Parking management method, parking management device and parking management system

Abstract

The invention relates to a parking management method, a parking management device and a parking management system, and the method comprises the steps: obtaining a first license plate of a vehicle which is historically parked in a target parking space, and a second license plate of a vehicle which is currently parked in the target parking space; matching the first license plate with the second license plate; under the condition that the first license plate and the second license plate are matched unsuccessfully, the caching frequency of the target parking space is increased; and generating a parking order of the vehicle corresponding to the first license plate when the caching frequency is greater than or equal to the preset frequency. By adopting the method, an accurate parking order can be generated.

Description

Technical Field

[0001] The present application relates to the field of intelligent parking management, and in particular to a parking management method, a parking management device and a parking management system. Background Art

[0002] With the global technological innovation, in order to reduce energy consumption, more and more researchers are vigorously developing new energy technologies for green resources such as solar energy and wind energy to reduce environmental pollution caused by energy consumption. Low-power cameras such as solar energy are powered by solar energy and transmitted via 4G wireless network. There is no need to connect to the network or electricity for construction. The product is easy to install, has a short construction period, and is maintenance-free after implementation, which greatly reduces the construction and maintenance costs and operation and management costs. Therefore, more manufacturers use this product in urban on-street parking systems to improve the intelligence of on-street parking operation and management.

[0003] However, factors such as irregular parking, pedestrians and passing cars on the road, and lighting environment cause the intelligent algorithm center to be unable to correctly identify the license plate number, resulting in incorrect parking orders and the operator being unable to collect parking fees. Related technologies increase the number of solar cameras and optimize the camera installation angle from the equipment aspect; or optimize from the image recognition aspect to improve the accuracy of license plate recognition to effectively solve the problem of generating incorrect orders. However, the cost of related technologies is high; when the collected vehicle images are blurred due to factors such as lighting and weather, there is a bottleneck in the optimization of image recognition methods, and there is still a problem of being unable to accurately obtain the parking status of the vehicle, resulting in inaccurate parking orders for parking spaces.

[0004] With regard to the problem in the related technology that parking orders for parking spaces cannot be accurately obtained, no effective solution has been proposed so far. Summary of the invention

[0005] Based on this, it is necessary to provide a parking management method, a parking management device and a parking management system that can solve the problem of inaccurate parking orders for parking spaces in response to the above technical problems.

[0006] In a first aspect, a parking management method is provided in this embodiment, the method comprising: Acquire first identification information of a vehicle parked in a target parking space at a first time, and acquire second identification information of a vehicle parked in the target parking space at a second time; matching the first identification information and the second identification information; In the case where the first identification information fails to match the second identification information, increasing the number of cache times corresponding to the target parking space; When the cache times are greater than or equal to the preset times, a parking order for the vehicle corresponding to the first identification information is generated.

[0007] In some embodiments, matching the first identification information and the second identification information includes: When the first identification information includes a first license plate number, the second identification information includes a second license plate number, and the second license plate number meets a preset condition, a first match is performed on the first license plate number and the second license plate number; wherein the preset condition includes one or more of the following: the second license plate number includes a preset identification, the second license plate number is blocked, and the type of the second license plate is unknown; When the first identification information includes the first license plate number, the second identification information includes the second license plate number, and the second license plate number does not meet the preset condition, a second match is performed on the first license plate number and the second license plate number.

[0008] In some embodiments, performing a first match on the first license plate number and the second license plate number includes: If the length of the first license plate number is consistent with the length of the second license plate number and the number of unmatched characters between the first license plate number and the second license plate number is less than or equal to a preset value, it is determined that the first license plate number and the second license plate number are matched successfully; if the length of the first license plate number is inconsistent with the length of the second license plate number or the number of unmatched characters between the first license plate number and the second license plate number is greater than a preset value, it is determined that the first license plate number and the second license plate number fail to match; and / or, When the characters in the first license plate number include the characters in the second license plate number, it is determined that the first license plate number and the second license plate number match successfully; when the characters in the first license plate number do not include the characters in the second license plate number, it is determined that the first license plate number and the second license plate number match unsuccessfully.

[0009] In some embodiments, matching the first identification information and the second identification information includes: When the first identification information includes a license plate number and the second identification information does not include a license plate number, it is determined that the first identification information and the second identification information do not match.

[0010] In some embodiments, when the first identification information fails to match the second identification information, increasing the number of cache times corresponding to the target parking space; and when the number of cache times is greater than or equal to a preset number, generating a parking order for the vehicle corresponding to the first identification information includes: acquiring a first image including the target parking space at the second time; When a vehicle is recognized according to the first image, but a license plate number is not recognized according to the first image, increasing a first cache count corresponding to the target parking space; When the first cache number is greater than or equal to the first preset number, a parking order for the vehicle corresponding to the first identification information is generated.

[0011] In some embodiments, when the first identification information fails to match the second identification information, increasing the number of cache times corresponding to the target parking space; and when the number of cache times is greater than or equal to a preset number, generating a parking order for the vehicle corresponding to the first identification information includes: acquiring a first image including the target parking space at the second time; In the case where no vehicle is recognized according to the first image, increasing a second cache count corresponding to the target parking space; When the second cache number is greater than or equal to the second preset number, a parking order for the vehicle corresponding to the first identification information is generated.

[0012] In some embodiments, after matching the first identification information and the second identification information, the method further includes: When the first identification information matches the second identification information successfully, the cached times of the target parking space are cleared.

[0013] In some embodiments, when the cache count is greater than or equal to a preset count, generating a parking order for a vehicle corresponding to the first identification information includes: Acquire a second image of the target parking space including the first license plate number; Obtaining the parking time of the vehicle corresponding to the first identification information according to the first shooting time and the last shooting time of the second image; A parking order for the vehicle corresponding to the first identification information is generated according to the parking time.

[0014] In a second aspect, a parking management device is provided in this embodiment, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the parking management method described in the first aspect when executing the computer program.

[0015] In a third aspect, a parking management system is provided in this embodiment, the system comprising a photographing device, a recognition device and the parking management device described in the first aspect above; wherein: The photographing device is used to photograph an image including the target parking space; The recognition device is used to obtain first identification information of the vehicle in the target parking space based on an image captured at the target parking space at a first time, and to obtain second identification information of the vehicle in the target parking space based on an image captured at the target parking space at a second time.

[0016] The above-mentioned parking management method, parking management device and parking management system determine whether the vehicle parked at the first time has left the target parking space according to the number of mismatches between the first identification information of the vehicle parked at the first time and the second identification information of the vehicle parked at the second time, thereby obtaining the parking status of the vehicle corresponding to the first identification information in the target parking space and generating an accurate parking order. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a hardware structure block diagram of a terminal of a parking management method in one embodiment of the present application; Figure 2 This is a flow chart of a parking management method in one embodiment of the present application; Figure 3 This is an architecture diagram of a parking order generation system based on a wiring-free camera in one embodiment of the present application; Figure 4 This is a flow chart of a method for generating a parking order using a wiring-free camera in one embodiment of the present application; Figure 5 It is a traditional parking order generation method; Figure 6 This is a flow chart of a method for generating a parking order in an event where a car and a license plate are present in one embodiment of the present application; Figure 7 A schematic diagram of a fuzzy matching rule in an embodiment of the present application; Figure 8 A flowchart of a method for generating a parking order in an event where a vehicle has no license plate or the license plate cannot be identified in one embodiment of the present application; Fig. 9 This is a flow chart of a method for generating a parking order in a no-car event in one embodiment of the present application; Fig.10 The present application is a diagram of the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0019] The method embodiment provided in this embodiment can be executed in a terminal, a computer or a similar computing device. For example, running on a terminal, Figure 1 FIG. 1 is a hardware structure diagram of a terminal of a parking management method according to an embodiment of the present application. Figure 1 As shown, the terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 and a memory 104 for storing data, wherein the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA. The above terminal may also include a transmission device 106 and an input and output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0020] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the parking management method in this embodiment. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the terminal via a network. Examples of the above network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0021] The transmission device 106 is used to receive or send data via a network. The above network includes a wireless network provided by the communication provider of the terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet wirelessly.

[0022] In this embodiment, a parking management method is provided. Figure 2 is a flow chart of the parking management method of this embodiment. Figure 2 As shown, the process includes the following steps: Step S202: acquiring first identification information of a vehicle parked in a target parking space at a first time, and acquiring second identification information of a vehicle parked in the target parking space at a second time.

[0023] The first time is earlier than the second time. The first identification information includes but is not limited to whether there is a vehicle parked in the target parking space at the first time, and vehicle attributes such as the license plate, vehicle logo, and vehicle color of the vehicle parked in the target parking space. Optionally, the first license plate of the vehicle parked in the target parking space is obtained based on the records in the database. Alternatively, the first identification information can be obtained based on the vehicle image recognition obtained by photographing the target parking space at the first time, or the target parking space is manually entered.

[0024] The second identification information includes, but is not limited to, whether there is a vehicle parked in the target parking space at the second time, and the vehicle attributes such as the license plate, logo, and color of the vehicle parked in the target parking space. The second identification information can be obtained by methods such as image recognition, radio frequency identification, and manual entry. Optionally, the second identification information is obtained by recognizing the vehicle image obtained by photographing the target parking space at the second time. It is understandable that due to the defects of the image recognition, radio frequency identification, and other methods themselves, the second identification information may be inaccurate.

[0025] Optionally, the first identification information is information obtained based on a parking space event obtained at a first time; and the second identification information is information obtained based on a parking space event obtained at a second time. Acquiring a parking space event is a process of acquiring an image of a target parking space based on a specified event interval, performing image recognition on the image containing the target parking space to obtain identification information of a vehicle parked in the target parking space, and then reporting the identification information of the vehicle parked in the target parking space to a terminal that executes the parking management method.

[0026] Step S204: matching the first identification information and the second identification information.

[0027] Among them, one or more information items such as vehicle type, color, character content in the license plate, etc. in the first identification information and the second identification information can be matched.

[0028] Optionally, matching the first identification information and the second identification information includes: determining whether the degree of matching between the first identification information and the second identification information meets a preset matching standard. If there are information items in the first identification information and the second identification information that do not meet the matching standard, the first identification information and the second identification information are determined to be mismatched; if all information items in the first identification information and the second identification information meet the preset matching standard, the first identification information and the second identification information are determined to be matched. Optionally, a preset matching standard is set correspondingly according to the identification information used for comparison. For example, when the identification information used for comparison is color, if the color difference between the first identification information and the second identification information is greater than or equal to a specified value, the first identification information and the second identification information are determined to match; otherwise, the first identification information and the second identification information do not match. When the identification information used for comparison is the character content of the license plate, if the number of different characters of the license plate in the first identification information and the characters of the license plate in the second identification information is greater than or equal to a specified number, the first identification information and the second identification information are determined to match; otherwise, the first identification information and the second identification information do not match.

[0029] Step S206: when the first identification information fails to match the second identification information, increase the number of cache times corresponding to the target parking space.

[0030] Among them, the greater the number of cache times of the target parking space, the greater the possibility that the vehicle currently parked in the target parking space does not belong to the historical parked vehicle corresponding to the first identification information, and the historical parked vehicle is more likely to have left the target parking space; conversely, the vehicle parked in the target parking space is more likely to still be a historical parked vehicle.

[0031] Optionally, an initial cache count is set for the target parking space, and after the first identification information and the second identification information of the target parking space fail to match, the cache count of the target parking space is increased based on a specified step length.

[0032] Step S208: When the cache times are greater than or equal to the preset times, a parking order for the vehicle corresponding to the first identification information is generated.

[0033] The preset number of times can be set or modified as required. When the number of cache times of the target parking space is greater than or equal to the preset number of times, and the target parking space has had the first identification information and the second identification information not matching for multiple times, it is determined that the vehicle corresponding to the first identification information has left the target parking space, and a parking order for the vehicle corresponding to the first identification information is generated.

[0034] In the above parking management method, the first identification information of the vehicle parked in the target parking space at the first time and the second identification information of the vehicle parked in the target parking space at the second time are matched, and the cache times corresponding to the target parking space are adjusted according to the matching between the first identification information and the second identification information; it is judged whether the vehicle corresponding to the first identification information has left the target parking space according to the cache times, so as to obtain the parking situation of the vehicle in the parking space and generate an accurate parking order, which reduces the influence of the inaccurate second identification information on the accuracy of the parking order and solves the problem of inaccurate parking order.

[0035] In some embodiments, after matching the first license plate and the second license plate, the method further includes: after matching the first identification information and the second identification information, the method further includes: if the first identification information and the second identification information match successfully, clearing the cached times of the target parking space.

[0036] Optionally, if the first license plate and the second license plate are obtained by an image recognition method, then when the first license plate and the second license plate are successfully matched, not only the cache times can be cleared, but also the image corresponding to the target parking space can be cleared. If the cache times of the target parking space are greater than the initial cache times, and the first identification information and the second identification information are successfully matched, the increased cache times of the target parking space may be caused by inaccurate identification information obtained historically. In this embodiment, by clearing the cache times of the target parking space, the terminal executing the parking management method determines that the vehicle corresponding to the first license plate has left and generates a parking order only when it is continuously determined that the vehicle parked in the target parking space has changed, which can further improve the accuracy of the parking order.

[0037] In some embodiments, matching the first identification information and the second identification information includes: performing a first matching between the first license plate number and the second license plate number when the first identification information includes the first license plate number, the second identification information includes the second license plate number, and the second license plate number meets a preset condition; wherein the preset condition includes one or more of the following: the second license plate number contains a preset identification, the second license plate number is obscured, and the type of the second license plate is unknown; performing a second matching between the first license plate number and the second license plate number when the first identification information includes the first license plate number, the second identification information includes the second license plate number, and the second license plate number does not meet the preset condition.

[0038] The first match is used to determine whether the similarity between the first license plate number and the second license plate number meets the preset matching criteria. The preset identifier is a character that does not exist in the license plate number. The preset identifier may be "#", " " When the second license plate number meets one or more preset conditions, the second license plate number is incomplete and there is a possibility of recognition error. By performing a first match on the first license plate number and the second license plate number, it can be more accurately determined whether the vehicles corresponding to the first license plate number and the second license plate number are the same vehicle.

[0039] The second match is used to determine whether the first license plate number and the second license plate number are exactly the same. Optionally, if the second license plate number does not meet all the preset conditions, the characters in the first license plate number can be directly compared to determine whether they are the same as the characters in the second license plate number; if they are the same, it is determined whether the vehicles corresponding to the first license plate number and the second license plate number are the same vehicle, and the cache times of the target parking space are cleared; if they are not the same, the cache times of the target parking space are increased.

[0040] In this embodiment, it is determined whether there is a possibility of inaccuracy in the recognition of the second license plate number by using preset conditions, and the first license plate number and the second license plate number are matched when the second license plate number meets the preset conditions.

[0041] In some of the embodiments, a first match is performed on the first license plate number and the second license plate number, including: when the length of the first license plate number is consistent with the length of the second license plate number and the number of unmatched characters between the first license plate number and the second license plate number is less than or equal to a preset value, judging that the first license plate number and the second license plate number are successfully matched; when the length of the first license plate number and the length of the second license plate number are inconsistent or the number of unmatched characters between the first license plate number and the second license plate number is greater than a preset value, judging that the first license plate number and the second license plate number fail to match; and / or, when the characters in the first license plate number include the characters in the second license plate number, judging that the first license plate number and the second license plate number are successfully matched; when the characters in the first license plate number do not include the characters in the second license plate number, judging that the first license plate number and the second license plate number fail to match.

[0042] Wherein, when the characters corresponding to the same position of the license plate number are different, the character is regarded as an unmatched character. Optionally, the character length in the first license plate number is first compared with the character length in the second license plate number. When the length of the first license plate number is inconsistent with the length of the second license plate number, it is judged that the first license plate number and the second license plate number fail to match. When the length of the first license plate number and the length of the second license plate number are consistent, the character content in the first license plate number and the character content in the second license plate number are compared: in the specified order, the characters in the first license plate number and the characters in the second license plate number are compared one by one. When the number of unmatched characters in the characters in the first license plate number and the second license plate number is greater than or equal to a preset value, it is judged that the first license plate number and the second license plate number fail to match; when the number of unmatched characters in the characters in the first license plate number and the second license plate number is less than or equal to a preset value, it is judged that the first license plate number and the second license plate number successfully match.

[0043] Furthermore, since the preset conditions satisfied by the second license plate number are different, the possibility of inaccurate recognition of the second license plate number is different from that of the real license plate number. The first matching rule can be obtained in combination with the preset conditions satisfied by the second license plate number. In the case where the second license plate number contains a preset identifier, the first matching rule is: when the length of the first license plate number is inconsistent with the length of the second license plate number or the number of unmatched characters between the first license plate number and the second license plate number is greater than a preset value, it is judged that the first license plate number and the second license plate number match failed. When the length of the first license plate number and the length of the second license plate number are consistent and the number of unmatched characters between the first license plate number and the second license plate number is less than or equal to a preset value, it is judged that the first license plate number and the second license plate number match successfully.

[0044] When the second license plate number is blocked, the first matching rule is: when the characters in the first license plate number contain the characters in the second license plate number, it is judged that the first license plate number and the second license plate number are matched successfully; when the characters in the first license plate number do not contain the characters in the second license plate number, it is judged that the first license plate number and the second license plate number are matched unsuccessfully.

[0045] In the case where the type of the second license plate number is unknown, the first matching rule is: when the length of the first license plate number is consistent with the length of the second license plate number, the number of unmatched characters between the first license plate number and the second license plate number is less than or equal to a preset value, and the characters in the first license plate number contain the characters in the second license plate number, it is determined that the first license plate number and the second license plate number are matched successfully. In the case where the length of the first license plate number is inconsistent with the length of the second license plate number, or the number of unmatched characters between the first license plate number and the second license plate number is greater than a preset value, or the characters in the first license plate number do not contain the characters in the second license plate number, it is determined that the first license plate number and the second license plate number fail to match. It is understandable that the correspondence between the second license plate number satisfying the preset conditions and the matching logic can be adjusted according to demand, which is not elaborated here.

[0046] In this embodiment, by performing fuzzy matching on the first license plate number and the second license plate number, the accuracy of the matching result of the first license plate number and the second license plate number can be improved, which helps to improve the accuracy of parking order generation.

[0047] In some embodiments, matching the first identification information and the second identification information includes: when the first identification information includes a license plate number and the second identification information does not include the license plate number, determining that the first identification information and the second identification information do not match.

[0048] If there is no vehicle parked in the target parking space at the second time, or if there is a vehicle parked in the target parking space at the second time but the license plate is not recognized, the second identification information does not include the second license plate number. Therefore, there is a possibility that the vehicle corresponding to the first license plate is not parked in the target parking space. By increasing the number of cache times of the target parking space, the accuracy of judging whether the vehicle parked in the target parking space has changed is improved.

[0049] In order to distinguish between the situation where there is no parked vehicle in the target parking space and the situation where there is a vehicle parked in the target parking space but the license plate number cannot be identified, in some embodiments, when the first identification information and the second identification information fail to match, the cache number corresponding to the target parking space is increased; when the cache number is greater than or equal to a preset number, a parking order for the vehicle corresponding to the first identification information is generated, including: acquiring a first image including the target parking space at a second time; when the vehicle is identified based on the first image and the license plate number is not identified based on the first image, increasing the first cache number corresponding to the target parking space; when the first cache number is greater than or equal to a first preset number, a parking order for the vehicle corresponding to the first identification information is generated.

[0050] The first cache count corresponds to the number of times that there is a parked vehicle in the target parking space, but the license plate number of the parked vehicle is not recognized because the license plate number is not recognized or is blocked, resulting in the number of times that there is no actual license plate number matching the first license plate number in the first image. Optionally, an initial first cache count is set, and when a new first image of the target parking space is received, if the vehicle can be recognized based on the first image but the license plate number cannot be recognized based on the first image, the first cache count is increased according to a specified step size. When the first cache count is greater than or equal to the first preset count, the parking time of the vehicle corresponding to the first license plate number is obtained based on the captured image of the vehicle corresponding to the first license plate number in the target parking space, and then a parking order is generated.

[0051] Furthermore, when a vehicle is identified based on the first image and the license plate number cannot be identified based on the first image, the number of user pushes for the first vehicle can be increased; when the number of user pushes is greater than or equal to the preset number of pushes, a preset push message is sent to the management terminal of the target parking space. The preset push message is used to indicate the situation that the vehicle license plate number cannot be identified by the first image. The management terminal can be a terminal of a parking management staff. By sending the preset push message, the management staff of the target parking space can manually process the parking order of the target parking space.

[0052] In this embodiment, by setting the first cache number and the corresponding first preset number, the scenarios where the vehicle license plate number is blocked or the vehicle has no license plate number, and the scenarios where the first license plate number and the second license plate number do not match are distinguished, thereby improving the practicality of the parking management method.

[0053] In some of the embodiments, when the first identification information fails to match the second identification information, the number of cache times corresponding to the target parking space is increased; when the number of cache times is greater than or equal to a preset number, a parking order for the vehicle corresponding to the first identification information is generated, including: acquiring a first image including the target parking space at a second time; when the vehicle is not identified based on the first image, the number of second cache times corresponding to the target parking space is increased; when the second number of cache times is greater than or equal to a second preset number, a parking order for the vehicle corresponding to the first identification information is generated.

[0054] Among them, the initial values ​​of the first cache number and the second cache number can be the same or different. The increase step size of the first cache number and the second cache number, as well as the values ​​of the first preset number and the second preset number can be set according to the needs. The second cache number corresponds to the number of times that there is no parked vehicle in the target parking space, resulting in the absence of a license plate matching the first license plate in the first image. Optionally, the initial second cache number is set, and when a new first image of the target parking space is received, if the vehicle cannot be identified according to the first image, the first cache number is increased according to the specified step size. When the second cache number is greater than or equal to the second preset number, the parking time of the vehicle corresponding to the first license plate is obtained according to the captured image of the vehicle corresponding to the first license plate in the target parking space, and then a parking order is generated. Furthermore, if the first identification information successfully matches the newly acquired identification information in the future time period, the terminal simultaneously clears the first cache number and the second cache number corresponding to the target parking space.

[0055] In this embodiment, by setting the second cache number and the corresponding second preset number, the parking management method can be adapted to the scenario where there is no car in the parking space.

[0056] In some embodiments, when the cache number is greater than or equal to a preset number of times, a parking order for the vehicle corresponding to the first identification information is generated, including: obtaining a second image of the target parking space containing the first license plate number; obtaining a parking time of the vehicle corresponding to the first identification information based on a first shooting time and a last shooting time of the second image; and generating a parking order for the vehicle corresponding to the first identification information based on the parking time.

[0057] The second image is one or more images including the target parking space and the first license plate. Optionally, when the number of cache times is greater than or equal to the preset number of times, the exit time of the vehicle corresponding to the first license plate number is obtained according to the last shooting time; the entry time of the vehicle corresponding to the first license plate number is obtained according to the first shooting time. The parking time is obtained according to the exit time and the entry time.

[0058] Furthermore, the first image of the target parking space is acquired at a second time. When the number of cache times is greater than or equal to the preset number of times, if the second license plate number can be obtained based on the first image recognition, the entry time of the vehicle corresponding to the second license plate number can also be obtained according to the shooting time of the first image.

[0059] In this embodiment, the parking time of the vehicle corresponding to the first license plate can be accurately obtained through the shooting time of the second image, thereby achieving the effect of improving the accuracy of the parking order.

[0060] In the related art, the parking time of vehicles in parking spaces is determined based on wire-free cameras, and parking orders are generated, but there is a problem of low parking order accuracy. This is because parking spaces are usually located on the roadside, and environmental information such as license plate obstruction and passing vehicles will reduce the license plate recognition rate of the intelligent algorithm center, causing the parking fee collection system to generate incorrect orders. In order to improve the accuracy of generating orders for wiring-free cameras used in parking fee collection systems, related technologies include: 1. Relying on toll collectors to manually process camera recognition errors or failures to recognize license plates to generate correct parking orders. Although this method can solve the problem of low order accuracy, it greatly increases human resources and cannot be automated; 2. Relying on the deployment of more cameras to improve the accuracy of parking orders greatly increases the cost of establishing the system; 3. The intelligent algorithm center optimizes the image recognition method, but it is more complex and difficult to implement, and the algorithm optimization relies more on the image quality collected by the equipment.

[0061] Based on the above problems, in one embodiment, a parking order generation method based on a wiring-free camera is provided. The parking order generation system architecture based on a wiring-free camera is as follows: Figure 3 As shown, the device side system includes one or more wiring-free cameras. The device side wakes up the wiring-free cameras at regular intervals, and captures images containing parking spaces through the wiring-free cameras, and sends the images to the parking fee platform. The parking fee platform forwards the image address to the algorithm intelligence center for image recognition. The intelligent algorithm center returns the parking space recognition results obtained by image recognition to the parking fee platform for logical processing of vehicle entry and exit. There are four states of parking space recognition results returned by the algorithm center, namely: no car in the parking space; there is a car in the parking space but the vehicle has no license plate; there is a car in the parking space, there is a license plate and the vehicle attributes can be identified; there is a car in the parking space and there is a license plate, but the vehicle attributes cannot be identified. Among them, vehicle attributes include license plate number, license plate occlusion, license plate type, license plate color, etc.

[0062] Figure 4 A flowchart of a parking order generation method for a wiring-free camera is provided. Figure 4 As shown, the following steps are included: Step S401: The wiring-free camera periodically captures parking space images and transmits the captured parking space images to the intelligent algorithm center.

[0063] The wiring-free camera is in a dormant state for a long time. Its core is to rely on solar power supply and 4G transmission to interact with the parking fee collection platform. The parking fee collection platform sets the working time and capture interval of the wiring-free camera. When the set capture time is reached, the camera wakes up and actively registers to the platform, so that the parking fee collection system obtains the captured image at that time and transmits it to the intelligent algorithm center.

[0064] Step S402: the intelligent algorithm center identifies the parking space image and reports the parking space event corresponding to the identification result to the parking fee collection system, wherein the intelligent algorithm center outputs the parking space status and vehicle attributes.

[0065] Step S403: the parking fee collection system generates a parking order according to the parking space event.

[0066] Among them, the parking fee collection system executes the vehicle entry and exit logic based on the parking space recognition results.

[0067] Figure 5 A traditional parking order generation method is provided. The traditional parking fee collection platform processes the vehicles in and out of the parking space according to the parking space events returned by the intelligent algorithm center. The traditional order generation method process is as follows Figure 5 As shown: When the recognition result is that there is a car in the parking space and the vehicle has a license plate, the parking space event is that vehicle B is parked. According to the records in the parking fee platform, it is determined that vehicle A is parked in the parking space. Determine whether vehicle B in the parking space event is the same as vehicle A. If so, only the snapshot record is stored; if not, vehicle A is exited and a parking order for vehicle A is generated. The exit time of vehicle A is the time when vehicle A was last captured in the stored snapshot record or the payment time of vehicle A. The parking fee platform records the entry of vehicle B and clears the record of vehicle A in the parking fee platform.

[0068] When there is a car in the parking space but the vehicle has no license plate, or there is a car in the parking space but the license plate cannot be identified, the intelligent algorithm center reports to the parking fee platform the parking space event of a car without a license plate being parked or a license plate cannot be identified. According to the records in the parking fee platform, if it is determined that the original parked vehicle in the parking space is vehicle A, if the parking fee platform receives the parking space event of a car without a license plate being parked or an unidentifiable parking space, the parking fee platform will remove vehicle A and generate a parking order.

[0069] When there is no car in the parking space, based on the records in the parking fee collection platform, it is determined that the original vehicle parked in the parking space is vehicle A. The parking fee collection platform then removes vehicle A and generates a parking order for vehicle A, clears the record of vehicle A in the parking fee collection platform, and stores the snapshot record when there is no car in the current parking space.

[0070] In the traditional parking order generation method, the parking fee collection platform completely relies on the recognition results of the intelligent algorithm center to generate parking orders. If the intelligent algorithm center makes a recognition error, the parking fee collection platform will generate a corresponding erroneous order.

[0071] Based on this, this embodiment optimizes the parking fee platform. In this embodiment, the parking fee platform's in-and-out vehicle logic system is optimized. Before the parking fee platform generates a parking order method, the parking space event is reported by the intelligent algorithm center. Optionally, the intelligent algorithm center obtains an image containing the target parking space by capturing the target parking space at a fixed time. The device-side system captures the image of the target parking space at the first time, and the intelligent algorithm center obtains identification information by identifying the captured image at the first time, and then reports the parking space event containing the first identification information to the parking fee platform. The device-side system captures the image of the target parking space at the second time, and the intelligent algorithm center obtains identification information by identifying the captured image at the second time, and then reports the parking space event containing the second identification information to the parking fee platform. The vehicle identified in the target parking space at the first time is recorded as vehicle A, and the vehicle identified in the target parking space at the second time is recorded as vehicle B. In the case where the first identification information includes the first license plate number of vehicle A and the vehicle B parked in the target parking space at the second time is an unlicensed vehicle, the first cache count is increased. When the first identification information includes the first license plate number of vehicle A and there is no vehicle parked in the target parking space at the second time, the second cache count is increased. When the first identification information includes the first license plate number of vehicle A and the second identification information includes the second license plate number of vehicle B, if the first license plate number and the second license plate number do not match, the second cache count is also increased.

[0072] Figure 6 A flowchart of a method for generating a parking order under the event of a car with a license plate is provided. Figure 6 As shown, including: Step S601, performing fuzzy matching on the first license plate number and the second license plate number.

[0073] Before the fuzzy matching of the first license plate number and the second license plate number is performed, the parking fee collection platform needs to judge the reported parking space event, including: when there is vehicle B in the target parking space at the second time and the license plate is valid, the parking fee collection platform judges whether the second license plate number of vehicle B meets the preset conditions. Among them, the preset conditions are to judge that the license plate number contains "#", the license plate is blocked, and the license plate type is unknown. If any of the above preset conditions is met, the step of fuzzy matching the first license plate number and the second license plate number (first matching) is performed. If all the above preset conditions are not met, the second license plate number is obtained according to the first image recognition, and the first license plate number and the second license plate number are matched for the second time.

[0074] Figure 7A schematic diagram of a fuzzy matching rule is provided. Figure 7 (a) provides fuzzy matching rules for the case where there is a car in the parking space, a license plate number, and the license plate number contains "#", such as Figure 7 As shown in (a), determine whether the length of the first license plate number is equal to the length of the second license plate number. If the license plate number lengths are not equal, the match fails. If the license plate number lengths are equal, determine whether the number of unmatched characters between the first license plate number and the second license plate number is less than or equal to a preset value. If the number of unmatched characters between the first license plate number and the second license plate number is less than or equal to the preset value, the match is successful; if the number of unmatched characters between the first license plate number and the second license plate number is greater than the preset value, the match fails. Optionally, when the number of different characters between the first license plate number and the second license plate number is less than or equal to 2, the match is successful; otherwise, the match fails. The preset value can be set to other values ​​as required.

[0075] Figure 7 (b) provides fuzzy matching rules when there is a car in the parking space, a license plate number, and the license plate number is obscured. Figure 7 As shown in (b), it is determined whether the first license plate number contains the second license plate number. If it does, the match is successful; if it does not, the match fails. For ease of understanding, for example, the first license plate number of the target parking space recorded on the platform is Sichuan A12345; if the second license plate number newly identified is 12345 or A12345, then the first license plate number contains the second license plate number, and the match is determined to be successful.

[0076] Figure 7 (c) provides fuzzy matching rules when there is a car and a license plate number in the parking space and the type of the license plate number is unknown, such as Figure 7 As shown in (c), if the fuzzy matching rules for the license plate number with “#” or the fuzzy matching rules for the license plate number being blocked are met, the match is successful; if the two fuzzy matching rules are not met, the match fails.

[0077] Step S602, when the fuzzy match between the first license plate number and the second license plate number is successful, the license plate number captured at the second time is modified to the first license plate number, and step S607 is executed.

[0078] Step S603, when the fuzzy matching between the first license plate number and the second license plate number fails, the license plate number captured at the second time is modified to the second license plate number, and step S604 is executed.

[0079] Step S604, the second cache count is incremented by one, and it is determined whether the second cache count is greater than or equal to the second preset count N. If so, step S605 is executed, and if not, step S608 is executed.

[0080] Step S605, obtaining the departure time of vehicle A according to the time when vehicle A was last captured.

[0081] Step S606, obtaining the entry time of vehicle B according to the time when vehicle B is first captured.

[0082] Step S607, clearing the second cache times and the first cache times, wherein the first cache times is the cache times obtained according to the event of a vehicle without a license plate or a license plate number that cannot be identified.

[0083] Step S608, storing the current snapshot record.

[0084] Figure 8 A flowchart of a method for generating a parking order in the event of a vehicle without a license plate or an unrecognizable license plate number is provided. Figure 8 As shown, including: Step S801, determine whether the number of user pushes of vehicle A reaches the preset number of pushes; determine whether the first cache number corresponding to the target parking space reaches the first preset number of pushes. If the number of user pushes of vehicle A does not reach the first preset number of pushes, or the first cache number of vehicle A does not reach the first preset number of pushes, then execute step S802; if the number of user pushes of vehicle A reaches the preset number of pushes, or the first cache number of vehicle A reaches the first preset number of pushes, then execute step S803.

[0085] Step S802, the number of user pushes of vehicle A is increased by one, the first cache number is increased by one, and the execution of the current parking order generation method is terminated until a new parking space event is received.

[0086] Step S803, when the number of user pushes of vehicle A reaches the preset number of pushes, the parking space event of vehicle A is pushed to the management terminal of the target parking space; when the first cache number of vehicle A reaches the first preset number of times, vehicle A is dispatched and the parking order generation method is terminated.

[0087] Fig. 9 A flowchart of a method for generating parking orders in the event of no cars is provided. Fig. 9 As shown, including: Step S901, the second cache count corresponding to the target parking space is increased by one.

[0088] Step S902, determine whether the second cache times is greater than or equal to the second preset times. If yes, execute step S903; if no, execute step S905.

[0089] Step S903, obtaining the departure time of vehicle A according to the time when vehicle A was last captured.

[0090] Step S904, clear the second cache times and the first cache times in the target parking space, and end the parking order generation.

[0091] Step S905, storing the current snapshot record.

[0092] according to Figure 6 , Figure 8 and Fig. 9 It can be seen that the prerequisite for delaying the vehicle exit in this embodiment is that the parking fee platform records that there is vehicle A parked in the target parking space; and the parking fee platform records that the license plate number of the vehicle parked in the target parking space has changed N times in a row. If the above two prerequisites are met, a parking order will be generated when vehicle A exits.

[0093] In this embodiment, by setting the global cache times on the parking fee collection platform, the cache times are used to obtain the number of times the license plate number changes in multiple snapshot results of the current parking space. When the current parking space is judged to have changed for multiple consecutive times, the vehicle is dispatched and a parking order is obtained based on the time when the vehicle was last captured. This reduces the impact of inaccurate capture image recognition results of the intelligent short-hair center on the accuracy of parking order generation, thereby greatly improving the accuracy of parking order generation.

[0094] When the target parking space receives a parking space event with a car and a license plate, the generation of the parking order does not completely rely on the image results recognized by the intelligent algorithm center through license plate fuzzy matching. The reported license plate is fuzzy matched according to different vehicle attributes to improve the recognition rate of the license plate.

[0095] When the target parking space receives an event that a car is present but has no license plate or cannot be identified, the message of the target parking space is pushed to the management terminal of the target parking space according to the number of user pushes, so that the toll collector or management user can manually process the parking order, thereby improving the accuracy of the parking order.

[0096] Based on the same inventive concept, an embodiment of the present application also provides a parking management device for implementing the above-mentioned parking management method.

[0097] In one embodiment, a parking management device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0098] The solution provided by the device to solve the problem is similar to the solution described in the above method, so the specific limitations in the parking management device embodiment can refer to the limitations on the parking management method above, which will not be repeated here.

[0099] Based on the same inventive concept, the embodiment of the present application also provides a parking management system for implementing the parking management method involved above. The parking management system includes a shooting device, a recognition device and a parking management device; the shooting device is used to shoot an image containing a target parking space; the recognition device is used to obtain a first license plate of a vehicle that has been parked in the target parking space in the past, and a second license plate of a vehicle that is currently parked in the target parking space based on the image. The shooting device can be any existing device such as a camera or a webcam. Optionally, the shooting device is a wire-free camera.

[0100] The parking management device is used to obtain the first identification information of a vehicle parked in a target parking space at a first time, and to obtain the second identification information of the vehicle parked in the target parking space at a second time; to match the first identification information and the second identification information; if the first identification information fails to match the second identification information, to increase the number of cache times corresponding to the target parking space; if the number of cache times is greater than or equal to a preset number, to generate a parking order for the vehicle corresponding to the first identification information.

[0101] Optionally, the parking management device matches the first identification information and the second identification information, including: when the first identification information includes the first license plate number, the second identification information includes the second license plate number, and the second license plate number meets a preset condition, a first matching is performed on the first license plate number and the second license plate number; wherein the preset condition includes one or more of the following: the second license plate number contains a preset identification, the second license plate number is blocked, and the second license plate type is unknown; when the first identification information includes the first license plate number, the second identification information includes the second license plate number, and the second license plate number does not meet the preset condition, a second matching is performed on the first license plate number and the second license plate number.

[0102] Optionally, a first match is performed on the first license plate number and the second license plate number, including: when the length of the first license plate number is consistent with the length of the second license plate number and the number of unmatched characters between the first license plate number and the second license plate number is less than or equal to a preset value, judging that the first license plate number and the second license plate number are successfully matched; when the length of the first license plate number and the second license plate number are inconsistent or the number of unmatched characters between the first license plate number and the second license plate number is greater than a preset value, judging that the first license plate number and the second license plate number are unmatched; and / or when the characters in the first license plate number contain the characters in the second license plate number, judging that the first license plate number and the second license plate number are successfully matched; when the characters in the first license plate number do not contain the characters in the second license plate number, judging that the first license plate number and the second license plate number are unmatched.

[0103] In one embodiment, matching the first identification information and the second identification information includes: when the first identification information includes a license plate number and the second identification information does not include the license plate number, determining that the first identification information and the second identification information do not match.

[0104] Optionally, in the event that the first identification information fails to match the second identification information, the number of cache times corresponding to the target parking space is increased; in the event that the number of cache times is greater than or equal to a preset number of times, a parking order for the vehicle corresponding to the first identification information is generated, including: acquiring a first image including the target parking space at a second time; in the event that the vehicle is identified based on the first image and the license plate number is not identified based on the first image, the first number of cache times corresponding to the target parking space is increased; in the event that the first number of cache times is greater than or equal to a first preset number of times, a parking order for the vehicle corresponding to the first identification information is generated.

[0105] Optionally, in the event that the first identification information fails to match the second identification information, the number of cache times corresponding to the target parking space is increased; in the event that the number of cache times is greater than or equal to a preset number of times, a parking order for the vehicle corresponding to the first identification information is generated, including: acquiring a first image including the target parking space at a second time; in the event that the vehicle is not identified based on the first image, the number of second cache times corresponding to the target parking space is increased; in the event that the second cache times is greater than or equal to a second preset number of times, a parking order for the vehicle corresponding to the first identification information is generated.

[0106] After matching the first identification information with the second identification information, the method further includes: if the first identification information matches the second identification information successfully, clearing the cached times of the target parking space.

[0107] In one embodiment, the parking management device generates a parking order for the vehicle corresponding to the first identification information when the number of cache times is greater than or equal to a preset number of times, including: acquiring a second image containing the first license plate number in the target parking space; obtaining the parking time of the vehicle corresponding to the first identification information based on the first shooting time and the last shooting time of the second image; and generating a parking order for the vehicle corresponding to the first identification information based on the parking time.

[0108] The implementation scheme for solving the problem provided by the parking management system is similar to the implementation scheme recorded in the above method, so the specific limitations of one or more parking management system embodiments provided above can refer to the limitations of the parking management method above, and will not be repeated here. Each device in the above parking management system can be implemented in whole or in part by software, hardware and a combination thereof. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0109] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Fig.10As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store vehicle data in the target parking space. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a parking management method is implemented.

[0110] Those skilled in the art will understand that Fig.10 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0111] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0112] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0113] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0114] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0115] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A parking management method, characterized in that: The method comprises: Acquire first identification information of a vehicle parked in a target parking space at a first time, and acquire second identification information of a vehicle parked in the target parking space at a second time; matching the first identification information and the second identification information; In the case where the first identification information fails to match the second identification information, increasing the number of cache times corresponding to the target parking space; When the cache times are greater than or equal to the preset times, a parking order for the vehicle corresponding to the first identification information is generated.

2. The method according to claim 1, characterized in that Matching the first identification information and the second identification information includes: When the first identification information includes a first license plate number, the second identification information includes a second license plate number, and the second license plate number meets a preset condition, a first match is performed on the first license plate number and the second license plate number; wherein the preset condition includes one or more of the following: the second license plate number includes a preset identification, the second license plate number is blocked, and the type of the second license plate is unknown; When the first identification information includes the first license plate number, the second identification information includes the second license plate number, and the second license plate number does not meet the preset condition, a second match is performed on the first license plate number and the second license plate number.

3. The method according to claim 2, characterized in that Performing a first match on the first license plate number and the second license plate number includes: If the length of the first license plate number is consistent with the length of the second license plate number and the number of unmatched characters between the first license plate number and the second license plate number is less than or equal to a preset value, it is determined that the first license plate number and the second license plate number are matched successfully; if the length of the first license plate number is inconsistent with the length of the second license plate number or the number of unmatched characters between the first license plate number and the second license plate number is greater than a preset value, it is determined that the first license plate number and the second license plate number fail to match; and / or, When the characters in the first license plate number include the characters in the second license plate number, it is determined that the first license plate number and the second license plate number match successfully; when the characters in the first license plate number do not include the characters in the second license plate number, it is determined that the first license plate number and the second license plate number match unsuccessfully.

4. The method according to claim 1, characterized in that: Matching the first identification information and the second identification information includes: When the first identification information includes a license plate number and the second identification information does not include a license plate number, it is determined that the first identification information and the second identification information do not match.

5. The method according to claim 4, characterized in that In the case where the first identification information fails to match the second identification information, increasing the number of cache times corresponding to the target parking space; When the cache count is greater than or equal to a preset count, generating a parking order for the vehicle corresponding to the first identification information includes: acquiring a first image including the target parking space at the second time; When a vehicle is recognized according to the first image, but a license plate number is not recognized according to the first image, increasing a first cache count corresponding to the target parking space; When the first cache number is greater than or equal to the first preset number, a parking order for the vehicle corresponding to the first identification information is generated.

6. The method according to claim 4, characterized in that In the case where the first identification information fails to match the second identification information, increasing the number of cache times corresponding to the target parking space; When the cache count is greater than or equal to a preset count, generating a parking order for the vehicle corresponding to the first identification information includes: acquiring a first image including the target parking space at the second time; In the case where no vehicle is recognized according to the first image, increasing a second cache count corresponding to the target parking space; When the second cache number is greater than or equal to the second preset number, a parking order for the vehicle corresponding to the first identification information is generated.

7. The method according to claim 1, characterized in that After matching the first identification information and the second identification information, the method further includes: When the first identification information matches the second identification information successfully, the cached times of the target parking space are cleared.

8. The method according to any one of claims 1 to 7, characterized in that: When the cache count is greater than or equal to a preset count, generating a parking order for the vehicle corresponding to the first identification information includes: Acquire a second image of the target parking space including the first license plate number; Obtaining the parking time of the vehicle corresponding to the first identification information according to the first shooting time and the last shooting time of the second image; A parking order for the vehicle corresponding to the first identification information is generated according to the parking time.

9. A parking management device, comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

10. A parking management system, characterized in that: The system comprises a photographing device, a recognition device and the parking management device according to claim 9; wherein, The photographing device is used to photograph an image including the target parking space; The recognition device is used to obtain first identification information of the vehicle in the target parking space based on an image captured at the target parking space at a first time, and to obtain second identification information of the vehicle in the target parking space based on an image captured at the target parking space at a second time.

Images