Vehicle parking control method, device, equipment, storage medium and program product

Abstract

The embodiment of the invention provides a vehicle parking control method and device, equipment, a storage medium and a program product. The method includes receiving, at a central control device, a plurality of parking results for a target vehicle from a local control device deployed in association with the target vehicle, where each parking result indicates whether parking of the target vehicle meets a parking requirement; in response to determining that the plurality of parking results all indicate that the parking of the target vehicle does not meet the parking requirement, sending a sample collection instruction to a local processing device; receiving a second target image related to the target vehicle from the local processing device, wherein the second target image is used as a training sample in the training data set; and updating the machine learning model using the training data set.

Description

Technical Field

[0001] Example embodiments of the present disclosure relate generally to the field of vehicle parking control, and more particularly to methods, apparatuses, devices, storage media, and computer-generated products for shared vehicle parking control. Background Art

[0002] Shared vehicles have become an important mode of transportation. Taking two-wheeled vehicles such as shared bicycles as an example, users can use their own portable devices (such as mobile phones) to conveniently control the vehicle and complete various operations such as unlocking, locking, paying, and account management. When the user has finished using the shared bicycle, he needs to return the shared bicycle. If the return of shared bicycles is not managed and monitored, it will have a negative impact on the city's civilized construction. In view of this, it is necessary to provide a solution for managing and monitoring the parking of shared vehicles to achieve the standardized return of shared vehicles. Summary of the Invention

[0003] In a first aspect of the present disclosure, a method for vehicle parking control is provided. The method includes: receiving, at a central control device, multiple parking results for a target vehicle from a local control device deployed in association with the target vehicle, the multiple parking results being determined by a machine learning model deployed at a local processing device deployed in association with the target vehicle based on multiple first target images collected, each parking result indicating whether the target vehicle is parked in compliance with parking requirements; in response to determining that the multiple parking results all indicate that the target vehicle is parked in compliance with parking requirements, sending a sample collection instruction to the local processing device; receiving a second target image associated with the target vehicle from the local processing device, the second target image being used as a training sample in a training dataset; and updating the machine learning model using the training dataset.

[0004] In a second aspect of the present disclosure, a method for vehicle parking control is provided. The method includes: at a local processing device deployed in association with a target vehicle, in response to a parking recognition instruction for the target vehicle, utilizing a machine learning model locally deployed on the local processing device to determine, based on a plurality of first target images captured, a plurality of parking results for the target vehicle, each parking result indicating whether the parking of the target vehicle complies with parking requirements; sequentially transmitting the plurality of parking results to a central control device; upon receiving a sample capture instruction from the central control device, capturing a second target image associated with the target vehicle; and transmitting the second target image to the central control device for use as a training sample in a training dataset, the training dataset being used by the central control device to update the machine learning model.

[0005] In a third aspect of the present disclosure, a method for controlling vehicle parking is provided. The method includes: at a user device, in response to a user trigger, sending a parking request for a target vehicle to a local control device of the target vehicle; receiving a first response to the parking request from a central control device of the target vehicle, the first response including at least first parking guidance information, the first parking guidance information being received when a parking result determined based on a captured first target image indicates that the target vehicle is parked in a manner that does not comply with parking requirements; presenting the first parking guidance information to the user; receiving a second response to the parking request from the central control device, the second response including at least second parking guidance information, the second parking guidance information being received when multiple parking results determined based on multiple captured first target images all indicate that the target vehicle is parked in a manner that does not comply with parking requirements, and determining a reason for the target vehicle not being parked in a manner that does not comply with parking requirements based on the captured second target image; and presenting the second parking guidance information to the user.

[0006] In a fourth aspect of the present disclosure, a vehicle parking control apparatus is provided. The apparatus includes: a parking result receiving module configured to receive, at a central control device, a plurality of parking results for a target vehicle from a local control device deployed in association with the target vehicle, the plurality of parking results being determined by a machine learning model deployed at a local processing device deployed in association with the target vehicle based on a plurality of first target images collected, each parking result indicating whether the parking of the target vehicle complies with parking requirements; a collection instruction sending module configured to send a sample collection instruction to the local processing device in response to determining that the plurality of parking results all indicate that the parking of the target vehicle does not comply with the parking requirements; a second target image receiving module configured to receive a second target image associated with the target vehicle from the local processing device, the second target image being used as a training sample in a training dataset; and a model updating module configured to update the machine learning model using the training dataset.

[0007] In a fifth aspect of the present disclosure, a vehicle parking control apparatus is provided. The apparatus includes: a parking result determination module configured to, at a local processing device deployed in association with a target vehicle, determine, in response to a parking identification instruction for the target vehicle, a plurality of parking results for the target vehicle based on a plurality of first target images captured, using a machine learning model locally deployed on the local processing device, each parking result indicating whether the parking of the target vehicle complies with parking requirements; a parking result sending module configured to sequentially send the plurality of parking results to a central control device; a second image acquisition module configured to acquire a second target image associated with the target vehicle upon receiving a sample acquisition instruction from the central control device; and a second image sending module configured to send the second target image to the central control device for use as a training sample in a training dataset, the training dataset being used by the central control device to update the machine learning model.

[0008] In a sixth aspect of the present disclosure, a vehicle parking control apparatus is provided. The apparatus includes: a parking request sending module configured to, at a user device, send a parking request for a target vehicle to a local control device of a target vehicle in response to a user trigger; a first response receiving module configured to receive a first response to the parking request from a central control device of the target vehicle, the first response including at least first parking guidance information, the first parking guidance information being received when a parking result determined based on a captured first target image indicates that the target vehicle is parked in a manner that does not comply with parking requirements; a first presentation module configured to present the first parking guidance information to a user; a second response receiving module configured to receive a second response to the parking request from the central control device, the second response including at least second parking guidance information, the second parking guidance information being received when multiple parking results determined based on multiple captured first target images all indicate that the target vehicle is parked in a manner that does not comply with parking requirements, and a reason for the target vehicle not being parked in a manner that does not comply with parking requirements is determined based on a captured second target image; and a second presentation module configured to present the second parking guidance information to the user.

[0009] In a seventh aspect of the present disclosure, an electronic device is provided. The device includes: at least one processing unit; and at least one memory, the at least one memory being coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions, when executed by the at least one processing unit, causing the electronic device to perform the method of any one of the first to third aspects.

[0010] In an eighth aspect of the present disclosure, a computer-readable storage medium is provided, wherein a computer program is stored on the computer-readable storage medium, and the computer program can be executed by a processor to implement the method of any one of the first to third aspects.

[0011] In a ninth aspect of the present disclosure, a computer program product is provided, comprising computer-executable instructions, wherein the computer-executable instructions implement the method of any one of the first to third aspects when executed by a processor.

[0012] It should be understood that the content described in this section is not intended to limit the key features or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0014] Figure 1A and 1B A schematic diagram illustrating an example environment in which embodiments of the present disclosure can be implemented;

[0015] Figure 2 shows an interactive schematic diagram for vehicle parking control according to some embodiments of the present disclosure;

[0016] Figure 3 An example application scenario of identifying parking lines and / or determining standard parking according to some embodiments of the present disclosure is shown;

[0017] Figure 4 A flowchart illustrating an example process for vehicle parking control according to further embodiments is shown;

[0018] Figure 5 A flowchart illustrating an example process for vehicle parking control according to further embodiments is shown;

[0019] Figure 6 A flowchart illustrating an example process for vehicle parking control according to further embodiments is shown;

[0020] Figure 7 A flowchart illustrating an example process for vehicle parking control according to further embodiments is shown;

[0021] Figure 8 FIG2 shows a schematic structural block diagram of an electronic device for vehicle parking control according to certain embodiments of the present disclosure;

[0022] Figure 9 FIG2 shows a schematic structural block diagram of an electronic device for vehicle parking control according to certain embodiments of the present disclosure;

[0023] Figure 10A schematic structural block diagram of an electronic device for vehicle parking control according to certain embodiments of the present disclosure is shown; and

[0024] Figure 11 A block diagram of a device capable of implementing various embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0025] The following describes embodiments of the present disclosure in more detail with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0026] It should be noted that the titles of any section / subsection provided herein are not limiting. Various embodiments are described throughout this document, and any type of embodiment may be included under any section / subsection. Furthermore, the embodiments described in any section / subsection may be combined in any manner with any other embodiments described in the same section / subsection and / or in different sections / subsections.

[0027] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may be included below. The terms "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may be included below.

[0028] As used herein, a "unit," "operating unit," or "subunit" may consist of any suitably structured machine learning model or network. As used herein, a group of elements or similar expressions may include one or more such elements. For example, a "group of convolutional units" may include one or more convolutional units.

[0029] The embodiments of the present disclosure may involve user data, data acquisition and / or use, etc. These aspects shall comply with the corresponding laws, regulations and relevant provisions. In the embodiments of the present disclosure, all data collection, acquisition, processing, processing, forwarding, use, etc. are carried out on the premise that the user is aware of and confirms them. Accordingly, when implementing the various embodiments of the present disclosure, the types, scope of use, and usage scenarios of the data or information that may be involved should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with the relevant laws and regulations. The specific notification and / or authorization method may vary according to the actual situation and application scenario, and the scope of the present disclosure is not limited in this respect.

[0030] In the mobile internet era, travel options are diverse and diverse. Shared vehicles, thanks to their low cost, speed, and flexibility, have become a necessary option for many urban residents for short trips. In addition to shared two-wheelers, shared vehicles also include shared electric motorcycles, shared cars, and more. As a new phenomenon, shared vehicles are not yet fully developed, and supporting management measures are inadequate. For example, parking management standards for shared vehicles are inconsistent and unregulated, leading many users to leave their vehicles unattended after use. Illegal parking not only impacts urban traffic but also severely damages the city's appearance and the experience of other users. As cities refine relevant regulations, shared vehicle service platforms are required to assist users in ensuring proper parking.

[0031] In the ongoing exploration of standardized parking determination solutions, visual parking solutions based on image processing technology have gained widespread application. In practice, parking lines are marked within pre-planned shared vehicle parking areas. Cameras are used to identify these marked lines, and users are guided to park their shared vehicles within a predetermined distance and / or angle from the lines based on the identified lines. However, parking lines can be irregularly drawn, resulting in them failing to meet image recognition requirements. Furthermore, in some cases, parking line maintenance is not timely, leading to damaged lines being left unrepaired. Furthermore, the intelligence of existing visual recognition algorithms needs to be further improved. For example, their simplistic processing logic makes them incapable of recognizing parking lines that are heavily covered in dust or severely damaged. These factors reduce the accuracy of parking line recognition, thereby impacting the determination of standardized parking. As can be seen, existing parking solutions offer suboptimal accuracy in some situations, resulting in users being unable to return their vehicles in a timely manner and impacting their experience. Therefore, existing parking control solutions need further improvement.

[0032] According to various embodiments of the present disclosure, a method, apparatus, device, storage medium, and program product for vehicle parking control are provided. The method includes: receiving, at a central control device, multiple parking results for a target vehicle from a local control device deployed in association with the target vehicle, the multiple parking results being determined by a machine learning model deployed at a local processing device deployed in association with the target vehicle based on multiple first target images collected, each parking result indicating whether the target vehicle is parked in compliance with parking requirements; in response to determining that the multiple parking results all indicate that the target vehicle is parked in compliance with parking requirements, sending a sample collection instruction to the local processing device; receiving a second target image associated with the target vehicle from the local processing device, the second target image being used as a training sample in a training dataset; and updating the machine learning model using the training dataset.

[0033] In this way, the central control device can obtain real parking scene images in a timely manner and update the machine learning model based on the parking scene images, thereby improving the accuracy of parking control.

[0034] Sample Environment

[0035] Figure 1A FIG2 is a schematic diagram of an example environment 100A in which embodiments of the present disclosure can be implemented. The environment 100A includes a target vehicle 130 , a central control device 110 (eg, a cloud platform), a user 160 , and a user device 120 used by the user 160 .

[0036] In some embodiments, the user device 140 may have an application installed and running, and present an interface for operation by the user 160. The user device 120 may be a terminal device that has a shared vehicle service application installed and running, including but not limited to a personal computer, a smartphone, a smartwatch, smart glasses, a smart helmet, a laptop, a tablet computer, a personal digital assistant, or any other appropriate portable electronic device.

[0037] In some embodiments, the target vehicle is a shared vehicle, such as a shared two-wheeled vehicle, a shared electric motorcycle, a shared car, or any other shared transportation vehicle that complies with laws and regulations.

[0038] In some implementations, the central control device 110 may be a remote server. In this case, the central control device 110 may be configured as a remote server that centrally manages and controls various shared vehicles, including the target vehicle 130. For example, the central control device 110 may manage and control the target vehicle 130 by at least communicating with the central control unit on the target vehicle 130. In some embodiments, at least some of the functions of the central control device 110 may be implemented by the user device 120.

[0039] In some embodiments, the central control device 110 can be implemented as a standalone server or a server cluster consisting of multiple servers. In other words, the central control device 110 can be one or a group of servers that provide service functions, or one or a group of virtual machines that can provide services. The present disclosure is not limited in the implementation form of the central control device 110.

[0040] Figure 1B A schematic diagram of an example environment 100B is shown in which embodiments of the present disclosure can be implemented.

[0041] like Figure 1B As shown, the environment 100B includes a central control device 110, a user device 120 and a target vehicle 130, wherein the target vehicle 130 includes a local control device 140 (eg, a vehicle central control) and a local processing device 150 (eg, a local camera module).

[0042] It should be understood that the local control device 140 and the local processing device 150 can be integrated into a single module or implemented as two independent modules. Furthermore, the local processing device 150 can be implemented in a pluggable manner. When the shared vehicle is a motorcycle, the local processing device 150 can be placed at the center of the bottom of the motorcycle's basket. Furthermore, the elevation angle of the basket bottom can be optimized to facilitate the camera's recognition of the parking line and better capture parking images.

[0043] In environment 100B, user device 120, local control device 140, and local processing device 150 may all be connected to central control device 110 for communication via a network, such as a cellular network, narrowband Internet of Things, etc. In some embodiments, user device 120 may be connected to local control device 140 via wireless communication, such as short-range wireless communication, including but not limited to Bluetooth, infrared, etc.

[0044] The user device 120 may have a pre-installed shared vehicle service application. The user device 120 may present a user interface to facilitate interaction. For example, the user device 120 may present a vehicle borrowing / returning interface 122 and a parking guidance interface 124 to the user 160. During operation, the user 160 communicates with the central control device 110110 and the local control device 140 via the user device 120. The central control device 110 may record a pre-planned area with corresponding parking lines as a vehicle parking zone. When the user 160 needs to return the vehicle, the user 160 drives the target vehicle 130 into the planned parking zone. The user 160 then triggers the vehicle return operation via the vehicle borrowing / returning interface 122 presented by the user device 120. If the vehicle is returned in a proper manner, subsequent processes such as fee settlement may proceed. If the vehicle is not returned in a proper manner, the user device 120 may present a parking guidance interface to guide the user 160 in a proper return, for example, directing the user 160 to park the target vehicle 130 at a predetermined distance or angle from the parking lines.

[0045] like Figure 1B As shown, in some embodiments, the local control device 140 may include a vehicle parking control module 141, a wireless communication module 144, a positioning module (e.g., a global positioning system (GPS) positioning module), a power module 143, and a speaker module 142. Furthermore, the above modules may be communicatively connected via a bus communication method, including but not limited to an RS-485 bus, a CAN bus, an IIC bus, and the like.

[0046] The target vehicle 130 may further include a local processing device 150 , which includes a camera module 153 , an image processing module 152 , and a control and communication module 151 .

[0047] In some embodiments, the vehicle parking control module 141 can power the local processing device 150 via the power module 143. Alternatively, in some embodiments, the local processing device 150 is powered by a lithium battery in the target vehicle 130. In some embodiments, the local control device 140 and the local processing device 150 can achieve a bidirectional communication connection via the wireless communication module 144 and the control communication module 151.

[0048] In some embodiments, the positioning module 145 can obtain the location of the target vehicle 130 and upload the location information of the target vehicle 130 to the central control device 110 in real time through the vehicle parking control module 141. After the user 160 triggers the vehicle return process through the user device 120, the local control device 140 can communicate with the local processing device 150 to wake up the local processing device 150.

[0049] Next, the local processing device 150 can capture parking images using the camera module 153 and, using the image processing module, identify parking lines and optionally determine whether the vehicle was parked properly. The local processing device 150 can feed back the recognition and / or determination results to the local control device 140. As an example embodiment, the local processing device 150 can capture an image of the parking area during parking using the camera module 153 and input the captured image into the image processing module 152 for parking line identification. The image processing module 152 uses a deep learning algorithm model to perform feature detection and matching, identifying feature points along the parking lines in the image. If the parking lines are successfully identified, the angle and distance of the motorcycle relative to the parking lines can be further calculated and transmitted to the control and communication module 151, which determines whether the user 160 has returned the motorcycle properly. The local processing device 150 can then feed back the determination results to the local control device 140 via bus communication / wireless communication.

[0050] Based on the recognition and / or determination results, the local control device 140 controls the speaker module 142 to play corresponding voice messages. For example, if the vehicle is determined to be improperly parked, the local control device 140 guides the user 160 to park properly, or if the vehicle is determined to be properly parked, the local control device 140 reminds the user 160 that the vehicle has been successfully returned. Furthermore, the local control device 140 may transmit the determination results to the platform 110, which then sends the determination results to the user device 120. The user device 120 may then present the determination results to the user 160.

[0051] In some embodiments, the central control device 110 includes a command control module 112 and an algorithm training module 114, wherein the command control module 112 is used to complete normal electric motorcycle borrowing and returning instructions, and the algorithm training module 114 is used to continuously process images in the parking scene sample library and / or optimize the current deep learning algorithm model for parking line recognition.

[0052] In some embodiments, if the cumulative number of messages indicating vehicle return failures received by the central control device 110 from the local control device 140 reaches a threshold number (e.g., two), the central control device 110 may send an instruction to the local processing device 150 of the target vehicle 130, instructing the local processing device 150 to send a captured image of the current parking scene to the central control device 110. The local processing device 150 captures the current parking scene image or obtains a previously stored parking scene image and sends the image to the central control device 110. In some embodiments, the central control device 110 may store the parking scene image in a parking scene sample library.

[0053] In some embodiments, central control device 110 may further analyze the reasons for user 160's parking failure based on the uploaded parking scene image using algorithm training module 114. If algorithm training module 114 determines that the vehicle return failure was caused by improper parking, central control device 110 may guide user 160 to park properly through user device 120.

[0054] Alternatively or additionally, in some embodiments, the central control device 110 can filter out parking lines that are below a set integrity threshold (i.e., there are damaged parking lines) based on images in the parking scene sample library, and provide the location information of these parking lines to urban operation and maintenance personnel to facilitate their timely maintenance of severely damaged parking lines.

[0055] Alternatively or additionally, in some embodiments, the central control device 110 may also periodically update its deep learning algorithm model / algorithm training module 114 to the local processing device 150 of the target vehicle 130 via online upgrades. In this way, the local processing device 150 can use the updated deep learning algorithm model to recognize stop lines, thereby optimizing and improving the target vehicle's return success rate.

[0056] Example Process

[0057] Figure 2 FIG2 shows a schematic diagram of a signaling flow 200 for controlling a target vehicle 130 according to some embodiments of the present disclosure. The signaling flow 200 is further described below through an embodiment. For ease of discussion, reference is made to FIG200. Figure 1A Environment 100A and Figure 1B Let’s discuss the environment 100B.

[0058] In operation, the central control device 110 receives a plurality of parking results for the target vehicle 130 from the local control device 140 deployed in association with the target vehicle 130, wherein the plurality of parking results are respectively determined by a machine learning model deployed at the local processing device 150 deployed in association with the target vehicle 130 based on a plurality of collected first target images, and each parking result indicates whether the parking of the target vehicle 130 complies with the parking requirements.

[0059] like Figure 2As shown, when the user 160 finishes using the vehicle, the user 160 sends (201) a request to return the vehicle through the user device 120. For example, when the user 160 triggers a control for requesting to return the vehicle or end the trip in the user interface presented by the shared vehicle application on the user device 120. Based on the triggering operation, the user device 120 sends (201) a parking request to the central control device 110. The central control device 110 sends (202) the parking request to the local control device 150 (for example, the central control device of the target vehicle 130). In response to the return request, the local control device 140 can send (204) a parking identification instruction to the local processing device 150.

[0060] At the local processing device 150, in response to the parking identification instruction for the target vehicle 130, the local processing device 150 can collect (206) a first target image, and use the machine learning model locally deployed on the local processing device 150 to determine (208) a parking result of the target vehicle 130 based on the collected first target image, wherein the parking result indicates whether the parking of the target vehicle 130 meets the parking requirements. The local processing device 150 can send (210) the parking result to the local control device 140, and the local control device 140 can send (212) the parking result to the central control device. Through the above example interaction process, the central control device 110 can obtain a parking result.

[0061] In some embodiments, if the parking result indicates that the parking requirements are met, the central control device 110 may instruct the user device 120 to complete subsequent processes, such as entering a payment process. Alternatively, if the parking result indicates that the parking requirements are not met, the central control device 110 may send (214) first parking guidance information to the user device 120. In some embodiments, the first parking guidance information may be included in the first response. The user device 120 may present the first parking guidance information to the user 160 to guide the user 160 to park in a standardized manner.

[0062] In some embodiments, the local processing device 150 may use a deep learning algorithm model to identify parking lines and / or determine whether parking is required. Figure 3 Example embodiments of identifying a stop line and / or determining whether parking is specified are described.

[0063] Figure 3 An example application scenario 300 of identifying parking lines and / or determining standard parking according to some embodiments of the present disclosure is shown. Figure 3 In the example scene 300, reference marks 310-1 to 310-8, also known as stop signs, are included. As an example, the reference marks 310-1 to 310-8 may be pre-drawn T-shaped stop lines.

[0064] In operation, when user 160 triggers the vehicle return process on user device 120, local control device 140 may wake up local processing device 150. Local processing device 150 may capture an image of the parking area when user 160 parks the vehicle through a camera module and input the image to image processing module 152 for parking line recognition.

[0065] In some embodiments, the image processing module 152 can perform feature detection and matching to identify feature points on the parking line using a deep learning algorithm. In operation, the deep learning algorithm can first determine the region of interest and then identify the reference markers within the region of interest. Figure 3 In the example embodiment, the target vehicle 130-1 may first determine the region of interest 320-1 and then perform feature extraction on the reference markers 310-1 to 310-6 in the region of interest 320-1. Figure 3 In the example embodiment, reference marks 310 - 1 to 310 - 6 are T-shaped marks. In this case, the deep learning algorithm can perform feature matching and comparison between the extracted features and a preset standard "T"-shaped template, and accordingly evaluate the similarity between the extracted "T"-shaped mark and the "T"-shaped mark in the template.

[0066] In some embodiments, when the similarity between the extracted “T”-shaped mark and the “T”-shaped mark in the template reaches or exceeds a set threshold ratio (eg, 60%), it is determined that the reference mark recognition is successful.

[0067] Additionally, in some embodiments, the deep learning algorithm does not need to identify all reference markers in the region of interest. Specifically, when the number of identified reference markers is greater than a threshold number, the deep learning algorithm can determine that the parking line has been successfully identified. Figure 3 In a specific embodiment, if the threshold number is 4, then when the target vehicle 130-1 recognizes any 4 reference marks from the reference marks 310-1 to 310-6, it can be determined that the stop line recognition is successful. In this way, the probability of the stop line recognition is improved.

[0068] Additionally, the threshold number may vary depending on the location of the target vehicle 130. Figure 3In the embodiment, target vehicle 130-2 is located at the edge of the parking lot compared to target vehicle 130-1. In this case, the number of reference markers to be identified within region of interest 310-2 of target vehicle 130-2 will be smaller than the number of reference markers to be identified within region of interest 310-1 of target vehicle 130-1. Therefore, the threshold value can be lowered when the target vehicle is located at the edge of the parking area. Specifically, when target vehicle 130 is located at a first position in the parking area, stop line recognition is determined to be successful when the number of identified reference markers reaches / exceeds a first threshold value. When target vehicle 130 is located at a second position in the parking area, stop line recognition is determined to be successful when the number of identified reference markers reaches / exceeds a second threshold value. The second position is closer to the edge of the parking area than the first position, and the second threshold value is smaller than the first threshold value.

[0069] Additionally, in some embodiments, when the stop line is successfully identified, the deep learning algorithm can calculate the angle and distance of the target vehicle 130 relative to the stop line and transmit these values ​​to the control and communication module 151. The control and communication module 151 then determines whether the user 160 has returned the vehicle properly and transmits the result back to the local control device 140 via bus communication. The local control device 140 then transmits the result to the central control device 110, which then sends the result to the user device 120 and ultimately presents it to the user 160.

[0070] Furthermore, if the parking result indicates that the parking requirements are not met, it is necessary to identify again whether the parking requirements are met. Figure 2 As shown. The local control device 140 can again send (216) a parking identification instruction to the local processing device 150. Accordingly, in response to the parking identification instruction for the target vehicle 130, the local processing device 150 can again collect (218) the first target image, and use the machine learning model locally deployed on the local processing device 150 to determine (220) a parking result of the target vehicle 130 based on the collected first target image, wherein the parking result indicates whether the parking of the target vehicle 130 meets the parking requirements. The local processing device 150 can send (222) the parking result to the local control device 140, and the local control device 140 can send (224) the parking result to the central control device 110. Through the above-mentioned example interaction process, the central control device can obtain another parking result.

[0071] In some embodiments, the local processing device 150 may iteratively capture first target images or determine corresponding parking results in response to a parking identification instruction. For example, in response to a parking identification instruction for the target vehicle 130, the local processing device 150 may capture a first target image using an image capture device and determine a first parking result for the target vehicle 130 based on the first target image using a machine learning model deployed locally on the local processing device 150. Furthermore, while the first parking result is being transmitted to the central control device 110, if the first parking result indicates that the target vehicle 130 is not parked in compliance with parking requirements, the local processing device 150 may continue to capture first target images using the image capture device and continue to determine at least one parking result for the target vehicle 130 based on subsequently captured first target images using the machine learning model until a determined parking result indicates that the target vehicle 130 is parked in compliance with parking requirements, or until the number of parking results indicating that the target vehicle 130 is not parked in compliance with parking requirements reaches a threshold number.

[0072] Through the above process, the central control device 110 can obtain multiple parking results.

[0073] Considering that if only the result of parking success or failure is fed back to the central control device 110, the central control device 110 cannot capture the real parking scene in time, nor can it know the detailed reasons for the failure of returning the vehicle. In view of this, according to some embodiments of the present invention, in response to determining that multiple parking results all indicate that the parking of the target vehicle 130 does not meet the parking requirements, that is, determining that the number of parking results indicating that the parking does not meet the parking requirements reaches / exceeds the threshold number (226), the central control device 110 sends a sample collection instruction to the local processing device 150. In response to the collection instruction, the local processing device 150 can collect (232) a second target image related to the target vehicle 130 and send the second target image (234) to the central control device 110. For the central control device 110, it can use the second target image as a training sample in the training data set and use the training data set to update (236) the machine learning model.

[0074] In some embodiments, the central control device 110 may send (238) an updated machine learning model to a local processing device 150 deployed in association with the target vehicle 130 and / or at least one other local processing device 150 deployed in association with at least one other vehicle to replace the machine learning model deployed locally on the local processing device 150 and / or at least one other local processing device 150.

[0075] Alternatively or additionally, in some embodiments, the central control device 110 may determine the reason why the parking of the target vehicle 130 does not comply with the parking requirements based on the second target image, and based on the determined reason, send (240) parking guidance information, such as the second parking guidance information, to the user device 120 using the target vehicle 130. As an example embodiment, the user device 120 receives a second response to the vehicle return request from the central control device 110, the second response including at least the second parking guidance information. Further, the second parking guidance information is received in the following case: multiple parking results determined based on multiple captured first target images all indicate that the parking of the target vehicle 130 does not comply with the parking requirements, and the reason why the parking of the target vehicle 130 does not comply with the parking requirements is determined based on the captured second target image. The user device 120 may present the second parking guidance information to the user 160 to regulate the user's parking.

[0076] Parking lines in cities deteriorate to varying degrees over time. Traditional solutions rely solely on historical vehicle return statistics and empirically-based adjustments to parking line recognition algorithms. This results in poor optimization and an inability to regularly adjust the algorithm. Furthermore, when parking lines become damaged, the service platform is unable to effectively count and screen them, hindering maintenance personnel from promptly repairing them.

[0077] According to some embodiments of the present disclosure, the central control device 110 may determine a status of at least one parking sign based on the second target image, and determine (242) a maintenance requirement for the at least one parking sign based on the status of the at least one parking sign. If it is determined that the parking sign is severely damaged, a maintenance person may be notified to promptly maintain the parking sign.

[0078] Through the above process, the present disclosure implements a vehicle parking control solution based on a deep learning algorithm. According to the vehicle parking control solution of the present disclosure, the accuracy of image recognition is improved, and the accuracy of parking determination is increased. Furthermore, according to the vehicle parking control solution of the present disclosure, the deep learning algorithm can be timely trained, optimized, and upgraded iteratively. Furthermore, according to the vehicle parking control solution of the present disclosure, the location information of parking lines requiring maintenance can be collected in a timely manner, facilitating city operations and maintenance personnel to promptly maintain severely damaged parking lines.

[0079] In order to better understand the above process, we will combine Figure 4 The above operation is further described, wherein Figure 4 A flowchart 400 is shown of an example process for vehicle parking control according to some embodiments. Figure 4The example operations discussed should not be construed as limiting the present disclosure.

[0080] At block 410, if a cloud platform (such as Figure 1B If the central control device 110 in the embodiment finds that the number of failed attempts to return the vehicle exceeds a threshold number (e.g., two times), it sends a picture taking instruction (i.e., a target image acquisition instruction) to a camera module (e.g., Figure 1B local processing device 150 in the system).

[0081] At block 420, after receiving the capture command, the camera module captures an image of the current parking scene (i.e., the second target image) and sends it to the cloud platform. At block 430, the uploaded image is identified to determine whether the return failure was caused by the user's improper return. If so, the user is instructed to park properly. Otherwise, the remaining steps are executed.

[0082] Furthermore, after receiving the current parking scene image, the cloud platform stores the received parking scene image in a sample library at block 440. At block 450, the parking line deep learning algorithm model deployed on the cloud platform is trained and updated iteratively based on the sample library data.

[0083] At block 460, the cloud platform can filter and export images of parking line damage levels below a set threshold. At block 470, the cloud platform can notify city maintenance personnel to regularly maintain severely damaged parking lines based on the image data.

[0084] In addition, after the update iteration, in box 480, the cloud platform can regularly upgrade the algorithm model trained by the cloud platform to the camera module.

[0085] Example Method

[0086] Figure 5 A flowchart illustrating a process 500 for vehicle parking control according to some embodiments of the present disclosure is shown. Next, for ease of description only, the process 500 is described by taking the central control device 110 as an example.

[0087] In box 510, the central control device 110 receives multiple parking results for the target vehicle 130 at the local control device 140 deployed in association with the target vehicle 130. The multiple parking results are respectively determined by the machine learning model locally deployed on the local processing device 150 based on the multiple collected first target images. Each parking result indicates whether the parking of the target vehicle 130 meets the parking requirements.

[0088] At block 520 , in response to determining that the plurality of parking results all indicate that the parking of the target vehicle 130 does not comply with the parking requirements, the central control device 110 sends a sample collection instruction to the local processing device 150 .

[0089] At block 530 , the central control device 110 receives a second target image associated with the target vehicle 130 from the local processing device 150 . The second target image is used as a training sample in the training dataset.

[0090] At block 540 , the central control device 110 updates the machine learning model using the training dataset.

[0091] In some embodiments, the central control device 110 sends an updated machine learning model to a local processing device 150 deployed in association with the target vehicle 130 and / or at least one other local processing device 150 deployed in association with at least one other vehicle to replace the machine learning model deployed locally on the local processing device 150 and / or at least one other local processing device 150.

[0092] In some embodiments, the central control device 110 determines the reason why the parking of the target vehicle 130 does not meet the parking requirements based on the second target image; and based on the reason, sends parking guidance information to the user device 120 corresponding to the user using the target vehicle 130.

[0093] In some embodiments, central control device 110 determines a status of at least one parking sign based on the second target image; and determines a maintenance requirement for the at least one parking sign based on the status of the at least one parking sign.

[0094] Figure 6 A flow chart illustrating a process 600 for vehicle parking control according to some embodiments of the present disclosure is shown. Next, for ease of description only, the process 600 is described as being performed at the local processing device 150 as an example.

[0095] In box 610, the local processing device 150 deployed in association with the target vehicle 130 responds to the parking identification instruction for the target vehicle 130 and uses the machine learning model locally deployed on the local processing device 150 to determine multiple parking results for the target vehicle 130 based on the multiple collected first target images, each parking result indicating whether the parking of the target vehicle 130 meets the parking requirements.

[0096] At block 620 , the local processing device 150 causes the plurality of parking results to be sequentially transmitted to the central control device 110 .

[0097] In block 630 , if a sample collection instruction is received from the central control device 110 , the local processing device 150 collects a second target image associated with the target vehicle 130 .

[0098] At block 640 , the local processing device 150 sends the second target image to the central control device 110 to be used as a training sample in a training dataset, which is used by the central control device 110 to update the machine learning model.

[0099] In some embodiments, in response to a parking identification instruction for the target vehicle 130, the local processing device 150 uses an image acquisition device to acquire a first target image; uses a machine learning model locally deployed on the local processing device 150 to determine a first parking result for the target vehicle 130 based on the first target image; and while the first parking result is being sent to the central control device 110, if the first parking result indicates that the parking of the target vehicle 130 does not meet the parking requirements, continues to use the image acquisition device to acquire the first target image and continues to use the machine learning model to determine at least one parking result for the target vehicle 130 based on subsequently acquired first target images until the determined parking result indicates that the parking of the target vehicle 130 meets the parking requirements, or the number of parking results indicating that the parking of the target vehicle 130 does not meet the parking requirements reaches a threshold number.

[0100] In some embodiments, the local processing device 150 receives an updated machine learning model from the central control device 110 to replace the locally deployed machine learning model.

[0101] In some embodiments, the local processing device 150 is independent of the local control device 140 of the target vehicle 130 and communicates with the local control device 140. Furthermore, in response to a parking recognition instruction received from the local control device 140, at block 620, the local processing device 150 captures a first target image to provide to the machine learning model, where each parking recognition instruction corresponds to a capture of the first target image; and obtains a parking result output by the machine learning model after processing the first target image.

[0102] In some embodiments, the local processing device 150 sends the plurality of parking results to the local control device 140 .

[0103] Figure 7 A flow chart illustrating a process 700 for vehicle parking control according to some embodiments of the present disclosure is shown. Next, for ease of description only, the process 700 is described by taking the user device 120 as an example.

[0104] At block 710 , in response to a user trigger, the user device 120 sends a parking request for the target vehicle 130 to the local control device 140 of the target vehicle 130 .

[0105] At block 720 , the user device 120 receives a first response to the parking request from the central control device 110 of the target vehicle 130 . The first response includes at least first parking guidance information. The first parking guidance information is received when a parking result determined based on the captured first target image indicates that the parking of the target vehicle 130 does not comply with parking requirements.

[0106] At block 730 , the user device 120 presents first parking guidance information to the user.

[0107] At block 740 , the user device 120 receives a second response to the parking request from the central control device 110 . The second response includes at least second parking guidance information. The second parking guidance information is received when: multiple parking results determined based on multiple captured first target images all indicate that the parking of the target vehicle 130 does not comply with the parking requirements; and a reason why the parking of the target vehicle 130 does not comply with the parking requirements is determined based on the captured second target image.

[0108] At block 750 , the user device 120 presents the second parking guidance information to the user.

[0109] Example devices and equipment

[0110] Figure 8 1 shows a schematic structural block diagram of an apparatus 800 for controlling vehicle parking according to some embodiments of the present disclosure. The apparatus 800 may be implemented as or included in the central control device 110. Each module / component in the apparatus 800 may be implemented by hardware, software, firmware, or any combination thereof.

[0111] As shown in the figure, the apparatus 800 includes a parking result receiving module 810, which is configured to receive, at the central control device 110, a plurality of parking results for the target vehicle 130 from a local processing device 150 deployed in association with the target vehicle 130, the plurality of parking results being respectively determined by a machine learning model locally deployed on the local processing device 150 based on a plurality of collected first target images, and each parking result indicating whether the parking of the target vehicle 130 complies with the parking requirements; a collection instruction sending module 820, which is configured to send a sample collection instruction to the local processing device 150 in response to determining that the plurality of parking results all indicate that the parking of the target vehicle 130 does not comply with the parking requirements; a second target image receiving module 830, which is configured to receive a second target image related to the target vehicle 130 from the local processing device 150, the second target image being used as a training sample in the training data set; and a model updating module 840, which is configured to update the machine learning model using the training data set.

[0112] In some embodiments, the device 800 also includes an update module configured to send an updated machine learning model to the local processing device deployed in association with the target vehicle and / or at least one other local processing device deployed in association with at least one other vehicle to replace the machine learning model deployed locally in the local processing device and / or the at least one other local processing device.

[0113] In some embodiments, the device 800 also includes a cloud reason determination module, which is configured to determine the reason why the parking of the target vehicle does not meet the parking requirements based on the second target image; and a guidance information sending module, which is configured to send parking guidance information to the user device corresponding to the user using the target vehicle based on the reason.

[0114] In some embodiments, the device 800 also includes a status determination module configured to determine the status of at least one parking mark based on the second target image; and a maintenance requirement determination module configured to determine the maintenance requirement of the at least one parking mark based on the status of the at least one parking mark.

[0115] Figure 9 : A schematic structural block diagram of an apparatus 900 for vehicle parking control according to some embodiments of the present disclosure is shown. The apparatus 900 may be implemented as or included in a local processing device 150 deployed in association with a target vehicle 130. Each module / component in the apparatus 900 may be implemented by hardware, software, firmware, or any combination thereof.

[0116] As shown in the figure, the apparatus 900 includes a parking result determination module 910, which is configured to, at a local processing device 150 deployed in association with the target vehicle 130, in response to a parking identification instruction for the target vehicle 130, respectively determine a plurality of parking results for the target vehicle 130 based on a plurality of first target images collected, using a machine learning model locally deployed on the local processing device 150, each parking result indicating whether the parking of the target vehicle 130 meets the parking requirements; a parking result sending module 920, which is configured to cause the plurality of parking results to be sequentially sent to the central control device 110; a second image acquisition module 930, which is configured to acquire a second target image associated with the target vehicle 130 if a sample acquisition instruction is received from the central control device 110; and a second image sending module 940, which is configured to send the second target image to the central control device 110 for use as a training sample in a training data set, which is used by the central control device 110 to update the machine learning model

[0117] In some embodiments, the parking result determination module 910 is further configured to, in response to a parking identification instruction for a target vehicle, capture a first target image using an image capture device; determine a first parking result of the target vehicle based on the first target image using a machine learning model deployed on the local processing device; and while the first parking result is being sent to the central control device, if the first parking result indicates that the parking of the target vehicle does not comply with parking requirements, continue to capture the first target image using the image capture device and continue to determine at least one parking result of the target vehicle based on subsequently captured first target images using the machine learning model until the determined parking result indicates that the parking of the target vehicle complies with parking requirements, or the number of parking results indicating that the parking of the target vehicle does not comply with parking requirements reaches a threshold number.

[0118] In some embodiments, the apparatus 900 further includes a replacement module configured to receive an updated machine learning model from the central control device to replace the locally deployed machine learning model.

[0119] In some embodiments, the local processing device is independent of the local control device of the target vehicle, and the local processing device communicates with the local control device, wherein the parking result determination module 910 is further configured to, in response to a parking recognition instruction received from the local control device, capture a first target image to provide to the machine learning model, each parking recognition instruction corresponding to a capture of the first target image; and obtain a parking result output by the machine learning model after processing the first target image.

[0120] In some embodiments, the apparatus 900 further includes a result sending module configured to send the plurality of parking results to the local control device.

[0121] Figure 10 1 shows a schematic structural block diagram of a vehicle parking control apparatus 1000 according to some embodiments of the present disclosure. The apparatus 1000 may be implemented as or included in a user device 120. Each module / component in the apparatus 1000 may be implemented by hardware, software, firmware, or any combination thereof.

[0122] As shown in the figure, the apparatus 1000 includes a parking request sending module 1010, which is configured to send a parking request for the target vehicle 130 to the local control device 140 of the target vehicle 130 at the user device 120 in response to a user trigger; a first response receiving module 1020, which is configured to receive a first response to the parking request from the central control device 110 of the target vehicle 130, the first response including at least first parking guidance information, the first parking guidance information being received in the following circumstances: a parking result determined based on the captured first target image indicates that the parking of the target vehicle 130 does not meet the parking requirements; a first presentation Module 1030 is configured to present first parking guidance information to the user. A second response receiving module 1040 is configured to receive a second response to the parking request from the central control device 110, the second response including at least second parking guidance information. The second parking guidance information is received when: multiple parking results determined based on multiple captured first target images all indicate that the parking of the target vehicle 130 does not comply with the parking requirements, and a reason 1050 for the non-compliance of the parking requirements for the target vehicle 130 is determined based on the captured second target image. Furthermore, a second presentation module is configured to present the second parking guidance information to the user.

[0123] Figure 11 1 shows a block diagram of an electronic device 1100 in which one or more embodiments of the present disclosure may be implemented. It should be understood that Figure 11 The electronic device 1100 shown is merely exemplary and should not be construed as limiting the functionality and scope of the embodiments described herein. The electronic device 1100 may include or be implemented as Figure 8-10 Devices 800-1000.

[0124] like Figure 11As shown, electronic device 1100 is in the form of a general-purpose computing device. Components of electronic device 1100 may include, but are not limited to, one or more processors or processing units 1110, memory 1120, storage device 1130, one or more communication units 1140, one or more input devices 1150, and one or more output devices 1160. Processing unit 1110 may be a real or virtual processor and is capable of performing various processes according to programs stored in memory 1120. In a multi-processor system, multiple processing units execute computer-executable instructions in parallel to increase the parallel processing capabilities of electronic device 1100.

[0125] The electronic device 1100 typically includes a plurality of computer storage media. Such media can be any available media accessible to the electronic device 1100, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 1120 can be a volatile memory (e.g., a register, a cache, a random access memory (RAM)), a non-volatile memory (e.g., a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 1130 can be a removable or non-removable medium and can include a machine-readable medium, such as a flash drive, a disk, or any other medium that can be used to store information and / or data (e.g., training data for training) and can be accessed within the electronic device 1100.

[0126] The electronic device 1100 may further include additional removable / non-removable, volatile / non-volatile storage media. Figure 11 As shown in FIG, a magnetic disk drive for reading from or writing to a removable, non-volatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, non-volatile optical disk may be provided. In these cases, each drive may be connected to a bus (not shown) by one or more data media interfaces. Memory 1120 may include a computer program product 1125 having one or more program modules configured to perform various methods or actions of various embodiments of the present disclosure.

[0127] The communication unit 1140 enables communication with other electronic devices via a communication medium. Additionally, the functions of the components of the electronic device 1100 can be implemented as a single computing cluster or multiple computing machines that can communicate via a communication connection. Thus, the electronic device 1100 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or other network nodes.

[0128] Input device 1150 may be one or more input devices, such as a mouse, keyboard, or trackball. Output device 1160 may be one or more output devices, such as a display, a speaker, or a printer. Electronic device 1100 may also communicate with one or more external devices (not shown) via communication unit 1140 as needed, such as storage devices, display devices, or the like, with one or more devices that allow a user to interact with electronic device 1100, or with any device that allows electronic device 1100 to communicate with one or more other electronic devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface (not shown).

[0129] According to an exemplary implementation of the present disclosure, a computer-readable storage medium is provided, on which computer-executable instructions are stored, wherein the computer-executable instructions are executed by a processor to implement the method described above. According to an exemplary implementation of the present disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, and the computer-executable instructions are executed by a processor to implement the method described above.

[0130] Various aspects of the present disclosure are described herein with reference to flowcharts and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to the present disclosure. It should be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.

[0131] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, such that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device is generated that implements the functions / actions specified in one or more blocks in the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium, where these instructions cause the computer, programmable data processing device, and / or other device to operate in a specific manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing various aspects of the functions / actions specified in one or more blocks in the flowchart and / or block diagram.

[0132] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0133] The flow charts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to multiple implementations of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a part for a module, program segment or instruction, and a part for a module, program segment or instruction comprises one or more executable instructions for realizing the logical function of the specification. In some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be realized by a special hardware-based system that performs the function or action of the specification, or can be realized by a combination of special hardware and computer instructions.

[0134] While various implementations of the present disclosure have been described above, the foregoing description is intended to be illustrative, not exhaustive, and not limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is selected to best explain the principles of the implementations, their practical applications, or improvements to existing technologies, or to enable others skilled in the art to understand the disclosure.

Claims

1. A method for controlling vehicle parking, comprising: receiving, at a central control device, a plurality of parking results for a target vehicle from a local control device deployed in association with the target vehicle, the plurality of parking results being determined by a machine learning model deployed at a local processing device deployed in association with the target vehicle based on a plurality of captured first target images, each parking result indicating whether the parking of the target vehicle complies with parking requirements; In response to determining that the plurality of parking results all indicate that the parking of the target vehicle does not comply with the parking requirement, sending a sample collection instruction to the local processing device; receiving a second target image associated with the target vehicle from the local processing device, the second target image being used as a training sample in a training dataset; as well as The machine learning model is updated using the training dataset.

2. The method according to claim 1, further comprising: Sending an updated machine learning model to the local processing device deployed in association with the target vehicle and / or at least one other local processing device deployed in association with at least one other vehicle to replace the machine learning model locally deployed on the local processing device and / or the at least one other local processing device.

3. The method according to claim 1, further comprising: determining, based on the second target image, a reason why the parking of the target vehicle does not comply with the parking requirement; as well as Based on the reason, parking guidance information is sent to a user device corresponding to a user using the target vehicle.

4. The method according to claim 1, further comprising: determining a status of at least one stop sign based on the second object image; as well as A maintenance need for the at least one stop marker is determined based on the status of the at least one stop marker.

5. A method for controlling vehicle parking, comprising: At a local processing device deployed in association with a target vehicle, in response to a parking identification instruction for the target vehicle, a machine learning model locally deployed on the local processing device is used to determine a plurality of parking results for the target vehicle based on a plurality of first target images collected, each parking result indicating whether the parking of the target vehicle complies with parking requirements; causing the plurality of parking results to be sequentially sent to a central control device; If a sample collection instruction is received from the central control device, collecting a second target image related to the target vehicle; as well as The second target image is sent to the central control device to be used as a training sample in a training data set, and the training data set is used by the central control device to update the machine learning model.

6. The method according to claim 5, wherein determining a plurality of parking results of the target vehicle based on the collected plurality of first target images comprises: In response to a parking recognition instruction for a target vehicle, capturing a first target image using an image capture device; Determine a first parking result for the target vehicle based on the first target image using a machine learning model locally deployed on the local processing device; as well as While the first parking result is being sent to the central control device, if the first parking result indicates that the parking of the target vehicle does not comply with parking requirements, continue to use the image acquisition device to acquire a first target image and continue to use the machine learning model to determine at least one parking result for the target vehicle based on subsequently acquired first target images until the determined parking result indicates that the parking of the target vehicle complies with parking requirements, or the number of parking results indicating that the parking of the target vehicle does not comply with parking requirements reaches a threshold number.

7. The method according to claim 5, further comprising: An updated machine learning model is received from the central control device to replace the locally deployed machine learning model.

8. The method of claim 5, wherein the local processing device is independent of and in communication with a local control device of the target vehicle, wherein determining a plurality of parking results for the target vehicle comprises: In response to a parking recognition instruction received from the local control device, capturing a first target image to provide to the machine learning model, wherein each parking recognition instruction corresponds to one capture of the first target image; as well as Obtain a parking result output by the machine learning model after processing the first target image.

9. The method according to claim 8, further comprising: The multiple parking results are sent to the local control device.

10. A method for controlling vehicle parking, comprising: At the user device, in response to a user trigger, sending a parking request for the target vehicle to a local control device of the target vehicle; receiving a first response to the parking request from a central control device of the target vehicle, the first response including at least first parking guidance information, the first parking guidance information being received when: a parking result determined based on the captured first target image indicates that parking of the target vehicle does not comply with parking requirements; presenting the first parking guidance information to the user; receiving a second response to the parking request from the central control device, the second response including at least second parking guidance information, the second parking guidance information being received when: a plurality of parking results determined based on a plurality of captured first target images all indicate that the parking of the target vehicle does not comply with parking requirements, and a reason why the parking of the target vehicle does not comply with the parking requirements is determined based on the captured second target image; as well as The second parking guide information is presented to the user.

11. A vehicle parking control device, comprising: a parking result receiving module configured to receive, at the central control device, a plurality of parking results for a target vehicle from a local control device deployed in association with the target vehicle, the plurality of parking results being determined by a machine learning model deployed at a local processing device deployed in association with the target vehicle based on a plurality of captured first target images, each parking result indicating whether the parking of the target vehicle complies with parking requirements; a collection instruction sending module configured to send a sample collection instruction to the local processing device in response to determining that the plurality of parking results all indicate that the parking of the target vehicle does not meet the parking requirement; A second target image receiving module is configured to receive a second target image related to the target vehicle from the local processing device, wherein the second target image is used as a training sample in a training dataset; as well as A model updating module is configured to update the machine learning model using the training data set.

12. A vehicle parking control device, comprising: a parking result determination module configured to, at a local processing device deployed in association with a target vehicle, determine, in response to a parking identification instruction for the target vehicle, a plurality of parking results for the target vehicle based on a plurality of captured first target images using a machine learning model locally deployed on the local processing device, each parking result indicating whether the parking of the target vehicle complies with parking requirements; a parking result sending module, configured to enable the plurality of parking results to be sent sequentially to a central control device; a second image acquisition module configured to acquire a second target image associated with the target vehicle upon receiving a sample acquisition instruction from the central control device; as well as The second image sending module is configured to send the second target image to the central control device to be used as a training sample in a training data set, and the training data set is used by the central control device to update the machine learning model.

13. A vehicle parking control device, comprising: a parking request sending module, configured to, at the user device, send a parking request for the target vehicle to the local control device of the target vehicle in response to a user trigger; a first response receiving module configured to receive a first response to the parking request from a central control device of the target vehicle, the first response including at least first parking guidance information, the first parking guidance information being received when: a parking result determined based on the captured first target image indicates that the parking of the target vehicle does not meet parking requirements; a first presentation module, configured to present the first parking guidance information to the user; a second response receiving module configured to receive a second response to the parking request from the central control device, the second response including at least second parking guidance information, the second parking guidance information being received when: a plurality of parking results determined based on a plurality of captured first target images all indicate that the parking of the target vehicle does not comply with parking requirements, and a reason why the parking of the target vehicle does not comply with the parking requirements is determined based on the captured second target image; as well as The second presentation module is configured to present the second parking guidance information to the user.

14. An electronic device comprising: at least one processing unit; as well as At least one memory, the at least one memory being coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions, when executed by the at least one processing unit, causing the electronic device to perform the method according to any one of claims 1 to 10 or claims 11-17.

15. A computer-readable storage medium having a computer program stored thereon, wherein the computer program is executable by a processor to implement the method according to any one of claims 1 to 4, any one of claims 5 to 9, or claim 10.

16. A computer program product comprising computer executable instructions, wherein the computer executable instructions, when executed by a processor, implement the method according to any one of claims 1 to 4, or any one of claims 5 to 9, or claim 10.

Images