Vehicle control method and vehicle control apparatus

Abstract

The vehicle control method of the present invention includes: measuring, by a measuring device, coordinates of a first entry point, the first entry point being an end point of a first entry line in a first parking space; generating, by a generating device, a first entry line measurement length based on the measured coordinates of the first entry point; tracking, by a generating device, a length of a first entry line based on the first entry line measured length to generate a first entry line tracked length; and calibrating, by the calibration device, coordinates of the first entry point based on a first error, the first error being a difference between the first entry line tracking length and the first entry line measurement length.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims the benefit of and priority to Korean Patent Application No. 10-2024-0026685, filed on February 23, 2024, in the Korean Intellectual Property Office, the entire contents of which are incorporated herein by reference. Technical Field

[0003] The technical concept of the present disclosure relates to a vehicle control method and device. Background Art

[0004] In recent advances in autonomous driving technology, various artificial intelligence models utilizing deep neural network-based computer vision techniques have been studied, such as object detection, semantic segmentation, depth map estimation, and lane detection. Specifically, research is underway to use artificial intelligence models to determine the location of parking spaces and perform automated parking. For example, automated parking can be performed by measuring the coordinates of the parking space's entry point using a network that identifies the parking space. For automated parking, it may be necessary to obtain the precise coordinates of the parking space's entry point. Summary of the Invention

[0005] The present disclosure is made in order to solve the above-mentioned problems occurring in the prior art and to maintain the advantages achieved by the prior art.

[0006] One aspect of the present disclosure provides a method and apparatus for obtaining precise coordinates of an entry point of a parking space.

[0007] One aspect of the present disclosure provides a method and apparatus for calibrating an entry point coordinate of a parking space when a slope exists on a road surface where a vehicle is located.

[0008] One aspect of the present disclosure provides a method and apparatus for reducing errors in a route for automatic parking control.

[0009] One aspect of the present disclosure provides a method and apparatus for shortening a time required to determine a route for automatic parking control.

[0010] One aspect of the present disclosure provides a method and apparatus for improving performance of automatic parking.

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

[0012] According to one aspect of the present disclosure, a vehicle control method includes: measuring the coordinates of a first entry point by a measuring device, the first entry point being an endpoint of a first entry line in a first parking space; and generating a first entry line measured length based on the measured coordinates of the first entry point by a generating device. The vehicle control method also includes: tracing the length of the first entry line based on the first entry line measured length by the generating device to generate the first entry line traced length; and calibrating the coordinates of the first entry point by a calibration device based on a first error, the first error being a difference between the first entry line traced length and the first entry line measured length.

[0013] According to an embodiment, the generation of the first entry line tracking length may also include: if i) the difference between the center point of the first entry line and the longitudinal position of the side camera of the vehicle is less than a first threshold, and ii) the difference between the measured length of the first entry line and the reference length of the entry line is less than a second threshold, then the generating device generates the first entry line tracking length by updating the second entry line tracking length generated in the previous frame.

[0014] According to an embodiment, the generation of the first entry line tracking length may also include: the generating device updates the second entry line tracking length based on i) the second entry line tracking length generated in the previous frame and ii) the first entry line measurement length generated in the current frame to generate the first entry line tracking length.

[0015] According to an embodiment, the generating of the first entry line tracing length may include: generating the first entry line tracing length by predicting the first entry line tracing length based on the second entry line tracing length and the first entry line measurement length using an arbitrary filter by a generating device.

[0016] According to an embodiment, if the tracking of the length of the first entry line is performed for the first time in a previous frame, the second entry line tracking length may be the entry line reference length.

[0017] According to an embodiment, the calibration of the coordinates of the first entry point may also include: if the first error is greater than a third threshold, the calibration device calibrates the coordinates of the first entry point based on the first error and the angle between the vehicle and the parking line adjacent to the first entrance line in the first parking space.

[0018] According to an embodiment, the vehicle control method may further include: measuring the coordinates of a second entry point of a second parking space by a measuring device, and generating a second entry line measurement length based on the coordinates of the second entry point by a generating device. Alternatively, the vehicle control method may further include: generating a second error by a generating device, the second error being the difference between the first entry line traced length and the second entry line measurement length; measuring the coordinates of a third entry point of a third parking space by a measuring device; and generating a third entry line measurement length based on the coordinates of the third entry point by the generating device. Alternatively, the vehicle control method may further include: generating a third error by a generating device, the third error being the difference between the first entry line traced length and the third entry line measurement length; and first calibrating the coordinates of the entry point of the second or third parking space corresponding to the smaller of the second and third errors by a calibrating device.

[0019] According to an embodiment, measuring the coordinates of the first entrance point of the first parking space may include: measuring the coordinates of the first entrance point of the first parking space by a measuring device based on a bird's-eye view (BEV) image using a neural network.

[0020] According to one aspect of the present disclosure, a vehicle control device includes: a memory storing computer-executable instructions; and at least one processor accessing the memory and executing the instructions. The at least one processor can measure the coordinates of a first entry point using a measuring device, where the first entry point is an endpoint of a first entry line in a first parking space. The at least one processor can generate a first entry line measured length based on the measured coordinates of the first entry point using a generating device, and generate a first entry line traced length by tracing the length of the first entry line based on the first entry line measured length. The at least one processor can calibrate the coordinates of the first entry point using a calibration device based on a first error, where the first error is the difference between the first entry line traced length and the first entry line measured length.

[0021] According to an embodiment, it may also be that if i) the difference between the center point of the first entry line and the longitudinal position of the side camera of the vehicle is less than a first threshold, and ii) the difference between the measured length of the first entry line and the reference length of the entry line is less than a second threshold, at least one processor generates the first entry line tracking length by generating a device by updating the second entry line tracking length generated in the previous frame.

[0022] According to an embodiment, at least one processor may generate the first entry line tracing length by updating the second entry line tracing length based on the second entry line tracing length generated in the previous frame and the first entry line measurement length generated in the current frame through a generating device.

[0023] According to an embodiment, at least one processor may generate the first entry line tracing length by using a generating device to predict the first entry line tracing length based on the second entry line tracing length and the first entry line measurement length using an arbitrary filter.

[0024] According to an embodiment, if the tracking of the length of the first entry line is performed for the first time in a previous frame, the second entry line tracking length may be the entry line reference length.

[0025] According to an embodiment, if the first error is greater than a third threshold, at least one processor may calibrate the coordinates of the first entry point based on the first error and the angle between the vehicle and the parking line adjacent to the first entrance line in the first parking space through a calibration device.

[0026] According to an embodiment, at least one processor may measure the coordinates of a second entrance point of a second parking space and the coordinates of a third entrance point of a third parking space using a measuring device. The at least one processor may generate a second entrance line measurement length based on the coordinates of the second entrance point using a generating device, generate a second error as the difference between the first entrance line traced length and the second entrance line measurement length, and generate a third entrance line measurement length based on the coordinates of the third entrance point. The at least one processor may generate a third error as the difference between the first entrance line traced length and the third entrance line measurement length. The at least one processor may first calibrate the coordinates of the entrance point of the second or third parking space corresponding to the smaller of the second and third errors using a calibrating device.

[0027] According to an embodiment, the at least one processor may measure the coordinates of the first entrance point of the first parking space based on a bird's-eye view (BEV) image by using a neural network through the measuring device.

[0028] The features briefly summarized above for the present disclosure are merely illustrative aspects of the following detailed description of the present disclosure, but do not limit the scope of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The above and other objects, features and advantages of the present disclosure will become more apparent from the following detailed description taken in conjunction with the accompanying drawings:

[0030] Figure 1 is a diagram for describing a parking space position calibration method according to an embodiment of the present disclosure;

[0031] Figure 2 is a flowchart illustrating a parking space position calibration method according to an embodiment of the present disclosure;

[0032] Figure 3 is a diagram for describing a parking space position calibration method according to an embodiment of the present disclosure;

[0033] Figure 4 is a flowchart illustrating a parking space position calibration method according to an embodiment of the present disclosure;

[0034] Figure 5 is a flowchart illustrating a parking space position calibration method according to an embodiment of the present disclosure;

[0035] Figure 6A is a diagram for describing a parking space position calibration method according to an embodiment of the present disclosure;

[0036] Figure 6B is a diagram for describing a parking space position calibration method according to an embodiment of the present disclosure;

[0037] Figure 6C is a diagram for describing a parking space position calibration method according to an embodiment of the present disclosure;

[0038] Figure 6D is a diagram for describing a parking space position calibration method according to an embodiment of the present disclosure;

[0039] Figure 6E is a diagram for describing a parking space position calibration method according to an embodiment of the present disclosure;

[0040] Figure 6F is a diagram for describing a parking space position calibration method according to an embodiment of the present disclosure;

[0041] Figure 7 is a block diagram illustrating a parking space position calibration apparatus according to an embodiment of the present disclosure; and

[0042] Figure 8 is a block diagram of a computing system for executing a parking space position calibration method according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0043] Hereinafter, the embodiments of the present disclosure will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily implement the present disclosure. However, the present disclosure can be implemented in many different forms and should not be construed as being limited to the embodiments described herein.

[0044] In addition, when describing the embodiments of the present disclosure, detailed descriptions of well-known features or functions are omitted to avoid unnecessarily obscuring the main points of the present disclosure. In the accompanying drawings, parts that are not related to the description are omitted, and the same reference numerals represent the same elements throughout the specification.

[0045] In the present disclosure, it should be understood that when an element is referred to as being "connected," "coupled," or "combined" with another element, the element may be directly connected, coupled, or combined with the other element, or intervening elements may exist therebetween. It should also be understood that the terms "include," "comprising," or "having" used in the present disclosure specify the presence of the elements described, but do not preclude the presence or addition of one or more other elements.

[0046] In this disclosure, terms such as first and second are used only to distinguish one element from other elements and do not limit the order or importance of the elements unless otherwise specified. Therefore, within the scope of this disclosure, a first component in one embodiment may be referred to as a second component in another embodiment, and similarly, a second component in one embodiment may be referred to as a first component in another embodiment.

[0047] In this disclosure, different elements are used only to clearly describe their features and do not mean that the elements are necessarily separate. In other words, multiple elements can be integrated to form a single hardware or software unit, or a single element can be distributed to form multiple hardware or software units. Therefore, even if not otherwise specified, such integrated or distributed embodiments are also included in the scope of this disclosure.

[0048] In the present disclosure, the elements described in the various embodiments are not necessarily required elements, and some elements may be optional. Therefore, embodiments comprising a subset of the elements described in an embodiment are also included in the scope of the present disclosure. In addition, embodiments comprising other elements in addition to the elements described in the various embodiments are also included in the scope of the present disclosure.

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

[0050] In the present disclosure, each of the phrases "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 with the relevant phrase, or any possible combination thereof.

[0051] When a component, device, element, etc. of the present disclosure is described as having a purpose or performing an operation, function, etc., the component, device or element should be considered herein as "configured to" satisfy the purpose or perform the operation or function.

[0052] The terms "unit," "device," or "module" used in this specification refer to a unit that processes at least one function or operation and can be implemented by hardware, software, or a combination thereof. The operation of the methods or functions described in connection with the forms disclosed herein may be directly embodied in hardware or a software module executed by a processor, or in a combination of hardware or software modules.

[0053] Below, refer to Figure 1-8 , describes the embodiments of the present disclosure in detail.

[0054] Figure 1 is a diagram for describing a method of correcting a parking space position according to an embodiment of the present disclosure.

[0055] Reference Figure 1 , the vehicle 100 may search for the location of the parking space 110. For example, the vehicle 100 may search for the location of the side parking space 110 using a side camera mounted on the vehicle 100. The parking space 110 may refer to a space in which the vehicle is parked.

[0056] Each of the parking spaces may include: an entrance line 120, an end line 130, a stop line 140, an entry point 151, a midpoint 152, and an end point 153. The entrance line 120 may refer to the line through which a vehicle enters the parking space. The two end points of the entrance line 120 may be referred to as entry points 151. The end line 130 may represent the other side of the entrance line 120, but is not limited thereto. The two end points of the end line 130 may be referred to as end points 153. The two sides of the parking space 110 adjacent to the entrance line 120 may be referred to as stop lines 140. Any point on the stop line 140 may be referred to as a midpoint 152. Although not shown in the figure, the angle related to the angle between the stop line 140 and the vehicle may be referred to as an entrance line angle. If the parking space 110 is located on the right side of the vehicle 100, the entrance line angle may have a negative value. Additionally, if the parking space 110 is located on the left side of the vehicle 100, the entrance line angle may have a positive value. For example, Figure 1 As shown, if there is a parking space 110 on the right side of the vehicle 100 and the angle between the parking line 140 and the vehicle 100 is 90°, the entry line angle may be -90°.

[0057] The location of the entry point 151 of the parking space 110 can be calculated based on the camera calibration information. The camera calibration can be calculated assuming that the road surface on which the vehicle 100 is located has no slope. Therefore, if the road surface on which the vehicle is located has a slope, errors may occur when measuring the location of the entry point of the parking space. If errors occur in the location of the entry point, errors may also occur in creating a route for automated parking, and determining the route for automated parking may take a considerable amount of time, which may degrade the performance of automated parking. Even if the road surface on which the vehicle 100 is located has a slope, the parking space position calibration method according to an embodiment of the present disclosure can obtain an accurate location of the entry point. The parking space position calibration method may correspond to a vehicle control method.

[0058] Figure 2 is a flowchart illustrating a parking space position calibration method according to an embodiment of the present disclosure.

[0059] Figure 3 is a diagram for describing a parking space position calibration method according to an embodiment of the present disclosure. Figure 3 right Figure 2 Provide a description.

[0060] Reference Figure 2 and Figure 3 According to an embodiment of the present disclosure, a parking space position calibration method may include, in operation S210, measuring the coordinates of first entry points 312 and 313 of first parking space 310 using a measurement device. For example, the parking space position calibration method may include, but is not limited to, measuring the coordinates of first entry points 312 and 313 of first parking space 310 using a neural network based on a Bird's Eye View (BEV) image. The neural network may be, but is not limited to, a PSRNet.

[0061] The parking space position calibration method may include, in operation S220, generating, by a generator, a first entrance line measurement length based on the measured coordinates of the first entrance points 312 and 313. For example, the parking space position calibration method may include generating the first entrance line measurement length by calculating the distance between the two endpoints of the first entrance line 311, namely, the first entrance points 312 and 313. Specifically, the parking space position calibration method may include generating the first entrance line measurement length by calculating the Euclidean distance between the first entrance points 312 and 313.

[0062] In operation S230 , the parking space position calibration method may include: a generator tracking the length of the first entrance line 311 based on the first entrance line measured length, thereby generating the first entrance line tracking length. More specific details about tracking the length of the first entrance line 311 are described below.

[0063] The parking space position calibration method may include, in operation S240, calibrating the coordinates of first entry points 312 and 313 using a calibration device based on a first error, the difference between the first entry line traced length and the first entry line measured length. In other words, the equation "first error = |first entry line traced length - first entry line measured length|" may be established. The parking space position calibration method may include calibrating the coordinates of first entry points 312 and 313 based on the first error. For example, the coordinates of first entry points 312 and 313 may be calibrated based on the first error and an entry line angle θ associated with the angle between vehicle 300 and stop line 315 adjacent to first entry line 311 in first parking space 310. The entry line angle θ may have negative or positive values ​​depending on whether the parking space is on the right or left side of the vehicle. For example, angle θ' between vehicle 300 and stop line 315 may be 90°. Because first parking space 310 is on the right side of vehicle 300, the negative entry line angle θ may be -90°, i.e., -θ'. More specific details regarding calibrating the coordinates of first entry points 312 and 313 are described below.

[0064] Figure 4 is a flowchart illustrating a parking space position calibration method according to an embodiment of the present disclosure. Figure 4 The flowchart can be described in more detail Figure 2 Flowchart of operation S230. Figure 3 right Figure 4 Provide a description.

[0065] Reference Figure 3 and Figure 4 The parking space position calibration method according to an embodiment of the present disclosure may include: in operation S231, determining whether the difference between the center point 314 of the first entrance line 311 and the longitudinal position of the side camera 301 of the vehicle is less than a first threshold. Here, the longitudinal direction may be the direction of travel of the vehicle 300. For example, in Figure 3 , the longitudinal direction may be the x-axis direction.

[0066] The parking space position calibration method may include determining, in operation S232, whether a difference between a measured length of the first entry line and a reference entry line length is less than a second threshold. The reference entry line length may refer to a standard value for an entry line of each type of predetermined parking space (e.g., a rectangular parking space, a parallelogram parking space, etc.). Operations S231 and S232 may be performed in any order.

[0067] The parking space position calibration method may include updating the second entry line tracking length generated in the previous frame (operation S233) if i) the difference between the center point 314 of the first entry line 311 and the longitudinal position of the vehicle's side camera 301 is less than a first threshold, and ii) the difference between the first entry line measured length and the entry line reference length is less than a second threshold. Specifically, if the difference between the center point 314 of the first entry line 311 and the longitudinal position of the vehicle's side camera 301 is less than the first threshold, this may mean that the distance between the side camera 301 and the first parking space 310 has become closer in the longitudinal direction by a certain distance. In other words, the parking space position calibration method may include updating the second entry line tracking length if the vehicle 300 is adjacent to the first parking space 310 by less than a predetermined distance.

[0068] Additionally, if the difference between the first entry line measured length and the entry line reference length is less than a second threshold, this may indicate that first parking space 310 is not an irregular parking space. In other words, if the difference between the entry line reference length (which is a predetermined standardized value) and the first entry line measured length is less than the second threshold, first parking space 310 may be a regular parking space. The parking space position calibration method may include updating the second entry line tracking length if first parking space 310 is not an irregular parking space.

[0069] A parking space position calibration method may include updating the second entry line tracking length based on the second entry line tracking length generated in a previous frame and the first entry line measurement length generated in a current frame, thereby generating a first entry line tracking length. Specifically, the parking space position calibration method may include using an arbitrary filter to generate the first entry line tracking length based on the second entry line tracking length and the first entry line measurement length. For example, the parking space position calibration method may include, but the present disclosure is not limited to, inputting the second entry line tracking length and the first entry line measurement length into a Kalman filter to predict the first entry line tracking length, thereby generating the first entry line tracking length.

[0070] The initial value of the entry line tracking length may be the above-mentioned entry line reference length. In other words, if the tracking of the length of the first entry line 311 is performed for the first time in the previous frame, the second entry line tracking length may be the entry line reference length.

[0071] Figure 5 is a flowchart illustrating a parking space position calibration method according to an embodiment of the present disclosure.

[0072] The parking space position calibration method according to an embodiment of the present disclosure may include calibrating the parking space positions in order of smaller longitudinal errors of entry points among the plurality of parking spaces.

[0073] Specifically, see Figure 5The parking space position calibration method according to an embodiment of the present disclosure may include measuring coordinates of a second entrance point of a second parking space in operation S510 .

[0074] The parking space position calibration method may include generating a second entrance line measurement length based on the coordinates of the second entrance point in operation S520. For example, the parking space position calibration method may include generating the second entrance line measurement length by calculating the Euclidean distance of the coordinates of the second entrance point.

[0075] The parking space position calibration method may include generating a second error, which is a difference between the first entrance line traced length and the second entrance line measured length, in operation S530 .

[0076] The parking space position calibration method may include measuring coordinates of a third entry point of a third parking space in operation S540 .

[0077] The parking space position calibration method may include generating a third entry line measurement length based on the coordinates of the third entry point in operation S550. For example, the parking space position calibration method may include generating the third entry line measurement length by calculating the Euclidean distance of the coordinates of the third entry point.

[0078] The parking space position calibration method may include generating a third error, which is a difference between the first entrance line traced length and the third entrance line measured length, in operation S560 .

[0079] The parking space position calibration method may include, in operation S570, first calibrating the coordinates of the entrance point of the second and third parking spaces corresponding to the smaller of the second and third errors. For example, if the second error is smaller than the third error, the coordinates of the entrance point of the second parking space may be calibrated before the coordinates of the entrance point of the third parking space.

[0080] Figures 6A to 6F is a diagram for describing a parking space position calibration method according to an embodiment of the present disclosure.

[0081] Reference Figure 6A The parking space position calibration method may include identifying parking spaces (parking space 1 to parking space 5). Specifically, the parking space position calibration method may include measuring an entry point, an entry line, a midpoint of the entry line, and an angle of the entry line of the parking space. For example, the parking space position calibration method may include using a neural network to measure the entry point, the entry line, the midpoint of the entry line, and the angle of the entry line of the parking space.

[0082] Reference Figure 6B, the parking space position calibration method may include: setting a reference parking space. Specifically, the parking space position calibration method may include: selecting a parking space with a minimum longitudinal distance from a side camera included in the vehicle 600 as a reference parking space. For example, Figure 6B , parking space 3 (parking space 3) can be selected as the reference parking space.

[0083] Reference Figure 6C , the parking space position calibration method may include: performing calibration on the longitudinal position of the entry point of parking space 4 (parking space 4). For example, the parking space position calibration method may include: calibrating the longitudinal position of the coordinates of the entry point in the order of the smallest longitudinal position error of the coordinates of the entry point among the parking spaces (parking space 2, parking space 4) adjacent to the reference parking space, i.e., parking space 3 (parking space 3). The longitudinal position error of the entry point may be the difference between the measured length of the entry line and the traced length of the entry line. In addition, the parking space position calibration method may include: calibrating the longitudinal position of the coordinates of the entry point if the longitudinal position error of the coordinates of the entry point is greater than a third threshold. Assuming that among the parking spaces (parking space 2, parking space 4), the parking space with the smallest longitudinal position error of the coordinates of the entry point is parking space 4 (parking space 4), the longitudinal position of the coordinates of the entry point of parking space 4 (parking space 4) may be calibrated. Specifically, the coordinate located below the x-axis (vertical axis) coordinate of the entry point of parking space 4, which is located longitudinally below parking space 3, which is the reference parking space, may be calculated as follows:

[0084] The x-axis coordinate of the calibrated lower entry point = (the x-axis coordinate of the lower entry point before calibration) - (error) * cos(θ”)

[0085] Here, the error can be the difference between the entry line traced length and the entry line measured length. If the entry line angle (θ) is greater than 0, θ" can be [entry line angle (θ) + 90°]; if the entry line angle is less than 0, θ" can be [entry line angle (θ) - 90°].

[0086] Reference Figure 6D, the parking space position calibration method may include: performing calibration on the longitudinal position of the entry point of parking space 5 (parking space 5). For example, the parking space position calibration method may include: calibrating the longitudinal position of the coordinates of the entry point in the order of the smaller longitudinal position error of the coordinates of the entry point among the parking spaces. In addition, the parking space position calibration method may include: calibrating the longitudinal position of the coordinates of the entry point if the longitudinal position error of the coordinates of the entry point is greater than a third threshold. Assuming that the parking space with the smaller longitudinal position error of the coordinates of the entry point among the parking spaces is parking space 5 (parking space 5), the longitudinal position of the coordinates of the entry point of parking space 5 (parking space 5) may be calibrated. Specifically, the coordinate located below among the x-axis coordinates of the entry point of parking space 5 that is longitudinally located below parking space 3 as the reference parking space may be calculated as follows:

[0087] The x-axis coordinate of the calibrated lower entry point = (the x-axis coordinate of the lower entry point before calibration) - (error) * cos(θ”)

[0088] Here, the error can be the difference between the entry line traced length and the entry line measured length. In addition, if the entry line angle (θ) is greater than 0, θ" can be [entry line angle (θ) + 90°], and if the entry line angle is less than 0, θ" can be [entry line angle (θ) - 90°].

[0089] Reference Figure 6E , the parking space position calibration method may include: performing calibration on the longitudinal position of the entry point of parking space 2 (parking space 2). For example, the parking space position calibration method may include: calibrating the longitudinal position of the coordinates of the entry point in the order of the smaller longitudinal position error of the coordinates of the entry point among the parking spaces. In addition, the parking space position calibration method may include: calibrating the longitudinal position of the coordinates of the entry point if the longitudinal position error of the coordinates of the entry point is greater than a third threshold. Assuming that the parking space with the smaller longitudinal position error of the coordinates of the entry point among the parking spaces is parking space 2 (parking space 2), the longitudinal position of the coordinates of the entry point of parking space 2 (parking space 2) may be calibrated. Specifically, the coordinate located above the x-axis coordinate of the entry point of parking space 2 that is longitudinally above parking space 3 as the reference parking space may be calculated as follows:

[0090] The x-axis coordinate of the calibrated upper entry point = (the x-axis coordinate of the upper entry point before calibration) - (error) * cos(θ”)

[0091] Here, the error can be the difference between the entry line traced length and the entry line measured length. In addition, if the entry line angle (θ) is greater than 0, θ" can be [entry line angle (θ) + 90°], and if the entry line angle is less than 0, θ" can be [entry line angle (θ) - 90°].

[0092] Reference Figure 6F The parking space position calibration method may include calibrating the longitudinal position of the entry point of the remaining parking space, namely parking space 1 (parking space 1). The parking space position calibration method may include calibrating the longitudinal position of the entry point coordinates if the longitudinal position error of the entry point coordinates is greater than a third threshold. Specifically, the x-axis coordinate of the entry point of parking space 1 that is longitudinally above parking space 3, which serves as the reference parking space, may be calculated as follows:

[0093] The x-axis coordinate of the calibrated upper entry point = (the x-axis coordinate of the upper entry point before calibration) + (error) * cos(θ”)

[0094] Here, the error can be the difference between the entry line traced length and the entry line measured length. In addition, if the entry line angle (θ) is greater than 0, θ" can be [entry line angle (θ) + 90°], and if the entry line angle is less than 0, θ" can be [entry line angle (θ) - 90°].

[0095] Figure 7 is a block diagram illustrating a parking space position calibration apparatus according to an embodiment of the present disclosure.

[0096] Reference Figure 7 According to an embodiment of the present disclosure, a parking space position calibration device 10 may include a memory 11, a measuring device 12, a generating device 13, and a calibration device 14. The measuring device 12, the generating device 13, and the calibration device 14 may correspond to a processor. Furthermore, the parking space position calibration device 10 may correspond to a vehicle control device.

[0097] The memory 11 may be configured to store computer-executable instructions.

[0098] In addition, the parking space position calibration device 10 may include at least one processor configured to access the memory 11 and execute instructions.

[0099] Parking space position calibration apparatus 10 may measure the coordinates of a first entrance point of a first parking space using measurement apparatus 12. For example, parking space position calibration apparatus 10 may use measurement apparatus 12 to measure the coordinates of the first entrance point of the first parking space based on a bird's-eye view (BEV) image using a neural network. Furthermore, parking space position calibration apparatus 10 may use generation apparatus 13 to generate a first entrance line measurement length based on the measured coordinates of the first entrance point, and to generate a first entrance line traced length based on the first entrance line measurement length by tracing the length of the first entrance line.

[0100] The parking space position calibration apparatus 10 may calibrate the coordinates of the first entry point based on a difference between the first entry line traced length and the first entry line measured length, ie, a first error, through the calibration apparatus 14 .

[0101] Furthermore, if i) the difference between the center point of the first entrance line and the longitudinal position of the vehicle's side camera is less than a first threshold, and ii) the difference between the first entrance line measured length and the entrance line reference length is less than a second threshold, the parking space position calibration device 10 may generate a first entrance line tracking length by updating the second entrance line tracking length generated in the previous frame via the generation device 13. Specifically, the parking space position calibration device 10 may generate the first entrance line tracking length by updating the second entrance line tracking length via the generation device 13 based on the second entrance line tracking length generated in the previous frame and the first entrance line measured length generated in the current frame. Furthermore, the parking space position calibration device 10 may generate the first entrance line tracking length by predicting the first entrance line tracking length based on the second entrance line tracking length and the first entrance line measured length via the generation device 13 using a specific filter. For example, the parking space position calibration device 10 may use a Kalman filter to predict the first entrance line tracking length. Furthermore, if the length of the first entrance line was tracked for the first time in the previous frame, the second entrance line tracking length may be the entrance line reference length.

[0102] The parking space position calibration apparatus 10 may calibrate the coordinates of the first entry point based on the first error and the angle between the vehicle and a parking line adjacent to the first entry line in the first parking space through the calibration apparatus 14 .

[0103] Parking space position calibration apparatus 10 may measure the coordinates of a second entrance point of a second parking space and a third entrance point of a third parking space using measurement device 12. Furthermore, parking space position calibration apparatus 10 may generate a second entrance line measurement length based on the coordinates of the second entrance point, generate a second error (the difference between the first entrance line tracking length and the second entrance line measurement length), generate a third entrance line measurement length based on the coordinates of the third entrance point, and generate a third error (the difference between the first entrance line tracking length and the third entrance line measurement length) using generation device 13.

[0104] The parking space position calibration apparatus 10 may first calibrate the coordinates of the entry point of the second parking space and the third parking space corresponding to the smaller value between the second error and the third error through the calibration apparatus 14 .

[0105] Figure 8 is a block diagram of a computing system for executing a parking space position calibration method according to an embodiment of the present disclosure.

[0106] Reference Figure 8The 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 1600 , and a network interface 1700 interconnected via a bus 1200 .

[0107] The processor 1100 may be a central processing unit (CPU) or a semiconductor device that processes instructions stored in the memory 1300 and / or the storage 1600. The memory 1300 and the storage 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.

[0108] Therefore, the operations of the methods or algorithms described in conjunction with the embodiments disclosed in this specification may be directly implemented by hardware modules, software modules, or a combination of hardware modules and software modules executed by the processor 1100. The software modules may reside on a storage medium (i.e., the memory 1300 and / or the storage 1600) such as RAM, flash memory, ROM, EPROM, EEPROM, registers, hard disks, removable disks, and CD-ROMs.

[0109] An exemplary storage medium may be coupled to the processor 1100. The processor 1100 may read information from the storage medium and may write information to the storage medium. Alternatively, the storage medium may be integrated with the processor 1100. The processor and the storage medium may reside in an application specific integrated circuit (ASIC). The ASIC may reside in a user terminal. In another embodiment, the processor and the storage medium may reside in the user terminal as separate components.

[0110] The above description only illustrates the technical ideas of the present disclosure, and a person skilled in the art may make various modifications and variations without departing from the essential characteristics of the present disclosure. Therefore, the embodiments of the present disclosure are intended to explain the spirit and scope of the present disclosure, but not to limit the spirit and scope of the present disclosure, so that the spirit and scope of the present disclosure are not limited by the embodiments. The scope of protection of the present disclosure should be interpreted by the following claims, and all technical ideas within the scope equivalent to them should be interpreted as included within the scope of the present disclosure.

[0111] According to the vehicle control method of the embodiment of the present disclosure, the precise coordinates of the entrance point of the parking space can be obtained.

[0112] According to the vehicle control method of the embodiment of the present disclosure, if there is a slope on the road where the vehicle is located, the coordinates of the entrance point of the parking space may be calibrated.

[0113] According to the vehicle control method of the embodiment of the present disclosure, it is possible to reduce errors in a route for automatic parking control.

[0114] According to the vehicle control method of the embodiment of the present disclosure, the time required to determine a route for automatic parking control can be shortened.

[0115] According to the vehicle control method of the embodiment of the present disclosure, the performance of automatic parking can be improved.

[0116] Effects obtainable in the present disclosure are not limited to the above-mentioned effects, and any other effects not mentioned herein should be clearly understood from the following description by those having ordinary skill in the art to which the present disclosure pertains.

[0117] Although the present disclosure has been described above with reference to the embodiments and the accompanying drawings, the present disclosure is not limited thereto, but may be variously modified and changed by one of ordinary skill in the art without departing from the spirit and scope of the present disclosure as claimed in the following claims.

Claims

1. A vehicle control method, wherein: include: measuring, by a measuring device, coordinates of a first entry point that is an endpoint of a first entry line in the first parking space; generating, by a generating device, a first entry line measurement length based on the measured coordinates of the first entry point; generating, by the generating device, a first entry line tracing length by tracing the length of the first entry line based on the first entry line measured length; and The coordinates of the first entry point are calibrated by a calibration device based on a first error, the first error being a difference between the first entry line traced length and the first entry line measured length.

2. The vehicle control method according to claim 1, wherein: Generating the first entry line tracing length includes: When the difference between the center point of the first entry line and the longitudinal position of the side camera of the vehicle is less than a first threshold, and when the difference between the measured length of the first entry line and the reference length of the entry line is less than a second threshold, the generating device generates the first entry line tracking length by updating the second entry line tracking length generated in the previous frame.

3. The vehicle control method according to claim 2, wherein: Generating the first entry line tracing length includes: The generating device generates the first entry line tracing length by updating the second entry line tracing length based on the second entry line tracing length generated in the previous frame and the first entry line measurement length generated in the current frame.

4. The vehicle control method according to claim 3, wherein: Generating the first entry line tracing length includes: The first entry line tracing length is generated by the generating device by predicting the first entry line tracing length based on the second entry line tracing length and the first entry line measured length using an arbitrary filter.

5. The vehicle control method according to claim 2, wherein: When the tracking of the length of the first entry line is performed for the first time in the previous frame, the second entry line tracking length is the entry line reference length.

6. The vehicle control method according to claim 1, wherein: Calibrating the coordinates of the first entry point includes: When the first error is greater than a third threshold, the calibration device calibrates the coordinates of the first entry point based on the first error and an angle between the vehicle and a parking line adjacent to the first entrance line in the first parking space.

7. The vehicle control method according to claim 1, wherein: Also includes: measuring, by the measuring device, the coordinates of a second entrance point of a second parking space; generating, by the generating device, a second entry line measurement length based on the coordinates of the second entry point; generating, by the generating device, a second error, the second error being a difference between the first entry line traced length and the second entry line measured length; measuring the coordinates of a third entrance point of a third parking space by the measuring device; generating, by the generating device, a third entry line measurement length based on the coordinates of the third entry point; generating, by the generating device, a third error, the third error being a difference between the first entry line traced length and the third entry line measured length; and The calibration device first calibrates the coordinates of the entry point of the second parking space and the third parking space corresponding to the smaller value between the second error and the third error.

8. The vehicle control method according to claim 1, wherein: Measuring the coordinates of the first entrance point of the first parking space includes: The coordinates of the first entrance point of the first parking space are measured by the measuring device based on a bird's-eye view image using a neural network.

9. A vehicle control device, in, include: a memory configured to store computer-executable instructions; and at least one processor configured to access the memory and execute the computer-executable instructions, Wherein, the at least one processor is configured as: measuring, by a measuring device, coordinates of a first entry point that is an endpoint of a first entry line in the first parking space; generating, by a generating device, a first entry line measured length based on the measured coordinates of the first entry point, and generating a first entry line traced length by tracing the length of the first entry line based on the first entry line measured length; and The coordinates of the first entry point are calibrated by a calibration device based on a first error, the first error being a difference between the first entry line traced length and the first entry line measured length.

10. The vehicle control apparatus according to claim 9, wherein The at least one processor is configured to: When the difference between the center point of the first entry line and the longitudinal position of the side camera of the vehicle is less than a first threshold, and when the difference between the measured length of the first entry line and the reference length of the entry line is less than a second threshold, the generating device generates the first entry line tracking length by updating the second entry line tracking length generated in the previous frame.

11. The vehicle control device according to claim 10, wherein The at least one processor is configured to: The generating device generates the first entry line tracing length by updating the second entry line tracing length based on the second entry line tracing length generated in the previous frame and the first entry line measurement length generated in the current frame.

12. The vehicle control device according to claim 11, wherein The at least one processor is configured to: The first entry line tracing length is generated by the generating device by predicting the first entry line tracing length based on the second entry line tracing length and the first entry line measured length using an arbitrary filter.

13. The vehicle control apparatus according to claim 10, wherein: When the tracking of the length of the first entry line is performed for the first time in the previous frame, the second entry line tracking length is the entry line reference length.

14. The vehicle control apparatus according to claim 9, wherein The at least one processor is configured to: When the first error is greater than a third threshold, the calibration device calibrates the coordinates of the first entry point based on the first error and an angle between the vehicle and a parking line adjacent to the first entrance line in the first parking space.

15. The vehicle control apparatus according to claim 9, wherein The at least one processor is configured to: measuring, by the measuring device, the coordinates of a second entrance point of the second parking space and the coordinates of a third entrance point of the third parking space; generating, by the generating device, a second entry line measurement length based on the coordinates of the second entry point, generating a second error as a difference between the first entry line traced length and the second entry line measurement length, generating a third entry line measurement length based on the coordinates of the third entry point, and generating a third error as a difference between the first entry line traced length and the third entry line measurement length; as well as The calibration device first calibrates the coordinates of the entry point of the second parking space and the third parking space corresponding to the smaller value between the second error and the third error.

16. The vehicle control apparatus according to claim 9, wherein The at least one processor is configured to: The coordinates of the first entrance point of the first parking space are measured by the measuring device based on a bird's-eye view image by using a neural network.

Images