Parking space detection method and device

Abstract

The invention discloses a parking space detection method and device. The method comprises the following steps: acquiring a drivable area and obstacle information around a vehicle; determining at least one edge point group according to the drivable area and the obstacle information; at least one to-be-selected parking space is determined according to the at least one edge point group, and each edge point group in the at least one edge point group corresponds to one to-be-selected parking space; and determining the parking space from the at least one parking space to be selected. According to the embodiment of the invention, the parking space detection efficiency can be improved.

Description

Technical Field

[0001] The present application belongs to the field of intelligent driving technology, and in particular, relates to a parking space detection method and device. Background Art

[0002] In current parking space detection technology, the waveform and intensity of the echo signal obtained by the distance sensor installed on the vehicle are usually input into the trained deep learning model to analyze whether there is an empty space on both sides of the vehicle body where the vehicle can be parked. If there is an empty space, it is further analyzed whether the empty space is a valid parking space.

[0003] However, distance sensors are usually laser radars or ultrasonic radars, which have the characteristics of large amount of information and high noise in a single frame. Therefore, the algorithm for detecting valid parking spaces based on the echo signal of the distance sensor is relatively complex, usually taking a long time and high resources, resulting in low efficiency of parking space detection. Summary of the invention

[0004] The embodiments of the present application provide a parking space detection method and device, which can solve the problem of poor accuracy of existing network analysis.

[0005] In a first aspect, an embodiment of the present application provides a method for detecting a parking space, the method comprising:

[0006] Obtain information about the drivable area and obstacles around the vehicle;

[0007] Determining at least one edge point group according to the drivable area and the obstacle information;

[0008] Determine at least one parking space to be selected according to the at least one edge point group, wherein each edge point group in the at least one edge point group corresponds to one parking space to be selected;

[0009] A parking space is determined from the at least one parking space to be selected.

[0010] In some embodiments, determining at least one edge point group according to the drivable area and the obstacle information includes:

[0011] Determine an edge point set according to the drivable area and the obstacle information, wherein the edge point set includes a plurality of edge points, and the plurality of edge points are used to characterize the position of the obstacle and the edge position of the drivable area;

[0012] The plurality of edge points in the edge point set are divided into at least one edge point group.

[0013] In some embodiments, dividing the plurality of edge points in the edge point set into at least one edge point group comprises:

[0014] Determine at least one region of interest according to the position of the vehicle, wherein each of the at least one region of interest is a rectangle parallel to the vehicle;

[0015] The plurality of edge points in the edge point set are divided into at least one edge point group according to the region of interest.

[0016] In some embodiments, dividing the plurality of edge points in the edge point set into at least one edge point group according to the region of interest includes:

[0017] For any region of interest among the at least one region of interest, determining a target edge point from the region of interest, wherein the target edge point is an edge point whose distance from a first edge of the region of interest is less than a first threshold, and the first edge is an edge of the region of interest adjacent to the vehicle;

[0018] In a pre-constructed vehicle coordinate system, a first distance in the longitudinal direction between each two closest target edge points in the longitudinal direction in the region of interest is calculated, wherein the vehicle coordinate system is a coordinate system with the vehicle as the origin, the driving direction of the vehicle as the positive direction of the longitudinal direction, and the direction from the left side to the right side of the vehicle as the positive direction of the transverse direction;

[0019] In the case that the first distance is greater than or equal to a second threshold, two target edge points corresponding to the first distance and all edge points in the vehicle coordinate system whose longitudinal coordinates are between the two target edge points are determined as an edge point group.

[0020] In some embodiments, determining at least one parking space to be selected according to the at least one edge point group includes:

[0021] For each edge point group in the at least one edge point group, determine a first edge point, a second edge point, and a third edge point in the edge point group, wherein in the vehicle coordinate system, the first edge point is an edge point with a maximum ordinate outside the target edge point, the second edge point is an edge point with a minimum ordinate outside the target edge point, and the third edge point is an edge point with a shortest distance from the first side outside the target edge point;

[0022] A parking space to be selected is determined according to the first edge point, the second edge point, and the third edge point.

[0023] In some embodiments, determining the to-be-selected parking space according to the first edge point, the second edge point, and the third edge point includes:

[0024] Determine the ordinate of the first edge point as a first ordinate, determine the ordinate of the second edge point as a second ordinate, and determine the abscissa of the third edge point as a first abscissa;

[0025] Determine the parking space corner point corresponding to the edge point group according to the first ordinate, the second ordinate and the first abscissa;

[0026] The parking space to be selected is determined according to the parking space corner point.

[0027] In some embodiments, when the parking space to be selected does not intersect with a line connecting any pair of adjacent edge points, before determining whether there is a parked vehicle within a preset range of the parking space to be selected, the method further includes:

[0028] Determine, according to the positions of the four sides of the parking space to be selected, a second horizontal coordinate, a third horizontal coordinate, a third vertical coordinate and a fourth vertical coordinate of the parking space to be selected in the vehicle coordinate system;

[0029] For any pair of adjacent edge points, obtaining first coordinates and second coordinates of the adjacent edge points;

[0030] It is determined whether adjacent edge points of the to-be-selected parking spaces intersect according to the second horizontal coordinate, the third horizontal coordinate, the third vertical coordinate, the fourth vertical coordinate, the first coordinate and the second coordinate.

[0031] In some embodiments, the parking spaces include parallel parking spaces and vertical parking spaces.

[0032] After determining a parking space from the at least one parking space to be selected, the method further includes:

[0033] In the case where there is an overlap between the parking space and other parking spaces, a target parking space in at least one of the overlapping parking spaces is deleted, and the target parking space is any one of a parallel parking space and a vertical parking space.

[0034] In a second aspect, an embodiment of the present application provides a parking space detection device, the device comprising:

[0035] An acquisition module is used to obtain the drivable area and obstacle information around the vehicle;

[0036] A first determination module, configured to determine at least one edge point group according to the drivable area and the obstacle information;

[0037] A second determination module is used to determine at least one parking space to be selected according to the at least one edge point group, wherein each edge point group in the at least one edge point group corresponds to one parking space to be selected;

[0038] The detection module is used to determine a parking space from the at least one parking space to be selected.

[0039] In a third aspect, an embodiment of the present application provides a parking space detection device, the device comprising: a processor and a memory storing computer program instructions;

[0040] When the processor executes the computer program instructions, the above parking space detection method is implemented.

[0041] In a fourth aspect, an embodiment of the present application provides a computer storage medium having computer program instructions stored thereon, and when the computer program instructions are executed by a processor, the above-mentioned parking space detection method is implemented.

[0042] In a fifth aspect, an embodiment of the present application provides a computer program product, which includes computer program instructions, and when the computer program instructions are executed by a processor, the above parking space detection method is implemented.

[0043] In the present application, the drivable area and obstacle information around the vehicle are obtained; at least one edge point group is determined based on the drivable area and obstacle information; at least one to-be-selected parking space is determined based on the at least one edge point group, wherein each edge point group in the at least one edge point group corresponds to a to-be-selected parking space; and a parking space is determined from the at least one to-be-selected parking space. In this way, the present application only needs to know the drivable area of ​​the vehicle and detect the obstacle information near the vehicle, and the parking spaces around the vehicle can be detected by pure mathematical methods. Compared with the related art that relies on model detection, it saves the cost and time of data annotation / model training and improves the efficiency of parking space detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0045] Figure 1 It is a flow chart of a parking space detection method provided in one embodiment of the present application;

[0046] Figure 2 This is a schematic diagram of a scene of a parking space detection method provided by an embodiment of the present application;

[0047] Figure 3 is a scene schematic diagram of a parking space detection method provided by another embodiment of the present application;

[0048] Figure 4 is a scene schematic diagram of a parking space detection method provided by another embodiment of the present application;

[0049] Figure 5 It is a structural schematic diagram of a parking space detection device provided in one embodiment of the present application;

[0050] Figure 6 It is a schematic diagram of the hardware structure of a parking space detection device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0051] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0052] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0053] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The embodiments will be described in detail below in conjunction with the accompanying drawings.

[0054] Specifically, in order to solve the problems in the prior art, the embodiments of the present application provide a method and device for detecting a parking space. The following first introduces the method for detecting a parking space provided in the embodiments of the present application.

[0055] Figure 1 A schematic flow chart of a parking space detection method provided by an embodiment of the present application is shown. The method comprises the following steps:

[0056] S110, obtaining information about a drivable area and obstacles around the vehicle.

[0057] In this embodiment, a surround view camera installed on a vehicle can be used to capture surround view images around the vehicle, and then the captured surround view images are processed and analyzed, and the surround view images are processed by denoising, filtering, image enhancement, etc. to improve the image quality and resolution, and then obstacle information is detected in the surround view images and the drivable area of ​​the vehicle is determined. The obstacle information may include the distance and direction of the obstacle relative to the vehicle, as well as the size of the obstacle. The drivable area of ​​the vehicle is planned based on the obstacle information.

[0058] S120: Determine at least one edge point group according to the drivable area and the obstacle information.

[0059] In this embodiment, the edge point group includes a plurality of edge points, which are points in space determined based on the drivable area and obstacle information, and which may be points representing the edges and corners of the drivable area and obstacles. The edge points can represent the contours of the drivable area and obstacles.

[0060] The edge point group is a collection of multiple edge points in a certain area. There is a parking space to be selected in the area surrounded by each edge point group. The parking space to be selected is a space within the detected drivable range that can accommodate the vehicle and does not have an edge point.

[0061] S130: Determine at least one parking space to be selected according to the at least one edge point group, wherein each edge point group in the at least one edge point group corresponds to a parking space to be selected.

[0062] In this embodiment, since there is a parking space to be selected in the area surrounded by each edge point group, and the parking space to be selected is a rectangular area, the four corner points of the parking space to be selected in the area surrounded by the edge point group can be obtained according to each edge point group, and the position of the parking space to be selected is determined based on the four corner points; or the four sides of the parking space to be selected in the area surrounded by the edge point group can be obtained according to each edge point group, and the position of the parking space to be selected is determined based on the four sides.

[0063] S140: Determine a parking space from the at least one parking space to be selected.

[0064] In this embodiment, after determining the position of the parking space to be selected in the space, it is necessary to screen the parking space from the parking space to be selected. Since the parking space to be selected is a parking space that can accommodate the vehicle and does not include edge points, and edge points are used to characterize the edges and corners of obstacles, but obstacles have volume, it is necessary to further determine whether there are obstacles and whether parking is allowed at this location. Only when it is detected that there are no obstacles in the parking space to be selected and it is confirmed that parking is allowed at the parking space to be selected, the parking space to be selected is determined as a parking space.

[0065] In the present application, the drivable area and obstacle information around the vehicle are obtained; at least one edge point group is determined based on the drivable area and obstacle information; at least one to-be-selected parking space is determined based on the at least one edge point group, wherein each edge point group in the at least one edge point group corresponds to a to-be-selected parking space; and a parking space is determined from the at least one to-be-selected parking space. In this way, the present application only needs to know the drivable area of ​​the vehicle and detect the obstacle information near the vehicle, and the parking spaces around the vehicle can be detected by pure mathematical methods. Compared with the related art that relies on model detection, it saves the cost and time of data annotation / model training and improves the efficiency of parking space detection.

[0066] As an optional embodiment, the above S120 may include:

[0067] Determine an edge point set according to the drivable area and the obstacle information, wherein the edge point set includes a plurality of edge points, and the plurality of edge points are used to characterize the position of the obstacle and the edge position of the drivable area;

[0068] The plurality of edge points in the edge point set are divided into at least one edge point group.

[0069] In this embodiment, the position of the edge point can be determined by the obstacle information detected by the surround view camera and the edge and corner points of the drivable area, and the set of all detected edge points is the edge point set.

[0070] Then the edge point set is divided into at least one edge point group, and each edge point group is further divided into a parking space to be selected.

[0071] As an optional embodiment, dividing the plurality of edge points in the edge point set into at least one edge point group includes:

[0072] Determine at least one region of interest according to the position of the vehicle, wherein each of the at least one region of interest is a rectangle parallel to the vehicle;

[0073] The plurality of edge points in the edge point set are divided into at least one edge point group according to the region of interest.

[0074] In this embodiment, the region of interest around the vehicle can be determined based on the position of the vehicle. The region of interest is an area near the vehicle where the vehicle may be parked. The region of interest is determined based on the position of the vehicle and rules set in advance by the user. Figure 2As shown, there are two regions of interest, namely a first region of interest 210 and a second region of interest 220. The first region of interest 210 is a rectangular region located on the left side of the vehicle and parallel to the vehicle, and the second region of interest 220 is a rectangular region located on the right side of the vehicle and parallel to the vehicle. The length of the region of interest is 15 meters and the width is 8 meters.

[0075] After the regions of interest near the vehicle are determined, edge point groups included in each region of interest may be obtained respectively.

[0076] As an optional embodiment, dividing the plurality of edge points in the edge point set into at least one edge point group according to the region of interest includes:

[0077] For any region of interest among the at least one region of interest, determining a target edge point from the region of interest, wherein the target edge point is an edge point whose distance from a first edge of the region of interest is less than a first threshold, and the first edge is an edge of the region of interest adjacent to the vehicle;

[0078] In a pre-constructed vehicle coordinate system, a first distance in the longitudinal direction between each two closest target edge points in the longitudinal direction in the region of interest is calculated, wherein the vehicle coordinate system is a coordinate system with the vehicle as the origin, the driving direction of the vehicle as the positive direction of the longitudinal direction, and the direction from the left side to the right side of the vehicle as the positive direction of the transverse direction;

[0079] In the case that the first distance is greater than or equal to a second threshold, two target edge points corresponding to the first distance and all edge points in the vehicle coordinate system whose longitudinal coordinates are between the two target edge points are determined as an edge point group.

[0080] In this embodiment, a vehicle coordinate system may be first constructed in space, wherein the vehicle coordinate system is a coordinate system with the vehicle as the origin, the direction from the rear of the vehicle to the front of the vehicle as the positive direction of the longitudinal axis, and the direction from the left side to the right side of the vehicle as the positive direction of the transverse axis. For each region of interest, the distance from each edge point in the region of interest to the first side may be calculated in order from the smallest to the largest longitudinal coordinate of each edge point, and all edge points whose distance is less than the first threshold value may be selected as target edge points.

[0081] There are two types of parking spaces: vertical parking spaces and parallel parking spaces. Vertical parking spaces are parking spaces that are vertical to the current position of the vehicle, and parallel parking spaces are parking spaces that are parallel to the current position of the vehicle. The minimum width of vertical parking spaces, the minimum length of vertical parking spaces, the minimum width of parallel parking spaces, and the minimum length of parallel parking spaces can be set in advance.

[0082] In the process of detecting vertical parking spaces in the region of interest, the first threshold is a preset minimum length of the vertical parking spaces, and in the process of detecting parallel parking spaces in the region of interest, the first threshold is a minimum width of the parallel parking spaces.

[0083] After determining all edge points in the region of interest, the first distance in the longitudinal direction between any two target edge points that are closest to each other in the longitudinal direction can be calculated. If the first distance is greater than or equal to the second threshold, it can be considered that the vehicle can be accommodated between the two target edge points. Therefore, the two target edge points and all edge points whose longitudinal coordinates in the vehicle coordinate system are between the two target edge points can be determined as an edge point group. There may be a parking space between an edge point group. If the first distance in the longitudinal direction between the two target edge points that are closest to each other in the longitudinal direction is less than the second threshold, it can be considered that the vehicle cannot be accommodated between the two target edge points. Therefore, the edge points between the two target edge points can be filtered out.

[0084] In the process of detecting vertical parking spaces in the region of interest, the second threshold is a preset minimum width of the vertical parking spaces, and in the process of detecting parallel parking spaces in the region of interest, the first threshold is a minimum length of the parallel parking spaces.

[0085] Through the above method, at least one edge point group can be obtained from the environmental information and obstacle information obtained by vehicle detection, and each edge point group may include a parking space to be selected. Therefore, the above method can divide the area around the vehicle into multiple areas that may include parking spaces, thereby facilitating further parking space detection.

[0086] As an optional embodiment, the above S130 includes:

[0087] For each edge point group in the at least one edge point group, determine a first edge point, a second edge point, and a third edge point in the edge point group, wherein in the vehicle coordinate system, the first edge point is an edge point with a maximum ordinate outside the target edge point, the second edge point is an edge point with a minimum ordinate outside the target edge point, and the third edge point is an edge point with a shortest distance from the first side outside the target edge point;

[0088] A parking space to be selected is determined according to the first edge point, the second edge point, and the third edge point.

[0089] As an optional embodiment, determining the to-be-selected parking space according to the first edge point, the second edge point, and the third edge point includes:

[0090] Determine the ordinate of the first edge point as a first ordinate, determine the ordinate of the second edge point as a second ordinate, and determine the abscissa of the third edge point as a first abscissa;

[0091] Determine the parking space corner point corresponding to the edge point group according to the first ordinate, the second ordinate and the first abscissa;

[0092] The parking space to be selected is determined according to the parking space corner point.

[0093] In this embodiment, since each edge point group surrounds or semi-surrounds a parking space to be selected that can accommodate the vehicle, and since the parking space to be selected in this embodiment is a rectangle, the specific position of the parking space to be selected can be determined by determining the four corner points of the parking space to be selected.

[0094] Specifically, for each edge point group, the first edge point with the largest ordinate outside the target edge point in the vehicle coordinate system in the edge point group can be determined, and its ordinate is marked as y max , the second edge point with the smallest ordinate outside the target edge point, whose ordinate is marked as y min , and the third edge point with the shortest distance to the first edge except the target edge point, whose horizontal coordinate is marked as x far , further, another abscissa x can be calculated according to the sum or difference of the abscissa of the third edge point and the third threshold value near :

[0095] In the first region of interest on the left side of the vehicle, there are:

[0096] x near =x far +w

[0097] Among them, x far is the horizontal coordinate of the third edge point, x near is another horizontal coordinate, and w is the minimum length of a perpendicular parking space, or the minimum width of a parallel parking space.

[0098] In the second region of interest to the right of the vehicle, there are:

[0099] x near =x far -w

[0100] Among them, x far is the horizontal coordinate of the third edge point, x near is another horizontal coordinate, and w is the minimum length of a perpendicular parking space, or the minimum width of a parallel parking space.

[0101] When y is determined max ,y min , x near , xfar After these four coordinates, the four parking space corner points corresponding to the edge point group can be determined as (x near ,y max )、(x near ,y min )、(x far ,y max ) and (x far ,y min ). After determining the four parking space corner points, the parking spaces to be selected formed by the four parking space corner points can be determined.

[0102] Since one parking space to be selected can be determined by each edge point group, at least one parking space to be selected can be determined based on at least one edge point group.

[0103] In this way, the parking spaces to be selected can be determined based on the drivable area and obstacle information around the vehicle through purely mathematical methods. Compared with the reliance on model detection in related technologies, this saves the cost and time of data annotation / model training and improves the efficiency of obtaining parking spaces to be selected.

[0104] As an optional embodiment, the above S140 may include:

[0105] For any one of the at least one parking space to be selected, if the parking space to be selected does not intersect with a line connecting any pair of adjacent edge points, determining whether there is a parked vehicle within a preset range of the parking space to be selected;

[0106] In the case where there is a parked vehicle within the preset range of the parking space to be selected, the parking space to be selected is determined as the parking space.

[0107] In this embodiment, since edge points are points in space determined based on the drivable area and obstacle information, edge points can represent the edges and corners of the drivable area and obstacles, but obstacles have volume, and edge points can only represent a part of the obstacles. There may also be obstacles at the location where the line connecting adjacent edge points is located. Therefore, after determining at least one parking space to be selected, it is also necessary to determine whether the parking space to be selected intersects with the line connecting adjacent edge points.

[0108] If the parking space to be selected intersects with the line connecting the adjacent edge points, then there may be an obstacle in the parking space to be selected, and thus the parking space to be selected cannot be determined as an actual parking space. If the parking space to be selected does not intersect with the line connecting the adjacent edge points, then there is no obstacle in the parking space to be selected, and it can be further determined whether there is a parked vehicle within a preset range around the parking space to be selected.

[0109] If there are parked vehicles around the parking space to be selected, it can be considered that parking is allowed in this area, and therefore the parking space to be selected can be determined as the actual parking space; if there are no parked vehicles around the parking space to be selected, it can be considered that parking is not allowed in this area, and therefore the parking space to be selected cannot be determined as the actual parking space.

[0110] As an optional embodiment, when the parking space to be selected does not intersect with a line connecting any pair of adjacent edge points, before determining whether there is a parked vehicle within a preset range of the parking space to be selected, the method further includes:

[0111] Determine, according to the positions of the four sides of the parking space to be selected, a second horizontal coordinate, a third horizontal coordinate, a third vertical coordinate and a fourth vertical coordinate of the parking space to be selected in the vehicle coordinate system;

[0112] For any pair of adjacent edge points, obtaining first coordinates and second coordinates of the adjacent edge points;

[0113] It is determined whether adjacent edge points of the to-be-selected parking spaces intersect according to the second horizontal coordinate, the third horizontal coordinate, the third vertical coordinate, the fourth vertical coordinate, the first coordinate and the second coordinate.

[0114] In this embodiment, after determining the position of the parking space to be selected in the vehicle coordinate system, the vertical coordinate of the side of the parking space to be selected parallel to the x-axis of the vehicle coordinate system that is farther from the x-axis is determined as the third vertical coordinate, recorded as yt, and the horizontal coordinate of the side of the parking space to be selected parallel to the x-axis that is closer to the x-axis is determined as the fourth vertical coordinate, recorded as yb. The horizontal coordinate of the side on the left side of the parking space to be selected parallel to the y-axis of the vehicle coordinate system is determined as the second horizontal coordinate, recorded as xl, and the horizontal coordinate of the side on the right side of the parking space to be selected parallel to the y-axis of the vehicle coordinate system is determined as the third horizontal coordinate, recorded as xr. And for any pair of adjacent edge points, determine the first coordinate and the second coordinate of the adjacent edge points. The horizontal coordinate of the first coordinate is pt1 x , the vertical coordinate of the first coordinate is pt1 y , the horizontal coordinate of the second coordinate is pt2 x , the ordinate of the second coordinate is pt2 y .

[0115] Thus, the first value R1, the second value R2, the third value R3 and the fourth value R4 can be calculated based on the second horizontal coordinate, the third horizontal coordinate, the third vertical coordinate, the fourth vertical coordinate, the first coordinate and the second coordinate. The specific calculation method is as follows:

[0116] R1=(pt1 y -pt2 y )*xl-(pt2 x -pt1 x )*yb+(pt1x *pt2 y -pt1 y *pt2 x )

[0117] R2=(pt1 y -pt2 y )*xl-(pt2 x -pt1 x )*yt+(pt1 x *pt2 y -pt1 y *pt2 x )

[0118] R3=(pt1 y -pt2 y )*xr-(pt2 x -pt1 x )*yb+(pt1 x *pt2 y -pt1 y *pt2 x )

[0119] R4=(pt1 y -pt2 y )*xr-(pt2 x -pt1 x )*yt+(pt1 x *pt2 y -pt1 y *pt2 x )

[0120] Among them, yt is the third ordinate, yb is the fourth ordinate, xl is the second abscissa, xr is the third abscissa, and the abscissa of the first coordinate is pt1 x , the vertical coordinate of the first coordinate is pt1 y , the horizontal coordinate of the second coordinate is pt2 x , the ordinate of the second coordinate is pt2 y , R1, R2, R3, and R4 are four values ​​obtained by calculation.

[0121] According to the above formula, if R1*R2*R3*R4 is not less than 0, it can be considered that the parking space to be selected does not intersect with the adjacent edge point.

[0122] Or, if pt1 x and pt2 x Not less than xr, or pt1 x and pt2 x If neither is greater than xl, it means that the parking space to be selected does not intersect with the adjacent edge point.

[0123] Or, if pt1 y and pt2 y Not less than yt, or pt1 y and pt2 y If neither is greater than yb, it means that the parking space to be selected does not intersect with the adjacent edge point.

[0124] like Figure 3 As shown, there are a first parking space 310 and a second parking space 320 to be selected in the region of interest, and the first parking space 310 intersects with a line connecting a pair of adjacent edge points, so the first parking space 310 to be selected can be determined as an invalid parking space, and the lines connecting all adjacent edge points do not intersect with the second parking space 320 to be selected, so the second parking space 320 to be selected is a valid parking space. After determining the valid parking space, the final parking space is further screened out from all the valid parking spaces.

[0125] By means of the above method, the parking spaces to be selected can be screened, and the parking spaces that are detected to have no obstacles among the parking spaces to be selected can be further screened.

[0126] As an optional embodiment, the parking spaces include parallel parking spaces and vertical parking spaces.

[0127] After determining a parking space from the at least one parking space to be selected, the method further includes:

[0128] In the case where there is an overlap between the parking space and other parking spaces, a target parking space in at least one of the overlapping parking spaces is deleted, and the target parking space is any one of a parallel parking space and a vertical parking space.

[0129] In this embodiment, the area of ​​interest is screened twice, the first time is to screen the vertical parking spaces, and the second time is to screen the parallel parking spaces. Since the two screenings are independent, there may be overlaps, and one of them is deleted as required.

[0130] like Figure 4 As shown, there are partially overlapping first parallel parking spaces 410 and first vertical parking spaces 420 in the same parking space to be selected, and either the first parallel parking space 410 or the first vertical parking space 420 can be selected as the final parking space.

[0131] Based on the parking space detection method provided in the above embodiment, the present application also provides a specific implementation of a parking space detection device. Please refer to the following embodiment.

[0132] See first Figure 5 The parking space detection device 500 provided in the embodiment of the present application includes the following modules:

[0133] An acquisition module 501 is used to acquire information about a drivable area and obstacles around the vehicle;

[0134] A first determining module 502, configured to determine at least one edge point group according to the drivable area and the obstacle information;

[0135] A second determination module 503 is configured to determine at least one parking space to be selected according to the at least one edge point group, wherein each edge point group in the at least one edge point group corresponds to one parking space to be selected;

[0136] The detection module 504 is configured to determine a parking space from the at least one parking space to be selected.

[0137] The device can obtain the drivable area and obstacle information around the vehicle; determine at least one edge point group based on the drivable area and obstacle information; determine at least one to-be-selected parking space based on the at least one edge point group, wherein each edge point group in the at least one edge point group corresponds to a to-be-selected parking space; and determine a parking space from the at least one to-be-selected parking space. In this way, the present application only needs to know the drivable area of ​​the vehicle and detect the obstacle information near the vehicle, and the parking spaces around the vehicle can be detected by pure mathematical methods. Compared with the related art that relies on model detection, it saves the cost and time of data annotation / model training and improves the efficiency of parking space detection.

[0138] As an implementation of the present application, the first determining module 502 may include:

[0139] A first determining unit is used to determine an edge point set according to the drivable area and the obstacle information, wherein the edge point set includes a plurality of edge points, and the plurality of edge points are used to represent the position of the obstacle and the edge position of the drivable area;

[0140] The dividing unit is used to divide the multiple edge points in the edge point set into at least one edge point group.

[0141] As an implementation of the present application, the above-mentioned division unit may further include:

[0142] A first determining submodule is used to determine at least one region of interest according to the position of the vehicle, wherein each of the at least one region of interest is a rectangle parallel to the vehicle;

[0143] The division subunit is used to divide the multiple edge points in the edge point set into at least one edge point group according to the region of interest.

[0144] As an implementation of the present application, the above-mentioned division subunit may also be used to, for any region of interest in the at least one region of interest, determine a target edge point from the region of interest, wherein the target edge point is an edge point whose distance from a first edge of the region of interest is less than a first threshold, and the first edge is an edge of the region of interest adjacent to the vehicle;

[0145] In a pre-constructed vehicle coordinate system, a first distance in the longitudinal direction between each two closest target edge points in the longitudinal direction in the region of interest is calculated, wherein the vehicle coordinate system is a coordinate system with the vehicle as the origin, the driving direction of the vehicle as the positive direction of the longitudinal direction, and the direction from the left side to the right side of the vehicle as the positive direction of the transverse direction;

[0146] In the case that the first distance is greater than or equal to a second threshold, two target edge points corresponding to the first distance and all edge points in the vehicle coordinate system whose longitudinal coordinates are between the two target edge points are determined as an edge point group.

[0147] As an implementation of the present application, the second determining module 503 may include:

[0148] a second determining unit, configured to determine, for each edge point group in the at least one edge point group, a first edge point, a second edge point, and a third edge point in the edge point group, wherein in the vehicle coordinate system, the first edge point is an edge point with a maximum ordinate outside the target edge point, the second edge point is an edge point with a minimum ordinate outside the target edge point, and the third edge point is an edge point with a shortest distance from the first side outside the target edge point;

[0149] The third determining unit is configured to determine a parking space to be selected according to the first edge point, the second edge point and the third edge point.

[0150] As an implementation of the present application, the third determining unit may also be configured to determine the ordinate of the first edge point as the first ordinate, determine the ordinate of the second edge point as the second ordinate, and determine the abscissa of the third edge point as the first abscissa;

[0151] Determine the parking space corner point corresponding to the edge point group according to the first ordinate, the second ordinate and the first abscissa;

[0152] The parking space to be selected is determined according to the parking space corner point.

[0153] As an implementation of the present application, the detection module 504 may include:

[0154] a judging unit, configured to judge, for any one of the at least one parking space to be selected, whether there is a parked vehicle within a preset range of the parking space to be selected, when the parking space to be selected does not intersect a line connecting any pair of adjacent edge points;

[0155] The detection unit is used to determine the to-be-selected parking space as a parking space when there is a parked vehicle within a preset range of the to-be-selected parking space.

[0156] As an implementation of the present application, the detection module 504 may also be used to:

[0157] Determine, according to the positions of the four sides of the parking space to be selected, a second horizontal coordinate, a third horizontal coordinate, a third vertical coordinate and a fourth vertical coordinate of the parking space to be selected in the vehicle coordinate system;

[0158] For any pair of adjacent edge points, obtaining first coordinates and second coordinates of the adjacent edge points;

[0159] It is determined whether adjacent edge points of the to-be-selected parking spaces intersect according to the second horizontal coordinate, the third horizontal coordinate, the third vertical coordinate, the fourth vertical coordinate, the first coordinate and the second coordinate.

[0160] As an implementation of the present application, the above-mentioned parking space detection device 500 may further include:

[0161] The deleting module is used to delete a target parking space in at least one overlapping parking space when there is an overlap between the parking space and other parking spaces, wherein the target parking space is any one of a parallel parking space and a vertical parking space.

[0162] The parking space detection device provided in the embodiment of the present invention can implement each step in the above method embodiment, and will not be described again here to avoid repetition.

[0163] Figure 6 A schematic diagram of the hardware structure of a parking space detection device provided in an embodiment of the present application is shown.

[0164] The detection device at the parking space may include a processor 601 and a memory 602 storing computer program instructions.

[0165] Specifically, the processor 601 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0166] The memory 602 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 602 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 602 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 602 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 602 is a non-volatile solid-state memory.

[0167] The memory may include read-only memory (ROM), random access memory (RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical or other physical / tangible memory storage devices. Thus, typically, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to an aspect of the present disclosure.

[0168] The processor 601 implements any one of the parking space detection methods in the above embodiments by reading and executing computer program instructions stored in the memory 602 .

[0169] In one example, the parking space detection device may further include a communication interface 603 and a bus 610. Figure 6 As shown, the processor 601, the memory 602, and the communication interface 603 are connected via a bus 610 and communicate with each other.

[0170] The communication interface 603 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0171] Bus 610 includes hardware, software or both, and the parts of the detection equipment of the parking space are coupled to each other. For example, but not limitation, the bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front-side bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 610 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the present application considers any suitable bus or interconnection.

[0172] The parking space detection device may be based on the above embodiment, thereby realizing the above parking space detection method and device.

[0173] In addition, in combination with the parking space detection method in the above-mentioned embodiment, the embodiment of the present application may provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by the processor, any one of the parking space detection methods in the above-mentioned embodiments is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here. Among them, the above-mentioned computer-readable storage medium may include a non-transitory computer-readable storage medium, such as a read-only memory (Read-Only Memory, referred to as ROM), a random access memory (Random Access Memory, referred to as RAM), a disk or an optical disk, etc., which are not limited here.

[0174] In addition, an embodiment of the present application also provides a computer program product, including computer program instructions, which can implement the steps and corresponding contents of the aforementioned method embodiment when executed by a processor.

[0175] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0176] The functional blocks shown in the above block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0177] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0178] Aspects of the present disclosure are described above with reference to the flowchart and / or block diagram of the method, device and computer program product according to the embodiment of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0179] The above are only specific implementation methods of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.

Claims

1. A method for detecting a parking space, characterized in that: The method comprises: Obtain information about the drivable area and obstacles around the vehicle; Determining at least one edge point group according to the drivable area and the obstacle information; Determine at least one parking space to be selected according to the at least one edge point group, wherein each edge point group in the at least one edge point group corresponds to one parking space to be selected; A parking space is determined from the at least one parking space to be selected.

2. The parking space detection method according to claim 1, characterized in that: The determining at least one edge point group according to the drivable area and the obstacle information comprises: Determine an edge point set according to the drivable area and the obstacle information, wherein the edge point set includes a plurality of edge points, and the plurality of edge points are used to characterize the position of the obstacle and the edge position of the drivable area; The plurality of edge points in the edge point set are divided into at least one edge point group.

3. The parking space detection method according to claim 2, characterized in that: The dividing the plurality of edge points in the edge point set into at least one edge point group comprises: Determine at least one region of interest according to the position of the vehicle, wherein each of the at least one region of interest is a rectangle parallel to the vehicle; The plurality of edge points in the edge point set are divided into at least one edge point group according to the region of interest.

4. The method for detecting a parking space according to claim 3, characterized in that: The dividing the plurality of edge points in the edge point set into at least one edge point group according to the region of interest comprises: For any region of interest among the at least one region of interest, determining a target edge point from the region of interest, wherein the target edge point is an edge point whose distance from a first edge of the region of interest is less than a first threshold, and the first edge is an edge of the region of interest adjacent to the vehicle; In a pre-constructed vehicle coordinate system, a first distance in the longitudinal direction between each two closest target edge points in the longitudinal direction in the region of interest is calculated, wherein the vehicle coordinate system is a coordinate system with the vehicle as the origin, the driving direction of the vehicle as the positive direction of the longitudinal direction, and the direction from the left side to the right side of the vehicle as the positive direction of the transverse direction; In the case that the first distance is greater than or equal to a second threshold, two target edge points corresponding to the first distance and all edge points in the vehicle coordinate system whose longitudinal coordinates are between the two target edge points are determined as an edge point group.

5. The parking space detection method according to claim 1, characterized in that: The determining at least one parking space to be selected according to the at least one edge point group includes: For each edge point group in the at least one edge point group, determine a first edge point, a second edge point, and a third edge point in the edge point group, wherein in the vehicle coordinate system, the first edge point is an edge point with a maximum ordinate outside the target edge point, the second edge point is an edge point with a minimum ordinate outside the target edge point, and the third edge point is an edge point with a shortest distance from the first side outside the target edge point; A parking space to be selected is determined according to the first edge point, the second edge point, and the third edge point.

6. The method for detecting a parking space according to claim 1, characterized in that: The determining of a parking space to be selected according to the first edge point, the second edge point, and the third edge point includes: Determine the ordinate of the first edge point as a first ordinate, determine the ordinate of the second edge point as a second ordinate, and determine the abscissa of the third edge point as a first abscissa; Determine the parking space corner point corresponding to the edge point group according to the first ordinate, the second ordinate and the first abscissa; The parking space to be selected is determined according to the parking space corner point.

7. The parking space detection method according to claim 1, characterized in that: The step of determining a parking space from the at least one parking space to be selected comprises: For any one of the at least one parking space to be selected, if the parking space to be selected does not intersect with a line connecting any pair of adjacent edge points, determining whether there is a parked vehicle within a preset range of the parking space to be selected; In the case where there is a parked vehicle within the preset range of the parking space to be selected, the parking space to be selected is determined as the parking space.

8. The method for detecting a parking space according to claim 7, characterized in that: Before determining whether there is a parked vehicle within a preset range of the parking space to be selected when the parking space to be selected does not intersect with a line connecting any pair of adjacent edge points, the method further includes: Determine, according to the positions of the four sides of the parking space to be selected, a second horizontal coordinate, a third horizontal coordinate, a third vertical coordinate and a fourth vertical coordinate of the parking space to be selected in the vehicle coordinate system; For any pair of adjacent edge points, obtaining first coordinates and second coordinates of the adjacent edge points; It is determined whether adjacent edge points of the to-be-selected parking spaces intersect according to the second horizontal coordinate, the third horizontal coordinate, the third vertical coordinate, the fourth vertical coordinate, the first coordinate and the second coordinate.

9. The method for detecting a parking space according to claim 1, characterized in that: The parking spaces include parallel parking spaces and vertical parking spaces. After determining a parking space from the at least one parking space to be selected, the method further includes: In the case where there is an overlap between the parking space and other parking spaces, a target parking space in at least one of the overlapping parking spaces is deleted, and the target parking space is any one of a parallel parking space and a vertical parking space.

10. A parking space detection device, characterized in that: The device comprises: An acquisition module is used to obtain the drivable area and obstacle information around the vehicle; A first determination module, configured to determine at least one edge point group according to the drivable area and the obstacle information; A second determination module is used to determine at least one parking space to be selected according to the at least one edge point group, wherein each edge point group in the at least one edge point group corresponds to one parking space to be selected; The detection module is used to determine a parking space from the at least one parking space to be selected.

Images