Apparatus for identifying object and method thereof

Abstract

The invention relates to an object recognition device and method. An object recognition device includes a sensor (e.g., LIDAR) and a processor. The processor may extract a plurality of representation points, determine a first reference contour point, a first representation point, a second representation point, and a third representation point among the plurality of representation points, determine a first distance between the first reference contour point and the second representation point; a first angle between a first ray extending from the first reference contour point to the first representation point and a second ray extending from the second representation point to the third representation point is determined, a fourth representation point is determined, and one of the first representation point, the second representation point, or the fourth representation point is determined as a contour point.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims the benefit of priority from Korean Patent Application No. 10-2023-0109247 filed in the Korean Intellectual Property Office on August 21, 2023, the entire contents of which are incorporated herein by reference. Technical Field

[0003] The present disclosure relates to an object recognition device and method, and more specifically, to the following technology: the technology is used to obtain contour points of an object based on a point cloud obtained by a light detection and ranging (LIDAR) device. Background Art

[0004] The technology to detect the surrounding environment and avoid obstacles is crucial for autonomous vehicles.

[0005] The vehicle can obtain data indicating the location of objects around the vehicle through light detection and ranging (LIDAR). The distance from the light detection and ranging (LIDAR) to the object can be measured based on the interval between the time when the light detection and ranging (LIDAR) emits laser light and the time when the laser light reflected from the object is received. The vehicle is able to identify the location of the point included in the object in the space where the vehicle is located based on the angle at which the laser light is emitted and the distance to the object.

[0006] Data obtained by light detection and ranging (LIDAR) are characterized by high resolution and a large number of points contained in the data. The importance of technology that can recognize the shapes of objects around the vehicle from the data by efficiently performing calculations within limited resources is increasing. Summary of the invention

[0007] The present disclosure aims to solve the above-mentioned problems occurring in the prior art while maintaining the advantages achieved by the prior art.

[0008] One aspect of the present disclosure provides an object recognition apparatus and method for identifying contour points among a plurality of representation points.

[0009] One aspect of the present disclosure provides an object recognition apparatus and method for improving the accuracy of contour points.

[0010] One aspect of the present disclosure provides an object recognition apparatus and method for reducing the amount of calculation for recognizing contour points.

[0011] The technical problems to be solved by the present disclosure are not limited to the above-mentioned problems, and technicians in the technical field to which the present disclosure belongs can clearly understand other technical problems not mentioned in this document through the following description.

[0012] According to one or more exemplary embodiments of the present disclosure, an object recognition device may include: a sensor and a processor, wherein the processor may be configured to: extract a plurality of representation points including at least a portion of the surface points of the object from a plurality of points obtained via the sensor and representing the object; determine a first reference contour point, wherein the first reference contour point is one of two outermost endpoints of the plurality of representation points; determine a first representation point adjacent to the first reference contour point among the plurality of representation points; determine a second representation point different from the first reference contour point among the plurality of representation points; determine a third representation point, wherein the third representation point is a point farther away from the first reference contour point among the two representation points on both sides of the second representation point; determine a first distance between the first reference contour point and the second representation point; determine a first angle between a first ray extending from the first reference contour point to the first representation point and a second ray extending from the second representation point to the third representation point degrees; determining one of the following as a contour point: a second representation point, determined based on: matching the second representation point based on the first representation point, and also based on determining that the first distance is greater than a threshold distance or the first angle is greater than or equal to a threshold angle; one of the first representation point or the second representation point, determined based on: not matching the second representation point based on the first representation point, and also based on determining that the first distance is greater than a threshold distance or the first angle is greater than or equal to a threshold angle, and also based on determining that other representation points of the plurality of representation points do not exist between the first representation point and the second representation point; and one of the second representation point or the fourth representation point, determined based on: not matching the second representation point based on the first representation point, and also based on determining that at least one other representation point of the plurality of representation points exists between the first representation point and the second representation point, and also based on determining that the first distance is greater than a threshold distance or the first angle is greater than or equal to a threshold angle. The fourth representation point may be a point closer to the first reference contour point of the two representation points on both sides of the second representation point; and controlling the vehicle based on the contour point.

[0013] The processor may also be configured to determine one of the following as a contour point: a second representation point, determined based on: determining that the first distance is greater than a threshold distance, and also based on matching the second representation point with the first representation point; a first representation point, determined based on: determining that the first distance is greater than the threshold distance, and also based on determining that other representation points do not exist between the first representation point and the second representation point; and a fourth representation point, determined based on: determining that the first distance is greater than the threshold distance, and also based on determining that at least one other representation point exists between the first representation point and the second representation point.

[0014] The processor may also be configured to determine one of the following: the second representation point is a contour point, determined based on: the second representation point is one of the two outermost endpoints, and also based on determining that the first distance is less than or equal to a threshold distance and the first angle is less than a threshold angle; and the contour point does not exist in the first representation point, the second representation point and the fourth representation point, determined based on: the second representation point is not one of the two outermost endpoints.

[0015] The processor may be further configured to determine that the second representative point is a contour point based on determining that the first distance is less than or equal to a threshold distance and the first angle is greater than or equal to a threshold angle.

[0016] The processor may also be configured to determine one of the following as a contour point: a second representation point, determined based on: determining that the second representation point is one of the two outermost endpoints, further based on determining that the first distance is greater than a threshold distance, and further based on the first representation point matching the second representation point; a first representation point, determined based on: determining that the second representation point is one of the two outermost endpoints, further based on determining that the first distance is greater than the threshold distance, further based on the first representation point not matching the second representation point, and further based on determining that no other representation points in a plurality of representation points exist between the first representation point and the second representation point; or a fourth representation point, determined based on: determining that the second representation point is one of the two outermost endpoints, further based on determining that the first distance is greater than the threshold distance, further based on the first representation point not matching the second representation point, and further based on determining that at least one other representation point in a plurality of representation points exists between the first representation point and the second representation point.

[0017] The processor may be further configured to determine the second representation point as a contour point based on determining that the second representation point is one of the two outermost endpoints and further based on determining that the first distance is less than or equal to a threshold distance.

[0018] The processor can also be configured to determine a fifth representation point based on determining that the contour point does not exist in the first representation point, the second representation point and the fourth representation point, the fifth representation point being a point farther away from the first reference contour point among the two representation points on both sides of the third representation point; and determine that one of the second representation point or the third representation point is a contour point based on determining that a second distance between the first reference contour point and the third representation point is greater than a threshold distance, or a second angle between the first ray and a third ray extending from the third representation point to the fifth representation point is greater than or equal to a threshold angle.

[0019] The processor may also be configured to: determine a second reference contour point and a third reference contour point, the third reference contour point being one of the two contour points on either side of the second reference contour point; determine a sixth representation point that is not between the second reference contour point and the third reference contour point; determine a seventh representation point, the seventh representation point being a point farther from the second reference contour point than the two representation points on either side of the sixth representation point; determine a second distance between the third reference contour point and the seventh representation point; determine a second angle between a third ray extending from the second reference contour point to the third reference contour point and a fourth ray extending from the sixth representation point to the seventh representation point; and determine one of the following as a contour point: the seventh representation point, determined based on: determining that the second distance is greater than a threshold distance or the second angle is greater than or equal to a threshold angle, and also based on the third reference contour point matching the sixth representation point; and one of the sixth representation point or the seventh representation point, determined based on: determining that the second distance is greater than a threshold distance or the second angle is greater than or equal to a threshold angle, and also based on the third reference contour point not matching the sixth representation point.

[0020] The processor may also be configured to determine one of the following as a contour point: a seventh representation point, determined based on: the second distance being greater than a threshold distance, and also based on the third reference contour point matching the sixth representation point; and or a sixth representation point, determined based on: the second distance being greater than a threshold distance, and also based on the third reference contour point not matching the sixth representation point.

[0021] The processor can also be configured to: determine whether the seventh representation point is one of the two outermost endpoints based on determining that the second distance is less than or equal to the threshold distance and the second angle is less than the threshold angle; and determine one of the following: the seventh representation point is a contour point, and the basis for determination is: based on the seventh representation point is one of the two outermost endpoints; and the contour point does not exist in the sixth representation point and the seventh representation point, and the basis for determination is: based on the seventh representation point is not one of the two outermost endpoints.

[0022] The processor may be further configured to determine that the seventh representation point is a contour point based on determining that the second distance is less than or equal to a threshold distance and the second angle is greater than or equal to a threshold angle.

[0023] The processor may also be configured to determine an eighth representation point based on determining that the contour point does not exist in the sixth representation point and the seventh representation point, the eighth representation point being a point farther away from the second reference contour point among the two representation points on both sides of the seventh representation point; and to determine that one of the seventh representation point and the eighth representation point is a contour point based on determining that a third distance between the third reference contour point and the eighth representation point is greater than a threshold distance, or a third angle between the third ray and a fifth ray extending from the seventh representation point to the eighth representation point is greater than or equal to a threshold angle.

[0024] According to one or more exemplary embodiments of the present disclosure, an object recognition method may include: extracting a plurality of representation points including at least a portion of the surface points of the object from a plurality of points obtained via a sensor and representing the object; determining a first reference contour point, the first reference contour point being one of the two outermost endpoints of the plurality of representation points; determining a first representation point adjacent to the first reference contour point among the plurality of representation points; determining a second representation point different from the first reference contour point among the plurality of representation points; determining a third representation point, the third representation point being a point farther away from the first reference contour point among the two representation points on both sides of the second representation point; determining a first distance between the first reference contour point and the second representation point; determining a first angle between a first ray extending from the first reference contour point to the first representation point and a second ray extending from the second representation point to the third representation point; and determining one of the following Determined as contour points: a second representation point, determined based on: matching the second representation point based on the first representation point, and also based on determining that the first distance is greater than a threshold distance or the first angle is greater than or equal to a threshold angle; one of the first representation point or the second representation point, determined based on: the first representation point does not match the second representation point, and also based on determining that the first distance is greater than a threshold distance or the first angle is greater than or equal to a threshold angle, and also based on determining that other representation points of the plurality of representation points do not exist between the first representation point and the second representation point; and one of the second representation point or the fourth representation point, determined based on: the first representation point does not match the second representation point, and also based on determining that at least one other representation point of the plurality of representation points exists between the first representation point and the second representation point, and also based on determining that the first distance is greater than a threshold distance or the first angle is greater than or equal to a threshold angle. The fourth representation point is a point closer to the first reference contour point of the two representation points on both sides of the second representation point; and controlling the vehicle based on the contour points.

[0025] The object recognition method may also include determining one of the following as a contour point: a second representation point, determined based on: determining that the first distance is greater than the threshold distance, and also based on matching the second representation point with the first representation point; a first representation point, determined based on: determining that the first distance is greater than the threshold distance, and also based on determining that other representation points do not exist between the first representation point and the second representation point; and a fourth representation point, determined based on: determining that the first distance is greater than the threshold distance, and also based on determining that at least one other representation point exists between the first representation point and the second representation point.

[0026] The object recognition method may also include determining one of the following: the second representation point is a contour point, determined based on: based on the second representation point being one of the two outermost endpoints, and also based on determining that the first distance is less than or equal to the threshold distance and the first angle is less than the threshold angle; and the contour point does not exist in the first representation point, the second representation point and the fourth representation point, determined based on: based on the second representation point not being one of the two outermost endpoints.

[0027] The object recognition method may further include: determining that the second representation point is a contour point according to determining that the first distance is less than or equal to a threshold distance and the first angle is greater than or equal to a threshold angle.

[0028] The object recognition method may also include determining one of the following as a contour point: a second representation point, determined based on: determining that the second representation point is one of the two outermost endpoints, and also based on determining that the first distance is greater than a threshold distance, and also based on the first representation point matching the second representation point; a first representation point, determined based on: determining that the second representation point is one of the two outermost endpoints, and also based on determining that the first distance is greater than the threshold distance, and additionally based on the first representation point not matching the second representation point, and also based on determining that no other representation points in a plurality of representation points exist between the first representation point and the second representation point; and a fourth representation point, determined based on: determining that the second representation point is one of the two outermost endpoints, and also based on determining that the first distance is greater than the threshold distance, and also based on the first representation point not matching the second representation point, and also based on determining that at least one other representation point in a plurality of representation points exists between the first representation point and the second representation point.

[0029] The object recognition method may further include: determining the second representation point as a contour point based on determining that the second representation point is one of the two outermost endpoints and further based on determining that the first distance is less than or equal to the threshold distance.

[0030] The object recognition method may also include determining a fifth representation point based on determining that the contour point does not exist in the first representation point, the second representation point and the fourth representation point, the fifth representation point being a point farther away from the first reference contour point among the two representation points on both sides of the third representation point; and determining that one of the second representation point or the third representation point is a contour point based on determining that a second distance between the first reference contour point and the third representation point is greater than a threshold distance, or a second angle between the first ray and a third ray extending from the third representation point to the fifth representation point is greater than or equal to a threshold angle.

[0031] The object recognition method may further include: determining a second reference contour point and a third reference contour point. The third reference contour point may be one of the two contour points on both sides of the second reference contour point; determining a sixth representation point that is not between the second reference contour point and the third reference contour point; determining a seventh representation point, the seventh representation point being a point farther from the second reference contour point than the two representation points on both sides of the sixth representation point; determining a second distance between the third reference contour point and the seventh representation point; determining a second angle between a third ray extending from the second reference contour point to the third reference contour point and a fourth ray extending from the sixth representation point to the seventh representation point; and determining one of the following as a contour point: the seventh representation point, determined based on: determining that the second distance is greater than a threshold distance or the second angle is greater than or equal to a threshold angle, and also based on the third reference contour point matching the sixth representation point; and one of the sixth representation point or the seventh representation point, determined based on: determining that the second distance is greater than a threshold distance or the second angle is greater than or equal to a threshold angle, and also based on the third reference contour point not matching the sixth representation point. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The above and other objects, features and advantages of the present disclosure will become more apparent through the following detailed description in conjunction with the accompanying drawings:

[0033] Figure 1 is a block diagram showing an object recognition device;

[0034] Figure 2 is an example showing the change of the moving direction of the object identified according to the selection of contour points;

[0035] Figure 3 A flowchart showing the operation of an object recognition device for recognizing contour points according to a specified angle and a specified distance in an object recognition device or an object recognition method;

[0036] Figure 4 A flowchart showing the operation of an object recognition device for recognizing contour points by using a reference contour point in an object recognition device or an object recognition method;

[0037] Figure 5 An example of reference contour points and identified representative points used to identify contour points in an object recognition device or an object recognition method is shown;

[0038] Figure 6 A flowchart showing the operation of an object recognition device for recognizing contour points by using a reference contour point in an object recognition device or an object recognition method;

[0039] Figure 7 A flowchart showing the operation of an object recognition device for recognizing that a specific representative point is a contour point through a reference contour point in an object recognition device or an object recognition method;

[0040] Figure 8 An example of a plurality of reference contour points and the identified representative points used to identify contour points in an object recognition device or an object recognition method is shown;

[0041] Fig. 9 A flowchart showing the operation of an object recognition device for recognizing contour points by using a plurality of reference contour points in an object recognition device or an object recognition method;

[0042] Fig.10 An example of identifying contour points in an object recognition device or an object recognition method is shown;

[0043] Fig.11 An example of illustrating the reliability of indicating the accuracy of recognized contour points in an object recognition device or an object recognition method; and

[0044] Fig.12 A computing system for an object recognition device or an object recognition method is shown. DETAILED DESCRIPTION

[0045] Hereinafter, one or more exemplary embodiments of the present disclosure will be described in detail with reference to the exemplary drawings. When adding reference numerals to the components in each figure, it should be noted that the same or equivalent components are represented by the same numerals even if they are shown in other drawings. In addition, when describing the exemplary embodiments of the present disclosure, detailed descriptions of well-known features or functions will be excluded to avoid unnecessarily obscuring the main points of the present disclosure.

[0046] 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 only used to distinguish one component from another component and do not limit the nature, order or sequence of the components. Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by technicians in the technical field to which the present disclosure relates. Such terms, like those defined in general dictionaries, should be interpreted as having the same meaning as the contextual meaning in the relevant technical field and should not be interpreted as having an ideal or overly formal meaning, except where explicitly defined in this application.

[0047] In addition, the terms “unit”, “device”, “member”, “body” and the like used hereinafter may indicate at least one shape structure, and may also indicate a unit for processing a function.

[0048] In addition, in the exemplary embodiments of the present disclosure, "greater than" or "less than" may be used to indicate whether a specific condition is satisfied or achieved, but this is only used to indicate an example and does not exclude "greater than or equal to" or "less than or equal to". A condition indicating "greater than or equal to" may be replaced by "greater than", a condition indicating "less than or equal to" may be replaced by "less than", and a condition indicating "greater than or equal to and less than" may be replaced by "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).

[0049] The following will refer to Figures 1 to 12 , describing in detail one or more exemplary embodiments of the present disclosure.

[0050] Figure 1 is a block diagram showing an object recognition device.

[0051] refer to Figure 1 , the object recognition device 101 can be implemented in the vehicle. In this case, the object recognition device 101 can be integrated with the internal control unit of the vehicle, or it can be implemented as an independent device and connected to the control unit of the vehicle through an independent connection part.

[0052] refer to Figure 1 The object recognition device 101 may include a sensor (eg, light detection and ranging (LIDAR)) 103 and a processor 105 .

[0053] The processor 105 of the object recognition device 101 may acquire position information of object points around the vehicle of the object recognition device 101 through a sensor (e.g., light detection and ranging (LIDAR)) 103. The processor 105 of the object recognition device 101 may acquire points representing objects through a sensor (e.g., light detection and ranging (LIDAR)) 103. Points acquired by a sensor (e.g., light detection and ranging (LIDAR)) and representing an object may be referred to as a point cloud, but the present disclosure is not limited thereto.

[0054] The processor 105 of the object recognition device 101 may extract a plurality of representative points, including some or all of the external points (eg, surface points) among the points representing the object.

[0055] The processor 105 of the object recognition device 101 may identify contour points from among the plurality of representation points. The contour points may represent the shape of the object. The contour points may include representation points that can represent the shape of the object from among the plurality of representation points.

[0056] The processor 105 of the object recognition device 101 may obtain information about the object, such as the shape of the object and the moving direction of the object, through the contour points.

[0057] Because the autonomous driving system or the driver assistance system needs to be able to detect the surrounding environment immediately, the size of the available memory and the available execution time of the object recognition device may be limited. The object recognition device can recognize objects within the limited memory size and limited execution time by reducing the number of contour points. This is because as the number of contour points is reduced, the amount of calculation required to obtain object information is also reduced.

[0058] However, as the number of contour points decreases, the accuracy of the object information also decreases. To compensate for the decrease in information accuracy, the processor 105 of the object recognition device 101 can identify valid contour points that can represent the shape of the object from multiple representation points to improve the accuracy of the object information.

[0059] The processor 105 of the object recognition device 101 may identify contour points according to a reference contour point according to the first method. The processor 105 of the object recognition device 101 may identify one of the two outermost (e.g., most protruding or farthest from the center of the object) endpoints of the plurality of representation points as the first reference contour point. The processor 105 of the object recognition device 101 may identify a first representation point (which is a representation point next to the first reference contour point), a second representation point, a third representation point (which is a representation point farther from the first reference contour point among the representation points on both sides of the second representation point), and a fourth representation point (which is a representation point farther from the first reference contour point among the representation points on both sides of the second representation point). According to the first method, the processor 105 of the object recognition device 101 may identify contour points different from the first reference contour point according to the first reference contour point, the first representation point, the second representation point, and the third representation point.

[0060] According to the first method, the processor 105 of the object recognition device 101 can identify that the contour point does not exist in the first representation point, the second representation point, the third representation point, and the fourth representation point based on the first reference contour point, the first representation point, the second representation point, the third representation point, and the fourth representation point. The processor 105 of the object recognition device 101 can identify the fifth representation point (which is a representation point farther away from the first reference contour point) among the representation points on both sides of the third representation point according to the first method, and identify contour points different from the first reference contour point again based on the first reference contour point, the first representation point, the third representation point, and the fifth representation point.

[0061] If at least one contour point different from the first reference contour point is identified by the first method, the processor 105 of the object recognition device 101 may identify contour points different from the plurality of contour points according to the second method. The processor 105 of the object recognition device 101 may identify a second reference contour point and a third reference contour point, which is one of two contours on both sides of the second reference contour point.

[0062] The processor 105 of the object recognition device 101 may identify a sixth representation point that is not between the second reference contour point and the third reference contour point, and a seventh representation point that is farther from the second reference contour point from among the two representation points on both sides of the sixth representation point.

[0063] The processor 105 of the object recognition device 101 may identify contour points different from the second reference contour points and the third reference contour points according to the second reference contour points, the third reference contour points, the sixth representation point, and the seventh representation point according to the second method.

[0064] The processor 105 of the object recognition device 101 may identify, according to the second method, a contour point that does not exist in the sixth representation point and the seventh representation point based on the second reference contour point, the third reference contour point, the sixth representation point, and the seventh representation point. The processor 105 of the object recognition device 101 may identify, according to the second method, an eighth representation point that is farther away from the representation point of the second reference contour point among the representation points on both sides of the seventh representation point, and identify contour points that are different from the second reference contour point and the third reference contour point based on the first reference contour point, the second reference contour point, the seventh representation point, and the eighth representation point.

[0065] The following will refer to Figures 4 to 7 The first method is described, while reference Figures 8 to 9 The second method is described.

[0066] Figure 2 An example is shown which illustrates the change in the moving direction of the identified object according to the selection of contour points.

[0067] refer to Figure 2 , the first screen 201 may display the moving direction of the object recognized based on the contour points. The first situation 203 of the first screen 201 may indicate the moving direction of the object recognized based on the contour points including the first contour point 205. The second situation 207 of the first screen 201 may indicate the moving direction of the object recognized based on the contour points including the second contour point 209. The second screen 211 may display the shape of the object recognized based on the contour points.

[0068] In the first screen 201, the recognized representation points of the first case 203 and the recognized representation points of the second case 207 may be the same. Even if the representation points are the same, the moving direction of the recognized object may be different, depending on which representation point is designated as a contour point by the existing object recognition device. For example, in the first case 203, when the object recognition device recognizes the first contour point 205 among the plurality of representation points as a contour point, the moving direction of the object may be recognized based on the gradient L2 of the first case 203. For example, in the second case 207, when the object recognition device recognizes the second contour point 209 among the plurality of representation points as a contour point, the moving direction of the object may be recognized based on the gradient L2 of the second case 207. Referring to the first screen 201, the moving direction of the object recognized in the first case 203 and the moving direction of the object recognized in the second case 207 may be different.

[0069] Depending on which representation point is identified as a contour point, the accuracy of information about the object (including the object moving direction) may vary. Specifically, depending on which representation point is designated as a contour point among the representation points located in the curved portion of the line connecting the representation points, the moving direction of the identified object may be significantly affected. For example, the θ value, which is the degree of inclination of the shape frame of the first case 203, may be different from the θ value as the degree of inclination of the shape frame of the second case 207.

[0070] Compared to existing object recognition devices, the processor of the object recognition device can increase the number of contour points recognized at curved portions of lines connecting representative points, thereby improving the accuracy of information about the object recognized from the contour points (e.g., the moving direction of the object).

[0071] The second screen 211 may display the shape of the recognized object according to the designated contour points. Because the outer representation points among the representation points of the curved portion of the line connecting the representation points are not recognized as contour points, the error of the information about the object recognized by the contour points (e.g., the moving direction of the object) may be greater than the error of the information about the object recognized by the contour points including the contour points (which are the outer representation points).

[0072] refer to Figure 3 A flowchart describing the operation of an object recognition apparatus that recognizes contour points to reduce errors in information about an object recognized by the contour points.

[0073] Figure 3 The present invention is a flowchart showing the operation of an object recognition device for recognizing contour points according to a specified angle and a specified distance in an object recognition device or an object recognition method.

[0074] The following assumptions Figure 1 The object recognition device 101 performs Figure 3 In addition, Figure 3In the description, the operations described as being performed by the device can be understood as being controlled by the processor 105 of the object recognition device 101.

[0075] refer to Figure 3 In the first operation 301, the processor of the object recognition device may define a first reference contour point, a first representation point, a second representation point, and a third representation point, or may also define a second reference contour point, a third reference contour point, a sixth representation point, and a seventh representation point.

[0076] The processor of the object recognition device may identify the first reference contour point, the first representation point, the second representation point, and the third representation point to identify the contour point by a first method using one reference contour point. Alternatively, the processor of the object recognition device may identify the second reference contour point, the third reference contour point, the sixth representation point, and the seventh representation point to identify the contour point by a second method using two reference contour points.

[0077] In the second operation 303, the processor of the object recognition device may identify the contour point. For example, in the first method, the first angle is a reference angle for identifying the contour point, and may include an angle between a half-line (e.g., a ray) extending from a first reference contour point (e.g., an initial point) to a first representation point and a half-line (e.g., a ray) extending from a second representation point (e.g., an initial point) to a third representation point. In the first method, the first distance is a reference distance for identifying the contour point, and may include a distance between the first reference contour point and the second representation point.

[0078] For example, in the second method, the second angle is a reference angle for identifying the contour point, and may include an angle between a half-line (e.g., a ray) extending from the second reference contour point to the third representation point and a half-line (e.g., a ray) extending from the sixth representation point to the seventh representation point. In the second method, the second distance is a reference distance for identifying the contour point, and may include a distance between the third reference contour point and the seventh representation point.

[0079] The first condition 311 may include the following conditions: the angle (eg, first angle, second angle) is less than a specified angle (eg, approximately 10°), and the distance (eg, first distance, second distance) is less than or equal to a specified distance (eg, approximately 3 meters).

[0080] In the first method, when the first condition 311 is satisfied, the processor of the object recognition device may recognize that there is no contour point among the first representation point, the second representation point, and the fourth representation point. The fourth representation point may include a representation point that is closer to the first reference contour point among the two representation points on both sides of the second representation point. The processor of the object recognition device may recognize a fifth representation point that is closer to the first reference contour point among the two representation points on both sides of the third representation point. In the first method, the processor of the object recognition device may re-recognize the contour point based on the first reference contour point, the first representation point, the third representation point, and the fifth representation point.

[0081] In the second method, when the first condition 311 is satisfied, the processor of the object recognition device may recognize that there is no contour point in the sixth representation point and the seventh representation point. The processor of the object recognition device may recognize an eighth representation point among two representation points on both sides of the seventh representation point, the eighth representation point being a representation point further away from the second reference contour point. The processor of the object recognition device may re-recognize the contour point in the second method based on the second reference contour point, the third reference contour point, the seventh representation point, and the eighth representation point.

[0082] The second condition 313 may include the following conditions: the angle (e.g., the first angle, the second angle) is less than a specified angle (e.g., about 10°) and the distance (e.g., the first distance, the second distance) is greater than a specified distance (e.g., about 3 meters). The third condition 315 may include the following conditions: the angle is greater than or equal to the specified angle and the distance is greater than the specified distance. The fourth condition 317 may include the following conditions: the angle is greater than or equal to the specified angle and the distance is less than or equal to the specified distance.

[0083] In the first method, when one of the second condition 313 , the third condition 315 , or the fourth condition 317 is satisfied, the processor of the object recognition device may identify one of the first, second, third, and fourth representation points as a contour point.

[0084] In the second method, when the first condition 311 is satisfied and one of the second condition 313 , the third condition 315 , or the fourth condition 317 is satisfied, the processor of the object recognition device may identify one of the sixth representation point and the seventh representation point as a contour point.

[0085] The following will refer to Figures 4 to 7 A first method for identifying contour points is described below. Figures 8 to 9 A second method for identifying contour points is described.

[0086] Figure 4 The present invention is a flowchart showing the operation of an object recognition device for recognizing contour points by using a reference contour point in an object recognition device or an object recognition method.

[0087] The following assumptions 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 device can be understood as being controlled by the processor 105 of the object recognition device 101.

[0088] refer to Figure 4 In a first operation 401, the processor of the object recognition device may identify one of two outermost (e.g., most protruding or farthest from the center of the object) endpoints among the plurality of extracted representative points as a first reference contour point. In order to extract the plurality of representative points, the processor of the object recognition device may obtain points representing the object through a sensor such as light detection and ranging (LIDAR). The processor of the object recognition device may identify some or all of the outer points (e.g., surface points) among the points obtained through the sensor such as light detection and ranging (LIDAR) as the plurality of representative points.

[0089] In the second operation 403, the processor of the object recognition device may identify a first representation point, a second representation point, and a third representation point. The first representation point may include a representation point that is adjacent to the first reference contour point among the plurality of representation points. The second representation point may include a representation point that is not between the first reference contour point and the first representation point. The third representation point may include a representation point that is farther away from the first reference contour point among the two representation points on both sides of the second representation point.

[0090] In a third operation 405 , the processor of the object recognition device may identify a distance between the first reference contour point and the second representation point.

[0091] In a fourth operation 407, the processor of the object recognition device may identify an angle between a half-line (e.g., ray) extending from the first reference contour point to the first representation point and a half-line (e.g., ray) extending from the second representation point to the third representation point. Using this angle, the degree of deviation of the line segment connecting the second representation point and the third representation point from the line segment connecting the first reference contour point and the first representation point may be identified.

[0092] In the fifth operation 409, the processor of the object recognition device may identify whether the first representation point matches the second representation point. When the first representation point matches the second representation point, the processor of the object recognition device may perform a sixth operation 411. When the first representation point does not match the second representation point, the processor of the object recognition device may perform a seventh operation 413.

[0093] In the sixth operation 411, the processor of the object recognition device may identify the second representation point as a contour point based on the distance being greater than or equal to the specified distance (e.g., about 3 meters) or the angle being greater than or equal to the specified angle (e.g., about 10 degrees). This is because, when the distance is greater than or equal to the specified distance, as the distance between the representation points increases, the accuracy of the information represented by the contour point may decrease. This is also because, when the angle is greater than the specified angle, the importance of the representation point may be high because the line segment connecting the representation points is curved. The processor of the object recognition device may identify the second representation point as a contour point because there is no representation point closer to the first reference contour point than the second representation point.

[0094] In the seventh operation 413, the processor of the object recognition device may identify whether at least one other representation point does not exist between the first representation point and the second representation point. When at least one other representation point exists between the first representation point and the second representation point, the processor of the object recognition device may perform an eighth operation 415. When at least one other representation point does not exist between the first representation point and the second representation point, the processor of the object recognition device may perform a ninth operation 417.

[0095] If the distance between the first reference contour point and the second representation point is greater than a specified distance, the processor of the object recognition device may identify the first representation point as a contour point because there is no representation point closer to the first reference contour point than the first representation point.

[0096] When the angle between a half-straight line (e.g., a ray) extending from a first reference contour point to a first representation point and a half-straight line (e.g., a ray) extending from a second representation point to a third representation point is greater than a specified angle (e.g., approximately 10°), the processor of the object recognition device may identify the second representation point as a contour point.

[0097] In an eighth operation 415 , the processor of the object recognition device may identify one of the first representation point and the second representation point as a contour point according to a distance greater than a specified distance or an angle greater than or equal to a specified angle.

[0098] If the distance between the first reference contour point and the second representation point is greater than a specified distance, the processor of the object recognition device may identify the first representation point closer to the first reference contour point than the second representation point as a contour point.

[0099] When the angle between a half-straight line (e.g., a ray) extending from a first reference contour point to a first representation point and a half-straight line (e.g., a ray) extending from a second representation point to a third representation point is greater than a specified angle (e.g., approximately 10°), the processor of the object recognition device may identify the second representation point as a contour point.

[0100] In a ninth operation 417 , the processor of the object recognition device may identify one of the second representation point and the fourth representation point as a contour point according to the distance being greater than a specified distance or the angle being greater than or equal to a specified angle.

[0101] The fourth representation point may include a representation point closer to the first reference contour point among the two representation points on both sides of the second representation point.

[0102] If the distance between the first reference contour point and the second representation point is greater than the specified distance, the processor of the object recognition device may identify a fourth representation point closer to the first reference contour point than the second representation point as a contour point because the fourth representation point is the representation point farthest from the reference contour point among the representation points within the specified distance.

[0103] When the angle between a half-line (e.g., ray) extending from the first reference contour point to the first representation point and a half-line (e.g., ray) extending from the second representation point to the third representation point is greater than a specified angle (e.g., about 10°), the processor of the object recognition device may identify the second representation point as a contour point. After identifying one or more contour points, the vehicle may be controlled (e.g., avoiding an object, braking to avoid a collision, etc.) based on the one or more identified contour points.

[0104] Figure 5 An example of reference contour points and recognized representative points used to recognize contour points in an object recognition device or an object recognition method is shown.

[0105] refer to Figure 5 , the processor of the object recognition device may identify a representation point including some or all of the external points (e.g., surface points) among the points obtained by a sensor (e.g., light detection and ranging (LIDAR)). The representation point in the first example 501 may include a first point 503, a second point 505, and a third point 507. The representation point in the second example 511 may include a first point 513, a second point 515, a third point 517, and a fourth point 519. The representation point in the third example 521 may include a first point 523, a second point 525, a third point 527, a fourth point 529, and a fifth point 531.

[0106] The first example 501 shows a method of identifying contour points using one reference contour point when a first representation point matches a second representation point. The first point 503 can be identified as a first reference contour point. The second point 505 can be identified as a first representation point and a second representation point. The third point 507 can be identified as a third representation point.

[0107] The second example 511 shows a method of identifying contour points using one reference contour point when the first representation point and the second representation point are different and at least one other representation point does not exist between the first representation point and the second representation point. The first point 513 can be identified as a first reference contour point. The second point 515 can be identified as a first representation point. The third point 517 can be identified as a second representation point. The fourth point 519 can be identified as a third representation point.

[0108] A third example 521 illustrates a method of identifying contour points using one reference contour point when the first representation point and the second representation point are different and at least one other representation point exists between the first representation point and the second representation point. A first point 523 may be identified as a first reference contour point. A second point 525 may be identified as a first representation point. A third point 527 may be identified as a fourth representation point. A fourth point 529 may be identified as a second representation point. A fifth point 531 may be identified as a third representation point.

[0109] In the first example 501, when the distance between the first point 503 as the first reference contour point and the second point 505 as the second representation point is greater than a specified distance (e.g., approximately 3 meters), the processor of the object recognition device may identify the second point 505 as the first representation point as a contour point.

[0110] In the first example 501, when a half straight line (e.g., a ray) extending from a first point 503 as a first reference contour point to a second point 505 as a first representation point and a half straight line (e.g., a ray) extending from the second point 503 as a second representation point to a third point 507 as a third representation point are greater than or equal to a specified angle (e.g., approximately 10°), the processor of the object recognition device may identify the second point 505 as a first representation point and a second representation point as a contour point.

[0111] In the first instance 501, based on identifying that the distance between the first point 503 as the first reference contour point and the second point 505 as the second representation point is less than or equal to the specified distance, and that the angle between the half-line (e.g., ray) extending from the first point 503 as the first reference contour point to the second point 505 as the first representation point and the half-line (e.g., ray) extending from the second point 505 as the second representation point to the third point 507 as the third representation point is less than the specified angle, the processor of the object recognition device can identify that there are no contour points in the second point 505 as the first representation point and the second representation point and the third point 507 as the third representation point.

[0112] According to recognizing that there is no contour point in the second point 505 as the first representation point and the second representation point and the third point 507 as the third representation point, the processor of the object recognition device may re-recognize the contour point as in the second example 511 .

[0113] In the second example 511, the distance between the first point 513 as the first reference contour point and the third point 517 as the second representation point is greater than a specified distance (e.g., approximately 3 meters), and the processor of the object recognition device may identify the second point 515 as the first representation point as a contour point.

[0114] In the second example 511, when the angle between a half-straight line (e.g., a ray) extending from a first point 513 as a first reference contour point to a second point 515 as a first representation point and a half-straight line (e.g., a ray) extending from a third point 517 as a second representation point to a fourth point 507 as a third representation point is greater than or equal to a specified angle (e.g., approximately 10°), the processor of the object recognition device may identify the third point 517 as a second representation point as a contour point.

[0115] In the second instance 511, based on identifying that the distance between the first point 513 as the first reference contour point and the third point 517 as the second representation point is less than or equal to the specified distance, and the angle between a half straight line (e.g., a ray) extending from the first point 513 as the first reference contour point to the second point 515 as the first representation point and the half straight line (e.g., a ray) between the third point 517 as the second representation point and the fourth point 519 as the third representation point is less than the specified angle, the processor of the object recognition device can identify that there are no contour points in the second point 515 as the first representation point, the third point 517 as the second representation point, and the fourth point 519 as the third representation point.

[0116] According to recognizing that there are no contour points in the second point 515 as the first representation point, the third point 517 as the second representation point, and the fourth point 519 as the third representation point, the processor of the object recognition device may re-recognize the contour points in the third instance 521 .

[0117] In the third example 521, the distance between the first point 523 as the first reference contour point and the fourth point 529 as the second representation point is greater than the specified distance (for example, approximately 3 meters), and the processor of the object recognition device may identify the third point 527 as the fourth representation point as a contour point.

[0118] In the third example 521, when the angle between a half-straight line (e.g., a ray) extending from a first point 523 as a first reference contour point to a second point 525 as a first representation point and a half-straight line (e.g., a ray) extending from a fourth point 529 as a second representation point to a fifth point 531 as a third representation point is greater than or equal to a specified angle (e.g., approximately 10°), the processor of the object recognition device may identify the fourth point 529 as a second representation point as a contour point.

[0119] In the third example 521, based on identifying that the distance between the first point 523 as the first reference contour point and the fourth point 529 as the second representation point is less than or equal to the specified distance, and that the angle between the half-line (e.g., ray) extending from the first point 523 as the first reference contour point to the second point 525 as the first representation point and the half-line (e.g., ray) extending from the fourth point 529 as the second representation point to the fifth point 531 as the third representation point is less than the specified angle, the processor of the object recognition device can identify that there are no contour points in the second point 525 as the first representation point, the third point 527 as the fourth representation point, the fourth point 529 as the second representation point, and the fifth point 531 as the third representation point.

[0120] Figure 6 The present invention is a flowchart showing the operation of an object recognition device for recognizing contour points by using a reference contour point in an object recognition device or an object recognition method.

[0121] The following assumptions Figure 1 The object recognition device 101 performs Figure 6 In addition, Figure 6 In the description, the operations described as being performed by the device can be understood as being controlled by the processor 105 of the object recognition device 101.

[0122] refer to Figure 6 In a first operation 601, a processor of an object recognition device may identify a first reference contour point and a first representation point. The first reference contour point may include one of two outermost (e.g., most prominent or farthest from the center of the object) endpoints of a plurality of representation points. The first representation point may include a representation point next to the first reference contour point.

[0123] In the second operation 603, the processor of the object recognition device may identify a second representation point and a third representation point. The second representation point may match the first representation point. The third representation point may include a representation point farther away from the first reference contour point from the two representation points on both sides of the second representation point.

[0124] In the third operation 605, the processor of the object recognition device may identify whether the second representation point is one of the two endpoints. When the second representation point is one of the two endpoints, the processor of the object recognition device may perform a fourth operation 607. When the second representation point is not one of the two endpoints, the processor of the object recognition device may perform a fifth operation 609. In other words, when the second representation point is one of the two endpoints, the processor of the object recognition device may identify the contour point through an exception operation because it is difficult to identify the third representation point.

[0125] In a fifth operation 609, the processor of the object recognition device may identify which of the second representation point and the fourth representation point is a contour point. Figure 7 A method for identifying contour points when the second representation point is one of the two endpoints is described.

[0126] In the fourth operation 607, the processor of the object recognition device may identify whether the distance between the first reference contour point and the second representation point is greater than a specified distance. When the distance between the first reference contour point and the second representation point is greater than the specified distance, the processor of the object recognition device may perform a sixth operation 611. When the distance between the first reference contour point and the second representation point is not greater than the specified distance, the processor of the object recognition device may perform a seventh operation 613.

[0127] This is because, in the case of identifying the second representation point as a contour point, when the distance between the first reference contour point and the second representation point is greater than a specified distance, the distance between the first reference contour point and the contour point identified based on the first reference contour point may be greater than the specified distance. When the distance between the contour points is greater than the specified distance, when the shape of the object identified by the contour point is compared with the precision map, the accuracy may be reduced. Therefore, in order to ensure that the reliability of the contour line of the object identified by the contour point is greater than the specified reliability value, the processor of the object recognition device may identify the second representation point or the fourth representation point as a contour point when the distance between the first reference contour point and the second representation point is greater than the specified distance.

[0128] In the sixth operation 611, the processor of the object recognition device may identify whether the first representation point and the second representation point match each other. When the first representation point and the second representation point match each other, the processor of the object recognition device may identify the eighth operation 615. When the first representation point does not match the second representation point, the processor of the object recognition device may identify the ninth operation 617.

[0129] In an eighth operation 615, the processor of the object recognition device may identify the second representation point as a contour point. When the first representation point and the second representation point match each other, there is no representation point closer to the first reference contour point than the second representation point.

[0130] In a ninth operation 617, the processor of the object recognition device may identify the fourth representation point as a contour point because the fourth representation point is the representation point farthest from the reference contour point among the representation points located within the specified distance.

[0131] In the seventh operation 613, the processor of the object recognition device may identify whether the angle recognized based on the first reference contour point, the first representation point, the second representation point, and the third representation point is less than the specified angle. When the angle recognized based on the first reference contour point, the first representation point, the second representation point, and the third representation point is less than the specified angle, the processor of the object recognition device may perform a tenth operation 619. When the angle recognized based on the first reference contour point, the first representation point, the second representation point, and the third representation point is greater than or equal to the specified angle, the processor of the object recognition device may perform a thirteenth operation 625.

[0132] This is because the importance of the second representation point may be very high because the second representation point is located in a portion in which an angle of a line segment connecting the representation points is bent when the angle is greater than or equal to a specified angle. An angle is identified based on the first reference contour point, the first representation point, the second representation point, and the third representation point, and the angle may include an angle between a half-line (e.g., a ray) extending from the first reference contour point to the first representation point and a half-line (e.g., a ray) extending from the second representation point to the third representation point.

[0133] In the tenth operation 619, the processor of the object recognition device may identify whether the second representation point is one of the two endpoints. When the second representation point is one of the two endpoints, the processor of the object recognition device may perform the eleventh operation 621. When the second representation point is not one of the two endpoints, the processor of the object recognition device may perform the twelfth operation 623.

[0134] Even if the distance between the first reference contour point and the second representation point is less than or equal to the specified distance and the angle is less than the specified angle, the processor of the object recognition device may still identify the second representation point as a contour point when the second representation point is one of the two endpoints.

[0135] In an eleventh operation 621 , the processor of the object recognition device may identify the second representation point as a contour point.

[0136] In the twelfth operation 623, the processor of the object recognition device may identify the second representation point and the third representation point as representation points of non-contour points. In other words, the processor of the object recognition device may identify that there are no contour points among the first representation point, the second representation point and the third representation point. In addition, the processor of the object recognition device may perform the second operation 603 again. It should be noted that when the second operation 603 is performed again, the processor of the object recognition device may identify the previous third representation point as the second representation point, and identify one of the two representation points on both sides of the previous second representation point that is farther away from the first reference contour point as the third representation point. In other words, the processor of the object recognition device may identify one of the two representation points on both sides of the third representation point that is farther away from the first reference contour point as the fifth representation point based on identifying that there are no contour points among the first representation point, the second representation point and the fourth representation point. The processor of the object recognition device can be configured to identify one of the second representation point and the fourth representation point as a contour point based on recognizing that the distance between the first reference contour point and the third representation point is greater than a specified distance, or the angle between a semi-straight line (e.g., a ray) extending from the first reference contour point to the first representation point and a semi-straight line (e.g., a ray) extending from the third representation point to the fifth representation point is greater than or equal to a specified angle.

[0137] In a thirteenth operation 625 , the processor of the object recognition device may identify the second representation point as a contour point.

[0138] Figure 7 The present invention is a flowchart showing the operation of an object recognition device for recognizing that a specific representative point is a contour point through a reference contour point in an object recognition device or an object recognition method.

[0139] The following assumptions Figure 1 The object recognition device 101 performs Figure 7 In addition, Figure 7 In the description, the operations described as being performed by the device can be understood as being controlled by the processor 105 of the object recognition device 101.

[0140] refer to Figure 7 In the first operation 701, the processor of the object recognition device may identify the first reference contour point and the first representation point. Figure 6 The first operation 601 in is the same as that in the first operation 601, so repeated description will be omitted below.

[0141] In the second operation 703, the processor of the object recognition device may identify the second representation point and the third representation point. Figure 6 The second operation 603 is the same as that in the above description, so repeated description will be omitted below.

[0142] In the third operation 705, the processor of the object recognition device may identify whether the second representation point is one of the two endpoints. When the second representation point is one of the two outermost (e.g., most protruding or farthest from the center of the object) endpoints among the plurality of representation points, since it is difficult to identify the third representation point, the processor of the object recognition device may identify the contour point through an exception operation.

[0143] In the fourth operation 707, the processor of the object recognition device may identify whether the distance between the first reference contour point and the second representation point is greater than a specified distance. When the distance between the first reference contour point and the second representation point is greater than the specified distance, the processor of the object recognition device may perform a fifth operation 709. When the distance between the first reference contour point and the second representation point is less than or equal to the specified distance, the processor of the object recognition device may perform a sixth operation 711. Since the execution manner of the fourth operation 707 is similar to that of Figure 6 The fourth operation 607 is the same as that in FIG. 6 , and thus repeated description will be omitted below.

[0144] In the sixth operation 711, the processor of the object recognition device may identify the second representation point as a contour point. Because when the second representation point is one of the two outermost (e.g., most protruding or farthest from the center of the object) endpoints of the plurality of representation points, a half-line (e.g., ray) extending from the second representation point to the third representation point cannot be identified, the angle between the half-line (e.g., ray) extending from the first reference contour point to the first representation point and the half-line (e.g., ray) extending from the second representation point to the third representation point may not be identified. Therefore, even if the distance between the first reference contour point and the second representation point is not greater than the specified distance, the processor of the object recognition device may identify the second representation point as a contour point without determining the angle condition.

[0145] In the fifth operation 709, the processor of the object recognition device may identify whether the first representation point and the second representation point match each other. When the first representation point matches the second representation point, the processor of the object recognition device may perform a seventh operation 713. When the first representation point does not match the second representation point, the processor of the object recognition device may perform an eighth operation 715. Because the fifth operation 709 is performed in the same manner as Figure 6 The sixth operation 611 in is the same, so repeated description will be omitted below.

[0146] In the seventh operation 713, the processor of the object recognition device may identify the second representation point as a contour point. Figure 6 The eighth operation 615 in is the same, so repeated description will be omitted below.

[0147] In the eighth operation 715, the processor of the object recognition device may identify the fourth representation point as a contour point. Figure 6The ninth operation 617 in is the same, so repeated description will be omitted below.

[0148] Figure 8 An example of a plurality of reference contour points and recognized representative points used to recognize contour points in an object recognition device or an object recognition method is shown.

[0149] refer to Figure 8 , the processor of the object recognition device may identify a representation point including some or all of the external points (e.g., surface points) among the points obtained by a sensor (e.g., light detection and ranging (LIDAR)). The representation point in the first example 801 may include a first point 803, a second point 805, and a third point 807. The representation point in the second example 811 may include a first point 813, a second point 815, a third point 817, and a fourth point 819.

[0150] The first example 801 shows a method of identifying contour points using two reference contour points when the third reference contour point and the sixth representation point match each other. The first point 803 can be identified as the second reference contour point. The second point 805 can be identified as the third reference contour point and the sixth representation point. The third point 807 can be identified as the seventh representation point.

[0151] The second example 811 illustrates a method of identifying contour points using two reference contour points when the third reference contour point and the sixth representation point do not match each other. The first point 813 can be identified as the second reference contour point. The second point 815 can be identified as the third reference contour point. The third point 817 can be identified as the sixth representation point. The fourth point 819 can be identified as the seventh representation point.

[0152] In the first example 801, the distance between the second point 805 as the third reference contour point and the third point 807 as the seventh representation point is greater than a specified distance (e.g., approximately 3 meters), and the processor of the object recognition device may identify the third point 807 as the seventh representation point as a contour point.

[0153] In the first example 801, when the angle between a half-straight line (e.g., a ray) extending from a first point 803 as a second reference contour point to a second point 805 as a third reference contour point and a half-straight line (e.g., a ray) extending from the second point 805 as a sixth representation point to a third point 807 as a seventh representation point is greater than or equal to a specified angle (e.g., approximately 10°), the processor of the object recognition device may identify the third point 807 as the seventh representation point as a contour point.

[0154] In the first instance 801, based on identifying that the distance between the second point 805 as the sixth representation point and the third point 807 as the seventh representation point is less than or equal to a specified distance and that the angle between a half-straight line (e.g., a ray) extending from the first point 803 as the second reference contour point to the second point 805 as the third reference contour point and a half-straight line (e.g., a ray) extending from the second point 805 as the sixth representation point to the third point 807 as the seventh representation point is less than a specified angle, the processor of the object recognition device can identify that there is no contour point between the second point 805 as the sixth representation point and the third point 807 as the seventh representation point.

[0155] The processor of the object recognition device may re-recognize the contour points as in the second example 811 according to recognizing that there are no contour points between the second point 805 as the sixth representation point and the third point 807 as the seventh representation point.

[0156] In the second example 811, the distance between the second point 815 as the third reference contour point and the fourth point 819 as the seventh representation point is greater than the specified distance (for example, about 3 meters), and the processor of the object recognition device can identify the third point 817 as the sixth representation point as a contour point.

[0157] In the second example 811, when the angle between a half-straight line (e.g., a ray) extending from a first point 813 as a second reference contour point to a second point 815 as a third reference contour point and a half-straight line (e.g., a ray) extending from a third point 817 as a sixth representation point to a fourth point 819 as a seventh representation point is greater than or equal to a specified angle (e.g., approximately 10°), the processor of the object recognition device may identify the fourth point 819 as the seventh representation point as a contour point.

[0158] In the second instance 811, based on identifying that the distance between the second point 815 as the third reference contour point and the fourth point 819 as the seventh representation point is less than or equal to a specified distance and that the angle between the half straight line (e.g., ray) extending from the first point 813 as the second reference contour point to the second point 815 as the third reference contour point and the half straight line (e.g., ray) extending from the third point 817 as the sixth representation point to the fourth point 819 as the seventh representation point is less than a specified angle, the processor of the object recognition device can identify that there are no contour points between the third point 817 as the sixth representation point and the fourth point 819 as the seventh representation point.

[0159] Fig. 9 The present invention is a flowchart showing the operation of an object recognition device for recognizing contour points using a plurality of reference contour points in an object recognition device or an object recognition method.

[0160] The following assumptions Figure 1 The object recognition device 101 performs Fig. 9In addition, Fig. 9 In the description, the operations described as being performed by the device can be understood as being controlled by the processor 105 of the object recognition device 101.

[0161] refer to Fig. 9 In a first operation 901, a processor of the object recognition device may identify a second reference contour point and a third reference contour point. The second reference contour point may include one contour point among a plurality of representative points. The third reference contour point may include one of two contours on both sides of the second reference contour point.

[0162] In the second operation 903, the processor of the object recognition device may identify a sixth representation point and a seventh representation point. The sixth representation point and the seventh representation point may not be located between the second reference contour point and the third reference contour point. The seventh representation point may include a representation point that is farther away from the second reference contour point from the two representation points on both sides of the sixth representation point.

[0163] In the third operation 905, the processor of the object recognition device may identify whether the distance between the third reference contour point and the seventh representation point is greater than a specified distance. When the distance between the third reference contour point and the seventh representation point is greater than the specified distance, the processor of the object recognition device may perform a fourth operation 907. When the distance between the third reference contour point and the seventh representation point is less than or equal to the specified distance, the processor of the object recognition device may perform a fifth operation 909.

[0164] This is because, in the case of identifying the seventh representation point as a contour point, when the distance between the third reference contour point and the seventh representation point is greater than a specified distance, the distance between the third reference contour point and the contour point identified based on the second reference contour point and the third reference contour point may be greater than the specified distance. When the distance between the contour points is greater than the specified distance, when the shape of the object identified by the contour point is compared with the precision map, the accuracy may be reduced. Therefore, in order to ensure reliability greater than a specified reliability value for the contour line of the object identified by the contour point, the distance between the third contour point and the seventh representation point may be considered when identifying the contour point.

[0165] In the fourth operation 907, the processor of the object recognition device may identify whether the sixth representation point and the third reference contour point match each other. When the sixth representation point and the third reference contour point match each other, the processor of the object recognition device may perform a sixth operation 911. When the sixth representation point and the third reference contour point do not match each other, the processor of the object recognition device may perform a seventh operation 913.

[0166] In the fifth operation 909, the processor of the object recognition device may identify whether the angle identified based on the second reference contour point, the third reference contour point, the sixth representation point, and the seventh representation point is less than the specified angle. When the angle determined based on the second reference contour point, the third reference contour point, the sixth representation point, and the seventh representation point is less than the specified angle, the processor of the object recognition device may perform an eighth operation 915. When the angle determined based on the second reference contour point, the third reference contour point, the sixth representation point, and the seventh representation point is greater than or equal to the specified angle, the processor of the object recognition device may perform a ninth operation 921.

[0167] The angle determined based on the second reference contour point, the third reference contour point, the sixth representation point, and the seventh representation point may include an angle between a half-line (e.g., a ray) extending from the second reference contour point to the third reference contour point and a half-line (e.g., a ray) extending from the sixth representation point to the seventh representation point. This is because the importance of the seventh representation point may be high because the seventh representation point is located in a portion where the angle of a line segment connecting the representation points is bent when it is greater than or equal to a specified angle. Therefore, the processor of the object recognition device may consider the angle identified based on the second reference contour point, the third reference contour point, the sixth representation point, and the seventh representation point when identifying the contour point.

[0168] In the eighth operation 915, the processor of the object recognition device may identify whether the seventh representation point is one of the two endpoints. When the seventh representation point is one of the two endpoints, the processor of the object recognition device may perform a tenth operation 917. When the seventh representation point is not one of the two endpoints, the processor of the object recognition device may perform an eleventh operation 919.

[0169] Even if the distance between the third reference contour point and the seventh representation point is less than or equal to the specified distance and the angle is less than the specified angle, the processor of the object recognition device may still identify the seventh representation point as a contour point when the seventh representation point is one of the two endpoints.

[0170] In a tenth operation 917 , the processor of the object recognition device may identify the seventh representation point as a contour point.

[0171] In the eleventh operation 919 , the processor of the object recognition device may identify the sixth and seventh representation points as representation points of non-contour points. In addition, the processor of the object recognition device may perform the second operation 903 again.

[0172] According to the recognition that there is no contour point in the sixth representation point and the seventh representation point, the processor of the object recognition device may recognize the representation point farther away from the second reference contour point among the two representation points on both sides of the seventh representation point as the eighth representation point. The processor of the object recognition device may be configured to recognize one of the sixth representation point and the seventh representation point as a contour point according to the recognition that the distance between the third reference contour point and the seventh representation point is greater than a specified distance or the angle between the half straight line (e.g., ray) extending from the second reference contour point to the third reference contour point and the half straight line (e.g., ray) extending from the sixth representation point to the seventh representation point is greater than or equal to a specified angle.

[0173] In a ninth operation 921 , the processor of the object recognition device may identify the seventh representation point as a contour point.

[0174] Fig.10 An example of recognizing contour points in an object recognition device or an object recognition method is shown.

[0175] refer to Fig.10 , the first screen 1001 may display the representation points and contour points recognized by the existing object recognition device. The second screen 1011 may display the representation points and contour points recognized by the object recognition device. The empty points in the first screen 1001 and the second screen 1011 may be the representation points that are not recognized as contour points. The solid points in the first screen 1001 and the second screen 1011 may be the representation points recognized as contour points.

[0176] In the first frame 1001 , when the conventional object recognition apparatus recognizes contour points, it may not perform angle comparison between the first reference line segment and subsequent reference line segments to recognize contour points.

[0177] In the second screen 1011, based on the representation point, identification is performed to determine whether the representation point is a contour point. Because when the object recognition device identifies a contour point, the angle between the identified contour point and the representation point on which it is based can be considered, so the representation point whose angle change exceeds the specified angle can be identified as a contour point.

[0178] Therefore, compared with the conventional object recognition device, the object recognition device can recognize the representative point whose angle changes exceed the specified angle as a contour point.

[0179] Fig.11 An example of reliability indicating the accuracy of recognized contour points in an object recognition device or an object recognition method is shown.

[0180] refer to Fig.11 The screen 1100 may display a first distribution graph 1103 of contour points recognized by a conventional object recognition device and a second distribution graph 1105 of contour points recognized by the object recognition device.

[0181] In the first distribution graph 1103, the reliability of the contour points recognized by the existing object recognition device may be about 66.5. In the second distribution graph 1105, the reliability of the contour points recognized by the object recognition device may be about 71.5. Therefore, the reliability of the contour points recognized by the object recognition device may be higher than the reliability of the contour points recognized by the existing object recognition device.

[0182] The processor of the object recognition device may calculate the reliability of the contour point according to at least one of the first variable value, the second variable value, the third variable value, the fourth variable value, the fifth variable value, or any combination thereof.

[0183] The first endpoint and the second endpoint may correspond to the two outermost (eg, most prominent or farthest from the center of the object) endpoints of the contour points. The peak point may include the contour point farthest from the line segment connecting the first endpoint and the second endpoint.

[0184] The first line segment may include a line segment connecting the first endpoint and the peak point. The second line segment may include a line segment connecting the second endpoint and the peak point.

[0185] The reliability of the contour point can be determined based on the sum of at least one of the value obtained by multiplying the first variable value by the weight, the value obtained by multiplying the second variable value by the weight, the value obtained by multiplying the third variable value by the weight, the value obtained by multiplying the fourth variable value by the weight, the value obtained by multiplying the fifth variable value by the weight, or any combination thereof.

[0186] The first variable value may include a value determined according to the variance of the contour points. For example, the processor of the object recognition device may identify the first variable value according to the variance value of the distance between the first line segment and the contour points near the first line segment and the variance value of the distance between the second line segment and the contour points near the second line segment.

[0187] The second variable value may be determined based on the contour point distribution of the first line segment and the contour point distribution of the second line segment.

[0188] For example, the contour point distribution of the first line segment may include identifying whether all contour points near the first line segment are distributed in only one direction relative to the first line segment. The contour point distribution of the second line segment may include identifying whether all contour points near the second line segment are distributed in only one direction.

[0189] The third variable value may be determined based on an average value of the contour point angles. The angle of each contour point may include an angle between a half straight line (e.g., a ray) extending from a specific contour point to one of the contour points on both sides of the specific contour point and a half straight line (e.g., a ray) extending from the specific contour point to another of the contour points on both sides of the specific contour point.

[0190] The fourth variable value may be determined based on the contour point distribution of the first line segment and the contour point distribution of the second line segment.

[0191] The fifth variable value may be determined according to a ratio of a length in a single direction of a contour box containing contour points in a specific layer to a length in a single direction of a cluster box containing contour points in a plurality of layers.

[0192] Fig.12 A computing system for an object recognition device or an object recognition method is shown.

[0193] refer to Fig.12 The computing system 1200 may include at least one processor 1210 , a memory 1230 , a user interface input device 1240 , a user interface output device 1250 , a storage 1260 , and a network interface 1270 , which are interconnected via a bus 1220 .

[0194] The processor 1210 may be a central processing unit (CPU) or a semiconductor device that processes instructions stored in the memory 1230 and / or the storage 1260. The memory 1230 and the storage 1260 may include various types of volatile or non-volatile storage media. For example, the memory 1230 may include a ROM (read only memory) 1231 and a RAM (random access memory) 1232.

[0195] Therefore, the operation of the method or algorithm is related to one or more exemplary embodiments disclosed herein and can be directly embodied in hardware or in a software module executed by the processor 1210, or in a combination thereof. The software module can reside on a storage medium (i.e., memory 1230 and / or storage 1260) such as RAM, flash memory, ROM, EPROM, EEPROM, registers, hard disk, removable disk, and CD-ROM.

[0196] An exemplary memory medium may be coupled to the processor 1210, and the processor 1210 may read information from the memory medium and may record information in the memory medium. Alternatively, the memory medium may be integrated with the processor 1210. The processor and the memory medium may be located in an application specific integrated circuit (ASIC). The ASIC may be located in a user terminal. In another case, the processor and the memory medium may exist in a user terminal as separate components.

[0197] The above description merely illustrates the technical idea of ​​the present disclosure, and those skilled in the art in the technical field to which the present disclosure belongs may make various modifications and changes without departing from the basic features of the present disclosure.

[0198] Therefore, one or more exemplary embodiments disclosed in the present disclosure are not used 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 by the exemplary embodiments. The protection scope of the present disclosure shall be interpreted by the following claims, and all technical ideas within the equivalent scope of the claims shall be interpreted as included in the scope of the present disclosure.

[0199] This technology can reduce the amount of calculation required for object recognition by recognizing some representative points obtained by a sensor such as light detection and ranging (LIDAR) as contour points.

[0200] In addition, the present technology can also improve the accuracy of contour points representing an object by using angle conditions and length conditions.

[0201] In addition, compared with multiple contour points, the present technology improves the accuracy of representing the object by increasing the spacing between contour points at the unchanged part of the object contour and decreasing the spacing between contour points at the changing part of the object contour.

[0202] In addition, this technology can also improve the accuracy of identifying the direction of movement of an object by increasing the accuracy of the contour points representing the object.

[0203] In addition, the present technology can enhance the user experience by improving the accuracy of contour points representing objects.

[0204] Additionally, the present technology may reduce the risk of accidents for autonomous vehicles or vehicles with enabled driver assistance devices by improving the accuracy of the direction in which an object is identified to be moving.

[0205] In addition, the present technology can improve the performance of autonomous driving or driving assistance equipment by increasing the accuracy of the direction of movement of identified objects.

[0206] Furthermore, various effects directly or indirectly understood through the present disclosure can also be provided.

[0207] Although the present disclosure has been described above with reference to one or more exemplary embodiments and the accompanying drawings, the present disclosure is not limited thereto, but may be variously modified and altered by those skilled in the art to which the present disclosure belongs without departing from the spirit and scope of the present disclosure as required by the following claims.

Claims

1. An object recognition device, comprising: sensor; as well as The processor is configured as: Extracting a plurality of representative points including at least a portion of the surface points of the object from a plurality of points obtained via the sensor and representing the object; Determine a first reference contour point, the first reference contour point being one of two outermost endpoints of the plurality of representation points; determining a first representation point adjacent to the first reference contour point among the plurality of representation points; determining a second representation point different from the first reference contour point among the plurality of representation points; determining a third representation point, wherein the third representation point is: a point farther away from the first reference contour point among the two representation points on both sides of the second representation point; determining a first distance between the first reference contour point and the second representative point; determining a first angle between a first ray extending from the first reference contour point to the first representation point and a second ray extending from the second representation point to the third representation point; Determine one of the following as a contour point: The second representation point is determined based on: matching the second representation point with the first representation point, and also based on determining that the first distance is greater than a threshold distance or the first angle is greater than or equal to a threshold angle, one of the first representation point or the second representation point, determined based on: based on the first representation point not matching the second representation point, further based on determining that the first distance is greater than the threshold distance or the first angle is greater than or equal to the threshold angle, and further based on determining that other representation points of the plurality of representation points do not exist between the first representation point and the second representation point, and one of the second representation point or the fourth representation point, determined based on: based on the first representation point not matching the second representation point, further based on determining that the at least one other representation point of the plurality of representation points exists between the first representation point and the second representation point, and further based on determining that the first distance is greater than the threshold distance or the first angle is greater than or equal to the threshold angle, wherein the fourth representation point is a point closer to the first reference contour point among the two representation points on either side of the second representation point; and The vehicle is controlled according to the contour points.

2. The object recognition device according to claim 1, wherein: The processor is further configured to determine one of the following as the contour point: The second representation point is determined based on: determining that the first distance is greater than the threshold distance, and also based on matching the first representation point with the second representation point, The first representation point is determined based on: determining that the first distance is greater than the threshold distance, and further based on determining that no other representation point exists between the first representation point and the second representation point, and The fourth representation point is determined based on: determining that the first distance is greater than the threshold distance, and also based on determining that the at least one other representation point exists between the first representation point and the second representation point.

3. The object recognition device according to claim 1, wherein: The processor is further configured to determine one of: The second representative point is the contour point, determined based on: the second representative point is one of the two outermost endpoints, and further based on determining that the first distance is less than or equal to the threshold distance and the first angle is less than the threshold angle, and The contour point does not exist in the first representation point, the second representation point and the fourth representation point, and is determined based on: the second representation point is not one of the two outermost endpoints.

4. The object recognition device according to claim 1, wherein: The processor is further configured to determine that the second representation point is the contour point according to determining that the first distance is less than or equal to the threshold distance and the first angle is greater than or equal to the threshold angle.

5. The object recognition device according to claim 1, wherein: The processor is further configured to determine one of the following as the contour point: The second representation point is determined based on: determining that the second representation point is one of the two outermost endpoints, determining that the first distance is greater than the threshold distance, and matching the first representation point with the second representation point, The first representation point is determined based on: based on determining that the second representation point is one of the two outermost endpoints, based on determining that the first distance is greater than the threshold distance, based on the first representation point not matching the second representation point, and based on determining that no other representation point in the plurality of representation points exists between the first representation point and the second representation point, and The fourth representation point is determined based on: determining that the second representation point is one of the two outermost endpoints, determining that the first distance is greater than the threshold distance, the first representation point does not match the second representation point, and determining that at least one other representation point among the multiple representation points exists between the first representation point and the second representation point.

6. The object recognition device according to claim 1, wherein: The processor is further configured to: Based on determining that the second representation point is one of the two outermost endpoints and also based on determining that the first distance is less than or equal to the threshold distance, the second representation point is determined to be the contour point.

7. The object recognition device according to claim 1, wherein: The processor is further configured to: determining a fifth representation point based on determining that the contour point does not exist in the first representation point, the second representation point, and the fourth representation point, the fifth representation point being a point farther from the first reference contour point among the two representation points on both sides of the third representation point; and One of the second representation point or the third representation point is determined to be the contour point based on determining that the second distance between the first reference contour point and the third representation point is greater than the threshold distance, or that the second angle between the first ray and the third ray extending from the third representation point to the fifth representation point is greater than or equal to the threshold angle.

8. The object recognition device according to claim 1, wherein: The processor is further configured to: determining a second reference contour point and a third reference contour point, wherein the third reference contour point is one of two contour points on both sides of the second reference contour point; determining a sixth representation point that is not between the second reference contour point and the third reference contour point; determining a seventh representation point, the seventh representation point being a point farther from the second reference contour point among the two representation points on both sides of the sixth representation point; determining a second distance between the third reference contour point and the seventh representation point; determining a second angle between a third ray extending from the second reference contour point to the third reference contour point and a fourth ray extending from the sixth representation point to the seventh representation point; and Determine one of the following as the contour point: The seventh representation point is determined based on: determining that the second distance is greater than the threshold distance or the second angle is greater than or equal to the threshold angle, and also matching the sixth representation point based on the third reference contour point; and One of the sixth representation point or the seventh representation point is determined based on: determining that the second distance is greater than the threshold distance or the second angle is greater than or equal to the threshold angle, and also based on the fact that the third reference contour point does not match the sixth representation point.

9. The object recognition device according to claim 8, wherein: The processor is further configured to determine one of the following as the contour point: The seventh representation point is determined based on: the second distance being greater than the threshold distance, and the third reference contour point matching the sixth representation point, and The sixth representation point is determined based on: the second distance is greater than the threshold distance, and the third reference contour point does not match the sixth representation point.

10. The object recognition device according to claim 8, wherein: The processor is further configured to: determining whether the seventh representation point is one of the two outermost endpoints based on determining that the second distance is less than or equal to the threshold distance and the second angle is less than the threshold angle; as well as Identify one of the following: According to the seventh representation point being one of the two outermost endpoints, determining the seventh representation point as the contour point, and According to the fact that the seventh representation point is not one of the two outermost endpoints, it is determined that the contour point does not exist in the sixth representation point and the seventh representation point.

11. The object recognition device according to claim 8, wherein: The processor is further configured to determine that the seventh representation point is the contour point according to determining that the second distance is less than or equal to the threshold distance and the second angle is greater than or equal to the threshold angle.

12. The object recognition device according to claim 8, wherein: The processor is further configured to: determining an eighth representation point, which is a point farther from the second reference contour point than the second reference contour point, based on determining that the contour point does not exist in the sixth representation point and the seventh representation point; and One of the seventh representation point and the eighth representation point is determined to be the contour point based on determining that a third distance between the third reference contour point and the eighth representation point is greater than the threshold distance, or a third angle between the third ray and a fifth ray extending from the seventh representation point to the eighth representation point is greater than or equal to the threshold angle.

13. A method for object recognition, the method comprising the following steps: Extracting a plurality of representative points including at least a portion of the surface points of the object from a plurality of points obtained via a sensor and representing the object; Determining a first reference contour point, the first reference contour point being one of two outermost endpoints of the plurality of representation points; determining a first representation point adjacent to the first reference contour point among the plurality of representation points; determining a second representation point different from the first reference contour point among the plurality of representation points; determining a third representation point, the third representation point being a point farther from the first reference contour point among the two representation points on both sides of the second representation point; determining a first distance between the first reference contour point and the second representative point; determining a first angle between a first ray extending from the first reference contour point to the first representation point and a second ray extending from the second representation point to the third representation point; Determine one of the following as a contour point: The second representation point is determined based on: matching the second representation point with the first representation point, and also based on determining that the first distance is greater than a threshold distance or the first angle is greater than or equal to a threshold angle, one of the first representation point or the second representation point, determined based on: based on the first representation point not matching the second representation point, further based on determining that the first distance is greater than the threshold distance or the first angle is greater than or equal to the threshold angle, and further based on determining that other representation points of the plurality of representation points do not exist between the first representation point and the second representation point, and one of the second representation point or the fourth representation point, determined based on: based on the first representation point not matching the second representation point, further based on determining that the at least one other representation point of the plurality of representation points exists between the first representation point and the second representation point, and further based on determining that the first distance is greater than the threshold distance or the first angle is greater than or equal to the threshold angle, wherein the fourth representation point is a point closer to the first reference contour point of the two representation points on either side of the second representation point; and The vehicle is controlled according to the contour points.

14. The object recognition method according to claim 13, further comprising determining one of the following as the contour point: The second representation point is determined based on: determining that the first distance is greater than the threshold distance, and also based on matching the first representation point with the second representation point, The first representation point is determined based on: determining that the first distance is greater than the threshold distance, and further based on determining that no other representation point exists between the first representation point and the second representation point, and The fourth representation point is determined based on: determining that the first distance is greater than the threshold distance, and also based on determining that the at least one other representation point exists between the first representation point and the second representation point.

15. The object recognition method according to claim 13, further comprising determining one of the following: The second representative point is the contour point, determined based on: the second representative point is one of the two outermost endpoints, and further based on determining that the first distance is less than or equal to the threshold distance and the first angle is less than the threshold angle, and The contour point does not exist in the first representation point, the second representation point and the fourth representation point, and is determined based on: the second representation point is not one of the two outermost endpoints.

16. The object recognition method according to claim 13, further comprising the following steps: The second representative point is determined to be the contour point according to determining that the first distance is less than or equal to the threshold distance and the first angle is greater than or equal to the threshold angle.

17. The object recognition method according to claim 13, further comprising determining one of the following as the contour point: The second representation point is determined based on: determining that the second representation point is one of the two outermost endpoints, determining that the first distance is greater than the threshold distance, and matching the first representation point with the second representation point, The first representation point is determined based on: based on determining that the second representation point is one of the two outermost endpoints, based on determining that the first distance is greater than the threshold distance, based on the first representation point not matching the second representation point, and based on determining that no other representation point in the plurality of representation points exists between the first representation point and the second representation point, and The fourth representation point is determined based on: determining that the second representation point is one of the two outermost endpoints, determining that the first distance is greater than the threshold distance, the first representation point does not match the second representation point, and determining that at least one other representation point among the multiple representation points exists between the first representation point and the second representation point.

18. The object recognition method according to claim 13, further comprising the following steps: Based on determining that the second representation point is one of the two outermost endpoints and also based on determining that the first distance is less than or equal to the threshold distance, the second representation point is determined to be the contour point.

19. The object recognition method according to claim 13, further comprising the following steps: determining a fifth representation point based on determining that the contour point does not exist in the first representation point, the second representation point, and the fourth representation point, the fifth representation point being a point farther from the first reference contour point among the two representation points on both sides of the third representation point; and One of the second representation point or the third representation point is determined to be the contour point based on determining that the second distance between the first reference contour point and the third representation point is greater than the threshold distance, or that the second angle between the first ray and the third ray extending from the third representation point to the fifth representation point is greater than or equal to the threshold angle.

20. The object recognition method according to claim 13, further comprising the following steps: Determining a second reference contour point and a third reference contour point, wherein the third reference contour point is one of two contour points on both sides of the second reference contour point; determining a sixth representation point that is not between the second reference contour point and the third reference contour point; determining a seventh representation point, the seventh representation point being a point farther from the second reference contour point among the two representation points on both sides of the sixth representation point; determining a second distance between the third reference contour point and the seventh representation point; determining a second angle between a third ray extending from the second reference contour point to the third reference contour point and a fourth ray extending from the sixth representation point to the seventh representation point; and Determine one of the following as the contour point: The seventh representation point is determined based on: determining that the second distance is greater than the threshold distance or the second angle is greater than or equal to the threshold angle, and also matching the sixth representation point based on the third reference contour point; and One of the sixth representation point or the seventh representation point is determined based on: determining that the second distance is greater than the threshold distance or the second angle is greater than or equal to the threshold angle, and also based on the fact that the third reference contour point does not match the sixth representation point.

Images