Parking space recognition method and device, vehicle and storage medium

Abstract

The application relates to the technical field of intelligent driving, in particular to a parking space identification method and device, a vehicle and a storage medium, wherein the method comprises the following steps: collecting a target parking space image, converting the target parking space image into a bird's-eye view image; pre-processing the bird's-eye view image to obtain a parking space image with complete parking lines, and judging whether the parking space image with complete parking lines meets a preset output condition; when the parking space image with complete parking lines meets the preset output condition, outputting a parking space deflection angle and a parking space size of the target parking space, and determining the target parking space according to the parking space deflection angle and the parking space size. Therefore, the problem that a large amount of data required by deep learning of a parking space identification method in the related art is high in cost is solved, the detection method has universality, can output the parking space more accurately, and can guide a driver to park a vehicle.

Description

Technical Field

[0001] This application relates to the field of intelligent driving technology, and in particular to a parking space recognition method, device, vehicle, and storage medium. Background Technology

[0002] Currently, in the field of intelligent driving, parking space recognition mostly adopts deep learning methods. First, a large number of parking space images with different postures must be collected, then labeled, and the model trained. Finally, it is used for parking space detection. It is highly dependent on big data. Among them, a very important link in the data loop is data collection, which requires a lot of manpower, material resources and time. Moreover, the collection and labeling process is time-consuming and has a large workload. Only when the sample is comprehensive enough can the accuracy be high in the later detection.

[0003] However, accumulating sample data is time-consuming, and it still needs to be labeled and trained before it can be used for parking space recognition. On the other hand, there are shortcomings in distance measurement. The errors in the labeling process and the errors in recognition are combined, making the distance measurement error immeasurable, which urgently needs to be solved. Summary of the Invention

[0004] This application provides a parking space recognition method, device, vehicle, and storage medium, which solves the problem of high cost of big data required by deep learning in related technologies for parking space recognition methods. The detection method has universality and can output parking spaces relatively accurately to guide drivers to park their vehicles.

[0005] The first aspect of this application provides a parking space identification method, comprising the following steps: acquiring a target parking space image and converting the target parking space image into a top-view image; preprocessing the top-view image to obtain a parking space image with complete parking lines, and determining whether the parking space image with complete parking lines meets a preset output condition; when the parking space image with complete parking lines meets the preset output condition, outputting the parking space deflection angle and parking space size of the target parking space, and determining the target parking space based on the parking space deflection angle and the parking space size.

[0006] Optionally, the above-mentioned parking space recognition method further includes: when the vehicle is reversing into the parking space, preprocessing the target parking space image and detecting multiple straight lines based on a preset Hough transform; fitting two parallel straight lines that meet preset fitting conditions among the multiple straight lines into a target straight line, and calculating the midpoint coordinates and line deflection angle of the target straight line; determining the equation of the target straight line based on the midpoint coordinates and the line deflection angle, and calculating the distance between the vehicle and the parking space line based on the equation of the target straight line.

[0007] Optionally, determining whether the complete parking space image of the parking space line meets the preset output conditions includes: determining whether the parking space image is a quadrilateral of a preset format, whether the pixel area of ​​the parking space is within a preset range, and whether the cosine value of each interior angle of the quadrilateral is less than a preset value; if the parking space image is a quadrilateral of the preset format, the pixel area of ​​the parking space is within the preset range, and the cosine value of each interior angle of the quadrilateral is less than the preset value, then it is determined that the parking space image meets the preset output conditions.

[0008] Optionally, after determining whether the complete parking space image with parking lines meets the preset output conditions, the method further includes: if the complete parking space image with parking lines does not meet the preset output conditions, then output that the target parking space was not detected.

[0009] A second aspect of this application provides a parking space recognition device, comprising: a data acquisition module for acquiring a target parking space image and converting the target parking space image into a top-view image; a judgment module for preprocessing the top-view image to obtain a parking space image with complete parking lines, and judging whether the parking space image with complete parking lines meets a preset output condition; and an output module for outputting the parking space deflection angle and parking space size of the target parking space when the parking space image with complete parking lines meets the preset output condition, and determining the target parking space based on the parking space deflection angle and the parking space size.

[0010] Optionally, the above-mentioned parking space recognition device further includes: a processing module, used to preprocess the target parking space image when the vehicle reverses into the parking space, and detect multiple straight lines based on a preset Hough transform; a first calculation module, used to fit two parallel straight lines that meet preset fitting conditions among the multiple straight lines into a target straight line, and calculate the midpoint coordinates and straight line deflection angle of the target straight line; and a second calculation module, used to determine the equation of the target straight line based on the midpoint coordinates and the straight line deflection angle, and calculate the distance between the vehicle and the parking space line based on the equation of the target straight line.

[0011] Optionally, the judgment module is further configured to: determine whether the parking space image is a quadrilateral of a preset format, whether the pixel area of ​​the parking space is within a preset range, and whether the cosine value of each interior angle of the quadrilateral is less than a preset value; if the parking space image is a quadrilateral of the preset format, the pixel area of ​​the parking space is within the preset range, and the cosine value of each interior angle of the quadrilateral is less than the preset value, then determine that the parking space image satisfies the preset output condition.

[0012] Optionally, after determining whether the complete parking space image with parking lines meets the preset output conditions, the determination module is further configured to: if the complete parking space image with parking lines does not meet the preset output conditions, output that the target parking space was not detected.

[0013] A third aspect of this application provides a vehicle, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the parking space recognition method as described in the above embodiments.

[0014] A fourth aspect of this application provides a computer-readable storage medium having a computer program stored thereon, which is executed by a processor to implement the parking space identification method as described in the above embodiments.

[0015] Therefore, by acquiring images of the target parking space, converting them into top-down views, and preprocessing these images, a complete parking space image with parking lines is obtained. If the complete parking space image meets preset output conditions, the parking space deflection angle and dimensions are output. Based on these parameters, the target parking space is determined, and the preprocessed image yields the target straight line. The distance between the vehicle and the parking space line is calculated using the midpoint coordinates and deflection angle of the target straight line. This solves the problem of high costs associated with the large amounts of data required for deep learning in related parking space recognition methods. The detection method is universal and can accurately output parking spaces, guiding drivers to park their vehicles.

[0016] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0017] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0018] Figure 1 This is a flowchart of a parking space identification method provided according to an embodiment of this application;

[0019] Figure 2 This is a flowchart of parking space detection according to an embodiment of this application;

[0020] Figure 3 This is a flowchart of a vehicle line detection according to an embodiment of this application;

[0021] Figure 4 This is a block diagram of a parking space recognition device according to an embodiment of this application;

[0022] Figure 5 This is a schematic diagram of the vehicle structure provided in an embodiment of this application. Detailed Implementation

[0023] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0024] The following description, with reference to the accompanying drawings, outlines a parking space recognition method, apparatus, vehicle, and storage medium according to embodiments of this application. Addressing the issue of high costs associated with the large amounts of data required for deep learning in related parking space recognition methods mentioned in the background section, this application provides a parking space recognition method. In this method, a target parking space image is acquired, converted into a top-view image, and preprocessed to obtain a complete parking space image with parking lines. If the complete parking space image meets preset output conditions, the parking space deflection angle and size of the target parking space are output. The target parking space is determined based on the deflection angle and size, and the parking space image is preprocessed to obtain a target straight line. The distance between the vehicle and the parking space line is calculated based on the midpoint coordinates and deflection angle of the target straight line. This solves the problem of high costs associated with the large amounts of data required for deep learning in related parking space recognition methods. The detection method is universal and can accurately output parking spaces, guiding drivers to park their vehicles.

[0025] Specifically, Figure 1 This is a flowchart illustrating a parking space identification method provided in an embodiment of this application.

[0026] like Figure 1 As shown, the parking space identification method includes the following steps:

[0027] In step S101, an image of the target parking space is acquired and converted into a top-down view image.

[0028] Specifically, such as Figure 2 As shown, four cameras are connected to the server, and the acquisition parameters are set, including image resolution, image exposure, and telephoto lens focal length. The parameters are adjusted to make the images acquired by the cameras clear. The cameras acquire images of the target parking space, and the side view images detected by the cameras are converted into top view images through inverse perspective transformation.

[0029] In step S102, the top view image is preprocessed to obtain a complete parking space image with parking lines, and it is determined whether the complete parking space image with parking lines meets the preset output conditions.

[0030] Specifically, since actual parking spaces may have problems such as blurred, discontinuous, or partially obscured edges, a series of methods such as dilation and erosion are needed to process the image to display the parking space lines completely in the image, thus obtaining a complete parking space image.

[0031] Further, determining whether a complete parking space image meets preset output conditions includes: determining whether the parking space image is a quadrilateral of a preset format, whether the pixel area of ​​the parking space is within a preset range, and whether the cosine value of each interior angle of the quadrilateral is less than a preset value; if the parking space image is a quadrilateral of a preset format, the pixel area of ​​the parking space is within a preset range, and the cosine value of each interior angle of the quadrilateral is less than a preset value, then the parking space image is determined to meet the preset output conditions. Here, a quadrilateral of a preset format refers to a parking space image that is a quadrilateral and is convex.

[0032] Optionally, after determining whether the complete parking space image with parking lines meets the preset output conditions, the method further includes: if the complete parking space image with parking lines does not meet the preset output conditions, then output "No target parking space detected".

[0033] Understandably, after reading the outline of a parking space line through the camera, the outline is further judged. If the detected parking space image is a quadrilateral and convex, the pixel area of ​​the parking space is within a preset range, and the cosine value of each interior angle of the quadrilateral is less than a preset value, then the parking space image is determined to meet the preset output conditions. If the parking space image does not need to meet the preset output conditions, then the output is that no parking space was detected.

[0034] In step S103, when the complete parking space image meets the preset output conditions, the parking space deflection angle and parking space size of the target parking space are output, and the target parking space is determined based on the parking space deflection angle and parking space size.

[0035] The system measures the parking space deflection angle using a vehicle angle measuring device and detects the parking space dimensions using a camera. The parking space deflection angle and dimensions are calculated based on the lateral parking line closest to the vehicle.

[0036] It should be understood that if a complete parking space image meets the preset output conditions, the parking space deflection angle and parking space size will be output. The midpoint of the vehicle's rear axle will be used as the reference point for the vehicle. The distance from the reference point to the straight line will be calculated based on the parking space deflection angle and parking space size, which is the distance between the vehicle and the parking space. The target parking space will then be determined.

[0037] Optionally, the above-mentioned parking space recognition method further includes: when the vehicle is reversing into the parking space, preprocessing the target parking space image and detecting multiple straight lines based on a preset Hough transform; fitting two parallel straight lines that meet preset fitting conditions into a target straight line, and calculating the midpoint coordinates and line deflection angle of the target straight line; determining the equation of the target straight line based on the midpoint coordinates and line deflection angle, and calculating the distance between the vehicle and the parking space line based on the equation of the target straight line.

[0038] Specifically, such as Figure 3 As shown, when a vehicle reverses into a parking space, a camera captures an image of the parking space. This image is then processed with filtering, edge detection, dilation, and erosion. A pre-defined Hough transform detects multiple straight lines within the parking space. Since the car line is a thick solid line, for ease of calculation, parallel lines with an angle difference of less than 4 are selected during detection. This involves fitting the two outermost lines of the entire car line to a target line. The midpoint coordinates and deflection angle of this target line are then calculated, resulting in a quadratic equation about the midpoint's x-coordinate. The coefficients are derived from the least squares equation relating actual distance to pixel distance. Finally, the distance between the vehicle and the parking space line is output based on this equation. The midpoint of the vehicle's rear axle is used as the vehicle's coordinate point.

[0039] It should be noted that since the detection of parking spaces and lane lines is carried out while the vehicle is in motion, it is recommended that the vehicle speed not exceed 30 km / h when searching for a parking space. For the detection of parking lines and the output of the distance between the vehicle and the parking lines during the parking process, since the movement distance is relatively short, the vehicle speed should be controlled at around 5 km / h during the parking process.

[0040] The parking space recognition method proposed in this application involves acquiring a target parking space image, converting it into a top-view image, and preprocessing the top-view image to obtain a parking space image with complete parking lines. If the parking space image with complete parking lines meets preset output conditions, the method outputs the parking space deflection angle and parking space size of the target parking space. The target parking space is then determined based on the parking space deflection angle and parking space size. This solves the problem of high cost associated with the large amounts of data required by deep learning in related technologies for parking space recognition. The detection method is universal and can accurately output parking spaces to guide drivers in parking.

[0041] Next, the parking space recognition device according to the embodiments of this application is described with reference to the accompanying drawings.

[0042] Figure 4 This is a block diagram of a parking space recognition device according to an embodiment of this application.

[0043] like Figure 4As shown, the parking space recognition device 10 includes: a data acquisition module 100, a judgment module 200, and an output module 300.

[0044] The acquisition module 100 is used to acquire images of the target parking space and convert them into top-view images; the judgment module 200 is used to preprocess the top-view images to obtain images of parking spaces with complete parking lines and to determine whether the images of parking spaces with complete parking lines meet preset output conditions; the output module 300 is used to output the parking space deflection angle and parking space size of the target parking space when the images of parking spaces with complete parking lines meet the preset output conditions, and to determine the target parking space based on the parking space deflection angle and parking space size.

[0045] Optionally, the parking space recognition device 10 described above further includes: a processing module, used to preprocess the target parking space image when the vehicle reverses into the parking space, and detect multiple straight lines based on a preset Hough transform; a first calculation module, used to fit two parallel straight lines that meet preset fitting conditions among the multiple straight lines into a target straight line, and calculate the midpoint coordinates and straight line deflection angle of the target straight line; and a second calculation module, used to determine the equation of the target straight line based on the midpoint coordinates and straight line deflection angle, and calculate the distance between the vehicle and the parking space line based on the equation of the target straight line.

[0046] Optionally, the judgment module 200 is further configured to: determine whether the parking space image is a quadrilateral of a preset format, whether the pixel area of ​​the parking space is within a preset range, and whether the cosine value of each interior angle of the quadrilateral is less than a preset value; if the parking space image is a quadrilateral of a preset format, the pixel area of ​​the parking space is within a preset range, and the cosine value of each interior angle of the quadrilateral is less than a preset value, then the parking space image is determined to meet the preset output conditions.

[0047] Optionally, after determining whether the complete parking space image with parking lines meets the preset output conditions, the determination module 200 is further configured to: if the complete parking space image with parking lines does not meet the preset output conditions, output that no target parking space was detected.

[0048] It should be noted that the foregoing explanation of the parking space recognition method embodiment also applies to the parking space recognition device of this embodiment, and will not be repeated here.

[0049] The parking space recognition device proposed in this application acquires an image of a target parking space, converts it into a top-view image, and preprocesses the top-view image to obtain a complete parking space image with parking lines. If the complete parking space image meets preset output conditions, it outputs the parking space deflection angle and parking space size of the target parking space. The target parking space is determined based on the parking space deflection angle and parking space size. The parking space image is then preprocessed to obtain a target straight line. The distance between the vehicle and the parking space line is calculated based on the midpoint coordinates and the straight line deflection angle. This solves the problem of high cost associated with the large amounts of data required by deep learning in related technologies for parking space recognition. The detection method is universal and can accurately output parking spaces, guiding drivers to park their vehicles.

[0050] Figure 5 A schematic diagram of the structure of a vehicle provided in an embodiment of this application. The vehicle may include:

[0051] The memory 501, the processor 502, and the computer program stored on the memory 501 and capable of running on the processor 502.

[0052] When the processor 502 executes the program, it implements the parking space recognition method provided in the above embodiments.

[0053] Furthermore, the vehicle also includes:

[0054] Communication interface 503 is used for communication between memory 501 and processor 502.

[0055] The memory 501 is used to store computer programs that can run on the processor 502.

[0056] The memory 501 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0057] If the memory 501, processor 502, and communication interface 503 are implemented independently, then the communication interface 503, memory 501, and processor 502 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 5The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0058] Optionally, in a specific implementation, if the memory 501, processor 502, and communication interface 503 are integrated on a single chip, then the memory 501, processor 502, and communication interface 503 can communicate with each other through an internal interface.

[0059] Processor 502 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0060] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the parking space recognition method described above.

[0061] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0062] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0063] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0064] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0065] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0066] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0067] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0068] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A parking space recognition method characterized by, The method comprises the following steps: Collecting a target parking space image and converting the target parking space image into an overhead image; Preprocessing the overhead image to obtain a parking space image with complete parking lines and judging whether the parking space image with complete parking lines meets a preset output condition; And When the parking space image with complete parking lines meets the preset output condition, outputting a parking space deflection angle and a parking space size of the target parking space and determining the target parking space according to the parking space deflection angle and the parking space size; Further comprising: when a vehicle is reversing into a garage, preprocessing the target parking space image and detecting a plurality of straight lines based on a preset Hough transform; fitting two parallel straight lines that meet a preset fitting condition into a target straight line among the plurality of straight lines and calculating a midpoint coordinate and a straight line deflection angle of the target straight line; determining a target straight line equation according to the midpoint coordinate and the straight line deflection angle and calculating a distance between the vehicle and a parking line according to the target straight line equation; The judging whether the parking space image with complete parking lines meets the preset output condition comprises: judging whether the parking space image is a quadrilateral of a preset format, whether a pixel area of the parking space is within a preset range and whether a cosine value of each internal angle of the quadrilateral is less than a preset value; if the parking space image is the quadrilateral of the preset format, the pixel area of the parking space is within the preset range and the cosine value of each internal angle of the quadrilateral is less than the preset value, it is determined that the parking space image meets the preset output condition.

2. The method of claim 1, wherein, After judging whether the parking space image with complete parking lines meets the preset output condition, further comprising: If the parking space image with complete parking lines does not meet the preset output condition, outputting that the target parking space is not detected.

3. A parking space recognition device, characterized by, Comprise: A collecting module for collecting a target parking space image and converting the target parking space image into an overhead image; A judging module for preprocessing the overhead image to obtain a parking space image with complete parking lines and judging whether the parking space image with complete parking lines meets a preset output condition; And An output module for outputting a parking space deflection angle and a parking space size of the target parking space when the parking space image with complete parking lines meets the preset output condition and determining the target parking space according to the parking space deflection angle and the parking space size; Further comprising: a processing module for preprocessing the target parking space image when a vehicle is reversing into a garage and detecting a plurality of straight lines based on a preset Hough transform; a first calculating module for fitting two parallel straight lines that meet a preset fitting condition into a target straight line among the plurality of straight lines and calculating a midpoint coordinate and a straight line deflection angle of the target straight line; and a second calculating module for determining a target straight line equation according to the midpoint coordinate and the straight line deflection angle and calculating a distance between the vehicle and a parking line according to the target straight line equation; The judging module is further configured to judge whether the parking space image is a quadrangle in a preset format, whether a pixel area of the parking space is within a preset range, and whether a cosine value of each internal angle of the quadrangle is less than a preset value; and determine that the parking space image satisfies the preset output condition if the parking space image is the quadrangle in the preset format, the pixel area of the parking space is within the preset range, and the cosine value of each internal angle of the quadrangle is less than the preset value.

4. The apparatus of claim 3, wherein, After judging whether the parking space image with the parking space line is complete satisfies the preset output condition, the judging module is further configured to: If the parking space image with the parking space line is complete does not satisfy the preset output condition, output that the target parking space is not detected.

5. A vehicle characterized by comprising: Comprise: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executes the program to implement the parking space identification method according to any one of claims 1-2.

6. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the parking space identification method according to any one of claims 1-2.

Images