Parking control method and device, electronic equipment and storage medium

Abstract

The application relates to a parking control method and device, electronic equipment and a storage medium. The method comprises the following steps: a target parking area is selected from a plurality of charging pile parking area regions according to vehicle model information, a current position and a remaining power of a target vehicle; a second virtual parking area image suitable for the target vehicle is determined according to a first virtual parking area image corresponding to an adjacent parking area of a used target parking area in the target parking area and a vehicle size of the target vehicle; after the target vehicle is parked in the second virtual parking area, a target distance is determined according to a vehicle height, a first correction height and a focal length of an image acquisition device; and the target vehicle is determined to be parked accurately when the target distance of the target vehicle matches a preset distance range. In this way, whether the target vehicle is parked accurately can be accurately determined, and the interference of inaccurate parking of the target vehicle on a parked vehicle in an adjacent parking area is reduced.

Description

[0001] This application is a divisional application of the invention patent application filed on August 9, 2024, with application number 202411093827.1 and entitled "Charging Pile Parking Space Control Method, Device, Electronic Equipment and Storage Medium". Technical Field

[0002] This application relates to the field of Internet of Things (IoT) technology, and in particular to a parking control method, device, electronic device, and storage medium. Background Technology

[0003] With the development of technology and the progress of society, parking spaces for new energy vehicles and charging stations are becoming increasingly common. However, there are numerous charging areas for charging stations, making it difficult for users to choose a specific charging area when they want to charge their vehicles. Furthermore, most existing parking spaces are divided into fixed parking spaces of the same size with relatively large dimensions. On the one hand, this makes it difficult to meet the charging needs of larger vehicles; on the other hand, it wastes parking space when the vehicle size is small, resulting in inefficient use of parking space.

[0004] Therefore, how to select parking and charging areas and effectively utilize parking spaces is an urgent problem to be solved. Summary of the Invention

[0005] Therefore, it is necessary to provide a parking control method, device, electronic device, and storage medium to address the aforementioned technical problems.

[0006] In a first aspect, this application provides a parking control method, the method comprising:

[0007] In response to receiving a reservation instruction for a charging station parking space for a target vehicle, the system obtains the vehicle model information, current location, remaining battery power, and a preset range of charging station parking spaces for the target vehicle; the vehicle model information includes at least the vehicle configuration; the vehicle configuration includes at least the vehicle dimensions; and the vehicle dimensions include the vehicle height.

[0008] Based on the vehicle model information, current location, and remaining battery power of the target vehicle, a target parking area is selected from the charging station parking area; the target parking area contains target parking spaces for the target vehicle to reserve in advance.

[0009] Obtain a first virtual parking space image corresponding to an adjacent used parking space of the target parking space; wherein, the first virtual parking space image contains a first virtual parking area;

[0010] Based on the first virtual parking space image and the vehicle dimensions, a second virtual parking space image is determined for the target parking space; wherein, the second virtual parking space image includes a second virtual parking area; the distance between the first long side of the first virtual parking area and the second long side of the second virtual parking area is a fixed distance; the first long side and the second long side of the same virtual parking area are located on adjacent sides;

[0011] After controlling the target vehicle to park in the second virtual parking area, the image of the target vehicle is acquired through the image acquisition device;

[0012] Based on the feature information of the target vehicle in the image, a first alternative height of the target vehicle in the image is determined; the feature information includes at least one of position information, color information, and texture information;

[0013] The first alternative height of the target vehicle is corrected according to the target correction amount to obtain the first corrected height;

[0014] The target distance is determined based on the vehicle height, the first corrected height, and the focal length of the image acquisition device;

[0015] The target distance of the target vehicle is matched with a preset distance range. If the match is successful, the target vehicle is determined to be parked accurately. The accurate parking of the target vehicle indicates that the target vehicle is located within the second virtual parking area in the second virtual parking space image.

[0016] In one embodiment, the vehicle model information further includes a first license plate character; the method further includes:

[0017] In response to the distance between the candidate vehicle and the charging pile being greater than a first threshold distance and less than or equal to a second threshold distance, the identification information of the candidate vehicle is acquired by the image acquisition device; the identification information includes at least one of a second license plate character and engine displacement;

[0018] The candidate vehicle whose identification information meets the third preset condition is determined to be the target vehicle; the target vehicle is a new energy vehicle; the third preset condition includes at least one of the following: the second license plate character is consistent with the first license plate character, the first license plate character indicates that the target vehicle is the new energy vehicle, and the engine displacement is zero.

[0019] In one embodiment, before controlling the target vehicle to park in the second virtual parking area, the method further includes:

[0020] After determining that the candidate vehicle whose identification information meets the third preset condition is the target vehicle, the parking space lock in the target parking space is unlocked.

[0021] The second virtual parking space image is displayed on the display interface of the target vehicle or the display interface of the charging software, so that the target vehicle can drive to the second virtual parking area in the second virtual parking space image and park there.

[0022] In one embodiment, the method for determining the target correction amount includes:

[0023] Obtain a training sample set; the training sample set includes N frames of first sample images labeled with the vehicle height and the target distance; N is a positive integer;

[0024] Input N frames of the first sample image into the initialization model to obtain the first two-dimensional coordinates of the first vehicle in the first sample image;

[0025] The first three-dimensional coordinates of the first vehicle are determined based on the first two-dimensional coordinates and the permutation matrix of the first vehicle in the first sample image.

[0026] The target height of the first vehicle is determined based on the first three-dimensional coordinates; the target height is used to characterize the actual predicted height of the first vehicle.

[0027] Based on the target height and body height of the first vehicle in the first sample image of the first frame, determine the error offset of the first sample image of the first frame;

[0028] The error correction amount is iterated until the difference between the error offset of the first sample image in frame 1+i and the error correction amount satisfies the convergence condition. The error correction amount obtained in this iteration is then determined as the target correction amount. i is a positive integer. 1+i is less than or equal to N.

[0029] In one embodiment, the step of correcting the first candidate height of the target vehicle according to the target correction amount to obtain a first corrected height includes:

[0030] Based on the target correction amount and the target height, determine the corrected target height;

[0031] Determine the second three-dimensional coordinates based on the corrected target height;

[0032] The second two-dimensional coordinates are determined based on the second three-dimensional coordinates and the permutation matrix;

[0033] The first corrected height is determined based on the second two-dimensional coordinates.

[0034] In one embodiment, the method further includes:

[0035] If a match fails, the system determines that the target vehicle has failed to park and outputs a warning message; the warning message is used to remind the user to adjust the parking position of the target vehicle.

[0036] Secondly, this application also provides a parking control device, the device comprising:

[0037] The acquisition module is used to, in response to receiving a reservation instruction for a charging station parking space for a target vehicle, acquire the vehicle model information, current location, remaining battery power, and charging station parking space area within a preset range of the target vehicle; the vehicle model information includes at least the vehicle configuration; the vehicle configuration includes at least the vehicle dimensions; the vehicle dimensions include the vehicle height;

[0038] The processing module is used to filter out a target parking area from the charging pile parking area based on the vehicle model information, the current location and the remaining battery power of the target vehicle; the target parking area contains target parking spaces for the target vehicle to reserve in advance.

[0039] The acquisition module is used to acquire a first virtual parking space image corresponding to an adjacent parking space that has been used by the target parking space; wherein, the first virtual parking space image includes a first virtual parking area;

[0040] The determining module is used to determine a second virtual parking space image of the target parking space based on the first virtual parking space image and the vehicle size; wherein the second virtual parking space image includes a second virtual parking area; the distance between the first long side of the first virtual parking area and the second long side of the second virtual parking area is a fixed distance; the first long side and the second long side of the same virtual parking area are located on adjacent sides;

[0041] The control module is used to perform the following steps:

[0042] After controlling the target vehicle to park in the second virtual parking area, the image of the target vehicle is acquired through the image acquisition device;

[0043] Based on the feature information of the target vehicle in the image, a first alternative height of the target vehicle in the image is determined; the feature information includes at least one of position information, color information, and texture information;

[0044] The first alternative height of the target vehicle is corrected according to the target correction amount to obtain the first corrected height;

[0045] The target distance is determined based on the vehicle height, the first corrected height, and the focal length of the image acquisition device;

[0046] The target distance of the target vehicle is matched with a preset distance range. If the match is successful, the target vehicle is determined to be parked accurately. The accurate parking of the target vehicle indicates that the target vehicle is located within the second virtual parking area in the second virtual parking space image.

[0047] Thirdly, this application also provides an electronic device, including a processor and a memory for storing processor-executable instructions; wherein the processor is configured to implement the parking control method described in any embodiment of this application when executing the computer program.

[0048] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the parking control method described in any embodiment of this application.

[0049] The aforementioned parking control method, device, electronic equipment, and storage medium can filter out a target parking area from multiple charging station parking space areas by using the target vehicle's model information, current location, and remaining battery power. This allows for convenient and quick determination of a relatively suitable parking and charging area. Furthermore, based on the first virtual parking space image corresponding to the used adjacent parking spaces within the target parking space area, and the vehicle size of the target vehicle, a second virtual parking space image suitable for the target vehicle can be determined. On one hand, this can meet the parking and charging needs of vehicles of different sizes. Compared to fixed parking spaces, each reservation can dynamically adjust the size information of the target parking space based on the usage status of the charging stations on both sides of the target parking space and the vehicle parking situation; achieving effective utilization of parking space space, thereby improving charging station revenue and accurately determining the usage status of charging stations and vehicle parking situation in each charging station parking space area. Moreover, by matching the target distance of the target vehicle with a preset distance range, if the match is successful, it can be determined that the target vehicle is parked accurately, reducing interference caused by inaccurate parking of the target vehicle to vehicles parked in adjacent parking spaces. Attached Figure Description

[0050] Figure 1 This is a flowchart illustrating a charging pile parking space control method according to an exemplary embodiment;

[0051] Figure 2 This is a schematic diagram illustrating a virtual parking space according to an exemplary embodiment;

[0052] Figure 3This is a schematic diagram illustrating a virtual parking space according to an exemplary embodiment;

[0053] Figure 4 This is a flowchart illustrating a charging pile parking space control method according to an exemplary embodiment;

[0054] Figure 5 This is a structural block diagram of a charging pile parking space control device according to an exemplary embodiment;

[0055] Figure 6 This is an internal structural diagram of an electronic device according to an exemplary embodiment. Detailed Implementation

[0056] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0057] The terms "first," "second," and "third" used in the embodiments of this application are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first," "second," or "third" may explicitly or implicitly include at least one of that feature. In the description of this application, "at least one" is used to indicate one or more; "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0058] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0059] In some embodiments, the charging pile parking space control method can be applied to an electronic device. The electronic device can be any mobile terminal or fixed terminal. The terminal can be a device that provides voice and / or data connectivity to the user. For example, the terminal can be an Internet of Things (IoT) terminal, such as a sensor device, a mobile phone (or "cellular" phone), and a computer with an IoT terminal, for example, a fixed, portable, pocket-sized, handheld, computer-embedded, or vehicle-mounted device. Portable devices can be smartwatches, smart bracelets, head-mounted devices, etc. Alternatively, the terminal can also be a device from an unmanned aerial vehicle (UAV). Alternatively, the terminal can also be a vehicle-mounted device, such as a vehicle computer with wireless communication capabilities, or a wireless terminal connected to an external vehicle computer. Alternatively, the terminal can also be a roadside device, such as a charging pile or parking space lock with wireless communication capabilities.

[0060] In some embodiments, such as Figure 1 As shown, a method for controlling parking spaces at charging stations is provided, including the following steps:

[0061] S101, in response to receiving a reservation instruction for a charging station parking space for the target vehicle, obtain the vehicle model information, current location, remaining battery power, and charging station parking space area within a preset range of the target vehicle; the vehicle model information includes at least the vehicle configuration; the vehicle configuration includes at least the vehicle size.

[0062] In this embodiment of the application, the vehicle model information may include, but is not limited to, at least one of the following: manufacturer, vehicle category, first license plate character, product serial number, and vehicle configuration.

[0063] In this embodiment of the application, the vehicle configuration may include, but is not limited to, at least one of vehicle size and drive method.

[0064] In this embodiment of the application, the vehicle dimensions may include, but are not limited to, at least one of the following: vehicle length, vehicle width, vehicle height, wheelbase, and track width.

[0065] In this application embodiment, the current location and the starting location in the following embodiments may include at least one of geographical location information and latitude and longitude information. For example, the current location may be a subway station at B street in city A; or, the current location may be 50°N latitude and 15°E longitude.

[0066] In some embodiments, the preset range can be determined based on the current location of the target vehicle. For example, the preset range can be within a four-kilometer radius of the current location.

[0067] In some embodiments, the method further includes:

[0068] Based on the vehicle model information of the target vehicle, determine whether the target vehicle is a new energy vehicle;

[0069] If the target vehicle is determined to be a new energy vehicle, the target parking area is selected from the charging pile parking area based on the vehicle model information, current location and remaining battery power.

[0070] In this application embodiment, the new energy vehicle may include, but is not limited to, at least one of hybrid electric vehicles, pure electric vehicles, and fuel cell electric vehicles.

[0071] In some embodiments, the determination of whether a target vehicle is a new energy vehicle is made by determining the number of digits in the first license plate character, whether the third letter is "D" or "F", and whether the background color of the first license plate character is green.

[0072] In some embodiments, the first license plate characters are classified and identified using classification models, segmentation models, etc., to determine whether the candidate vehicle is a new energy vehicle.

[0073] S102, a target parking area is selected from the charging pile parking area based on the vehicle model information, current location and remaining battery power of the target vehicle; the target parking area contains target parking spaces for the target vehicle to reserve in advance.

[0074] In some embodiments, based on the vehicle size in the vehicle model information, alternative parking areas with sufficient remaining space to accommodate the target vehicle can be selected from the charging station parking area; based on the remaining battery power of the target vehicle, target parking areas that can be reached with the remaining battery power can be selected from the alternative parking area.

[0075] S103, obtain the first virtual parking space image corresponding to the used adjacent parking spaces of the target parking space.

[0076] In some embodiments, the target parking area may include the 1st to the Kth virtual parking spaces; K is a positive integer and K is greater than 1. The target parking space is the jth virtual parking space, and the adjacent parking spaces are the (j-1)th virtual parking space and / or the (j+1)th virtual parking space; j is a positive integer.

[0077] In this embodiment, the virtual parking space image refers to a parking space image output on the display interface of an electronic device and / or software application. For example, the virtual parking space image is displayed on the display interface of the central control screen of the target vehicle or the display interface of the user's mobile terminal.

[0078] For example, such as Figure 2 As shown, the display interface of the first charging software displays virtual parking space images of different parking space areas.

[0079] S104, determine the second virtual parking space image of the target parking space based on the first virtual parking space image and the vehicle size.

[0080] In some embodiments, the first virtual parking space image includes a first virtual parking area; the second virtual parking space image includes a second virtual parking area; the distance between the first long side of the first virtual parking area and the second long side of the second virtual parking area is a fixed distance; the first long side and the second long side of the same virtual parking area are located on adjacent sides.

[0081] In this way, on the one hand, the parking space of the charging pile can be used precisely to improve the space utilization rate; on the other hand, by setting a fixed distance between the long sides of adjacent virtual parking areas, the space for users to get in and out of the car can be guaranteed, making it easier for the target vehicle to drive into / out of the charging pile parking space and reducing the possibility of friction and collision between different vehicles.

[0082] In this embodiment, the virtual parking area includes two long sides and two short sides.

[0083] For example, such as Figure 2 As shown, the first long side of the first virtual parking area and the second long side of the second virtual parking area are separated by a fixed distance.

[0084] In some embodiments, the size of the second virtual parking area of ​​the target parking space is the same as the size of the target vehicle, or it is floated upward by a preset value based on the vehicle size.

[0085] S105, based on the second virtual parking space image, control the target vehicle to park.

[0086] In this embodiment, the target parking area can be selected from multiple charging station parking areas by using the vehicle model information, current location, and remaining battery power of the target vehicle. This allows for convenient and quick determination of a relatively suitable parking and charging area. Furthermore, based on the first virtual parking space image corresponding to the used adjacent parking spaces of the target parking space within the target parking area, and the vehicle size of the target vehicle, a second virtual parking space image suitable for the target vehicle can be determined. On the one hand, this can meet the parking and charging needs of vehicles of different sizes. Compared to fixed parking spaces, the size information of the target parking space can be dynamically adjusted each time a reservation is made, based on the usage status of the charging stations on both sides of the target parking space and the vehicle parking situation. This achieves effective utilization of parking space space, thereby increasing the revenue of charging stations and accurately determining the usage status of charging stations and the vehicle parking situation in each charging station parking area.

[0087] In some embodiments, the step of filtering the target parking area from the charging pile parking area based on the vehicle model information of the target vehicle, the current location, and the remaining battery power includes:

[0088] Get the starting position of the start time within the preset time window;

[0089] The path information from the starting position to the current position is input into the prediction model to obtain at least one target predicted position for the next time corresponding to the current position.

[0090] A first set of regions is selected from the charging pile parking space area based on at least one of the target predicted locations; the first set of regions includes at least one first region.

[0091] A second set of regions that meets a first preset condition is selected from the first set of regions based on the remaining battery power and / or the vehicle size; the second set of regions includes at least one second region.

[0092] The second region in the second region set that meets the second preset condition is determined as the target parking space region.

[0093] In this embodiment, the preset time window can be a time window within the same day that starts at any historical time and ends at the next time after the current time. For example, the current time is t. m The preset time window starts at time t1 and ends at time t. m+1 m is a positive integer and m is greater than 1.

[0094] For example, the current time is 8:20 AM, and the time interval is 10 minutes; the start time of the preset time window can be 7:20 AM, the end time can be 8:30 AM, and the duration of the preset time window is 1 hour.

[0095] In this embodiment of the application, the path information may include, but is not limited to, the target vehicle's identification information, location information, and time information.

[0096] For example, the route information includes at least two locations. For instance, the route information could be from the user's home (first time) to subway station A (second time), and then from subway station A (second time) to company C (third time). Alternatively, the route could be from 40°N 10°E (first time) to 50°N 15°E (second time).

[0097] In this application embodiment, the prediction model may include, but is not limited to, recurrent neural networks (RNN), long short-term memory networks (LSTM), and gated recurrent units (GRU).

[0098] In some embodiments, inputting the path information from the starting position to the current position into the prediction model to obtain at least one target predicted position for the next time corresponding to the current position includes:

[0099] Input the path information from the starting position to the current position into the prediction model to obtain the predicted position and probability value;

[0100] Based on the probability value corresponding to at least one predicted location, the predicted location corresponding to the probability value that satisfies the fourth preset condition is determined as the target predicted location.

[0101] In this embodiment of the application, the probability value indicates the likelihood that the target vehicle will reach the predicted location.

[0102] In this embodiment, the fourth preset condition can be a probability value greater than or equal to a preset threshold. For example, the preset threshold can be 0.6, 0.7, etc.

[0103] In some embodiments, a first set of regions that are less than a first distance from the target predicted location is selected from the charging pile parking space region.

[0104] For example, the charging pile parking area includes area A, area B, area C and area D. The distances of the four areas from the target predicted location are 1 km, 1.5 km, 2 km and 4 km respectively. The first distance is 2 km, so area A, area B and area C are determined to belong to the first area set.

[0105] In this embodiment of the application, distance may include straight-line distance and / or travel distance.

[0106] In some embodiments, the first preset condition includes:

[0107] The target vehicle consumes less power from its current location to reach the first area than the remaining power, and the area of ​​the remaining area in the first area is greater than or equal to the vehicle size, at least one of the following:

[0108] In this embodiment, the remaining area refers to the total area of ​​the non-parking area in the first region.

[0109] For example, in the first region A, the area of ​​the parked area is S1, the area of ​​the unparked area is S2, and the vehicle body area is determined to be S3 based on the vehicle size. If S2 is greater than S3, and other preset conditions are met, then the first region A is determined to belong to the second region set.

[0110] In this embodiment, the influence of historical location on the predicted target location can be considered to improve the accuracy and effectiveness of the predicted target location. Furthermore, the predicted target location that the user intends to visit in the future can be predicted based on historical paths. This allows the selection of charging station parking areas between the current location and the predicted target location as a first set of areas, reducing the need to travel to charging station parking areas in the opposite direction to the predicted target location, thus saving energy and time. A second set of areas is then selected based on remaining battery power and / or vehicle size, allowing for the selection of more suitable charging station parking spaces nearby. Finally, the second area that meets the second preset condition is selected as the target parking area, achieving intelligent selection of charging station parking spaces and improving the user experience.

[0111] In some embodiments, determining the second region in the second region set that satisfies the second preset condition as the target parking space region includes:

[0112] Based on the current location and at least one predicted target location, at least one predicted path is determined;

[0113] Based on the similarity between the predicted path and at least one historical path, the maximum similarity is determined as the target similarity of the predicted path;

[0114] The predicted path with the highest target similarity is determined as the target path;

[0115] The second region corresponding to the predicted location of the target in the target path is determined as the target parking space region.

[0116] In some embodiments, the similarity between the predicted path and the historical path can be determined based on at least one of Dynamic Time Warping (DTW), Longest Common Sub-Sequence (LCSS), One Way Distance (OWD), and Edit Distance (ED).

[0117] In some embodiments, the predicted path includes a locations, the historical path includes b locations, the predicted path and the historical path differ in g locations, and the similarity can be d = (ag) / b.

[0118] In some embodiments, L predicted paths are determined based on the current location and L predicted target locations, and P historical paths are defined; the maximum similarity among the similarities between the first predicted path and the P historical paths is defined as the target similarity; the predicted path corresponding to the maximum target similarity among the L target similarities is defined as the target path; and the second region closest to the predicted target location in the target path is defined as the target parking space region.

[0119] In this embodiment of the application, since there may be multiple second regions in the second region set that can be used for parking and charging, by selecting the predicted path with the highest target similarity as the target path, the error can be further reduced and the accuracy and reliability of the target path can be improved.

[0120] In some embodiments, the vehicle model information further includes a first license plate character; the method further includes:

[0121] In response to the distance between the candidate vehicle and the charging pile being greater than a first threshold distance and less than or equal to a second threshold distance, the identification information of the candidate vehicle is acquired through an image acquisition device; the identification information includes at least one of a second license plate character and an engine displacement.

[0122] The candidate vehicle whose identification information meets the third preset condition is determined to be the target vehicle; the target vehicle is a new energy vehicle; the third preset condition includes at least one of the following: the first license plate character is consistent with the second license plate character, the first license plate character indicates that the target vehicle is the new energy vehicle, and the engine displacement is zero.

[0123] In some embodiments, the first threshold distance and the second threshold distance can be determined based on the length of the second virtual parking space image. For example, if the length of the second virtual parking space image is 5.5m, the first threshold distance can be 5.5m and the second threshold distance can be 6m.

[0124] For example, such as Figure 3 As shown, when the distance between the candidate vehicle and the charging pile is greater than the first threshold distance and less than or equal to the second threshold distance, that is, when the candidate vehicle approaches the second virtual parking space but does not enter the second virtual parking space, the identification information of the candidate vehicle is obtained through the image acquisition device.

[0125] In some embodiments, controlling the target vehicle to park based on the second virtual parking space image includes:

[0126] After determining that the candidate vehicle whose identification information meets the third preset condition is the target vehicle, the parking space lock in the target parking space is unlocked.

[0127] The second virtual parking space image is displayed on the display interface of the target vehicle or the display interface of the charging software, so that the target vehicle can drive to the second virtual parking area in the second virtual parking space image and park there.

[0128] For example, the display interface of the target vehicle can be the central control screen interface; the charging software can be located on the central control screen interface of the target vehicle, or it can be located on the screen interface of the user's mobile terminal.

[0129] In this embodiment, the parking space lock is only unlocked and the vehicle is allowed entry when the candidate vehicle is determined to be the target vehicle (a new energy vehicle) and a reserved vehicle, thus preventing non-new energy vehicles such as fuel vehicles from occupying the target parking space.

[0130] In some embodiments, the vehicle dimensions include the vehicle height; controlling the target vehicle to park based on the second virtual parking space image includes:

[0131] After controlling the target vehicle to park in the second virtual parking area, an image of the target vehicle is acquired;

[0132] Based on the feature information of the target vehicle in the image, a first alternative height of the target vehicle in the image is determined; the feature information includes at least one of position information, color information, and texture information;

[0133] Based on the vehicle height, the first alternative height, and the focal length of the image acquisition device, determine the center position of the target vehicle and the target distance of the image acquisition device.

[0134] The target distance of the target vehicle is matched with a preset distance range. If the match is successful, the target vehicle is determined to be parked accurately. The accurate parking of the target vehicle indicates that the target vehicle is located within the second virtual parking area in the second virtual parking space image.

[0135] In some embodiments, the image acquisition device may be located on the charging station, or the image acquisition device may be wirelessly connected to the charging station.

[0136] In this embodiment of the application, the alternative height indicates the two-dimensional height of the target vehicle in the image.

[0137] In this embodiment, the vehicle height indicates the three-dimensional height of the target vehicle.

[0138] In some embodiments, such as Figure 2 As shown, after the target vehicle stops in the second virtual parking area, an image of the target vehicle is acquired by an image acquisition device; the image is input into a 3D model to obtain the first alternative height of the target vehicle in the image; using the pinhole imaging principle, the center position of the target vehicle and the target distance of the image acquisition device are determined based on the vehicle height, the first alternative height and the focal length.

[0139] In some embodiments, the location information includes first two-dimensional coordinates of the center location; determining the alternative height of the target vehicle in the image based on the feature information of the target vehicle in the image includes:

[0140] The candidate height is determined based on the first two-dimensional coordinates.

[0141] For example, one way to determine the target distance is as follows: Where f indicates focal length; h1 indicates the first alternative height; h2 indicates vehicle height; S t Indicates the distance to the target.

[0142] In some embodiments, the method further includes:

[0143] If a match fails, the system determines that the target vehicle has failed to park and outputs a warning message; the warning message is used to remind the user to adjust the parking position of the target vehicle.

[0144] In some embodiments, determining that the target vehicle is parked accurately upon successful matching includes:

[0145] Output a reminder message; the reminder message is used to remind the user that the parking spot is accurate and ready for charging.

[0146] In some embodiments, the method further includes:

[0147] The virtual parking space page is displayed; the virtual parking space page includes a parking space display area and a reminder display area; the parking space display area is used to display a first virtual parking space image and / or a second virtual parking space image; the reminder display area is used to display warning information or reminder information.

[0148] For example, the virtual parking space page can be the display interface of the target vehicle or the display interface of the charging software.

[0149] In this embodiment of the application, by using the pinhole imaging principle and the alternative height (two-dimensional height) and body height (three-dimensional height) of the target vehicle in the image, the target distance between the center position of the target vehicle and the image acquisition device can be obtained relatively accurately.

[0150] In some embodiments, the training methods for the 3D model include:

[0151] Obtain the training sample set; the training sample set includes N frames of the first sample images with labeled vehicle height and target distance; N is a positive integer;

[0152] Input N frames of the first sample images into the initialization model to obtain the first two-dimensional coordinates of the first vehicle in the first sample images;

[0153] The first three-dimensional coordinates of the first vehicle are determined based on the first two-dimensional coordinates and permutation matrix of the first vehicle in the first sample image;

[0154] Based on the first three-dimensional coordinates, the target height of the first vehicle is determined; the target height is used to characterize the actual predicted height of the first vehicle.

[0155] The error offset of the first frame sample image is determined based on the target height and body height of the first vehicle in the first frame sample image.

[0156] The error correction amount is iterated until the difference between the error offset and the error correction amount of the sample image of frame 1+i satisfies the convergence condition. The error correction amount obtained in this iteration is then determined as the target correction amount, and the trained initial model is obtained. i is a positive integer; 1+i is less than or equal to N.

[0157] In some embodiments, the image acquisition device is a camera, the two-dimensional coordinates indicate the coordinates of the pixel at the center position of the vehicle in the pixel coordinate system, and the three-dimensional coordinates indicate the coordinates of the center position of the vehicle in the camera coordinate system; the camera coordinate system indicates a three-dimensional rectangular coordinate system established with the focal center of the image acquisition device as the origin and the optical axis as the z-axis.

[0158] In this embodiment of the application, the error correction amount indicates a preset initial error value between the target height and the vehicle height.

[0159] In this embodiment, the error offset indicates the actual error value between the target height and the vehicle height.

[0160] In some embodiments, the 3D model processes the image to obtain the candidate height and target height of the target vehicle. Since the 3D model itself has inherent errors, the determined candidate height and target height will also contain errors, leading to errors in the target distance calculated based on the first candidate height. Therefore, during the training of the 3D model, the error correction amount can be iteratively adjusted to make the error correction amount as close as possible to the actual error value.

[0161] For example, in the first frame image, the target height is 4, the vehicle height is 5, the error offset is 1, the error correction is 0.2, and the difference between the error offset and the error correction is 0.8. The 3D model performs the first iteration on the error correction. Then, the error offset of the second frame image is obtained, which is 0.8, and the error correction is 0.3. The 3D model performs the second iteration on the error correction. This process continues until the error offset of the (i+1)th frame image is close to the difference between the error offset and the error correction and cannot be reduced further. At this point, the sum of the target height of the target vehicle and the error correction is close to the vehicle height, and the convergence condition is satisfied, and the error correction of the (i+1)th frame image is the target correction.

[0162] In some embodiments, the method further includes:

[0163] Obtain the verification sample set; the verification sample set includes P frames of second sample images with labeled vehicle height and target distance; P is a positive integer;

[0164] Input the second sample image into the trained initialization model to obtain the first two-dimensional coordinates of the second vehicle in the second sample image;

[0165] The first three-dimensional coordinates of the second vehicle are determined based on the first two-dimensional coordinates and permutation matrix of the second vehicle in the second sample image;

[0166] Determine the target height of the second vehicle based on the first three-dimensional coordinates;

[0167] Determine the sum of the target height and the target correction amount for the second vehicle, and then determine the corrected target height for the second vehicle.

[0168] If the difference between the corrected target height and the vehicle height is within the expected range, the initialized model after training is determined to be a three-dimensional model.

[0169] In some embodiments, determining the target distance between the center position of the target vehicle and the target distance of the image acquisition device based on the vehicle height, the first alternative height, and the focal length includes:

[0170] The first alternative height of the target vehicle is corrected according to the target correction amount to obtain the first corrected height;

[0171] The target distance is determined based on the vehicle height, the first corrected height, and the focal length.

[0172] In some embodiments, correcting the first candidate height of the target vehicle according to the target correction amount to obtain a first corrected height includes:

[0173] Determine the corrected target height based on the target correction amount and the target height;

[0174] Determine the second three-dimensional coordinates based on the corrected target height;

[0175] The second two-dimensional coordinates are determined based on the second three-dimensional coordinates and the permutation matrix;

[0176] The first corrected height is determined based on the second two-dimensional coordinates.

[0177] In this embodiment, by iterating the error correction amount, the sum of the obtained error correction amount and the target height is made close to the actual body height of the target vehicle. This can correct the error of the candidate height obtained from the three-dimensional model, reduce the interference caused by the error, and improve the accuracy of the target distance.

[0178] The following provides specific examples in conjunction with any of the above embodiments:

[0179] Specific example 1: Figure 4 This is an example illustrating a parking space control method for charging piles; such as Figure 4 As shown, the charging pile parking space control method is executed by electronic equipment, and the charging pile parking space control method includes:

[0180] S401, in response to receiving a reservation instruction for a charging station parking space for the target vehicle, obtains the vehicle model information, current location, remaining battery power, and the charging station parking space area within a preset range for the target vehicle.

[0181] In one optional embodiment, the vehicle model information includes at least the vehicle configuration; the vehicle configuration includes at least the vehicle size. Based on the first license plate character in the vehicle model, it is determined whether the target vehicle is a new energy vehicle. If yes, proceed to S402; otherwise, output the reservation result as "reservation failed" and stop the reservation operation.

[0182] S402: Target parking areas are selected from the charging station parking areas based on the vehicle model information, current location, and remaining battery power of the target vehicle.

[0183] In one optional embodiment, the starting position of the starting time within a preset time window is obtained; the path information from the starting position to the current position is input into the prediction model to obtain at least one target predicted position for the next time corresponding to the current position; a first set of regions is selected from the charging pile parking space region based on at least one target predicted position; a second set of regions is selected from the first set of regions based on the remaining battery power and / or vehicle size; and a target parking space region is selected from the second set of regions.

[0184] S403, Obtain the image of the first virtual parking space corresponding to the adjacent used parking space of the target parking space.

[0185] S404, Based on the first virtual parking space image and the vehicle size, determine the second virtual parking space image of the target parking space.

[0186] S405, in response to the distance between the candidate vehicle and the charging pile being greater than a first threshold distance and less than or equal to a second threshold distance, the identification information of the candidate vehicle is acquired through the image acquisition device.

[0187] In one alternative embodiment, the identification information includes at least one of a second license plate character and an engine displacement.

[0188] S406, determine whether the alternative vehicle is the target vehicle.

[0189] In an optional embodiment, if the second license plate character of the candidate license plate is consistent with the first license plate character of the target vehicle, then the first license plate character can indicate that the target vehicle is a new energy vehicle and the candidate vehicle is the target vehicle that has been successfully booked, then the candidate vehicle is determined to be the target vehicle; if yes, proceed to S407; if no, proceed to S413.

[0190] S407 controls the unlocking of the parking space lock in the target parking space.

[0191] S408 displays a second virtual parking space image on the target vehicle's display interface or the charging software's display interface, so that the target vehicle can drive to the second virtual parking area in the second virtual parking space image and park there.

[0192] S409: After controlling the target vehicle to park in the second virtual parking area, acquire an image of the target vehicle.

[0193] S410: Based on the image of the target vehicle, determine the center position of the target vehicle and the target distance of the image acquisition device.

[0194] In one optional embodiment, a first alternative height of the target vehicle in the image is determined based on the feature information of the target vehicle in the image; the center position of the target vehicle and the target distance of the image acquisition device are determined based on the vehicle height, the first alternative height and the focal length of the image acquisition device.

[0195] S411, match the target distance of the target vehicle with the preset distance range to determine whether the match is successful.

[0196] In one optional embodiment, if the target distance is within a preset distance range, the match is considered successful. If yes, proceed to S412; otherwise, adjust the parking position of the target vehicle and proceed to S409.

[0197] S412, confirming the target vehicle's accurate parking.

[0198] In an alternative embodiment, if it is determined that the target vehicle is parked accurately, it is determined that the target vehicle can be charged using a charging station.

[0199] S413, It has been determined that the candidate vehicle is not the target vehicle.

[0200] In an optional embodiment, if it is determined that the candidate vehicle is not the target vehicle, that is, the candidate vehicle is not the reserved target vehicle, wait for other candidate vehicles to approach, and when the next candidate vehicle is detected, proceed to S406.

[0201] The aforementioned charging station parking space control method, device, electronic equipment, and storage medium can filter out a target parking space area from multiple charging station parking space areas by using the target vehicle's model information, current location, and remaining battery power. This allows for convenient and quick determination of a relatively suitable parking and charging area. Furthermore, based on the first virtual parking space image corresponding to the used adjacent parking spaces within the target parking space area, and the vehicle size of the target vehicle, a second virtual parking space image suitable for the target vehicle can be determined. On one hand, this can meet the parking and charging needs of vehicles of different sizes. Compared to fixed parking spaces, each reservation can dynamically adjust the size information of the target parking space based on the usage status of the charging stations on both sides of the target parking space and the vehicle parking situation; achieving effective utilization of parking space space, thereby increasing charging station revenue and accurately determining the usage status of charging stations and vehicle parking situation in each charging station parking space area.

[0202] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0203] Based on the same inventive concept, this application also provides a charging pile parking space control device for implementing the charging pile parking space control method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more embodiments of the charging pile parking space control device provided below can be found in the limitations of the charging pile parking space control method described above, and will not be repeated here.

[0204] In some embodiments, such as Figure 5 As shown, a charging pile parking space control device is provided, the device comprising:

[0205] The acquisition module 510 is used to, in response to receiving a reservation instruction for a target vehicle to reserve a charging station parking space, acquire the vehicle model information, current location, remaining battery power, and charging station parking space area within a preset range of the target vehicle; the vehicle model information includes at least the vehicle configuration; the vehicle configuration includes at least the vehicle size;

[0206] The first processing module 520 is used to filter out a target parking area from the charging pile parking area based on the vehicle model information, the current location and the remaining battery power of the target vehicle; the target parking area contains target parking spaces for the target vehicle to reserve in advance.

[0207] The acquisition module 510 is used to acquire the first virtual parking space image corresponding to the used adjacent parking spaces of the target parking space;

[0208] The determining module 530 is used to determine a second virtual parking space image of the target parking space based on the first virtual parking space image and the vehicle size;

[0209] The control module 540 is used to control the target vehicle to park based on the second virtual parking space image.

[0210] In some embodiments, the first processing module includes:

[0211] The first acquisition unit is used to acquire the starting position of the start time within the preset time window;

[0212] The prediction unit is used to input the path information from the starting position to the current position into the prediction model to obtain at least one target prediction position for the next time corresponding to the current position.

[0213] A processing unit is configured to filter out a first set of regions from the charging pile parking space region based on at least one of the target predicted locations; the first set of regions includes at least one first region;

[0214] The processing unit is configured to filter a second set of regions from the first set of regions that meets a first preset condition based on the remaining battery power and / or the vehicle size; the second set of regions includes at least one second region.

[0215] The processing unit is used to determine the second region in the second region set that meets the second preset condition as the target parking space region.

[0216] In some embodiments, the first preset condition includes:

[0217] The target vehicle consumes less power from its current location to reach the first area than the remaining power, and the area of ​​the remaining area in the first area is greater than or equal to the vehicle size, at least one of the following:

[0218] In some embodiments, the processing unit is configured to perform the following steps:

[0219] Based on the current location and at least one predicted target location, at least one predicted path is determined;

[0220] Based on the similarity between the predicted path and at least one historical path, the maximum similarity is determined as the target similarity of the predicted path;

[0221] The predicted path with the highest target similarity is determined as the target path;

[0222] The second region corresponding to the predicted location of the target in the target path is determined as the target parking space region.

[0223] In some embodiments, the first virtual parking space image includes a first virtual parking area; the second virtual parking space image includes a second virtual parking area; the distance between the first long side of the first virtual parking area and the second long side of the second virtual parking area is a fixed distance; the first long side and the second long side of the same virtual parking area are located on adjacent sides.

[0224] In some embodiments, the vehicle model information further includes a first license plate character; the device further includes:

[0225] The acquisition module is used to acquire the identification information of the candidate vehicle through an image acquisition device in response to the distance between the candidate vehicle and the charging pile being less than a threshold distance; the identification information includes at least one of a second license plate character and engine displacement;

[0226] The second processing module is used to determine that the candidate vehicle whose identification information meets the third preset condition is the target vehicle; the target vehicle is a new energy vehicle; the third preset condition includes at least one of the following: the first license plate character is consistent with the second license plate character, the first license plate character indicates that the target vehicle is the new energy vehicle, and the displacement is zero.

[0227] In some embodiments, the control module is configured to perform the following steps;

[0228] After determining that the candidate vehicle whose identification information meets the third preset condition is the target vehicle, the parking space lock in the target parking space is unlocked.

[0229] The second virtual parking space image is displayed on the display interface of the target vehicle or the display interface of the charging software, so that the target vehicle can drive to the second virtual parking area in the second virtual parking space image and park there.

[0230] In some embodiments, the vehicle dimensions include vehicle height; the control module includes:

[0231] The second acquisition unit is used to acquire an image of the target vehicle after controlling the target vehicle to park in the second virtual parking area;

[0232] The determining unit is configured to determine a first alternative height of the target vehicle in the image based on the feature information of the target vehicle in the image; the feature information includes at least one of position information, color information, and texture information;

[0233] The determining unit is used to determine the center position of the target vehicle and the target distance of the image acquisition device based on the vehicle height, the first alternative height and the focal length of the image acquisition device;

[0234] The determining unit is used to match the target distance of the target vehicle with a preset distance range, and if the match is successful, determine that the target vehicle is parked accurately; the accurate parking of the target vehicle indicates that the target vehicle is located in the second virtual parking area in the second virtual parking space image.

[0235] In some embodiments, the determining unit is configured to perform the following steps:

[0236] The first alternative height of the target vehicle is corrected according to the target correction amount to obtain the first corrected height;

[0237] The target distance is determined based on the vehicle height, the first corrected height, and the focal length.

[0238] Each module in the aforementioned charging pile parking space control device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of an electronic device, either in hardware form or independently of the sample processing device, or stored in the memory of the electronic device in software form, so that the processor can call and execute the operations corresponding to each module. In one embodiment, an electronic device is provided, which can be a terminal, and its internal structure diagram can be as follows: Figure 6As shown, the electronic device includes a processor, memory, communication interface, display screen, and input device connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage medium. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a charging pile parking space control method. The display screen can be an LCD screen or an e-ink screen. The input device can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the device's casing, or an external keyboard, touchpad, or mouse.

[0239] Those skilled in the art will understand that Figure 6 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the electronic device to which the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0240] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0241] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.) and / or features involved in this application are all information, data and / or features authorized by the user or fully authorized by all parties.

[0242] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0243] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0244] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A parking control method characterized by, The method comprises: In response to receiving a reservation instruction for a target vehicle to reserve a charging pile parking space, vehicle model information, a current location, a remaining power and a charging pile parking area within a preset range of the target vehicle are acquired; the vehicle model information at least comprises vehicle configuration; the vehicle configuration at least comprises vehicle size; the vehicle size comprises vehicle body height; A target parking area is selected from the charging pile parking area according to the vehicle model information, the current location and the remaining power of the target vehicle; the target parking area contains target parking spaces for the target vehicle to reserve in advance; A first virtual parking image corresponding to a used adjacent parking space of the target parking space is acquired; the first virtual parking image contains a first virtual parking area; A second virtual parking image of the target parking space is determined according to the first virtual parking image and the vehicle size; the second virtual parking image contains a second virtual parking area; the distance between the first long side of the first virtual parking area and the second long side of the second virtual parking area is a fixed distance; the first long side and the second long side of the same virtual parking area are located on adjacent two sides; After the target vehicle is controlled to stop at the second virtual parking area, an image of the target vehicle is acquired by an image acquisition device; According to the feature information of the target vehicle on the image, a first alternative height of the target vehicle on the image is determined; the feature information comprises at least one of position information, color information and texture information; According to a target correction amount, the first alternative height of the target vehicle is corrected to obtain a first corrected height; According to the vehicle body height, the first corrected height and the focal length of the image acquisition device, a target distance is determined; According to the target distance of the target vehicle and a preset distance range, matching is performed; if the matching is successful, it is determined that the target vehicle is parked accurately; the target vehicle parked accurately represents that the target vehicle is located in the second virtual parking area in the second virtual parking image; The determination method of the target correction amount comprises: A training sample set is acquired; the training sample set comprises N frames of first sample images in which the vehicle body height and the target distance are labeled; N is a positive integer; The N frames of first sample images are input into an initialized model to obtain first two-dimensional coordinates of a first vehicle in the first sample images; According to the first two-dimensional coordinates of the first vehicle in the first sample images and a permutation matrix, first three-dimensional coordinates of the first vehicle are determined; According to the first three-dimensional coordinates, a target height of the first vehicle is determined; the target height is used to represent the actual predicted height of the first vehicle; According to the target height of the first vehicle in the first frame of first sample images and the vehicle body height of the first vehicle, an error offset of the first frame of first sample images is determined; The error correction quantity is iterated until a difference between an error offset of the first sample image of the 1+i th frame and the error correction quantity satisfies a convergence condition, and the error correction quantity obtained in the current iteration is determined as the target correction quantity when the difference satisfies the convergence condition; i is a positive integer; 1+i is less than or equal to N.

2. The method of claim 1, wherein, The vehicle model information further includes first license plate characters; and the method further includes: In response to a distance between the alternative vehicle and the charging pile being greater than a first threshold distance and less than or equal to a second threshold distance, acquiring, by the image acquisition device, identification information of the alternative vehicle; the identification information includes at least one of second license plate characters and a displacement; Determining that the alternative vehicle whose identification information satisfies a third preset condition is the target vehicle; the target vehicle is a new energy vehicle; and the third preset condition includes at least one of the second license plate characters being identical to the first license plate characters, the first license plate characters representing that the target vehicle is the new energy vehicle, and the displacement being zero.

3. The method of claim 2, wherein, Before controlling the target vehicle to stop at the second virtual parking area, the method further includes: After determining that the alternative vehicle whose identification information satisfies the third preset condition is the target vehicle, controlling a parking lock in the target parking space to be unlocked; Displaying, on a display interface of the target vehicle or a display interface of charging software, the second virtual parking space image, so that the target vehicle drives to the second virtual parking area in the second virtual parking space image to stop.

4. The method of claim 1, wherein, The method further includes: According to the target correction quantity and the target height, determining a corrected target height; According to the corrected target height, determining a second three-dimensional coordinate; According to the second three-dimensional coordinate and the permutation matrix, determining a second two-dimensional coordinate; According to the second two-dimensional coordinate, determining the first corrected height.

5. The method of claim 1, wherein, The method further includes: In the case of a failed match, determining that the target vehicle fails to stop and outputting a warning information; the warning information is used to remind a user to adjust a stopping position of the target vehicle.

6. A parking control device, characterized by The device includes: An acquisition module, configured to, in response to receiving a reservation instruction of a target vehicle reserving a charging pile parking space, acquire vehicle model information of the target vehicle, a current location of the target vehicle, a remaining amount of electricity of the target vehicle, and charging pile parking area within a preset range; the vehicle model information at least includes vehicle configuration; the vehicle configuration at least includes vehicle size; and the vehicle size includes vehicle body height; A processing module, configured to filter out a target parking area from the charging pile parking area according to the vehicle model information of the target vehicle, the current location of the target vehicle, and the remaining amount of electricity of the target vehicle; and the target parking area contains a target parking space for the target vehicle to reserve in advance; The acquisition module is configured to acquire a first virtual parking space image corresponding to a used adjacent parking space of the target parking space; and the first virtual parking space image contains a first virtual parking area. determining a second virtual parking space image of the target parking space according to the first virtual parking space image and the vehicle size, wherein the second virtual parking space image comprises a second virtual parking area, a first long side of the first virtual parking area and a second long side of the second virtual parking area are at a fixed distance, and the first long side and the second long side of a same virtual parking area are located on two adjacent sides; a control module configured to perform the following steps: after controlling the target vehicle to park in the second virtual parking area, acquiring an image of the target vehicle by using an image acquisition device; determining a first candidate height of the target vehicle in the image according to feature information of the target vehicle in the image, wherein the feature information comprises at least one of position information, color information, and texture information; correcting the first candidate height of the target vehicle according to a target correction amount to obtain a first corrected height; determining a target distance according to the vehicle height, the first corrected height, and a focal length of the image acquisition device; matching the target distance of the target vehicle with a preset distance range, and determining that the target vehicle is parked accurately in a case of successful matching, wherein the target vehicle parked accurately indicates that the target vehicle is located in the second virtual parking area in the second virtual parking space image; wherein the target correction amount is determined in the following manner: obtaining a training sample set, wherein the training sample set comprises N frames of first sample images in which the vehicle height and the target distance are labeled, and N is a positive integer; inputting the N frames of first sample images into an initialized model to obtain first two-dimensional coordinates of a first vehicle in the first sample images; determining first three-dimensional coordinates of the first vehicle according to the first two-dimensional coordinates of the first vehicle in the first sample images and a permutation matrix; determining a target height of the first vehicle according to the first three-dimensional coordinates, wherein the target height is used to represent an actual predicted height of the first vehicle; determining an error offset of the first frame of first sample images according to the target height of the first vehicle in the first frame of first sample images and the vehicle height of the first vehicle; iterating the error correction amount until a difference between the error offset of the first+i frame of first sample images and the error correction amount satisfies a convergence condition, and determining that the error correction amount obtained in the iteration is the target correction amount, wherein i is a positive integer, 1+i is less than or equal to N. 7.An electronic device comprising a memory and a processor, the memory storing a computer program, wherein, The processor executes the computer program to implement the method of any one of claims 1 to 5.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 5.

Images