Parking behavior detection method, device, parking lot monitoring system and storage medium

Abstract

The present application relates to a parking behavior detection method, device, parking lot monitoring system and storage medium, wherein the parking behavior detection method includes: when detecting the target vehicle's exit behavior at the parking lot, obtaining the target vehicle's entrance front information, exit front information and exit rear information; respectively comparing the exit front information and exit rear information with the entrance front information to determine whether the vehicle information comparison fails; if so, obtaining the target vehicle's on-site monitoring information in the parking lot based on license plate recognition; performing a time comparison on the time information of the on-site monitoring information and the time information corresponding to the exit behavior to obtain the detection result of the target vehicle's abnormal exit behavior. It can realize the preparation detection of abnormal parking behavior based on image recognition and feature comparison, and then realize the accurate detection of vehicle parking fee evasion behavior.

Description

Technical Field

[0001] The present application relates to the field of video surveillance, and in particular to a parking behavior detection method, device, parking lot monitoring system and storage medium. Background Art

[0002] Unmanned parking lots can combine license plate recognition, parking space detection, smart barriers, mobile payment and other technologies to achieve automatic and efficient parking management. When a vehicle enters the parking lot, it is registered based on image recognition, and when the vehicle leaves the parking lot, it is charged and settled based on image recognition before being released.

[0003] At present, in the actual application scenarios of unmanned parking lots, there are still loopholes in which drivers use image recognition triggers and lift control to achieve abnormal parking behaviors of parking fee evasion. At present, it is impossible to accurately detect the parking fee evasion behavior of vehicles when they leave the parking lot.

[0004] With regard to the problem in related technologies that it is impossible to accurately detect the parking fee evasion behavior of vehicles, no effective solution has been proposed so far. Summary of the invention

[0005] In this embodiment, a parking behavior detection method, device, parking lot monitoring system and storage medium are provided to solve the problem that the related art cannot accurately detect the parking fee evasion behavior of vehicles.

[0006] In a first aspect, a parking behavior detection method is provided in this embodiment, which is used in a monitoring system of a parking lot, wherein the monitoring system is provided with image acquisition devices at the entrance, exit and inside the parking lot, and the method comprises:

[0007] When the target vehicle is detected to be driving out of the exit of the parking lot, the entrance vehicle front information, exit vehicle front information and exit vehicle rear information of the target vehicle are obtained; wherein the entrance vehicle front information, the exit vehicle front information and the exit vehicle rear information are all acquired based on the image acquisition device; the exit vehicle front information is the vehicle front information of the target vehicle before driving out of the exit; the exit vehicle rear information is the vehicle rear information of the target vehicle after driving out of the exit;

[0008] The exit vehicle front information, the exit vehicle rear information and the entrance vehicle front information are respectively compared to determine whether the vehicle information comparison fails; if so, the on-site monitoring information of the target vehicle in the parking lot is obtained based on license plate recognition;

[0009] The time information of the on-site monitoring information is compared with the time information corresponding to the exit behavior to obtain the detection result of the abnormal exit behavior of the target vehicle.

[0010] In some embodiments, the exit vehicle head information, the exit vehicle tail information and the entrance vehicle head information are respectively compared to determine whether the vehicle information comparison fails, including:

[0011] Compare the exit vehicle head information with the entry vehicle head information to obtain a first comparison result;

[0012] Comparing the exit vehicle tail information with the entrance vehicle head information to obtain a second comparison result;

[0013] If the first comparison result indicates that the exit vehicle front information is consistent with the entrance vehicle front information, and the second comparison result indicates that the exit vehicle rear information is inconsistent with the entrance vehicle front information, it is confirmed that the vehicle information comparison is successful.

[0014] In some embodiments, the method further comprises:

[0015] If the first comparison result indicates that the exit vehicle front information is inconsistent with the entry vehicle front information, or the exit vehicle rear information is empty, it is confirmed that the vehicle information comparison has failed.

[0016] In some of the embodiments, when confirming that the vehicle information comparison is successful, the method further includes:

[0017] Confirm that the exit exit behavior of the target vehicle is a normal exit behavior.

[0018] In some embodiments, obtaining on-site monitoring information of the target vehicle in the parking lot based on license plate recognition includes:

[0019] The target license plate information of the target vehicle is sent to an on-site image acquisition device deployed in the parking lot, so that the on-site image acquisition device extracts on-site monitoring information of the target vehicle in the parking lot based on license plate recognition.

[0020] In some embodiments, the time information of the on-site monitoring information is compared with the time information corresponding to the exit behavior to obtain the detection result of the abnormal exit behavior of the target vehicle, including:

[0021] The time information of the on-site monitoring information is compared with the time information corresponding to the exit behavior. If the time information of the on-site monitoring information is later than the time information corresponding to the exit behavior, it is confirmed that the target vehicle has abnormal exit behavior.

[0022] In some of the embodiments, after determining that the target vehicle has abnormal exit behavior, the method further includes:

[0023] When the exit behavior of the target vehicle is detected again, the parking fee information of the target vehicle is determined according to the current exit time and the entrance time of the target vehicle.

[0024] In the second aspect, a parking behavior detection device is provided in this embodiment, including: an acquisition module, an information comparison module and an abnormality detection module; wherein:

[0025] The acquisition module is used to acquire the entrance vehicle front information, exit vehicle front information and exit vehicle rear information of the target vehicle when detecting the exit behavior of the target vehicle at the exit of the parking lot; wherein the entrance vehicle front information, the exit vehicle front information and the exit vehicle rear information are all acquired based on the image acquisition device; the exit vehicle front information is the vehicle front information of the target vehicle before exiting the exit; the exit vehicle rear information is the vehicle rear information of the target vehicle after exiting the exit;

[0026] The information comparison module is used to compare the exit vehicle front information, the exit vehicle rear information and the entrance vehicle front information respectively, and determine whether the vehicle information comparison fails; if so, obtain the on-site monitoring information of the target vehicle in the parking lot based on license plate recognition;

[0027] The abnormality detection module is used to compare the time information of the on-site monitoring information with the time information corresponding to the exit behavior to obtain the detection result of the abnormal exit behavior of the target vehicle.

[0028] In a third aspect, a parking lot monitoring system is provided in this embodiment, comprising: an entrance image acquisition device, an exit image acquisition device, an in-park image acquisition device, and a server; wherein the server is connected to the entrance image acquisition device, the exit image acquisition device, and the in-park image acquisition device, respectively;

[0029] The entrance image acquisition device is used to collect vehicle head information of vehicles entering the entrance of the parking lot;

[0030] The exit image acquisition device is used to collect the front and rear information of vehicles leaving the exit of the parking lot;

[0031] The on-site image acquisition device is used to collect vehicle information in the parking lot;

[0032] The server is used to execute the parking behavior detection method described in the first aspect above.

[0033] In a fourth aspect, in this embodiment, a storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the parking behavior detection method described in the first aspect is implemented.

[0034] Compared with the related art, the present embodiment provides a parking behavior detection method, device, parking lot monitoring system and storage medium. The parking behavior detection method, when detecting the target vehicle exiting the parking lot, obtains the target vehicle's entrance front information, exit front information and exit rear information; wherein the entrance front information, exit front information and exit rear information are all acquired based on the image acquisition device; the exit front information is the target vehicle's front information before exiting; the exit rear information is the target vehicle's rear information after exiting; the exit front information and exit rear information are respectively compared with the entrance front information to determine whether the vehicle information comparison fails; if so, the target vehicle's on-site monitoring information in the parking lot is obtained based on license plate recognition; the time information of the on-site monitoring information is compared with the time information corresponding to the exit exit behavior to obtain the detection result of the target vehicle's abnormal exit behavior. It can realize the preparation detection of abnormal parking behavior based on image recognition and feature comparison, and then realize the accurate detection of vehicle parking fee evasion behavior.

[0035] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0037] Figure 1 is a hardware structure block diagram of a terminal of the parking behavior detection method of this embodiment;

[0038] Figure 2 is a flow chart of the parking behavior detection method of this embodiment;

[0039] Figure 3 is a flow chart of a parking behavior detection method in some embodiments;

[0040] Figure 4 is a structural block diagram of the parking behavior detection device of this embodiment;

[0041] Figure 5 It is a schematic diagram of the structure of the parking lot monitoring system of this embodiment. DETAILED DESCRIPTION

[0042] In order to more clearly understand the purpose, technical solutions and advantages of the present application, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments.

[0043] Unless otherwise defined, the technical terms or scientific terms involved in this application shall have the general meaning understood by people with general skills in the technical field to which this application belongs. The words "one", "a", "the", "these" and the like in this application do not indicate a quantitative limitation, and they may be singular or plural. The terms "include", "comprise", "have" and any variants thereof involved in this application are intended to cover non-exclusive inclusions; for example, a process, method and system, product or device comprising a series of steps or modules (units) is not limited to the listed steps or modules (units), but may include unlisted steps or modules (units), or may include other steps or modules (units) inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there may be three relationships, for example, "A and / or B" may mean: A exists alone, A and B exist at the same time, and B exists alone. Generally, the character " / " indicates that the objects associated with each other are in an "or" relationship. The terms "first", "second", "third", etc. in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0044] 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 is a hardware structure block diagram of the terminal of the parking behavior detection method of this embodiment. 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.

[0045] 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 behavior detection 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-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0046] The transmission device 106 is used to receive or send data via a network. The above network includes a wireless network provided by a 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.

[0047] In this embodiment, a parking behavior detection method is provided. Figure 2 is a flow chart of the parking behavior detection method of this embodiment. Figure 2 As shown, the process includes the following steps:

[0048] Step S210, when the target vehicle is detected exiting the parking lot, the entrance vehicle front information, exit vehicle front information and exit vehicle rear information of the target vehicle are obtained; wherein the entrance vehicle front information, exit vehicle front information and exit vehicle rear information are all acquired based on the image acquisition device; the exit vehicle front information is the vehicle front information of the target vehicle before exiting the exit; the exit vehicle rear information is the vehicle rear information of the target vehicle after exiting the exit.

[0049] Image acquisition devices with license plate recognition functions and connected to the parking fee collection system can be deployed at the entrance, exit and inside the parking lot. For example, an entrance image acquisition device for detecting the front information of a vehicle when it enters the parking lot can be deployed at the entrance of the parking lot, and an exit image acquisition device for detecting the front information of the vehicle before it exits the barrier and the rear information of the vehicle after it exits the barrier can be deployed at the exit of the parking lot. The specific deployment method, setting location and number of the image acquisition devices can be set by those skilled in the art according to the needs of the actual application scenario. In particular, one entrance image acquisition device can be deployed at the entrance, and two exit image acquisition devices can be deployed at the exit to realize the front information acquisition and the rear information acquisition at the exit respectively.

[0050] Specifically, the above-mentioned entrance vehicle front information can be the feature information obtained by capturing a vehicle image after the entrance image acquisition device recognizes the license plate of the target vehicle when the target vehicle enters the entrance of the parking lot, and extracting features of the vehicle in the captured image (for example, including vehicle outline features and vehicle front features). Specifically, the exit vehicle front information can be the feature information obtained by the exit image acquisition device recognizing the license plate and capturing the vehicle image when the target vehicle exits the parking lot before the exit parking bar is raised, and extracting features of the vehicle in the captured image (for example, including vehicle outline features and vehicle front features). Specifically, the exit vehicle rear information can be the feature information obtained by the exit image acquisition device recognizing the license plate and capturing the vehicle after the exit parking bar is raised, and extracting features of the vehicle in the captured image (for example, including vehicle outline features and vehicle rear features). The entrance vehicle front information can be saved and generated as a vehicle entrance record, the exit vehicle front information can be saved and generated as a pre-exit record, and the exit vehicle rear information can be saved and generated as a post-exit record.

[0051] The exit behavior of the target vehicle at the parking lot exit is detected. Specifically, the front or rear end of the target vehicle reaches the parking lot exit, triggering the image acquisition device at the exit to perform license plate recognition and capture, and then controlling the parking bar to lift. At this time, it can be determined that the target vehicle has exited the exit.

[0052] Step S220, respectively compare the exit vehicle front information, exit vehicle rear information and entrance vehicle front information to determine whether the vehicle information comparison fails; if so, obtain the on-site monitoring information of the target vehicle in the parking lot based on license plate recognition.

[0053] For unattended parking lots, when a vehicle enters the parking lot, it will directly reverse to the parking lot exit. After completing the license plate recognition and fee settlement (no fee will be deducted at this time), the exit will lift the barrier to let the vehicle pass. At this time, the vehicle does not leave the parking lot, but directly enters the parking space. When the vehicle finally leaves the parking lot, since the parking fee collection system does not have the corresponding entry record of the vehicle, it will be released by default. In this way, when the vehicle performs the above parking behavior in the parking lot, it will complete the parking fee evasion.

[0054] In this regard, in this step, in order to realize the recognition of the above-mentioned parking behavior, the above-mentioned exit vehicle front information and exit vehicle rear information are respectively compared with the entrance vehicle front information to determine the feature similarity, and whether the vehicle information comparison fails is determined based on the similarity result. Among them, the condition for judging the comparison failure is that, based on the feature comparison results of the above-mentioned exit vehicle front information, exit vehicle rear information and entrance vehicle front information, it is determined that the target vehicle is reversing to the exit, and the exit image acquisition device recognizes the target vehicle's rear information before the bar is lifted. In this case, it indicates that the target vehicle has potential abnormal parking behavior (there may be an intention to evade fees). It should also be noted that when performing the comparison, if the target vehicle's rear information after the bar is lifted is not identified, the above-mentioned exit vehicle rear information is empty, and the vehicle information comparison will also be considered to have failed.

[0055] After confirming that the target vehicle has potential abnormal parking behavior, a corresponding vehicle abnormality record can be generated for the target vehicle, and the above-mentioned entrance vehicle front information, exit vehicle front information and exit vehicle rear information are all saved in the vehicle abnormality record, and the entrance and exit vehicle video recordings of the corresponding time period are extracted according to the target vehicle entrance and exit record time and saved in the vehicle abnormality record. In addition, further verification can be performed based on the comparison of time information. Among them, the above-mentioned on-site monitoring information can specifically be the image information of the target vehicle in the parking lot collected by the image acquisition device with license plate recognition function deployed in the parking lot. When the vehicle information comparison fails, the license plate information of the target vehicle can be sent to all image acquisition devices in the parking lot to obtain the on-site monitoring information of the target vehicle based on the license plate information, and the on-site monitoring information page can be saved in the vehicle abnormality record.

[0056] Step S230, comparing the time information of the on-site monitoring information with the time information corresponding to the exit behavior to obtain the detection result of the abnormal exit behavior of the target vehicle.

[0057] The purpose of comparing the time information of the on-site monitoring information with the time information corresponding to the exit behavior is to determine whether the target vehicle does not leave the parking lot but enters the parking space in the parking lot after reaching the parking lot exit and triggering the toll collection and lifting the barrier. In this case, the time information corresponding to the on-site monitoring information of the target vehicle in the parking lot will be later than the time information corresponding to the exit behavior.

[0058] In this step, the time information corresponding to the on-site monitoring information is compared with the time information corresponding to the exit behavior to determine whether the time corresponding to the target vehicle's parking in the parking lot is later than the time when the target vehicle arrives at the parking lot exit. If so, it is confirmed that the target vehicle has abnormal parking behavior with the above-mentioned intention to evade fees. It can be understood that when there are multiple on-site monitoring information of the target vehicle, the time information corresponding to each on-site monitoring information can be compared with the time information corresponding to the exit behavior. If both are later than the time corresponding to the exit behavior, it is confirmed that there is abnormal parking behavior.

[0059] In particular, in some of the embodiments, when it is confirmed that the target vehicle has the above-mentioned abnormal parking behavior, parking charges can be calculated from the time when the target vehicle actually enters the parking lot, and when the target vehicle subsequently leaves the parking lot, parking charges are settled according to the actual parking time, and the corresponding vehicle abnormality record is displayed, and abnormal warning information is sent to the client of the parking lot manager for reminder.

[0060] In the above steps S210 to S230, when the target vehicle is detected to be driving out of the parking lot, the entrance vehicle head information, exit vehicle head information and exit vehicle tail information of the target vehicle are obtained; wherein the entrance vehicle head information, exit vehicle head information and exit vehicle tail information are all acquired based on the image acquisition device; the exit vehicle head information is the vehicle head information of the target vehicle before driving out of the exit; the exit vehicle tail information is the vehicle tail information of the target vehicle after driving out of the exit; the exit vehicle head information and the exit vehicle tail information are respectively compared with the entrance vehicle head information to determine whether the vehicle information comparison fails; if so, the on-site monitoring information of the target vehicle in the parking lot is obtained based on the license plate recognition; the time information of the on-site monitoring information is compared with the time information corresponding to the exit driving behavior to obtain the detection result of the abnormal driving out behavior of the target vehicle. It can realize the preparation detection of abnormal parking behavior based on image recognition and feature comparison, and then realize the accurate detection of vehicle parking evasion behavior.

[0061] In one embodiment, based on the above step S220, the exit vehicle head information, the exit vehicle tail information and the entrance vehicle head information are respectively compared to determine whether the vehicle information comparison fails, which may specifically include:

[0062] The exit vehicle front information is compared with the entrance vehicle front information to obtain a first comparison result; the exit vehicle rear information is compared with the entrance vehicle front information to obtain a second comparison result; if the first comparison result indicates that the exit vehicle front information is consistent with the entrance vehicle front information, and the second comparison result indicates that the exit vehicle rear information is inconsistent with the entrance vehicle front information, then it is confirmed that the vehicle information comparison is successful.

[0063] Specifically, the exit vehicle head information is compared with the entrance vehicle head information to determine whether the feature similarity between the exit vehicle head information and the entrance vehicle head information is greater than a preset similarity threshold. If so, it is confirmed that the exit vehicle head information is consistent with the entrance vehicle head information, indicating that the target vehicle arrives at the parking lot exit in a forward driving manner. In addition, it is necessary to further determine whether the exit vehicle tail information after the bar is lifted is inconsistent with the entrance vehicle head information to determine whether the vehicle is driving forward from the parking lot exit after the bar is lifted. The specific comparison method can be based on any image feature similarity comparison method in the current image processing technology, and this embodiment does not specifically limit this. The exit vehicle head information, entrance vehicle head information and exit vehicle tail information of the same vehicle can all be associated based on the identified license plate information.

[0064] The vehicle information comparison is successful only after confirming that the target vehicle's exit front information before the barrier is lifted is consistent with the entrance front information, and the exit rear information after the barrier is lifted is inconsistent with the entrance front information, indicating that the target vehicle is leaving the parking lot exit normally. Therefore, this embodiment can accurately identify the behavior of a vehicle leaving the parking lot exit normally based on two comparisons.

[0065] In one embodiment, the parking behavior detection method may further include:

[0066] If the first comparison result indicates that the exit vehicle front information is inconsistent with the entrance vehicle front information, or the exit vehicle rear information is empty, it is confirmed that the vehicle information comparison has failed.

[0067] When the exit vehicle front information is inconsistent with the entrance vehicle front information, it indicates that the target vehicle may not arrive at the exit parking bar with the front of the vehicle, but arrive at the exit parking bar with the side or rear of the vehicle. At this time, the target vehicle has potential abnormal parking behavior and needs further verification. Alternatively, the rear information of the vehicle leaving the exit after the bar is lifted is not extracted, which also indicates that the target vehicle did not leave the exit in a forward driving manner, and thus has potential abnormal parking behavior. Therefore, when it is determined based on the comparison results that there are two situations, it is confirmed that the vehicle information comparison has failed. This embodiment can determine the target vehicle's potential abnormal parking behavior based on the comparison results.

[0068] Additionally, in one embodiment, when confirming that the vehicle information comparison is successful, the parking behavior detection method may further include:

[0069] Confirm that the target vehicle's exit behavior is normal.

[0070] In one embodiment, based on the above step S220, obtaining the on-site monitoring information of the target vehicle in the parking lot based on license plate recognition may specifically include:

[0071] The target license plate information of the target vehicle is sent to the on-site image acquisition device deployed in the parking lot, so that the on-site image acquisition device can extract the on-site monitoring information of the target vehicle in the parking lot based on the license plate recognition.

[0072] When the above vehicle information comparison fails, the target license plate information of the target vehicle is sent to each on-site image acquisition device deployed in the parking lot for license plate recognition. When the on-site image acquisition device detects the target vehicle corresponding to the target license plate information, it captures the vehicle image and records the vehicle to generate on-site monitoring information, which is saved in the above vehicle abnormality record. In this way, the present embodiment can accurately track and identify the target vehicle in the parking lot, and determine the actual parking time of the target vehicle in the parking lot.

[0073] In one embodiment, based on the above step S230, the time information of the on-site monitoring information is compared with the time information corresponding to the exit behavior to obtain the detection result of the abnormal exit behavior of the target vehicle, which may include:

[0074] The time information of the on-site monitoring information is compared with the time information corresponding to the exit behavior. If the time information of the on-site monitoring information is later than the time information corresponding to the exit behavior, it is confirmed that the target vehicle has abnormal exit behavior.

[0075] If the on-site monitoring information of the target vehicle collected by the on-site image acquisition device is queried based on the vehicle abnormality record corresponding to the identified target license plate information, and the time corresponding to all on-site monitoring information of the target vehicle is later than the time corresponding to the exit behavior of the target vehicle, then it is judged that the target vehicle has abnormal parking behavior.

[0076] In addition, in one embodiment, after determining that the target vehicle has abnormal exit behavior, the parking behavior detection method may further include:

[0077] When the exit behavior of the target vehicle is detected again, the parking fee information of the target vehicle is determined according to the current exit time and the entrance time of the target vehicle.

[0078] When the exit behavior of the target vehicle is detected again, the actual parking time of the target vehicle is determined according to the time of the currently detected exit behavior and the entrance time of the target vehicle in the vehicle abnormality record, and then the parking fee is settled based on the actual parking time.

[0079] In particular, if the target vehicle completes the parking payment process, the corresponding vehicle abnormality record will be eliminated. If the parking payment process is not completed, the vehicle abnormality record can be sorted out and subsequent measures can be taken, and the target vehicle can be marked.

[0080] Figure 3 is a flow chart of a parking behavior detection method in some embodiments, such as Figure 3 As shown, the parking behavior detection method includes the following steps:

[0081] Step S301, when the target vehicle enters the parking lot, the entrance vehicle head information is collected and a vehicle entrance record is generated.

[0082] Step S302, when the target vehicle exits the parking lot, the front vehicle information of the exit is collected to generate a record before the vehicle exits, and the rear vehicle information of the exit is collected to generate a record after the vehicle exits.

[0083] Step S303, compare the vehicle profile and feature values ​​of the three records in steps S301 and S302 to determine whether the vehicle information is successfully compared; if so, execute step S304; otherwise, execute step S305. The specific process of determining whether the vehicle information is successfully compared can refer to the above embodiment, which will not be repeated here.

[0084] Step S304, executing the normal parking fee settlement process.

[0085] Step S305, generating a vehicle abnormality record, and sending the target license plate information of the target vehicle to the on-site image acquisition device for detection.

[0086] Step S306, obtaining the on-site monitoring information of the target vehicle monitored by the on-site image acquisition device based on the target license plate information.

[0087] Step S307: If the time of the on-site monitoring information is later than the corresponding time recorded before and after the exit, it is confirmed that the target vehicle has abnormal parking behavior.

[0088] Step S308: When the target vehicle drives out again, the parking fee is settled according to the abnormal record of the vehicle and an abnormal warning is issued.

[0089] Step S309, determine whether the target vehicle has completed payment normally; if so, execute step S310; otherwise, execute step S311.

[0090] Step S310, deleting the vehicle abnormality record of the target vehicle.

[0091] Step S311, upload the vehicle abnormality record to the associated processing platform, and mark the target vehicle. The processing platform can be a related platform for vehicle and traffic management.

[0092] The above steps S301 to S311 can provide early warning for vehicles that trigger the settlement bar lifting direction by reversing to the exit of the parking lot to achieve parking fee evasion, and use image acquisition equipment to collect evidence in the parking lot to complete the correct parking time charging process, so as to realize abnormal parking behavior detection and timely warning of fee evasion.

[0093] In this embodiment, a parking behavior detection device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. The terms "module", "unit", "subunit", etc. used below can be a combination of software and / or hardware that implements the predetermined functions. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0094] Figure 4 is a structural block diagram of the parking behavior detection device 40 of this embodiment. Figure 4 As shown, the parking behavior detection device 40 includes: an acquisition module 42, an information comparison module 44 and an abnormality detection module 46; wherein:

[0095] The acquisition module 42 is used to acquire the entrance vehicle front information, exit vehicle front information and exit vehicle rear information of the target vehicle when the exit behavior of the target vehicle at the parking lot is detected; wherein the entrance vehicle front information, exit vehicle front information and exit vehicle rear information are all acquired based on the image acquisition device; the exit vehicle front information is the vehicle front information of the target vehicle before exiting; the exit vehicle rear information is the vehicle rear information of the target vehicle after exiting; the information comparison module 44 is used to compare the exit vehicle front information, the exit vehicle rear information with the entrance vehicle front information respectively, and determine whether the vehicle information comparison fails; if so, the on-site monitoring information of the target vehicle in the parking lot is acquired based on the license plate recognition; the abnormality detection module 46 is used to compare the time information of the on-site monitoring information with the time information corresponding to the exit behavior, and obtain the detection result of the abnormal exit behavior of the target vehicle.

[0096] It should be noted that the above modules can be functional modules or program modules, and can be implemented by software or hardware. For modules implemented by hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0097] In this embodiment, a parking lot monitoring system is also provided. Figure 5 FIG. 5 is a schematic diagram of the structure of the parking lot monitoring system 50 of this embodiment. Figure 5As shown, the monitoring system 50 of the parking lot includes: an entrance image acquisition device 52, an exit image acquisition device 54, an in-field image acquisition device 56 and a server 58; wherein the server 58 is connected to the entrance image acquisition device 52, the exit image acquisition device 54 and the in-field image acquisition device 56 respectively; the entrance image acquisition device 52 is used to acquire the front information of vehicles entering the parking lot; the exit image acquisition device 54 is used to acquire the front information and the rear information of vehicles leaving the parking lot; the in-field image acquisition device 56 is used to acquire the vehicle information in the parking lot; the server 58 is used to execute the parking behavior detection method provided in any of the above embodiments.

[0098] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and will not be repeated in this embodiment.

[0099] In addition, in combination with the parking behavior detection method provided in the above embodiments, a storage medium may be provided in this embodiment to implement the parking behavior detection method. The storage medium stores a computer program; when the computer program is executed by a processor, any parking behavior detection method in the above embodiments is implemented.

[0100] It should be understood that the specific embodiments described here are only used to explain this application, rather than to limit it. According to the embodiments provided in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the protection scope of this application.

[0101] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0102] Obviously, the drawings are only some examples or embodiments of the present application. For ordinary technicians in the field, the present application can also be applied to other similar situations based on these drawings without creative work. In addition, it is understandable that although the work done in this development process may be complicated and lengthy, for ordinary technicians in the field, certain changes in design, manufacturing or production based on the technical content disclosed in this application are only conventional technical means and should not be regarded as insufficient content disclosed in this application.

[0103] The term "embodiment" in this application refers to a specific feature, structure or characteristic described in conjunction with the embodiment that can be included in at least one embodiment of the present application. The appearance of this phrase in various locations in the specification does not necessarily mean the same embodiment, nor does it mean that it is mutually exclusive with other embodiments and is independent or optional. It is clearly or implicitly understood by those of ordinary skill in the art that the embodiments described in this application can be combined with other embodiments without conflict.

[0104] The above-mentioned 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 patent protection. 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 scope of protection of the present application. Therefore, the scope of protection of the present application shall be subject to the attached claims.

Claims

1. A parking behavior detection method, characterized in that: A monitoring system for a parking lot, the monitoring system comprising an entrance image acquisition device arranged at the entrance of the parking lot, an exit image acquisition device arranged at the exit of the parking lot, and an in-parking image acquisition device arranged in the parking lot, the method comprising: When the target vehicle is detected to be driving out of the exit of the parking lot, the entrance vehicle front information, exit vehicle front information and exit vehicle rear information of the target vehicle are obtained; wherein: The entrance vehicle head information includes the vehicle outline features and vehicle head features obtained by the entrance image acquisition device after identifying the license plate of the target vehicle by capturing the vehicle image and extracting the features; The exit vehicle head information includes the vehicle outline features and vehicle head features obtained by the exit image acquisition device when the target vehicle exits the parking lot and before the parking bar is lifted, by identifying the license plate and performing vehicle capture and feature extraction; The exit vehicle rear information includes the vehicle outline features and vehicle rear features obtained by the exit image acquisition device after the target vehicle is lifted after the parking bar is raised and the license plate is recognized and the vehicle is captured and feature extracted; Compare the exit vehicle head information with the entry vehicle head information to obtain a first comparison result; Comparing the exit vehicle tail information with the entrance vehicle head information to obtain a second comparison result; If the first comparison result indicates that the exit vehicle head information is inconsistent with the entry vehicle head information, or the exit vehicle tail information is empty, it is confirmed that the vehicle information comparison has failed; In the case where the vehicle information comparison fails, obtaining on-site monitoring information of the target vehicle in the parking lot based on license plate recognition; the on-site monitoring information is the monitoring information of the target vehicle extracted by the on-site image acquisition device based on license plate recognition; The time information of the on-site monitoring information is compared with the time information corresponding to the exit behavior. If the time information of the on-site monitoring information is later than the time information corresponding to the exit behavior, it is confirmed that the target vehicle has abnormal exit behavior.

2. The parking behavior detection method according to claim 1, characterized in that: The method further comprises: If the first comparison result indicates that the exit vehicle front information is consistent with the entrance vehicle front information, and the second comparison result indicates that the exit vehicle rear information is inconsistent with the entrance vehicle front information, it is confirmed that the vehicle information comparison is successful.

3. The parking behavior detection method according to claim 2, characterized in that: When confirming that the vehicle information comparison is successful, the method further includes: Confirm that the exit exit behavior of the target vehicle is a normal exit behavior.

4. The parking behavior detection method according to claim 1, characterized in that: Acquiring on-site monitoring information of the target vehicle in the parking lot based on license plate recognition includes: The target license plate information of the target vehicle is sent to an on-site image acquisition device deployed in the parking lot, so that the on-site image acquisition device extracts on-site monitoring information of the target vehicle in the parking lot based on license plate recognition.

5. The parking behavior detection method according to any one of claims 1 to 4, characterized in that: After determining that the target vehicle has abnormal exit behavior, the method further includes: When the exit behavior of the target vehicle is detected again, the parking fee information of the target vehicle is determined according to the current exit time and the entrance time of the target vehicle.

6. A parking behavior detection device, characterized in that: A monitoring system for a parking lot, the monitoring system comprising an entrance image acquisition device arranged at the entrance of the parking lot, an exit image acquisition device arranged at the exit of the parking lot, and an in-field image acquisition device arranged in the parking lot, the device comprising: an acquisition module, an information comparison module, and an abnormality detection module; wherein: The acquisition module is used to acquire the entrance vehicle head information, exit vehicle head information and exit vehicle tail information of the target vehicle when detecting the target vehicle driving out of the exit of the parking lot; wherein: The entrance vehicle head information includes the vehicle outline features and vehicle head features obtained by the entrance image acquisition device after identifying the license plate of the target vehicle by capturing the vehicle image and extracting the features; The exit vehicle head information includes the vehicle outline features and vehicle head features obtained by the exit image acquisition device when the target vehicle exits the parking lot and before the parking bar is lifted, by identifying the license plate and performing vehicle capture and feature extraction; The exit vehicle rear information includes the vehicle outline features and vehicle rear features obtained by the exit image acquisition device after the target vehicle is lifted after the parking bar is raised and the license plate is recognized and the vehicle is captured and feature extracted; The information comparison module is used to compare the exit vehicle front information with the entrance vehicle front information to obtain a first comparison result; compare the exit vehicle rear information with the entrance vehicle front information to obtain a second comparison result; if the first comparison result indicates that the exit vehicle front information is inconsistent with the entrance vehicle front information, or the exit vehicle rear information is empty, it is confirmed that the vehicle information comparison has failed; in the case of the vehicle information comparison failure, the on-site monitoring information of the target vehicle in the parking lot is obtained based on the license plate recognition; the on-site monitoring information is the monitoring information of the target vehicle extracted by the on-site image acquisition device based on the license plate recognition; The abnormality detection module is used to compare the time information of the on-site monitoring information with the time information corresponding to the exit behavior. If the time information of the on-site monitoring information is later than the time information corresponding to the exit behavior, it is confirmed that the target vehicle has abnormal exit behavior.

7. A parking lot monitoring system, characterized in that: include: An entrance image acquisition device, an exit image acquisition device, an on-site image acquisition device, and a server; wherein the server is connected to the entrance image acquisition device, the exit image acquisition device, and the on-site image acquisition device, respectively; The entrance image acquisition device is used to collect vehicle head information of vehicles entering the entrance of the parking lot; The exit image acquisition device is used to collect the front and rear information of vehicles leaving the exit of the parking lot; The on-site image acquisition device is used to collect vehicle information in the parking lot; The server is used to execute the parking behavior detection method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the parking behavior detection method according to any one of claims 1 to 5 are implemented.

Images