Parking space detection method, controller, vehicle and computer readable storage medium

Abstract

The invention relates to the technical field of vehicles, in particular to a parking space detection method, a controller, a vehicle and a computer readable storage medium, and the method comprises the steps: obtaining a ground image, and extracting a lane line in the ground image; according to the geometric information of the lane lines, at least one angular point is obtained, and the angular point is an intersection point formed by intersection of the lane lines; determining a parking space angular point representing the parking space from all the angular points; the parking space information is determined according to the parking space angular points and the lane lines, real-time parking space detection on a low-computing-power platform is achieved, and the parking space detection efficiency and accuracy are improved.

Description

Technical Field

[0001] The present invention relates to the field of vehicle technology, and in particular to a parking space detection method, a controller, a vehicle and a computer-readable storage medium. Background Art

[0002] In recent years, with the development of automobile intelligence, automatic parking technology has been promoted and applied in various scenarios. Automatic parking technology can enable the car to automatically find and accurately park at an appropriate parking position. Correspondingly, parking space detection has become the core perception module in automatic parking technology. In related technologies, the pure visual parking space detection method based on the neural network model has been favored by relevant practitioners. However, the application of the neural network model has increasingly higher requirements on the computing power of the vehicle platform. Summary of the invention

[0003] In view of this, an embodiment of the present invention provides a parking space detection method, a controller, a vehicle and a computer-readable storage medium to solve the problem that the vehicle computer platform cannot meet the high computing power requirements.

[0004] In a first aspect, an embodiment of the present invention provides a parking space detection method, the parking space detection method comprising: acquiring a ground image, and extracting lane lines in the ground image;

[0005] Obtain at least one corner point according to the geometric information of the lane lines, wherein the corner point is a point formed by the intersection of the lane lines;

[0006] Determine a parking space corner point representing the parking space from all corner points;

[0007] Parking space information is determined according to the parking space corner point and the lane line.

[0008] In a second aspect, an embodiment of the present invention provides a controller, comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor implements the parking space detection method as described in the first aspect when executing the computer program.

[0009] According to a third aspect, a vehicle comprises an image collector and the controller according to the second aspect, wherein the image collector is used to collect images.

[0010] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the parking space detection method as described in the first aspect is implemented.

[0011] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0012] The present invention acquires a ground image and extracts lane lines in the ground image; obtains at least one corner point according to geometric information of the lane lines, wherein the corner point is an intersection point formed by the intersection of the lane lines; determines a parking space corner point representing the parking space from all corner points; determines parking space information according to the parking space corner point and the lane lines, thereby realizing real-time parking space detection on a low computing power platform and improving the efficiency and accuracy of parking space detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0014] Figure 1 is a flow chart of a parking space detection method provided in Embodiment 1 of the present invention;

[0015] Figure 2 This is a schematic diagram of lane edge line extraction provided by Embodiment 1 of the present invention;

[0016] Figure 3 This is a schematic diagram of lane line extraction provided by Embodiment 1 of the present invention;

[0017] Figure 4 This is a schematic diagram of parking space corner point detection provided by Embodiment 1 of the present invention;

[0018] Figure 5 is a schematic diagram of the correlation between the lane line edge line spacing and the lane line confidence provided in the first embodiment of the present invention;

[0019] Figure 6 is a structural schematic diagram of a vehicle provided by Embodiment 2 of the present invention;

[0020] Figure 7 It is a structural diagram of a controller provided in Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0021] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0022] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0023] It should also be understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0024] As used in the present specification and the appended claims, the term "if" may be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" may be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]", depending on the context.

[0025] In addition, in the description of the present specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0026] References to "one embodiment" or "some embodiments" etc. described in the present specification mean that one or more embodiments of the present invention include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0027] It should be understood that the order of execution of the steps in the following embodiments does not imply a precedence of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0028] In order to illustrate the technical solution of the present invention, specific embodiments are provided below for illustration.

[0029] The vehicle includes various image collectors and controllers, etc., wherein the image collector is used to collect ground images at the vehicle, for example, the image collector can be a camera, specifically, in order to obtain ground images, the camera can be set to be a panoramic camera or a plurality of fisheye cameras; the controller is used to analyze and process ground images to detect parking space information, and the controller can be connected to the image collector wirelessly or by wire, for example, the wired connection can include a controller area network bus (CAN, Controller Area Network) or a hard line, etc., to realize the acquisition of ground images, and obtain the real position information of the parking space based on the acquired ground images, and this part of information can be used to realize the vehicle's automatic driving, assisted driving, assisted parking, etc.

[0030] See also Figure 1 , is a flow chart of a parking space detection method provided in Embodiment 1 of the present invention, such as Figure 1 As shown, the parking space detection method may include the following steps:

[0031] Step S101, acquiring a ground image, extracting lane lines in the ground image; and obtaining at least one corner point according to geometric information of the lane lines.

[0032] The ground image is a panoramic image around the vehicle, that is, an image obtained when looking down at the vehicle from directly above the vehicle, wherein the image includes image information of the vehicle and a certain range around the vehicle. Lane lines can be indicative lines set on the ground, which need to be obtained by line extraction and other operations on the ground image. The geometric information of lane lines can refer to the position, size, length, width and other information of lane lines in the ground image. A corner point can refer to the intersection formed by two intersecting lane lines, or the intersection formed by the extension of two lane lines, or the end point of a lane line with special meaning, etc.

[0033] In an embodiment of the present invention, the image collector on the vehicle is at least four fisheye cameras, which are deployed at four positions on the vehicle, front, back, left and right, so that images around the vehicle can be collected. Compared with ordinary cameras, fisheye cameras have advantages such as long shooting distance and wide field of view.

[0034] Among them, the specific method of using a fisheye camera to collect images at the vehicle and form a ground image is: use multiple fisheye cameras on the vehicle to collect images at the vehicle at the same time, after obtaining the image collected by each fisheye camera at the same time, convert or splice the images collected by each fisheye camera according to the calibration parameters of each fisheye camera, etc., to obtain a ground image that can include the image around the vehicle.

[0035] After acquiring the ground image at the vehicle, the ground image is preprocessed to obtain a high-quality ground image to improve subsequent detection results. The specific preprocessing is: adaptive image brightness enhancement, adaptive image sharpening and denoising of the ground image. For adaptive image brightness enhancement, the statistical values ​​of the illumination intensity, color saturation and pixel value distribution of the ground image are obtained, and the ground image is adjusted and optimized based on the statistical values ​​of the ground image. Adaptive image brightness enhancement is a prior art, and the specific content is not repeated here. For adaptive image sharpening and denoising, during the driving process of the vehicle, the fisheye camera is a motion camera, and the degree of blur of the collected image in the parallel direction of the vehicle's movement is greater than its vertical direction, and the blur range is different at different movement speeds. Based on the movement speed information and the movement direction information, the ground image can be de-motion blurred. It can be understood that the convolution kernel size in the de-motion blurring process needs to be learned through a small number of samples.

[0036] It should be noted that the parameter learning method for de-motion blur processing includes but is not limited to machine learning algorithms such as k-mean clustering and ridge regression. De-motion blur processing is an existing technology and will not be described in detail here.

[0037] In order to realize parking space detection, the present invention needs to capture the ground image of the vehicle in an environment with a clear parking space. The ground image needs to contain ground lines to detect the parking space. Since the brightness of the lane line in the image is higher than the brightness of the background, the lane line in the ground image can be extracted based on the brightness. In the present invention, the intersection of two intersecting lane lines is used as the corner point, and the geometric information of the lane line extracted from the ground image is analyzed to determine the intersection, thereby obtaining the location of the intersection, the corresponding lane line and other information.

[0038] Optionally, extracting lane lines in the ground image includes:

[0039] Extract lane edge lines from a ground image; cluster the lane edge lines to obtain at least one cluster; cluster each cluster separately to obtain a target lane edge line corresponding to each cluster; determine the lane line based on the target lane edge line and an endpoint of the target lane edge line.

[0040] Among them, based on the acquired ground image, the edge lines with gradient values ​​greater than the preset gradient threshold in the ground image are extracted through first-order gradient detection and / or second-order gradient detection according to the brightness of each pixel in the ground image, and the lane edge lines are obtained. Figure 2 , which shows a schematic diagram of lane edge line extraction. Figure 2 The dotted lines 1-12 in the figure are the extracted lane edge lines.

[0041] It should be noted that the lane edge line can be directly obtained by using the first-order gradient detection, or the edge line can be first obtained by using the first-order gradient detection, and then the edge line obtained by the first-order gradient detection can be corrected by using the second gradient detection to obtain a more accurate lane edge line.

[0042] For the extracted lane edge lines, the DBSCAN clustering algorithm is used to cluster all the extracted lane edge lines to obtain at least one clustering cluster to eliminate abnormal edge lines, and then for any clustering cluster, the lane edge lines in the clustering cluster are analyzed and processed to obtain the target lane edge lines in the clustering cluster. Therefore, for any target lane edge line, the distance between the target lane edge line and other target lane edge lines is calculated respectively, and another target lane line corresponding to the minimum distance is obtained. It is worth noting that the lane line includes two edge lines, each edge line has two endpoints, and the two edge lines and the corresponding four endpoints can construct a lane line. Then, according to the target lane edge line and the endpoint of another target lane line corresponding to the minimum distance, the lane line is constructed. Similarly, all target lane lines are traversed, and all lane lines in the ground image are confirmed according to the endpoints of all target lane lines. Reference Figure 3 , which shows a schematic diagram of lane line extraction. Figure 3 The dotted line in is the lane edge line, and the area 31 between the two lane edge lines is the lane line. The DBSCAN clustering algorithm is used to filter out the edge lines that are too short and too long that conform to the actual lane line conditions, thereby ensuring the accuracy of lane line extraction.

[0043] Optionally, each cluster is clustered separately to obtain the target lane edge line corresponding to each cluster, including:

[0044] For any cluster, calculate the distance between any two lane edge lines;

[0045] For any distance, whether the distance is less than a preset distance threshold is detected. If the distance is detected to be less than the preset distance threshold, the two lane edge lines corresponding to the distance are used as the first lane edge lines;

[0046] All first lane edge lines in the cluster are obtained, the length of each first lane edge line in the cluster is calculated respectively, and according to the length, a first lane edge line in the cluster is selected as the target lane edge line.

[0047] Among them, for all lane edge lines in any cluster, the distance between any two lane edge lines is calculated respectively, and for any distance, whether the distance is less than a preset distance threshold is detected. If it is detected that the distance is less than the preset distance threshold, it means that the detected lane edge line may be mis-segmented and misplaced accordingly, and then the two lane edge lines corresponding to the distance less than the preset distance threshold are taken as the first lane edge lines. According to the distance between the two lane edge lines, all the first lane edge lines in the cluster are obtained, and the length of each first lane edge line is calculated respectively. The absolute value of the difference between the length of the first lane edge line and the preset length threshold is calculated, and the first lane edge line with the smallest absolute value of the difference is taken as the target lane edge line.

[0048] Optionally, after extracting the lane lines in the ground image, the following steps are included:

[0049] For any lane line, the edge parallel score and edge distance score of the lane line are obtained, and the lane line confidence of the lane line is calculated based on the edge parallel score and the edge distance score.

[0050] Among them, the edge parallel score and edge distance score of the lane line can be calculated based on the numerical attributes of the lane line. Specifically, the present invention can train two lightweight calculation models, and the information input models can respectively obtain calculation results. Therefore, the trained edge parallel score calculation model and the trained edge distance score calculation model are obtained, and the geometric information of the lane line is obtained, wherein the geometric information includes but is not limited to the direction, length, intersection, brightness mean and brightness variance of the polygonal area corresponding to the lane line of the two lane lines. The geometric information of the lane line is respectively input into the trained edge parallel score calculation model and the trained edge distance score calculation model, and the edge parallel score and edge distance score are correspondingly obtained, wherein the parameters in the edge parallel score calculation model and the edge distance score calculation model are obtained through rule models and learnable machine learning methods. Reference Figure 4 , which shows a schematic diagram of the correlation between the lane line edge line spacing and the lane line confidence. Based on the correlation, for any lane line, the product between the edge parallel score and the edge distance score corresponding to the lane line is calculated, and the product is used as the lane line confidence of the lane line. The calculation expression of the lane line confidence is:

[0051] P lane =P parallel ×P distance

[0052] Among them, P lane is the lane line confidence, the value range of the lane line confidence is [0, 1], P parallel is the edge parallel score, P distance is the edge distance score.

[0053] Optionally, at least one corner point is obtained according to the geometric information of the lane line, including:

[0054] Any two lane lines are selected as target lane lines. Based on the positions of the target lane lines, whether the target lane lines intersect is detected. If the target lane lines intersect, the intersection point between the target lane lines is taken as the corner point.

[0055] Among them, for the detected lane lines, any two lane lines are selected as target lane lines, and according to the positions of the target lane lines, it is detected whether the target lane lines intersect. If the two target lane lines intersect, it means that there is an intersection between the two target lane lines, and then the intersection between the target lane lines is taken as a corner point. On the contrary, if the two target lane lines do not intersect, they do not constitute an intersection, and there is no corner point between the two target lane lines. Similarly, all lane lines are traversed to obtain all corner points.

[0056] Step S102: determining a parking space corner point representing the parking space from all corner points.

[0057] The parking space corner point is the intersection of the parking space lines that constitute the parking space. In the embodiment of the present invention, the parking space corner point includes five preset corner point types, namely T-type, I-type, U-type, L-type and Y-type, see Figure 5 , which shows a schematic diagram of parking angle detection. Figure 5 The corner point 51 in FIG. 5 is a detected corner point of an L-shaped parking space, and then the parking space corner point that can represent the parking space is identified from all the corner points to improve the accuracy of subsequent parking space detection.

[0058] Optionally, a parking space corner point representing the parking space is determined from all corner points, including:

[0059] For any corner point, obtain the lane line corresponding to the corner point, and calculate the corner point confidence corresponding to the corner point based on the geometric information of the lane line corresponding to the corner point;

[0060] If the detected corner point confidence is not less than a preset corner point confidence threshold, the corresponding corner point is confirmed to be a parking space corner point.

[0061] Among them, two lane lines can constitute a corner point. For any corner point, the two lane lines corresponding to the corner point are obtained, and the corner point confidence corresponding to the corner point is calculated according to the geometric information of the two lane lines corresponding to the corner point, which is used to characterize the probability that the corner point belongs to various types of parking corner points in the parking space, and then detect whether the corner point confidence is less than the preset corner point confidence threshold. If the corner point confidence is less than the preset corner point confidence threshold, it means that the corresponding corner point does not belong to the parking space corner point and the parking space cannot be constructed, then there is no need to identify the corner point. If the corner point confidence is not less than the preset corner point confidence threshold, it means that the corresponding corner point belongs to any one of the preset corner point types of parking space corner points and can characterize the parking space. Therefore, the corner point corresponding to the corner point confidence not less than the preset corner point confidence threshold is confirmed as the parking space corner point that can characterize the parking space, thereby improving the accuracy of parking space corner point detection.

[0062] Optionally, the corner point confidence corresponding to the corner point is calculated according to the geometric information of the lane line corresponding to the corner point, including:

[0063] Get the direction and length of each lane line respectively, construct the polygonal area of ​​each lane line, get the brightness mean and brightness variance of the polygonal area, and the detection value of whether two lane lines intersect;

[0064] According to the direction, length, brightness mean, brightness variance and detection value, the confidence level of the corner point type corresponding to each preset corner point type is obtained;

[0065] Get the intersection score and angle score between two lane lines, and get the corner point confidence of the corner point based on the corner point type confidence, intersection score and angle score.

[0066] Among them, according to the two lane lines corresponding to the corner point, the direction and length of each lane line are obtained respectively. Since the lane line is composed of two edge lines, the two edge lines of the lane line are connected to obtain the polygonal area of ​​the lane line, and then the brightness mean and brightness variance of the polygonal area corresponding to each lane line are obtained. At the same time, the detection value of whether the two lane lines intersect is detected, and the detection value corresponding to the intersection between the two lane lines is set to 1. Conversely, the detection value corresponding to the non-intersection between the two lane lines is set to 0. The direction, length, brightness mean, brightness variance and detection value are combined into a feature vector of the two lane lines. The feature vector is used as the input of the parking space corner point type determiner, and the corresponding output belongs to each preset corner point type corresponding to the corner point type confidence, which is used to characterize the probability that the corner point belongs to each corner point type.

[0067] At the same time, the intersection score and angle score between the two lane lines are obtained, where the intersection score and angle score are obtained in the same way as the edge parallel score and edge distance score, that is, the intersection score and angle score are obtained through the corresponding trained calculation models, and the calculation model is also obtained through the rule model and the learnable machine learning method. Combining the corner point type confidence, intersection score and angle score, the corner point confidence is obtained, and the calculation expression of the corner point confidence is:

[0068] P mp =P type ×P corss ×P angle

[0069] Among them, P mp is the corner point confidence, the value range of the corner point confidence is [0, 1], P type is the corner type confidence, P corss is the intersection score, P angle is the angle fraction.

[0070] Step S103, determining parking space information according to the parking space corner points and lane lines.

[0071] The parking space information may refer to information that can characterize the specific location of the parking space. The present invention detects parking space corner points and lane lines in the ground image to confirm the parking space information.

[0072] Optionally, the parking space information is determined based on the parking space corner points and lane lines, including:

[0073] Obtaining corner point information of all parking space corner points and geometric information of all lane lines, and constructing at least one parking space according to the corner point information of all parking space corner points and geometric information of all lane lines;

[0074] For any parking space, the parking position reliability of the parking space is calculated based on the corner point information of the parking space corner point corresponding to the parking space and the geometric information of the lane line;

[0075] The parking space corresponding to the vehicle position confidence level not less than a preset vehicle position confidence level threshold is obtained as the target parking space, and the parking space information of the target parking space is confirmed.

[0076] Among them, the present invention can train a lightweight detection model, and the information input model can be sent to the corresponding parking space. Specifically, since the important features of a parking space are lane lines and parking corner points, and an ideal parking space is composed of four parking corner points and four lane lines, and the four lane lines include the entrance line of the parking space, two left and right dividing lines, and the bottom boundary line, the corner point information of all parking corner points detected in the ground image and the geometric information of all lane lines are used as inputs of the detection model, and the detection model is trained to obtain a trained detection model, so that the corner point information of all parking corner points and the geometric information of all lane lines are input into the trained detection model, and at least one parking space is output correspondingly.

[0077] Since lane lines and parking corner points are the key to parking spaces, for any parking space, the parking position reliability of the parking space is calculated based on the corner point information of the parking corner points corresponding to the parking space and the geometric information of the lane lines, where the corner point information includes but is not limited to: the corner point type of the parking space corner points, the center coordinates between the parking space corner points, and the geometric position of the lane lines includes but is not limited to: the angle between the lane lines and the entrance lines, the polygon area formed by the lane lines, the distance between the lane lines, and the angle difference between the lane lines and the horizontal line.

[0078] Check whether the obtained vehicle position reliability is less than the preset vehicle position reliability threshold. If the vehicle position reliability is less than the preset vehicle position reliability threshold, it means that the corresponding constructed parking space cannot correspond to the actual parking space, and the parking space corner point of the corresponding parking space will not be recognized. On the contrary, if the vehicle position reliability is not less than the preset vehicle position reliability threshold, it means that the corresponding constructed parking space can correspond to the actual parking space. Therefore, the parking space corresponding to the vehicle position reliability not less than the preset vehicle position reliability threshold is the target parking space, and then according to the position of the target parking space in the ground image, the parking space information corresponding to the target parking space can be obtained, thereby improving the accuracy of parking space detection.

[0079] Optionally, the parking position reliability of the parking space is calculated according to the corner point information of the parking space corner point corresponding to the parking space and the geometric information of the lane line, including:

[0080] The parking space shape score of the parking space is calculated based on the corner point information of the parking space corner points corresponding to the parking space and the geometric information of the lane line. The corner point distance score of the parking space is calculated based on the corner point information of the parking space corner points corresponding to the parking space. The lane line confidence of the parking space is calculated based on the geometric information of the lane line of the parking space.

[0081] The parking position confidence of the parking space is calculated according to the parking space shape score, corner point distance score, corner point type confidence and lane line confidence of the parking space.

[0082] Among them, the present invention can train two score calculation models of different magnitudes, and the corresponding scores can be obtained by inputting information into the score calculation model. Therefore, the trained corner point distance score calculation model and the parking space morphology score calculation model are obtained, and the corner point type of the parking space corner point in the parking space and the center coordinates between any two parking space corner points are used as the input of the corner point distance score calculation model, and the corner point distance score of the parking space is output accordingly; similarly, the lane line in the parking space includes an entrance line, two left and right dividing lines, and a bottom boundary line, then the angle between the dividing line in the parking space and the entrance line is obtained, the polygon area corresponding to the parking space is obtained, and the distance between the left and right dividing lines is obtained, which can characterize the width of the parking space and the angle difference between the two dividing lines and the horizontal line, and then the angle, polygon area, distance, and angle difference are used as the morphological features of the parking space, and the morphological features are used as the input of the parking space morphology score calculation model, and the parking space morphology score of the parking space is output accordingly.

[0083] Calculate the product of the parking space shape score, corner point distance score, corner point type confidence and lane line confidence, and confirm that the product is the vehicle position confidence of the parking space. The calculation expression of the vehicle position confidence is:

[0084] P slot =P type ×P sp ×P sd ×P morph

[0085] Among them, P slot is the vehicle position reliability, the value range of the vehicle position reliability is [0,1], P type is the corner type confidence, P sp is the lane line confidence of the lane line, P sd is the corner distance score, P morph is the parking space shape score.

[0086] It should be noted that the lane line confidence of the lane line is obtained in step S101.

[0087] Optionally, the parking space information includes a first parking space coordinate of the parking space in the image coordinate system, and the parking space detection method further includes:

[0088] According to a conversion relationship between an image coordinate system of the ground image and a world coordinate system, the first parking space coordinates are converted into second parking space coordinates of the parking space in the world coordinate system.

[0089] The first parking space coordinates may refer to information that can characterize the specific position of the parking space in the ground image, and the first parking space coordinates include but are not limited to: the two-dimensional coordinates of the entrance line, the two-dimensional coordinates of the lane dividing line, and the two-dimensional coordinates of the parking space entrance corner point.

[0090] In the embodiment of the present invention, the first parking space coordinates of the parking space are obtained according to the position of the parking space in the ground image. It should be noted that, for the entrance line, the entrance line can be obtained by the coordinates of the front parking space corner point of the parking space. Then, the image coordinate system is transformed into the world coordinate system through a formula to obtain the real position of the parking space, that is, the second parking space coordinates. Then, according to the conversion relationship between the image coordinate system of the ground image and the world coordinate system, the first parking space coordinates of each parking space are transformed into a coordinate system to obtain the second parking space coordinates corresponding to each parking space, wherein the conversion formula is:

[0091]

[0092] Among them, (X w ,Y w ,Z w ) represents the coordinates of the world coordinate system, (x, y) represents the coordinates of the image coordinate system of the bird's-eye view image, Z represents the height of the camera relative to the ground, R represents rotation, and M represents the transformation matrix, where the specific parameters of the transformation matrix can be obtained through methods such as camera parameter calibration.

[0093] In summary, the embodiments of the present invention acquire a ground image and extract lane lines in the ground image; obtain at least one corner point based on the geometric information of the lane lines, wherein the corner point is an intersection point formed by the intersection of the lane lines; determine the parking space corner point representing the parking space from all the corner points; determine the parking space information based on the parking space corner point and the lane lines, thereby realizing real-time parking space detection on a low computing power platform and improving the efficiency and accuracy of parking space detection.

[0094] See also Figure 6 , which shows a structural block diagram of a vehicle provided in the second embodiment of the present invention, the vehicle includes an image collector 61 and a controller 62, the controller 62 is connected to the image collector 61, the image collector 61 is used to collect images, the controller 62 includes a processor, a memory, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the steps of the parking space detection method in the first embodiment are implemented.

[0095] For a detailed description of the controller, see the explanation of Embodiment 3 below. The parking space detection method comprises: acquiring a ground image, extracting lane lines in the ground image; obtaining at least one corner point based on geometric information of the lane lines, wherein the corner point is a point formed by the intersection of the lane lines; determining a parking space corner point representing a parking space from all corner points; and determining parking space information based on the parking space corner point and the lane lines.

[0096] Figure 7 This is a schematic diagram of the structure of a controller provided in Embodiment 3 of the present invention. Figure 7 As shown, the controller of this embodiment includes: at least one processor ( Figure 7Only one is shown in the figure), a memory, and a computer program stored in the memory and executable on at least one processor, and when the processor executes the computer program, the steps in any of the above-mentioned parking space detection method embodiments are implemented.

[0097] The controller may include, but is not limited to, a processor and a memory. A person skilled in the art will understand that Figure 7 This is merely an example of a controller and does not constitute a limitation of the controller. The controller may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, it may also include a network interface, a display screen, and an input device.

[0098] The processor may be a CPU, or other general-purpose processors, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0099] The memory includes a readable storage medium, an internal memory, etc., wherein the internal memory may be the memory of the controller, and the internal memory provides an environment for the operation of the operating system and the computer-readable instructions in the readable storage medium. The readable storage medium may be the hard disk of the controller, and in other embodiments, it may also be an external storage device of the controller, for example, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the controller. Further, the memory may also include both an internal storage unit of the controller and an external storage device. The memory is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of a computer program, etc. The memory may also be used to temporarily store data that has been output or is to be output.

[0100] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention. The specific working process of the units and modules in the above-mentioned device can refer to the corresponding process in the above-mentioned method embodiment, which will not be repeated here. If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned method embodiment can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device capable of carrying computer program code, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0101] The present invention implements all or part of the processes in the above-mentioned method embodiment, and can also be completed by a computer program product. When the computer program product runs on a controller, the controller can implement the steps in the above-mentioned method embodiment when executing.

[0102] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0103] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0104] In the embodiments provided by the present invention, it should be understood that the disclosed devices / controllers and methods can be implemented in other ways. For example, the device / controller embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0105] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0106] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A parking space detection method, It is characterized in that The parking space detection method comprises: Acquire a ground image, and extract lane lines in the ground image; Obtain at least one corner point according to the geometric information of the lane lines, wherein the corner point is a point formed by the intersection of the lane lines; Determine a parking space corner point representing the parking space from all corner points; Parking space information is determined according to the parking space corner point and the lane line.

2. The parking space detection method according to claim 1, It is characterized in that The parking space information includes a first parking space coordinate of the parking space in the image coordinate system, and the parking space detection method further includes: According to a conversion relationship between an image coordinate system of the ground image and a world coordinate system, the first parking space coordinates are converted into second parking space coordinates of the parking space in the world coordinate system.

3. The parking space detection method according to claim 1, It is characterized in that The extracting lane lines in the ground image includes: Extract lane edge lines in the ground image; cluster the lane edge lines to obtain at least one cluster; cluster each cluster separately to obtain a target lane edge line corresponding to each cluster; determine the lane line based on the target lane edge line and the endpoint of the target lane edge line.

4. The parking space detection method according to claim 3, It is characterized in that The step of clustering each cluster to obtain the target lane edge line corresponding to each cluster includes: For any cluster, respectively calculate the distance between any two lane edge lines; For any distance, detecting whether the distance is less than a preset distance threshold, if it is detected that the distance is less than the preset distance threshold, taking the two lane edge lines corresponding to the distance as the first lane edge lines; All first lane edge lines in the cluster are obtained, the length of each first lane edge line in the cluster is calculated respectively, and according to the length, one of the first lane edge lines in the cluster is selected as the target lane edge line.

5. The parking space detection method according to claim 1, It is characterized in that After extracting the lane lines in the ground image, the method includes: For any lane line, an edge parallel score and an edge distance score of the lane line are obtained, and a lane line confidence of the lane line is calculated based on the edge parallel score and the edge distance score.

6. The parking space detection method according to claim 1, It is characterized in that The obtaining at least one corner point according to the geometric information of the lane line includes: Any two of the lane lines are selected as target lane lines, and based on the positions of the target lane lines, whether the target lane lines intersect is detected, and if it is detected that the target lane lines intersect, the intersection point between the target lane lines is used as a corner point.

7. The parking space detection method according to claim 1, It is characterized in that The step of determining a parking space corner point representing the parking space from all corner points includes: For any corner point, obtain the lane line corresponding to the corner point, and calculate the corner point confidence corresponding to the corner point according to the geometric information of the lane line corresponding to the corner point; If it is detected that the corner point confidence is not less than a preset corner point confidence threshold, the corresponding corner point is confirmed to be a parking space corner point.

8. The parking space detection method according to claim 7, It is characterized in that The calculating the corner point confidence corresponding to the corner point according to the geometric information of the lane line corresponding to the corner point includes: respectively obtaining the direction and length of each lane line, constructing a polygonal area of ​​each lane line, obtaining a brightness mean and brightness variance of the polygonal area, and a detection value for detecting whether two lane lines intersect; Obtaining, according to the direction, the length, the brightness mean, the brightness variance and the detection value, a corner point type confidence corresponding to each preset corner point type that the corner point belongs to; The intersection score and the angle score between the two lane lines are obtained, and the corner point confidence of the corner point is obtained according to the corner point type confidence, the intersection score and the angle score.

9. The parking space detection method according to claim 8, It is characterized in that Determining parking space information according to the parking space corner point and the lane line includes: Obtaining corner point information of all parking space corner points and geometric information of all lane lines, and constructing at least one parking space according to the corner point information of all parking space corner points and geometric information of all lane lines; For any parking space, the parking position reliability of the parking space is calculated according to the corner point information of the parking space corner point corresponding to the parking space and the geometric information of the lane line; A parking space corresponding to a vehicle position reliability that is not less than a preset vehicle position reliability threshold is acquired as a target parking space, and parking space information of the target parking space is determined.

10. The parking space detection method according to claim 9, It is characterized in that The calculating the parking position reliability of the parking space according to the corner point information of the parking space corner point corresponding to the parking space and the geometric information of the lane line includes: Calculate the parking space shape score of the parking space according to the corner point information of the parking space corner point corresponding to the parking space and the geometric information of the lane line; calculate the corner point distance score of the parking space according to the corner point information of the parking space corner point corresponding to the parking space; and calculate the lane line confidence of the parking space according to the geometric information of the lane line of the parking space; The parking position confidence of the parking space is calculated according to the parking space shape score, the corner point distance score, the corner point type confidence and the lane line confidence of the parking space.

11. A controller, It is characterized in that The controller includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the parking space detection method according to any one of claims 1 to 10 is implemented.

12. A vehicle, It is characterized in that The vehicle comprises an image collector and the controller as claimed in claim 11, wherein the image collector is used to collect images.

13. A computer-readable storage medium storing a computer program. It is characterized in that When the computer program is executed by a processor, the parking space detection method according to any one of claims 1 to 10 is implemented.

Images