at the right boundary in a table. The table may be referred to as the field of view (FOV), but the embodiments of the present disclosure are not limited thereto.

[0116] According to an embodiment of the present disclosure, the processor of the object recognition device may recognize whether among the first object 615 of the second situation 611, the second object 617 of the second situation 611, and the third object 619 of the second situation 611 there is an object that obscures another object or an object that is obscured by another object.

[0117] According to an embodiment of the present disclosure, the processor of the object recognition device may differently perform a process of recognizing whether an object is an occluding object or an occluded object when a first outer point and a second outer point overlap each other and a process of recognizing whether an object is an occluding object or an occluded object when a first outer point and a second outer point do not overlap each other.

[0118] According to an embodiment of the present disclosure, the processor of the object recognition device may not recognize whether at least one of the first object 615 of the second situation 611 and the second object 617 of the second situation 611 is an occluding object or an occluded object based on determining that an angle (e.g., θ1) between a straight line connecting the first outer point of the first object 615 of the second situation 611 and the second LiDAR 613 and a straight line connecting the second outer point of the second object 617 of the second situation 611 and the second LiDAR 613 is greater than or equal to a threshold angle when the first outer point of the first object 615 of the second situation 611 and the second outer point of the second object 617 of the second situation 611 do not overlap with each other.

[0119] According to an embodiment of the present disclosure, the processor of the object recognition device may recognize whether at least one of the second object 617 of the second situation 611 and the third object 619 of the second situation 611 is an occluding object or an occluded object based on determining that an angle (e.g., θ2) between a straight line connecting the first outer point of the second object 617 of the second situation 611 and the second LiDAR 613 and a straight line connecting the second outer point of the third object 619 of the second situation 611 and the second LiDAR 613 is less than or equal to the threshold angle when the first outer point of the second object 617 of the second situation 611 and the second outer point of the third object 619 of the second situation 611 do not overlap with each other.

[0120] For example, the processor of the object recognition device may recognize the third object 619, which is one of the second object 617 in the second situation 611 and the third object 619 in the second situation 611, as an occluded object corresponding to an outer point that forms a larger distance among a distance between the first outer point of the second object 617 of the second situation 611 and the second LiDAR 613 and a distance between the second outer point of the third object 619 of the second situation 611 and the second LiDAR 613. The processor of the object recognition device may recognize the second object 617, which is different from an object recognized as an occluded object among the second object 617 of the second situation 611 and the third object 619 of the second situation 611, as an occluded object.

[0121] A method by which the processor of the object recognition device according to an embodiment recognizes whether at least one of the second object 617 of the second situation 611 and the third object 619 of the second situation 611 is an occluding object and an occluded object when the first outer point of the second object 617 of the second situation 611 and the second outer point of the third object 619 of the second situation 611 overlap each other is described with reference to Fig. 7 described.

[0122] The processor of the object recognition device may store the relationship between an occluding object and an occluded object in a table. The table may be referred to as an occlusion map, but embodiments of the present disclosure are not limited thereto. The processor of the object recognition device may assign a particular first value (e.g., about 1) to rows and columns of the table corresponding to objects that represent occluding objects. The processor of the object recognition device may assign a second value (e.g., about -1) to the rows and columns of the table corresponding to objects that represent occluding objects. The processor of the object recognition device may assign a third value (e.g., about 0) to the rows and columns of the table corresponding to objects that are neither occluding nor occluded objects.

[0123] Fig. 7 illustrates an example of a determination for detecting whether an object occludes another object or is occluded by another object when external points overlap each other in an object detection apparatus or an object detection method according to an embodiment of the present disclosure.

[0124] With reference to Fig. 7, in a first situation 701, a first outer point of a first object 705 of the first situation 701 and a second outer point of a second object 707 of the first situation 701, which are detected by a first LiDAR 703, may overlap.

[0125] In a second situation 711, the processor of the object detection device may detect that the first outer point of a first object 715 and the second outer point of a second object 717 detected by a second LiDAR 713 overlap each other. Based on a distance from a straight line connecting a first point of the first object 715 and a second point of the first object 715 to the second LiDAR 713 and a distance from a straight line connecting a third point of the second object 717 and a fourth point of the second object 717 to the second LiDAR 713, the processor of the object detection device may detect in the second situation 711 whether the first object 715 or the second object 717 is an object that occludes or is occluded by another object.

[0126] In a third situation 721, the processor of the object detection device may detect that a first outer point of a first object 725 and a second outer point of a second object 727, detected via a third LiDAR 723, overlap each other. The processor of the object recognition device may, based on a distance to the third LiDAR 723 from a point where a straight line connecting a first point of the first object 725 and the third LiDAR 723 and a straight line connecting the third point and the fourth point of the second object 727 meet, a distance to the third LiDAR 723 from a point where the straight line connecting the second point of the first object 725 and the third LiDAR 723 and the straight line connecting the third point of the second object 727 and the fourth point of the second object 727 meet, a distance to the third LiDAR 723 from a point,at which the straight line connecting the third point of the second object 727 and the third LiDAR 723 and the straight line connecting the first point of the first object 725 and the second point of the first object 725 meet, or a distance to the third LiDAR 723 from a point at which the straight line connecting the fourth point of the second object 727 and the third LiDAR 723 and the line connecting the first point of the first object 725 and the second point of the first object 725 meet, detect whether the first object 725 or the second object 727 is an object that occludes another object or is occluded by another object.

[0127] According to one embodiment of the present disclosure, in the first situation 701, the processor of the object detection device may not be able to detect which of the first object 705 and the second object 707 is an occluding object or an occluded object simply by comparing a distance between the first outer point of the first object 705 and the first LiDAR 703 and a distance between the second outer point of the second object 707 and the first LiDAR 703. This is because the first outer point and the second outer point overlap each other.

[0128] If the processor of the object detection device detects an occluding object and an occluded object simply based on comparing the distance between the first outer point of the first object 705 and the first LiDAR 703 with the distance between the second outer point of the second object 707 and the first LiDAR 703, the processor of the object detection device may perceive a correlation different from the actual correlation.

[0129] According to an embodiment of the present disclosure, the processor of the object recognition device may recognize in the second situation 711 that the first outer point of the first object 715 in the second situation 711 (e.g., B in the second situation 711) and the second outer point of the second object 717 in the second situation 711 (e.g., C in the second situation 711) overlap each other. The processor of the object recognition device can recognize as an object hidden by the first object 715 of the second situation 711 the second object 717 of the second situation 711, which is at a greater distance than a distance to the second LiDAR 713 from a straight line connecting the first point of the first object 715 in the second situation 711 (e.g., A in the second situation 711) and the second point of the first object 715, and a distance to the second LiDAR 713 from a straight line connecting the third point of the second object 717 (e.g.,C in the second situation 711) and the fourth point of the second object 717 (e.g. D in the second situation 711).

[0130] The processor of the object recognition device may recognize, as an object occluding the second object 717 of the second situation 711, the first object 715 of the second situation 711 that corresponds to a shorter distance among a distance to the second LiDAR 713 from a straight line connecting the first point of the first object 715 in the second situation 711 and the second point of the first object 715, and a distance to the second LiDAR 713 from a straight line connecting the third point of the second object 717 and the fourth point of the second object 717.

[0131] According to an embodiment of the present disclosure, the processor of the object recognition device may recognize in the third situation 721 that the first outer point of the first object 725 in the third situation 721 (e.g., B in the third situation 721) and the second outer point of the second object 727 in the third situation 721 (e.g., C in the third situation 721) overlap each other. The processor of the object recognition device may detect a first projection point (e.g., E in the third situation 721), which is a point where a straight line connecting a first point of the first object 725 in the third situation 721 (e.g., A in the third situation 721) and a third LiDAR 723, and a straight line connecting a third point (e.g., C in the third situation 721) and a fourth point (e.g., D in the third situation 721) of the second object 727 in the third situation 721 meet.

[0132] The processor of the object detection device may detect that the distance from the first projection point to the third LiDAR 723 is greater than the distance from the first point of the first object 725 of the third situation 721 to the third LiDAR 723, and the distance from the second point of the first object 725 of the third situation 721 to the third LiDAR 723. The processor of the object detection device may detect the first object 725 of the third situation 721 as an object that occludes another object (e.g., the second object 727 of the third situation 721) based on determining that the distance from the first projection point to the third LiDAR 723 is greater than the distance from the first point of the first object 725 of the third situation 721 to the third LiDAR 723 and the distance from the second point of the first object 725 of the third situation 721 to the third LiDAR 723.

[0133] The processor of the object recognition device may detect a second projection point, which is a point where the straight line connecting the first point of the second object 727 of the third situation 721 and the third LiDAR 723 meets the straight line connecting the first point and the second point of the first object 725 of the third situation 721.

[0134] The processor of the object detection device may detect the second object 727 of the third situation 721 as an object that is occluded by another object (e.g., the first object 725 of the third situation 721) based on determining that the distance from the second projection point to the third LiDAR 723 is less than or equal to the distance from the first point of the first object 725 of the third situation 721 to the third LiDAR 723, or less than or equal to the distance from the second point of the first object 725 of the third situation 721 to the third LiDAR 723.

[0135] Another method of recognizing objects as an occluding object or as an occluded object based on determining that a first outer point and a second outer point overlap each other will be described below with reference to Fig. 8 described.

[0136] Fig. 8 shows another example of a determination for detecting whether an object occludes or is occluded by another object when external points overlap each other in an object detection apparatus or an object detection method according to an embodiment of the present disclosure.

[0137] With reference to Fig. 8, a processor of an object recognition device may recognize at least one of a first object 803 and a second object 805 as an occluded object or occluding object based on determining that a first outer point of the first object 803 obtained by a LiDAR 801 and a second outer point of the second object 805 obtained by the LiDAR 801 overlap each other. A first straight line 807 may represent a straight line connecting the first point and the second point of the first object 803.

[0138] According to one embodiment of the present disclosure, the processor of the object recognition device may detect a first point (e.g., point A), a second point (e.g., point B), a third point (e.g., point C), and a fourth point (e.g., point D). The first point may be located on the far left with respect to a host vehicle in a point cloud representing the first object 803. The second point may be located on the far right with respect to the host vehicle in the point cloud representing the first object 803. The third point may be located on the far left with respect to a host vehicle in a point cloud representing the second object 805. The fourth point may be located on the far right with respect to a host vehicle in a point cloud representing the second object 805.

[0139] According to an embodiment of the present disclosure, the processor of the object recognition device may recognize whether the first object 803 or the second object 805 is an occluded object or an occluding object based on determining that the first outer point (e.g., point B) and the second outer point (e.g., point C) overlap each other.

[0140] According to an embodiment of the present disclosure, the processor of the object recognition device may recognize the first straight line 807 passing through the first point and the second point according to the coordinates of the first point (e.g., point A) of the first object 803 and the coordinates of the second point (e.g., point B) of the first object 803 based on determining that the first outer point and the second outer point overlap each other. The processor of the object recognition device may assign to the second object 805 a reliability corresponding to the number of the third points of the second object 805 or the fourth points of the second object 805 included in an area to which the LiDAR 801 belongs among two areas separated by the first straight line 807.

[0141] The processor of the object recognition device can recognize a second straight line passing through the third point and the fourth point according to the coordinates of the third point of the second object 805 and the coordinates of the fourth point of the second object 805. The processor of the object recognition device can assign to the first object 803 a reliability that includes a value different from the reliability of the second object 805 equal to the number of first points of the first object 803 or second points of the first object 803 included in an area to which the LiDAR 801 belongs, among the two areas separated by the second straight line passing through the third point and the fourth point.

[0142] The processor of the object recognition device may recognize the first object 803 with a higher reliability value than an object occluding another object by comparing the reliability value of the first object 803 and the reliability value of the second object 805. The processor of the object recognition device may recognize the second object 805 with a lower reliability value than an object occluded by another object by comparing the reliability value of the first object 803 and the reliability value of the second object 805.

[0143] Fig. 9 illustrates an example of an iterative determination for detecting whether an object occludes or is occluded by another object in an object detection apparatus or method according to an embodiment of the present disclosure.

[0144] With reference to Fig. 9, a first table 901 may represent the IDs of objects located at the left or right boundary. The first table 901 may be referred to as the field of view (FOV), but embodiments of the present disclosure are not limited thereto.

[0145] A second table 911 may represent a correlation between an occluded object and an occluding object. The second table 911 may be referred to as an occlusion map, but embodiments of the present disclosure are not limited thereto.

[0146] In a situation 921, the processor of the object detection device may detect a first object 925, a second object 926, and a third object 927 via a LiDAR 923.

[0147] The processor of the object recognition device may recognize the second object 926 as being occluded by the first object 925 located at the left or right boundary by referring to the first table 901 and the second table 911. The processor of the object recognition device may iteratively recognize the fourth object occluded by the second object 926 by referring to the first table 901 and the second table 911.

[0148] The processor of the object recognition device may assign a first value (e.g., about 1) to the rows and columns of the second table 911 that represent occluded objects. The processor of the object recognition device may assign a second value (e.g., about -1) to the rows and columns of the second table 911 that represent occluding objects. The processor of the object recognition device may assign a third value (e.g., about 0) to the rows and columns of the second table 911 that represent objects that are neither occluding nor occluded objects.

[0149] According to an embodiment of the present disclosure, a processor of the object detection device may detect that the first object 925 is an object that occludes the second object 926 and the second object 926 is an object that is occluded by the first object 925 based on determining that an angle (e.g., θ) between a line segment connecting the first outer point of the first object 925 and the LiDAR 923 and a line segment connecting the second outer point of the second object 926 and the LiDAR 923 is smaller than a threshold angle when the first object 925 and the second object 926 do not overlap each other.

[0150] Fig. 10 shows a flowchart of an operation of an object recognition device for recognizing whether an object occludes another object or is occluded by another object when external points do not overlap each other, in the object recognition device or the object recognition method according to an embodiment of the present disclosure.

[0151] In the following, it is assumed that the object recognition device 101 of Fig. 1 the process of Fig. 10. Furthermore, operations described as being performed by the object recognition device may be understood to be controlled by the processor 105 of the object recognition device 101.

[0152] According to Fig. 10, the processor of the object recognition device according to the various embodiments of the present disclosure may, in a first operation 1001, recognize a first point, a second point, a third point, and a fourth point.

[0153] According to an embodiment of the present disclosure, the processor of the object detection device may detect a first point that is the leftmost point with respect to the host vehicle in a point cloud obtained via the LiDAR and representing the first object, a second point that is the rightmost point with respect to the host vehicle in the point cloud representing the first object, a third point that is the leftmost point with respect to the host vehicle in a point cloud representing the second object, and a fourth point that is the rightmost point with respect to the host vehicle in the point cloud representing the second object.

[0154] In a second operation 1003, the processor of the object recognition device according to the various embodiments of the present disclosure may recognize a first external point and a second external point.

[0155] According to an embodiment of the present disclosure, the processor of the object recognition device may recognize a first external point closer to the second object, which is one of the first point and the second point, and a second external point closer to the first object, which is one of the third point and the fourth point.

[0156] In a third operation 1005, the processor of the object detection device according to various embodiments of the present disclosure may detect an angle between a line segment connecting the first outer point and the LiDAR and a line segment connecting the second outer point and the LiDAR.

[0157] According to an embodiment of the present disclosure, the processor of the object detection device may detect an angle between a line segment connecting the first outer point and a LiDAR and a line segment connecting the second outer point and the LiDAR based on determining that the first outer point and the second outer point do not overlap each other.

[0158] In a fourth operation 1007, according to various embodiments of the present disclosure, the processor of the object detection device may detect that the angle is greater than a threshold angle. The angle may include an angle between a line segment connecting the first outer point and the LiDAR and a line segment connecting the second outer point and the LiDAR. If the angle is not greater than the threshold angle, the processor of the object detection device may perform a fifth operation 1009. If the angle is greater than the threshold angle, the processor of the object detection device may not detect an occluding object and an occluded object among the first object and the second object.

[0159] In the fifth operation 1009, the processor of the object recognition device according to various embodiments of the present disclosure may recognize an object corresponding to an external point forming a large distance as an occluded object.

[0160] According to an embodiment of the present disclosure, the processor of the object detection device may detect an object that is one of the first object and the second object corresponding to one of the first outer point and the second outer point that forms a larger distance among a distance between the first outer point and the LiDAR and a distance between the second outer point and the LiDAR as an occluded object.

[0161] In a sixth operation 1011, the processor of the object recognition device according to various embodiments of the present disclosure may recognize an object recognized as an object occluded by another object and an object recognized as an object occluding another object.

[0162] According to an embodiment of the present disclosure, the processor of the object recognition device may recognize which of the first object and the second object is an object occluded by another object or an object occluding another object.

[0163] According to an embodiment of the present disclosure, the processor of the object recognition device may recognize that the first object and the second object do not occlude each other when the angle is greater than the threshold angle.

[0164] In a seventh operation 1013, the processor of the object recognition device according to various embodiments of the present disclosure may operate or control the host vehicle based on the first object or the second object.

[0165] In an eighth operation 1015, the processor of the object detection device according to various embodiments of the present disclosure may operate or control the host vehicle based on an occluding object and an occluded object.

[0166] Fig. 11 shows an example of comparing the accuracy of a determination for an occluding object detected based on an existing object detection apparatus or an object detection method with the accuracy of a determination for an occluding object detected based on an object detection apparatus or an object detection method according to an embodiment of the present disclosure.

[0167] With reference to Fig. 11, a first graphical representation 1103 in a first row 1101 may show a non-detection rate of objects detected based on the object detection device or the object detection method according to an embodiment and located at the left boundary of the fan-shaped area or the right boundary of the fan-shaped area, and a non-detection rate of objects detected based on an existing object detection device or an object detection method and located at the left boundary of the fan-shaped area or the right boundary of the fan-shaped area. The non-detection rate may refer to the rate of failed detection of an object.

[0168] According to one embodiment of the present disclosure, Basic may indicate a case where an object is a passenger car. Bus may indicate a case where an object is a bus. Special Vehicle may indicate a case where an object is a vehicle such as a tanker truck or a trailer. PTW Vehicle may indicate a case where an object is a two-wheeled vehicle such as a motorcycle. Gas may indicate a case where an object is exhaust gas.

[0169] The non-recognition rate of the existing object recognition device or the existing object recognition method must not differ by more than about 0.2 from the non-recognition rate of the object recognition device or the object recognition method according to an embodiment of the present disclosure.

[0170] A second graphical representation 1105 in the first row 1101 may show a misdetection rate of objects detected based on the object detection device or the object detection method according to an embodiment and located at the left boundary of the fan-shaped area or the right boundary of the fan-shaped area, and a misdetection rate of objects detected based on an existing object detection device or an existing object detection method and located at the left boundary of the fan-shaped area or the right boundary of the fan-shaped area. The misdetection rate may refer to the rate at which an object is detected as present even though the object is not present.

[0171] The misrecognition rate of the existing object recognition device or the existing object recognition method may be greater than the misrecognition rate of the object recognition device or the object recognition method according to an embodiment of the present disclosure.

[0172] A third graphical representation 1107 in the first row 1101 may show the average number of errors for objects detected based on the object detection device or the object detection method according to an embodiment and located at the left boundary of the fan-shaped area or the right boundary of the fan-shaped area, and the average number of errors for objects detected based on a conventional object detection device or a conventional object detection method and located at the left boundary of the fan-shaped area or the right boundary of the fan-shaped area. The average number of errors may refer to how often the number of frames with an error is detected on average among a certain number of frames (e.g., about 5000).

[0173] The average error count of the existing object recognition device or the existing object recognition method may be greater than the average error count of the object recognition device or the object recognition method according to an embodiment of the present disclosure.

[0174] A fourth graphical representation 1113 in a second row 1111 may show the non-detection rate of an object detected based on an object detection device or an object detection method according to an embodiment and recognized as an occluding object or an occluded object, and the non-detection rate of an object detected based on an existing object detection device or an existing object detection method and recognized as an occluding object or an occluded object. The non-detection rate may refer to the rate at which an object that is not an occluding object or an occluding object is incorrectly detected as an occluded object or an occluding object.

[0175] The non-recognition rate of the existing object recognition device or the existing object recognition method may be greater than the non-recognition rate of the object recognition device or the object recognition method according to an embodiment of the present disclosure.

[0176] According to one embodiment of the present disclosure, Basic may indicate a case where an object is a passenger car. Bus may indicate a case where an object is a bus. Special Vehicle may indicate a case where an object is a vehicle such as a tanker truck or a trailer. Gas may indicate a case where an object is exhaust gas. Road Marking may indicate a case where an object is a pavement attached to a road.

[0177] A fifth graphical representation 1115 in the second row 1111 may show the misrecognition rate of an object detected based on an object detection device or an object detection method according to an embodiment and not detected as an occluding object or occluded object, and the misrecognition rate of an object detected based on an existing object detection device or an existing object detection method and not detected as an occluding object or occluded object. The misrecognition rate may refer to the rate at which an occluding object or an occluded object is incorrectly detected as an occluded object or an occluding object.

[0178] The error detection rate of the existing object detection device or the existing object detection method may not deviate by more than about 0.2 from the error detection rate of the object detection device or the object detection method according to an embodiment of the present disclosure.

[0179] A sixth graphical representation 1117 in the second row 1111 may show the average number of errors of an object whose properties are misrecognized based on an object recognition device or an object recognition method according to an embodiment of the present disclosure, and the average number of errors of an object whose properties are misrecognized based on an existing object recognition device or an object recognition method. The average number of errors may refer to how often the number of frames with an error is detected on average among a certain number of frames (e.g., about 5000).

[0180] The average error count of the existing object recognition device or the existing object recognition method must not differ by more than about 20 from the average error count of the object recognition device or the method for object recognition according to an embodiment of the present disclosure.

[0181] According to an embodiment of the present disclosure, the accuracy of the object determination of the existing object recognition device or the existing object recognition method must not differ significantly from the accuracy of the object determination of the object recognition device or the object recognition method according to an embodiment of the present disclosure.

[0182] However, the time required for the object recognition device or the object recognition method according to the various embodiments of the present disclosure may be shorter than the time required for the existing object recognition device or the existing object recognition method. The time required for an existing object recognition device or an existing object recognition method and the time required for an object recognition device or an object recognition method according to an embodiment are described below with reference to Fig. 12 described.

[0183] Fig. 12 shows an example of a calculation amount determined based on an existing object recognition device or an existing object recognition method and an example of a calculation amount determined based on an object recognition device or an object recognition method according to an embodiment of the present disclosure.

[0184] With reference to Fig. 12, a first graphical representation 1203 may show, in a first row 1201 in a first scenario, a first line 1205 representing the central processing unit (CPU) computing time required by an existing object recognition device or method, and a second line 1207 representing a CPU computing time required by an object recognition device or method according to an embodiment of the present disclosure. The CPU computing time may refer to the time required by a CPU to process the calculations. The first line 1205 and the second line 1207 may represent the CPU computing time required in the first through fifth passes.

[0185] A second graphical representation 1209 in the first row 1201 may show, in the first scenario, the ratio of the CPU computing time required by an object recognition device or an object recognition method according to an embodiment to the CPU computing time required by the existing object recognition device or the existing object recognition method. The second graphical representation 1209 may represent the ratio of the CPU computing time required in the first to fifth passes.

[0186] A third graphical representation 1213 in a second row 1211 may show, in a second scenario, a third line 1215 representing CPU computing time required by an existing object recognition device or method, and a fourth line 1217 representing CPU computing time required by the object recognition device or method according to an embodiment of the present disclosure. The third line 1215 and the fourth line 1217 may represent the CPU computing time required in the first through fifth passes.

[0187] A fourth graphical representation 1219 in the second row 1211 may show, in the second scenario, the ratio of the CPU computing time required by an object recognition device or an object recognition method according to an embodiment to the CPU computing time required by the existing object recognition device or the existing object recognition method.

[0188] The fourth graphical representation 1219 may represent the ratio of CPU computing time consumed in the first to the fifth pass.

[0189] The first line 1205 and the second line 1207 of the first graphical representation 1203 may indicate that the CPU computing time required in the existing object recognition device or the existing object recognition method is longer than the CPU computing time required by the object recognition device or the object recognition method according to an embodiment of the present disclosure.

[0190] The second graphical representation 1209 may indicate that the CPU time consumed by the object recognition device or the object recognition method according to an embodiment of the present disclosure is about 19% of the CPU time consumed by the existing object recognition device or the existing object recognition method.

[0191] The third line 1215 and the fourth line 1217 of the third graphical representation 1213 may indicate that the CPU computing time required in the existing object recognition device or the existing object recognition method is longer than the CPU computing time required by the object recognition device or the object recognition method according to an embodiment of the present disclosure.

[0192] The fourth graphical representation 1219 may indicate that the CPU time consumed by the object recognition device or the object recognition method according to an embodiment of the present disclosure is about 19% of the CPU time consumed by the existing object recognition device or the existing object recognition method.

[0193] The accuracy of an object determination in the object recognition device or the object recognition method according to various embodiments of the present disclosure may differ from the accuracy of the object determination in the existing object recognition device or the existing object recognition method by less than a reference value. The CPU time required for the object recognition device or the existing object recognition method according to various embodiments of the present disclosure may be reduced to approximately 1 / 5 times compared to the CPU time required for the existing object recognition device or the existing object recognition method.

[0194] Fig. 13 shows a computer system related to an object recognition device or an object recognition method according to an embodiment of the present disclosure.

[0195] With reference to Fig. 13, a computer system 1300 may include at least a processor 1310, a memory 1330, a user interface input device 1340, a user interface output device 1350, a storage 1360, and a network interface 1370 interconnected via a bus 1320.

[0196] Processor 1310 may be a central processing unit (CPU) or a semiconductor device that processes instructions stored in memory 1330 and / or storage 1360. Memory 1330 and storage 1360 may include various types of volatile or non-volatile storage media. For example, memory 1330 may include read-only memory (ROM) 1331 and random access memory (RAM) 1332.

[0197] Thus, the operations of the method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware or in a software module executed by processor 1310, or in a combination thereof. The software module may be located on a storage medium (i.e., memory 1330 and / or storage 1360) such as RAM, flash memory, ROM, EPROM, EEPROM, register, hard disk, removable disk, and CD-ROM.

[0198] The exemplary storage medium may be coupled to processor 1310, and processor 1310 may read information from the storage medium and store information on the storage medium. Alternatively, the storage medium may be integrated with processor 1310. The processor and storage medium may be encapsulated in an application-specific integrated circuit (ASIC). The ASIC may be encapsulated within a user terminal. Alternatively, the processor and storage medium may be encapsulated as separate components in the user terminal.

[0199] The above description merely illustrates the technical idea of ​​the present disclosure, and various modifications and variations can be made by a person skilled in the art to which the present disclosure belongs without departing from the essential characteristics of the present disclosure.

[0200] Accordingly, the embodiment included in an embodiment of 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 equivalent scope should be considered to be included in the scope of the present disclosure.

[0201] The present technology can improve the accuracy of determining whether each of the objects is an object occluding another object or an object occluded by another object by comparing distance values ​​for objects represented by a point cloud.

[0202] Furthermore, the present technology can improve the accuracy of determining whether each object is an object occluding another object or an object occluded by another object by comparing the reliabilities assigned to the objects represented by a point cloud.

[0203] Furthermore, the present technology can enhance user experience by improving the accuracy of determining whether each object is an object occluding another object or an object occluded by another object.

[0204] Furthermore, the present technology can improve the performance of autonomous driving or driver-assisted driving by improving the accuracy of determining whether each object is an object occluding another object or an object occluded by another object.

[0205] In addition, various effects can be provided which are directly or indirectly understood by the present disclosure.

[0206] In various embodiments of the present disclosure, the memory and the processor may be provided as one chip or as separate chips.

[0207] In various embodiments of the present disclosure, the scope of the present disclosure includes software or machine-executable instructions (e.g., an operating system, an application, firmware, a program, etc.) that enable operations according to the methods of the various embodiments to be performed on a device or computer, and a non-transitory computer-readable medium comprising such software or instructions stored thereon and executable on the device or computer.

[0208] In various embodiments of the present disclosure, the control device may be implemented in the form of hardware or software, or may be implemented in a combination of hardware and software.

[0209] Furthermore, the terms used in the patent specification such as “unit”, “module”, etc. include units for processing at least one function or operation, which can be implemented by hardware, software, or a combination thereof.

[0210] In one embodiment of the present disclosure, the vehicle may be referred to as being based on a concept including various means of transportation. In some cases, the vehicle may be understood as being based on a concept that includes not only various land transportation means such as cars, motorcycles, trucks, and buses traveling on roads, but also various means of transportation such as airplanes, drones, ships, etc.

[0211] For ease of explanation and precise definition in the appended claims, the terms "top," "bottom," "inside," "outside," "upward," "downward," "front," "backward," "rearward," "inside," "outside," "inward," "outward," "internal," "external," "inner," "outer," "forward," and "backward" are used to describe features of the embodiments with reference to the positions of such features as illustrated in the figures. It is further understood that the term "connect" or its derivatives refer to both direct and indirect connection.

[0212] The term "and / or" may include a combination of a plurality of related listed items, or any plurality of related listed items. For example, "A and / or B" includes all three cases, such as "A," "B," and "A and B."

[0213] In this specification, unless otherwise specified, a singular term includes a plural term unless the context clearly indicates otherwise.

[0214] In embodiments of the present disclosure, "at least one of A and B" may refer to "at least one of A or B" or to "at least one of combinations of at least one of A and B." Furthermore, "one or more of A and B" may refer to "one or more of A or B" or "one or more combinations of one or more of A and B."

[0215] In the embodiment of the present disclosure, it is to be understood that a term such as "comprising" or "having" is intended to indicate the presence of the features, numbers, steps, operations, elements, parts, or combinations thereof described in the specification, and does not exclude the possibility of adding or having one or more other features, numbers, steps, operations, elements, parts, or combinations thereof.

[0216] According to an embodiment of the present disclosure, components may be combined with each other to be realized as a unit, or some components may be omitted.

[0217] The foregoing descriptions of specific embodiments of the present disclosure have been presented for purposes of illustration and description. They are not exhaustive and are not intended to limit the present disclosure to the precise forms disclosed, and obviously many modifications and changes are possible in light of the above teachings. The embodiments were chosen and described in order to explain certain principles of the invention and their practical application in order to enable others skilled in the art to make and use various embodiments of the present disclosure, as well as various alternatives and modifications thereof. It is intended that the scope of the present disclosure be determined by the claims appended hereto and their equivalents. Fig. 3. 301 first situation 311 second situation Fig. 5. 501 first situation 503 first LiDAR 505 first object 507 second object 509 point cloud 511 first point 513 second situation 515 second LiDAR 517 first object 519 second object Fig. 6. 601 first situation 603 first LiDAR 605 first object 607 second object 611 second situation 613 second LiDAR 615 first object 617 second object 619 third object Fig. 7. 701 first situation 703 first LiDAR 705 first object 707 second object 711 second situation 713 second LiDAR 715 first object 717 second object 721 third situation 723 third LiDAR 725 first object 727 second object Fig. 8. 801 LiDAR 803 first object 805 second object 807 first straight line Fig. 9. 901 first table 911 second table 921 Situation 923 LiDAR 925 first object 926 second object 927 third object Fig. 11. 1101 first row 1103 first graphic representation 1105 second graphic representation 1107 third graphic representation 1111 second row 1113 fourth graphic representation 1115 fifth graphic representation 1117 sixth graphic representation Fig. 12. 1201 first row 1203 first graphic representation 1205 first line 1207 second line 1209 second graphic representation 1211 second row 1213 third graphic representation 1215 third line 1217 fourth line 1219 fourth graphic representation Fig. 13. 1300 computer system

Claims

[1] Object recognition device, comprising: a Light Detection and Ranging (LiDAR); and a processor that is functionally connected to the LiDAR, wherein the processor is configured to: detect a first point that is the leftmost point, with respect to a host vehicle, in a point cloud obtained by the LiDAR and representing a first object, a second point that is the rightmost point, with respect to the host vehicle, in the point cloud representing the first object, a third point that is the leftmost point, with respect to the host vehicle, in a point cloud representing a second object, and a fourth point that is the rightmost point, with respect to the host vehicle, in the point cloud representing the second object; detect a first outer point closer to the second object that is one of the first point and the second point, and a second outer point closer to the first object that is one of the third point and the fourth point; detect an angle between a line segment connecting the first outer point and the LiDAR and a line segment connecting the second outer point and the LiDAR based on determining that the first outer point and the second outer point do not overlap; in response to the angle being less than or equal to a threshold angle, detect an object as an occluded object that is one of the first object and the second object, that corresponds to one of the first outer point and the second outer point that forms a longer distance among a distance between the first outer point and the LiDAR and a distance between the second outer point and the LiDAR; and to recognize an object other than the object recognized as the occluded object among the first object and the second object as an object that obscures the occluded object. [2] Object recognition device according to claim 1, wherein the processor is further configured to assign a reliability to the first object and assign a reliability to the second object with a value that is different from the reliability assigned to the first object based on a distance between a straight line connecting the first point and the second point and the LiDAR and a distance between a straight line connecting the third point and the fourth point and the LiDAR, based on a determination that the first outer point and the second outer point overlap each other, and wherein the reliability assigned to the first object and the reliability assigned to the second object are arranged to indicate whether a corresponding object is an object that occludes another object. [3] The object recognition device of claim 1, wherein the processor is further configured to: detect a point cloud representing at least one of the first object and the second object detected in a plane formed by a first axis and a second axis below the first axis, the second axis, and a third axis; and based on determining that an azimuth angle of the first outer point with respect to an origin corresponding to the LiDAR and the first axis is included in a range between an azimuth angle of the third point with respect to the origin and the first axis and an azimuth angle of the fourth point with respect to the origin and the first axis, to detect whether the first outer point and the second outer point overlap each other. [4] The object recognition device of claim 1, wherein the processor is further configured to: according to coordinates of the first point and coordinates of the second point, based on determining that the first outer point and the second outer point overlap each other, to detect a straight line passing through the first point and the second point; to assign to the second object a reliability corresponding to the number of third points or fourth points included in an area to which the LiDAR belongs, among two areas separated by the straight line; according to the coordinates of the third point and the coordinates of the fourth point, to identify a straight line passing through the third point and the fourth point; to assign to the first object a reliability comprising a value different from the reliability of the second object, equal to the number of first points or second points included in an area to which the LiDAR belongs, among two areas separated by the straight line passing through the third point and the fourth point; and to detect an object with a higher reliability value than an object that obscures another object by comparing a reliability value of the first object and a reliability value of the second object. [5] The object recognition device of claim 1, wherein the processor is further configured to: according to coordinates of the first point and coordinates of the second point, based on determining that the first outer point and the second outer point overlap each other, to recognize a first function which is a function of a straight line passing through the first point and the second point; assign to the second object a reliability corresponding to a number of equal signs, such as a sign of a value obtained by substituting coordinates of an origin corresponding to the LiDAR in the first function, a sign of a value obtained by substituting coordinates of the third point in the first function, and a sign of a value obtained by substituting coordinates of the fourth point in the first function; to recognize a second function, which is a function of a straight line passing through the third point and the fourth point, according to the coordinates of the third point and the coordinates of the fourth point; to assign to the first object a reliability corresponding to a number of equal signs, such as a sign of a value obtained by substituting the coordinates of the origin corresponding to the LiDAR into the second function, a sign of a value obtained by substituting the coordinates of the first point into the second function, and a sign of a value obtained by substituting the coordinates of the second point into the second function; and to detect an object with a higher reliability value than an object that obscures another object by comparing a reliability value of the first object and a reliability value of the second object. [6] The object recognition device of claim 1, wherein the processor is further configured to: detect a fan-shaped region comprising a point cloud included in a particular layer and representing the first object located on the far left with respect to the host vehicle and a point cloud included in the particular layer and representing the second object located on the far right with respect to the host vehicle, the fan-shaped region comprising a minimum central angle with respect to an origin corresponding to the LiDAR; and based on determining that the at least one point of a point cloud included in a plurality of layers including the specific layer and representing the first object and a point cloud included in the plurality of layers including the specific layer and representing the second object is located outside the fan-shaped region, to expand an area of ​​the fan-shaped region by increasing the central angle of the fan-shaped region to include at least one point located outside the fan-shaped region. [7] The object recognition device of claim 1, wherein the processor is further configured to: detect a fan-shaped region comprising a point cloud representing the first object located on the far left with respect to the host vehicle and a point cloud representing the second object located on the far right with respect to the host vehicle, including a minimum center angle with respect to an origin corresponding to the LiDAR; detect a fifth point, located to the far left of the host vehicle, in a point cloud representing a third object, and a sixth point, located to the far right of the host vehicle, in a point cloud representing the third object; detect a left angle between a line segment representing a left boundary of the fan-shaped area and a line segment connecting the fifth point and the LiDAR, or a right angle between a line segment representing a right boundary of the fan-shaped area and a line segment connecting the sixth point and the LiDAR; and detect the third object as being at the left boundary or on the right boundary based on the left angle or the right angle being less than or equal to a given angle. [8] The object recognition device of claim 1, wherein the processor is further configured to: to detect a point cloud representing the first object among points contained in a plurality of layers; and to detect a point cloud representing the second object among points included in the plurality of layers. [9] The object recognition device according to claim 1, wherein the processor is further configured to recognize the first outer point and the second outer point based on an angle between a line segment connecting the first point and the LiDAR and a line segment connecting the third point and the LiDAR, an angle between the line segment connecting the first point and the LiDAR and a line segment connecting the fourth point and the LiDAR, an angle between a line segment connecting the second point and the LiDAR and the line segment connecting the third point and the LiDAR, and an angle between the line segment connecting the second point and the LiDAR and the line segment connecting the fourth point and the LiDAR. [10] The object recognition device according to claim 7, wherein the processor is further configured to recognize a fourth object occluded by at least one object and to iteratively recognize a fifth object occluded by the fourth object based on a table representing the occluded object and the occluding object and the at least one object located at the left boundary or the right boundary. [11] Object recognition method, comprising: Detecting, by a processor, a first point that is a leftmost point with respect to a host vehicle in a point cloud obtained by light detection and ranging (LiDAR) and representing a first object, a second point that is a rightmost point with respect to the host vehicle in the point cloud representing the first object, a third point that is a leftmost point with respect to the host vehicle in a point cloud representing a second object, and a fourth point that is a rightmost point with respect to the host vehicle in the point cloud representing the second object; detecting, by the processor, a first outer point closer to the second object, which is one of the first point and the second point, and a second outer point closer to the first object, which is one of the third point and the fourth point; Detecting, by the processor, an angle between a line segment connecting the first outer point and the LiDAR and a line segment connecting the second outer point and the LiDAR based on determining that the first outer point and the second outer point do not overlap each other; Detecting, by the processor, an object as an occluded object that is one of the first object and the second object corresponding to one of the first outer point and the second outer point that forms a longer distance among a distance between the first outer point and the LiDAR and a distance between the second outer point and the LiDAR when the angle is less than or equal to a threshold angle; and Detecting, by the processor, an object other than the object detected as an occluded object among the first object and the second object as an object occluding the occluded object. [12] The object recognition method according to claim 11, further comprising: Assigning a reliability to the first object by the processor and assigning a reliability to the second object with a value different from the reliability assigned to the first object according to a distance between a straight line connecting the first point and the second point and the LiDAR and a distance between a straight line connecting the third point and the fourth point and the LiDAR, based on determining that the first outer point and the second outer point overlap each other, wherein the reliability assigned to the first object and the reliability assigned to the second object are arranged to indicate whether a corresponding object is an object that occludes another object. [13] The object recognition method according to claim 11, further comprising: detecting, by the processor, a point cloud representing at least one of the first object and the second object detected in a plane formed by a first axis and a second axis below the first axis, the second axis, and a third axis; and Detecting, by the processor, whether the first outer point and the second outer point overlap each other based on determining that an azimuth angle of the first outer point with respect to an origin corresponding to the LiDAR and the first axis is included in a range between an azimuth angle of the third point with respect to the origin and the first axis and an azimuth angle of the fourth point with respect to the origin and the first axis. [14] The object recognition method according to claim 11, further comprising: detecting, by the processor, a straight line passing through the first point and the second point according to coordinates of the first point and coordinates of the second point based on determining that the first outer point and the second outer point overlap each other; Assigning a reliability to the second object equal to the number of third points or fourth points included in an area to which the LiDAR belongs among two areas separated by the straight line; detecting, by the processor, a straight line passing through the third point and the fourth point according to coordinates of the third point and coordinates of the fourth point; Assigning a reliability to the first object by the processor with a different value than the reliability assigned to the second object equal to a number of the first points or the second points included in an area to which the LiDAR belongs among two areas separated by the straight line passing through the third point and the fourth point; and Detecting, by the processor, an object having a higher reliability value than an object occluding another object by comparing a reliability value of the first object and a reliability value of the second object. [15] The object recognition method according to claim 11, further comprising: detecting, by the processor, a first function that is a function of a straight line passing through the first point and the second point according to coordinates of the first point and coordinates of the second point based on determining that the first outer point and the second outer point overlap each other; Assigning a reliability to the second object by the processor equal to a number of signs equal to a sign of a value obtained by substituting coordinates of an origin corresponding to the LiDAR into the first function, a sign of a value obtained by substituting coordinates of the third point into the first function, and a sign of a value obtained by substituting coordinates of the fourth point into the first function; detecting, by the processor, a second function that is a function of a straight line passing through the third point and the fourth point, according to the coordinates of the third point and the coordinates of the fourth point; Assigning a reliability to the first object by the processor equal to a number of signs equal to a sign of a value obtained by substituting the coordinates of the origin corresponding to the LiDAR into the second function, a sign of a value obtained by substituting the coordinates of the first point into the second function, and a sign of a value obtained by substituting the coordinates of the second point into the second function; and Detecting, by the processor, an object having a higher reliability value than an object occluding another object by comparing a reliability value of the first object and a reliability value of the second object. [16] The object recognition method according to claim 11, further comprising: detecting, by the processor, a fan-shaped region comprising a point cloud included in a particular layer and representing the first object located on the far left with respect to the host vehicle and a point cloud included in the particular layer and representing the second object located on the far right with respect to the host vehicle, the fan-shaped region comprising a minimum central angle with respect to an origin corresponding to the LiDAR; and Expanding, by the processor, a region of the fan-shaped region by increasing the central angle of the fan-shaped region to include at least one point located outside the fan-shaped region based on determining that the at least one point of a point cloud included in a plurality of layers including the particular layer and representing the first object and a point cloud included in the plurality of layers including the particular layer and representing the second object is located outside the fan-shaped region. [17] The object recognition method according to claim 11, further comprising: detecting, by the processor, a fan-shaped region comprising a point cloud representing the first object located on the far left with respect to the host vehicle and a point cloud representing the second object located on the far right with respect to the host vehicle, including a minimum center angle with respect to an origin corresponding to the LiDAR; detecting, by the processor, a fifth point located at the far left of the host vehicle in a point cloud representing a third object and a sixth point located at the far right of the host vehicle in a point cloud representing the third object; Detecting, by the processor, a left angle between a line segment representing a left boundary of the fan-shaped region and a line segment connecting the fifth point and the LiDAR, or a right angle between a line segment representing a right boundary of the fan-shaped region and a line segment connecting the sixth point and the LiDAR; and Detecting the third object as being at the left boundary or at the right boundary based on the left angle or the right angle being less than or equal to a predetermined angle. [18] The object detection method according to claim 11, wherein detecting the first point, which is the leftmost point with respect to the host vehicle in the point cloud obtained by the LiDAR and representing the first object, the second point, which is the rightmost point with respect to the host vehicle in the point cloud representing the first object, the third point, which is the leftmost point with respect to the host vehicle in the point cloud representing the second object, and the fourth point, which is the rightmost point with respect to the host vehicle in the point cloud representing the second object, comprises: detecting, by the processor, a point cloud representing the first object from among points comprised in a plurality of layers; and detecting, by the processor, a point cloud representing the second object among the points included in the plurality of layers. [19] The object detection method according to claim 11, wherein detecting the first outer point closer to the second object, which is one of the first point and the second point, and the second outer point closer to the first object, which is one of the third point and the fourth point, comprises detecting the first outer point and the second outer point based on an angle between a line segment connecting the first point and the LiDAR and a line segment connecting the third point and the LiDAR, an angle between the line segment connecting the first point and the LiDAR and a line segment connecting the fourth point and the LiDAR, an angle between a line segment connecting the second point and the LiDAR and the line segment connecting the third point and the LiDAR, and an angle between the line segment connecting the second point and the LiDAR,and the line segment connecting the fourth point and the LiDAR. [20] The object recognition method according to claim 17, further comprising: Detecting, by the processor, a fourth object that is occluded by at least one object, and iteratively detecting a fifth object that is occluded by the fourth object based on a table representing the occluded object and the occluding object, and the at least one object that is located at the left boundary or at the right boundary.

Images