Method, device and equipment for judging berthability of ramp parking space

Abstract

The invention discloses a method, a device and equipment for judging the berthability of a ramp parking space, and relates to the technical field of intelligent driving. Acquiring a ramp image, and preprocessing the ramp image to obtain a target parking space; extracting parameter information and image information of the target parking space; determining the gradient of the target parking space according to the gradient of the vehicle and the parameter information of the target parking space; detecting the target parking space according to the image information of the target parking space to obtain a parking space availability detection result; and judging whether the target parking space can be parked or not according to the gradient of the target parking space and the parking space availability detection result. And based on the gradient of the target parking space and the parking space availability detection result, whether the target parking space can be parked or not is judged, and the efficiency and accuracy of the ramp parking space berthability judgment method are improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent driving technology, and in particular to a method, device and equipment for determining the parking availability of a ramp parking space. Background Art

[0002] In the current era of rapid technological development, intelligent driving technology is booming at an unprecedented speed. Valet parking technology, as an important application in the field of intelligent driving, is gradually becoming a key factor in improving travel convenience and user experience. This technology can greatly save drivers' time and energy, and bring people a more comfortable and high-quality experience. In the process of enjoying valet parking services, whether the vehicle can accurately identify and park in a parking space under various complex and changing environmental conditions is an important yardstick for measuring the maturity and practicality of the technology.

[0003] However, although valet parking technology has made significant progress, existing technical solutions still face challenges when faced with specific scenarios, such as parking space recognition on ramps, and lack an efficient and accurate recognition method. Summary of the invention

[0004] The main purpose of the present application is to provide a method, device and equipment for determining the parking availability of a ramp parking space, aiming to solve the technical problem that the existing ramp parking availability determination scheme cannot guarantee both high efficiency and accuracy.

[0005] To achieve the above purpose, the present application proposes a method for determining the parking availability of a ramp parking space, the method comprising:

[0006] Get the vehicle's own slope;

[0007] Acquire a ramp image, and pre-process the ramp image to obtain a target parking space;

[0008] Extract parameter information and image information of the target parking space;

[0009] Determining the slope of the target parking space according to the vehicle's own slope and parameter information of the target parking space;

[0010] Detecting the target parking space according to the image information of the target parking space to obtain a parking space availability detection result;

[0011] Whether the target parking space is available is determined according to the slope of the target parking space and the parking space availability detection result.

[0012] In one embodiment, the step of obtaining the vehicle's own slope includes:

[0013] Obtain the vehicle's left and right acceleration, vertical acceleration and pitch angular velocity;

[0014] Obtaining the vehicle's own pitch angle according to the left-right acceleration and the vertical acceleration;

[0015] Setting a weight coefficient and a time constant, and obtaining a time interval according to the weight coefficient and the time constant;

[0016] Obtaining a filtered pitch angle according to the pitch angle of the vehicle itself, the pitch angle velocity, the weight coefficient and the time interval;

[0017] Obtaining the vehicle's own slope angle according to the filtered pitch angle;

[0018] The vehicle's own slope is determined according to the vehicle's own slope angle.

[0019] In one embodiment, the parameter information of the target parking space includes at least the front height of the parking space, the rear height of the parking space, and the length of the parking space;

[0020] The step of determining the slope of the target parking space according to the vehicle's own slope and the parameter information of the target parking space comprises:

[0021] Obtaining a target parking space pitch angle according to the parking space front height, the parking space rear height and the parking space length;

[0022] Obtaining a target parking space slope angle according to the target parking space pitch angle and the vehicle's own slope angle;

[0023] The slope of the target parking space is determined according to the target parking space slope angle.

[0024] In one embodiment, the step of acquiring a ramp image and preprocessing the ramp image to obtain a target parking space includes:

[0025] Acquire a ramp image, and perform corner point detection on the ramp image to obtain position information of corner points after corner point detection;

[0026] Performing edge detection on the ramp image to obtain edge lines after edge detection;

[0027] The target parking space is obtained through the position information of the corner points and the edge line.

[0028] In one embodiment, the step of performing corner point detection on the ramp image to obtain position information of corner points after corner point detection includes:

[0029] Acquire the horizontal gradient and the vertical gradient of the ramp image, and obtain the autocorrelation matrix of pixels according to the horizontal gradient and the vertical gradient;

[0030] Defining empirical constants, and obtaining the determinant and the sum of diagonal elements of the autocorrelation matrix;

[0031] Obtaining a calculation response function according to the empirical constant, the determinant of the autocorrelation matrix and the sum of the diagonal elements;

[0032] Obtaining the response value of each corner point according to the calculation response function;

[0033] If the response value of the corner point is greater than a preset response value threshold, the corner point is retained and the position information of the corner point is obtained.

[0034] In one embodiment, the step of performing edge detection on the ramp image to obtain edge lines comprises:

[0035] Performing denoising processing on the ramp image;

[0036] Obtaining the gradient strength of pixels in the horizontal and vertical directions in the denoised ramp image;

[0037] According to the gradient strength in the horizontal direction and the vertical direction of the pixel, the refined edge is retained by a non-maximum suppression technique;

[0038] performing double threshold detection on the thinned edge;

[0039] If the gradient intensity of the pixel corresponding to the thinned edge is greater than a first preset intensity threshold, marking the thinned edge as a strong edge;

[0040] If the gradient intensity of the pixel corresponding to the thinned edge is greater than the second preset intensity threshold and less than the first preset intensity threshold, marking the thinned edge as a weak edge;

[0041] retaining weak edges connected to the strong edges;

[0042] The edge line is obtained by connecting the weak edge connected to the strong edge and the strong edge.

[0043] In one embodiment, after the step of determining whether the target parking space is available for parking according to the slope of the target parking space and the parking space availability detection result, the method further includes:

[0044] Selecting a number of reference points according to the image information of the target parking space;

[0045] Obtaining a perspective transformation matrix, and applying the perspective transformation matrix to the image information of the target parking space so that the plurality of reference points are mapped to updated positions;

[0046] The image information after the mapping and updating of the reference points is obtained, and the image information after the mapping and updating of the reference points is displayed on the display interface.

[0047] In one embodiment, the step of detecting the target parking space according to the image information of the target parking space to obtain a parking space availability detection result includes:

[0048] Establishing a corresponding parking space geometric model according to the image information of the target parking space;

[0049] Applying an object detection algorithm to detect the parking space geometric model;

[0050] Obtaining a parking space availability detection result to determine whether the target parking space is occupied;

[0051] The step of judging whether the target parking space is available for parking according to the slope of the target parking space and the parking space availability detection result comprises:

[0052] If the slope of the target parking space is less than a preset slope threshold, and the parking space availability detection result determines that the target parking space is not occupied, then it is determined that the target parking space is available for parking.

[0053] In addition, to achieve the above-mentioned purpose, the present application also proposes a device for determining the parking availability of a ramp parking space, the device comprising:

[0054] An acquisition module is used to obtain the vehicle's own slope;

[0055] A processing module, used for acquiring a ramp image and preprocessing the ramp image to obtain a target parking space;

[0056] The acquisition module is also used to extract parameter information and image information of the target parking space;

[0057] The acquisition module is further used to determine the slope of the target parking space according to the vehicle's own slope and the parameter information of the target parking space;

[0058] A detection module, used to detect the target parking space according to the image information of the target parking space, and obtain a parking space availability detection result;

[0059] The judging module is used to judge whether the target parking space is available according to the slope of the target parking space and the parking space availability detection result.

[0060] In addition, to achieve the above-mentioned purpose, the present application also proposes a device for determining the parking availability of a ramp parking space, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the method for determining the parking availability of a ramp parking space as described above.

[0061] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the method for determining the parking availability of a ramp parking space as described above are implemented.

[0062] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the method for determining the parking availability of a ramp parking space as described above are implemented.

[0063] One or more technical solutions proposed in this application include obtaining the vehicle's own slope; obtaining a ramp image, and preprocessing the ramp image to obtain a target parking space; extracting parameter information and image information of the target parking space; determining the slope of the target parking space based on the vehicle's own slope and the parameter information of the target parking space; detecting the target parking space based on the image information of the target parking space to obtain a parking space availability detection result; and determining whether the target parking space is available for parking based on the slope of the target parking space and the parking space availability detection result. Whether the target parking space is available for parking is determined based on the slope of the target parking space and the parking space availability detection result, thereby improving the efficiency and accuracy of the method for determining the parking availability of a ramp parking space. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0065] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0066] Figure 1 A flow chart of Embodiment 1 of the method for determining the parking availability of a ramp parking space provided in the present application;

[0067] Figure 2 A brief schematic diagram of an implementation method provided in Example 1 of the method for determining the parking availability of a ramp parking space of the present application;

[0068] Figure 3 A flow chart of Embodiment 2 of the method for determining the parking availability of a ramp parking space provided in the present application;

[0069] Figure 4 This is a schematic diagram of the module structure of a device for determining the parking availability of a ramp parking space according to an embodiment of the present application;

[0070] Figure 5 Schematic diagram of the device structure of the hardware operating environment involved in the method for determining the parking availability of a ramp parking space in an embodiment of the present application.

[0071] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0072] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0073] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0074] The main solutions of the embodiments of this application are:

[0075] As intelligent driving technology is booming at an unprecedented rate, valet parking technology, as an important application in the field of intelligent driving, is gradually becoming a key factor in improving travel convenience and user experience. This technology can greatly save drivers' time and energy, bringing people a more comfortable and high-quality experience. In the process of enjoying valet parking services, whether the vehicle can accurately identify and park in a parking space under various complex and changing environmental conditions is an important measure of the maturity and practicality of the technology. However, although valet parking technology has made significant progress, when faced with specific scenarios, such as parking space identification on ramps, existing technical solutions still face challenges and lack an efficient and accurate identification method.

[0076] The present application provides a solution to determine whether a target parking space is available for parking based on the slope of the target parking space and the parking space availability detection result, thereby improving the efficiency and accuracy of the method for determining the parking availability of a sloped parking space.

[0077] It should be noted that the execution subject of this embodiment may be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a ramp parking space parking availability judgment device, etc. The following takes the ramp parking space parking availability judgment device as an example to illustrate this embodiment and the following embodiments.

[0078] Based on this, the embodiment of the present application provides a method for determining the parking availability of a ramp parking space, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the method for determining the parking availability of a ramp parking space of the present application.

[0079] In this embodiment, the method for determining whether a ramp parking space is parkable includes steps S10 to S60:

[0080] Step S10: Obtain the vehicle's own slope.

[0081] It should be noted that the vehicle's own slope refers to the angle between the longitudinal direction (from the front to the rear) or the lateral direction (from left to right) of the vehicle body and the horizontal plane when the vehicle is stationary or moving. This angle can intuitively reflect the posture of the vehicle and is an important part of the vehicle posture parameters.

[0082] In this embodiment, the step of obtaining the vehicle's own slope includes obtaining the vehicle's own left and right acceleration a y , vertical acceleration a z and the pitch angular velocity ω x According to the left and right acceleration a y and the vertical acceleration a z , get the vehicle's own pitch angle θ; set the weight coefficient α and the time constant τ, and get the time interval d according to the weight coefficient α and the time constant τ t According to the vehicle's own pitch angle θ, the pitch angular velocity ω x , the weight coefficient α and the time interval d t , get the filtered pitch angle θ filtered ; According to the filtered pitch angle θ filtered Get the vehicle's own slope angle θ slope ; According to the vehicle's own slope angle θ slope Determine the vehicle's own slope Slope (%).

[0083] Left-right acceleration usually refers to the speed of the vehicle's speed change in the left-right direction on the horizontal plane (usually with the vehicle's forward direction as a reference, perpendicular to the left and right sides of the forward direction). Acceleration is a vector, which has both magnitude and direction. In the case of left-right acceleration, the direction points to the left or right side of the vehicle, and the magnitude indicates the change in speed per unit time in this direction.

[0084] Vertical acceleration usually refers to the speed of an object's velocity change in the direction perpendicular to the ground (or reference plane). In common scenarios, such as vehicle driving or object movement, vertical acceleration is mainly used to describe the dynamic characteristics of an object in the up and down directions. Acceleration is a vector. The direction of vertical acceleration can be upward or downward, and its magnitude represents the change in vertical velocity per unit time.

[0085] Pitch angular velocity is usually a physical quantity that describes the speed of an object's rotation around a horizontal axis (usually the axis connecting the left and right sides of the object). It is widely used in aerospace, ship navigation, and vehicle engineering. It is a vector whose direction follows the right-hand screw rule. Its magnitude represents the change in the pitch angle of the object (the angle between the object's longitudinal axis and the horizontal plane) per unit time, and the unit is generally radians per second (rad / s).

[0086] The vehicle's pitch angle usually refers to the angle between the longitudinal axis of the vehicle (from the front to the rear) and the horizontal plane, which is used to describe the vehicle's posture in the vertical plane. This angle is an important parameter for measuring changes in the vehicle's body posture and has important applications in many fields such as vehicle dynamics and autonomous driving. The filtered pitch angle is the pitch angle that has been improved in accuracy by the complementary filtering algorithm.

[0087] Weight coefficients refer to the numerical values ​​assigned to different data points (or signal samples) participating in the filtering calculation in the filtering algorithm. These coefficients are used to determine the relative importance of each data point in the final filtering result.

[0088] The time constant is a parameter used to describe the dynamic characteristics of the filtering process. The definition and calculation of the time constant may be different for different types of filters. In a first-order low-pass filter, the time constant is a key parameter that determines the filter's response speed to changes in the input signal.

[0089] The time interval refers to the time difference between two adjacent sampling or processing of the signal in the filtering algorithm. In digital filtering, the signal is discrete, and the signal samples are obtained through a certain sampling frequency. The time interval between two adjacent samples is the sampling time interval. For example, if the sampling frequency is 100Hz, then the time interval is 1 / 100 = 0.01 seconds.

[0090] In addition, the vehicle's own slope angle refers to the angle formed by the longitudinal (front to rear) or transverse (left to right) center axis of the vehicle body and the horizontal plane. This angle is a key parameter for describing the vehicle's posture and is used to measure the degree of inclination of the vehicle in a vertical or horizontal plane relative to a horizontal reference.

[0091] In addition, the vehicle's own slope usually refers to the inclination of the slope where the vehicle is located. It can be expressed as the ratio of the vertical height of the slope to the horizontal distance. This is a dimensionless quantity, usually expressed as a percentage or angle. For example, if the vertical height of a slope is 1 meter and the horizontal distance is 10 meters, then the slope of the slope can be expressed as 10%.

[0092] Specifically, a can be obtained through the vehicle's accelerometer y (left-right acceleration) and a z (vertical acceleration), and obtain ω through the gyroscope x (pitch angular velocity), and the vehicle's own pitch angle θ is obtained by the calculation method shown in the following formula 1:

[0093]

[0094] Define θ filtered is the pitch angle after filtering, and the weight coefficient α (such as 0.98) and time constant τ in the filtering algorithm are set by the user, and the time interval d is calculated by the equation shown in the following equation 2 t :

[0095]

[0096] In obtaining the time interval d t Then, the filtered pitch angle θ is calculated by the equation shown in the following formula 3 filtered :

[0097] θ filtered =α(θ filtered +ω x *d t )+(1-α)*θ (Formula 3)

[0098] After filtering, the pitch angle θ is obtained. filtered After that, the filtered pitch angle θ can be used filtered Indicates the vehicle's own slope angle θ slope , as shown in Equation 4 below:

[0099] θ slope =θ filtered (Formula 4)

[0100] After obtaining the vehicle's own slope angle θ slope , the vehicle's own slope Slope (%) can be determined by the method shown in the following formula 5:

[0101] Slope(%)=tan(θ slope )*100 (Formula 5)

[0102] For example: if the vertical height of a slope is 1 meter and the horizontal distance is 10 meters, then the slope of the slope can be expressed as 10%, and the slope angle is about 5.71 degrees.

[0103] Step S20: Acquire a ramp image, and pre-process the ramp image to obtain a target parking space.

[0104] It should be noted that ramp images usually refer to images or videos with color information acquired by the vehicle's own on-board camera in a ramp scene. These images record the appearance characteristics of the ramp, including the surface texture, color, shape of the ramp, and the environmental information around the ramp, such as surrounding buildings, vegetation, signs, etc. At the same time, it can also capture dynamic elements such as vehicles driving on the ramp and people walking.

[0105] The target parking space refers to a specific parking space in a parking lot, parking garage, etc., where the driver of the vehicle expects to park the vehicle. In the present application, it is a specific parking space where the vehicle can be parked on the ramp through intelligent recognition.

[0106] The steps of preprocessing the ramp image usually include converting the color image into a grayscale image, denoising, corner detection, and edge detection.

[0107] It is understandable that color images contain information of three channels: red, green, and blue, and the amount of data is relatively large. After converting it to a grayscale image, each pixel only needs to be represented by a grayscale value, and the amount of data is reduced. In the subsequent image processing process, such as corner detection, edge detection and other operations, the computational complexity will be reduced and the processing speed will be accelerated.

[0108] Denoising can make images clearer and restore the original details and features of the image. For example, if a landscape photo has a lot of noise, it will affect the audience's appreciation of the landscape details (such as the texture of leaves and the shape of clouds). Denoising can improve the visual effect of the image. Usually, Gaussian blur can be used for denoising.

[0109] A corner point is a special local feature in an image. It is the intersection of two edges or a point where the direction changes dramatically in a local area. Intuitively, a corner point appears in an image as a corner of an object, a turning point of a boundary, and other locations. For example, in an image of a building, the corners of the building and the corners of the windows are corner points. Corner point detection can help find corresponding feature points in different images. By matching these corner points, the transformation relationship between images is calculated to achieve seamless stitching. For example, when identifying parking spaces, the corner points in adjacent photos are detected, and these corner points are used to align the photos to generate a complete panoramic view of the parking space.

[0110] Edges are areas in an image where pixel values ​​change dramatically, marking the boundaries between different objects or areas. This change can be reflected in grayscale values, colors, textures, and other aspects. For example, in a black-and-white image, the transition from a black area to a white area is an edge; in a color image, the boundary between different color areas is also an edge. Through edge detection, a shape model of an object can be constructed to identify and classify different objects. For example, in parking space recognition, edge detection is used to identify the outline of the parking space and thus determine the target parking space.

[0111] Step S30: extracting parameter information and image information of the target parking space.

[0112] It should be noted that the parameter information of the target parking space at least includes the front height of the parking space, the rear height of the parking space and the length of the parking space. In addition, the front height of the parking space refers to the vertical distance from the ground to the obstacles above the parking space (such as the ceiling of the parking garage, awnings, etc.) or to the boundary of the space to which the parking space belongs (such as the bottom of the upper parking space of the three-dimensional parking garage) at the front position of the parking space (usually the end facing the front of the vehicle). This height is very important for judging whether the vehicle can smoothly enter the parking space and whether there is enough space for the front part of the vehicle after parking.

[0113] The rear height of the parking space refers to the vertical distance from the ground to the obstacle or space boundary above the parking space at the rear end of the parking space (the end facing the rear of the vehicle). It is mainly used to evaluate whether there is enough space at the rear of the vehicle when reversing into the parking space, and whether the vehicle can avoid collision with the obstacles above.

[0114] The length of a parking space refers to the size of the parking space in the parking direction of the vehicle. It is the distance from the front end of the parking space (the direction of the front of the vehicle entering) to the rear end (the direction of the rear of the vehicle). The length of a parking space is one of the key factors to measure whether a parking space can accommodate vehicles. Its length needs to meet the normal parking needs of most vehicles.

[0115] The image of the target parking space can clearly show the overall shape of the target parking space, which is commonly a rectangle, parallelogram (in the diagonal parking area), etc. The image can be used to understand the specific layout of the parking spaces in the parking lot or garage, such as whether they are arranged in rows alone or in groups, and the relative position relationship with surrounding parking spaces, passages, walls, columns, etc. In addition, the boundaries of the target parking space are usually clearly presented in the image, which may be defined by lines on the ground (such as white or yellow solid lines, dotted lines, etc.). The clarity and integrity of these lines can be observed in the image, and they are crucial for accurately identifying the scope of the parking space. The image information of the target parking space is specific information that can reflect the image of the target parking space.

[0116] Step S40: determining the slope of the target parking space according to the vehicle's own slope and the parameter information of the target parking space.

[0117] It should be noted that, as described above, the parameter information of the target parking space at least includes the front height of the parking space, the rear height of the parking space, and the length of the parking space. These parameter information lays the foundation for subsequent steps, so it is necessary to obtain these parameter information.

[0118] Specifically, according to the front height h of the parking space front , the rear height of the parking space h rear and the parking space length d, the target parking space pitch angle θ is obtained p , as shown in Equation 6 below:

[0119]

[0120] And according to the pitch angle θ of the target parking space p and the vehicle's own slope angle θ slope , the target parking space slope angle β is obtained, as shown in the following formula 7:

[0121] β=|θ slope -θ p |(Formula 7)

[0122] Finally, the slope of the target parking space is determined according to the slope angle β of the target parking space. p (%), as shown in Formula 8 below:

[0123] Slope p (%) = tan(β)*100 (Formula 8)

[0124] When the slope of the target parking space is less than the preset slope threshold, it can be preliminarily determined that the slope of the target parking space is suitable for parking. It can be understood that the preset slope threshold is the slope threshold set by the user, which can usually be expressed by the upper limit of the parkable slope. The upper limit of the parkable slope refers to the maximum slope value at which the vehicle can be parked safely and stably in a parking space (including various types such as ground parking spaces, underground parking spaces, and multi-level parking spaces) or parking area.

[0125] Step S50: Detect the target parking space according to the image information of the target parking space to obtain a parking space availability detection result.

[0126] It should be noted that this detection usually refers to object detection of the target parking space. It can be understood that the target parking space is an area. In this application, the sensor can be used to directly perform object detection on the area to determine whether the target parking space is occupied by other vehicles or some objects.

[0127] This embodiment may also establish a corresponding parking space geometry model according to the image information of the target parking space; apply an object detection algorithm to detect the parking space geometry model; and obtain a parking space availability detection result to determine whether the target parking space is occupied.

[0128] Specifically, the image information includes at least position information and direction information. The four vertex coordinates are determined according to the position information and the direction information, and a rectangular parking space model or a parallelogram parking space model with four vertex coordinates is established. The object detection algorithm is applied to detect the rectangular parking space model or the parallelogram parking space model. It should be explained that the object detection algorithm can be a single shot multi-box detector (Single Shot MultiBox Detector, SSD), which is a deep learning algorithm for object detection. In addition, the purpose of the detection is to confirm whether other vehicles, animals, pedestrians or obstacles appear in the target parking space. If the detection result shows that no other vehicles, animals, pedestrians or obstacles appear in the target parking space, it is determined that the target parking space is not occupied, and the parking space is displayed as available; correspondingly, if the detection result shows that other vehicles, animals, pedestrians or obstacles appear in the target parking space, it is determined that the target parking space is occupied, and the parking space is displayed as unavailable.

[0129] Step S60: determining whether the target parking space is available according to the slope of the target parking space and the parking space availability detection result.

[0130] It should be noted that, in the present application, the determination of whether the target parking space is available is based on two criteria, namely, the slope of the target parking space and the parking space availability detection result; if the slope of the target parking space is less than the preset slope threshold and the parking space availability detection result determines that the target parking space is not occupied, then the target parking space is determined to be available for parking.

[0131] It can be understood that the parking space availability judgment based on the slope of the target parking space and the parking space availability detection result improves the accuracy of the slope parking space availability judgment method.

[0132] In a feasible implementation, reference may be made to Figure 2 , after step S60, steps A61 to A63 may also be included:

[0133] Step A61: Selecting a number of reference points according to the image information of the target parking space.

[0134] It should be noted that the integrity of the image information of the target parking space must be ensured first. The image information of the target parking space needs to clearly show the parking space and the surrounding environment, including adjacent parking spaces, passages, obstacles, etc.

[0135] In addition, when acquiring the image information of the target parking space, several reference points may be selected in the image. For example, for a rectangular parking space, the four corner points of the parking space may be selected as control points.

[0136] Step A62: Obtain a perspective transformation matrix, and apply the perspective transformation matrix to the image information of the target parking space so that the plurality of reference points are mapped to updated positions.

[0137] It should be noted that the perspective transformation matrix can be calculated using relevant functions in a computer according to the several reference points mentioned above.

[0138] In addition, after obtaining the perspective transformation matrix, the perspective transformation matrix is ​​applied to the image information of the target parking space so that the several reference points are mapped to the updated positions. For example, the image information of the target parking space is a side view of the target parking space. After several reference points are mapped to the updated positions, what is displayed on the display interface is a top view of the target parking space.

[0139] Step A63: Obtain image information after mapping and updating of a plurality of reference points, and display the image information after mapping and updating of the plurality of reference points on a display interface.

[0140] It should be noted that the image information after mapping and updating of several reference points is usually image information of a top view; in addition, the display interface includes at least a vehicle cockpit interface and a mobile phone-related APP interface. For example, the image information of the target parking space is a side view of the parking space. After being mapped to the updated position through several reference points, what is displayed on the vehicle cockpit interface is a top view of the target parking space.

[0141] It is understandable that the step of displaying the updated image information of the plurality of reference points on the display interface can allow the driver or passenger to further confirm whether the target parking space is available.

[0142] This embodiment provides a method for determining the parking availability of a ramp parking space, which includes obtaining the vehicle's own slope; obtaining a ramp image, and preprocessing the ramp image to obtain a target parking space; extracting parameter information and image information of the target parking space; determining the slope of the target parking space based on the vehicle's own slope and the parameter information of the target parking space; detecting the target parking space based on the image information of the target parking space to obtain a parking space availability detection result; and determining whether the target parking space is available for parking based on the slope of the target parking space and the parking space availability detection result. Whether the target parking space is available for parking is determined based on the slope of the target parking space and the parking space availability detection result, thereby improving the efficiency and accuracy of the method for determining the parking availability of a ramp parking space.

[0143] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 3 , step S20 includes steps S201 to S203:

[0144] Step S201: Acquire a ramp image, and perform corner point detection on the ramp image to obtain position information of corner points after corner point detection.

[0145] It should be noted that corner points refer to the points where two edges in an image intersect. These points appear as areas with significant intensity changes in the image, and are usually the intersection points of the edges of objects.

[0146] In addition, an edge refers to a line or boundary formed by a location in an image where the pixel value changes dramatically. This change can be a sudden change in grayscale value, such as a transition from a black area to a white area; it can also be a change in color channel value, such as a sudden change from a red area to a green area in a color image; it can also be a change in other image features such as texture. Intuitively, an edge outlines the boundaries between different objects or different parts of an object in an image, and is an important feature of an image.

[0147] In a specific implementation, before performing corner point detection, the color image of the ramp image needs to be converted into a grayscale image, and the grayscale image needs to be denoised. The corner point detection includes: obtaining the horizontal gradient and the vertical gradient of the ramp image, and obtaining the autocorrelation matrix of the pixel according to the horizontal gradient and the vertical gradient; defining empirical constants, and obtaining the determinant of the autocorrelation matrix and the sum of the diagonal elements; obtaining a calculated response function according to the empirical constants, the determinant of the autocorrelation matrix and the sum of the diagonal elements; obtaining the response value of each corner point according to the calculated response function; if the response value of the corner point is greater than a preset response value threshold, retaining the corner point and obtaining the position information of the corner point.

[0148] Specifically, the Sobel operator is used to calculate the horizontal and vertical gradients of the image. x and I y , according to the horizontal and vertical gradients of the image I x and I y , and the pixel autocorrelation matrix M is obtained by the method shown in the following formula 9:

[0149]

[0150] And define an empirical constant k (generally 0.04 to 0.06), obtain the determinant det(M) of the autocorrelation matrix and the sum of the diagonal elements trace(M) through the autocorrelation matrix M of the pixel, and obtain the calculation response function R according to the empirical constant k, the determinant det(M) of the autocorrelation matrix and the sum of the diagonal elements trace(M), as shown in the following formula 10:

[0151] R = det(M) - k*trace(M) 2 (Formula 10)

[0152] The response value of each corner point is obtained according to the calculated response function R. By setting a preset response value threshold, the corner points corresponding to the response values ​​less than or equal to the preset response value threshold are filtered, and the corner points corresponding to the response values ​​greater than the preset response value threshold are retained, and the position information of all the retained corner points is determined.

[0153] Step S202: performing edge detection on the ramp image to obtain edge lines after edge detection.

[0154] In a specific implementation, the Canny edge detection algorithm is used to extract the edges in the image and highlight the parking space markings. The edge detection mainly includes: denoising the ramp image; obtaining the gradient strengths of the pixels in the denoised ramp image in the horizontal and vertical directions; retaining the refined edges according to the gradient strengths of the pixels in the horizontal and vertical directions and through the non-maximum suppression technology; performing double threshold detection on the refined edges; if the gradient strength of the pixels corresponding to the refined edges is greater than a first preset strength threshold, marking the refined edges as strong edges; if the gradient strength of the pixels corresponding to the refined edges is greater than a second preset strength threshold and less than the first preset strength threshold, marking the refined edges as weak edges; retaining the weak edges connected to the strong edges; and obtaining edge lines by connecting the weak edges connected to the strong edges and the strong edges.

[0155] It should be noted that denoising can effectively avoid erroneously identifying noise as an edge during edge detection. After denoising, the horizontal direction G of the pixels in the denoised ramp image is obtained. x and the vertical gradient strength G y , and through the horizontal direction of the pixel G x and the vertical gradient strength G y The pixel gradient strength G and direction θ′ are obtained. The specific calculation method is shown in the following equations 11 and 12:

[0156]

[0157] In addition, pixels themselves have no direction, but when performing edge detection, for a pixel located on the edge, its gradient direction (perpendicular to the edge itself) gives the pixel a directional attribute in the edge scene.

[0158] Then, non-maximum suppression is performed to remove pixels that do not meet the local maximum. This means that only the local maximum in the gradient direction is retained to obtain a refined edge, and the refined edge is subjected to dual threshold detection, and a first preset intensity threshold and a second preset intensity threshold are set. The edge corresponding to the pixel gradient intensity greater than the first preset intensity threshold is marked as a strong edge, the edge corresponding to the pixel gradient intensity greater than the second preset intensity threshold but less than the first preset intensity threshold is marked as a weak edge, and the edge corresponding to the pixel gradient intensity less than the second preset intensity threshold is marked as a non-edge. It can be understood that the non-edge is directly filtered out. If it is a weak edge, it is determined whether it is connected to a strong edge. If the weak edge is connected to any strong edge, the weak edge is retained, and a continuous edge line is formed by connecting the strong edge and the weak edge connected to it. This step can be achieved by recursion or graph traversal method.

[0159] Step S203: obtaining a target parking space through the position information of the corner points and the edge line.

[0160] It should be noted that the possible parking area can be obtained through the corner point position information and edge lines after corner point detection, that is, the accuracy of the parking area initially obtained may not be high, and the target parking space can also be identified by the shape and area of ​​the obtained area.

[0161] This embodiment acquires a ramp image, and performs corner point detection on the ramp image to obtain position information of the corner points after corner point detection; performs edge detection on the ramp image to obtain edge lines after edge detection; and obtains a target parking space through the position information of the corner points and the edge lines. By performing corner point detection and edge detection on the ramp image, the target parking space is acquired, which effectively improves the accuracy of identifying the target parking space.

[0162] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the method for determining the parking availability of a ramp parking space of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0163] This application also provides a device for determining whether a parking space on a slope is available. Figure 4 , the ramp parking space parking availability judgment device comprises:

[0164] The acquisition module 10 is used to acquire the vehicle's own slope.

[0165] The processing module 20 is used to obtain a ramp image and pre-process the ramp image to obtain a target parking space.

[0166] The acquisition module 10 is also used to extract parameter information and image information of the target parking space.

[0167] The acquisition module 10 is further used to determine the slope of the target parking space according to the vehicle's own slope and the parameter information of the target parking space.

[0168] The detection module 30 is used to detect the target parking space according to the image information of the target parking space to obtain a parking space availability detection result.

[0169] The judging module 40 is used to judge whether the target parking space is available according to the slope of the target parking space and the parking space availability detection result.

[0170] The device for determining the parking availability of a ramp parking space provided by the present application adopts the method for determining the parking availability of a ramp parking space in the above-mentioned embodiment, and can solve the technical problem that the existing method for determining the parking availability of a ramp parking space cannot guarantee both high efficiency and accuracy. Compared with the prior art, the beneficial effects of the device for determining the parking availability of a ramp parking space provided by the present application are the same as the beneficial effects of the method for determining the parking availability of a ramp parking space provided by the above-mentioned embodiment, and the other technical features of the device for determining the parking availability of a ramp parking space are the same as the features disclosed in the above-mentioned embodiment method, and will not be described in detail here.

[0171] In one embodiment, the acquisition module 10 is also used to acquire the left-right acceleration, vertical acceleration and pitch angular velocity of the vehicle itself; obtain the vehicle's own pitch angle according to the left-right acceleration and the vertical acceleration; set a weight coefficient and a time constant, and obtain a time interval according to the weight coefficient and the time constant; obtain a filtered pitch angle according to the vehicle's own pitch angle, the pitch angular velocity, the weight coefficient and the time interval; obtain the vehicle's own slope angle according to the filtered pitch angle; and determine the vehicle's own slope according to the vehicle's own slope angle.

[0172] In one embodiment, the acquisition module 10 is further used to obtain the pitch angle of the target parking space according to the front height of the parking space, the rear height of the parking space and the length of the parking space, and the parameter information of the target parking space at least includes the front height of the parking space, the rear height of the parking space and the length of the parking space; obtain the slope angle of the target parking space according to the pitch angle of the target parking space and the slope angle of the vehicle itself; and determine the slope of the target parking space according to the slope angle of the target parking space.

[0173] In one embodiment, the processing module 20 is further used to acquire a ramp image, and perform corner point detection on the ramp image to obtain position information of the corner points after corner point detection; perform edge detection on the ramp image to obtain edge lines after edge detection; and obtain a target parking space through the position information of the corner points and the edge lines.

[0174] In one embodiment, the processing module 20 is further used to obtain the horizontal gradient and the vertical gradient of the ramp image, and obtain the autocorrelation matrix of the pixel according to the horizontal gradient and the vertical gradient; define empirical constants, and obtain the determinant of the autocorrelation matrix and the sum of the diagonal elements; obtain a calculated response function according to the empirical constants, the determinant of the autocorrelation matrix, and the sum of the diagonal elements; obtain the response value of each corner point according to the calculated response function; if the response value of the corner point is greater than a preset response value threshold, retain the corner point and obtain the position information of the corner point.

[0175] In one embodiment, the processing module 20 is further used to perform denoising on the ramp image; obtain the gradient strengths of pixels in the denoised ramp image in the horizontal and vertical directions; retain the thinned edge according to the gradient strengths of the pixels in the horizontal and vertical directions and by using a non-maximum suppression technique; perform double threshold detection on the thinned edge; if the gradient strength of the pixel corresponding to the thinned edge is greater than a first preset strength threshold, mark the thinned edge as a strong edge; if the gradient strength of the pixel corresponding to the thinned edge is greater than a second preset strength threshold and less than the first preset strength threshold, mark the thinned edge as a weak edge; retain the weak edge connected to the strong edge; and obtain an edge line by connecting the weak edge connected to the strong edge and the strong edge.

[0176] In one embodiment, the judgment module 40 is further used to select a number of reference points according to the image information of the target parking space; obtain a perspective transformation matrix, apply the perspective transformation matrix to the image information of the target parking space, so that the number of reference points are mapped to updated positions; obtain the image information after the number of reference points are mapped and updated, and display the image information after the number of reference points are mapped and updated on a display interface; if the slope of the target parking space is less than a preset slope threshold, and the parking space availability detection result determines that the target parking space is not occupied, then the target parking space is determined to be available for parking.

[0177] In one embodiment, the detection module 30 is further used to establish a corresponding parking space geometry model according to the image information of the target parking space; apply an object detection algorithm to detect the parking space geometry model; and obtain a parking space availability detection result to determine whether the target parking space is occupied.

[0178] The present application provides a device for determining the parking availability of a ramp parking space, the device comprising: at least one processor; and a memory in communication with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method for determining the parking availability of a ramp parking space in the first embodiment.

[0179] Reference below Figure 5 , which shows a schematic diagram of the structure of a device for determining the parking availability of a ramp parking space suitable for implementing the embodiment of the present application. The device for determining the parking availability of a ramp parking space in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The ramp parking space parking availability judgment device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0180] like Figure 5As shown, the ramp parking space parkingability determination device may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. Various programs and data required for the operation of the ramp parking space parkingability determination device are also stored in the RAM 1004. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems may be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 may allow the ramp parking space parkingability determination device to communicate wirelessly or wired with other devices to exchange data. Although the ramp parking space parkingability determination device having various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have alternatively.

[0181] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0182] The ramp parking space parking availability judgment device provided by the present application adopts the ramp parking space parking availability judgment method in the above embodiment, which can solve the technical problem that the existing ramp parking space parking availability judgment scheme cannot ensure both high efficiency and accuracy. Compared with the prior art, the beneficial effects of the ramp parking space parking availability judgment device provided by the present application are the same as the beneficial effects of the ramp parking space parking availability judgment method provided by the above embodiment, and the other technical features of the ramp parking space parking availability judgment device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0183] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0184] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0185] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the method for determining the parking availability of a ramp parking space in the above-mentioned embodiment.

[0186] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0187] The computer-readable storage medium may be included in the device for determining the parking availability of a ramp parking space; or may exist independently without being assembled into the device for determining the parking availability of a ramp parking space.

[0188] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the device for determining the parking availability of a ramp parking space, the device for determining the parking availability of a ramp parking space: obtains the vehicle's own slope; obtains a ramp image, and pre-processes the ramp image to obtain a target parking space; extracts parameter information and image information of the target parking space; determines the slope of the target parking space according to the vehicle's own slope and the parameter information of the target parking space; detects the target parking space according to the image information of the target parking space to obtain a parking space availability detection result; and determines whether the target parking space is parkable according to the slope of the target parking space and the parking space availability detection result.

[0189] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0190] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0191] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0192] The readable storage medium provided in the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned ramp parking space parking availability determination method, and can solve the technical problem that the existing ramp parking space parking availability determination scheme cannot guarantee both high efficiency and accuracy. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in the present application are the same as the beneficial effects of the ramp parking space parking availability determination method provided in the above-mentioned embodiment, and will not be elaborated here.

[0193] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for determining the parking availability of a ramp parking space.

[0194] The computer program product provided by the present application can solve the technical problem that the existing ramp parking space parking availability judgment scheme cannot guarantee both high efficiency and accuracy. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the ramp parking space parking availability judgment method provided by the above embodiment, which will not be elaborated here.

[0195] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A method for determining the parking availability of a ramp parking space, characterized in that: The method for determining the parking availability of a ramp parking space comprises: Get the vehicle's own slope; Acquire a ramp image, and pre-process the ramp image to obtain a target parking space; Extract parameter information and image information of the target parking space; Determining the slope of the target parking space according to the vehicle's own slope and parameter information of the target parking space; Detecting the target parking space according to the image information of the target parking space to obtain a parking space availability detection result; Whether the target parking space is available is determined according to the slope of the target parking space and the parking space availability detection result.

2. The method according to claim 1, characterized in that The step of obtaining the vehicle's own slope comprises: Obtain the vehicle's left and right acceleration, vertical acceleration and pitch angular velocity; Obtaining the vehicle's own pitch angle according to the left-right acceleration and the vertical acceleration; Setting a weight coefficient and a time constant, and obtaining a time interval according to the weight coefficient and the time constant; Obtaining a filtered pitch angle according to the pitch angle of the vehicle itself, the pitch angle velocity, the weight coefficient and the time interval; Obtaining the vehicle's own slope angle according to the filtered pitch angle; The vehicle's own slope is determined according to the vehicle's own slope angle.

3. The method according to claim 2, characterized in that The parameter information of the target parking space at least includes the front height of the parking space, the rear height of the parking space and the length of the parking space; The step of determining the slope of the target parking space according to the vehicle's own slope and the parameter information of the target parking space comprises: Obtaining a target parking space pitch angle according to the parking space front height, the parking space rear height and the parking space length; Obtaining a target parking space slope angle according to the target parking space pitch angle and the vehicle's own slope angle; The slope of the target parking space is determined according to the target parking space slope angle.

4. The method according to claim 1, characterized in that The step of acquiring the ramp image and preprocessing the ramp image to obtain the target parking space includes: Acquire a ramp image, and perform corner point detection on the ramp image to obtain position information of corner points after corner point detection; Performing edge detection on the ramp image to obtain edge lines after edge detection; The target parking space is obtained through the position information of the corner points and the edge line.

5. The method according to claim 4, characterized in that The step of performing corner point detection on the ramp image to obtain position information of the corner points after corner point detection comprises: Acquire the horizontal gradient and the vertical gradient of the ramp image, and obtain the autocorrelation matrix of pixels according to the horizontal gradient and the vertical gradient; Defining empirical constants, and obtaining the determinant and the sum of diagonal elements of the autocorrelation matrix; Obtaining a calculation response function according to the empirical constant, the determinant of the autocorrelation matrix and the sum of the diagonal elements; Obtaining the response value of each corner point according to the calculation response function; If the response value of the corner point is greater than a preset response value threshold, the corner point is retained and the position information of the corner point is obtained.

6. The method according to claim 4, characterized in that The step of performing edge detection on the ramp image to obtain edge lines comprises: Performing denoising processing on the ramp image; Obtaining the gradient strength of pixels in the horizontal and vertical directions in the denoised ramp image; According to the gradient strength in the horizontal direction and the vertical direction of the pixel, the refined edge is retained by a non-maximum suppression technique; performing double threshold detection on the thinned edge; If the gradient intensity of the pixel corresponding to the thinned edge is greater than a first preset intensity threshold, marking the thinned edge as a strong edge; If the gradient intensity of the pixel corresponding to the thinned edge is greater than the second preset intensity threshold and less than the first preset intensity threshold, marking the thinned edge as a weak edge; retaining weak edges connected to the strong edges; The edge line is obtained by connecting the weak edge connected to the strong edge and the strong edge.

7. The method according to claim 1, characterized in that After the step of judging whether the target parking space is available for parking according to the slope of the target parking space and the parking space availability detection result, the method further includes: Selecting a number of reference points according to the image information of the target parking space; Obtaining a perspective transformation matrix, and applying the perspective transformation matrix to the image information of the target parking space so that the plurality of reference points are mapped to updated positions; The image information after the mapping and updating of the reference points is obtained, and the image information after the mapping and updating of the reference points is displayed on the display interface.

8. The method according to claim 1, characterized in that The step of detecting the target parking space according to the image information of the target parking space to obtain a parking space availability detection result comprises: Establishing a corresponding parking space geometric model according to the image information of the target parking space; Applying an object detection algorithm to detect the parking space geometric model; Obtaining a parking space availability detection result to determine whether the target parking space is occupied; The step of judging whether the target parking space is available for parking according to the slope of the target parking space and the parking space availability detection result comprises: If the slope of the target parking space is less than a preset slope threshold, and the parking space availability detection result determines that the target parking space is not occupied, then it is determined that the target parking space is available for parking.

9. A device for determining the parking availability of a ramp parking space, characterized in that: The device comprises: An acquisition module is used to obtain the vehicle's own slope; A processing module, used for acquiring a ramp image and preprocessing the ramp image to obtain a target parking space; The acquisition module is also used to extract parameter information and image information of the target parking space; The acquisition module is further used to determine the slope of the target parking space according to the vehicle's own slope and the parameter information of the target parking space; A detection module, used to detect the target parking space according to the image information of the target parking space, and obtain a parking space availability detection result; The judging module is used to judge whether the target parking space is available according to the slope of the target parking space and the parking space availability detection result.

10. A device for determining the parking availability of a ramp parking space, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the method for determining the parking availability of a ramp parking space as claimed in any one of claims 1 to 8.

Images