Method and device for estimating gradient of parking space

Abstract

The present invention relates to a method and an apparatus for estimating a gradient of a parking space, the apparatus comprising: a parking space detection module configured to recognize a type of the parking space based on an image captured by an image capturing device, and to recognize a position of the parking space by detecting a plurality of key points corresponding to the parking space; and a gradient estimation module configured to obtain angle information formed by key points in the type of the parking space, estimate a rotation matrix based on an estimation condition preset according to the angle information and the type of the parking space, and estimate a gradient of the parking space using the estimated rotation matrix and a predetermined reference rotation matrix.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to Korean Patent Application No. 10-2023-0094096, filed on Jul. 19, 2023, which is hereby incorporated by reference in its entirety for all purposes. Technical Field

[0003] The present invention relates to a technology for estimating the slope of a parking space, and more particularly to a method and device for estimating the slope of a parking space based on key points corresponding to the parking space detected through an image. Background Art

[0004] With the advancement of technology in recent years, vehicles capable of automatic driving and automatic parking have been developed and popularized. Typically, in a vehicle with an automatic parking function, when the driver activates the automatic parking function by operating a separate switch or executing a command, the vehicle system searches for a parking space for parking, provides parking route guidance, and operates the vehicle to be parked to park.

[0005] The technology of estimating the position of a parking space based on parking lines is highly dependent on camera image recognition performance, and when a parking space exists on a sloped road surface, it is difficult to estimate the accurate position of the parking space, which may deteriorate automatic parking control performance.

[0006] According to a conventional technique for estimating a slope of a parking space, the slope is estimated using a camera calibration value performed under the assumption that a road surface on which the parking space exists is on the same plane.

[0007] However, in actual environments, parking spaces have different slopes, which may lead to degradation of automatic parking control performance.

[0008] Therefore, a method is needed to improve the performance of automatic parking control by estimating the slope of each parking space.

[0009] The information included in this Background of the Invention section is only for enhancement of understanding of the general background of the invention and should not be taken as an admission or any form of suggestion that this information constitutes the prior art already known to a person skilled in the art. Summary of the invention

[0010] Various aspects of the present invention are directed to providing a method and apparatus for estimating a slope of a parking space based on key points corresponding to the parking space detected through an image.

[0011] The technical problems to be solved by the present invention are not limited to the above-mentioned problems, and those skilled in the art to which the present invention belongs will clearly understand any other technical problems not mentioned herein through the following description.

[0012] According to one aspect of the present invention, a device for estimating the slope of a parking space includes: a parking space detection module that identifies the type of a parking space based on an image captured by an image capturing device, and identifies the position of the parking space by detecting a plurality of key points corresponding to the parking space; and a slope estimation module that obtains angle information formed by key points in the type of the parking space, estimates a rotation matrix based on an estimation condition preset according to the angle information and the type of the parking space, and estimates the slope of the parking space using the estimated rotation matrix and a predetermined reference rotation matrix.

[0013] According to an exemplary embodiment of the present invention, the parking space detection module detects two start points from an entrance line of the parking space and two end points from an end line of the parking space as key points, and recognizes the position of the parking space using the key points including the two start points and the two end points.

[0014] According to an exemplary embodiment of the present invention, a slope estimation module obtains first angle information formed by a first stop line connecting a first starting point among the two starting points and a first end point among the two end points and an entrance line, and second angle information formed by a second stop line connecting a second starting point among the two starting points and a second end point among the two end points and the entrance line.

[0015] According to an exemplary embodiment of the present invention, the slope estimation module estimates the rotation matrix so that when the type of the parking space is orthogonal / parallel or the first angle information and the second angle information are obtuse angles and acute angles or acute angles and obtuse angles, the difference between the first angle information and the second angle information converges to a preset minimum value range, and the first angle information and the second angle information converge to a right angle.

[0016] According to an exemplary embodiment of the present invention, the slope estimation module estimates the rotation matrix so that when the type of the parking space is inclined or the first angle information and the second angle information are acute angles and acute angles or obtuse angles and obtuse angles, the difference between the first angle information and the second angle information converges to a preset minimum value range, and the first angle information and the second angle information are within a preset angle range.

[0017] According to an exemplary embodiment of the present invention, the slope estimation module estimates the rotation matrix so that the absolute value that differs by 90 degrees from the first angle information and the absolute value that differs by 90 degrees from the second angle information are within a range of 10 degrees to 60 degrees.

[0018] According to an exemplary embodiment of the present invention, the parking space detection module identifies the parking space by restoring at least a portion of the lost parking line in the case where at least a portion of the parking line of the parking space is lost, thereby identifying the type of the parking space.

[0019] According to an exemplary embodiment of the present invention, the parking space detection module identifies the type of the virtual parking space by identifying the virtual parking space using surrounding information including information about the parked vehicle.

[0020] According to an exemplary embodiment of the present invention, the parking space detection module recognizes a virtual parking space by considering the position of the parking block and the position of the parked vehicle in case the parking block is detected.

[0021] According to an exemplary embodiment of the present invention, the reference rotation matrix is ​​a rotation matrix for a road surface without a slope, and the slope estimation module estimates the slope of the parking space based on a difference between the estimated rotation matrix and the reference rotation matrix.

[0022] According to one aspect, a method for estimating a slope of a parking space includes the following steps: identifying a type of a parking space based on an image captured by an image capturing device, and identifying a position of the parking space by detecting a plurality of key points corresponding to the parking space; obtaining angle information formed by key points in the type of the parking space; estimating a rotation matrix based on an estimation condition preset according to the angle information and the type of the parking space; and estimating the slope of the parking space using the estimated rotation matrix and a predetermined reference rotation matrix.

[0023] According to an exemplary embodiment of the present invention, the step of identifying the position of the parking space includes: detecting two starting points from an entrance line of the parking space and two end points from an end line of the parking space as key points, and identifying the position of the parking space using the key points including the two starting points and the two end points.

[0024] According to an exemplary embodiment of the present invention, the step of obtaining angle information includes: obtaining first angle information formed by a first stop line connecting a first starting point among the two starting points and a first end point among the two end points and an entrance line, and obtaining second angle information formed by a second stop line connecting a second starting point among the two starting points and a second end point among the two end points and the entrance line.

[0025] According to an exemplary embodiment of the present invention, the step of estimating the rotation matrix includes: estimating the rotation matrix so that when the type of the parking space is orthogonal / parallel or the first angle information and the second angle information are obtuse angles and acute angles or acute angles and obtuse angles, the difference between the first angle information and the second angle information converges to a preset minimum value range, and the first angle information and the second angle information converge to a right angle.

[0026] According to an exemplary embodiment of the present invention, the step of estimating the rotation matrix includes: estimating the rotation matrix so that when the type of the parking space is inclined or the first angle information and the second angle information are acute angles and acute angles or obtuse angles and obtuse angles, the difference between the first angle information and the second angle information converges to a preset minimum value range, and the first angle information and the second angle information are within a preset angle range.

[0027] According to an exemplary embodiment of the present invention, the step of estimating the rotation matrix includes: estimating the rotation matrix so that the absolute value of the first angle information and the absolute value of the second angle information that differ by 90 degrees are within a range of 10 degrees to 60 degrees.

[0028] According to an exemplary embodiment of the present invention, the step of identifying the position of the parking space includes: in a case where at least a portion of a parking line of the parking space is lost, identifying the parking space by restoring at least a portion of the lost parking line, thereby identifying the type of the parking space.

[0029] According to an exemplary embodiment of the present invention, the step of identifying the location of the parking space includes identifying the type of the virtual parking space by identifying the virtual parking space using surrounding information including information about the parked vehicle.

[0030] According to an exemplary embodiment of the present invention, the step of identifying the position of the parking space includes: in a case where the parking block is detected, identifying a virtual parking space by considering the position of the parking block and the position of the parked vehicle.

[0031] According to an exemplary embodiment of the present invention, the reference rotation matrix is ​​a rotation matrix for a road surface without a slope, and the slope estimation module is configured to estimate the slope of the parking space based on a difference between the estimated rotation matrix and the reference rotation matrix.

[0032] The features briefly summarized above regarding the present invention are merely exemplary aspects of the detailed description of the invention described below and do not limit the scope of the invention.

[0033] The method and apparatus of the present invention have other features and advantages which shall be apparent or set forth in more detail in the accompanying drawings incorporated herein and in the following detailed description, which together serve to illustrate certain principles of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 A block diagram showing an apparatus for estimating a parking space slope according to an exemplary embodiment of the present invention;

[0035] Figure 2 An example diagram for describing a process of detecting a parking space is shown;

[0036] Figure 3A and Figure 3B An example diagram for describing a process of estimating a slope when the type of a parking space is orthogonal / parallel is shown;

[0037] Figure 4A and Figure 4B An example diagram for describing a process of estimating a slope when the type of a parking space is an inclined surface is shown;

[0038] Figure 5 An operational flowchart showing a method for estimating a parking space slope according to another exemplary embodiment of the present invention; and

[0039] Figure 6 is a block diagram of a computing system for executing a method for estimating a slope of a parking space according to another exemplary embodiment of the present invention.

[0040] It should be understood that the accompanying drawings are not necessarily drawn to scale, presenting somewhat simplified representations of various features illustrative of the basic principles of the invention. The intended design features of the present invention as included herein, including, for example, specific dimensions, orientations, locations, and shapes will be determined in part by the specific intended application and use environment.

[0041] In the drawings, reference numbers refer to the same or equivalent parts of the present invention throughout the several figures of the drawing. DETAILED DESCRIPTION

[0042] Reference will now be made in detail to various embodiments of the present invention, examples of which are shown in the accompanying drawings and described below. Although the present invention will be described in conjunction with exemplary embodiments of the present invention, it should be understood that this description is not intended to limit the present invention to those exemplary embodiments of the present invention. On the other hand, the present invention is intended to cover not only the exemplary embodiments of the present invention, but also various alternatives, modifications, equivalents and other embodiments that may be included within the spirit and scope of the present invention as defined by the appended claims.

[0043] Hereinafter, exemplary embodiments of the present invention are described in detail with reference to the accompanying drawings so that those skilled in the art can easily perform the present invention. However, the present invention can also be embodied in several different forms and is not limited to the exemplary embodiments described herein.

[0044] When describing the exemplary embodiments of the present invention, when it is determined that the detailed description of a known configuration or function may confuse the main points of the present invention, its detailed description will be omitted. In addition, in the accompanying drawings, parts not related to the description of the present invention are omitted, and similar parts are provided with similar reference numerals.

[0045] It will be understood that when an element is referred to as being “connected,” “coupled,” or “fixed” to another element, it may be directly connected or coupled to the other element, or intervening elements may be present. In addition, unless explicitly described to the contrary, the terms “comprises,” “has,” or “includes” will be understood to mean the inclusion of stated elements but not the exclusion of any other elements.

[0046] In an exemplary embodiment of the present invention, terms such as first and second are used only to distinguish one component from other components, and do not limit the order or importance of the components unless specifically mentioned. Therefore, within the scope of the present invention, a first element in an exemplary embodiment of the present invention may be referred to as a second element in another exemplary embodiment of the present invention, and similarly, a second element in an exemplary embodiment of the present invention may be referred to as a first element in another exemplary embodiment of the present invention.

[0047] In an exemplary embodiment of the present invention, different components are used only to clearly describe their features, and do not necessarily mean that these components are separate. That is, multiple components can be integrated to form a hardware or software unit, or a component can be distributed to form multiple hardware or software units. Therefore, even if not specifically mentioned, such integrated or distributed embodiments are also included in the scope of the present invention.

[0048] In an exemplary embodiment of the present invention, the components described in various embodiments do not necessarily mean necessary parts, and some parts may be optional parts. Therefore, exemplary embodiments including a subset of the parts described in an exemplary embodiment are also included in the scope of the present invention. In addition, in addition to the parts described in each exemplary embodiment of the present invention, exemplary embodiments including other parts are also included in the scope of the present invention.

[0049] In an exemplary embodiment of the present invention, for the convenience of description, the expressions of positional relationships used in the specification, such as top, bottom, left or right, are described, and when the drawings shown in the specification are viewed in reverse, the positional relationships described in the specification can also be interpreted in the opposite manner.

[0050] In an exemplary embodiment of the present invention, each of phrases such as "A or B", "at least one of A and B", "at least one of A or B", "A, B or C", "at least one of A, B and C", and "at least one of A, B or C" may include any one of the items listed together in the corresponding phrase, or any possible combination thereof.

[0051] Embodiments of the present invention may clearly estimate the position of a parking space by estimating the slope of the parking space based on key points of the parking space detected through image recognition, thereby improving automatic parking control performance.

[0052] An embodiment of the present invention may set different conditions for estimating the slope (hereinafter referred to as "estimation conditions") according to the type of the detected parking space, for example, orthogonal / parallel / inclined, etc., and use the estimation conditions according to the type of the parking space and the angle information formed by the key points to clearly estimate the slope of the parking space.

[0053] Here, parking spaces may be classified into an orthogonal / parallel type and an inclined type. When there is no slope, in an orthogonal / parallel type parking space, the angle formed by the parking lines may be orthogonal (or 90 degrees), and in an inclined type parking space, the angle formed by the parking lines may be an obtuse angle or an acute angle. On the other hand, when there is a slope, the two angles formed by the parking lines in the orthogonal / parallel type parking space may be an obtuse angle, an acute angle, or an acute angle, an obtuse angle, and the two angles formed by the parking lines of the inclined type parking space may be an acute angle, an acute angle, or an obtuse angle, an obtuse angle.

[0054] Two angles formed by the parking lines in an exemplary embodiment of the present invention will be described below in the detailed description of the present invention.

[0055] Figure 1 A block diagram of an apparatus for estimating a parking space slope according to an exemplary embodiment of the present invention is shown. The apparatus for estimating a parking space slope may be provided in an automatic vehicle or a vehicle equipped with an advanced driver assistance system (ADAS).

[0056] refer to Figure 1 According to an exemplary embodiment of the present invention, an apparatus 100 for estimating a parking space slope may include: a parking space detection module (or a parking space detector) 110 , and a slope estimation module (or a slope estimator) 120 .

[0057] The parking space detection module 110 may receive an image captured by an image capturing device (eg, a camera sensor), such as a parking space image, and detect a parking space from the parking space image.

[0058] According to an exemplary embodiment of the present invention, the parking space detection module 110 may identify the type of the parking space based on the parking space image, and detect key points corresponding to the parking space to identify the location of the parking space.

[0059] For example, the parking space detection module 110 may detect two starting points of an entrance line from a parking space identified in a parking space image, detect two end points of an end line from the identified parking space, detect the two starting points and the two end points as key points, and use the detected key points to identify the location of the parking space.

[0060] In this case, the key points of the parking space can be defined using 3D coordinates based on EOL (End Of Line) camera calibration.

[0061] The parking space may be a rectangular space with all parking lines drawn. However, in some cases only three parking lines are drawn, in some cases some parking lines are missing, in some cases only two parking lines are drawn, and in some cases no parking lines are drawn.

[0062] According to an exemplary embodiment of the present invention, when at least a portion of a parking line of a parking space is missing or does not exist, the parking space detection module 110 may identify the type of the parking space by identifying a virtual parking space through image analysis, and identify the location of the virtual parking space by detecting key points in the virtual parking space.

[0063] According to an exemplary embodiment of the present invention, when at least a portion of a parking line of a parking space is lost, the parking space detection module 110 may use the remaining parking lines or use parking line information from a nearby parking space to restore at least a portion of the lost parking line, thereby identifying the parking space to identify the type of the parking space and the location of the parking space.

[0064] According to an exemplary embodiment of the present invention, the parking space detection module 110 can identify the type of the virtual parking space by identifying the virtual parking space using surrounding information including information about the parked vehicles. For example, the parking space detection module can be configured to determine whether the parking space is a possible parking space based on information about the parked vehicles and information about the space between the parked vehicles, even when there is a parking space between the parked vehicles but no parking line, and when the corresponding space is a possible parking space, identify the corresponding space as a virtual parking space. In this case, the parking space detection module 110 can set the parking line of the virtual parking space by considering the position of the parked vehicle, the position of the wheel, etc., and identify the type of the virtual parking space and the position of the virtual parking space based on the set virtual parking line.

[0065] According to an exemplary embodiment of the present invention, when there is a parking block in the parking space, the parking space detection module 110 can identify the parking block, and can identify a virtual parking space based on the position of the parking block, the positions of surrounding parked vehicles, and surrounding environment information, for example, the surrounding environment information is obtained through a lidar sensor, a laser sensor, an ultrasonic sensor, etc.

[0066] As described above, the parking space detection module 110 may recognize a parking space through various methods, and recognize the type of the recognized parking space and the location of the parking space based on key points.

[0067] The parking space detection module 110 may use an artificial intelligence network based on deep learning to identify the parking space, or may use image processing technology to identify the parking space, but is not restricted or limited by these technologies.

[0068] The slope estimation module 120 can obtain angle information formed by key points in the type of the parking space identified by the parking space detection module 110, estimate a rotation matrix based on an estimation condition preset according to the angle information and the type of the parking space, and use the estimated rotation matrix and a predetermined reference rotation matrix to estimate the slope of the parking space.

[0069] Here, the reference rotation matrix may refer to a rotation matrix when there is no slope on the road surface, and the slope estimation module may estimate the slope of the parking space based on the difference between the estimated rotation matrix and the reference rotation matrix.

[0070] According to an exemplary embodiment of the present invention, the slope estimation module 120 may obtain first angle information formed by connecting a first stop line and a first end point of two start points and two end points included in the key point and an entrance line, and second angle information formed by connecting a second stop line and a second end point and the entrance line. Here, the angle information may be information related to a specific angle, or may be angle information such as an acute angle, an obtuse angle, a right angle, etc.

[0071] According to an exemplary embodiment of the present invention, the slope estimation module 120 can estimate the rotation matrix so that when the type of the parking space is orthogonal / parallel or the first angle information and the second angle information are obtuse angles, acute angles or acute angles, obtuse angles, the difference between the first angle information and the second angle information converges to a preset minimum value range, and the first angle information and the second angle information converge to a right angle. Here, it is most desirable that the angle information difference converges to 0. However, since errors may occur, the convergence range can be set by taking this into consideration, and the convergence range set as described above can be limited to a minimum value range. It should be noted that it is most desirable that the first angle information and the second angle information converge to a right angle. However, by setting the angle information to a specific range of about 90 degrees, the angle information difference converges to the minimum value range, and the angle information converges to a specific range, so that the rotation matrix can also be estimated.

[0072] According to an exemplary embodiment of the present invention, the slope estimation module 120 can estimate the rotation matrix so that when the type of the parking space is inclined or the first angle information, the second angle information is an acute angle, an acute angle or an obtuse angle, an obtuse angle, the difference between the first angle information and the second angle information converges to a preset minimum value range, and the first angle information and the second angle information are within a preset angle range. Here, it is most desirable that the angle information difference converges to 0. However, since errors may occur, the convergence range can be set by taking this into consideration, and the convergence range set as described above can be limited to a minimum value range. In addition, the angle range of the first angle information and the angle range of the second angle information can be set by an individual or business operator who provides the technology of the present invention. For example, the angle range can be 10°≤|θ-90°|≤60°, and θ is the first angle information or the second angle information.

[0073] In an exemplary embodiment of the present invention, the parking space detection module 110 and the slope estimation module 120 may be implemented in the form of hardware or software such as at least one processor, or may be implemented in a combination of hardware and software.

[0074] The following will refer to Figure 2 , Figure 3A and Figure 3B as well as Figure 4A and Figure 4B , a device for estimating the slope of a parking space of the present invention is described in more detail.

[0075] Figure 2 An example diagram for describing a process of detecting a parking space is shown.

[0076] refer to Figure 2 , the vehicle 200 can identify each parking space by analyzing an image captured by an image capturing device (e.g., a camera sensor) while moving in the entrance direction of the parking space.

[0077] exist Figure 2 In this case, since the parking spaces are separated by parking lines, the parking space detection module 110 can identify the parking lines and the parking spaces through the parking lines by real-time analysis of the image, thereby identifying the type of the parking space, and identifying the location of the parking space by detecting key points of the identified parking space.

[0078] In this case, the parking space detection module 110 may detect intersections of a parking space entrance line and a stop line as two start points and detect intersections of a parking space end line and a stop line as two end points, thereby detecting four key points.

[0079] When the corresponding vehicle moves in the driving direction to identify the parking space, the vehicle can identify the type and location of each parking space through real-time analysis of the image. When performing the automatic parking function in a specific parking space, the vehicle can clearly estimate the slope of the specific parking space to improve the automatic parking control performance.

[0080] The following will refer to Figure 3A and Figure 3B as well as Figure 4A and Figure 4B to describe the process of estimating slope.

[0081] Figure 3A and Figure 3B An example diagram for describing a process of estimating a slope when the type of a parking space is orthogonal / parallel is shown. Figure 3A shows the case where there is no slope on the road, and Figure 3B Indicates the situation where the road surface has a slope.

[0082] from Figure 3A It can be seen that when the parking space type is orthogonal / parallel and there is no slope on the road surface, the angle between the first parking line connecting key points (A) and (B) and the parking space entrance line, that is, the angle between the entrance line connecting key points (A) and (C), and the angle between the second parking line connecting key points (C) and (D) and the parking space entrance line, that is, the first angle information (θ 1 ) and the second angle information (θ 2 ) converges to 90 degrees, and the difference between the angles, i.e. |θ 1 -θ 2 |converges to 0, in this way, the slope of the parking space can be estimated to be 0.

[0083] On the other hand, Figure 3B As shown, when the parking space type is orthogonal / parallel and the road surface has a slope, the difference between the angle between the first parking line connecting key points (A) and (B) and the entrance line connecting key points (A) and (C) and the angle between the second parking line connecting key points (C) and (D) and the parking space entrance line |θ 1 -θ 2 |Increase characteristic, and based on this characteristic, the rotation matrix (yaw angle, pitch angle, roll angle) of the parking space can be estimated, where the difference between the angles (|θ 1 -θ 2 |) converges to 0, and each angle converges to 90 degrees. In this case, the process of estimating the rotation matrix can be a process of repeatedly performing the process of determining whether the above estimation conditions are met while changing the yaw angle, pitch angle, and roll angle little by little, such as Figure 3BAs shown, and through this process, a rotation matrix that satisfies the estimation condition can be estimated. In other words, the rotation matrix of the parking space can be estimated by performing an iterative process so that the key points (A) and (C) are moved to (B') and (D'). Of course, the process of estimating the rotation matrix is ​​not constrained or limited by the iterative process, and various methods for estimating the rotation matrix that satisfies the estimation condition can be applied.

[0084] When a rotation matrix satisfying the estimation condition is estimated through the above process, the slope of the corresponding parking space, ie, the slope of the parking space whose type is orthogonal / parallel, may be estimated based on the difference between the estimated rotation matrix and the reference rotation matrix.

[0085] Figure 4A and Figure 4B An example diagram for describing a process of estimating a slope when the type of a parking space is an incline is shown. Figure 4A shows the case where there is no slope on the road, and Figure 4B The situation where the road surface has a slope is shown.

[0086] from Figure 4A It can be seen that when the parking space type is inclined and there is no slope on the road surface, the angle between the first parking line connecting key points (A) and (B) and the entrance line connecting key points (A) and (C) and the angle between the second parking line connecting key points (C) and (D) and the entrance line, that is, the first angle information (θ 1 ) and the second angle information (θ 2 ) between |θ 1 -θ 2 | converges to 0 degrees or the minimum range, and the first angle information (θ 1 ) and the second angle information (θ 2 ) all satisfy 10°≤|θ-90°|≤60°, so the slope of the parking space can be estimated to be 0.

[0087] On the other hand, Figure 4B As shown, when the parking space type is inclined and the road surface has a slope, the difference between the angle between the first parking line connecting the key points (A) and (B) and the entrance line connecting the key points (A) and (C) and the angle between the second parking line connecting the key points (C) and (D) and the parking space entrance line |θ 1 -θ 2 |Increase characteristic, and based on this characteristic, the rotation matrix (yaw angle, pitch angle, roll angle) of the parking space can be estimated, where the difference between the angles (|θ 1 -θ 2 |) converges to 0, and the first angle information (θ 1 ) and the second angle information (θ 2) all satisfy 10°≤|θ-90°|≤60°. In this case, the process of estimating the rotation matrix may be a process of iteratively executing a process of determining whether the above estimation conditions are satisfied, while changing the yaw angle, pitch angle, and roll angle little by little, such as Figure 4B As shown, and through this process, a rotation matrix that satisfies the estimation condition can be estimated. Of course, the process of estimating the rotation matrix is ​​not constrained or limited by the iterative process, and various methods for estimating the rotation matrix that satisfies the estimation condition can be applied.

[0088] When a rotation matrix satisfying the estimation condition is estimated through the above process, the slope of the corresponding parking space, that is, the slope of the parking space whose type is an inclined space, may be estimated based on the difference between the estimated rotation matrix and the reference rotation matrix.

[0089] As described above, the apparatus for estimating the slope of a parking space according to an exemplary embodiment of the present invention can accurately estimate the slope of the type of each parking space based on key points corresponding to the parking space detected through an image, and improve the automatic parking control performance and quality by estimating the slope of each parking space.

[0090] Figure 5 FIG. 1 is a flowchart showing an operation of a method for estimating a parking space slope according to another exemplary embodiment of the present invention, and FIG. Figure 1 , Figure 2 , Figure 3A , Figure 3B , Figure 4A and Figure 4B The operation process performed by the device.

[0091] refer to Figure 5 , a method for estimating a slope of a parking space according to another exemplary embodiment of the present invention may include identifying a type of a parking space based on an image captured by an image capturing device, and detecting a plurality of key points corresponding to the parking space to identify a position of the parking space (S510 and S520).

[0092] According to an exemplary embodiment of the present invention, in S510, when at least a portion of a parking line of a parking space is lost, the type of the parking space may be identified by restoring at least a portion of the lost parking line and identifying the parking space.

[0093] According to an exemplary embodiment of the present invention, S510 may include identifying a type of the virtual parking space by identifying the virtual parking space using surrounding information including information about the parked vehicle.

[0094] According to an exemplary embodiment of the present invention, S510 may include identifying the type of the virtual parking space by considering the position of the parking block, the position of the parked vehicle, and (if necessary) surrounding environment information when the parking block is detected.

[0095] According to an exemplary embodiment of the present invention, S520 may include detecting two starting points of an entrance line from a parking space identified in the parking space image and detecting two end points of an end line from the identified parking space, detecting the two starting points and the two end points as key points, and using the detected key points to identify the position of the parking space.

[0096] When the type and position of the parking space are identified through the above process, angle information formed by key points in the type of the parking space may be obtained, and a rotation matrix of the parking space may be estimated based on an estimation condition preset according to the angle information and the type of the parking space (S530 and S540).

[0097] According to an exemplary embodiment of the present invention, S530 may include obtaining first angle information formed by a first stop line connecting the first start point and the first end point and the entrance line, and second angle information formed by a second stop line connecting the second start point and the second end point and the entrance line.

[0098] According to an exemplary embodiment of the present invention, S540 may include estimating a rotation matrix so that when the type of the parking space is orthogonal / parallel or the first angle information and the second angle information are obtuse angles and acute angles or acute angles and obtuse angles, the difference between the first angle information and the second angle information converges to a preset minimum value range, and the first angle information and the second angle information converge to a right angle.

[0099] According to an exemplary embodiment of the present invention, S540 may include estimating a rotation matrix so that when the type of the parking space is inclined or the first angle information and the second angle information are acute angles and acute angles or obtuse angles and obtuse angles, the difference between the first angle information and the second angle information converges to a preset minimum value range, and the first angle information and the second angle information are within a preset angle range, for example, 10°≤|θ-90°|≤60°.

[0100] When the rotation matrix of the parking space is estimated through S540 , the slope of the parking space may be estimated using the estimated rotation matrix and a predetermined reference rotation matrix ( S550 ).

[0101] Here, the reference rotation matrix may be a rotation matrix with respect to a case where there is no slope of the road surface, and S550 may include estimating the slope of the parking space based on a difference between the estimated rotation matrix and the reference rotation matrix.

[0102] Even when the description of the method according to another exemplary embodiment of the present invention is omitted, the method according to another exemplary embodiment of the present invention may include Figure 1 , Figure 2 , Figure 3A , Figure 3B , Figure 4A and Figure 4B This is obvious to those skilled in the art.

[0103] Figure 6 is a block diagram of a computing system for executing a method for estimating a slope of a parking space according to another exemplary embodiment of the present invention.

[0104] refer to Figure 6 According to another exemplary embodiment of the present invention, the method for estimating the slope of a parking space can be implemented by a computing system. The computing system 1000 may include at least one processor 1100, a memory 1300, a user interface input device 1400, a user interface output device 1500, a storage device 1600, and a network interface 1700, which are connected to each other via a bus 1200.

[0105] The processor 1100 may be a central processing unit (CPU) or a semiconductor device for processing instructions stored in the memory 1300 and / or the storage device 1600. The memory 1300 and the storage device 1600 may include various types of volatile or non-volatile storage media. For example, the memory 1300 may include a read-only memory (ROM) 1310 and a random access memory (RAM) 1320.

[0106] Therefore, the operation of the method or algorithm described in conjunction with the exemplary embodiments contained herein may be directly embodied in a hardware or software module executed by the processor 1100, or in a combination thereof. The software module may reside on a storage medium (i.e., memory 1300 and / or storage device 1600), such as RAM, flash memory, ROM, EPROM, EEPROM, register, hard disk, removable disk, or CD-ROM. The exemplary storage medium may be coupled to the processor 1100, and the processor 1100 may read information from the storage medium and may record information in the storage medium. Alternatively, the storage medium may be integrated with the processor 1100. The processor 1100 and the storage medium may reside in an application specific integrated circuit (ASIC). The ASIC may reside in a user terminal. In another case, the processor 1100 and the storage medium may reside in a user terminal as separate components.

[0107] The above description is merely an explanation of the technical idea of ​​the present invention, and those skilled in the art to which the present invention belongs may make various modifications and changes without departing from the basic features of the present invention. Therefore, the exemplary embodiments included in the present invention are not intended to limit the technical idea of ​​the present invention, but are used to describe the present invention, and the scope of the technical idea of ​​the present invention is not limited by the embodiments. The protection scope of the present invention should be interpreted by the attached claims, and all technical ideas within the scope equivalent thereto should be interpreted as included within the scope of the present invention.

[0108] According to an exemplary embodiment of the present invention, a method and apparatus for estimating a slope of a parking space based on key points corresponding to the parking space detected through an image may be provided.

[0109] According to an exemplary embodiment of the present invention, automatic parking control performance and quality may be improved by estimating the slope of each parking space.

[0110] Effects obtainable in one exemplary embodiment of the present invention are not limited to the above-mentioned effects, and any other effects not mentioned herein will be clearly understood from the following description by those skilled in the art to which the present invention pertains.

[0111] In various exemplary embodiments of the present invention, each of the above operations may be performed by a control device, and the control device may be composed of a plurality of control devices, or may be composed of an integrated single control device.

[0112] In various exemplary embodiments of the present invention, the memory and the processor may be provided as one chip, or may be provided as separate chips.

[0113] In various exemplary embodiments of the present invention, the scope of the present invention includes software or machine executable commands (e.g., operating systems, applications, firmware, programs, etc.) that are capable of operating according to the methods of various embodiments to be executed on a device or computer, including a non-transitory computer-readable medium on which such software or commands are stored and executable on the device or computer.

[0114] In various exemplary embodiments of the present invention, the control device may be implemented in the form of hardware or software, or may be implemented in a combination of hardware and software.

[0115] In addition, terms such as “unit” and “module” included in the specification refer to a unit for processing at least one function or operation, which can be implemented by hardware, software or a combination thereof.

[0116] In an exemplary embodiment of the present invention, a vehicle may be referred to as being based on a concept that includes various vehicles. In some cases, a vehicle may be interpreted as being based on a concept that includes not only various land vehicles that travel on roads, such as cars, motorcycles, trucks, and buses, but also various vehicles such as airplanes, drones, ships, and the like.

[0117] To facilitate interpretation and precise definition of the appended claims, the terms "upper," "lower," "inner," "outer," "up," "lower," "upward," "downward," "front," "rear," "rear," "inside," "outer," "inwardly," "outwardly," "inner," "outer," "inner," "inner," "external," "forward," and "rearward" are used to describe features of the exemplary embodiments with reference to the positions of such features as shown in the accompanying drawings. It will be further understood that the term "connect" or its derivatives refer to both direct and indirect connections.

[0118] In the present specification, unless otherwise stated, a singular expression includes a plural expression unless the context clearly indicates otherwise.

[0119] In exemplary embodiments of the present invention, it should be understood that terms such as “including” or “having” are intended to specify the presence of features, numbers, steps, operations, elements, parts, or a combination thereof described in the specification, and do not exclude the possibility of adding or existing one or more other features, numbers, elements, parts, or a combination thereof.

[0120] The foregoing descriptions of specific exemplary embodiments of the present invention have been given above for the purpose of illustration and description. They are not intended to be exhaustive or to limit the present invention to the exact form disclosed, and it is apparent that many modifications and variations can be made in light of the above teachings. Exemplary embodiments are selected and described to illustrate certain principles of the present invention and their practical applications, so that other persons skilled in the art can utilize the various exemplary embodiments of the present invention and their various substitutions and modifications. The scope of the present invention is intended to be defined by the appended claims and their equivalents.

Claims

1. A device for estimating a parking space slope, the device comprising: a parking space detection module configured to identify a type of a parking space based on an image captured by an image capture device, and to identify a position of the parking space by detecting a plurality of key points corresponding to the parking space; as well as A slope estimation module is configured to obtain angle information formed by key points in the type of the parking space, estimate a rotation matrix based on an estimation condition preset according to the angle information and the type of the parking space, and estimate the slope of the parking space using the estimated rotation matrix and a predetermined reference rotation matrix.

2. The device according to claim 1, wherein: The parking space detection module is configured to detect two start points from an entrance line of the parking space and two end points from an end line of the parking space as the key points, and recognize the position of the parking space using the key points including the two start points and the two end points.

3. The device according to claim 2, wherein: The slope estimation module is configured to obtain first angle information formed by a first stop line connecting a first starting point among the two starting points and a first end point among the two end points and the entrance line, and second angle information formed by a second stop line connecting a second starting point among the two starting points and a second end point among the two end points and the entrance line.

4. The device according to claim 3, wherein: The slope estimation module is configured to estimate the rotation matrix so that when the type of the parking space is orthogonal / parallel or the first angle information and the second angle information are an obtuse angle and an acute angle or an acute angle and an obtuse angle, the difference between the first angle information and the second angle information converges to a preset minimum value range, and the first angle information and the second angle information converge to a right angle.

5. The device according to claim 3, wherein: The slope estimation module is configured to estimate the rotation matrix so that when the type of the parking space is inclined or the first angle information and the second angle information are acute angle and acute angle or obtuse angle and obtuse angle, the difference between the first angle information and the second angle information converges to a preset minimum value range, and the first angle information and the second angle information are within a preset angle range.

6. The device according to claim 5, wherein: The slope estimation module is configured to estimate the rotation matrix so that an absolute value that is 90 degrees different from the first angle information and an absolute value that is 90 degrees different from the second angle information are within a range between 10 degrees and 60 degrees.

7. The device according to claim 1, wherein: The parking space detection module is configured to identify the parking space by restoring at least a portion of the parking line that has been lost, if at least a portion of the parking line of the parking space is lost, thereby identifying a type of the parking space.

8. The device according to claim 1, wherein: The parking space detection module is configured to identify a type of the virtual parking space by identifying the virtual parking space using surrounding information including information about a parked vehicle.

9. The device according to claim 8, wherein: The parking space detection module is configured to identify the virtual parking space by considering a position of the parking block and a position of the parked vehicle if a parking block is detected.

10. The device according to claim 1, in, The reference rotation matrix is ​​a rotation matrix for a road surface without a slope, and The slope estimation module is configured to estimate the slope of the parking space based on a difference between the estimated rotation matrix and the reference rotation matrix.

11. A method for estimating a parking space slope, the method comprising the following steps: identifying, by a processor, a type of a parking space based on an image captured by an image capturing device, and identifying a position of the parking space by detecting a plurality of key points corresponding to the parking space; obtaining, by the processor, angle information formed by key points in the type of the parking space; estimating, by the processor, a rotation matrix based on an estimation condition preset according to the angle information and the type of the parking space; as well as The slope of the parking space is estimated by the processor using the estimated rotation matrix and a predetermined reference rotation matrix.

12. The method according to claim 11, wherein: The step of recognizing the position of the parking space includes detecting two start points from an entrance line of the parking space and two end points from an end line of the parking space as the key points, and recognizing the position of the parking space using the key points including the two start points and the two end points.

13. The method according to claim 12, wherein: The step of obtaining the angle information includes: obtaining first angle information formed by a first stop line connecting a first starting point among the two starting points and a first end point among the two end points and the entrance line, and obtaining second angle information formed by a second stop line connecting a second starting point among the two starting points and a second end point among the two end points and the entrance line.

14. The method according to claim 13, wherein: The step of estimating the rotation matrix includes: estimating the rotation matrix so that when the type of the parking space is orthogonal / parallel or the first angle information and the second angle information are an obtuse angle and an acute angle or an acute angle and an obtuse angle, the difference between the first angle information and the second angle information converges to a preset minimum value range, and the first angle information and the second angle information converge to a right angle.

15. The method according to claim 13, wherein: The step of estimating the rotation matrix includes: estimating the rotation matrix so that when the type of the parking space is inclined or the first angle information and the second angle information are acute angle and acute angle or obtuse angle and obtuse angle, the difference between the first angle information and the second angle information converges to a preset minimum value range, and the first angle information and the second angle information are within a preset angle range.

16. The method according to claim 15, wherein: The step of estimating the rotation matrix includes: estimating the rotation matrix so that an absolute value that differs by 90 degrees from the first angle information and an absolute value that differs by 90 degrees from the second angle information are within a range between 10 degrees and 60 degrees.

17. The method according to claim 11, wherein: The step of identifying the position of the parking space includes: in a case where at least a portion of a parking line of the parking space is lost, identifying the parking space by restoring at least a portion of the parking line that has been lost, thereby identifying the type of the parking space.

18. The method according to claim 11, wherein: The identifying of the location of the parking space includes identifying a type of the virtual parking space by identifying the virtual parking space using surrounding information including information about the parked vehicle.

19. The method according to claim 18, wherein: The step of identifying the position of the parking space includes identifying the virtual parking space by considering the position of the parking block and the position of the parked vehicle in a case where a parking block is detected.

20. The method according to claim 11, in, The reference rotation matrix is ​​a rotation matrix for a road surface without a slope, and The step of estimating the slope of the parking space includes estimating the slope of the parking space based on a difference between the estimated rotation matrix and the reference rotation matrix.

Images