Parking space information determination method and device, vehicle and storage medium

Abstract

The invention relates to a parking space information determination method and device, a vehicle and a storage medium, and relates to the technical field of computers. The method comprises the following steps: acquiring a plurality of parking space aerial views in a target area; different parking space aerial views correspond to different sub-regions in the target region; one subarea comprises at least one parking space; determining a target parking space image in each parking space aerial view; the target parking space image is a parking space image with the largest parking space image area in at least one parking space image included in the parking space aerial view; and determining parking space information of a plurality of parking spaces in the target area based on the target parking space images in the plurality of parking space aerial views. Therefore, the accuracy of the parking space information of the plurality of parking spaces in the target area can be improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to the field of parking space information collection technology in a parking lot, and specifically to a method, device, vehicle and storage medium for determining parking space information. Background Art

[0002] With the continuous development of intelligent driving of automobiles, more and more users rely on the intelligent driving function of automobiles. The automatic parking function is an important function of automobile intelligent driving, which is used to assist or replace users in parking. At present, the verification requirements for the automatic parking function are getting higher and higher. In order to realize efficient and rapid verification of the intelligent parking function of the vehicle, it is necessary to verify the intelligent parking function of the vehicle based on the parking space information. The higher the accuracy of the parking space information, the more accurate the verification result of the intelligent parking function of the vehicle.

[0003] In the related technology, the acquisition area is planned, the parking space coordinate point information is obtained based on the city map, the acquisition points are sampled and output, the parking space is retrieved and the parking space information is extracted according to the acquisition point input coordinate point, and the extracted parking space information is submitted to the database for storage. This method obtains the coordinate points of the parking space through network data and extracts the parking space information. The parking space information accuracy of this method is low and cannot be used to verify the intelligent parking function of the vehicle. Therefore, how to improve the accuracy of the collected parking space information is a technical problem that needs to be solved urgently. Summary of the invention

[0004] The present application provides a method, device, vehicle and storage medium for determining parking space information, so as to at least solve the technical problem of low accuracy in the acquisition of parking space information in the related art. The technical solution of the present application is as follows:

[0005] According to a first aspect of the present application, a method for determining parking space information is provided, the method comprising: obtaining multiple parking space bird's-eye views within a target area; different parking space bird's-eye views correspond to different sub-areas within the target area; a sub-area includes at least one parking space; determining a target parking space image in each parking space bird's-eye view; the target parking space image is a parking space image with the largest parking space image area among at least one parking space image included in the parking space bird's-eye view; based on the target parking space image in the multiple parking space bird's-eye views, determining parking space information of multiple parking spaces within the target area.

[0006] According to the above technical means, the parking space image with the largest parking space image area in the parking space bird's-eye view is determined as the target parking space image, so that the target parking space image is the parking space image with the highest accuracy in each parking space bird's-eye view, and based on the target parking space images of multiple parking space bird's-eye views, multiple parking spaces in the target area are determined, thereby improving the accuracy of the parking space information of the multiple parking spaces in the target area, so as to perform intelligent parking verification on the vehicle based on the high-precision parking space information, thereby realizing efficient and rapid verification of the intelligent parking function.

[0007] In a possible implementation, determining a target parking space image in each parking space bird's-eye view includes: for each parking space bird's-eye view, extracting vertex coordinates of each parking space image in the parking space bird's-eye view; and determining the target parking space image in the parking space bird's-eye view based on the vertex coordinates of each parking space image in the parking space bird's-eye view.

[0008] According to the above technical means, the vertex coordinates contain the precise location information of the parking spaces in the sub-area corresponding to the parking space bird's-eye view. Based on the vertex coordinates of each parking space image in the parking space bird's-eye view, the target parking space image with the largest parking space image area in the parking space bird's-eye view can be more accurately determined, thereby improving the accuracy of the target parking space image, thereby improving the accuracy of the parking space information of multiple parking spaces in the target area.

[0009] In another possible implementation, the parking space bird's-eye view also includes: an image of a collection device used to generate the parking space bird's-eye view; the vertex coordinates include: vertex relative coordinates; the vertex relative coordinates are determined based on the position of the image of the collection device in the parking space bird's-eye view; based on the vertex coordinates of each parking space image in the parking space bird's-eye view, a target parking space image in the parking space bird's-eye view is determined, including: for each parking space bird's-eye view, based on the vertex relative coordinates of each parking space image in the parking space bird's-eye view, determining the relative distance between each parking space image in the parking space bird's-eye view and the image of the collection device; determining the parking space image with the shortest relative distance as the target parking space image in the parking space bird's-eye view.

[0010] According to the above technical means, relative coordinates can reduce the errors caused by changes in the position of the acquisition equipment. Based on the relative coordinates of the vertices of each parking space image in the parking space bird's-eye view, the relative distance can be determined more accurately, thereby more accurately determining the target parking space image in the parking space bird's-eye view, thereby improving the accuracy of the parking space information of multiple parking spaces in the target area.

[0011] In another possible implementation, the vertex coordinates include: vertex absolute coordinates; the parking space information includes: parking space length, parking space width and parking space type; based on the target parking space images in multiple parking space bird's-eye views, determining the parking space information of multiple parking spaces in the target area, including: based on the vertex absolute coordinates of the target parking space images in the multiple parking space bird's-eye views, determining the vertex absolute coordinates of the multiple parking spaces in the target area; for each of the multiple parking spaces in the target area, based on the vertex absolute coordinates of each parking space, determining the parking space length and parking space width of each parking space; based on the parking space length and parking space width of each parking space, determining the angle between two adjacent parking space lines of each parking space; determining the parking space type of each parking space according to the angle between two adjacent parking space lines, the parking space length and the parking space width of each parking space.

[0012] According to the above technical means, the absolute coordinates provide detailed information of the parking space vertices in the parking space image. Based on the absolute coordinates of the vertices of the parking space image, the parking space length and parking space width of each parking space in the target area can be determined more accurately, thereby more accurately determining the parking space type, thereby improving the accuracy of the parking space information of multiple parking spaces in the target area.

[0013] In another possible implementation, based on the absolute coordinates of the vertices of the target parking space image in each parking space bird's-eye view, determining the absolute coordinates of the vertices of multiple parking spaces in the target area includes: based on the absolute coordinates of the vertices of the target parking space image in each parking space bird's-eye view, judging whether the target parking spaces corresponding to the target parking space images in two adjacent parking space bird's-eye views belong to the same parking space; when the target parking spaces corresponding to the target parking space images in two adjacent parking space bird's-eye views belong to the same parking space, determining the average value of the absolute coordinates of the vertices of the target parking space images in the two adjacent parking space bird's-eye views as the absolute coordinates of the vertices of the parking spaces in the target area; when the target parking spaces corresponding to the target parking space images in two adjacent parking space bird's-eye views do not belong to the same parking space, respectively determining the absolute coordinates of the vertices of the target parking space images in the two adjacent parking space bird's-eye views as the absolute coordinates of the vertices of the parking spaces in the target area.

[0014] According to the above technical means, whether the target parking space corresponding to the target parking space images in two adjacent parking space bird's-eye views belongs to the same parking space is judged based on the absolute coordinates of the vertices, thereby avoiding the overlapping of the target parking spaces corresponding to the target parking space images in two adjacent parking space bird's-eye views. The parking space information of multiple parking spaces in the target area can be determined more accurately, and when the target parking spaces corresponding to the target parking space images in two adjacent parking space bird's-eye views belong to the same parking space, the average coordinate calculation of the same parking space is performed, thereby reducing the data inconsistency problem caused by image acquisition angle or acquisition equipment error.

[0015] In another possible implementation, based on the absolute coordinates of the vertices of the target parking space image in each parking space bird's-eye view, determining whether the target parking spaces corresponding to the target parking space images in two adjacent parking space bird's-eye views belong to the same parking space includes: determining the target distance between the same vertices of the target parking space images in the two adjacent parking space bird's-eye views based on the absolute coordinates of the vertices of the target parking space image in each parking space bird's-eye view; when the target distance is greater than a preset distance, the target parking spaces corresponding to the target parking space images in the two adjacent parking space bird's-eye views do not belong to the same parking space; when the target distance is not greater than the preset distance, the target parking spaces corresponding to the target parking space images in the two adjacent parking space bird's-eye views belong to the same parking space.

[0016] According to the above technical means, the target distance between the same vertices of the target parking space images in two adjacent parking space bird's-eye views is used to determine whether the target parking space corresponding to the target parking space images in two adjacent parking space bird's-eye views belongs to the same parking space, thereby improving the accuracy of parking space recognition and avoiding parking space overlap caused by image overlap or close arrangement of parking spaces.

[0017] In another possible implementation, the plurality of bird's-eye views of parking spaces are obtained by stitching together a plurality of images captured by a capture device in a target area.

[0018] According to the above-mentioned technical means, by stitching together multiple images captured by the acquisition device in the target area to obtain multiple parking space bird's-eye views, possible distortion and errors in a single image captured by the acquisition device are reduced, and the accuracy of the parking space bird's-eye view is improved. In addition, the multiple parking space bird's-eye views obtained based on the stitching of multiple images can provide richer detail information, which is helpful to identify the vertices and parking space lines of multiple parking spaces in the target area, thereby improving the accuracy of the parking space information of multiple parking spaces in the target area.

[0019] In another possible implementation, when the acquisition device is acquiring images in the target area, the driving speed of the acquisition device is within a preset driving speed range, the distance between the acquisition device and the parking space line of the target area is within a preset distance range, and the angle between the acquisition device and the parking space line of the target area is within a preset angle range.

[0020] According to the above technical means, by setting the driving speed of the acquisition device, the distance between the acquisition device and the parking space lines in the target area, and the angle between the acquisition device and the parking space lines in the target area, the image quality collected by the acquisition device in the target area is ensured to be consistent, and image blur or distortion caused by the acquisition device driving too fast or too slow is avoided, thereby improving the accuracy of multiple parking space bird's-eye views. In addition, by setting the driving speed of the acquisition device within a preset driving speed range, it is ensured that the target parking space images of the multiple parking space bird's-eye views include the parking space images corresponding to each parking space in the target area, thereby avoiding missing parking spaces in the target area and improving the completeness of parking space information of multiple parking spaces in the target area.

[0021] In yet another possible implementation, the method further includes: based on the parking space information of the multiple parking spaces and a triple standard deviation method, eliminating abnormal parking space information from the parking space information of the multiple parking spaces.

[0022] According to the above technical means, abnormal parking space information in the parking space information of multiple parking spaces is eliminated by the triple standard deviation method, thereby improving the quality of the parking space information of multiple parking spaces in the target area, thereby improving the accuracy and reliability of the intelligent parking verification of vehicles.

[0023] According to the second aspect provided by the present application, a parking space information determination device is provided, the device comprising: an acquisition module and a determination module. The acquisition module is used to acquire multiple parking space bird's-eye views in a target area; different parking space bird's-eye views correspond to different sub-areas in the target area; a sub-area includes at least one parking space; the determination module is used to determine the target parking space image in each parking space bird's-eye view; the target parking space image is the parking space image with the largest parking space image area among at least one parking space image included in the parking space bird's-eye view; the determination module is also used to determine the parking space information of multiple parking spaces in the target area based on the target parking space images in the multiple parking space bird's-eye views.

[0024] In a possible implementation, the determination module is specifically used to extract the vertex coordinates of each parking space image in the parking space bird's-eye view for each parking space; and determine the target parking space image in the parking space bird's-eye view based on the vertex coordinates of each parking space image in the parking space bird's-eye view.

[0025] In another possible implementation, the parking space bird's-eye view also includes: an image of a collection device used to generate the parking space bird's-eye view; the vertex coordinates include: vertex relative coordinates; the vertex relative coordinates are determined based on the position of the image of the collection device in the parking space bird's-eye view; the determination module is specifically used to determine, for each parking space bird's-eye view, the relative distance between each parking space image in the parking space bird's-eye view and the image of the collection device based on the vertex relative coordinates of each parking space image in the parking space bird's-eye view; and determine the parking space image with the shortest relative distance as the target parking space image in the parking space bird's-eye view.

[0026] In another possible implementation, the vertex coordinates include: vertex absolute coordinates; the parking space information includes: parking space length, parking space width and parking space type; the determination module is specifically used to determine the vertex absolute coordinates of multiple parking spaces in the target area based on the vertex absolute coordinates of the target parking space images in multiple parking space bird's-eye views; for each of the multiple parking spaces in the target area, based on the vertex absolute coordinates of each parking space, determine the parking space length and parking space width of each parking space; based on the parking space length and parking space width of each parking space, determine the angle between two adjacent parking space lines of each parking space; determine the parking space type of each parking space according to the angle between two adjacent parking space lines, the parking space length and the parking space width of each parking space.

[0027] In another possible implementation, the determination module is specifically used to determine whether the target parking spaces corresponding to the target parking space images in two adjacent parking space bird's-eye views belong to the same parking space based on the absolute coordinates of the vertices of the target parking space image in each parking space bird's-eye view; when the target parking spaces corresponding to the target parking space images in two adjacent parking space bird's-eye views belong to the same parking space, the average value of the absolute coordinates of the vertices of the target parking space images in the two adjacent parking space bird's-eye views is determined as the absolute coordinates of the vertices of the parking spaces within the target area; when the target parking spaces corresponding to the target parking space images in two adjacent parking space bird's-eye views do not belong to the same parking space, the absolute coordinates of the vertices of the target parking space images in the two adjacent parking space bird's-eye views are respectively determined as the absolute coordinates of the vertices of the parking spaces within the target area.

[0028] In another possible implementation, the determination module is specifically used to determine the target distance between the same vertices of the target parking space images in two adjacent parking space bird's-eye views based on the absolute coordinates of the vertices of the target parking space image in each parking space bird's-eye view; when the target distance is greater than a preset distance, the target parking spaces corresponding to the target parking space images in the two adjacent parking space bird's-eye views do not belong to the same parking space; when the target distance is not greater than the preset distance, the target parking spaces corresponding to the target parking space images in the two adjacent parking space bird's-eye views belong to the same parking space.

[0029] In another possible implementation, the plurality of bird's-eye views of parking spaces are obtained by stitching together a plurality of images captured by a capture device in a target area.

[0030] In another possible implementation, when the acquisition device is acquiring images in the target area, the driving speed of the acquisition device is within a preset driving speed range, the distance between the acquisition device and the parking space line of the target area is within a preset distance range, and the angle between the acquisition device and the parking space line of the target area is within a preset angle range.

[0031] In yet another possible implementation, the device further includes: a rejection module; the rejection module is used to reject abnormal parking space information from the parking space information of the multiple parking spaces based on the parking space information of the multiple parking spaces and a triple standard deviation method.

[0032] According to the third aspect provided by the present application, a vehicle is provided, comprising: a processor; a memory for storing processor executable instructions; wherein the processor is configured to execute instructions to implement the method of the above-mentioned first aspect and any possible implementation manner thereof.

[0033] According to the fourth aspect provided by the present application, a computer-readable storage medium is provided. When the instructions in the computer-readable storage medium are executed by the processor of the vehicle, the vehicle is enabled to execute the method in the above-mentioned first aspect and any possible implementation method thereof.

[0034] According to the fifth aspect provided by the present application, a computer program product is provided, the computer program product comprising computer instructions, and when the computer instructions are executed on a vehicle, the vehicle executes the method of the above-mentioned first aspect and any possible implementation manner thereof.

[0035] Therefore, the above technical features of the present application have the following beneficial effects:

[0036] (1) The parking space image with the largest parking space image area in the parking space bird's-eye view is determined as the target parking space image, so that the target parking space image is the parking space image with the highest accuracy in each parking space bird's-eye view, and multiple parking spaces in a target area are determined based on the target parking space images of multiple parking space bird's-eye views, thereby improving the accuracy of parking space information of multiple parking spaces in the target area, so as to perform intelligent parking verification on the vehicle based on the high-precision parking space information, thereby realizing efficient and rapid verification of the intelligent parking function.

[0037] (2) The vertex coordinates contain the precise location information of the parking spaces in the sub-area corresponding to the parking space bird's-eye view. Based on the vertex coordinates of each parking space image in the parking space bird's-eye view, the target parking space image with the largest parking space image area in the parking space bird's-eye view can be more accurately determined, thereby improving the accuracy of the target parking space image and thus improving the accuracy of the parking space information of multiple parking spaces in the target area.

[0038] (3) Relative coordinates can reduce the error caused by the change of the position of the acquisition equipment. Based on the relative coordinates of the vertices of each parking space image in the parking space bird's-eye view, the relative distance can be determined more accurately, thereby more accurately determining the target parking space image in the parking space bird's-eye view, thereby improving the accuracy of the parking space information of multiple parking spaces in the target area.

[0039] (4) The absolute coordinates provide detailed information about the parking space vertices in the parking space image. Based on the absolute coordinates of the vertices in the parking space image, the parking space length and parking space width of each parking space in the target area can be determined more accurately, thereby more accurately determining the parking space type, thereby improving the accuracy of the parking space information of multiple parking spaces in the target area.

[0040] (5) Based on the absolute coordinates of the vertices, it is determined whether the target parking spaces corresponding to the target parking space images in two adjacent parking space bird's-eye views belong to the same parking space, thereby avoiding the overlapping of the target parking spaces corresponding to the target parking space images in two adjacent parking space bird's-eye views. The parking space information of multiple parking spaces in the target area can be determined more accurately. In addition, when the target parking spaces corresponding to the target parking space images in two adjacent parking space bird's-eye views belong to the same parking space, the average coordinates of the same parking space are calculated, thereby reducing the data inconsistency problem caused by the error of the image acquisition angle or the acquisition device.

[0041] (6) By using the target distance between the same vertices of the target parking space images in two adjacent parking space bird's-eye views, it is determined whether the target parking spaces corresponding to the target parking space images in two adjacent parking space bird's-eye views belong to the same parking space, thereby improving the accuracy of parking space recognition and avoiding parking space overlap caused by image overlap or close arrangement of parking spaces.

[0042] (7) Multiple parking space bird's-eye views are obtained by stitching together multiple images captured by the acquisition device in the target area, thereby reducing the distortion and error that may exist in a single image captured by the acquisition device, and improving the accuracy of the parking space bird's-eye view. In addition, the multiple parking space bird's-eye views obtained by stitching together multiple images can provide richer detail information, which is helpful for identifying the vertices and parking space lines of multiple parking spaces in the target area, thereby improving the accuracy of the parking space information of multiple parking spaces in the target area.

[0043] (8) By setting the driving speed of the acquisition device, the distance between the acquisition device and the parking space lines in the target area, and the angle between the acquisition device and the parking space lines in the target area, the quality of the images collected by the acquisition device in the target area is ensured to be consistent, and image blur or distortion caused by the acquisition device driving too fast or too slow is avoided, thereby improving the accuracy of multiple parking space bird's-eye views. In addition, by setting the driving speed of the acquisition device within a preset driving speed range, it is ensured that the target parking space images of the multiple parking space bird's-eye views include the parking space images corresponding to each parking space in the target area, thereby avoiding missing parking spaces in the target area and improving the completeness of the parking space information of multiple parking spaces in the target area.

[0044] (9) The triple standard deviation method is used to eliminate abnormal parking space information from multiple parking spaces, thereby improving the quality of parking space information of multiple parking spaces in the target area, thereby improving the accuracy and reliability of intelligent parking verification of vehicles.

[0045] It should be noted that the technical effects brought about by any implementation method in the second to fifth aspects can refer to the technical effects brought about by the corresponding implementation method in the first aspect, and will not be repeated here.

[0046] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification are used to explain the principles of the present application, and do not constitute an improper limitation on the present application.

[0048] Figure 1 is a flow chart showing a method for determining parking space information according to an exemplary embodiment;

[0049] Figure 2 is a bird's-eye view of parking spaces in a target area according to an exemplary embodiment;

[0050] Figure 3 is a flow chart showing another method for determining parking space information according to an exemplary embodiment;

[0051] Figure 4 is a flow chart showing another method for determining parking space information according to an exemplary embodiment;

[0052] Figure 5 is a flow chart showing another method for determining parking space information according to an exemplary embodiment;

[0053] Figure 6 is a flow chart showing another method for determining parking space information according to an exemplary embodiment;

[0054] Figure 7 is a flow chart showing another method for determining parking space information according to an exemplary embodiment;

[0055] Figure 8 is a flow chart showing another method for determining parking space information according to an exemplary embodiment;

[0056] Fig. 9 is a flow chart showing another method for determining parking space information according to an exemplary embodiment;

[0057] Fig.10 is a flow chart showing a method of determining a target parking space image according to an exemplary embodiment;

[0058] Fig.11 is a flow chart showing a method of determining a parking space size and a parking space type according to an exemplary embodiment;

[0059] Fig.12 is a flow chart showing a method of outputting parking space information according to an exemplary embodiment;

[0060] Fig.13 is a block diagram of a parking space information determination device according to an exemplary embodiment;

[0061] Fig.14 is a block diagram of a vehicle according to an exemplary embodiment. DETAILED DESCRIPTION

[0062] In order to enable ordinary persons in the art to better understand the technical solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0063] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the attached claims.

[0064] At present, with the continuous development of intelligent driving of automobiles, more and more users are using the functions of intelligent driving. The main function of automatic parking is to assist or replace users in parking. As an important functional module in the intelligent driving module of automobiles, the automatic parking function is becoming more and more popular among users. At present, the verification requirements for the automatic parking function are getting higher and higher. In order to achieve efficient, fast and sufficient verification of the intelligent parking function, it is necessary to verify the intelligent parking function of the vehicle based on the parking space information. The higher the accuracy of the parking space information, the more accurate the verification result of the intelligent parking function of the vehicle. Therefore, how to improve the accuracy of collecting parking space information is a technical problem that needs to be solved urgently.

[0065] In the related art, the acquisition area is planned, the parking space coordinate point information is obtained based on the city map, and the acquisition points are sampled and output. According to the acquired acquisition points, the coordinate points are input to retrieve the parking space and extract the parking space information, and the extracted parking space information is submitted to the database for storage. In another related art, a number of image acquisition devices are set on the periphery of the vehicle body to record the image data of the peripheral environment of the vehicle body, and the target recognition calculation is performed according to the radar device. Through the data of the image acquisition device and the radar device, the required parking space environment information data is collected and classified, and the physical size parameters of the parking space in the parking scene data segment are calibrated by the data calibration method. Finally, the calibrated parking scene data is stored in the database, and the retrieval operation is implemented through the vehicle system, or the parking scene data of the database is monitored in real time by the remote terminal to obtain the parking space information. The above two methods obtain the coordinate points of the parking space through network data and image acquisition devices respectively to obtain the parking space information. The accuracy of the parking space information is low and cannot be used to verify the intelligent parking function of the vehicle. Therefore, how to improve the accuracy of the collected parking space information is a technical problem that needs to be solved urgently.

[0066] In response to the above problems, the present application proposes a method for determining parking space information, in which the parking space image with the largest parking space image area in the parking space bird's-eye view is determined as the target parking space image, so that the target parking space image is the parking space image with the highest accuracy in each parking space bird's-eye view, and based on the target parking space images of multiple parking space bird's-eye views, multiple parking spaces in a target area are determined, thereby improving the accuracy of parking space information of multiple parking spaces in the target area, so as to perform intelligent parking verification on the vehicle based on the high-precision parking space information, thereby realizing efficient and rapid verification of the intelligent parking function.

[0067] For ease of understanding, the parking space information determination method provided in this application is specifically introduced below with reference to the accompanying drawings.

[0068] Figure 1 is a flow chart of a method for determining parking space information according to an exemplary embodiment. Figure 1 As shown, the parking space information determination method includes the following steps:

[0069] S101, obtaining a plurality of bird's-eye views of parking spaces in a target area.

[0070] The bird's-eye views of different parking spaces correspond to different sub-areas in the target area, and one sub-area includes at least one parking space.

[0071] As a possible implementation manner, the determining device may obtain a plurality of bird's-eye views of parking spaces in the target area.

[0072] Exemplarily, the acquisition device can move within the target area to acquire images of parking spaces within the target area. During the movement of the acquisition device within the target area, multiple images of the parking spaces within the target area can be acquired at preset time intervals. The determination device can perform stitching processing based on the multiple images acquired by the acquisition device to obtain multiple bird's-eye views of the parking spaces corresponding to different times.

[0073] It should be noted that the multiple parking space bird's-eye views are obtained by stitching multiple images collected by the acquisition device in the target area. When the acquisition device is collecting images in the target area, the driving speed of the acquisition device is within a preset driving speed range, the distance between the acquisition device and the parking space line of the target area is within a preset distance range, and the angle between the acquisition device and the parking space line of the target area is within a preset angle range, so as to ensure that the target parking space image of the multiple parking space bird's-eye views includes the parking space image corresponding to each parking space in the target area, so as to avoid missing the parking spaces in the target area.

[0074] As an example, the driving speed of the acquisition device is within 5km / h-15km / h, the distance between the acquisition device and the parking space line of the target area is between 0.5m-1.5m, and the angle between the acquisition device and the parking space line of the target area is between -10°-10°. The above is an example of the preset driving speed range, preset distance range, and preset angle range, which are not limited in the embodiments of the present application, and relevant technicians can set them based on actual conditions and needs.

[0075] S102: Determine a target parking space image in each parking space bird's-eye view.

[0076] The target parking space image is a parking space image with the largest parking space image area among at least one parking space image included in the parking space bird's-eye view.

[0077] As a possible implementation manner, after the determination device acquires multiple parking space bird's-eye views in the target area, it can determine the target parking space image in each of the multiple parking space bird's-eye views.

[0078] Exemplarily, the determination device may extract the vertex coordinates of each parking space image in each of the multiple parking space bird's-eye views, and determine the target parking space image in each parking space bird's-eye view based on the vertex coordinates of each parking space image in each parking space bird's-eye view.

[0079] S103: Determine parking space information of multiple parking spaces in the target area based on the target parking space images in the multiple parking space bird's-eye views.

[0080] As a possible implementation manner, after the determination device determines the target parking space image in each parking space bird's-eye view, it can determine the parking space information of multiple parking spaces in the target area based on the target parking space images in multiple parking space bird's-eye views.

[0081] Exemplarily, the parking space information includes: parking space length, parking space width and parking space type. The determination device can extract the absolute coordinates of the vertices of each parking space image in the multiple parking space bird's-eye views, thereby determining the absolute coordinates of the vertices of multiple parking spaces in the target area based on the absolute coordinates of the vertices of the target parking space image in the multiple parking space bird's-eye views, and for each of the multiple parking spaces in the target area, based on the absolute coordinates of the vertices of each parking space, determine the parking space length and parking space width of each parking space, thereby determining the angle between two adjacent parking space lines of each parking space. The determination device can determine the parking space type of each parking space based on the angle between two adjacent parking space lines of each parking space, the parking space length and the parking space width, and obtain the parking space information of multiple parking spaces in the target area. Among them, the absolute coordinates of the vertices of the parking space are the vertex coordinates determined with the initial position of the acquisition device in the target area as the origin.

[0082] It should be understood that the determination device determines the parking space image with the largest parking space image area in the parking space bird's-eye view as the target parking space image, so that the target parking space image is the parking space image with the highest accuracy in each parking space bird's-eye view, and determines multiple parking spaces in the target area based on the target parking space images of multiple parking space bird's-eye views, thereby improving the accuracy of the parking space information of the multiple parking spaces in the target area, so as to perform intelligent parking verification on the vehicle based on the high-precision parking space information, thereby realizing efficient and rapid verification of the intelligent parking function.

[0083] In some embodiments, Figure 2 is a bird's-eye view of parking spaces in a target area according to an exemplary embodiment. Figure 2 As shown, the acquisition device S4 is respectively connected to the three smart cameras S1, S2, and S3 on the acquisition vehicle. The acquisition vehicle is used to move in the target area to collect images of parking spaces. A smart camera is installed in the front, right, and rear of the acquisition vehicle. The front camera S1 is installed in the front right of the acquisition vehicle, the right rear camera S2 is installed directly behind the acquisition vehicle, and the right side camera S3 is installed on the right rearview mirror of the acquisition vehicle. The smart cameras S1, S2, and S3 can transmit the collected original images to the acquisition device S4. After receiving the original images, the acquisition device S4 performs dedistortion, splicing, and other processing on the original images according to the calibration parameters to obtain a bird's-eye view of the parking spaces. Figure 2 As shown, the parking space bird's-eye view includes a top view image of the right side of the collected vehicle, where O1 is the center point of the collected vehicle, D represents the distance between the midpoint O2 of the parking space line of parking space 1 and the center point O1 of the collected vehicle, L represents the distance between the collected vehicle and the parking space line of the target area, and α represents the angle between the collected vehicle and the parking space line of the target area. The multiple parking spaces in the target area include: parking space 1, parking space 2, parking space 3 and parking space 4, S5 represents the four vertex coordinates P0, P1, P2, P3 of parking space 1, and θ represents the angle between the two parking space lines of parking space 1.

[0084] It should be understood that different acquisition vehicles and different camera positions affect the processing effect of the stimulus image. Therefore, when determining the position of the camera on the acquisition vehicle, it is necessary to calibrate the actual vehicle parameters of the installed acquisition device S4, and set the parking space acquisition device S4 according to the calibration parameters. The embodiment of the present application does not limit the specific number of cameras on the acquisition vehicle. The above is shown as three as an example, and relevant technical personnel can set it based on actual conditions and needs. The multiple cameras on the acquisition vehicle can obtain multiple frames of images of the parking space at different angles, and transmit the original images to the acquisition module, process the images, and thus generate a bird's-eye view of the parking space, thereby extracting the vertex features of the parking space image in the parking space bird's-eye view, and determining the coordinates of the four vertices of the parking space image through the positional relationship of the vertices. In the process of the acquisition vehicle moving in the target area and acquiring the right parking space, the camera of the acquisition vehicle acquires the original image, and outputs the vertex coordinates of the right parking space according to each frame of the image. As the acquisition vehicle continues to scan, the vertex coordinate information of the parking space can be continuously updated and recorded according to the acquisition time of the acquisition vehicle. When the acquisition vehicle completes the acquisition of a row of parking spaces, the acquisition can be paused and the acquisition data can be saved, and then the next row of parking spaces can be acquired.

[0085] It should also be understood that the determination device obtains multiple parking space bird's-eye views by splicing multiple images collected by the acquisition device in the target area, thereby reducing the distortion and error that may exist in a single image collected by the acquisition device, improving the accuracy of the parking space bird's-eye view, and the multiple parking space bird's-eye views obtained based on the splicing of multiple images can provide richer detail information, which is helpful to identify the vertices and parking space lines of multiple parking spaces in the target area, thereby improving the accuracy of the parking space information of multiple parking spaces in the target area. In addition, the determination device also ensures that the image quality collected by the acquisition device in the target area is consistent by setting the driving speed of the acquisition device, the distance between the acquisition device and the parking space line in the target area, and the angle between the acquisition device and the parking space line in the target area, thereby avoiding image blur or distortion caused by the driving speed of the acquisition device being too fast or too slow, thereby improving the accuracy of the multiple parking space bird's-eye views, and by setting the driving speed of the acquisition device within the preset driving speed range, it is ensured that the target parking space image of the multiple parking space bird's-eye views includes the parking space image corresponding to each parking space in the target area, thereby avoiding missing the parking space in the target area, thereby improving the completeness of the parking space information of multiple parking spaces in the target area.

[0086] As an example, the acquisition device extracts vertex coordinate data of the parking space image in the parking space bird's-eye view as shown in Table 1 below.

[0087] Table 1

[0088]

[0089]

[0090]

[0091]

[0092]

[0093] As shown in Table 1, relative_time represents the acquisition time. Figure 2 , slots0_base_0x represents the relative coordinate of the P0 vertex of the 0th parking space image in the parking space bird's-eye view on the x-axis, slots0_base_0y represents the relative coordinate of the P0 vertex of the 0th parking space image in the parking space bird's-eye view on the y-axis, slots0_base_1x represents the relative coordinate of the P1 vertex of the 0th parking space image in the parking space bird's-eye view on the x-axis, slots0_base_1y represents the relative coordinate of the P1 vertex of the 0th parking space image in the parking space bird's-eye view on the y-axis. The relative coordinates of the axis, slots0_odom_0x represents the absolute coordinates of the P0 vertex of the 0th parking space image in the parking space bird's-eye view on the x-axis, slots0_odom_0y represents the absolute coordinates of the P0 vertex of the 0th parking space image in the parking space bird's-eye view on the y-axis, slots0_odom_1x represents the absolute coordinates of the P1 vertex of the 0th parking space image in the parking space bird's-eye view on the x-axis, slots0_odom_1y represents the absolute coordinates of the P Table 1 represents the absolute coordinate of the P1 vertex in the y-axis of the 0th parking space image in the parking space bird's-eye view, slots0_odom_2x represents the absolute coordinate of the P2 vertex in the 0th parking space image in the parking space bird's-eye view, slots0_odom_2y represents the absolute coordinate of the P2 vertex in the 0th parking space image in the parking space bird's-eye view, slots0_odom_3x represents the absolute coordinate of the P3 vertex in the 0th parking space image in the parking space bird's-eye view, slots0_odom_3y represents the absolute coordinate of the P3 vertex in the 0th parking space image in the parking space bird's-eye view, slots1_base_0x represents the relative coordinate of the P0 vertex in the 1st parking space image in the parking space bird's-eye view, slots1_base_0y represents the relative coordinate of the P0 vertex in the 1st parking space image in the parking space bird's-eye view. Table 1 can also include the relative coordinates and absolute coordinates of the vertices of other parking spaces in the target area. Table 1 only shows some examples of vertex data, and the specific value of each parameter is shown in Table 1.

[0094] In some embodiments, the determining device may extract the vertex coordinates of each parking space image in the parking space bird's-eye view, thereby determining the target parking space image in the parking space bird's-eye view based on the vertex coordinates of the parking space image. Figure 3 As shown, the above step S102 can be specifically implemented as the following steps S1021-S1022:

[0095] S1021. For each parking space bird's-eye view, extract the vertex coordinates of each parking space image in the parking space bird's-eye view.

[0096] As a possible implementation manner, for each parking space bird's-eye view of the plurality of parking space bird's-eye views, the determining device may extract the vertex coordinates of each parking space image in the parking space bird's-eye view.

[0097] Exemplarily, the determination device may import the vertex data of each parking space image in the collected parking space bird's-eye view into a database for integration processing, and extract all parking space vertex data through the keywords of the vertex coordinates of the parking space image, eliminate data irrelevant to the parking space information, and obtain the vertex coordinates of each parking space image in the parking space bird's-eye view. For example: the determination device extracts the vertex data of the parking space image under relative coordinates, first uses the find command to find the signal information containing the "slots_base" keyword, and then extracts the found signal information and its data. The determination device extracts the vertex data of the parking space image under absolute coordinates, first uses the find command to find the signal information containing the "slots_odom" keyword, and then extracts the found signal information and its data.

[0098] S1022: Determine a target parking space image in the parking space bird's-eye view based on vertex coordinates of each parking space image in the parking space bird's-eye view.

[0099] As a possible implementation manner, after the determination device extracts the vertex coordinates of each parking space image in each parking space bird's-eye view, it can determine the target parking space image in each parking space bird's-eye view based on the vertex coordinates of each parking space image in each parking space bird's-eye view.

[0100] Exemplarily, each parking space bird's-eye view includes vertex data of multiple parking space images. Due to the acquisition angle, calibration error, and splicing error of the acquisition device, the vertex data of some parking space images are inaccurate. The determination device can extract the target parking space image with the highest vertex data accuracy in each parking space bird's-eye view. The parking space image closest to the acquisition device in the parking space bird's-eye view is the target parking space image with the highest accuracy. Therefore, the determination device can determine the relative distance between each parking space image in the parking space bird's-eye view and the image of the acquisition device based on the relative coordinates of the vertices of each parking space image in the parking space bird's-eye view for each parking space, thereby determining the parking space image with the shortest relative distance as the target parking space image in each parking space bird's-eye view.

[0101] It should be understood that the vertex coordinates include the precise location information of the parking spaces in the sub-area corresponding to the parking space bird's-eye view. The determination device can more accurately determine the target parking space image with the largest parking space image area in the parking space bird's-eye view based on the vertex coordinates of each parking space image in the parking space bird's-eye view, thereby improving the accuracy of the target parking space image and thus improving the accuracy of the parking space information of multiple parking spaces in the target area.

[0102] In some other embodiments, the parking space bird's-eye view also includes: an image of a collection device used to generate the parking space bird's-eye view, and the vertex coordinates include: vertex relative coordinates, which are determined based on the position of the image of the collection device in the parking space bird's-eye view. The determination device can determine the relative distance between each parking space image in the parking space bird's-eye view and the image of the collection device based on the vertex relative coordinates of each parking space image in the parking space bird's-eye view, thereby determining the target parking space image in the parking space bird's-eye view. Therefore, if Figure 4 As shown, the above step S1022 can be specifically implemented as the following steps S1022a-S1022b:

[0103] S1022a. For each parking space bird's-eye view, determine the relative distance between each parking space image in the parking space bird's-eye view and the image of the acquisition device based on the relative coordinates of the vertices of each parking space image in the parking space bird's-eye view.

[0104] As a possible implementation method, for each parking space bird's-eye view in multiple parking space bird's-eye views, the determination device can determine the relative distance between each parking space image in the parking space bird's-eye view and the image of the acquisition device based on the relative coordinates of the vertices of each parking space image in the parking space bird's-eye view, so as to determine the target parking space image in the parking space bird's-eye view based on the relative distance.

[0105] Exemplary, combined Figure 2 In the parking space bird's-eye view, when the center point O1 of the collected vehicle is closest to the parking space image, the information collection accuracy of the parking space image is the highest. Therefore, the determination device can respectively determine the parking space image closest to the center point O1 of the collected vehicle in each parking space bird's-eye view as the target parking space image of the parking space bird's-eye view. Figure 2 The distance D from point O1 to point O2 is the distance from point O1 to the parking space image, and point O2 is the midpoint of vertices P0 and P1 of the parking space image.

[0106] As an example, the determining device may determine the relative distance between each parking space image in the parking space bird's-eye view and the image of the acquisition device based on the following expression:

[0107] O2 x =(P0 x +P1 x ) / 2;

[0108] O2 y=(P0 y +P1 y ) / 2;

[0109]

[0110] Among them, O2 x represents the coordinate of the midpoint O2 of the vertices P0 and P1 of the parking space image in the parking space bird's-eye view on the x-axis, P0 x represents the coordinate of vertex P0 on the x-axis of the parking space image in the parking space bird's-eye view, P1 x represents the coordinate of the vertex P1 on the x-axis of the parking space image in the parking space bird's-eye view, O2 y Indicates the coordinate of the midpoint O2 of the vertices P0 and P1 of the parking space image in the parking space bird's-eye view on the y-axis, P0 y The coordinate of vertex P0 on the y-axis of the parking space image in the bird's-eye view of the parking space, P1 y represents the coordinate of the vertex P1 of the parking space image in the parking space bird's-eye view on the y-axis, D represents the relative distance between the parking space image and the image of the acquisition device, O1 x Indicates the coordinate of the center point O1 of the collected vehicle on the x-axis, O1 y Indicates the y coordinate of the center point O1 of the collected vehicle.

[0111] S1022b: Determine the parking space image with the shortest relative distance as the target parking space image in the parking space bird's-eye view.

[0112] As a possible implementation manner, after the determination device determines the relative distance between each parking space image in the parking space bird's-eye view and the image of the acquisition device, it can determine that the parking space image with the shortest relative distance is the target parking space image in the parking space bird's-eye view.

[0113] Exemplarily, the determination device may take the relative distance of the first parking space image in the parking space bird's-eye view as the minimum distance value, and compare it with the relative distance of the second parking space image in the parking space bird's-eye view; when the relative distance of the second parking space image is less than the minimum distance value, the minimum distance value is updated to the relative distance of the second parking space image; when the relative distance of the second parking space image is greater than the minimum distance value, the relative distance of the third parking space image in the parking space bird's-eye view is compared with the minimum distance value, and so on, until the relative distances of all parking space images in the parking space bird's-eye view are compared, and the parking space image with the shortest relative distance in the parking space bird's-eye view is determined, which is the target parking space image.

[0114] It should be understood that relative coordinates can reduce errors caused by changes in the position of the acquisition equipment. The determination device can more accurately determine the relative distance based on the relative coordinates of the vertices of each parking space image in the parking space bird's-eye view, thereby more accurately determining the target parking space image in the parking space bird's-eye view, thereby improving the accuracy of the parking space information of multiple parking spaces in the target area.

[0115] In some other embodiments, the vertex coordinates include: vertex absolute coordinates, and the parking space information includes: parking space length, parking space width, and parking space type. The determination device can determine the vertex absolute coordinates of multiple parking spaces in the target area based on the vertex absolute coordinates of the target parking space images in the multiple parking space bird's-eye views, thereby determining the parking space length, parking space width, and parking space type of the multiple parking spaces in the target area. Figure 5 As shown, the above step S103 can be specifically implemented as the following steps S1031-S1034:

[0116] S1031 . Determine the absolute coordinates of vertices of a plurality of parking spaces in a target area based on the absolute coordinates of vertices of the target parking space images in the plurality of parking space bird's-eye views.

[0117] As a possible implementation manner, the determining device may determine the absolute coordinates of vertices of multiple parking spaces in the target area based on the absolute coordinates of vertices of the target parking space images in the multiple parking space bird's-eye views.

[0118] Exemplarily, the determination device may determine whether the target parking spaces corresponding to the target parking space images in two adjacent parking space bird's-eye views belong to the same parking space based on the absolute coordinates of the vertices of the target parking space images in each parking space bird's-eye view. Thus, if the target parking spaces corresponding to the target parking space images in two adjacent parking space bird's-eye views belong to the same parking space, the determination device may determine the average value of the absolute coordinates of the vertices of the target parking space images in the two adjacent parking space bird's-eye views as the absolute coordinates of the vertices of the parking spaces within the target area. If the target parking spaces corresponding to the target parking space images in the two adjacent parking space bird's-eye views do not belong to the same parking space, the determination device may respectively determine the absolute coordinates of the vertices of the target parking space images in the two adjacent parking space bird's-eye views as the absolute coordinates of the vertices of the parking spaces within the target area. The determination device may determine the absolute coordinates of the vertices of multiple parking spaces within the target area.

[0119] S1032: For each parking space among the multiple parking spaces in the target area, determine a parking space length and a parking space width of each parking space based on the absolute coordinates of the vertices of each parking space.

[0120] As a possible implementation manner, after the determination device determines the absolute coordinates of the vertices of multiple parking spaces in the target area, it can determine the parking space length and parking space width of each parking space in the target area based on the absolute coordinates of the vertices of each parking space.

[0121] Exemplary, combined Figure 2For each of the multiple parking spaces in the target area, the determination device can determine the distance between the vertices P0P1, the distance between the vertices P0P2, and the distance between the vertices P1P3 of the parking space based on the absolute coordinates of the vertices of the parking space, so that the distance between the vertices P0P1 is used as the parking space width, and the average value of the distance between the vertices P0P2 and the distance between the vertices P1P3 is determined as the parking space length.

[0122] As an example, the determining device may determine the parking space length and parking space width of each parking space based on the following expression:

[0123]

[0124] Among them, L P0P1 Indicates the distance between the vertices P0 and P1 of the parking space, that is, the width of the parking space, P1 x represents the coordinate of the vertex P1 of the parking space on the x-axis, P0 x represents the coordinate of the vertex P0 of the parking space on the x-axis, P1 y represents the coordinate of the vertex P1 of the parking space on the y-axis, P0 y represents the coordinate of the vertex P0 of the parking space on the y-axis, L P0P2 Represents the distance between the vertices P0 and P2 of the parking space, P2 x Represents the coordinate of the vertex P2 of the parking space on the x-axis, P2 y represents the coordinate of the vertex P2 of the parking space on the y-axis, L P1P3 Represents the distance between the vertices P1 and P3 of the parking space, P2 x Represents the coordinate of the vertex P2 of the parking space on the x-axis, P2 y Represents the coordinate of the vertex P2 of the parking space on the y-axis.

[0125] S1033: Determine the angle between two adjacent parking space lines of each parking space based on the parking space length and parking space width of each parking space.

[0126] As a possible implementation manner, after the determination device determines the parking space length and parking space width of each parking space, it can determine the angle between two adjacent parking space lines of each parking space based on the parking space length and parking space width of each parking space, so as to determine the parking space type based on the angle.

[0127] Exemplary, combined Figure 2 , the determining device may determine the angle between two adjacent parking space lines of each parking space based on the following expression:

[0128]

[0129] Among them, L P1P2 The distance between the vertices P1P2 of the parking space, θ represents the angle between two adjacent parking space lines of the parking space.

[0130] S1034: Determine the parking space type of each parking space according to the angle between two adjacent parking space lines of each parking space, the parking space length, and the parking space width.

[0131] As a possible implementation method, after the determination device determines the angle between two adjacent parking space lines of each parking space, the parking space type of each parking space can be determined according to the angle between the two adjacent parking space lines of each parking space, the parking space length and the parking space width, thereby obtaining the parking space information of each parking space.

[0132] Exemplarily, the determination device can judge the parking space type according to the size of θ, the parking space length and the parking space width. When 10°<θ<80° or 110°<θ<170°, the determination device determines that the parking space type is an inclined parking space. When 80°≤θ≤110° and the parking space width is less than the parking space length, the determination device determines that the parking space type is a vertical parking space. When 80°≤θ≤110° and the parking space width is greater than the parking space length, the determination device determines that the parking space type is a parallel parking space.

[0133] It should be understood that the absolute coordinates provide detailed information of the parking space vertices in the parking space image. The determination device can more accurately determine the parking space length and parking space width of each parking space in the target area based on the absolute coordinates of the vertices of the parking space image, thereby more accurately determining the parking space type and improving the accuracy of the parking space information of multiple parking spaces in the target area.

[0134] As an example, the determining device determines parking space information of multiple parking spaces in the target area as shown in Table 2.

[0135] Table 2

[0136]

[0137]

[0138] As shown in Table 2, the parking space information includes: serial number, parking space width, parking space length and parking space type, and the specific value of each parameter is shown in Table 2.

[0139] In some other embodiments, the determination device may also determine whether the target parking spaces corresponding to the target parking space images in two adjacent parking space bird's-eye views belong to the same parking space based on the absolute coordinates of the vertices of the target parking space images in each parking space bird's-eye view, thereby determining the absolute coordinates of the vertices of multiple parking spaces in the target area based on the absolute coordinates of the vertices of the target parking space images in multiple parking space bird's-eye views. Figure 6 As shown, the above step S1031 can be specifically implemented as the following steps S1031a-S1031c:

[0140] S1031a. Based on the absolute coordinates of the vertices of the target parking space image in each parking space bird's-eye view, determine whether the target parking spaces corresponding to the target parking space images in two adjacent parking space bird's-eye views belong to the same parking space.

[0141] As a possible implementation manner, the determination device may determine whether the target parking spaces corresponding to the target parking space images in two adjacent parking space bird's-eye views belong to the same parking space based on the absolute coordinates of the vertices of the target parking space image in each parking space bird's-eye view.

[0142] Exemplarily, the determination device may determine the target distance between the same vertices of the target parking space images in two adjacent parking space bird's-eye views based on the absolute coordinates of the vertices of the target parking space images in each parking space bird's-eye view, so that when the target distance is greater than a preset distance, the target parking spaces corresponding to the target parking space images in the two adjacent parking space bird's-eye views do not belong to the same parking space. When the target distance is not greater than the preset distance, the target parking spaces corresponding to the target parking space images in the two adjacent parking space bird's-eye views belong to the same parking space.

[0143] S1031b. When the target parking spaces corresponding to the target parking space images in two adjacent parking space bird's-eye views belong to the same parking space, an average value of the vertex absolute coordinates of the target parking space images in the two adjacent parking space bird's-eye views is determined as the vertex absolute coordinates of the parking space in the target area.

[0144] As a possible implementation method, when the target parking spaces corresponding to the target parking space images in two adjacent parking space bird's-eye views belong to the same parking space, the determination device can determine the average value of the vertex absolute coordinates of the target parking space images in the two adjacent parking space bird's-eye views as the vertex absolute coordinates of the parking space within the target area.

[0145] S1031c. When the target parking spaces corresponding to the target parking space images in two adjacent parking space bird's-eye views do not belong to the same parking space, the vertex absolute coordinates of the target parking space images in the two adjacent parking space bird's-eye views are respectively determined as the vertex absolute coordinates of the parking spaces in the target area.

[0146] As a possible implementation method, when the target parking spaces corresponding to the target parking space images in two adjacent parking space bird's-eye views do not belong to the same parking space, the determination device can respectively determine the absolute coordinates of the vertices of the target parking space images in the two adjacent parking space bird's-eye views as the absolute coordinates of the vertices of the parking spaces within the target area.

[0147] It should be understood that the determination device determines whether the target parking space corresponding to the target parking space images in two adjacent parking space bird's-eye views belongs to the same parking space based on the absolute coordinates of the vertices, thereby avoiding the overlapping of the target parking spaces corresponding to the target parking space images in two adjacent parking space bird's-eye views. The parking space information of multiple parking spaces in the target area can be determined more accurately, and when the target parking spaces corresponding to the target parking space images in two adjacent parking space bird's-eye views belong to the same parking space, the average coordinates of the same parking space are calculated, thereby reducing the data inconsistency problem caused by image acquisition angle or acquisition equipment error.

[0148] In some other embodiments, the determination device determines whether the target parking spaces corresponding to the target parking space images in two adjacent parking space bird's-eye views belong to the same parking space by determining the target distance between the same vertices of the target parking space images in the two adjacent parking space bird's-eye views. Figure 7 As shown, the above step S1031a can be specifically implemented as the following steps S701-S703:

[0149] S701: Determine a target distance between the same vertices of the target parking space images in two adjacent parking space bird's-eye views based on the absolute coordinates of the vertices of the target parking space image in each parking space bird's-eye view.

[0150] As a possible implementation manner, the determining device may determine the target distance between the same vertices of the target parking space images in two adjacent parking space bird's-eye views based on the absolute coordinates of the vertices of the target parking space image in each parking space bird's-eye view.

[0151] Exemplary, combined Figure 2 The determination device can determine the target distance between the P0 points of the target parking space images in the two adjacent parking space bird's-eye views. The determination device can determine the target distance between the same vertices of the target parking space images in the two adjacent parking space bird's-eye views based on the following expression:

[0152]

[0153] Among them, L P0P0′ P0′ represents the target distance between the same vertices of the target parking space images in two adjacent parking space bird's-eye views. x 、P0 x Respectively represent the coordinates of point P0 on the x-axis of the target parking space image in the two adjacent parking space bird's-eye views, P0′ y 、P0 y They respectively represent the coordinates of point P0 on the y-axis of the target parking space image in two adjacent parking space bird's-eye views.

[0154] S702: When the target distance is greater than the preset distance, the target parking spaces corresponding to the target parking space images in two adjacent parking space bird's-eye views do not belong to the same parking space.

[0155] As a possible implementation, when the target distance is greater than a preset distance, the determination device can determine that the target parking spaces corresponding to the target parking space images in two adjacent parking space bird's-eye views do not belong to the same parking space. The preset distance is set by relevant technicians according to actual conditions and requirements, for example: 1m, and this embodiment of the application does not limit this.

[0156] S703: When the target distance is not greater than the preset distance, the target parking spaces corresponding to the target parking space images in two adjacent parking space bird's-eye views belong to the same parking space.

[0157] As a possible implementation manner, when the target distance is not greater than a preset distance, the determination device may determine that the target parking spaces corresponding to the target parking space images in two adjacent parking space bird's-eye views belong to the same parking space.

[0158] It should be understood that the determination device judges whether the target parking spaces corresponding to the target parking space images in two adjacent parking space bird's-eye views belong to the same parking space by using the target distance between the same vertices of the target parking space images in two adjacent parking space bird's-eye views, thereby improving the accuracy of parking space recognition and avoiding parking space overlap caused by image overlap or close arrangement of parking spaces.

[0159] In some other embodiments, after the determination device determines the parking space information of multiple parking spaces in the target area, it can also eliminate abnormal data in the multiple parking space information based on the triple standard deviation method. Figure 8 As shown, the parking space information determination method provided in the embodiment of the present application further includes the following step S104:

[0160] S104: based on the parking space information of the plurality of parking spaces and the triple standard deviation method, remove abnormal parking space information from the parking space information of the plurality of parking spaces.

[0161] As a possible implementation manner, the determining device may eliminate abnormal parking space information from the parking space information of the multiple parking spaces based on the parking space information of the multiple parking spaces and a triple standard deviation method.

[0162] Exemplarily, the parking space information of multiple parking spaces finally determined by the determination device still has abnormal sizes of individual parking spaces, or has large deviations from the sizes of the collected parking spaces. Therefore, the determination device can eliminate abnormal parking spaces through the triple standard deviation method and output the final high-precision parking space information.

[0163] It should be understood that the determination device eliminates abnormal parking space information from the parking space information of multiple parking spaces through the triple standard deviation method, thereby improving the quality of the parking space information of multiple parking spaces in the target area, thereby improving the accuracy and reliability of the intelligent parking verification of the vehicle.

[0164] As an example, the parking space information after the determination device eliminates abnormal parking space information from the parking space information of multiple parking spaces is shown in Table 3.

[0165] Table 3

[0166] Serial number Parking space width Parking space length Parking space type 6 2395.897 5152.869 Vertical parking space 7 2456.112 5438.469 Vertical parking space 8 2433.275 5316.719 Vertical parking space 9 2446.792 5509.879 Vertical parking space 10 2419.846 5300.749 Vertical parking space 11 2405.486 5281.438 Vertical parking space 14 2444.846 5235.219 Vertical parking space 15 2446.287 5339.834 Vertical parking space 16 2448.078 5582.995 Vertical parking space 17 2327.762 4971.694 Vertical parking space 19 2353.486 5131.653 Vertical parking space 21 2446.52 5112.229 Vertical parking space 22 2435.146 5239.778 Vertical parking space 23 2514.085 4959.987 Vertical parking space 24 2320.092 5234.275 Vertical parking space 25 2520.327 5099.015 Vertical parking space 26 2471.064 5270.686 Vertical parking space 27 2518.649 5297.57 Vertical parking space 28 2434.98 5030.208 Vertical parking space 29 2508.28 5299.078 Vertical parking space 31 2494.533 4980.241 Vertical parking space 32 2388.57 4954.866 Vertical parking space 34 2423.17 5388.178 Vertical parking space 37 2392.166 5376.563 Vertical parking space 38 2452.157 5161.732 Vertical parking space

[0167] As shown in Table 3, it includes serial number, parking space width, parking space length and parking space type. The specific value of each parameter is shown in Table 3. Compared with Table 2, the parking space information with serial numbers 1, 2, 3, 4, 5, 12, and 13 in Table 2 is abnormal data due to the large parking space length and parking space width, and is eliminated by the determination device. The parking space information with serial numbers 18, 20, 30, 33, 35, and 36 is eliminated by the determination device due to the abnormal parking space information, and the parking space information data in Table 3 is obtained.

[0168] In some embodiments, after the determination device determines the parking space information of multiple parking spaces in the target area, it can also compare the parking space information with the actual parking space information to verify the accuracy of the parking space information. The comparison result is shown in Table 4 below.

[0169] Table 4

[0170]

[0171]

[0172] As shown in Table 4, it includes: serial number, parking space width, parking space length, parking space type, measured parking space width, measured parking space length, parking space width error, parking space length error, and measured parking space type. The specific values ​​of each parameter are shown in Table 4. The results of the determination device are compared with the measured results. The parking space width error is less than 4%, the parking space length error is less than 5%, and the parking space type has no error. The accuracy of the determination device meets the engineering requirements and can be used for statistical analysis.

[0173] Fig. 9 is a flow chart showing another method for determining parking space information according to an exemplary embodiment. Fig. 9 As shown, the process includes the following steps: S901, installation and debugging of acquisition equipment. S902, acquisition of parking space information (equivalent to the above step S101). S903, extraction of parking space vertex coordinate information (equivalent to the above step S102). S904, output of parking space information. S905, verification of the accuracy of parking space information (equivalent to the above step S103).

[0174] Fig.10 is a flow chart showing a method of determining a target parking space image according to an exemplary embodiment. Fig.10As shown, the process includes the following steps: reading the first group of data (i.e., the data of multiple parking space images in the first parking space bird's-eye view), reading the coordinate information of parking space 1, calculating the distance D from O2 to O1, judging whether the distance D is less than Dmin, and when the distance D is less than Dmin, Dmin=D, and when the distance D is not less than Dmin, judging whether it is the last parking space, and when it is not the last parking space, reading the next parking space information, and recalculating the distance D from O2 to O1 for judgment. In the case of the last parking space, respectively storing the parking space ID of Dmin=D in each group of data, for example: storing the parking space ID of the first group of data Dmin=D, storing the parking space ID of the second group of data Dmin=D, storing the parking space ID of the third group of data Dmin=D, etc., judging whether it is the last group of data, and ending in the case of the last group of data, and reading the next group of data in the case of not the last group of data, and rereading the coordinate information of parking space 1 in the group of data, and iterating the above steps until the last group of data.

[0175] Fig.11 is a flow chart showing a method of determining a parking space size and a parking space type according to an exemplary embodiment. Fig.11 As shown, the process includes the following steps: reading the parking space ID in the first group of data, reading the parking space coordinate information under the ID, calculating the size of the parking space, determining the type of the parking space, and storing the size and type of the parking space in each group of data, for example: storing the size and type of the parking space in the first group of data, storing the size and type of the parking space in the second group of data, storing the size and type of the parking space in the third group of data…, determining whether it is the last group of data, and ending if it is the last group of data; if it is not the last group of data, reading the parking space ID in the next group of data, and reading the parking space coordinate information under the ID, and iterating the above steps until the last group of data.

[0176] Fig.12 is a flow chart showing a method of outputting parking space information according to an exemplary embodiment. Fig.12As shown, the process includes the following steps: reading the parking space ID in the first group of data, reading the parking space ID in the second group of data, reading the absolute coordinate information of the parking space under the ID, calculating the distance between the parking space vertex P0 of the two groups of data, judging whether the distance is less than 1m, if the distance is less than 1m, the parking spaces of the two groups of data are the same parking spaces, if the distance is not less than 1m, the parking spaces of the two groups of data are different parking spaces, jumping to the next parking space, storing the parking space size and type of each parking space, for example: storing the parking space size and type of parking space 1, storing the parking space size and type of parking space 2, storing the parking space size and type of parking space 3..., judging whether it is the last group of data, if it is not the last group of data, reading the parking space ID in the next group of adjacent data, and reading the absolute coordinate information of the parking space under the ID, repeating the above steps until the last group of data. If it is the last group of data, respectively calculate the average value of each parking space size, eliminate abnormal parking spaces, and output the size and type of each parking space.

[0177] The above mainly introduces the solution provided by the embodiment of the present application from the perspective of the method. In order to realize the above functions, the parking space information determination device or the vehicle includes a hardware structure and / or software module corresponding to the execution of each function. It should be easily appreciated by those skilled in the art that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0178] The embodiments of the present application can exemplarily divide the functional modules of the parking space information determination device or the vehicle according to the above method. For example, the parking space information determination device or the vehicle may include various functional modules corresponding to the various functional divisions, or two or more functions may be integrated into one processing module. The above integrated modules can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiments of the present application is schematic and is only a logical functional division. There may be other division methods in actual implementation.

[0179] Fig.13 is a block diagram of a parking space information determination device according to an exemplary embodiment. Fig.13 The parking space information determining device 1300 includes: an acquisition module 1301 and a determination module 1302 .

[0180] In one possible implementation, the acquisition module 1301 is used to acquire multiple parking space bird's-eye views in a target area; different parking space bird's-eye views correspond to different sub-areas in the target area; a sub-area includes at least one parking space; the determination module 1302 is used to determine the target parking space image in each parking space bird's-eye view; the target parking space image is the parking space image with the largest parking space image area among at least one parking space image included in the parking space bird's-eye view; the determination module 1302 is also used to determine the parking space information of multiple parking spaces in the target area based on the target parking space image in the multiple parking space bird's-eye views.

[0181] In another possible implementation, the determination module 1302 is specifically used to extract the vertex coordinates of each parking space image in the parking space bird's-eye view for each parking space; and determine the target parking space image in the parking space bird's-eye view based on the vertex coordinates of each parking space image in the parking space bird's-eye view.

[0182] In another possible implementation, the parking space bird's-eye view also includes: an image of a collection device used to generate the parking space bird's-eye view; the vertex coordinates include: vertex relative coordinates; the vertex relative coordinates are determined based on the position of the image of the collection device in the parking space bird's-eye view; the determination module 1302 is specifically used to determine, for each parking space bird's-eye view, the relative distance between each parking space image in the parking space bird's-eye view and the image of the collection device based on the vertex relative coordinates of each parking space image in the parking space bird's-eye view; and determine the parking space image with the shortest relative distance as the target parking space image in the parking space bird's-eye view.

[0183] In another possible implementation, the vertex coordinates include: vertex absolute coordinates; the parking space information includes: parking space length, parking space width and parking space type; the determination module 1302 is specifically used to determine the vertex absolute coordinates of multiple parking spaces in the target area based on the vertex absolute coordinates of the target parking space images in multiple parking space bird's-eye views; for each of the multiple parking spaces in the target area, based on the vertex absolute coordinates of each parking space, determine the parking space length and parking space width of each parking space; based on the parking space length and parking space width of each parking space, determine the angle between two adjacent parking space lines of each parking space; determine the parking space type of each parking space according to the angle between two adjacent parking space lines, the parking space length and the parking space width of each parking space.

[0184] In another possible implementation, the determination module 1302 is specifically used to determine whether the target parking spaces corresponding to the target parking space images in two adjacent parking space bird's-eye views belong to the same parking space based on the absolute coordinates of the vertices of the target parking space image in each parking space bird's-eye view; when the target parking spaces corresponding to the target parking space images in two adjacent parking space bird's-eye views belong to the same parking space, the average value of the absolute coordinates of the vertices of the target parking space images in the two adjacent parking space bird's-eye views is determined as the absolute coordinates of the vertices of the parking spaces within the target area; when the target parking spaces corresponding to the target parking space images in two adjacent parking space bird's-eye views do not belong to the same parking space, the absolute coordinates of the vertices of the target parking space images in the two adjacent parking space bird's-eye views are respectively determined as the absolute coordinates of the vertices of the parking spaces within the target area.

[0185] In another possible implementation, the determination module 1302 is specifically used to determine the target distance between the same vertices of the target parking space images in two adjacent parking space bird's-eye views based on the absolute coordinates of the vertices of the target parking space image in each parking space bird's-eye view; when the target distance is greater than a preset distance, the target parking spaces corresponding to the target parking space images in the two adjacent parking space bird's-eye views do not belong to the same parking space; when the target distance is not greater than the preset distance, the target parking spaces corresponding to the target parking space images in the two adjacent parking space bird's-eye views belong to the same parking space.

[0186] In yet another possible implementation, the plurality of bird's-eye views of parking spaces are obtained by stitching together a plurality of images captured by a capture device in a target area.

[0187] In another possible implementation, when the acquisition device is acquiring images in the target area, the driving speed of the acquisition device is within a preset driving speed range, the distance between the acquisition device and the parking space line of the target area is within a preset distance range, and the angle between the acquisition device and the parking space line of the target area is within a preset angle range.

[0188] In yet another possible implementation, the apparatus further includes: a removal module 1303; the removal module 1303 is configured to remove abnormal parking space information from the parking space information of the plurality of parking spaces based on the parking space information of the plurality of parking spaces and a triple standard deviation method.

[0189] According to the above technical means, the parking space image with the largest parking space image area in the parking space bird's-eye view is determined as the target parking space image, so that the target parking space image is the parking space image with the highest accuracy in each parking space bird's-eye view, and based on the target parking space images of multiple parking space bird's-eye views, multiple parking spaces in the target area are determined, thereby improving the accuracy of the parking space information of the multiple parking spaces in the target area, so as to perform intelligent parking verification on the vehicle based on the high-precision parking space information, thereby realizing efficient and rapid verification of the intelligent parking function.

[0190] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0191] Fig.14 FIG. 1 is a block diagram of a vehicle according to an exemplary embodiment. Fig.14 As shown, vehicle 1400 includes, but is not limited to, a processor 1401 and a memory 1402 .

[0192] The memory 1402 is used to store executable instructions of the processor 1401. It can be understood that the processor 1401 is configured to execute instructions to implement the parking space information determination method in the above embodiment.

[0193] It should be noted that those skilled in the art can understand that Fig.14 The vehicle structure shown in the figure does not constitute a limitation on the vehicle, and the vehicle may include Fig.14 More or fewer components may be shown, or certain components may be combined, or the components may be arranged differently.

[0194] The processor 1401 is the control center of the vehicle, which uses various interfaces and lines to connect various parts of the entire vehicle, and executes various functions of the vehicle and processes data by running or executing software programs and / or modules stored in the memory 1402, and calling data stored in the memory 1402, so as to monitor the vehicle as a whole. The processor 1401 may include one or more processing units. Optionally, the processor 1401 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, etc., and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 1401.

[0195] The memory 1402 may be used to store software programs and various data. The memory 1402 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required by at least one functional module (such as a determination unit, a processing unit, etc.), etc. In addition, the memory 1402 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0196] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as a memory 1402 including instructions, and the above instructions can be executed by the processor 1401 of the vehicle 1400 to implement the parking space information determination method in the above embodiment.

[0197] In actual implementation, Fig.13 The functions of the acquisition module 1301, the determination module 1302 and the elimination module 1303 in the embodiment can be realized by Fig.14 The processor 1401 in the embodiment calls the computer program stored in the memory 1402 to implement. The specific execution process can refer to the description of the method part in the above embodiment, which will not be repeated here.

[0198] Optionally, the computer-readable storage medium may be a non-temporary computer-readable storage medium, for example, the non-temporary computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0199] In an exemplary embodiment, the embodiment of the present application further provides a computer program product including one or more instructions, which can be executed by the processor 1401 of the vehicle to complete the parking space information determination method in the above embodiment.

[0200] It should be noted that when the instructions in the above-mentioned computer-readable storage medium or one or more instructions in the computer program product are executed by the vehicle's processor, the various processes of the above-mentioned method embodiment are implemented, and the same technical effect as the above-mentioned method can be achieved. To avoid repetition, they will not be repeated here.

[0201] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0202] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0203] The units described as separate components may or may not be physically separated, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0204] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0205] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or the full classification part or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium, including a number of instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to execute the full classification part or part of the steps of each embodiment method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, ROM, RAM, disk or CD and other media that can store program code.

[0206] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto, and any changes or substitutions within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for determining parking space information, characterized in that: The method comprises: Acquire multiple parking space bird's-eye views in the target area; different parking space bird's-eye views correspond to different sub-areas in the target area; and a sub-area includes at least one parking space; Determine a target parking space image in each parking space bird's-eye view; the target parking space image is a parking space image with the largest parking space image area among at least one parking space image included in the parking space bird's-eye view; Based on the target parking space images in the multiple parking space bird's-eye views, parking space information of multiple parking spaces in the target area is determined.

2. The method according to claim 1, characterized in that Determining the target parking space image in each parking space bird's-eye view includes: For each parking space bird's-eye view, extracting vertex coordinates of each parking space image in the parking space bird's-eye view; A target parking space image in the parking space bird's-eye view is determined based on the vertex coordinates of each parking space image in the parking space bird's-eye view.

3. The method according to claim 2, characterized in that The parking space bird's-eye view also includes: an image of a collection device used to generate the parking space bird's-eye view; the vertex coordinates include: vertex relative coordinates; the vertex relative coordinates are determined based on the position of the image of the collection device in the parking space bird's-eye view; the determining of the target parking space image in the parking space bird's-eye view based on the vertex coordinates of each parking space image in the parking space bird's-eye view includes: For each parking space bird's-eye view, determining a relative distance between each parking space image in the parking space bird's-eye view and the image of the acquisition device based on the relative coordinates of the vertices of each parking space image in the parking space bird's-eye view; The parking space image with the shortest relative distance is determined as the target parking space image in the parking space bird's-eye view.

4. The method according to claim 2, characterized in that: The vertex coordinates include: vertex absolute coordinates; the parking space information includes: parking space length, parking space width and parking space type; the determining the parking space information of multiple parking spaces in the target area based on the target parking space images in the multiple parking space bird's-eye views includes: Determining the absolute coordinates of vertices of a plurality of parking spaces within the target area based on the absolute coordinates of vertices of the target parking space images in the plurality of parking space bird's-eye views; For each of the multiple parking spaces in the target area, based on the absolute coordinates of the vertices of each parking space, determine the parking space length and the parking space width of each parking space; Determine the angle between two adjacent parking space lines of each parking space based on the parking space length and the parking space width of each parking space; The parking space type of each parking space is determined according to the angle between two adjacent parking space lines of each parking space, the parking space length and the parking space width.

5. The method according to claim 4, characterized in that The determining the absolute coordinates of the vertices of the plurality of parking spaces in the target area based on the absolute coordinates of the vertices of the target parking space image in each parking space bird's-eye view includes: Based on the absolute coordinates of the vertices of the target parking space image in each parking space bird's-eye view, determining whether the target parking spaces corresponding to the target parking space images in two adjacent parking space bird's-eye views belong to the same parking space; When the target parking spaces corresponding to the target parking space images in the two adjacent parking space bird's-eye views belong to the same parking space, an average value of the vertex absolute coordinates of the target parking space images in the two adjacent parking space bird's-eye views is determined as the vertex absolute coordinates of the parking spaces in the target area; When the target parking spaces corresponding to the target parking space images in the two adjacent parking space bird's-eye views do not belong to the same parking space, the vertex absolute coordinates of the target parking space images in the two adjacent parking space bird's-eye views are respectively determined as the vertex absolute coordinates of the parking spaces in the target area.

6. The method according to claim 5, characterized in that The determining, based on the absolute coordinates of the vertices of the target parking space image in each parking space bird's-eye view, whether the target parking spaces corresponding to the target parking space images in two adjacent parking space bird's-eye views belong to the same parking space comprises: Determine a target distance between the same vertices of the target parking space images in the two adjacent parking space bird's-eye views based on the absolute coordinates of the vertices of the target parking space image in each parking space bird's-eye view; When the target distance is greater than the preset distance, the target parking spaces corresponding to the target parking space images in the two adjacent parking space bird's-eye views do not belong to the same parking space; When the target distance is not greater than the preset distance, the target parking spaces corresponding to the target parking space images in the two adjacent parking space bird's-eye views belong to the same parking space.

7. The method according to claim 1, characterized in that The plurality of parking space bird's-eye views are obtained by stitching together a plurality of images captured by a capture device within the target area.

8. The method according to claim 7, characterized in that During the process of the acquisition device acquiring images of the target area, the driving speed of the acquisition device is within a preset driving speed range, the distance between the acquisition device and the parking space line of the target area is within a preset distance range, and the angle between the acquisition device and the parking space line of the target area is within a preset angle range.

9. The method according to any one of claims 1 to 8, characterized in that: The method further comprises: Based on the parking space information of the multiple parking spaces and the triple standard deviation method, abnormal parking space information in the parking space information of the multiple parking spaces is eliminated.

10. A parking space information determination device, characterized in that: The device comprises: an acquisition module and a determination module; The acquisition module is used to acquire a plurality of bird's-eye views of parking spaces within a target area; different bird's-eye views of parking spaces correspond to different sub-areas within the target area; and a sub-area includes at least one parking space; The determination module is used to determine a target parking space image in each parking space bird's-eye view; the target parking space image is a parking space image with the largest parking space image area among at least one parking space image included in the parking space bird's-eye view; The determination module is further configured to determine parking space information of multiple parking spaces in the target area based on the target parking space images in the multiple parking space bird's-eye views.

11. A vehicle, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the method as claimed in any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that: When the computer-executable instructions stored in the computer-readable storage medium are executed by a processor of a vehicle, the vehicle is capable of performing the method of any one of claims 1 to 9.

13. A computer program product, characterized in that The computer program product comprises computer instructions which, when executed on a vehicle, cause the vehicle to perform the method according to any one of claims 1 to 9.

Images