An automatic parking method, device, vehicle, medium and system

Abstract

The application discloses an automatic parking method, device, vehicle, medium and system, and the method comprises the following steps: performing polar coordinate transformation on a vehicle top view image of a target vehicle according to road position information to obtain a transformed image; determining a target parking spot coordinate according to the transformed image, wherein the target parking spot coordinate is a coordinate of a parking spot in a world coordinate system, and the parking spot is a point corresponding to a parking space; determining a vehicle parking path of the target vehicle based on the target parking spot coordinate, and controlling the target vehicle to park according to the vehicle parking path. The method can improve the recognition rate of a curved parking space by performing polar coordinate transformation on a vehicle top view image of a target vehicle according to road position information to obtain a transformed image, thereby enhancing the effect of automatic parking.

Description

Technical Field

[0001] This invention relates to the field of intelligent parking technology, and more particularly to an automatic parking method, device, vehicle, medium, and system. Background Technology

[0002] Current automatic parking systems are mainly designed for recognizing parking spaces in straight-line scenarios. This results in poor recognition rates when encountering curved or concave parking spaces, leading to poor parking performance. Summary of the Invention

[0003] This invention provides an automatic parking method, apparatus, vehicle, medium, and system to improve the recognition rate of parking spaces and enhance the effect of automatic parking.

[0004] According to one aspect of the present invention, an automatic parking method is provided, comprising:

[0005] The target vehicle's top-view image is transformed using polar coordinates based on road location information to obtain the transformed image.

[0006] The target parking spot coordinates are determined based on the transformed image. The target parking spot coordinates are the coordinates of the parking spot in the world coordinate system, and the parking spot is the point corresponding to the parking spot.

[0007] The parking path of the target vehicle is determined based on the coordinates of the target parking spot, and the target vehicle is controlled to park according to the parking path.

[0008] According to another aspect of the present invention, an automatic parking device is provided, comprising:

[0009] The transformation module is used to perform polar coordinate transformation on the top view image of the target vehicle based on the road location information to obtain the transformed image.

[0010] The first determining module is used to determine the coordinates of the target parking spot based on the transformed image. The coordinates of the target parking spot are the coordinates of the parking spot in the world coordinate system, and the parking spot is the point corresponding to the parking spot.

[0011] The second determining module is used to determine the parking path of the target vehicle based on the coordinates of the target parking spot, and to control the target vehicle to park according to the parking path.

[0012] According to another aspect of the present invention, a vehicle is provided, the vehicle comprising:

[0013] At least one processor; and

[0014] A memory communicatively connected to the at least one processor; wherein,

[0015] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the automatic parking method according to any embodiment of the present invention.

[0016] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the automatic parking method according to any embodiment of the present invention.

[0017] According to another aspect of the present invention, an automatic parking system is provided, the system comprising roadside equipment and a vehicle, the roadside equipment being disposed at a location where the road has a change in curvature.

[0018] The roadside equipment is used to send road location information to the vehicle;

[0019] The vehicle is used to perform polar coordinate transformation on the top-view image of the target vehicle based on the road location information to obtain the transformed image; determine the target parking spot coordinates based on the transformed image, wherein the target parking spot coordinates are the coordinates of the parking spot in the world coordinate system, and the parking spot is the point corresponding to the parking space; determine the parking path of the target vehicle based on the target parking spot coordinates, and control the target vehicle to park according to the parking path.

[0020] This invention provides an automatic parking method, device, vehicle, medium, and system. The method includes: performing polar coordinate transformation on a top-view image of a target vehicle based on road location information to obtain a transformed image; determining the coordinates of a target parking spot based on the transformed image, wherein the target parking spot coordinates are the coordinates of the parking spot in the world coordinate system, and the parking spot is the point corresponding to the parking space; determining a parking path for the target vehicle based on the target parking spot coordinates, and controlling the target vehicle to park according to the parking path. By using the above technical solution, and performing polar coordinate transformation on a top-view image of the target vehicle based on road location information to obtain a transformed image, the recognition rate of curved parking spaces can be improved, thereby enhancing the effect of automatic parking.

[0021] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a flowchart of an automatic parking method provided according to Embodiment 1 of the present invention;

[0024] Figure 2 This is a flowchart of an automatic parking method provided according to Embodiment 2 of the present invention;

[0025] Figure 3 This is a schematic diagram of a polar coordinate transformation according to Embodiment 2 of the present invention;

[0026] Figure 4 This is a flowchart of an automatic parking method provided according to Embodiment 2 of the present invention;

[0027] Figure 5 This is a schematic diagram of an automatic parking device according to Embodiment 3 of the present invention;

[0028] Figure 6 This is a schematic diagram of the structure of a vehicle according to Embodiment 4 of the present invention;

[0029] Figure 7 This is a schematic diagram of an automatic parking system provided according to Embodiment 5 of the present invention. Detailed Implementation

[0030] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0031] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0032] Example 1

[0033] Figure 1 This is a flowchart of an automatic parking method according to Embodiment 1 of the present invention. This embodiment is applicable to automatic parking situations. The method can be executed by an automatic parking device, which can be implemented in hardware and / or software and can be configured in a vehicle.

[0034] It can be argued that as urban roads become increasingly congested and the driving and parking environment becomes more complex, "parking difficulties" have become a widespread concern. Therefore, research on automated parking systems has become a hot topic in the field of intelligent transportation. To alleviate the shortage of parking spaces in cities, many urban roads or residential roads have designated parking areas. Since some roads are not straight and often have curves, parking spaces are also marked along these roads.

[0035] A complete automated parking system comprises three main components: parking space recognition, path planning, and vehicle control. The initial stage of parking space perception and recognition is the foundation and crucial information source for the entire parking system. The main function of parking space recognition is to utilize various sensors (such as cameras and ultrasonic sensors) installed around the vehicle to acquire real-time information about the surrounding environment and, in parking scenarios, use algorithms to detect recommended parking spaces that meet the vehicle's size requirements and have available parking space.

[0036] Currently, the mainstream vision-based automatic parking systems on the market mainly target parking space recognition in straight-line scenarios. They do not yet support parking spaces with curves, such as concave or convex curves, resulting in poor parking space recognition rates. Even if a parking space is detected, the detection accuracy is not high, leading to poor parking performance.

[0037] Based on this, the present invention provides an automatic parking method that solves the problems of low detection rate and poor parking accuracy for convex or concave curved parking spaces by fusing roadside equipment information and surround-view camera images for visual detection of parking spaces along road curves. This improves the adaptability of the parking system to special scenarios and thus enhances the detection robustness of the automatic parking system. Figure 1 As shown, the method includes:

[0038] S110. Perform polar coordinate transformation on the top-view image of the target vehicle based on the road location information to obtain the transformed image.

[0039] Road location information can refer to information about the roads surrounding the target vehicle. This may include, for example, the relative position of the road to the target vehicle (e.g., lateral distance from lane lines, longitudinal distance from stop lines), road structural information (e.g., curvature, longitudinal and lateral slopes, number of lanes), and / or rule information (e.g., lane type, speed limit, flow direction, right-of-way regulations, traffic light status). The source of road location information is not limited; it can be obtained through roadside equipment or collected by the target vehicle. The vehicle top-view image can be understood as a top-view image of the target vehicle, used to represent the front, rear, left, and right states of the target vehicle. This embodiment does not limit the method for determining the vehicle top-view image; it can be obtained directly or generated from image information collected by the vehicle. The target vehicle can be considered as the vehicle about to park.

[0040] Specifically, this step can perform polar coordinate transformation on the top-view image of the target vehicle based on the road location information to obtain the transformed image. The polar coordinate transformation process is not limited. For example, the corresponding transformed points can be obtained by directly performing polar coordinate transformation on each point in the top-view image of the vehicle, thereby obtaining the transformed image. This embodiment will not elaborate further on this.

[0041] In one embodiment, before performing polar coordinate transformation on the top-view image of the target vehicle based on road location information to obtain the transformed image, the method further includes:

[0042] Receive road location information sent by roadside equipment; and / or,

[0043] A top-down view of the target vehicle is generated based on image information captured by the target camera, which is mounted on the vehicle body.

[0044] Among them, roadside equipment can be considered as equipment installed on the side of the road to collect road location information; the number and location of roadside equipment are not limited and can be deployed according to the actual road conditions. For example, multiple roadside equipment can be deployed at nodes where the road curvature changes, while one roadside equipment can be deployed on a straight road.

[0045] A target camera can be understood as a camera installed on the body of a target vehicle to collect image information, which may include information about the surroundings of the target vehicle.

[0046] In one implementation, the roadside device can send the collected road location information to the target vehicle, thereby receiving the road location information sent by the roadside device. For example, the roadside device can send the collected road location information to the on-board unit of the target vehicle, and then the road location information can be acquired.

[0047] In one implementation, the target camera can acquire image information, and then generate a top-down view of the target vehicle based on the image information acquired by the target camera, in order to perform subsequent operations.

[0048] In one embodiment, the step of performing polar coordinate transformation on the top-view image of the target vehicle based on road location information to obtain the transformed image includes:

[0049] When the target vehicle is parked on a curved road, the top-view image of the target vehicle is transformed into polar coordinates based on the road location information to obtain the transformed image.

[0050] In one implementation, when the road where the target vehicle is parked is a curved road, it is necessary to perform polar coordinate transformation on the top view image of the target vehicle in order to detect subsequent parking spots and park the vehicle based on the transformed image.

[0051] In one implementation, when the road where the target vehicle is to be parked is a straight road, subsequent parking spot detection and parking can be performed directly based on the vehicle's top-view image without requiring polar coordinate transformation of the vehicle's top-view image. This improves the applicability of the automatic parking method.

[0052] S120. Determine the target parking spot coordinates based on the transformed image. The target parking spot coordinates are the coordinates of the parking spot in the world coordinate system, and the parking spot is the point corresponding to the parking spot.

[0053] The target parking spot coordinates can be considered as the coordinates of the parking spot in the world coordinate system, and the parking spot is the point corresponding to the parking spot.

[0054] After obtaining the transformed image in the previous step, the coordinates of the target parking spot can be determined based on the transformed image. For example, the coordinates of the target parking spot can be obtained by performing parking spot detection on the transformed image. The specific process of parking spot detection can be determined according to the actual image situation.

[0055] In one embodiment, determining the target parking location coordinates based on the transformed image includes:

[0056] Parking location detection is performed on the transformed image to obtain the image coordinates corresponding to the parking locations;

[0057] The target vehicle location coordinates are determined based on the image coordinates.

[0058] The image coordinates corresponding to the parking spot can be understood as the coordinates of the parking spot in the image.

[0059] Specifically, in the process of determining the coordinates of the target parking spot based on the transformed image, parking spot detection can be performed on the transformed image first to obtain the image coordinates corresponding to the parking spot. For example, the transformed image can be directly input into a parking spot detection module to obtain the image coordinates corresponding to the parking spot. The parking spot detection module can be a pre-set module used to detect the image coordinates of the parking spot. Alternatively, the image coordinates corresponding to the parking spot can be obtained by performing a series of detection steps such as preprocessing the transformed image, line detection, and parking spot determination.

[0060] After obtaining the image coordinates, the target parking spot coordinates can be determined based on them. In one implementation, the image coordinates can be considered as the coordinates of the parking spot in the polar coordinate system, while the target parking spot coordinates can be understood as the coordinates of the parking spot in the world coordinate system. Therefore, coordinate transformation is required to obtain the target parking spot coordinates. The means of coordinate transformation are not limited. For example, the image coordinates can be directly converted to the target parking spot coordinates, or the image coordinates can be first converted to the coordinates of the parking spot in the top view image of the vehicle, and then converted to the target parking spot coordinates.

[0061] In one embodiment, determining the target parking location coordinates based on the image coordinates includes:

[0062] The image coordinates are transformed to obtain the original parking spot coordinates, which are the coordinates of the parking spot in the top view image of the vehicle.

[0063] The coordinates of the target parking spot are determined based on the original parking spot coordinates.

[0064] The original parking spot coordinates can be considered as the coordinates of the parking spot in the top view image of the vehicle.

[0065] Specifically, the image coordinates can be transformed first to obtain the original parking spot coordinates, such as by inverse polar coordinate transformation to obtain the original parking spot coordinates from the image coordinates; then the target parking spot coordinates can be determined based on the original parking spot coordinates, such as by calculation to determine the target parking spot coordinates corresponding to the original parking spot coordinates.

[0066] S130. Determine the parking path of the target vehicle based on the coordinates of the target parking spot, and control the target vehicle to park according to the parking path.

[0067] A vehicle parking path can refer to a path determined based on the coordinates of a target parking spot, used to control the parking of a target vehicle. The specific process of determining the vehicle parking path based on the target parking spot coordinates is not limited here, as long as the vehicle parking path can be obtained.

[0068] After obtaining the vehicle parking path, the target vehicle can be controlled to park based on the determined parking path, such as by sending a control signal containing the vehicle parking path to the controller to control the target vehicle.

[0069] This invention provides an automatic parking method that involves performing a polar coordinate transformation on a top-view image of a target vehicle based on road location information to obtain a transformed image; determining the target parking space coordinates based on the transformed image, where the target parking space coordinates are the coordinates of the parking space in the world coordinate system, and the parking space is the point corresponding to the parking space; determining the parking path of the target vehicle based on the target parking space coordinates, and controlling the target vehicle to park according to the parking path. This method, by performing a polar coordinate transformation on the top-view image of the target vehicle based on road location information to obtain a transformed image, can improve the recognition rate of curved parking spaces, thereby enhancing the effect of automatic parking.

[0070] Example 2

[0071] Figure 2 This is a flowchart of an automatic parking method according to Embodiment 2 of the present invention, which is an optimization based on the above embodiments. In this embodiment, the process of performing polar coordinate transformation on the top-view image of the target vehicle based on road location information to obtain the transformed image is further specified as follows: determining the radius of curvature of the current road based on the road location information; and performing polar coordinate transformation on the top-view image of the vehicle based on the radius of curvature to obtain the transformed image.

[0072] For details not covered in this embodiment, please refer to Embodiment 1.

[0073] like Figure 2 As shown, the method includes:

[0074] S210. Determine the radius of curvature of the current road based on the road location information.

[0075] The radius of curvature can be used to describe the degree of curvature of a road. It can be assumed that the larger the radius of curvature, the less curved the road is.

[0076] In this embodiment, the radius of curvature of the current road can be determined first based on the road location information, and then the transformed image can be determined based on the determined radius of curvature. The method for determining the radius of curvature is not limited; for example, the radius of curvature of the current road can be calculated based on a preset formula and the road location information.

[0077] In one embodiment, determining the radius of curvature of the current road based on road location information includes:

[0078] The road curve equation is obtained by fitting the current road based on the road location information;

[0079] The radius of curvature of the current road is calculated based on the road curve equation and the position information of the target vehicle.

[0080] The road curve equation can refer to the curve equation of the current road, used to determine the radius of curvature of the current road. The target vehicle's position information can be used to characterize the target vehicle's position.

[0081] In one implementation, the current road can be fitted with the road location information to obtain the road curve equation. The fitting method can be, for example, the least squares method. Then, based on the obtained road curve equation and the location information of the target vehicle, the radius of curvature of the current road can be calculated. For example, the radius of curvature of the current road can be determined according to a preset calculation formula.

[0082] For example, a curved road can be differentiated as much as possible until it approximates a circular arc. The radius corresponding to this arc is the radius of curvature of the curve. Assuming the equation of the road curve is f(x), and the position information of the target vehicle can be coordinate x0, then the radius of curvature ρ can be determined using the following formula:

[0083]

[0084] S220. Perform polar coordinate transformation on the vehicle top view image according to the radius of curvature to obtain the transformed image.

[0085] In this embodiment, the vehicle top view image can be transformed into polar coordinates based on the radius of curvature determined in the previous step to obtain the transformed image. The process of obtaining the transformed image can be determined according to the actual situation, as long as the transformed image can be obtained.

[0086] In one embodiment, performing polar coordinate transformation on the vehicle top-view image based on the radius of curvature to obtain the transformed image includes:

[0087] Calculate the target angle covered by the vehicle top view image, where the target angle is the central angle subtended by the target arc, and the target arc is the arc along the current road direction in the vehicle top view image;

[0088] Based on the radius of curvature and the target angle, the top view image of the vehicle is transformed into polar coordinates to obtain the transformed image.

[0089] In this embodiment, the target angle can be the central angle of the target arc, which is the arc along the current road direction in the vehicle top view image. The target angle can be calculated based on the target arc and the radius of curvature. The target arc can be approximated by the range of the top view, and the target angle can be the quotient of the target arc and the radius of curvature.

[0090] For example, Figure 3 This is a schematic diagram of a polar coordinate transformation according to Embodiment 2 of the present invention. First, the pixel value of point P on the circular image (such as a top view image of a vehicle) is (x, y). According to the polar coordinate formula, the radius... The angle θ = arctan(y / x) gives the polar coordinates of point P (ρ0, θ0). Figure 3 As shown, the horizontal coordinate of the rectangle corresponds to each radius on the circular diagram, and the vertical coordinate corresponds to the angle range on the circular diagram. Thus, the coordinates of point P on the rectangle can be obtained.

[0091] S230. Determine the target parking spot coordinates based on the transformed image. The target parking spot coordinates are the coordinates of the parking spot in the world coordinate system, and the parking spot is the point corresponding to the parking spot.

[0092] S240. Determine the parking path of the target vehicle based on the coordinates of the target parking spot, and control the target vehicle to park according to the parking path.

[0093] This invention provides an automatic parking method in Embodiment 2, which determines the radius of curvature of the current road based on road location information; performs polar coordinate transformation on the vehicle's top-view image according to the radius of curvature to obtain a transformed image; determines the target parking spot coordinates based on the transformed image, where the target parking spot coordinates are the coordinates of the parking spot in the world coordinate system, and the parking spot is the point corresponding to the parking space; determines the parking path of the target vehicle based on the target parking spot coordinates, and controls the target vehicle to park according to the parking path. Using this method, by determining the radius of curvature of the current road and performing polar coordinate transformation on the vehicle's top-view image according to the radius of curvature, the transformed image can be accurately obtained, providing a foundation for improving parking space recognition rate.

[0094] Figure 4 This is a flowchart of an automatic parking method according to Embodiment 2 of the present invention, as shown below. Figure 4As shown, firstly, the automatic parking system can be activated to begin parking space detection; the onboard unit (OBU) can acquire information such as the relative position of the vehicle to the vehicle (i.e., road position information) broadcast by multiple roadside units (RSUs, i.e., roadside devices), and the least squares method is used to fit the cubic equation f(x) of the road curve (i.e., fitting the current road based on the road position information to obtain the road curve equation), and the curvature radius ρ of the road is obtained according to the curve radius calculation formula and the vehicle position x0 (i.e., the curvature radius of the current road is calculated based on the road curve equation and the position information of the target vehicle).

[0095] Subsequently, the four-channel image information from the front, rear, left, and right sides of the vehicle body is transformed by inverse perspective to generate a top-view image (i.e., a top-view image of the target vehicle is generated based on the image information collected by the target camera, which is mounted on the vehicle body). The top-view image can cover a world coordinate range of 12 meters by 12 meters. For example, the top-view range can be approximated as the arc length, and then the angle θ covered by the top-view is calculated based on the radius of curvature ρ and the arc length, such as θ = arc length / radius ρ (i.e., the target angle covered by the vehicle top-view image is calculated, where the target angle is the central angle subtended by the target arc, and the target arc is the arc along the current road direction in the vehicle top-view image).

[0096] Furthermore, the curvature of the curve in the top-view image can be regarded as part of a circle in polar coordinates. Based on the radius of curvature ρ and the angle θ, the image is transformed into a rectangular image by polar coordinate transformation. At this time, the curve in the image becomes a straight line (that is, based on the radius of curvature and the target angle, the top-view image of the vehicle is transformed into a polar coordinate image).

[0097] Secondly, the transformed image is output to the conventional straight-line parking space detection module, where a series of detection modules such as image preprocessing, straight-line detection, and parking space determination are performed, and the image coordinates of the detected parking space are output (that is, the transformed image is used to detect parking spaces and obtain the image coordinates corresponding to the parking spaces).

[0098] Finally, the coordinates of the parking spot image are inversely transformed to the coordinates on the original top view, and then calculated to the world coordinate output (that is, the coordinates of the image are transformed to obtain the original parking spot coordinates; the coordinates of the target parking spot are determined based on the original parking spot coordinates).

[0099] In summary, this embodiment of the invention mainly acquires road information through multiple RSU units arranged on the roadside. Since parking spaces are marked along the road, the curvature of the parking space line is consistent with the road. According to the fitted road curve equation, the radius of the approximate curvature circle (i.e., the curvature radius of the current road) can be obtained. At the same time, the panoramic overhead view of the vehicle (i.e., the vehicle top view image) is obtained by transforming the images of four surround-view cameras installed on the vehicle body. According to the radius information, the top view is transformed into a polar coordinate transformation, turning the curve into a straight line (i.e., according to the curvature radius and the target angle, the vehicle top view image is transformed into a polar coordinate transformation to obtain the transformed image). Finally, it is input into a conventional straight-line parking space recognition module for parking space recognition. The coordinates of the interior corner points of the recognized parking space are restored to the coordinates of the overhead view, and the world coordinates of the parking space are further obtained and input into the planning and control module (i.e., based on the target parking space coordinates, the vehicle parking path of the target vehicle is determined, and the target vehicle is controlled to park according to the vehicle parking path).

[0100] As can be seen, the embodiments of the present invention have made modular additions based on the existing straight parking space detection module, which improves the adaptability of the parking system to special scenarios without affecting the original straight parking space detection, and further improves the detection robustness of the automatic parking system.

[0101] Example 3

[0102] Figure 5 This is a structural schematic diagram of an automatic parking device according to Embodiment 3 of the present invention. Figure 5 As shown, the device includes:

[0103] The transformation module 310 is used to perform polar coordinate transformation on the top view image of the target vehicle based on the road location information to obtain the transformed image.

[0104] The first determining module 320 is used to determine the coordinates of the target parking spot based on the transformed image. The coordinates of the target parking spot are the coordinates of the parking spot in the world coordinate system, and the parking spot is the point corresponding to the parking spot.

[0105] The second determining module 330 is used to determine the parking path of the target vehicle based on the coordinates of the target parking spot, and control the target vehicle to park according to the parking path.

[0106] An automatic parking device provided in Embodiment 3 of the present invention performs polar coordinate transformation on a top-view image of a target vehicle based on road location information using a transformation module 310 to obtain a transformed image. A first determining module 320 determines the target parking space coordinates based on the transformed image; the target parking space coordinates are the coordinates of the parking space in the world coordinate system, and the parking space is the point corresponding to the parking space. A second determining module 330 determines the parking path of the target vehicle based on the target parking space coordinates and controls the target vehicle to park according to the parking path. Using this device, by performing polar coordinate transformation on the top-view image of the target vehicle based on road location information to obtain a transformed image, the recognition rate of curved parking spaces can be improved, thereby enhancing the effect of automatic parking.

[0107] Optionally, the transformation module 310 includes:

[0108] The first determining unit is used to determine the radius of curvature of the current road based on the road location information;

[0109] The transformation unit is used to perform polar coordinate transformation on the vehicle top view image according to the radius of curvature to obtain the transformed image.

[0110] Optionally, the first determining unit is specifically used for:

[0111] The road curve equation is obtained by fitting the current road based on the road location information;

[0112] The radius of curvature of the current road is calculated based on the road curve equation and the position information of the target vehicle.

[0113] Optionally, the transformation unit is specifically used for:

[0114] Calculate the target angle covered by the vehicle top view image, where the target angle is the central angle subtended by the target arc, and the target arc is the arc along the current road direction in the vehicle top view image;

[0115] Based on the radius of curvature and the target angle, the top view image of the vehicle is transformed into polar coordinates to obtain the transformed image.

[0116] Optionally, the automatic parking device provided in this embodiment of the invention further includes:

[0117] The receiving unit is used to receive road location information sent by the roadside equipment before performing polar coordinate transformation on the vehicle top view image of the target vehicle based on the road location information to obtain the transformed image.

[0118] And / or, a generation unit is configured to generate a top-view image of the target vehicle based on image information acquired by a target camera, before performing polar coordinate transformation on the top-view image of the target vehicle based on road location information to obtain the transformed image, wherein the target camera is mounted on the vehicle body of the target vehicle.

[0119] Optionally, the first determining module 320 includes:

[0120] The parking spot detection unit is used to detect parking spots in the transformed image and obtain the image coordinates corresponding to the parking spots.

[0121] The second determining unit is used to determine the coordinates of the target vehicle location based on the image coordinates.

[0122] Optionally, the second determining unit is specifically used for:

[0123] The image coordinates are transformed to obtain the original parking spot coordinates, which are the coordinates of the parking spot in the top view image of the vehicle.

[0124] The coordinates of the target parking spot are determined based on the original parking spot coordinates.

[0125] Optionally, the transformation module 310 is specifically used for:

[0126] When the target vehicle is parked on a curved road, the top-view image of the target vehicle is transformed into polar coordinates based on the road location information to obtain the transformed image.

[0127] The automatic parking device provided in this embodiment of the invention can execute the automatic parking method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0128] Example 4

[0129] Figure 6 A schematic diagram of a vehicle 10, which can be used to implement embodiments of the present invention, is shown. The vehicle is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The vehicle can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0130] like Figure 6As shown, vehicle 10 includes at least one processor 11 and a memory, such as read-only memory (ROM) 12 and random access memory (RAM) 13, communicatively connected to at least one processor 11. The memory stores computer programs executable by at least one processor. Processor 11 can perform various appropriate actions and processes based on the computer program stored in ROM 12 or loaded from storage unit 18 into RAM 13. RAM 13 can also store various programs and data required for the operation of vehicle 10. Processor 11, ROM 12, and RAM 13 are interconnected via bus 14. Input / output (I / O) interface 15 is also connected to bus 14.

[0131] Multiple components in vehicle 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows vehicle 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0132] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the method of automatic parking.

[0133] In some embodiments, the method of automatic parking may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on vehicle 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the method of automatic parking described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform method of automatic parking by any other suitable means (e.g., by means of firmware).

[0134] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0135] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0136] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0137] To provide interaction with the user, the systems and technologies described herein can be implemented in a vehicle having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the vehicle. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0138] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0139] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0140] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and no limitation is imposed herein.

[0141] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

[0142] Example 5

[0143] Figure 7 This is a structural schematic diagram of an automatic parking system according to Embodiment 5 of the present invention, as shown below. Figure 7 As shown, the system includes roadside equipment 1 and vehicle 2. The roadside equipment 1 is installed at a location where the road curvature changes.

[0144] Roadside device 1 is used to send road location information to vehicle 2;

[0145] Vehicle 2 is used to perform polar coordinate transformation on the top-view image of the target vehicle based on the road location information to obtain the transformed image; determine the target parking spot coordinates based on the transformed image, wherein the target parking spot coordinates are the coordinates of the parking spot in the world coordinate system, and the parking spot is the point corresponding to the parking space; determine the parking path of the target vehicle based on the target parking spot coordinates, and control the target vehicle to park according to the parking path.

[0146] In this embodiment, the roadside device 1 can be considered as a device located on the roadside, used to collect road location information. In this embodiment, the roadside device 1 can be set at a location where the road has curvature changes. The specific number of roadside devices is not limited and can be deployed according to the actual road conditions. For example, it can be determined according to the curvature of the road or the environment on both sides of the road. This embodiment does not limit this.

[0147] Specifically, the roadside device 1 can collect road location information and send the collected road location information to the vehicle 2. After receiving the road location information, the vehicle 2 can perform polar coordinate transformation on the target vehicle's top view image based on the road location information when parking, and determine the target parking position coordinates based on the transformed image, thereby determining the target vehicle's parking path and controlling the target vehicle to park according to the parking path.

Claims

1. An automatic parking method, characterized in that, include: The target vehicle's top-view image is transformed using polar coordinates based on road location information to obtain the transformed image. The target parking spot coordinates are determined based on the transformed image. The target parking spot coordinates are the coordinates of the parking spot in the world coordinate system, and the parking spot is the point corresponding to the parking spot. The parking path of the target vehicle is determined based on the coordinates of the target parking spot, and the target vehicle is controlled to park according to the parking path. The step of performing polar coordinate transformation on the top-view image of the target vehicle based on road location information to obtain the transformed image includes: The radius of curvature of the current road is determined based on the road location information; Calculate the target angle covered by the vehicle top view image, where the target angle is the central angle subtended by the target arc, and the target arc is the arc along the current road direction in the vehicle top view image; Based on the radius of curvature and the target angle, the top view image of the vehicle is transformed into polar coordinates to obtain the transformed image.

2. The method according to claim 1, characterized in that, Determining the radius of curvature of the current road based on road location information includes: The road curve equation is obtained by fitting the current road based on the road location information; The radius of curvature of the current road is calculated based on the road curve equation and the position information of the target vehicle.

3. The method according to claim 1, characterized in that, Before performing polar coordinate transformation on the top-view image of the target vehicle based on road location information to obtain the transformed image, the method further includes: Receive road location information sent by roadside equipment; and / or, A top-down view of the target vehicle is generated based on image information captured by the target camera, which is mounted on the vehicle body.

4. The method according to claim 1, characterized in that, Determining the target parking location coordinates based on the transformed image includes: Parking location detection is performed on the transformed image to obtain the image coordinates corresponding to the parking locations; The target vehicle location coordinates are determined based on the image coordinates.

5. The method according to claim 4, characterized in that, Determining the target parking spot coordinates based on the image coordinates includes: The image coordinates are transformed to obtain the original parking spot coordinates, which are the coordinates of the parking spot in the top view image of the vehicle. The coordinates of the target parking spot are determined based on the original parking spot coordinates.

6. The method according to claim 1, characterized in that, The step of performing polar coordinate transformation on the top-view image of the target vehicle based on road location information to obtain the transformed image also includes: When the target vehicle is parked on a curved road, the top-view image of the target vehicle is transformed into polar coordinates based on the road location information to obtain the transformed image.

7. An automatic parking device, characterized in that, include: The transformation module is used to perform polar coordinate transformation on the top view image of the target vehicle based on the road location information to obtain the transformed image. The transformation module includes: a first determining unit and a transformation unit; The first determining unit is used to determine the radius of curvature of the current road based on the road location information; The transformation unit is used to calculate the target angle covered by the vehicle top view image, where the target angle is the central angle subtended by the target arc, and the target arc is the arc along the current road direction in the vehicle top view image; and to perform polar coordinate transformation on the vehicle top view image according to the radius of curvature and the target angle to obtain the transformed image; The first determining module is used to determine the coordinates of the target parking spot based on the transformed image. The coordinates of the target parking spot are the coordinates of the parking spot in the world coordinate system, and the parking spot is the point corresponding to the parking spot. The second determining module is used to determine the parking path of the target vehicle based on the coordinates of the target parking spot, and to control the target vehicle to park according to the parking path.

8. A vehicle, characterized in that, The vehicles include: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor to enable the at least one processor to perform the automatic parking method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the automatic parking method according to any one of claims 1-6.

10. An automatic parking system, characterized in that, The system includes roadside equipment and vehicles, with the roadside equipment positioned at locations where the road exhibits curvature changes. The roadside equipment is used to send road location information to the vehicle; The vehicle is used to determine the radius of curvature of the current road based on road location information; Calculate the target angle covered by the vehicle top-view image, where the target angle is the central angle subtended by the target arc, and the target arc is the arc along the current road direction in the vehicle top-view image; perform polar coordinate transformation on the vehicle top-view image based on the radius of curvature and the target angle to obtain the transformed image; The target parking spot coordinates are determined based on the transformed image. The target parking spot coordinates are the coordinates of the parking spot in the world coordinate system, and the parking spot is the point corresponding to the parking spot. The parking path of the target vehicle is determined based on the coordinates of the target parking spot, and the target vehicle is controlled to park according to the parking path.

Images