Apparatus for recognizing object and method thereof

Abstract

In an object recognition apparatus and method, the object recognition apparatus includes a LiDAR and a processor. The processor may identify a first point, a second point, a third point, and a fourth point, identify a first contour point and a second contour point, identify an angle between a line segment connecting the first contour point and the LiDAR and a line segment connecting the second contour point and the LiDAR, and when the angle is less than or equal to a threshold angle, identify a first contour point and a second contour point. An object that is one of the first object and the second object is recognized as an occluded object, and an object different from the object recognized as the occluded object among the first object and the second object is recognized as an object that occludes the occluded object.

Description

Technical Field

[0001] The present disclosure relates to object recognition apparatus and methods, and more particularly, to a technique for recognizing characteristics of an object represented by a point cloud obtained by light detection and ranging (LiDAR). Background Art

[0002] Autonomous vehicles or vehicles with activated driver assistance systems require technology to detect their surroundings and distinguish obstacles in order to adjust their driving path and avoid obstacles with minimal driver intervention.

[0003] The vehicle can obtain data indicating the position of objects / objects around the vehicle through light detection and ranging (LiDAR). The distance from the LiDAR to the object can be obtained by the interval between the time when the LiDAR emits laser light and the time when the laser light reflected by the object is received. The vehicle can identify the position of a point contained outside the object in the space where the vehicle is located based on the angle of the emitted laser light and the distance to the object.

[0004] An autonomously driven vehicle or a vehicle with an activated driver assistance device can recognize information about an object represented by a point based on the acquired position information of the point.

[0005] The information included in the Background of the disclosure is only for enhancement of understanding of the general background of the disclosure and should not be taken as an acknowledgement or any form of suggestion that this information constitutes the prior art already known to a person skilled in the art. Summary of the invention

[0006] Various aspects of the present disclosure are directed to providing an object recognition apparatus and method for recognizing 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 object recognition apparatus and method for improving the accuracy of determining whether an object represented by a point cloud is an object that occludes another object or an object that is occluded by another object by comparing confidence values ​​of multiple objects represented by the point clouds.

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

[0009] The technical problems to be solved by the present disclosure are not limited to the above-mentioned problems, and those skilled in the art to which the present disclosure belongs will clearly understand any other technical problems not mentioned herein through the following description.

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

[0011] According to an exemplary embodiment of the present disclosure, the processor can identify a first point, a second point, a third point, and a fourth point, wherein the first point is a point located at the leftmost side relative to the vehicle in a point cloud representing a first object obtained by the LiDAR, the second point is a point located at the rightmost side relative to the vehicle in a point cloud representing the first object, the third point is a point located at the leftmost side relative to the vehicle in a point cloud representing a second object, and the fourth point is a point located at the rightmost side relative to the vehicle in a point cloud representing the second object; and identify a first contour point closer to the second object and a second contour point closer to the first object, the first contour point being one of the first point and the second point, and the second contour point being one of the third point and the fourth point. one; based on recognizing that the first contour point and the second contour point do not overlap with each other, identifying an angle between a line segment connecting the first contour point and the LiDAR and a line segment connecting the second contour point and the LiDAR; in response to the angle being less than or equal to a threshold angle, identifying an object that is one of the first object and the second object as an occluded object, the object corresponding to one of the first contour point and the second contour point that forms a longer distance between the distance between the first contour point and the LiDAR and the distance between the second outer point and the LiDAR; and identifying an object, different from the object identified as the occluded object, among the first object and the second object as an object that occludes the occluded object.

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

[0013] According to an exemplary embodiment of the present disclosure, the processor can identify a point cloud, the point cloud representing at least one of the first object and the second object identified in a plane formed by the first axis and the second axis among the first axis, the second axis and the third axis; and identify whether the first contour point and the second contour point overlap with each other based on identifying that the azimuth of the first contour point relative to the origin corresponding to the LiDAR and the first axis is contained in a range between the azimuth of the third point relative to the origin and the first axis and the azimuth of the fourth point relative to the origin and the first axis.

[0014] According to an exemplary embodiment of the present disclosure, the processor may identify a straight line passing through the first point and the second point based on the coordinates of the first point and the coordinates of the second point based on recognizing that the first contour point and the second contour point overlap with each other; assign credibility to the second object according to the amount of the third point or the fourth point contained in the area to which the LiDAR belongs among the two areas separated by the straight line; identify 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; assign credibility having a value different from the credibility to the first object according to the amount of the first point or the second point contained in the area to which the LiDAR belongs among the two areas separated by the straight line passing through the third point and the fourth point; and identify the object with a larger credibility value as an object that occludes another object by comparing the value of the credibility of the first object with the value of the credibility of the second object.

[0015] According to an exemplary embodiment of the present disclosure, the processor may identify a first function, which is a function of a straight line passing through the first point and the second point, based on recognizing that the first contour point and the second contour point overlap each other, according to the coordinates of the first point and the coordinates of the second point; assign credibility to the second object by the number of signs that are the same as the sign of the value obtained by substituting the coordinates of the third point into the first function and the sign of the value obtained by substituting the coordinates of the fourth point into the first function; identify 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; assign credibility to the first object by the number of signs that are the same as the sign of the value obtained by substituting the coordinates of the first point into the second function and the sign of the value obtained by substituting the coordinates of the second point into the second function; and identify the object having a larger credibility value as an object that occludes another object by comparing the value of the credibility of the first object with the value of the credibility of the second object.

[0016] According to an exemplary embodiment of the present disclosure, the processor can identify a fan-shaped area including a point cloud contained in a specific layer and representing the first object located at the leftmost side relative to the vehicle, and a point cloud contained in a specific layer and representing the second object located at the rightmost side relative to the vehicle, the fan-shaped area including a minimum central angle relative to the origin corresponding to the LiDAR; and based on identifying that at least one point in the point cloud representing the first object contained in multiple layers including the specific layer and the point cloud representing the second object contained in multiple layers including the specific layer is located outside the fan-shaped area, the area of ​​the fan-shaped area is expanded by increasing the central angle of the fan-shaped area to include the at least one point located outside the fan-shaped area.

[0017] According to an exemplary embodiment of the present disclosure, the processor can identify a fan-shaped area including a point cloud representing the first object located at the leftmost side relative to the vehicle and a point cloud representing the second object located at the rightmost side relative to the vehicle, the fan-shaped area including a minimum center angle relative to the origin corresponding to the LiDAR; identify a fifth point located at the leftmost side relative to the vehicle in the point cloud representing the third object, and a sixth point located at the rightmost side relative to the vehicle in the point cloud representing the third object; identify 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 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; and based on the left angle or the right angle being less than or equal to a predetermined angle, identify the third object as being located on the left boundary or on the right boundary.

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

[0019] According to an exemplary embodiment of the present disclosure, the processor identifies the first contour point and the second contour point based on the following angles: 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 a 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 a line segment connecting the third point and the LiDAR, and an angle between a line segment connecting the second point and the LiDAR and a line segment connecting the fourth point and the LiDAR.

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

[0021] According to one aspect of the present disclosure, an object recognition method includes identifying a first point, a second point, a third point, and a fourth point, wherein the first point is obtained by a light detection and ranging device (LiDAR) and represents a point in a point cloud of a first object that is located at the leftmost relative to a vehicle, the second point is a point in a point cloud representing the first object that is located at the rightmost relative to the vehicle, the third point is a point in a point cloud representing a second object that is located at the leftmost relative to the vehicle, and the fourth point is a point in a point cloud representing the second object that is located at the rightmost relative to the vehicle; identifying a first contour point that is closer to the second object and a second contour point that is closer to the first object, the first contour point being one of the first point and the second point, and the second contour point being one of the third point and the fourth point. one of the points; identifying an angle between a line segment connecting the first contour point and the LiDAR and a line segment connecting the second contour point and the LiDAR based on recognizing that the first contour point and the second contour point do not overlap with each other; identifying an object that is one of the first object and the second object as an occluded object when the angle is less than or equal to a threshold angle, the object corresponding to one of the first contour point and the second contour point that forms a longer distance between the distance between the first contour point and the LiDAR and the distance between the second outer point and the LiDAR; and identifying an object that is different from the object identified as the occluded object among the first object and the second object as an object that occludes the occluded object.

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

[0023] According to an exemplary embodiment of the present disclosure, the object recognition method may further include: identifying a point cloud, the point cloud representing at least one of the first object and the second object recognized in a plane formed by the first axis and the second axis among the first axis, the second axis and the third axis; and identifying whether the first contour point and the second contour point overlap with each other based on recognizing that the azimuth of the first contour point relative to the origin corresponding to the LiDAR and the first axis is contained in a range between the azimuth of the third point relative to the origin and the first axis and the azimuth of the fourth point relative to the origin and the first axis.

[0024] According to an exemplary embodiment of the present disclosure, the object recognition method may further include: based on identifying that the first contour point and the second contour point overlap with each other, identifying 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; assigning credibility to the second object according to the number of the third point or the fourth point contained in the area to which the LiDAR belongs among the two areas separated by the straight line; identifying 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 credibility including a value different from the credibility assigned to the second object to the first object according to the number of the first point or the second point contained in the area to which the LiDAR belongs among the two areas separated by the straight line passing through the third point and the fourth point; and identifying the object with a larger credibility value as an object that occludes another object by comparing the value of the credibility of the first object with the value of the credibility of the second object.

[0025] According to an exemplary embodiment of the present disclosure, the object recognition method may further include: based on recognizing that the first contour point and the second contour point overlap each other, identifying a first function according to the coordinates of the first point and the coordinates of the second point, the first function being a function of a straight line passing through the first point and the second point; assigning credibility to the second object by the number of signs that are 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; identifying a second function according to the coordinates of the third point and the coordinates of the fourth point, the second function being a function of a straight line passing through the third point and the fourth point; assigning credibility to the first object by the number of signs that are the same as 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 by comparing the value of the credibility of the first object with the value of the credibility of the second object, identifying the object having a larger credibility value as an object that occludes another object.

[0026] According to an exemplary embodiment of the present disclosure, the object recognition method may further include: identifying a fan-shaped area including a point cloud contained in a specific layer and representing a first object located at the leftmost side relative to the vehicle and a point cloud contained in a specific layer and representing a second object located at the rightmost side relative to the vehicle, the fan-shaped area including a minimum central angle relative to the origin corresponding to the LiDAR; and based on identifying that at least one point in the point cloud representing the first object contained in multiple layers including the specific layer and the point cloud representing the second object contained in multiple layers including the specific layer is located outside the fan-shaped area, the area of ​​the fan-shaped area is expanded by increasing the central angle of the fan-shaped area to include the at least one point located outside the fan-shaped area.

[0027] According to an exemplary embodiment of the present disclosure, the object recognition device method may also include: identifying a fan-shaped area including a point cloud representing a first object located at the leftmost side relative to the vehicle and a point cloud representing a second object located at the rightmost side relative to the vehicle, the fan-shaped area including a minimum center angle relative to the origin corresponding to the LiDAR; identifying a fifth point located at the leftmost side relative to the vehicle in the point cloud representing a third object, and a sixth point located at the rightmost side relative to the vehicle in the point cloud representing the third object; identifying 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 based on the left angle or the right angle being less than or equal to a predetermined angle, identifying the third object as being located on the left boundary or on the right boundary.

[0028] According to an exemplary embodiment of the present disclosure, identifying the first point as the leftmost point relative to the vehicle in the point cloud obtained by the LiDAR and representing the first object, the second point as the rightmost point relative to the vehicle in the point cloud representing the first object, the third point as the leftmost point relative to the vehicle in the point cloud representing the second object, and the fourth point as the rightmost point relative to the vehicle in the point cloud representing the second object includes: identifying the point cloud representing the first object among points contained in multiple layers; and identifying the point cloud representing the second object among points contained in multiple layers.

[0029] According to an exemplary embodiment of the present disclosure, identifying the first contour point that is closer to the second object as one of the first point and the second point, and identifying the second contour point that is closer to the first object as one of the third point and the fourth point includes: identifying the first contour point and the second contour point based on the following angles: 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 a 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 a line segment connecting the third point and the LiDAR, and an angle between a line segment connecting the second point and the LiDAR and a line segment connecting the fourth point and the LiDAR.

[0030] According to an exemplary embodiment of the present disclosure, the object recognition device method may further include: based on a table representing the obstructed object and the obstructing object and at least one object located on the left boundary or the right boundary, identifying a fourth object obstructed by the at least one object and iteratively identifying a fifth object obstructed by the fourth object.

[0031] The method and apparatus of the present disclosure have other features and advantages that will be apparent from or set forth in more detail in the accompanying drawings and the following detailed description incorporated herein, which together serve to explain certain principles of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 is a block diagram illustrating an object recognition apparatus according to an exemplary embodiment of the present disclosure.

[0033] Figure 2 A flowchart showing the operation of an object recognition device for determining whether an object is an occluding object or an occluded object in an object recognition device or an object recognition method according to an exemplary embodiment of the present disclosure;

[0034] Figure 3 An example of contour points that may overlap with each other in an object recognition apparatus or an object recognition method according to an exemplary embodiment of the present disclosure is shown;

[0035] Figure 4 A flowchart showing the operation of an object recognition device for recognizing an object blocked by an object located at a left boundary or a right boundary based on a fan-shaped area in an object recognition device or an object recognition method according to an exemplary embodiment of the present disclosure;

[0036] Figure 5An example of enlarging the area of ​​a sector region based on contour points in an object recognition device or an object recognition method according to an exemplary embodiment of the present disclosure is shown;

[0037] Figure 6 An example of determination for identifying whether an object is occluding or being occluded by another object when contour points do not overlap with each other in an object recognition apparatus or an object recognition method according to an exemplary embodiment of the present disclosure is shown;

[0038] Figure 7 An example of determination for identifying whether an object is occluding or being occluded by another object when contour points overlap each other in an object recognition apparatus or an object recognition method according to an exemplary embodiment of the present disclosure is shown;

[0039] Figure 8 Another example of determination for identifying whether an object is occluding or being occluded by another object when contour points overlap each other in an object recognition apparatus or an object recognition method according to an exemplary embodiment of the present disclosure is shown;

[0040] Fig. 9 An example of iterative determination for identifying whether an object is blocking another object or is blocked by another object in an object recognition apparatus or an object recognition method according to an exemplary embodiment of the present disclosure is shown;

[0041] Fig.10 A flowchart showing the operation of an object recognition device for recognizing whether an object is occluding or being occluded by another object when contour points do not overlap with each other in an object recognition device or an object recognition method according to an exemplary embodiment of the present disclosure;

[0042] Fig.11 An example of comparing the accuracy of determination of an occluding object identified by an existing object recognition device or object recognition method with the accuracy of determination of an occluding object identified by an object recognition device or object recognition method according to an exemplary embodiment of the present disclosure is shown;

[0043] Fig.12 An example of the amount of calculation recognized by an existing object recognition device or object recognition method and an example of the amount of calculation recognized by an object recognition device or object recognition method according to an exemplary embodiment of the present disclosure are shown; and

[0044] Fig.13 A determination system related to an object recognition apparatus or an object recognition method according to an exemplary embodiment of the present disclosure is shown.

[0045] It will be appreciated that the drawings are not necessarily drawn to scale, but rather present somewhat simplified representations of various features illustrating the basic principles of the present disclosure. The specific design features of the present disclosure as included herein (including, for example, specific dimensions, orientations, locations, and shapes) will be determined in part by the particular intended application and use environment.

[0046] In the drawings, reference numerals refer to the same or equivalent parts of the present disclosure throughout the several views. DETAILED DESCRIPTION

[0047] Reference will now be made in detail to various embodiments of the present disclosure, examples of which are shown in the accompanying drawings and described below. Although the present disclosure will be described in conjunction with the exemplary embodiments of the present disclosure, it should be understood that this description is not intended to limit the present disclosure to those exemplary embodiments of the present disclosure. On the other hand, the present disclosure is intended to cover not only the exemplary embodiments of the present disclosure, but also various alternatives, modifications, equivalents and other embodiments that may be included within the spirit and scope of the present disclosure as defined by the appended claims.

[0048] Hereinafter, various exemplary embodiments of the present disclosure will be described in detail with reference to the exemplary drawings. When adding reference numerals to the components of each drawing, it should be noted that the same or equivalent components are designated by the same reference numerals even when they are shown on other drawings. In addition, when describing the exemplary embodiments of the present disclosure, detailed descriptions of well-known features or functions will be excluded so as not to unnecessarily obscure the gist of the present disclosure.

[0049] When describing the components of the exemplary embodiments of the present disclosure, terms such as first, second, "A", "B", (a), (b), etc. may be used. These terms are intended only to distinguish one component from another, and these terms do not limit the nature, order, or sequence of the constituent components. Unless otherwise defined, all terms (including technical or scientific terms) used herein include the same meanings as those commonly understood by those skilled in the art to which the present disclosure belongs. Such terms (such as those defined in commonly used dictionaries) should be interpreted as having the same meanings as the contextual meanings in the relevant technical field, and should not be interpreted as having ideal or overly formal meanings unless explicitly defined as having such meanings in this application.

[0050] In addition, the terms “unit”, “device”, “member”, “body” and the like used hereinafter may indicate at least one shape structure or may indicate a unit of a processing function.

[0051] In addition, in the embodiments of the present disclosure, the expression "greater than" or "less than" may be used to indicate whether a specific condition is satisfied or achieved, but is only used to indicate an example, and does not exclude "greater than or equal to" or "less than or equal to". The condition indicating "greater than or equal to" may be replaced with "greater than", the condition indicating "less than or equal to" may be replaced with "less than", and the 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" refers to at least one of the elements from A (including A) to B (including B).

[0052] In the following, reference will be made to Figures 1 to 13 Various exemplary embodiments of the present disclosure are described in detail.

[0053] Figure 1 is a block diagram illustrating an object recognition apparatus according to an exemplary embodiment of the present disclosure.

[0054] Reference Figure 1 According to an exemplary embodiment of the present disclosure, the object recognition device 101 may be implemented inside a vehicle. In this case, the object recognition device 101 may be formed integrally with an internal control unit of the vehicle, or may be implemented as a separate device and connected to the control unit of the vehicle through a separate connection device.

[0055] Reference Figure 1 , the object recognition device 101 may include a LiDAR 103 and a processor 105 .

[0056] According to an exemplary embodiment of the present disclosure, the processor 105 of the object recognition device 101 may obtain a point cloud representing an object through the LiDAR 103 .

[0057] According to an exemplary 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.

[0058] According to an exemplary embodiment of the present disclosure, the processor 105 of the object recognition device 101 can recognize multiple objects based on the point cloud. The processor 105 of the object recognition device 101 can recognize a first point and a second point, the first point is a point located at the leftmost relative to the vehicle in the point cloud representing the first object, and the second point is a point located at the rightmost relative to the vehicle in the point cloud representing the first object. The processor of the object recognition device can recognize a third point and a fourth point, the third point is a point located at the leftmost relative to the vehicle in the point cloud representing the second object, and the fourth point is a point located at the rightmost relative to the vehicle in the point cloud representing the second object.

[0059] According to an exemplary embodiment of the present disclosure, the processor 105 of the object recognition device 101 may recognize a first contour point closer to the second object, the first contour point being one of the first point and the second point. The processor 105 of the object recognition device 101 may recognize a second contour point closer to the first object, the second contour point being one of the third point and the fourth point.

[0060] According to an exemplary embodiment of the present disclosure, the processor 105 of the object recognition apparatus 101 may recognize whether the first contour point and the second contour point overlap each other. Figure 3 A method for identifying whether a first contour point and a second contour point overlap each other is described.

[0061] When the first contour point and the second contour point overlap each other, the processor 105 of the object recognition device 101 may recognize the reliability of the first object and the reliability of the second object based on the distance from the straight line connecting the first point and the second point to the LiDAR 103 and the distance from the straight line connecting the third point and the fourth point to the LiDAR 103. For example, the longer the distance between the straight line and the LiDAR 103, the lower the reliability may be assigned to the object corresponding to the straight line by the processor of the object recognition device.

[0062] The processor 105 of the object recognition device 101 can identify whether the first object is an object that blocks another object, or whether the first object is an object blocked by another object, based on the credibility assigned to the first object and the credibility assigned to the second object. The processor 105 of the object recognition device 101 can identify whether the second object is an object that blocks another object, or whether the second object is an object blocked by another object, based on the credibility assigned to the first object and the credibility assigned to the second object. For example, the object with a greater credibility between the first object and the second object can be the object that blocks the other object.

[0063] The following will refer to Figure 7 and Figure 8 A method of identifying whether an object occludes another object or is occluded by another object when a first outline point and a second outline point overlap each other is described.

[0064] When the first contour point and the second contour point do not overlap with each other, the processor 105 of the object recognition device 101 may recognize one of the first object and the second object as an occluding object and recognize the other of the first object and the second object as an occluded object based on the distance between the first contour point and the LiDAR 103 and the distance between the second contour point and the LiDAR 103. Figure 6A method of identifying whether an object occludes another object or identifying whether an object is occluded by another object when a first contour point and a second contour point do not overlap with each other is described.

[0065] According to an exemplary embodiment of the present disclosure, the processor 105 of the object recognition device 101 may store the ID of the object in a table showing the obstructed objects and the obstructing objects based on recognizing the object as an obstructing object. Fig. 9 Description A table showing occluded objects and occluding objects.

[0066] Figure 2 A flowchart showing the operation of an object recognition device for determining whether an object is an object that blocks another object or whether an object is blocked by another object in an object recognition device or an object recognition method according to an exemplary embodiment of the present disclosure.

[0067] In the following, it is assumed Figure 1 The object recognition device 101 performs Figure 2 In addition, Figure 2 In the description, the 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.

[0068] Reference Figure 2 In the first operation 201, the processor of the object recognition device according to various exemplary embodiments of the present disclosure may recognize a first contour point and a second contour point. To recognize the first contour point and the second contour point, the processor of the object recognition device may recognize a first point, a second point, a third point, and a fourth point.

[0069] In other words, the processor of the object recognition device can recognize a point cloud representing at least one of the first object and the second object recognized in a plane formed by the first axis and the second axis among the first axis, the second axis and the third axis. The first axis can be called the x-axis. The second axis can be called the y-axis. The third axis can be called the z-axis. The processor of the object recognition device can recognize a first point, a second point, a third point and a fourth point, the first point being the point located on the leftmost relative to the vehicle among the point cloud obtained via LiDAR and representing the first object, the second point being the point located on the rightmost relative to the vehicle among the point cloud representing the first object, the third point being the point located on the leftmost relative to the vehicle among the point cloud representing the second object, and the fourth point being the point located on the rightmost relative to the vehicle among the point cloud representing the second object. The processor of the object recognition device can recognize a first contour point and a second contour point, the first contour point being one of the first point and the second point close to the second object, and the second contour point being one of the third point and the fourth point close to the first object.

[0070] In the second operation 203, the processor of the object recognition device according to various exemplary embodiments of the present disclosure may identify whether the first contour point and the second contour point overlap with each other. When the first contour point and the second contour point overlap with each other, the processor of the object recognition device may perform a third operation 205. When the first contour point and the second contour point do not overlap with each other, the processor of the object recognition device may perform a fourth operation 209.

[0071] The processor of the object recognition device can recognize that the first contour point and the second contour point overlap with each other based on recognizing that the azimuth angle of the first contour point relative to the origin and the first axis corresponding to the LiDAR is included in the range between the azimuth angle of the third point relative to the origin and the first axis and the azimuth angle of the fourth point relative to the origin and the first axis.

[0072] According to an exemplary embodiment of the present disclosure, the first axis may be referred to as an x-axis, the second axis may be referred to as a y-axis, and the third axis may be referred to as a z-axis.

[0073] In the third operation 205 , the processor of the object recognition device according to various exemplary embodiments of the present disclosure may assign credibility to the first object and assign credibility to the second object.

[0074] According to an exemplary embodiment of the present disclosure, based on recognizing that the first contour point and the second contour point overlap each other, 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 second point. The processor of the object recognition device may assign credibility to the second object as much as the number of the third point or the fourth point included in the 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 credibility including a value different from the credibility of the second object to the first object according to the number of the first point or the second point included in the area to which the LiDAR belongs among the two areas separated by the straight line passing through the third point and the fourth point.

[0075] According to an exemplary embodiment of the present disclosure, based on recognizing that the first contour point and the second contour point overlap each other, the processor of the object recognition device may identify a first function based on the coordinates of the first point and the coordinates of the second point, the first function being a function of a straight line passing through the first point and the second point. The processor of the object recognition device may assign credibility to the second object by the number of symbols that are the same as the symbol of the value obtained by substituting the coordinates of the third point into the first function and the symbol of the value obtained by substituting the coordinates of the fourth point into the first function. The processor of the object recognition device may identify a second function based on the coordinates of the third point and the coordinates of the fourth point, the second function being a function of a straight line passing through the third point and the fourth point. The processor of the object recognition device may assign credibility to the first object by the number of symbols that are the same as the symbol of the value obtained by substituting the coordinates of the first point into the second function and the symbol of the value obtained by substituting the coordinates of the second point into the second function.

[0076] In the fifth operation 207, the processor of the object recognition device according to various exemplary embodiments of the present disclosure may be configured to determine an obstructed object and an obstructing object. The processor of the object recognition device may compare the credibility value of the first object and the credibility value of the second object, and recognize the object with a high credibility value as an object that obstructs the other object.

[0077] In the fourth operation 209, the processor of the object recognition device according to various exemplary embodiments of the present disclosure may identify whether the angle between the line segment connecting the first contour point and the LiDAR and the line segment connecting the second contour point and the LiDAR is less than or equal to a threshold angle. When the angle between the line segment connecting the first contour point and the LiDAR and the line segment connecting the second contour point and the LiDAR is less than or equal to the threshold angle, the processor of the object recognition device according to various exemplary embodiments of the present disclosure may perform a sixth operation 211. When the angle between the line segment connecting the first contour point and the LiDAR and the line segment connecting the second contour point and the LiDAR is greater than the threshold angle, the processor of the object recognition device according to various exemplary embodiments of the present disclosure may perform a seventh operation 213.

[0078] According to an exemplary embodiment of the present disclosure, the threshold angle may increase as the distance from the object to the LiDAR becomes shorter.

[0079] In a sixth operation 211 , the processor of the object recognition apparatus according to various exemplary embodiments of the present disclosure may recognize a distance between the first contour point and the LiDAR and a distance between the second contour point and the LiDAR.

[0080] In an eighth operation 215 , the processor of the object recognition device according to various exemplary embodiments of the present disclosure may be configured to determine an occluding object and an occluded object.

[0081] The processor of the object recognition device can identify an object that is one of the first object and the second object as an occluded object, the object corresponding to one of the first contour point and the second contour point that forms a longer distance between the distance between the first contour point and the LiDAR and the distance between the second outside and the LiDAR.

[0082] The processor of the object recognition device can recognize an object that is one of the first object and the second object as an occluding object, the object corresponding to one of the first contour point and the second contour point that forms a shorter distance between the distance between the first contour point and the LiDAR and the distance between the second outer part and the LiDAR. This is because the object located close to the LiDAR has a high probability of occluding the object located far from the LiDAR.

[0083] In the seventh operation 213, the processor of the object recognition device according to various exemplary embodiments of the present disclosure may not determine whether the object is an obstructed object or an obstructing object. This is because the first object does not obstruct the second object, and the second object does not obstruct the first object.

[0084] In a ninth operation 217 , the processor of the object recognition device according to various exemplary embodiments of the present disclosure may be configured to operate the host vehicle based on the blocking object and the blocked object.

[0085] Figure 3 An example of contour points that may overlap with each other in an object recognition apparatus or an object recognition method according to an exemplary embodiment of the present disclosure is shown.

[0086] Reference Figure 3 In the first state 301, the first contour point of the first object (e.g., point B in the first state 301) and the second contour point of the second object (e.g., point C in the first state 301) may overlap with each other. In the second state 311, the first contour point of the first object (e.g., point B in the second state 311) and the second contour point of the second object (e.g., point C in the second state 311) may not overlap with each other.

[0087] According to an exemplary embodiment of the present disclosure, a processor of the object recognition device may recognize a point cloud representing at least one of the first object and the second object recognized in a plane formed by the first axis and the second axis among the first axis, the second axis, and the third axis.

[0088] According to an exemplary embodiment of the present disclosure, the processor of the object recognition device can identify: a first point (for example, point A in the first state 301 or point A in the second state 311), which is obtained via LiDAR and represents the point in the point cloud of the first object that is located at the leftmost point relative to the vehicle; a second point (for example, point B in the first state 301 or point B in the second state 311), which is the point in the point cloud representing the first object that is located at the rightmost point relative to the vehicle; a third point (for example, point C in the first state 301 or point C in the second state 311), which is the point in the point cloud representing the second object that is located at the leftmost point relative to the vehicle; and a fourth point (for example, point D in the first state 301 or point D in the second state 311), which is the point in the point cloud representing the second object that is located at the rightmost point relative to the vehicle.

[0089] According to an exemplary embodiment of the present disclosure, the processor of the object recognition device can recognize: a first contour point (for example, point B in the first state 301 or point B in the second state 311), which is a point between the first point and the second point that is close to the second object; and a second contour point (for example, point C in the first state 301 or point C in the second state 311), which is a point between the third point and the fourth point that is close to the first object.

[0090] According to an exemplary embodiment of the present disclosure, the processor of the object recognition device can recognize that the azimuth of the first contour point (e.g., point B in the first condition 301) relative to the origin and the first axis corresponding to the LiDAR is included in the range between the azimuth of the third point (e.g., point C in the first condition 301) relative to the origin and the first axis and the azimuth of the fourth point (e.g., point D in the first condition 301) relative to the origin and the first axis, so as to recognize that the first contour point (e.g., point B in the first condition 301) and the second contour point (e.g., point C in the first condition 301) overlap with each other.

[0091] According to an exemplary embodiment of the present disclosure, the processor of the object recognition device can recognize that: the azimuth angle of the first contour point (for example, point B in the second condition 311) relative to the origin and the first axis corresponding to the LiDAR is not included in the range between the azimuth angle of the third point (for example, point C in the second condition 311) relative to the origin and the first axis and the azimuth angle of the fourth point (for example, point D in the second condition 311) relative to the origin and the first axis, so as to recognize that the first contour point (for example, point B in the second condition 311) and the second contour point (for example, point C in the second condition 311) do not overlap with each other.

[0092] According to an exemplary embodiment of the present disclosure, when the angle between the line segment connecting the first contour point (e.g., point B in the second condition 311) and the LiDAR and the line segment connecting the second contour point (e.g., point C in the second condition 311) and the LiDAR is less than or equal to a threshold angle, one of the first object and the second object may be identified as an occluded object, and the other object may be identified as an occluding object.

[0093] According to an exemplary embodiment of the present disclosure, a method of identifying an occluding object among the first object and the second object when a first contour point (e.g., point B in the first state 301) and a second contour point (e.g., point C in the first state 301) overlap with each other may be different from a method of identifying an occluding object among the first object and the second object when the first contour point (e.g., point B in the second state 311) and the second contour point (e.g., point C in the second state 311) do not overlap.

[0094] Figure 4 A flowchart showing the operation of an object recognition device for recognizing an object blocked by an object located at a left boundary or a right boundary based on a fan-shaped area in an object recognition device or an object recognition method according to an exemplary embodiment of the present disclosure is shown.

[0095] In the following, it is assumed Figure 1 The object recognition device 101 performs Figure 4 In addition, Figure 4 In the description, the 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.

[0096] Reference Figure 4 In a first operation 401, a processor of an object recognition device according to various exemplary embodiments of the present disclosure may obtain a point cloud via LiDAR.

[0097] According to an exemplary embodiment of the present disclosure, a processor of an object recognition device may recognize a sector-shaped area including a point cloud that is included in a specific layer and represents a first object located at the far left relative to the vehicle, and a point cloud that is included in a specific layer and represents a second object located at the far right relative to the vehicle, the sector-shaped area including a minimum center angle relative to an origin corresponding to the LiDAR. The sector-shaped area may be recognized based on the point cloud included in the specific layer.

[0098] In the second operation 403 , the processor of the object recognition device according to various exemplary embodiments of the present disclosure may recognize a first point, a second point, a third point, a fourth point, a first contour point, and a second contour point.

[0099] According to an exemplary embodiment of the present disclosure, the processor of the object recognition device may recognize a point cloud representing a first object among points included in a plurality of layers including a specific layer (for example, all layers including points representing objects). The processor of the object recognition device may recognize a point cloud representing a second object among points included in a plurality of layers including the specific layer.

[0100] According to an exemplary embodiment of the present disclosure, a processor of an object recognition device may recognize points forming two line segments as first contour points and second contour points, wherein the two line segments form a minimum angle among the following angles: 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 a 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 a line segment connecting the third point and the LiDAR, and an angle between a line segment connecting the second point and the LiDAR and a line segment connecting the fourth point and the LiDAR.

[0101] In a third operation 405 , the processor of the object recognition device according to various exemplary embodiments of the present disclosure may expand the area of ​​the sector-shaped region.

[0102] The processor of the object recognition device can expand the area of ​​the fan-shaped area by increasing the central angle of the fan-shaped area to include at least one point located outside the fan-shaped area, based on recognizing that at least one point in the point cloud representing the first object contained in multiple layers including the specific layer and the point cloud representing the second object contained in multiple layers including the specific layer is located outside the fan-shaped area.

[0103] In a fourth operation 407 , the processor of the object recognition device according to various exemplary embodiments of the present disclosure may recognize whether the third object is located at the left boundary or the right boundary.

[0104] According to an exemplary embodiment of the present disclosure, the processor of the object recognition device can recognize the fifth point located at the leftmost relative to the vehicle in the point cloud representing the third object and the sixth point located at the rightmost relative to the vehicle in the point cloud representing the third object.

[0105] According to an exemplary embodiment of the present disclosure, the processor of the object recognition device can identify the left angle between the line segment representing the left boundary of the fan-shaped area and the line segment connecting the fifth point and the LiDAR, or identify the right angle between the line segment representing the right boundary of the fan-shaped area and the line segment connecting the sixth point and the LiDAR.

[0106] According to an exemplary 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.

[0107] According to an exemplary embodiment of the present disclosure, the processor of the object recognition device may store the ID of the object located at the left boundary or the right boundary in a table.

[0108] In a fifth operation 409 , the processor of the object recognition device according to various exemplary embodiments of the present disclosure may recognize whether at least one of the first object and the second object is an occluding object and an occluded object.

[0109] According to an exemplary embodiment of the present disclosure, a processor of an object recognition device may differently execute a method of recognizing whether an object is blocking another object or being blocked by another object when a first contour point and a second contour point overlap with each other, and a method of recognizing whether an object is blocking another object or being blocked by another object when the first contour point and the second contour point do not overlap with each other.

[0110] In a sixth operation 411 , the processor of the object recognition device according to various exemplary embodiments of the present disclosure may recognize an object blocked by an object on a left boundary or a right boundary and an object blocked iteratively.

[0111] According to an exemplary embodiment of the present disclosure, based on a table representing occluded objects and occluding objects and at least one object located on the left boundary or the right boundary, a processor of the object recognition device can recognize a fourth object occluded by the at least one object and iteratively recognize a fifth object occluded by the fourth object.

[0112] For example, the processor of the object recognition device may recognize a fifth object that is obstructed by the fourth object based on a table representing obstructed objects and obstructing objects.

[0113] In a seventh operation 413 , the processor of the object recognition device according to various exemplary embodiments of the present disclosure may operate the host vehicle based on the blocking object and the blocked object.

[0114] Figure 5 An example of enlarging the area of ​​a sector-shaped region based on contour points in an object recognition apparatus or an object recognition method according to an exemplary embodiment of the present disclosure is shown.

[0115] Reference Figure 5In the first situation 501, the processor of the object recognition device may recognize a first point 511 through the first LiDAR 503, the first point 511 being a point located at the leftmost relative to the vehicle in the point cloud 509 representing the first object 505 in the first situation 501. The processor of the object recognition device may recognize a second point through the first LiDAR 503, the second point being a point located at the rightmost relative to the vehicle in the point cloud 509 representing the first object 505 in the first situation 501. The processor of the object recognition device may recognize a third point through the first LiDAR 503, the third point being a point located at the leftmost relative to the vehicle in the point cloud representing the second object 507 in the first situation 501, and recognize a fourth point through the first LiDAR 503, the fourth point being a point located at the rightmost relative to the vehicle in the point cloud representing the second object 507 in the first situation 501.

[0116] In the second condition 513 , the processor of the object recognition device may expand the area of ​​the sector-shaped region based on the point cloud representing the first object 517 in the second condition 513 and obtained by the second LiDAR 515 and the point cloud representing the second object 519 in the second condition 513 and obtained by the second LiDAR 515 .

[0117] In the first situation 501, the processor of the object recognition device may recognize: a first point, which is a point located at the leftmost relative 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, which is a point located at the rightmost relative to the host vehicle in the point cloud representing the first object 505 in the first situation 501; a third point, which is a point located at the leftmost relative to the host vehicle in the point cloud representing the second object 507 in the first situation 501; and a fourth point, which is a point located at the rightmost relative 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 referred to as angle critical points (ACPs), but embodiments of the present disclosure may not be limited thereto.

[0118] According to an exemplary embodiment of the present disclosure, the first point may include a maximum azimuth angle relative to the origin corresponding to the first LiDAR 503 and the first axis among the point cloud representing the first object 505 in the first situation 501. The second point may include a minimum azimuth angle relative to the first axis among the point cloud representing the first object 505 in the first situation 501. The first axis may be referred to as an x-axis.

[0119] Furthermore, according to an exemplary embodiment of the present disclosure, the processor of the object recognition device may recognize a sector-shaped area including a point cloud of a first object 505 included in a specific layer and representing a first state 501 located at the leftmost relative to the host vehicle and a point cloud of a second object 507 included in a specific layer and representing a first state 501 located at the rightmost relative to the host vehicle, the sector-shaped area including a minimum central angle relative to the origin corresponding to the first LiDAR 503. The sector-shaped area may be recognized based on the point cloud included in the specific layer.

[0120] In the second state 513, the processor of the object identification device can expand the area of ​​the fan-shaped area by increasing the central angle of the fan-shaped area to include at least one point located outside the fan-shaped area, based on identifying that at least one point is located outside the fan-shaped area in the point cloud of the first object 517 representing the second state 513 contained in multiple layers including the specific layer (for example, all layers including points representing objects) and the point cloud of the second object 519 representing the second state 513 contained in multiple layers including the specific layer.

[0121] According to an exemplary embodiment of the present disclosure, as time passes, the second object 507 in the first state 501 may move to the position of the second object 519 in the second state 513 .

[0122] Figure 6 An example of determination for identifying whether an object is blocking or being blocked by another object when contour points do not overlap with each other in an object recognition device or an object recognition method according to an exemplary embodiment of the present disclosure is shown.

[0123] Reference Figure 6 In the first situation 601, the processor of the object recognition device can recognize the first object 605 of the first situation 601 and the second object 607 of the first situation 601 based on the point cloud obtained by the first LiDAR 603. The processor of the object recognition device can recognize that the second object 607 in the first situation 601 is located at the right boundary of the fan-shaped area.

[0124] In the second state 611, the processor of the object recognition device may recognize the first object 615, the second object 617, and the third object 619 through the second LiDAR 613. The processor of the object recognition device may recognize the occluding object and the occluded object among the first object 615, the second object 617, and the third object 619.

[0125] According to an exemplary embodiment of the present disclosure, the processor of the object recognition device can recognize: the fifth point, which is the leftmost point in the point cloud representing the second object 607 in the first condition 601 relative to the vehicle; and the sixth point, which is the rightmost point in the point cloud representing the second object 607 in the first condition 601 relative to the vehicle.

[0126] According to an exemplary embodiment of the present disclosure, the processor of the object recognition device can identify the left angle between the line segment representing the left boundary of the fan-shaped area and the line segment connecting the fifth point and the first LiDAR 603, or identify the right angle between the line segment representing the right boundary of the fan-shaped area and the line segment connecting the sixth point and the first LiDAR 603.

[0127] According to an exemplary embodiment of the present disclosure, the processor of the object recognition device can recognize that the second object 607 in the first situation 601 is not located at the left boundary based on the left angle being greater than or equal to the predetermined angle. The processor of the object recognition device can recognize that the second object 607 in the first situation 601 is located at the right boundary based on the right angle being less than or equal to the predetermined angle.

[0128] According to an exemplary embodiment of the present disclosure, the processor of the object recognition device may store the ID of the second object 607 located at the right boundary of the first state 601 in a table. The table may be referred to as a field of view (FOV) list, but the embodiments of the present disclosure may not be limited thereto.

[0129] According to an exemplary embodiment of the present disclosure, the processor of the object recognition device can identify whether there is an object that blocks another object or is blocked by another object among the first object 615 of the second state 611, the second object 617 of the second state 611, and the third object 619 of the second state 611.

[0130] According to an exemplary embodiment of the present disclosure, a processor of an object recognition device may differently execute a method of recognizing whether an object is an occluding object or an occluded object when a first contour point and a second contour point overlap with each other, and a method of recognizing whether an object is an occluding object or an occluded object when the first contour point and the second contour point do not overlap with each other.

[0131] According to an exemplary embodiment of the present disclosure, when the first contour points of the first object 615 of the second condition 611 and the second contour points of the second object 617 of the second condition 611 do not overlap with each other, the processor of the object recognition device may not recognize whether at least one of the first object 615 of the second condition 611 and the second object 617 of the second condition 611 is an occluding object or an occluded object based on recognizing that the angle (for example, θ1) between the straight line connecting the first contour points of the first object 615 of the second condition 611 and the second LiDAR 613 and the straight line connecting the second contour points of the second object 617 of the second condition 611 and the second LiDAR 613 is greater than or equal to a threshold angle.

[0132] According to an exemplary embodiment of the present disclosure, when the first contour points of the second object 617 of the second condition 611 and the second contour points of the third object 619 of the second condition 611 do not overlap with each other, the processor of the object recognition device can identify whether at least one of the second object 617 of the second condition 611 and the second object 619 of the second condition 611 is an occluding object or an occluded object based on recognizing that the angle (for example, θ2) between the straight line connecting the first contour points of the second object 617 of the second condition 611 and the second LiDAR 613 and the straight line connecting the second contour points of the third object 619 of the second condition 611 and the second LiDAR 613 is less than or equal to a threshold angle.

[0133] 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 obstructed object, the third object corresponding to the contour point with a longer distance between the distance between the first contour point of the second object 617 forming the second situation 611 and the second LiDAR 613 and the distance between the second contour point of the third object 619 in 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 the object recognized as the obstructed object, among the second object 617 in the second situation 611 and the third object 619 in the second situation 611, as an obstructing object.

[0134] Will refer to Figure 7 A method is described in which a processor of an object recognition device according to an exemplary embodiment recognizes whether at least one of the second object 617 of the second condition 611 and the second object 619 of the second condition 611 is an occluding object or an occluded object when a first contour point of a second object 617 of the second condition 611 and a second contour point of a third object 619 of the second condition 611 overlap with each other.

[0135] The processor of the object recognition device may store the relationship between the occluding object and the occluded object in a table. The table may be referred to as an occlusion map, but the embodiments of the present disclosure may not be limited thereto. The processor of the object recognition device may assign a specified first value (e.g., approximately 1) to the row and column in the table corresponding to the object being the occluded object. The processor of the object recognition device may assign a second value (e.g., approximately -1) to the row and column in the table corresponding to the object being the occluding object. The processor of the object recognition device may assign a third value (e.g., approximately 0) to the row and column in the table corresponding to the object that is neither the occluding object nor the occluded object.

[0136] Figure 7 An example of determination for identifying whether an object is shielding or being shielded by another object when contour points overlap each other is shown in an object recognition apparatus or an object recognition method according to an exemplary embodiment of the present disclosure.

[0137] Reference Figure 7 , in the first situation 701 , a first contour point of a first object 705 of the first situation 701 identified by the first LiDAR 703 and a second contour point of a second object 707 of the first situation 701 may overlap with each other.

[0138] In the second situation 711, the processor of the object recognition device may recognize that the first contour point of the first object 715 and the second contour point of the second object 717 recognized by the second LiDAR 713 overlap with each other. In the second situation 711, the processor of the object recognition device may recognize whether the first object 715 or the second object 717 is an object that is blocking the other object or is blocked by the other object based on the distance from the straight line connecting the first point of the first object 715 and the second point of the first object 715 to the second LiDAR 713 and the distance from the straight line connecting the third point of the second object 717 and the fourth point of the second object 717 to the second LiDAR 713.

[0139] In the third situation 721 , the processor of the object recognition device may recognize that the first contour point of the first object 725 and the second contour point of the second object 727 recognized via the third LiDAR 723 overlap with each other. The processor of the object recognition device may recognize whether the first object 725 or the second object 727 is an object that is blocking another object or is blocked by another object based on the following distances: a distance from a point where a straight line connecting a first point of the first object 725 and the third LiDAR 723 intersects a straight line connecting a third point and a fourth point of the second object 727 to the third LiDAR 723, a distance from a point where a straight line connecting a second point of the first object 725 and the third LiDAR 723 intersects a straight line connecting the third point of the second object 727 and the fourth point of the second object 727 to the third LiDAR 723, a distance from a point where a straight line connecting the third point of the second object 727 and the third LiDAR 723 intersects a straight line connecting the first point of the first object 725 and the second point of the first object 725 to the third LiDAR 723, or a distance from a point where a straight line connecting the fourth point of the second object 727 and the third LiDAR 723 intersects The distance from the point where the straight line 723 intersects the straight line connecting the first point of the first object 725 and the second point of the first object 725 to the third LiDAR 723.

[0140] According to an exemplary embodiment of the present disclosure, in the first situation 701, the processor of the object recognition device may not be able to recognize which one of the first object 705 and the second object 707 is the occluding object or the occluded object simply by comparing the distance between the first contour point of the first object 705 and the first LiDAR 703 and the distance between the second contour point of the second object 707 and the first LiDAR 703. This is because the first contour point and the second contour point overlap each other.

[0141] When the processor of the object recognition device identifies the occluding object and the occluded object simply based on comparing the distance between the first contour point of the first object 705 and the first LiDAR 703 and the distance between the second contour point of the second object 707 and the first LiDAR 703, the processor of the object recognition device may perceive a correlation different from the actual correlation.

[0142] According to an exemplary embodiment of the present disclosure, in the second situation 711, the processor of the object recognition device may recognize that a first contour point of the first object 715 in the second situation 711 (e.g., B in the second situation 711) and a second contour 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 may recognize the second object 717 in the second situation 711 corresponding to a longer distance among the following distances: a distance from a straight line connecting a first point of the first object 715 in the second situation 711 (e.g., A in the second situation 711) 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 (e.g., C in the second situation 711) and a fourth point of the second object 717 (e.g., D in the second situation 711) to the second LiDAR 713 as an object blocked by the first object 715 in the second situation 711.

[0143] The processor of the object recognition device can identify the first object 715 of the second condition 711 corresponding to the shorter distance among the following distances: the distance from the straight line connecting the first point of the first object 715 in the second condition 711 and the second point of the first object 715 to the second LiDAR 713, and the distance from the straight line connecting the third point of the second object 717 and the fourth point of the second object 717 to the second LiDAR 713.

[0144] According to an exemplary embodiment of the present disclosure, in the third situation 721, the processor of the object recognition device may recognize that a first contour point (e.g., B in the third situation 721) of the first object 725 in the third situation 721 and a second contour point (e.g., C in the third situation 721) of the second object 727 in the third situation 721 overlap each other. The processor of the object recognition device may recognize a first projection point (e.g., E in the third situation 721), which is a point where a straight line connecting a first point (e.g., A in the third situation 721) of the first object 725 in the third situation 721 and the third LiDAR 723 intersects 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.

[0145] The processor of the object recognition device may recognize 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 in the third situation 721 to the third LiDAR 723 and the distance from the second point of the first object 725 in the third situation 721 to the third LiDAR 723. The processor of the object recognition device may recognize the first object 725 in the third situation 721 as an object that is blocking another object (e.g., the second object 727 in the third situation 721) based on recognizing 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 in the third situation 721 to the third LiDAR 723 and the distance from the second point of the first object 725 in the third situation 721 to the third LiDAR 723.

[0146] The processor of the object recognition device can identify a second projection point, which is a point where a straight line connecting the first point of the second object 727 of the third situation 721 and the third LiDAR 723 intersects a straight line connecting the first point and the second point of the first object 725 of the third situation 721.

[0147] The processor of the object recognition device can identify the second object 727 in the third condition 721 as an object obscured by another object (for example, the first object 725 in the third condition 721) based on recognizing 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 in the third condition 721 to the third LiDAR 723, or is less than or equal to the distance from the second point of the first object 725 in the third condition 721 to the third LiDAR 723.

[0148] The following will refer to Figure 8 Another method of identifying an object as an occluding object or an occluded object based on identifying that a first contour point and a second contour point overlap each other is described.

[0149] Figure 8 Another example of determination for identifying whether an object is blocking or being blocked by another object when contour points overlap each other in an object recognition apparatus or an object recognition method according to an exemplary embodiment of the present disclosure is shown.

[0150] Reference Figure 8 , the processor of the object recognition device may recognize at least one of the first object 803 and the second object 805 as an obstructed object or an obstructing object based on recognizing that the first contour point of the first object 803 obtained by the LiDAR 801 and the second contour point of the second object 805 obtained by the LiDAR 801 overlap each other. The first straight line 807 may represent a straight line connecting the first point and the second point of the first object 803.

[0151] According to an exemplary embodiment of the present disclosure, the processor of the object recognition device can identify 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 can be located at the far left relative to the vehicle in the point cloud representing the first object 803. The second point can be located at the far right relative to the vehicle in the point cloud representing the first object 803. The third point can be located at the far left relative to the vehicle in the point cloud representing the second object 805. The fourth point can be located at the far right relative to the vehicle in the point cloud representing the second object 805.

[0152] According to an exemplary embodiment of the present disclosure, the processor of the object recognition device can identify whether the first object 803 or the second object 805 is an occluded object or an occluding object based on recognizing that the first contour point (e.g., point B) and the second contour point (e.g., point C) overlap with each other.

[0153] According to an exemplary embodiment of the present disclosure, based on recognizing that the first contour point and the second contour point overlap each other, the processor of the object recognition device may recognize a 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. The processor of the object recognition device may assign credibility to the second object 805 according to the number of third points of the second object 805 or fourth points of the second object 805 included in the area to which the LiDAR 801 belongs, among the two areas separated by the first straight line 807.

[0154] The processor of the object recognition device may recognize a second straight line passing through the third point and the fourth point based on 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 may assign a credibility including a value different from the credibility of the second object 805 to the first object 803 according to the number of the first point of the first object 803 or the second point of the first object 803 included in the area to which the LiDAR 801 belongs, out of the two areas separated by the second straight line passing through the third point and the fourth point.

[0155] The processor of the object recognition device can identify the first object 803 with a larger credibility value as an object that blocks another object by comparing the credibility value of the first object 803 with the credibility value of the second object 805. The processor of the object recognition device can identify the second object 805 with a lower credibility value as an object blocked by another object by comparing the credibility value of the first object 803 with the credibility value of the second object 805.

[0156] Fig. 9An example of iterative determination for identifying whether an object is blocking another object or is blocked by another object in an object recognition apparatus or an object recognition method according to an exemplary embodiment of the present disclosure is shown.

[0157] Reference Fig. 9 , the first table 901 may indicate the ID of the object located on the left boundary or the right boundary. The first table 901 may be referred to as a field of view (FOV) list, but the embodiments of the present disclosure may not be limited thereto.

[0158] The second table 911 may indicate the correlation between the blocked objects and the blocking objects. The second table 911 may be referred to as an occlusion map, but the embodiments of the present disclosure may not be limited thereto.

[0159] In state 921 , the processor of the object recognition device may recognize a first object 925 , a second object 926 , and a third object 927 through LiDAR 923 .

[0160] The processor of the object recognition device can identify the second object 926 as being blocked by the first object 925 located on the left or right boundary by referring to the first table 901 and the second table 911. The processor of the object recognition device can iteratively identify a fourth object blocked by the second object 926 by referring to the first table 901 and the second table 911.

[0161] The processor of the object recognition device may assign a first value (e.g., approximately 1) to the row and column representing the occluded object in the second table 911. The processor of the object recognition device may assign a second value (e.g., approximately -1) to the row and column representing the occluding object in the second table 911. The processor of the object recognition device may assign a third value (e.g., approximately 0) to the row and column representing the object that is neither the occluding object nor the occluded object in the second table 911.

[0162] According to an exemplary embodiment of the present disclosure, when the first object 925 and the second object 926 do not overlap with each other, the processor of the object recognition device can recognize that the first object 925 is an object that obscures the second object 926 and the second object 926 is an object obscured by the first object 925 based on recognizing that the angle (e.g., θ) between the line segment connecting the first contour point of the first object 925 and the LiDAR 923 and the line segment connecting the second contour point of the second object 926 and the LiDAR 923 is less than a threshold angle.

[0163] Fig.10 A flowchart showing the operation of an object recognition apparatus for recognizing whether an object is occluding or being occluded by another object when contour points do not overlap with each other in an object recognition apparatus or an object recognition method according to an exemplary embodiment of the present disclosure.

[0164] In the following, it is assumed Figure 1 The object recognition device 101 performs Fig.10 In addition, Fig.10 In the description, the 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.

[0165] Reference Fig.10 In a first operation 1001, a processor of an object recognition device according to various exemplary embodiments of the present disclosure may recognize a first point, a second point, a third point, and a fourth point.

[0166] According to an exemplary embodiment of the present disclosure, a processor of an object recognition device can recognize: a first point, which is obtained via LiDAR and is located at the leftmost point relative to the vehicle in a point cloud representing a first object; a second point, which is located at the rightmost point relative to the vehicle in the point cloud representing the first object; a third point, which is located at the leftmost point relative to the vehicle in the point cloud representing a second object; and a fourth point, which is located at the rightmost point relative to the vehicle in the point cloud representing the second object.

[0167] In the second operation 1003 , the processor of the object recognition apparatus according to various exemplary embodiments of the present disclosure may recognize a first contour point and a second contour point.

[0168] According to an exemplary embodiment of the present disclosure, the processor of the object recognition device can recognize: a first contour point closer to the second object, which is one of the first point and the second point; and a second contour point closer to the first object, which is one of the third point and the fourth point.

[0169] In the third operation 1005 , the processor of the object recognition apparatus according to various exemplary embodiments of the present disclosure may recognize an angle between a line segment connecting the first contour point and the LiDAR and a line segment connecting the second contour point and the LiDAR.

[0170] According to an exemplary embodiment of the present disclosure, the processor of the object recognition device may recognize an angle between a line segment connecting the first contour point and the LiDAR and a line segment connecting the second contour point and the LiDAR based on recognizing that the first contour point and the second contour point do not overlap with each other.

[0171] In the fourth operation 1007, the processor of the object recognition device according to various exemplary embodiments of the present disclosure may identify whether the angle is greater than a threshold angle. The angle may include an angle between a line segment connecting the first contour point and the LiDAR and a line segment connecting the second contour point and the LiDAR. When the angle is not greater than the threshold angle, the processor of the object recognition device may perform a fifth operation 1009. When the angle is greater than the threshold angle, the processor of the object recognition device may not identify an occluding object and an occluded object among the first object and the second object.

[0172] In a fifth operation 1009 , the processor of the object recognition apparatus according to various exemplary embodiments of the present disclosure may recognize an object corresponding to contour points forming a long distance as an occluded object.

[0173] According to an exemplary embodiment of the present disclosure, the processor of the object recognition device can identify an object that is one of the first object and the second object as an occluded object, which object corresponds to a contour point among the first contour point and the second contour point that forms a longer distance between the distance between the first contour point and the LiDAR and the distance between the second outside and the LiDAR.

[0174] In a sixth operation 1011 , the processor of the object recognition device according to various exemplary embodiments of the present disclosure may recognize an object recognized as an object blocked by another object and an object recognized as an object blocking another object.

[0175] According to an exemplary embodiment of the present disclosure, the processor of the object recognition device may recognize which one of the first object and the second object is an object blocked by the other object or an object blocking the other object.

[0176] According to an exemplary embodiment of the present disclosure, when the angle is greater than a threshold angle, the processor of the object recognition device may recognize that the first object and the second object do not block each other.

[0177] In a seventh operation 1013 , the processor of the object recognition device according to various exemplary embodiments of the present disclosure may operate the host vehicle based on the first object or the second object.

[0178] In an eighth operation 1015 , the processor of the object recognition device according to various exemplary embodiments of the present disclosure may operate the host vehicle based on the blocking object and the blocked object.

[0179] Fig.11 An example is shown of comparing the accuracy of determination of an occluding object recognized by an existing object recognition apparatus or object recognition method with the accuracy of determination of an occluding object recognized by an object recognition apparatus or object recognition method according to an exemplary embodiment of the present disclosure.

[0180] Reference Fig.11 , the first diagram 1103 in the first row 1101 may show the non-recognition rate of objects identified by the object recognition device or object recognition method according to the exemplary embodiment and located on the left or right boundary of the fan-shaped area, and the non-recognition rate of objects identified by the existing object recognition device or object recognition method and located on the left or right boundary of the fan-shaped area. The non-recognition rate may refer to the ratio of failure to recognize an object.

[0181] According to an exemplary embodiment of the present disclosure, "basic" may indicate a case where the object is a passenger car. "Bus" may indicate a case where the object is a bus. "Special car" may indicate a case where the object is a vehicle such as a tanker or a trailer. "PTW" may indicate a case where the object is a two-wheeled vehicle such as a motorcycle. "Gas" may indicate a case where the object is exhaust gas.

[0182] The non-recognition rate of the existing object recognition device or the existing object recognition method and the non-recognition rate of the object recognition device or the object recognition method according to the exemplary embodiment of the present disclosure may differ by no more than about 0.2.

[0183] The second diagram 1105 in the first row 1101 may show the false recognition rate of an object identified by the object recognition device or object recognition method according to the exemplary embodiment and located on the left or right boundary of the fan-shaped area, and the false recognition rate of an object identified by the existing object recognition device or object recognition method and located on the left or right boundary of the fan-shaped area. The false recognition rate may refer to the ratio of identifying an object as existing when the object does not exist.

[0184] The misrecognition rate of an existing object recognition apparatus or an existing object recognition method may be greater than the misrecognition rate of an object recognition apparatus or an object recognition method according to an exemplary embodiment of the present disclosure.

[0185] The third diagram 1107 in the first row 1101 may show the average number of errors of objects identified by the object recognition device or object recognition method according to the exemplary embodiment and located on the left or right boundary of the fan-shaped area, and the average number of errors of objects identified by the conventional object recognition device or object recognition method and located on the left or right boundary of the fan-shaped area. The average number of errors may refer to the average number of times a plurality of frames with errors are identified on average among a specified number of frames (e.g., approximately 5000).

[0186] The average number of errors of an existing object recognition apparatus or an existing object recognition method may be greater than the average number of errors of an object recognition apparatus or an object recognition method according to an exemplary embodiment of the present disclosure.

[0187] The fourth diagram 1113 in the second row 1111 may show the non-recognition rate of objects identified by the object recognition device or the object recognition method according to the exemplary embodiment and identified as an occluding object or an occluded object, and the non-recognition rate of objects identified by the existing object recognition device or the object recognition method and identified as an occluding object or an occluded object. The non-recognition rate may refer to the ratio of an object that is not an occluding object or an occluding object being mistakenly recognized as an occluding object or an occluding object.

[0188] The non-recognition rate of the existing object recognition apparatus or object recognition method may be greater than the non-recognition rate of the object recognition apparatus or object recognition method according to the exemplary embodiments of the present disclosure.

[0189] According to an exemplary embodiment of the present disclosure, "basic" may indicate a case where the object is a passenger car. "Bus" may indicate a case where the object is a bus. "Special car" may indicate a case where the object is a vehicle such as a tanker or a trailer. "Gas" may indicate a case where the object is exhaust gas. Road sign may indicate a case where the object is a sign attached to a road.

[0190] The fifth diagram 1115 in the second row 1111 may show the misrecognition rate of objects that are identified by the object recognition device or the object recognition method according to the exemplary embodiment and are not identified as occluding objects or occluded objects, and the misrecognition rate of objects that are identified by the existing object recognition device or the object recognition method and are not identified as occluding objects or occluded objects. The misrecognition rate may refer to the ratio at which an occluding object or occluded object is mistakenly identified as an occluded object or an occluding object.

[0191] The misrecognition rate of an existing object recognition device or an existing object recognition method and the misrecognition rate of an object recognition device or an object recognition method according to an exemplary embodiment of the present disclosure may differ by no more than about 0.2.

[0192] The sixth diagram 1117 in the second row 1111 may show the average number of errors of objects whose characteristics are incorrectly recognized based on the object recognition device or object recognition method according to the exemplary embodiment of the present disclosure, and the average number of errors of objects whose characteristics are incorrectly recognized based on the existing object recognition device or object recognition method. The average number of errors may refer to the average number of times a plurality of frames with errors are recognized among a specified number of frames (e.g., approximately 5000).

[0193] The average number of errors of an existing object recognition device or an existing object recognition method and the average number of errors of an object recognition device or an object recognition method according to an exemplary embodiment of the present disclosure may differ by no more than about 20.

[0194] According to an exemplary embodiment of the present disclosure, the accuracy of object determination by an existing object recognition apparatus or an existing object recognition method may not be significantly different from the accuracy of object determination by an object recognition apparatus or an object recognition method according to an exemplary embodiment of the present disclosure.

[0195] However, the time required for the object recognition device or the object recognition method according to various exemplary embodiments of the present disclosure may be shorter than the time required for the existing object recognition device or the existing object recognition method. Fig.12 The time required for a conventional object recognition apparatus or object recognition method and the time required for an object recognition apparatus or method according to an exemplary embodiment are described.

[0196] Fig.12 An example of a calculation amount recognized by an existing object recognition device or object recognition method and an example of a calculation amount recognized by an object recognition device or object recognition method according to an exemplary embodiment of the present disclosure are shown.

[0197] Reference Fig.12 , the first diagram 1203 in the first row 1201 may show a first line 1205 in the first scene, which represents the central processing unit (CPU) computing time required for the existing object recognition device or object recognition method; and a second line 1207, which represents the CPU computing time required for the object recognition device or object recognition method according to the exemplary embodiment of the present disclosure. The CPU computing time may refer to the time required for the CPU to process the calculation. The first line 1205 and the second line 1207 may represent the CPU computing time required in the first round to the fifth round.

[0198] The second diagram 1209 in the first row 1201 may show the ratio of the CPU computing time required by the object recognition device or object recognition method according to the exemplary embodiment and the CPU computing time required by the existing object recognition device or the existing object recognition method in the first scenario. The second diagram 1209 may represent the ratio of the CPU computing time consumed in the first round to the fifth round.

[0199] The third diagram 1213 in the second line 1211 may show the third line 1215 in the second scene, which indicates the CPU computing time required for the existing object recognition device or object recognition method; and the fourth line 1217, which indicates the CPU computing time required for the object recognition device or object recognition method according to the exemplary embodiment of the present disclosure. The third line 1215 and the fourth line 1217 may indicate the CPU computing time required in the first to fifth rounds.

[0200] A fourth graph 1219 in the second row 1211 may illustrate a ratio of a CPU computing time required for the object recognition apparatus or the object recognition method according to the exemplary embodiment to a CPU computing time required for an existing object recognition apparatus or the existing object recognition method in the second scenario.

[0201] The fourth graph 1219 may represent the ratio of the CPU computing time consumed in the first round to the fifth round.

[0202] The first line 1205 and the second line 1207 of the first diagram 1203 may indicate that the CPU calculation time required by the existing object recognition apparatus or the existing object recognition method is longer than the CPU calculation time required by the object recognition apparatus or the object recognition method according to the exemplary embodiment of the present disclosure.

[0203] The second graph 1209 may indicate that the CPU time consumed by the object recognition apparatus or the object recognition method according to the exemplary embodiment of the present disclosure is approximately 19% of the CPU time consumed by the existing object recognition apparatus or the existing object recognition method.

[0204] The third line 1215 and the fourth line 1217 of the third graph 1213 may indicate that the CPU calculation time required by the existing object recognition apparatus or the existing object recognition method is longer than the CPU calculation time required by the object recognition apparatus or the object recognition method according to the exemplary embodiment of the present disclosure.

[0205] The fourth graph 1219 may indicate that the CPU time consumed by the object recognition apparatus or the object recognition method according to the exemplary embodiment of the present disclosure is approximately 19% of the CPU time consumed by the existing object recognition apparatus or the existing object recognition method.

[0206] The difference between the accuracy of object determination in the object recognition device or object recognition method according to various exemplary embodiments of the present disclosure and the accuracy of object determination in the existing object recognition device or the existing object recognition method may be less than the reference value. Compared with the CPU time required by the existing object recognition device or the existing object recognition method, the CPU time required by the object recognition device or the existing object recognition method according to various exemplary embodiments of the present disclosure may be reduced to about 1 / 5.

[0207] Fig.13 A computing system related to an object recognition apparatus or an object recognition method according to an exemplary embodiment of the present disclosure is shown.

[0208] Reference Fig.13 , the computing system 1300 may include at least one 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 connected to each other via a bus 1320 .

[0209] The processor 1310 may be a central processing unit (CPU) or a semiconductor device that processes instructions stored in the memory 1330 and / or the storage 1360. The memory 1330 and the storage 1360 may include various types of volatile or non-volatile storage media. For example, the memory 1330 may include a read-only memory (ROM) 1331 and a random access memory (RAM) 1332.

[0210] Therefore, the operations of the methods or algorithms described in conjunction with the exemplary embodiments disclosed herein may be embodied directly in hardware or in a software module executed by the processor 1310, or in a combination thereof. The software module may reside on a storage medium (i.e., memory 1330 and / or storage 1360) such as RAM, flash memory, ROM, EPROM, EEPROM, registers, hard disk, removable disk, and CD-ROM.

[0211] An exemplary storage medium may be coupled to the processor 1310, and the processor 1310 may read information from the storage medium and may record information in the storage medium. Alternatively, the storage medium may be integrated with the processor 1310. The processor and the storage medium may reside in an application specific integrated circuit (ASIC). The ASIC may reside in a user terminal. In another case, the processor and the storage medium may reside in a user terminal as separate components.

[0212] The above description is merely an illustration of the technical idea of ​​the present disclosure, and those skilled in the art to which the present disclosure belongs may make various modifications and variations without departing from the essential characteristics of the present disclosure.

[0213] Therefore, the exemplary embodiments included in the exemplary embodiments of the present disclosure are not intended to limit the technical ideas of the present disclosure, but are used to describe the present disclosure, and the scope of the technical ideas of the present disclosure is not limited to the embodiments. The protection scope of the present disclosure should be interpreted by the attached claims, and all technical ideas within the scope equivalent thereto should be interpreted as included within the scope of the present disclosure.

[0214] The present technology can improve the accuracy of determining whether each object is an object that occludes another object or an object that is occluded by another object by comparing the distance values ​​of the objects represented by the point clouds.

[0215] Furthermore, the present technique may improve the accuracy of determining whether each object is an object that occludes or is occluded by another object by comparing the confidences assigned to the objects represented by the point clouds.

[0216] Furthermore, the present technology may enhance the user experience by improving the accuracy of determining whether each object is an object that occludes another object or an object that is occluded by another object.

[0217] 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 that occludes another object or an object that is occluded by another object.

[0218] Furthermore, various effects directly or indirectly understood by the present disclosure can be provided.

[0219] In various exemplary embodiments of the present disclosure, the memory and the processor may be provided as one chip, or provided as separate chips.

[0220] In various exemplary embodiments of the present disclosure, the scope of the present disclosure includes software or machine executable commands (for example, operating systems, applications, firmware, programs, etc.) for enabling operations according to the methods of the various embodiments to be performed on a device or computer, and non-transitory computer-readable media (including such software or commands stored thereon and executable on a device or computer).

[0221] In various exemplary 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.

[0222] In addition, terms such as “unit” and “module” included in the present specification refer to a unit for processing at least one function or operation, which can be implemented by hardware, software, or a combination thereof.

[0223] In an exemplary embodiment of the present disclosure, a vehicle may be referred to as being based on a concept including various transportation devices. In some cases, a vehicle may be interpreted as being based on a concept including not only various land transportation devices traveling on roads, such as cars, motorcycles, trucks, and buses, but also various transportation devices, such as airplanes, drones, ships, and the like.

[0224] To facilitate interpretation and accurate definition of the appended claims, the terms "upper", "lower", "inner", "outer", "upper", "lower", "upward", "downward", "front", "rear", "rear", "inwardly", "outwardly", "interior", "exterior", "inner", "exterior", "forward", and "rearward" are used to describe features of the exemplary embodiments with reference to the positions of such features as shown in the figures. It should also be understood that the term "connect" or its derivatives refer to both direct and indirect connections.

[0225] The term "and / or" may include a combination of a plurality of related listed items or any one of a plurality of related listed items. For example, "A and / or B" includes all three situations such as "A", "B" and "A and B".

[0226] In this specification, unless otherwise stated, a singular expression includes a plural expression unless the context clearly indicates otherwise.

[0227] In exemplary embodiments of the present disclosure, “at least one of A and B” may refer to “at least one of A or B” or “at least one of a combination 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 of a combination of one or more of A and B”.

[0228] In the exemplary embodiments of the present disclosure, it should be understood that terms such as “including” or “having” are intended to indicate the presence of features, numbers, steps, operations, elements, parts, or a combination thereof described in the specification, and do not exclude the possibility of adding or existing one or more other features, numbers, steps, operations, elements, parts, or a combination thereof.

[0229] According to exemplary embodiments of the present disclosure, components may be combined with each other to be implemented as one, or some components may be omitted.

[0230] The foregoing descriptions of specific exemplary embodiments of the present disclosure are given for purposes of illustration and description. They are not intended to be exhaustive or to limit the present disclosure to the precise form disclosed, and it is apparent that many modifications and variations are possible in light of the above teachings. The exemplary embodiments are selected and described to explain certain principles of the present disclosure and their practical applications, so that other persons skilled in the art can make and utilize various exemplary embodiments of the present disclosure and various alternatives and modifications thereof. The scope of the present disclosure is intended to be defined by the appended claims and their equivalents.

Claims

1. An object recognition device, comprising: Light detection and ranging device (LiDAR); and a processor operably connected to the LiDAR, Wherein, the processor is configured to: Identify a first point, a second point, a third point, and a fourth point, wherein the first point is a point located at the leftmost relative to the host vehicle in a point cloud representing a first object obtained by the LiDAR, the second point is a point located at the rightmost relative to the host vehicle in a point cloud representing the first object, the third point is a point located at the leftmost relative to the host vehicle in a point cloud representing a second object, and the fourth point is a point located at the rightmost relative to the host vehicle in a point cloud representing the second object; identifying a first contour point closer to the second object and a second contour point closer to the first object, the first contour point being one of the first point and the second point, and the second contour point being one of the third point and the fourth point; Based on identifying that the first contour point and the second contour point do not overlap each other, identifying an angle between a line segment connecting the first contour point and the LiDAR and a line segment connecting the second contour point and the LiDAR; In response to the angle being less than or equal to a threshold angle, identifying an object that is one of the first object and the second object as an occluded object, the object corresponding to one of the first contour point and the second contour point that forms a longer distance between the first contour point and the LiDAR and the second outer point; and An object, among the first object and the second object, which is different from the object identified as the blocked object is identified as an object blocking the blocked object.

2. The object recognition device according to claim 1, in, The processor is further configured to: assign a credibility to the first object and assign a credibility different from the credibility assigned to the first object to the second object according to a distance between a straight line connecting the first point and the second point and a distance between a straight line connecting the third point and the fourth point and the LiDAR based on recognizing that the first contour point and the second contour point overlap each other, and The credibility assigned to the first object and the credibility assigned to the second object are configured to indicate whether the corresponding object is an object that blocks another object.

3. The object recognition device according to claim 1, wherein: The processor is further configured to: identifying a point cloud representing at least one of the first object and the second object identified in a plane formed by the first axis and the second axis among the first axis, the second axis, and the third axis; as well as Based on identifying that the azimuth of the first contour point relative to the origin corresponding to the LiDAR and the first axis is included in the range between the azimuth of the third point relative to the origin and the first axis and the azimuth of the fourth point relative to the origin and the first axis, identifying whether the first contour point and the second contour point overlap with each other.

4. The object recognition device according to claim 1, wherein: The processor is further configured to: Based on recognizing that the first contour point and the second contour point overlap each other, identifying 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; assigning credibility to the second object according to the number of the third points or the fourth points included in the area to which the LiDAR belongs, among the two areas separated by the straight line; identifying 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 to the first object a credibility including a value different from the credibility assigned to the second object in accordance with the number of the first points or the second points included in an area to which the LiDAR belongs, out of two areas separated by a straight line passing through the third point and the fourth point; as well as By comparing the credibility value of the first object and the credibility value of the second object, the object with the larger credibility value is identified as the object that occludes the other object.

5. The object recognition device according to claim 1, wherein: The processor is further configured to: Based on recognizing that the first contour point and the second contour point overlap each other, identifying a first function according to the coordinates of the first point and the coordinates of the second point, the first function being a function of a straight line passing through the first point and the second point; assigning the credibility to the second object in an amount of the number of signs that are the same as the sign of the value obtained by substituting the coordinates corresponding to the origin of the LiDAR into the first function, among the sign of the value obtained by substituting the coordinates of the third point into the first function and the sign of the value obtained by substituting the coordinates of the fourth point into the first function; identifying a second function according to the coordinates of the third point and the coordinates of the fourth point, the second function being a function of a straight line passing through the third point and the fourth point; assigning credibility to the first object in an amount of the number of signs that are the same as the sign of a value obtained by substituting coordinates corresponding to the origin of the LiDAR into the second function, among signs of a value obtained by substituting coordinates of the first point into the second function and signs of a value obtained by substituting coordinates of the second point into the second function; as well as By comparing the credibility value of the first object and the credibility value of the second object, the object with the larger credibility value is identified as the object that occludes the other object.

6. The object recognition device according to claim 1, wherein: The processor is further configured to: Identifying a sector-shaped area including a point cloud of a first object included in a specific layer and representing a leftmost position relative to the host vehicle and a point cloud of a second object included in a specific layer and representing a rightmost position relative to the host vehicle, the sector-shaped area including a minimum central angle relative to an origin corresponding to the LiDAR; as well as Based on identifying that at least one point in the point cloud representing the first object contained in multiple layers including the specific layer and the point cloud representing the second object contained in multiple layers including the specific layer are located outside the fan-shaped area, the area of ​​the fan-shaped area is expanded by increasing the central angle of the fan-shaped area to include the at least one point located outside the fan-shaped area.

7. The object recognition device according to claim 1, wherein: The processor is further configured to: Identifying a sector-shaped area including a point cloud representing a first object located at the far left relative to the host vehicle and a point cloud representing a second object located at the far right relative to the host vehicle, the sector-shaped area including a minimum central angle relative to an origin corresponding to the LiDAR; identifying a fifth point in the point cloud representing the third object that is located farthest to the left relative to the host vehicle, and a sixth point in the point cloud representing the third object that is located farthest to the right relative to the host vehicle; identifying a left angle between a line segment representing a left boundary of the sector-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 sector-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, the third object is identified as being located on the left boundary or on the right boundary.

8. The object recognition device according to claim 1, wherein: The processor is further configured to: identifying a point cloud representing the first object among the points contained in the plurality of layers; and A point cloud representing the second object is identified among the points contained in the plurality of layers.

9. The object recognition device according to claim 1, wherein: The processor is further configured to: The first contour point and the second contour point are identified based on the following angles: 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 a 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 a line segment connecting the third point and the LiDAR, and an angle between a line segment connecting the second point and the LiDAR and a 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: Based on the table representing the occluded objects and the occluding objects and at least one object located on the left boundary or the right boundary, a fourth object occluded by the at least one object is identified and a fifth object occluded by the fourth object is iteratively identified.

11. A method for object recognition, comprising the following steps: A processor identifies a first point, a second point, a third point, and a fourth point, wherein the first point is a point located at the leftmost relative to the host vehicle in a point cloud representing a first object obtained by a light detection and ranging device (LiDAR), the second point is a point located at the rightmost relative to the host vehicle in a point cloud representing the first object, the third point is a point located at the leftmost relative to the host vehicle in a point cloud representing a second object, and the fourth point is a point located at the rightmost relative to the host vehicle in a point cloud representing the second object; identifying, by the processor, a first contour point closer to the second object and a second contour point closer to the first object, the first contour point being one of the first point and the second point, and the second contour point being one of the third point and the fourth point; identifying, by the processor, an angle between a line segment connecting the first contour point and the LiDAR and a line segment connecting the second contour point and the LiDAR based on identifying that the first contour point and the second contour point do not overlap with each other; When the angle is less than or equal to a threshold angle, identifying, by the processor, an object that is one of the first object and the second object as an occluded object, the object corresponding to one of the first contour point and the second contour point that forms a longer distance between the first contour point and the LiDAR and the second outer point and the LiDAR; as well as An object among the first object and the second object that is different from the object identified as the obstructed object is identified by the processor as an object obstructing the obstructed object.

12. The object recognition method according to claim 11, further comprising the following steps: assigning, by the processor, a credibility to the first object and a credibility different from the credibility 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 recognizing that the first contour point and the second contour point overlap each other, The credibility assigned to the first object and the credibility assigned to the second object are configured to indicate whether the corresponding object is an object that blocks another object.

13. The object recognition method according to claim 11, further comprising the following steps: identifying, by the processor, a point cloud representing at least one of the first object and the second object identified in a plane formed by the first axis and the second axis among a first axis, a second axis, and a third axis; as well as Based on identifying that the azimuth of the first contour point relative to the origin corresponding to the LiDAR and the first axis is included in the range between the azimuth of the third point relative to the origin and the first axis and the azimuth of the fourth point relative to the origin and the first axis, the processor identifies whether the first contour point and the second contour point overlap with each other.

14. The object recognition method according to claim 11, further comprising: Based on recognizing that the first contour point and the second contour point overlap each other, the processor identifies, according to coordinates of the first point and coordinates of the second point, a straight line passing through the first point and the second point; assigning, by the processor, credibility to the second object according to the number of the third points or the fourth points included in the area to which the LiDAR belongs, among the two areas separated by the straight line; The processor identifies 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, by the processor, a credibility including a value different from the credibility assigned to the second object to the first object in accordance with the number of the first points or the second points included in an area to which the LiDAR belongs, out of two areas separated by a straight line passing through the third point and the fourth point; as well as The processor compares the credibility value of the first object with the credibility value of the second object to identify the object with the larger credibility value as the object that blocks the other object.

15. The object recognition method according to claim 11, further comprising the following steps: Based on recognizing that the first contour point and the second contour point overlap each other, the processor identifies a first function according to the coordinates of the first point and the coordinates of the second point, the first function being a function of a straight line passing through the first point and the second point; assigning, by the processor, credibility to the second object in an amount of the number of signs that are the same as the sign of a value obtained by substituting coordinates corresponding to the origin of the LiDAR into the first function, among the sign of a value obtained by substituting coordinates of the third point into the first function and the sign of a value obtained by substituting coordinates of the fourth point into the first function; identifying, by the processor, a second function according to the coordinates of the third point and the coordinates of the fourth point, wherein the second function is a function of a straight line passing through the third point and the fourth point; assigning, by the processor, credibility to the first object in an amount equal to the number of signs of a value obtained by substituting the coordinates of the first point into the second function and a value obtained by substituting the coordinates of the second point into the second function, as the sign of the value obtained by substituting the coordinates corresponding to the origin of the LiDAR into the second function; as well as The processor compares the credibility value of the first object with the credibility value of the second object to identify the object with the larger credibility value as the object that blocks the other object.

16. The object recognition method according to claim 11, further comprising the following steps: identifying, by the processor, a sector-shaped area including a point cloud included in a specific layer and representing a first object located at the far left relative to the host vehicle and a point cloud included in a specific layer and representing a second object located at the far right relative to the host vehicle, the sector-shaped area including a minimum central angle relative to an origin corresponding to the LiDAR; as well as Based on identifying that at least one point in the point cloud representing the first object contained in multiple layers including the specific layer and the point cloud representing the second object contained in multiple layers including the specific layer are located outside the fan-shaped area, the processor expands the area of ​​the fan-shaped area by increasing the central angle of the fan-shaped area to include the at least one point located outside the fan-shaped area.

17. The object recognition method according to claim 11, further comprising the following steps: identifying, by the processor, a sector-shaped area including a point cloud representing a first object located at the far left relative to the host vehicle and a point cloud representing a second object located at the far right relative to the host vehicle, the sector-shaped area including a minimum central angle relative to an origin corresponding to the LiDAR; identifying, by the processor, a fifth point located at the leftmost side relative to the host vehicle in the point cloud representing the third object and a sixth point located at the rightmost side relative to the host vehicle in the point cloud representing the third object; identifying, by the processor, a left angle between a line segment representing a left boundary of the sector-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 sector-shaped area and a line segment connecting the sixth point and the LiDAR; as well as The processor identifies the third object as being located on the left boundary or on the right boundary based on the left angle or the right angle being less than or equal to a predetermined angle.

18. The object recognition method according to claim 11, wherein: The step of identifying the first point as a point located at the leftmost side relative to the host vehicle in the point cloud obtained by the LiDAR and representing the first object, the second point as a point located at the rightmost side relative to the host vehicle in the point cloud representing the first object, the third point as a point located at the leftmost side relative to the host vehicle in the point cloud representing the second object, and the fourth point as a point located at the rightmost side relative to the host vehicle in the point cloud representing the second object includes: identifying, by the processor, a point cloud representing the first object among the points contained in the plurality of layers; and A point cloud representing the second object is identified by the processor among the points included in the plurality of layers.

19. The object recognition method according to claim 11, wherein: The step of identifying the first contour point closer to the second object as one of the first point and the second point, and the second contour point closer to the first object as one of the third point and the fourth point comprises: The first contour point and the second contour point are identified based on the following angles: 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 a 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 a line segment connecting the third point and the LiDAR, and an angle between a line segment connecting the second point and the LiDAR and a line segment connecting the fourth point and the LiDAR.

20. The object recognition method according to claim 17, further comprising: The processor identifies, based on a table representing the occluded objects and the occluding objects and at least one object located on the left boundary or the right boundary, a fourth object occluded by the at least one object and iteratively identifies a fifth object occluded by the fourth object.

Images