Parking management method, device and equipment, and storage medium

Abstract

The application discloses a parking management method and device, equipment and a storage medium, relates to the technical field of image recognition, and at least solves the problems of low efficiency and high labor cost in determining the missed detection time of a parking space in the related art. The method comprises the following steps: in the case that the target parking space misses detection of the entering and leaving of a vehicle, determining the similarity between the current image of the target parking space and a plurality of historical images in a preset time period of the target parking space; based on the similarity between the current image and the plurality of historical images, determining two adjacent historical images with image content jump from the plurality of historical images; and based on the collection time of the two adjacent historical images, determining the time when the target parking space misses detection of the entering and leaving of a vehicle.

Description

Technical Field

[0001] This application relates to the field of image recognition technology, and in particular to a parking management method, apparatus, device, and storage medium. Background Technology

[0002] With the construction of urban public parking facilities, the problem of managing on-street parking has become increasingly prominent. One related technology for on-street parking management uses high-position cameras to identify vehicles entering and leaving parking spaces, as well as their license plate numbers, and reports the results to a management system to automatically record on-street parking behavior. However, because high-position cameras are not entirely accurate in identifying vehicles entering and leaving parking spaces, there is a possibility of missed detections. If a vehicle is missed, the monitoring images uploaded to the management system from the high-position camera need to be manually reviewed to determine the time of the missed detection, which is not only inefficient but also increases significant labor costs. Summary of the Invention

[0003] This application provides a parking management method, device, equipment, and storage medium for determining the time of missed vehicle entry and exit at parking spaces, thereby solving the problems of low efficiency and high labor costs in determining the time of missed parking space entry and exit in related technologies.

[0004] To achieve the above objectives, the embodiments of this application provide the following technical solutions:

[0005] Firstly, a parking management method is provided, comprising: in the event of a missed vehicle entry / exit at a target parking space, determining the similarity between the current image of the target parking space and multiple historical images of the target parking space within a preset time period; the start time of the preset time period is no earlier than the time currently recorded in the vehicle entry / exit records of the target parking space, and the end time of the preset time period is no later than the acquisition time of the current image; based on the similarity between the current image and multiple historical images, determining two adjacent historical images from the multiple historical images whose image content changes; and based on the acquisition time of the two adjacent historical images, determining the time when the missed vehicle entry / exit at the target parking space occurred.

[0006] This technical solution enables automatic determination of missed detection times, avoiding the need for manual review of surveillance images to determine missed detection times, thus improving the efficiency of determining missed detection times and reducing labor costs.

[0007] In one possible implementation, determining the similarity between a current image of a target berth and multiple historical images of the target berth within a preset time period includes: acquiring a local image of the current image of the target berth; determining the similarity between the local image and a target region image of each historical image within the preset time period; wherein the target region image and the local image are used to represent the same spatial region of the target berth. This reduces the area used in determining similarity, thereby reducing the computational load.

[0008] In another possible implementation, if a vehicle enters the target parking space but is missed during inspection, the current image of the target parking space includes a partial image of the vehicle parked there. This helps reduce computational load and improves the accuracy of determining when a vehicle leaves the target parking space is missed.

[0009] In another possible implementation, if a vehicle fails to be detected at the target berth, the area of ​​a local portion of the current image of the target berth is greater than or equal to a second preset threshold. This reduces the image area used to determine similarity, thereby reducing the computational load.

[0010] In another possible implementation, based on the similarity between the current image and multiple historical images, two adjacent historical images whose image content has changed are identified from the multiple historical images. This includes: determining that the image content of the two adjacent historical images has changed if the difference between a first similarity and a second similarity is greater than or equal to a first preset threshold; wherein the first similarity is the similarity between the current image and one of the two adjacent historical images, and the second similarity is the similarity between the current image and the other of the two adjacent historical images. This helps reduce the computational load and improves the speed of obtaining the time when vehicles miss entering or leaving the target berth.

[0011] In another possible implementation, if the parking status corresponding to the current image of the target parking space differs from the parking status currently recorded in the vehicle entry / exit record of the target parking space, it is determined that a vehicle entry / exit has been missed at the target parking space. Specifically, if the parking status corresponding to the current image of the target parking space is a vehicle-occupied state, and the parking status currently recorded in the vehicle entry / exit record of the target parking space is a vehicle-free state, the missed detection status of the target parking space is a vehicle entry missed detection status; if the parking status corresponding to the current image of the target parking space is a vehicle-free state, and the parking status currently recorded in the vehicle entry / exit record of the target parking space is a vehicle-occupied state, the missed detection status of the target parking space is a vehicle exit missed detection status.

[0012] This technical solution enables automatic identification of target parking spaces where vehicles have missed inspections, eliminating the need for regular inspections by patrol personnel. This reduces the workload of regular manual inspections, lowers labor costs, and improves the timeliness of target parking space detection.

[0013] Secondly, a parking management device is provided, comprising: a determination unit, configured to determine the similarity between the current image of the target parking space and multiple historical images of the target parking space within a preset time period when a vehicle entry / exit miss occurs at the target parking space; the start time of the preset time period is not earlier than the time currently recorded in the vehicle entry / exit records of the target parking space, and the end time of the preset time period is not later than the acquisition time of the current image; a similarity unit, configured to determine two adjacent historical images whose image content changes based on the similarity between the current image and the multiple historical images; and a miss detection unit, configured to determine the time when a vehicle entry / exit miss occurs at the target parking space based on the acquisition time of the two adjacent historical images.

[0014] In one possible implementation, the determining unit is specifically used to acquire a local image of the current image of the target berth; determine the similarity between the local image and the target area image of each historical image within a preset time period; wherein the target area image and the local image are used to characterize the same spatial region of the target berth.

[0015] In another possible implementation, if a vehicle is missed during entry into the target parking space, the partial image of the current image of the target parking space includes a partial image of the vehicle parked in the target parking space.

[0016] In another possible implementation, if a vehicle fails to be detected at the target parking space, the area of ​​a local image of the current image of the target parking space is greater than or equal to a second preset threshold.

[0017] In another possible implementation, the similarity unit is specifically used to determine that the image content of two adjacent historical images has changed when the difference between the first similarity and the second similarity is greater than or equal to a first preset threshold; wherein, the first similarity is the similarity between the current image and one of the two adjacent historical images, and the second similarity is the similarity between the current image and the other of the two adjacent historical images.

[0018] In another possible implementation, the determining unit is specifically configured to determine that a vehicle entry / exit miss has occurred at the target parking space when the parking status corresponding to the current image of the target parking space differs from the parking status currently recorded in the vehicle entry / exit record of the target parking space. Specifically, if the parking status corresponding to the current image of the target parking space is a vehicle-occupied state, and the parking status currently recorded in the vehicle entry / exit record of the target parking space is a vehicle-free state, the miss status of the target parking space is a vehicle entry miss; if the parking status corresponding to the current image of the target parking space is a vehicle-free state, and the parking status currently recorded in the vehicle entry / exit record of the target parking space is a vehicle-occupied state, the miss status of the target parking space is a vehicle exit miss.

[0019] Thirdly, an electronic device is provided, comprising: a processor; the processor being connected to a memory for storing computer execution instructions, the processor executing the computer execution instructions stored in the memory to enable the electronic device to implement the parking management method as described in the first aspect above and any possible implementation thereof.

[0020] Fourthly, a parking management system is provided, comprising: a camera (such as a high-position camera) for acquiring parking space images, parking status of the parking space, and entry / exit records of the parking space; and an electronic device for implementing the parking management method of the first aspect and any possible implementation thereof based on the parking space images, parking status of the parking space, and entry / exit records of the parking space.

[0021] Fifthly, a computer-readable storage medium is provided, storing computer-executable instructions that, when executed on an electronic device, cause the electronic device to perform the parking management method described in the first aspect and any possible implementation thereof.

[0022] In a sixth aspect, a computer program product is provided, comprising computer instructions that, when executed on an electronic device, cause the electronic device to perform the parking management method described in the first aspect and any possible implementation thereof.

[0023] The technical effects of any of the implementation methods in aspects two through six can be found in the technical effects of the corresponding implementation methods in aspect one, and will not be repeated here. Attached Figure Description

[0024] Figure 1 This is a parking space image shown according to an exemplary embodiment;

[0025] Figure 2 This is a block diagram illustrating an electronic device according to an exemplary embodiment;

[0026] Figure 3 This is a flowchart illustrating a parking management method according to an exemplary embodiment;

[0027] Figure 4 This is a schematic diagram illustrating a preset time period according to an exemplary embodiment;

[0028] Figure 5 This is a flowchart illustrating another parking management method according to an exemplary embodiment;

[0029] Figure 6 This is another parking space image shown according to an exemplary embodiment;

[0030] Figure 7 This is another parking space image shown according to an exemplary embodiment;

[0031] Figure 8 This is a flowchart illustrating another parking management method according to an exemplary embodiment;

[0032] Figure 9 This is another parking space image shown according to an exemplary embodiment;

[0033] Figure 10 This is a schematic diagram illustrating a parking space entry and exit record according to an exemplary embodiment;

[0034] Figure 11 This is a schematic diagram illustrating vehicle entry and exit records for another parking space according to an exemplary embodiment;

[0035] Figure 12 This is a block diagram illustrating a parking management device according to an exemplary embodiment. Detailed Implementation

[0036] To enable those skilled in the art to better understand the technical solutions of this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.

[0037] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0038] First, a brief introduction to the application scenarios involved in this application will be given.

[0039] With the construction of urban public parking facilities, the problem of managing on-street parking has become increasingly prominent. One related technology for on-street parking management uses high-position cameras to identify vehicles entering and leaving parking spaces, as well as their license plate numbers, and reports the results to a management system to automatically record on-street parking behavior. However, because high-position cameras are not entirely accurate in identifying vehicles entering and leaving parking spaces, there is a possibility of missed detections. If a vehicle is missed, the monitoring images uploaded to the management system from the high-position camera need to be manually reviewed to determine the time of the missed detection, which is not only inefficient but also increases significant labor costs.

[0040] Specifically, such as Figure 1 As shown, the first area shows multiple berth parking images collected by the high-position camera, the second area shows the enlarged image of the selected berth parking image in the first area, and the third area is the vehicle entry and exit records of multiple berths collected by the high-position camera. It can be understood that the multiple berths shown in the third area correspond one by one to the multiple berths shown in the berth parking image in the second area.

[0041] Furthermore, when the patrol personnel conduct regular inspections, they select multiple berth parking images in the first area one by one and display them enlarged in the second area. Specifically, taking Figure 1 as an example for illustration, the second area shows the berth parking image newly collected by the high-position camera. It can be seen that there is no vehicle parked at berth 8016036, while in the vehicle entry and exit records of the third area, there is a vehicle Zhejiang A6186 parked at berth 8016036. At this time, the patrol personnel determine that there is a missed inspection of the vehicle leaving the berth at berth 8016036. In order to determine the time when the vehicle leaving the berth at berth 8016036 is missed, the patrol personnel page through multiple berth parking images in the first area one by one and observe the change in the parking state of berth 8016036 in the berth parking images to determine the time when the parked vehicle Zhejiang A6186 leaves berth 8016036, that is, the time when the vehicle leaving the berth at berth 8016036 is missed. It can be seen that this method of manually page through berth parking images one by one to determine the time of missed vehicle entry and exit not only has low efficiency but also increases a large amount of labor costs.

[0042] In view of the above problems, the present application provides a parking management method. When a vehicle entry or exit is missed at a target berth, based on the similarity between the current image of the target berth and multiple (such as each) historical images within a preset time period, two adjacent historical images with a jump in image content are determined, and according to the acquisition times of the two adjacent historical images, the time when the vehicle entry or exit is missed at the target berth is obtained, thereby realizing the automatic determination of the missed inspection time, avoiding manually page through surveillance images to determine the missed inspection time, improving the efficiency of determining the missed inspection time, and reducing the labor cost.

[0043] Secondly, the implementation environment (implementation architecture) involved in the present application will be briefly introduced below.

[0044] The parking management method provided in this application can be applied to electronic devices. This application does not limit the specific form of the electronic device. For example, the electronic device can be a terminal device or a network device. The terminal device can be referred to as: terminal, user equipment (UE), access terminal, user unit, user station, mobile station, remote station, remote terminal, mobile device, user terminal, wireless communication device, user agent, or user equipment, etc. Specifically, the terminal device can be a mobile phone, augmented reality (AR) device, virtual reality (VR) device, tablet computer, laptop computer, ultra-mobile personal computer (UMPC), netbook, personal digital assistant (PDA), etc. The network device can be a server, etc. The server can be a single physical or logical server, or two or more physical or logical servers sharing different responsibilities and cooperating to achieve the various functions of the server.

[0045] In terms of hardware implementation, the aforementioned computer equipment can be implemented through, for example... Figure 2 The electronic device shown is an example of this. Figure 2 The diagram shown is a hardware structure schematic of an electronic device 200 provided in an embodiment of this application. The electronic device 20 can be used to implement the functions of the aforementioned electronic device.

[0046] Figure 2 The electronic device 200 shown may include a processor 201, a memory 202, a communication interface 203, and a bus 204. The processor 201, the memory 202, and the communication interface 203 can be connected via the bus 204.

[0047] The processor 201 is the control center of the electronic device 200. It can be a general-purpose central processing unit (CPU) or other general-purpose processors. The general-purpose processor can be a microprocessor or any conventional processor.

[0048] As an example, processor 201 may include one or more CPUs, for example Figure 2 CPU 0 and CPU 1 are shown in the diagram.

[0049] The memory 202 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto.

[0050] In one possible implementation, the memory 202 can exist independently of the processor 201. The memory 202 can be connected to the processor 201 via a bus 204 and is used to store data, instructions, or program code. When the processor 201 calls and executes the instructions or program code stored in the memory 202, it can implement the vehicle abnormal behavior detection method provided in this application embodiment.

[0051] In another possible implementation, the memory 202 can also be integrated with the processor 201.

[0052] Communication interface 203 is used for electronic device 200 to connect with other devices via a communication network, which may be Ethernet, radio access network (RAN), wireless local area network (WLAN), etc. Communication interface 203 may include a receiving unit for receiving data and a transmitting unit for transmitting data. As an example, communication interface 203 is used for electronic device 200 to connect with a high-position camera via a communication network.

[0053] Bus 204 can be an industry standard architecture (ISA) bus, a peripheral component interconnect (PCI) bus, or an extended industry standard architecture (EISA) bus. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 2 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0054] It should be pointed out that, Figure 2The structure shown does not constitute a limitation on the electronic device 200, except... Figure 2 In addition to the components shown, the electronic device 200 may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0055] Furthermore, to facilitate understanding of this application, the relevant elements involved in this application are now described.

[0056] On-street parking: refers to the act of parking motor vehicles in designated parking spaces on urban roads.

[0057] High-position camera: A smart camera installed on a high pole in the road, which can detect parking spaces on the same side or opposite side of the road. Usually, one high-position camera manages 3 to 5 parking spaces.

[0058] Parking space images: Images captured by the high-position camera at regular intervals. The parking space images include images of all parking spaces within the field of view of the high-position camera.

[0059] Parking space entry and exit records: These records document the entry and exit behavior of vehicles in and out of each parking space. Specifically, when detecting parking behavior in each parking space, the high-position camera automatically identifies the vehicles entering and exiting the parking space and their license plate numbers, and then uses this information, along with the time the vehicles entered and exited the parking space, to create an entry and exit record for that parking space.

[0060] It should be noted that the electronic device can acquire vehicle entry and exit records and / or parking images of the parking space, or the high-position camera can automatically send vehicle entry and exit records and / or parking images of the parking space to the electronic device.

[0061] For ease of understanding, the task processing method provided in this application will be described in detail below with reference to the accompanying drawings.

[0062] Figure 3 This is a flowchart illustrating a parking management method according to an exemplary embodiment, the parking management method being used in an electronic device. Figure 3 As shown, the parking management methods include the following S301-S303.

[0063] S301: In the event that a vehicle enters or exits the target parking space but is missed during inspection, determine the similarity between the current image of the target parking space and multiple historical images of the target parking space within a preset time period.

[0064] The start time of the preset time period is no earlier than the current recorded time in the vehicle entry / exit record of the target berth, and the end time of the preset time period is no later than the current image acquisition time.

[0065] In one implementation, such as Figure 4As shown, the preset time period includes any time interval between the current record time in the vehicle entry / exit log and the current image acquisition time. For example, Figure 4 The time periods shown are 1, 2, 3, and 4. Each time period includes the acquisition time of two adjacent historical images where the image content changes abruptly.

[0066] It should be noted that the current image acquisition time is later than the current record time in the vehicle entry / exit log. For example, if the current record time in the vehicle entry / exit log is 14:00 on November 10, 2021, then the current image acquisition time is later than 14:00 on November 10, 2021. For example, it could be 15:00 on November 10, 2021.

[0067] Missed vehicle entry / exit detection refers to a discrepancy between the current parking status of the target parking space in the parking space image and the current parking status recorded in the vehicle entry / exit record of the target parking space. Missed vehicle entry / exit detection includes missed exit detection and missed entry detection.

[0068] This application does not limit how the electronic device determines if a vehicle has missed entering or leaving the target parking space.

[0069] In one implementation, the missed vehicle entry / exit detection at a target parking space can be determined by inspection personnel. The electronic device determines this by receiving user instructions. For example, inspection personnel manually inspect the parking space images and vehicle entry / exit records every preset time interval (e.g., 0.5 hours) to check for target parking spaces where missed entry / exit detection has occurred, and input instructions to the electronic device indicating that a missed entry / exit detection has occurred at the target parking space.

[0070] In another implementation, missed vehicle entry / exit at the target berth can be determined by electronic equipment. Specific implementation details are provided below and will not be repeated here.

[0071] Optionally, the current image of the target parking space is the image of the target parking space in the first image, which is the parking image of the parking space where vehicle entry / exit was determined to have been missed. That is, the current image of the target parking space is a local area image of the parking space. The historical image of the target parking space is the image of the target parking space in the second image, which is the parking image of the parking space acquired earlier than the acquisition time of the first image. That is, the historical image of the target parking space is also a local area image of the parking space.

[0072] For example, such as Figure 1As shown, the parking images of the first parking space displayed in the second area include parking spaces 8016037, 8016036, 8016035, and 8016034. When a vehicle enters or exits a parking space 8016036 and is missed, the current image of the target parking space is the image of the area where parking space 8016036 is located in the first parking image. In this case, the historical image of the target parking space is the image of the area where parking space 8016036 is located in the historical parking images, where historical parking images refer to images in the first area that were collected earlier than the first parking image.

[0073] This application does not limit how the electronic device determines the current image of the target berth.

[0074] In one implementation, when the electronic device determines that a vehicle has missed its entry or exit at a target parking space, it automatically identifies the current image of the target parking space in the parking space image. For example, the electronic device can determine the current image of the target parking space based on the pre-stored coordinates of each parking space. The method for obtaining historical images of the target parking space is the same as the method for obtaining the current image of the target parking space, and will not be described again here.

[0075] In another implementation, when the electronic device determines that a vehicle has missed its entry or exit at the target parking space, it issues a prompt message to instruct the inspection personnel to mark the current image of the target parking space on the parking space image; and receives the current image of the target parking space marked by the inspection personnel on the parking space image. Further, the electronic device can determine the coordinates of the historical images of the target parking space in the historical parking space images based on the coordinates of the marked current image of the target parking space on the parking space image, thereby obtaining the historical image of the target parking space.

[0076] The embodiments of this application do not limit the method used to determine the similarity between images. For example, mean hash algorithm, difference hash algorithm, perceptual hash algorithm, etc. can be used.

[0077] When a vehicle fails to pass inspection at the target parking space, the parking space's status becomes "vehicle failed to pass inspection". When a vehicle fails to pass inspection at the target parking space, the parking space's status becomes "vehicle failed to pass inspection".

[0078] Vehicle departure missed detection status: There is no parked vehicle in the current image of the target parking space, but there is a parked vehicle in the vehicle entry / exit records of the target parking space. For example, if there is a parked vehicle in the vehicle entry / exit records of the target parking space, it can be specifically reflected in the fact that the current entry time recorded in the vehicle entry / exit records of the target parking space is the most recent entry time, but the exit time is not recorded.

[0079] Vehicle entry missed detection status: There is a parked vehicle in the current image of the target parking space, but no parked vehicle is recorded in the vehicle entry / exit records of the target parking space. For example, if there is no parked vehicle in the vehicle entry / exit records of the target parking space, it can be specifically reflected in the fact that the current record of the vehicle entry / exit records of the target parking space is the last exit time, and no entry time is recorded.

[0080] In one implementation, when the target berth's missed detection status is "vehicle entry missed detection status," the current record in the target berth's entry / exit log is the most recent exit time. At this time, the start time of the preset time period is the most recent exit time of the target berth, and the end time of the preset time period is the current image acquisition time.

[0081] In another implementation, when the target berth's missed detection status is "vehicle exit missed detection status," the current entry / exit record for the target berth shows the most recent entry time. In this case, the start time of the preset time period is the most recent entry time of the target berth, and the end time of the preset time period is the current image acquisition time.

[0082] S302: Based on the similarity between the current image and each of the plurality of historical images, determine the two adjacent historical images from the plurality of historical images whose image content has changed.

[0083] Optionally, two adjacent historical images can be two historical images acquired at adjacent times. The acquisition time is the time when the high-position camera captures the parking space image. For example, if the high-position camera captures a parking space image every 2 minutes, then two adjacent historical images are two adjacent historical images acquired at a 2-minute interval.

[0084] In one implementation, a jump in the image content of two adjacent historical images can be determined when the difference between the first similarity and the second similarity is greater than or equal to a first preset threshold, i.e., when a jump occurs between the first similarity and the second similarity. For example, the difference between the first similarity and the second similarity can be determined based on the difference or ratio between them. Here, the first similarity is the similarity between the current image and the first historical image among the two adjacent historical images, and the second similarity is the similarity between the current image and other historical images among the two adjacent historical images besides the first historical image. By determining the relationship between the difference between the two similarities and the first preset threshold, the two adjacent historical images whose image content has jumped can be identified without comparing the content between the two images, significantly reducing computational load and thus improving the speed of obtaining the missed detection time of vehicle entry / exit at the target berth.

[0085] It should be noted that, in the embodiments of this application, determining the content jump between two adjacent historical images from multiple historical images can also be achieved in the following ways: the electronic device can determine that the content jump between two adjacent historical images has occurred when the difference in the image content of two adjacent historical images is a preset difference. For example, when the missed detection state of the target berth is the vehicle entry missed detection state, the image content jump between two adjacent historical images can be determined when the first historical image collected within a preset time period does not contain a parked vehicle, while the subsequent historical image contains a parked vehicle. When the missed detection state of the target berth is the vehicle exit missed detection state, the image content jump between two adjacent historical images can be determined when the first historical image collected contains a parked vehicle, while the subsequent historical image does not contain a parked vehicle.

[0086] S303: Based on the acquisition time of two adjacent historical images, determine the time when a vehicle enters or leaves the target berth and is missed during inspection.

[0087] In one implementation, based on the missed detection status of the target berth, the acquisition time of the target historical image in two adjacent historical images is determined as the time when the target berth sends the missed detection of vehicle entry / exit.

[0088] Optionally, when the missed detection status of the target berth is a vehicle entry missed detection status, the time when the vehicle entry missed detection occurred at the target berth is determined based on the acquisition time of the later acquired historical image among two adjacent historical images. When the missed detection status of the target berth is a vehicle exit missed detection status, the time when the vehicle exit missed detection occurred at the target berth is determined based on the acquisition time of the earlier acquired historical image among two adjacent historical images.

[0089] It is understandable that if the missed detection status of the target berth is a vehicle entry missed detection status, then there is a parked vehicle in the current image of the target berth. In two adjacent historical images where the image content changes abruptly, the earlier historical image did not show a parked vehicle, while the later historical image does. This means the parked vehicle entered the target berth during the interval between the acquisition of the two adjacent historical images. Therefore, the acquisition time of the later historical image is determined as the time when the vehicle entry missed detection occurred at the target berth. In other words, the acquisition time of the historical image containing a parked vehicle is taken as the time when the vehicle entry missed detection occurred at the target berth. This proves that the vehicle was parked at the target berth, thus ensuring the accuracy of the vehicle entry missed detection status for the target berth.

[0090] Understandably, when the missed detection status of the target berth is a vehicle departure missed detection status, there is no parked vehicle in the current image of the target berth. In two adjacent historical images where the image content changes abruptly, the earlier historical image shows a parked vehicle, while the later historical image does not. This means the parked vehicle left the target berth during the interval between the acquisition of the two adjacent historical images. Therefore, the acquisition time of the earlier historical image is determined as the time when the vehicle departure missed detection occurred at the target berth; that is, the acquisition time of the historical image showing a parked vehicle is taken as the time when the vehicle departure missed detection occurred at the target berth. This proves that the vehicle was parked at the target berth, thus ensuring the accuracy of the vehicle departure missed detection at the target berth.

[0091] In another implementation, based on the parking status corresponding to the current image of the target berth, the acquisition time of the target historical image between two adjacent historical images is determined as the time when the target berth sends a missed vehicle entry / exit detection. The parking status corresponding to the current image includes either a vehicle present or no vehicle present.

[0092] Optionally, when the parking status corresponding to the current image is a vehicle-occupied state, the time of missed vehicle entry detection at the target parking space is determined based on the acquisition time of the later historical image among two adjacent historical images. When the parking status corresponding to the current image is a vehicle-free state, the time of missed vehicle exit detection at the target parking space is determined based on the acquisition time of the earlier historical image among two adjacent historical images.

[0093] In another implementation, based on the currently recorded parking status in the vehicle entry / exit log, the acquisition time of the target historical image between two adjacent historical images is determined as the time when the target parking space sends a missed vehicle entry / exit detection. The currently recorded parking status in the vehicle entry / exit log includes a vehicle present or a vehicle absent status.

[0094] Optionally, if the current recorded parking status in the vehicle entry / exit record is "no vehicle," the time when the target parking space experiences a missed vehicle entry detection is determined based on the acquisition time of the later historical image among two adjacent historical images. If the current recorded parking status in the vehicle entry / exit record is "vehicle present," the time when the target parking space experiences a missed vehicle exit detection is determined based on the acquisition time of the earlier historical image among two adjacent historical images.

[0095] By identifying the target berth's missed detection status using historical images, and then determining the time when vehicles entered or left the target berth based on the acquisition time of these historical images, the accuracy of the missed detection time can be improved, avoiding the need to record the time when vehicles enter or leave the target berth in advance.

[0096] In the above embodiments, when a vehicle enters or exits a target berth and is missed, the similarity between the current image of the target berth and each historical image is used to determine two adjacent historical images where the image content changes. The time when the vehicle enters or exits a target berth is missed is obtained based on the acquisition time of the two adjacent historical images. This achieves automatic determination of the missed detection time, avoids manually reviewing monitoring images to determine the missed detection time, improves the efficiency of determining the missed detection time, and reduces labor costs.

[0097] Another possible implementation, combined with Figure 3 ,like Figure 5 As shown, S301 includes:

[0098] S301a: Obtain a partial image of the current image of the target berth.

[0099] Optionally, in the event of a missed vehicle entry at the target parking space, the partial image of the current image of the target parking space includes a partial image of the vehicle parked at the target parking space. For example, the partial image of the parked vehicle may be at least one of the following: headlight image, taillight image, front wheel image, rear wheel image, or roof image of the parked vehicle.

[0100] In one implementation, a partial image of the current image can be marked by the inspection personnel. For example, when it is determined that a vehicle has been missed during entry or exit at a target parking space, and the missed detection status of the target parking space is a missed entry status, the inspection personnel use a mouse to mark a partial image on the current image of the target parking space, which includes a partial image of the vehicle parked at the target parking space.

[0101] In another implementation, a partial image of the current image can be automatically determined by an electronic device. For example, when it is determined that a vehicle entry or exit has been missed at the target parking space, and the missed detection status of the target parking space is a missed entry status, the electronic device automatically marks a partial image on the current image of the target parking space based on pre-stored image coordinate information. This partial image includes a partial image of the vehicle parked at the target parking space.

[0102] Optionally, if a vehicle fails to be detected at the target parking space, the area of ​​a local image of the current image of the target parking space is greater than or equal to a second preset threshold.

[0103] Optionally, a partial image of the current image includes the parking space markings and / or shoulder of the target parking space.

[0104] Optionally, the local image of the current image includes the image of the central region of the target berth (i.e., the region within a preset range centered on the center point of the current image). Since the area occupied by the target vehicle when it is parked in the target berth is usually the central region of the target berth, selecting the local region as the central region when the target berth's missed detection status is a missed detection status of a vehicle leaving the berth (no vehicle is parked in the target berth) helps improve the accuracy of determining the two adjacent historical images where the content jumps.

[0105] In one implementation, a portion of the current image can be marked by the inspector. For example, when it is determined that a vehicle has missed an entry or exit at a target parking space, and the missed detection status of the target parking space is determined to be a missed exit status, the inspector uses a mouse to mark a portion of the current image of the target parking space, and marks at least one of the parking space lines, shoulder, and center area of ​​the target parking space within the portion of the image.

[0106] In another implementation, the local image of the current image can be automatically determined by the electronic device. For example, when it is determined that a vehicle entry or exit is missed at the target parking space, and the missed detection status of the target parking space is a missed exit status, the electronic device automatically marks a local image on the current image of the target parking space according to the pre-stored image coordinate information. The area image represented by the image coordinate information includes at least one of the parking space markings, shoulder, and center area of ​​the target parking space.

[0107] S301b: Determine the similarity between a local image and the target region image of each historical image within a preset time period.

[0108] Among them, the target area image and the local image are used to represent the same spatial area of ​​the target berth.

[0109] It should be noted that when the three-dimensional coordinates of the target area image on the target berth are the same as the three-dimensional coordinates of the local image on the target berth, the target area image and the local image are determined to represent the same spatial area of ​​the target berth.

[0110] In one implementation, the similarity between a local image and a target area image of each historical image within a preset time period is determined, which is the similarity between the current image of the target berth and each historical image within the preset time period.

[0111] In one implementation, a vehicle entry miss occurs at the target parking space, for example, such as Figure 6 As shown, Figure 6 Partial image 601 is shown in (a) of the diagram. Figure 6 (b) Figure 6 (c) and Figure 6Image (d) shows target area image 602, local image 601, and target area image 602, representing the same spatial region of the target berth. By determining the local image 601, it is found that... Figure 6 (b) Figure 6 (c) and Figure 6 The similarity between target region images 602 in (d) is derived from... Figure 6 (b) Figure 6 (c) and Figure 6 In section (d), the two adjacent historical images where the image content changes abruptly are identified as follows: Figure 6 (c) and Figure 6 (d) in the text. Furthermore, since the missed detection status of the target parking space is the missed vehicle entry status, based on... Figure 6 The collection time of (d) in the data determined that the time of missed detection of vehicles entering and leaving the target berth was 11:57:24 on August 27, 2021.

[0112] In the above embodiments, when the missed detection state of the target berth is the vehicle entry missed detection state, by acquiring a partial image of the vehicle parked at the target berth, on the one hand, the area of ​​the image used to determine the similarity is reduced, thereby reducing the amount of computation. On the other hand, when the partial image includes a partial image of the vehicle parked at the target berth, the historical image with a jump in image content between it and the partial image is most likely to indicate that there is no vehicle parked at the target berth, thereby improving the accuracy of determining the vehicle exit missed detection time at the target berth.

[0113] In one implementation, a vehicle departure is missed at the target parking space, for example, such as Figure 7 As shown, Figure 7 Partial image 701 is shown in (a) of the image. Figure 7 (b) Figure 7 (c) and Figure 7 Image (d) shows target area image 702, local image 701, and target area image 702, representing the same spatial region of the target berth. By determining the local image 701, it is found that... Figure 7 (b) Figure 7 (c) and Figure 7 The similarity between target region images 702 in (d) is derived from... Figure 7 (b) Figure 7 (c) and Figure 7 In section (d), the two adjacent historical images where the image content changes abruptly are identified as follows: Figure 7 (c) and Figure 7 (d) in the text. Furthermore, since the target parking space's missed detection status is a vehicle departure missed detection status, based on... Figure 7The data collection time in (c) indicates that the time when the vehicle entered or exited the target berth was missed was 14:11:25 on August 27, 2021.

[0114] In the above embodiments, when the missed detection state of the target berth is the vehicle departure missed detection state, acquiring a local image with an area greater than or equal to a second preset threshold can prevent the area of ​​the local image from being smaller than the remaining area on the target berth after the vehicle is parked, which would make it impossible to accurately determine the two adjacent historical images where the image content changes, thus affecting the accuracy of determining the vehicle departure missed detection time of the target berth. Furthermore, by determining the similarity between the current image of the target berth and multiple historical images of the target berth through the similarity of the local image and the target region image of each historical image, the similarity between the current image of the target berth and multiple historical images of the target berth can be reduced while ensuring the accuracy of the two adjacent historical images where the image content changes, thereby reducing the area used to determine the similarity and thus reducing the computational load.

[0115] In the above embodiments, by acquiring a local image of the current image of the target berth and determining the similarity between the local image and the target area image of each historical image within a preset time period, the similarity between the current image of the target berth and multiple historical images of the target berth within a preset time period is determined, thereby reducing the area used to determine the similarity and thus reducing the amount of computation.

[0116] Another possible implementation, combined with Figure 3 ,like Figure 8 As shown, the parking management method also includes S101-S102.

[0117] S101: Determine the current parking status corresponding to the current image of multiple parking spaces, and the parking status currently recorded in the vehicle entry and exit records of multiple parking spaces. The current parking status includes a vehicle present or a vehicle absent status.

[0118] In one implementation, after acquiring a parking space image, the electronic device identifies the current parking status of multiple (e.g., each) parking spaces in the parking space image.

[0119] In another implementation, after the high-position camera captures a parking image of a parking space, it identifies the current parking status of multiple (e.g., each) parking spaces in the parking image, and the electronic device obtains the current parking status of the multiple parking spaces determined by the high-position camera.

[0120] Optionally, the high-position camera monitors vehicle entry and exit behavior at each parking space and generates entry and exit records for each parking space. Further, when a new entry or exit behavior occurs at each parking space, the high-position camera updates the parking space's entry and exit records based on the new behavior. For example, when a vehicle enters a parking space, the license plate number and the most recent entry time are recorded in the corresponding entry and exit record. Further, when a vehicle exits a parking space, the entry and exit records for that parking space are updated; specifically, the license plate number and the most recent entry time are updated to the most recent exit time. After each update, the high-position camera sends the updated entry and exit records to an electronic device, which then displays the updated records upon receipt.

[0121] S102: If the current parking status corresponding to the current image of any parking space among multiple parking spaces is different from the parking status currently recorded in the vehicle entry and exit record of that parking space, determine that the parking space is the target parking space, and determine that the target parking space has missed vehicle entry and exit detection.

[0122] Optionally, if the parking status corresponding to the current image of the target parking space is "no car" and the current recorded parking status in the vehicle entry / exit record of the target parking space is "car present", then the missed detection status of the target parking space is determined to be a missed exit status. For example, if... Figure 1 As shown in the second area, the current parking status of parking space 8016036 is "no car". As shown in the third area, the current parking status recorded in the vehicle entry and exit records of parking space 8016036 is "car present". Therefore, the missed detection status of parking space 8016036 is "missed vehicle exit".

[0123] If the current image of the target parking space shows a vehicle present, and the current entry / exit record for the target parking space shows a vehicle absent, then the missed detection status of the target parking space is determined to be a missed entry status. For example, if... Figure 9 As shown in the second area, the current parking status of parking space 8016036 is "with a car". As shown in the third area, the current parking status recorded in the vehicle entry and exit records of parking space 8016036 is "without a car". Therefore, the missed detection status of parking space 8016036 is "missed vehicle entry".

[0124] It should be noted that the parking status of the target parking space in the current image can be determined based on whether there is a parked vehicle in the current image. When there is a parked vehicle in the current image, the parking status of the target parking space in the current image is "with vehicle"; when there is no parked vehicle in the current image, the parking status of the target parking space in the current image is "without vehicle".

[0125] In the above embodiments, by determining the current parking status of multiple parking spaces and the current vehicle entry and exit records of multiple parking spaces, and when the current parking status of the target parking space differs from the parking status in the current vehicle entry and exit records of the target parking space, it is determined that the target parking space has missed vehicle entry and exit checks. This achieves automatic identification of the target parking space where the vehicle entry and exit checks have missed checks, eliminating the need for regular inspections by patrol personnel, reducing the workload of regular manual inspections, lowering labor costs, and improving the timeliness of target parking space detection.

[0126] In another possible implementation, the parking management method also includes outputting a reminder message when a vehicle fails to be detected entering or leaving the target parking space.

[0127] Optionally, the alert information for missed vehicle entry / exit detection may include the identifier of the target parking space. Further, the alert information may also include the time when the parking image of the target parking space where the missed vehicle entry / exit detection occurred was captured.

[0128] In the above embodiments, when it is determined that a vehicle has missed its entry or exit at the target berth, an alert is output to notify the inspection personnel that a vehicle has missed its entry or exit at the target berth. On the one hand, this allows the inspection personnel to mark a local image in the current image of the target berth in a timely manner. On the other hand, it can remind the inspection personnel to reconfirm, thereby improving the accuracy of determining that a vehicle has missed its entry or exit at the target berth.

[0129] In another possible implementation, the parking management method further includes: updating the current recorded time in the vehicle entry / exit record of the target parking space based on the time when a vehicle enters or exits the target parking space but is missed.

[0130] In one implementation, such as Figure 10 As shown, Figure 10 (a) shows the vehicle entry and exit records for the target parking space before the update. Figure 10 (b) shows the updated entry and exit records for the target parking space. Specifically, before the update, the current recorded parking status in the entry and exit records for the target parking space was "occupied," and the entry and exit records for the target parking space included the identifier of the target parking space (i.e., Figure 10 (a) 8016036), parking vehicle markings (i.e. Figure 10 (a) Zhejiang A6186) and the most recent entry time (i.e. Figure 10 (a) 2021 / 08 / 27 12:59:24). Further, when the target parking space's missed detection status is a missed vehicle exit status, the current recorded time in the target parking space's entry / exit record is updated based on the acquisition time of the earlier historical image among two adjacent historical images. After the update, the target parking space's entry / exit record includes the target parking space's identifier (i.e.,...). Figure 10In Figure (b) 10, the last departure time (8016036) and the last departure time (i.e., 2021 / 08 / 27 14:03:24) can be understood as the acquisition time of the first historical image acquired in two adjacent historical images.

[0131] In another implementation, such as Figure 11 As shown, Figure 11 (a) shows the vehicle entry and exit records for the target parking space before the update. Figure 11 (b) shows the updated entry and exit records for the target parking space. Specifically, before the update, the current recorded parking status in the entry and exit records for the target parking space was "no vehicle," and the entry and exit records for the target parking space included the identifier of the target parking space (i.e., Figure 11 (a) 8016036) and the last departure time (i.e. Figure 11 (a) 2021 / 08 / 27 11:48:08. Further, when the target parking space's missed detection status is a missed vehicle entry status, the current recorded time in the target parking space's entry / exit record is updated based on the acquisition time of the later-acquired historical image among two adjacent historical images. After the update, the target parking space's entry / exit record includes the target parking space's identifier (i.e.,...). Figure 11 (b) 8016036), parking vehicle markings (i.e. Figure 11 (b) Zhejiang A6186) and the most recent entry time (i.e. Figure 11 In (b) of the image, 2021 / 08 / 27 12:01:24, it is understandable that the most recent vehicle entry time is the acquisition time of the later historical image among two adjacent historical images.

[0132] For example, the vehicle entry / exit record for the target parking space contains a parked vehicle. In this case, the entry / exit record includes the target parking space identifier, the parked vehicle identifier, and the entry time. The parked vehicle is the vehicle parked in the target parking space, and the entry time is the time the parked vehicle entered the target parking space. Further, after the parked vehicle leaves the target parking space, but before a new vehicle enters the target parking space, the vehicle entry / exit record for the target parking space is updated to include the target parking space identifier and the last exit time. The last exit time is the time the parked vehicle left the target parking space.

[0133] Optionally, updating the current vehicle entry / exit record for the target berth can be done by updating the exit time to the entry time and adding a vehicle identifier.

[0134] In one implementation, the missed detection state of the target parking space is the vehicle entry missed detection state, that is, there is a parked vehicle in the parking image of the target parking space, but no parked vehicle in the current vehicle entry / exit record of the target parking space. Specifically, the current vehicle entry / exit record of the target parking space includes the identifier of the target parking space and the last exit time. In this case, the time when the target parking space experiences a missed vehicle entry / exit is specifically the vehicle entry missed detection time. Further, the current vehicle entry / exit record of the target parking space is updated to include the identifier of the target parking space, the identifier of the parked vehicle, and the entry time. The entry time is the acquisition time of the later historical image among two adjacent historical images.

[0135] Optionally, the identifiers of parked vehicles in the updated entry / exit records can be obtained by identifying parked vehicles in the target historical image.

[0136] Optionally, updating the current entry / exit record for the target berth can be done by updating the entry time to the exit time.

[0137] In one implementation, the missed detection state of the target parking space is the exit missed detection state, that is, there is no parked vehicle in the parking image of the target parking space, but there is a parked vehicle in the current entry / exit record of the target parking space. Specifically, the current entry / exit record of the target parking space includes the identifier of the target parking space, the identifier of the parked vehicle, and the entry time. In this case, the time of the missed entry / exit detection of the target parking space is specifically the exit missed detection time of the target parking space. Further, the current entry / exit record of the target parking space is updated to include the identifier of the target parking space and the last exit time. The last exit time is the acquisition time of the earlier historical image among two adjacent historical images.

[0138] In the above embodiments, the current vehicle entry and exit records of the target berth are automatically updated based on the time when vehicles miss inspection. This eliminates the need for manual entry by inspection personnel, improving the efficiency of updating vehicle entry and exit records and reducing labor costs.

[0139] The foregoing primarily describes the solutions of the embodiments of this application from a methodological perspective. It is understood that, in order to achieve the above-described functions, the computer device includes at least one of the hardware structures and software modules corresponding to the execution of each function. Those skilled in the art should readily recognize that, based on the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0140] This application embodiment can divide the parking management device into functional units according to the above method example. For example, each function can be divided into a separate functional unit, or two or more functions can be integrated into one processing unit. The integrated unit can be implemented in hardware or as a software functional unit. It should be noted that the unit division in this application embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0141] For example, Figure 12 A possible structural schematic diagram of the parking management device (denoted as parking management device 1200) involved in the above embodiments is shown. The parking management device 1200 includes a determination unit 1201, a similarity unit 1202, and a missed detection unit 1203. The determination unit 1201 is used to determine the similarity between the current image of the target parking space and multiple historical images of the target parking space within a preset time period when a missed entry / exit occurs at the target parking space; wherein the start time of the preset time period is not earlier than the time of the current record in the entry / exit records of the target parking space, and the end time of the preset time period is not later than the acquisition time of the current image. For example, Figure 3 S301 shown Figure 5 S301a-S301b are shown. Similarity unit 1202 is used to determine two adjacent historical images from multiple historical images whose image content has changed, based on the similarity between the current image and multiple historical images respectively. For example, Figure 3 S302 is shown. The missed detection unit 1203 is used to determine the time when a vehicle entered or exited the target berth was missed, based on the acquisition time of two adjacent historical images. For example, Figure 3 S303 is shown.

[0142] Optionally, the determining unit 1201 is specifically used to acquire a local image of the current image of the target berth; determine the similarity between the local image and the target area image of each historical image within the preset time period; wherein the target area image and the local image are used to represent the same spatial region of the target berth.

[0143] Optionally, in the event that a vehicle is missed during entry inspection at the target parking space, the partial image of the current image of the target parking space includes a partial image of the vehicle parked at the target parking space.

[0144] Optionally, if a vehicle fails to be detected at the target parking space, the area of ​​a local image of the current image of the target parking space is greater than or equal to a second preset threshold.

[0145] Optionally, the similarity unit 1202 is specifically used to determine that the image content of two adjacent historical images has changed when the difference between the first similarity and the second similarity is greater than or equal to a first preset threshold; wherein, the first similarity is the similarity between the current image and one of the two adjacent historical images, and the second similarity is the similarity between the current image and the other of the two adjacent historical images.

[0146] Optionally, the determining unit 1201 is specifically used to determine that a vehicle entry / exit miss has occurred at the target parking space when the parking status corresponding to the current image of the target parking space is different from the parking status currently recorded in the vehicle entry / exit record of the target parking space; wherein, if the parking status corresponding to the current image of the target parking space is a vehicle-occupied state and the parking status currently recorded in the vehicle entry / exit record of the target parking space is a vehicle-free state, the miss status of the target parking space is determined to be a vehicle entry miss; if the parking status corresponding to the current image of the target parking space is a vehicle-free state and the parking status currently recorded in the vehicle entry / exit record of the target parking space is a vehicle-occupied state, the miss status of the target parking space is determined to be a vehicle exit miss.

[0147] For a detailed description of the above-mentioned optional methods, please refer to the foregoing method embodiments, which will not be repeated here. Furthermore, the explanation of any of the parking management devices 1200 provided above, as well as the description of their beneficial effects, can be found in the corresponding method embodiments described above, and will not be repeated here.

[0148] As an example, combined Figure 2 The functions implemented by some or all of the determination unit 1201, similarity unit 1202, and miss detection unit 1203 in the parking management device 1200 can be achieved through Figure 2 Processor 201 in the middle executes Figure 2 The program code in memory 202 is used for implementation. The determining unit 1201 can also be implemented through... Figure 2 The receiving unit in the communication interface 203 is implemented.

[0149] This application also provides a computer-readable storage medium storing a computer program that, when run on a computer, causes the computer to perform the method executed by any of the parking management devices described above.

[0150] For explanations of the relevant content and descriptions of the beneficial effects in any of the computer-readable storage media provided above, please refer to the corresponding embodiments described above, which will not be repeated here.

[0151] This application also provides a chip. This chip integrates a control circuit for implementing the functions of the parking management device 1200 described above, and one or more ports. Optionally, the functions supported by this chip can be referred to above, and will not be repeated here. Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium. The storage medium mentioned above can be a read-only memory, random access memory, etc. The processing unit or processor mentioned above can be a central processing unit, a general-purpose processor, an application-specific integrated circuit (ASIC), a microprocessor (digital signal processor, DSP), a field-programmable gate array (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof.

[0152] This application also provides a computer program product containing instructions that, when executed on a computer, cause the computer to perform any of the methods described in the above embodiments. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions may be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or may include one or more data storage devices such as servers or data centers that can be integrated with the medium. The available medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., SSD), etc.

[0153] It should be noted that the devices for storing computer instructions or computer programs provided in the embodiments of this application, such as but not limited to the memory, computer-readable storage medium and communication chip, are all non-transitory.

[0154] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented using software programs, implementation can be, in whole or in part, in the form of a computer program product. This computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device containing one or more servers, data centers, etc., that can be integrated with the medium. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state disks, SSDs).

[0155] Although this application has been described herein in conjunction with various embodiments, those skilled in the art, by reviewing the accompanying drawings, the disclosure, and the appended claims, will understand and implement other variations of the disclosed embodiments in carrying out the claimed application. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude multiple instances. A single processor or other unit can implement several functions listed in the claims. While different dependent claims may recite certain measures, this does not mean that these measures cannot be combined to produce good results.

[0156] Although this application has been described in conjunction with specific features and embodiments, it is obvious that various modifications and combinations can be made thereto without departing from the spirit and scope of this application. Accordingly, this specification and drawings are merely exemplary illustrations of this application as defined by the appended claims, and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from the spirit and scope of this application. Thus, if such modifications and modifications of this application fall within the scope of the claims of this application and their equivalents, this application is also intended to include such modifications and modifications.

Claims

1. A parking management method, characterized in that, include: In the event that a vehicle enters or exits a target parking space but is missed, the first similarity between the current image of the target parking space and a first historical image among multiple historical images of the target parking space within a preset time period, and the second similarity between the current image and a second historical image among the multiple historical images are determined; the start time of the preset time period is no earlier than the time currently recorded in the vehicle entry / exit record of the target parking space, and the end time of the preset time period is no later than the acquisition time of the current image. The first historical image and the second historical image are adjacent historical images; If the difference between the first similarity and the second similarity is greater than or equal to the first preset threshold, the time when the target berth was missed in vehicle entry and exit is determined based on the acquisition time of the first historical image and the second historical image.

2. The parking management method according to claim 1, characterized in that, The step of determining the first similarity between the current image of the target berth and a first historical image among a plurality of historical images of the target berth within a preset time period, and a second similarity with a second historical image among the plurality of historical images, includes: Obtain a partial image of the current image of the target berth; Determine the similarity between the local image and the target area image of the first historical image and the second historical image within the preset time period; wherein the target area image and the local image are used to represent the same spatial area of ​​the target berth.

3. The parking management method according to claim 2, characterized in that, In the event that a vehicle is missed during entry inspection at the target parking space, the partial image of the current image of the target parking space includes a partial image of the vehicle parked at the target parking space.

4. The parking management method according to claim 2, characterized in that, In the event that a vehicle fails to be detected at the target parking space, the area of ​​a local image of the current image of the target parking space is greater than or equal to a second preset threshold.

5. The parking management method according to any one of claims 1 to 4, characterized in that, The method further includes: If the parking status corresponding to the current image of the target parking space is different from the parking status currently recorded in the vehicle entry and exit record of the target parking space, it is determined that the target parking space has experienced a missed vehicle entry and exit detection. Wherein, if the parking status corresponding to the current image of the target parking space is a vehicle-occupied state, and the parking status currently recorded in the vehicle entry and exit records of the target parking space is a vehicle-free state, the missed detection status of the target parking space is a vehicle-entry missed detection status. If the parking status corresponding to the current image of the target parking space is "no car" and the current recorded parking status in the vehicle entry / exit record of the target parking space is "car present", then the missed detection status of the target parking space is "missed vehicle exit".

6. A parking management device, characterized in that, include: The determining unit is configured to, in the event of a missed vehicle entry / exit at the target berth, determine the first similarity between the current image of the target berth and a first historical image among a plurality of historical images of the target berth within a preset time period, and the second similarity between the current image and a second historical image among the plurality of historical images; the start time of the preset time period is not earlier than the time currently recorded in the vehicle entry / exit record of the target berth, and the end time of the preset time period is not later than the acquisition time of the current image; The first historical image and the second historical image are adjacent historical images; The missed detection unit is used to determine the time when a vehicle enters or leaves the target berth based on the acquisition time of the two adjacent historical images, when the difference between the first similarity and the second similarity is greater than or equal to a first preset threshold.

7. The apparatus according to claim 6, characterized in that, The determining unit is specifically used to acquire a local image of the current image of the target berth; determine the similarity between the local image and the target area image of the first historical image and the second historical image within the preset time period; wherein, the target area image and the local image are used to represent the same spatial area of ​​the target berth; In the event that a vehicle is missed during the detection of an entry into the target parking space, the partial image of the current image of the target parking space includes a partial image of the vehicle parked in the target parking space. In the event that a vehicle fails to be detected at the target parking space, the area of ​​a local image of the current image of the target parking space is greater than or equal to a second preset threshold. The determining unit is specifically used to determine that a vehicle entry / exit miss has occurred at the target parking space when the parking status corresponding to the current image of the target parking space is different from the parking status currently recorded in the vehicle entry / exit record of the target parking space; wherein, when the parking status corresponding to the current image of the target parking space is a vehicle-occupied state and the parking status currently recorded in the vehicle entry / exit record of the target parking space is a vehicle-free state, the miss status of the target parking space is determined to be an entry miss status; when the parking status corresponding to the current image of the target parking space is a vehicle-free state and the parking status currently recorded in the vehicle entry / exit record of the target parking space is a vehicle-occupied state, the miss status of the target parking space is determined to be an exit miss status.

8. An electronic device, characterized in that, include: processor; The processor is connected to a memory for storing computer execution instructions, and the processor executes the computer execution instructions stored in the memory to enable the electronic device to implement the method as described in any one of claims 1-5.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed on an electronic device, cause the electronic device to perform the method of any one of claims 1-5.

Images