Vehicle video analysis management system based on entrance and exit of parking lot

Abstract

The invention discloses a vehicle video analysis management system based on a parking lot entrance and exit, and relates to the technical field of parking lot management, and the system comprises the following modules: a vehicle recognition recording module which controls a camera in the parking lot entrance to take a picture of a vehicle to obtain an entry picture, obtains a vehicle license plate number through the entry picture, and sends the vehicle license plate number to a server; the vehicle following distance is obtained through the entering picture, and the vehicle is reminded through the vehicle following distance; according to the scheme, in the payment confirmation module, a payment kiosk is arranged at an entrance of a parking lot exit channel to charge vehicles which are driven away, vehicles which are subjected to vehicle-following fee evasion are captured through a driving-away picture at the payment kiosk, and an interception kiosk is arranged at an exit of the parking lot exit channel to intercept vehicles which are not subjected to vehicle-following fee evasion to take fees. The information of the vehicle with the fee repayment function is included in the vehicle database, so that the vehicle can focus on the fee payment condition after entering the parking lot, and the revenue of the parking lot is prevented from being influenced by vehicle-following fee evasion when the vehicle leaves the parking lot.

Description

Technical Field

[0001] The present invention relates to the technical field of parking lot management, and in particular to a vehicle video analysis and management system based on a parking lot entrance and exit. Background Art

[0002] With the increasing congestion of urban traffic, parking lots, as important facilities to solve parking problems, their management efficiency and service quality are of great significance to the normal operation of the city.

[0003] Traditional parking lot management methods mainly rely on manual management, which has many problems, such as low vehicle entry and exit efficiency, opaque charges, and low parking space utilization. Therefore, most parking lots currently use smart management systems to operate and manage parking lots.

[0004] In actual applications, parking lots that use smart management systems have found that when the traffic volume is large, there is a serious problem of vehicles following cars in and out of the parking lot. As a result, there are often problems such as inaccurate parking spaces and serious vehicle evasion, which results in the ineffective utilization of parking resources. In order to improve the accuracy of the number of parking spaces in the parking lot and to avoid the impact of vehicles following cars and evading fees on the parking lot's revenue, we propose a vehicle video analysis management system based on the entrances and exits of the parking lot. Summary of the invention

[0005] 1. Technical issues to be resolved In view of the deficiencies in the prior art, the present invention provides a vehicle video analysis and management system based on parking lot entrances and exits to solve the above-mentioned problems in the prior art.

[0006] (II) Technical solution To achieve the above objectives, the present invention is implemented through the following technical solutions: A vehicle video analysis and management system based on parking lot entrances and exits, comprising the following modules: The vehicle identification and recording module uses a camera at the entrance of the parking lot to take a photo of the vehicle to obtain an entry photo, obtains the vehicle license plate number through the entry photo, obtains the vehicle following distance through the entry photo, reminds the vehicle through the vehicle following distance, establishes a vehicle database, and enters the vehicle information into the vehicle database; Payment confirmation module: a payment booth is set up at the entrance of the parking lot exit passage, and a photo of the vehicle leaving is taken to obtain a departure photo. An interception booth is set up at the exit of the parking lot exit passage to obtain payment information, and the departure photo is compared with the entry photo. The interception booth is controlled by the payment information to intercept the vehicle that has not paid the fee and make up the fee, and the information of the vehicle that has paid the fee is included in the vehicle database; The parking space statistics module obtains the total number of parking spaces in the parking lot, the total number of entries and the total number of exits, and obtains the total number of remaining spaces through the total number of parking spaces, the total number of entries, the total number of exits and the total number of fees paid. Multiple monitoring probes are arranged in the parking lot to take pictures of all parking spaces to obtain reference photos, and the number of parking vacancies is obtained through the reference photos. The final remaining parking spaces are obtained through the total number of remaining spaces and the number of parking vacancies.

[0007] Preferably, in the vehicle identification and recording module, the vehicle following distance is obtained by entering the photo, and the vehicle is reminded by the vehicle following distance, specifically: Step 1: Obtain multiple entry photos of a single vehicle, identify and lock the front license plate of the vehicle through the entry photos, identify and lock the rear license plate of the vehicle in front of the vehicle through the entry photos, and measure the distance between the front license plate of the vehicle and the rear license plates of the vehicles in front of the vehicle in the multiple entry photos to obtain a reference distance; Step 2: Set a distance ratio preset threshold, obtain the following distance by multiplying the reference distance by the distance ratio preset threshold, set a safety distance preset threshold, and compare the following distance with the safety distance preset threshold; Step 3: If the following distance is less than the preset threshold of the safety distance, the speaker will remind the vehicle to keep a distance from the following vehicle, and the license plate number of the vehicle will be marked as a target of attention.

[0008] Preferably, in the payment confirmation module, the departure photo is compared with the entry photo, and the payment information is used to control the interception booth to intercept the unpaid vehicle and make the fee payment, specifically: Step 1: Obtain an entry photo of the toll-paying vehicle from the vehicle database according to the license plate number, measure the vehicle length in the entry photo of the toll-paying vehicle to obtain the entry length, set a preset threshold for the length ratio, and obtain the entry vehicle length of the toll-paying vehicle by multiplying the entry length of the toll-paying vehicle by the preset threshold for the length ratio, measure the vehicle length of the toll-paying vehicle through the exit photo to obtain the exit length, and obtain the exit length by multiplying the exit length by the preset threshold for the length ratio; Step 2: Compare the length of the entering vehicle with the length of the leaving vehicle. If the length of the entering vehicle is different from the length of the leaving vehicle, turn on the speaker to remind the vehicle to keep a distance from the following vehicle. Obtain the license plate number of the vehicle behind the paying vehicle through the photo of the paying vehicle leaving, and define the vehicle as a following target. When the following target leaves the payment booth, check in the payment system whether the vehicle has completed payment. If the following target has not paid, send the license plate number of the vehicle to the interception booth to remind the management staff to intercept and collect the fee, and mark the vehicle as a leaving target.

[0009] Preferably, the vehicle information for the supplementary payment is included in the vehicle database in the payment confirmation module, specifically: obtaining the license plate number of the vehicle entering the target of interest, obtaining the license plate number of the vehicle leaving the target of interest, comparing whether the license plate numbers entering the target of interest and leaving the target of interest are the same, if the license plate numbers are the same, then marking the license plate number as a toll evasion license plate and storing it in the vehicle database.

[0010] Preferably, the total number of entries and the total number of exits are obtained in the parking space statistics module, specifically: Step 1: Obtain all entry photos, identify the license plate numbers of all entry photos, delete duplicate license plate numbers based on the identification results, and count the remaining license plate numbers to obtain the total number of entries; Step 2: Obtain all departure photos, perform license plate number recognition on all departure photos, delete duplicate license plate numbers based on the recognition results, and count the remaining license plate numbers to obtain the total number of departures.

[0011] Preferably, in the parking space statistics module, the total number of remaining spaces is obtained by obtaining the total number of parking spaces, the total number of entries, the total number of departures, and the total number of fees paid, specifically: Step 1: Obtain the license plate numbers of all vehicles that have paid the fees, and obtain the license plate numbers of all vehicles that have left; Step 2: Delete the license plate numbers of all vehicles that have paid the supplementary fees and the license plate numbers of all vehicles that have left the vehicle to obtain the supplementary payment reference license plate numbers, and count all the supplementary payment reference license plate numbers to obtain the total number of supplementary payments; The total number of remaining vacancies is calculated as follows: Among them, Sy represents the total number of remaining vacancies, Tz represents the total number of parking spaces in the parking lot, Jr represents the total number of entries, Ls represents the total number of departures, and Bj represents the total number of fees paid.

[0012] Preferably, in the parking space statistics module, multiple monitoring probes are arranged in the parking lot to take pictures of all parking spaces to obtain reference photos, specifically: Step 1: Arrange multiple surveillance cameras in the parking lot so that the multiple surveillance cameras can capture all parking spaces; Step 2: Set the surveillance camera screenshot time interval, and capture video images from all surveillance camera videos at the same time according to the surveillance camera screenshot time interval; Step 3: Determine whether there are blurred images in all video images. If there are blurred images, lock the surveillance camera that took the image through the image and mark it as a re-shooting camera. Re-capture the video image of the re-shooting camera and determine whether the re-captured image is blurred. If the re-captured image is blurred, turn on the alarm to remind the management personnel to check the re-shooting camera.

[0013] Preferably, determining whether there is a blurred picture in all video pictures is specifically as follows: Step 1: Get all video images, grayscale process all video images to get grayscale images, use Sobel operator to get the horizontal gradient and vertical gradient of each video image, and get the gradient amplitude of each video image through the horizontal gradient and vertical gradient; Step 2: Set a preset gradient amplitude threshold, determine the relationship between the gradient amplitude of each video image and the preset gradient amplitude threshold, and if the gradient amplitude of the video image is less than the preset gradient amplitude threshold, define the video image as a blurred image; The calculation method of the gradient amplitude is as follows: Wherein, Tf represents the gradient amplitude, Sp represents the horizontal gradient, and Ct represents the vertical gradient.

[0014] Preferably, the number of parking spaces is obtained by referring to the photos in the parking space statistics module, specifically: Step 1: Obtain all reference images, identify parking space marking lines in all reference images, and if the parking space marking lines are complete, mark the parking space as an empty space; Step 2: Delete the empty parking spaces that are repeatedly identified among all the empty parking spaces, and count the empty parking spaces after repeated deletion to obtain the number of parking spaces.

[0015] Preferably, in the parking space statistics module, the final remaining parking spaces are obtained by the total number of remaining spaces and the number of parking spaces, specifically: Step 1: Get the total number of remaining vacancies, get the number of parking spaces, and get the remaining parking spaces by the total number of remaining vacancies and the number of parking spaces; Step 2: Determine whether the remaining parking spaces are an integer. If the remaining parking spaces are an integer, mark the remaining parking spaces as the final remaining parking spaces. If the remaining parking spaces are not an integer, take the integer part of the remaining parking spaces and mark it as the final remaining parking spaces. The calculation method of the remaining parking spaces is as follows: Among them, Zg represents the remaining parking spaces, Sy represents the total number of remaining spaces, and Tk represents the number of parking spaces. and are weights, , , .

[0016] (III) Beneficial effects The present invention provides a vehicle video analysis and management system based on parking lot entrances and exits, which has the following beneficial effects: (1) In the payment confirmation module, this solution charges vehicles leaving the parking lot by setting up a payment booth at the entrance of the parking lot exit passage, capturing vehicles that follow other vehicles and evade fees by taking photos of the vehicles leaving the parking lot at the payment booth, setting up an interception booth at the exit of the parking lot exit passage to intercept and collect fees from vehicles that follow other vehicles and fail to pay fees, and adding the information of vehicles that have paid fees to the vehicle database, so that it is easier to pay attention to the payment status of the vehicle after it enters the parking lot, which is beneficial to avoid vehicles that follow other vehicles and evade fees when leaving the parking lot, affecting the parking lot's revenue; (2) In the parking space statistics module, this solution obtains the total number of remaining spaces through the total number of parking spaces, the total number of entries, the total number of departures, and the total number of fees paid. The remaining parking spaces in the parking lot are counted based on the photos of vehicles leaving the parking lot and paying fees and the photos of vehicles entering the parking lot. The number of parking spaces is obtained by taking reference photos taken by multiple surveillance cameras arranged in the parking lot. Finally, the final remaining parking spaces are obtained by the total number of remaining spaces and the number of parking spaces. The remaining parking spaces are counted based on the surveillance cameras managed in the parking lot. Finally, the two statistical results are combined and summarized to obtain the final remaining parking spaces. This is beneficial to improving the accuracy of the statistical results of the remaining parking spaces, thereby helping to avoid the situation where vehicles evade fees and cause incorrect statistical results, thereby facilitating the full utilization of parking space resources in the parking lot. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a structural schematic diagram of a vehicle video analysis and management system based on a parking lot entrance and exit of the present invention; Figure 2 The present invention is a flowchart of a vehicle video analysis and management system based on a parking lot entrance and exit. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] See also Figure 1-Figure 2 The present invention provides a vehicle video analysis and management system based on a parking lot entrance and exit, comprising the following modules: The vehicle identification and recording module uses a camera at the entrance of the parking lot to take a photo of the vehicle to obtain an entry photo, obtains the vehicle license plate number through the entry photo, obtains the vehicle following distance through the entry photo, reminds the vehicle through the vehicle following distance, establishes a vehicle database, and enters the vehicle information into the vehicle database; Payment confirmation module: a payment booth is set up at the entrance of the parking lot exit passage, and a photo of the vehicle leaving is taken to obtain a departure photo. An interception booth is set up at the exit of the parking lot exit passage to obtain payment information, and the departure photo is compared with the entry photo. The interception booth is controlled by the payment information to intercept the vehicle that has not paid the fee and make up the fee, and the information of the vehicle that has paid the fee is included in the vehicle database; The parking space statistics module obtains the total number of parking spaces in the parking lot, the total number of entries and the total number of exits, and obtains the total number of remaining spaces through the total number of parking spaces, the total number of entries, the total number of exits and the total number of fees paid. Multiple monitoring probes are arranged in the parking lot to take pictures of all parking spaces to obtain reference photos, and the number of parking vacancies is obtained through the reference photos. The final remaining parking spaces are obtained through the total number of remaining spaces and the number of parking vacancies.

[0020] In this embodiment, in the vehicle identification module, the solution uses a camera at the entrance of the parking lot to take a photo of the vehicle to obtain an entry photo, and the license plate number of the vehicle entering the parking lot is captured through the entry photo, so as to record the vehicle, obtain the following distance of the vehicle through the entry photo, and remind the vehicle according to the following distance, and register the vehicle information entering the parking lot by establishing a vehicle database, so as to facilitate the subsequent billing management of the vehicle and parking space statistics; In the payment confirmation module, this solution charges the vehicles leaving by setting up a payment booth at the entrance of the parking lot exit passage, captures the vehicles that follow the vehicle and evades the fee by taking the departure photo at the payment booth, sets up an interception booth at the exit of the parking lot exit passage to intercept the vehicles that follow the vehicle and fail to pay the fee, and includes the information of the vehicle that has paid the fee in the vehicle database, so that it is convenient for the vehicle to pay attention to the payment status after entering the parking lot in the future, which is beneficial to avoid the impact of the parking lot's revenue on the vehicles that follow the vehicle and evade the fee when leaving the parking lot; In the parking space statistics module, this solution obtains the total number of remaining spaces through the total number of parking spaces, the total number of entries, the total number of departures and the total number of fees paid, and then counts the remaining parking spaces in the parking lot based on the photos of vehicles leaving the parking lot and paying the fees and the photos of vehicles entering the parking lot, and obtains the number of parking vacancies through reference photos taken by multiple monitoring probes arranged in the parking lot, and finally obtains the final remaining parking spaces through the total number of remaining spaces and the number of parking vacancies, and then counts the remaining parking spaces based on the monitoring probes managed in the parking lot, and finally combines and summarizes the two statistical results to obtain the final remaining parking spaces, which is beneficial to improve the accuracy of the statistical results of the remaining parking spaces, thereby helping to avoid the situation where the statistical results are incorrect due to vehicle evasion, and thus facilitates the full utilization of parking lot parking space resources.

[0021] In the vehicle identification record module, the vehicle following distance is obtained by entering the photo, and the vehicle is reminded based on the vehicle following distance. Specifically: Step 1: Obtain multiple entry photos of a single vehicle, identify and lock the front license plate of the vehicle through the entry photos, identify and lock the rear license plate of the vehicle in front of the vehicle through the entry photos, and measure the distance between the front license plate of the vehicle and the rear license plates of the vehicles in front of the vehicle in the multiple entry photos to obtain a reference distance; Step 2: Set a distance ratio preset threshold, obtain the following distance by multiplying the reference distance by the distance ratio preset threshold, set a safety distance preset threshold, and compare the following distance with the safety distance preset threshold; Step 3: If the following distance is less than the preset threshold of the safety distance, the speaker will remind the vehicle to keep a distance from the following vehicle, and the license plate number of the vehicle will be marked as a target of attention.

[0022] In this embodiment, by locking and measuring the distance between the front license plate of the vehicle in the photo and the rear license plate of the preceding vehicle, the following vehicle situation of the vehicle can be grasped, and the following vehicle can be reminded and marked, which is helpful to prevent the vehicle from following the vehicle too closely when entering the parking lot, resulting in the license plate number not being entered into the vehicle database, and thus helping to prevent the vehicle from being unable to pay normally and evading the fee later; It is worth mentioning that the value of the preset threshold in this solution can be obtained by weight analysis method, which will not be elaborated here.

[0023] In the payment confirmation module, the exit photo is compared with the entry photo, and the payment information is used to control the interception booth to intercept the unpaid vehicle and make up the fee. Specifically: Step 1: Obtain an entry photo of the toll-paying vehicle from the vehicle database according to the license plate number, measure the vehicle length in the entry photo of the toll-paying vehicle to obtain the entry length, set a preset threshold for the length ratio, and obtain the entry vehicle length of the toll-paying vehicle by multiplying the entry length of the toll-paying vehicle by the preset threshold for the length ratio, measure the vehicle length of the toll-paying vehicle through the exit photo to obtain the exit length, and obtain the exit length by multiplying the exit length by the preset threshold for the length ratio; Step 2: Compare the length of the entering vehicle with the length of the leaving vehicle. If the length of the entering vehicle is different from the length of the leaving vehicle, turn on the speaker to remind the vehicle to keep a distance from the following vehicle. Obtain the license plate number of the vehicle behind the paying vehicle through the photo of the paying vehicle leaving, and define the vehicle as a following target. When the following target leaves the payment booth, check in the payment system whether the vehicle has completed payment. If the following target has not paid, send the license plate number of the vehicle to the interception booth to remind the management staff to intercept and collect the fee, and mark the vehicle as a leaving target.

[0024] In this embodiment, by comparing the lengths of the paying vehicles, it is determined whether there is a vehicle following the paying vehicle intentionally to block the license plate. The following vehicle is marked based on the comparison result and the interception booth manager is notified to collect the fees from the following vehicle that has not paid the fee. This helps to avoid the impact on the parking lot's revenue by following the vehicle to evade fees when the vehicle leaves the parking lot.

[0025] In the payment confirmation module, the vehicle information of the fee-evading vehicle is included in the vehicle database, specifically: obtaining the license plate number of the vehicle entering the target of interest, obtaining the license plate number of the vehicle leaving the target of interest, and comparing whether the license plate numbers entering the target of interest and leaving the target of interest are the same. If the license plate numbers are the same, the license plate number is marked as a fee-evading license plate and stored in the vehicle database.

[0026] In this embodiment, the license plate numbers of the vehicles entering the target of interest and leaving the target of interest are compared to see if they are the same. If the license plate numbers are the same, the license plate number is marked as a toll evasion license plate and stored in the vehicle database, so that it is convenient for the vehicle to pay attention to the payment status after entering the parking lot in the future, which is further beneficial to avoid vehicles evading fees when leaving the parking lot, affecting the parking lot's revenue.

[0027] Get the total number of entries and exits in the parking space statistics module, specifically: Step 1: Obtain all entry photos, identify the license plate numbers of all entry photos, delete duplicate license plate numbers based on the identification results, and count the remaining license plate numbers to obtain the total number of entries; Step 2: Obtain all departure photos, perform license plate number recognition on all departure photos, delete duplicate license plate numbers based on the recognition results, and count the remaining license plate numbers to obtain the total number of departures.

[0028] In this embodiment, the total number of entries is obtained through entry photos, and the total number of departures is obtained through departure photos, and duplicate vehicles in the photos are deleted, so as to facilitate subsequent accurate grasp of the remaining parking spaces in the parking lot, and further facilitate full utilization of parking space resources in the parking lot.

[0029] In the parking space statistics module, the total number of remaining spaces is obtained through the total number of parking spaces, the total number of entries, the total number of departures, and the total number of fees paid. Specifically: Step 1: Obtain the license plate numbers of all vehicles that have paid the fees, and obtain the license plate numbers of all vehicles that have left; Step 2: Delete the license plate numbers of all vehicles that have paid the supplementary fees and the license plate numbers of all vehicles that have left the vehicle to obtain the supplementary payment reference license plate numbers, and count all the supplementary payment reference license plate numbers to obtain the total number of supplementary payments; The total number of remaining vacancies is calculated as follows: Among them, Sy represents the total number of remaining vacancies, Tz represents the total number of parking spaces in the parking lot, Jr represents the total number of entries, Ls represents the total number of departures, and Bj represents the total number of fees paid.

[0030] In this embodiment, the reference license plate number for supplementary payment is obtained by deleting the license plate number of the vehicles that have paid the full fee that is the same as the total number of vehicles that have left, so as to facilitate the subsequent accurate grasp of the remaining parking spaces in the parking lot, and further facilitate the full utilization of the parking lot resources.

[0031] In the parking space statistics module, multiple monitoring probes are arranged in the parking lot to take pictures of all parking spaces to obtain reference photos, specifically: Step 1: Arrange multiple surveillance cameras in the parking lot so that the multiple surveillance cameras can capture all parking spaces; Step 2: Set the surveillance camera screenshot time interval, and capture video images from all surveillance camera videos at the same time according to the surveillance camera screenshot time interval; Step 3: Determine whether there are blurred images in all video images. If there are blurred images, lock the surveillance camera that took the image through the image and mark it as a re-shooting camera. Re-capture the video image of the re-shooting camera and determine whether the re-captured image is blurred. If the re-captured image is blurred, turn on the alarm to remind the management personnel to check the re-shooting camera.

[0032] In this embodiment, images are captured by monitoring probes, making it easier to subsequently identify the remaining empty parking spaces in the parking lot based on video images. Blurred images are reshot to more accurately calculate the remaining empty parking spaces in the parking lot, thereby further facilitating full utilization of parking lot resources.

[0033] Determine whether there are blurred images in all video images, specifically: Step 1: Get all video images, grayscale process all video images to get grayscale images, use Sobel operator to get the horizontal gradient and vertical gradient of each video image, and get the gradient amplitude of each video image through the horizontal gradient and vertical gradient; Step 2: Set a preset gradient amplitude threshold, determine the relationship between the gradient amplitude of each video image and the preset gradient amplitude threshold, and if the gradient amplitude of the video image is less than the preset gradient amplitude threshold, define the video image as a blurred image; The calculation method of the gradient amplitude is as follows: Wherein, Tf represents the gradient amplitude, Sp represents the horizontal gradient, and Ct represents the vertical gradient.

[0034] In this embodiment, the image is grayed out, and then the horizontal gradient and vertical gradient of each video image are obtained according to the Sobel operator to calculate the gradient amplitude, and finally the image gradient amplitude is compared according to the preset threshold of the gradient amplitude, so as to determine whether the image is a blurred image; It is worth mentioning that calculating the horizontal gradient and vertical gradient of a grayscale image by using the Sobel operator is an existing technology, and the specific calculation method will not be described in detail here.

[0035] In the parking space statistics module, the number of parking spaces is obtained by referring to the photos, specifically: Step 1: Obtain all reference images, identify parking space marking lines in all reference images, and if the parking space marking lines are complete, mark the parking space as an empty space; Step 2: Delete the empty parking spaces that are repeatedly identified among all the empty parking spaces, and count the empty parking spaces after repeated deletion to obtain the number of parking spaces.

[0036] In this embodiment, since the parking space marking line will be blocked by the vehicle when there is a car in the parking space, the complete parking space marking line cannot be photographed. Therefore, by identifying whether the parking space marking line in the reference image is complete, it is possible to determine whether there is a car in the parking space, thereby facilitating the calculation of the remaining empty parking spaces in the parking lot, and further facilitating the full utilization of the parking space resources in the parking lot.

[0037] In the parking space statistics module, the final remaining parking spaces are obtained by the total number of remaining spaces and the number of parking spaces, specifically: Step 1: Get the total number of remaining vacancies, get the number of parking spaces, and get the remaining parking spaces by the total number of remaining vacancies and the number of parking spaces; Step 2: Determine whether the remaining parking spaces are an integer. If the remaining parking spaces are an integer, mark the remaining parking spaces as the final remaining parking spaces. If the remaining parking spaces are not an integer, take the integer part of the remaining parking spaces and mark it as the final remaining parking spaces. The calculation method of the remaining parking spaces is as follows: Among them, Zg represents the remaining parking spaces, Sy represents the total number of remaining spaces, and Tk represents the number of parking spaces. and are weights, , , .

[0038] In this embodiment, the final remaining parking spaces are obtained by the total number of remaining vacancies and the number of parking spaces, and the remaining parking spaces are counted according to the monitoring probes managed in the parking lot. Finally, the two statistical results are combined and summarized to obtain the final remaining parking spaces, which is beneficial to improving the accuracy of the statistical results of the remaining parking spaces, thereby helping to avoid the situation where the statistical results are incorrect due to vehicle evasion, and thus facilitating full utilization of parking space resources in the parking lot; It is worth mentioning that the weight values ​​in this scheme can be obtained through the hierarchical analysis method, which will not be elaborated here.

[0039] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. A person of ordinary skill in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution.

[0040] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0041] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A vehicle video analysis and management system based on parking lot entrances and exits, characterized in that: Includes the following modules: The vehicle identification and recording module uses a camera at the entrance of the parking lot to take a photo of the vehicle to obtain an entry photo, obtains the vehicle license plate number through the entry photo, obtains the vehicle following distance through the entry photo, reminds the vehicle through the vehicle following distance, establishes a vehicle database, and enters the vehicle information into the vehicle database; Payment confirmation module: a payment booth is set up at the entrance of the parking lot exit passage, and a photo of the vehicle leaving is taken to obtain a departure photo. An interception booth is set up at the exit of the parking lot exit passage to obtain payment information, and the departure photo is compared with the entry photo. The interception booth is controlled by the payment information to intercept the vehicle that has not paid the fee and make up the fee, and the information of the vehicle that has paid the fee is included in the vehicle database; The parking space statistics module obtains the total number of parking spaces in the parking lot, the total number of entries and the total number of exits, and obtains the total number of remaining spaces through the total number of parking spaces, the total number of entries, the total number of exits and the total number of fees paid. Multiple monitoring probes are arranged in the parking lot to take pictures of all parking spaces to obtain reference photos, and the number of parking vacancies is obtained through the reference photos. The final remaining parking spaces are obtained through the total number of remaining spaces and the number of parking vacancies.

2. A vehicle video analysis and management system based on a parking lot entrance and exit according to claim 1, characterized in that: In the vehicle identification record module, the vehicle following distance is obtained by entering the photo, and the vehicle is reminded based on the vehicle following distance. Specifically: Step 1: Obtain multiple entry photos of a single vehicle, identify and lock the front license plate of the vehicle through the entry photos, identify and lock the rear license plate of the vehicle in front of the vehicle through the entry photos, and measure the distance between the front license plate of the vehicle and the rear license plates of the vehicles in front of the vehicle in the multiple entry photos to obtain a reference distance; Step 2: Set a distance ratio preset threshold, obtain the following distance by multiplying the reference distance by the distance ratio preset threshold, set a safety distance preset threshold, and compare the following distance with the safety distance preset threshold; Step 3: If the following distance is less than the preset threshold of the safety distance, the speaker will remind the vehicle to keep a distance from the following vehicle, and the license plate number of the vehicle will be marked as a target of attention.

3. A vehicle video analysis and management system based on parking lot entrance and exit according to claim 2, characterized in that: In the payment confirmation module, the exit photo is compared with the entry photo, and the payment information is used to control the interception booth to intercept the unpaid vehicle and make up the fee. Specifically: Step 1: Obtain an entry photo of the toll-paying vehicle from the vehicle database according to the license plate number, measure the vehicle length in the entry photo of the toll-paying vehicle to obtain the entry length, set a preset threshold for the length ratio, and obtain the entry vehicle length of the toll-paying vehicle by multiplying the entry length of the toll-paying vehicle by the preset threshold for the length ratio, measure the vehicle length of the toll-paying vehicle through the exit photo to obtain the exit length, and obtain the exit length by multiplying the exit length by the preset threshold for the length ratio; Step 2: Compare the length of the entering vehicle with the length of the leaving vehicle. If the length of the entering vehicle is different from the length of the leaving vehicle, turn on the speaker to remind the vehicle to keep a distance from the following vehicle. Obtain the license plate number of the vehicle behind the paying vehicle through the photo of the paying vehicle leaving, and define the vehicle as a following target. When the following target leaves the payment booth, check in the payment system whether the vehicle has completed payment. If the following target has not paid, send the license plate number of the vehicle to the interception booth to remind the management staff to intercept and collect the fee, and mark the vehicle as a leaving target.

4. The vehicle video analysis and management system based on the parking lot entrance and exit according to claim 3 is characterized by: In the payment confirmation module, the vehicle information of the fee-evading vehicle is included in the vehicle database, specifically: obtaining the license plate number of the vehicle entering the target of interest, obtaining the license plate number of the vehicle leaving the target of interest, and comparing whether the license plate numbers entering the target of interest and leaving the target of interest are the same. If the license plate numbers are the same, the license plate number is marked as a fee-evading license plate and stored in the vehicle database.

5. The vehicle video analysis and management system based on the parking lot entrance and exit according to claim 1 is characterized by: Get the total number of entries and exits in the parking space statistics module, specifically: Step 1: Obtain all entry photos, identify the license plate numbers of all entry photos, delete duplicate license plate numbers based on the identification results, and count the remaining license plate numbers to obtain the total number of entries; Step 2: Obtain all departure photos, perform license plate number recognition on all departure photos, delete duplicate license plate numbers based on the recognition results, and count the remaining license plate numbers to obtain the total number of departures.

6. A vehicle video analysis and management system based on parking lot entrances and exits according to claim 5, characterized in that: In the parking space statistics module, the total number of remaining spaces is obtained through the total number of parking spaces, the total number of entries, the total number of departures, and the total number of fees paid. Specifically: Step 1: Obtain the license plate numbers of all vehicles that have paid the fees, and obtain the license plate numbers of all vehicles that have left; Step 2: Delete the license plate numbers of all vehicles that have paid the supplementary fees and the license plate numbers of all vehicles that have left the vehicle to obtain the supplementary payment reference license plate numbers, and count all the supplementary payment reference license plate numbers to obtain the total number of supplementary payments; The total number of remaining vacancies is calculated as follows: Among them, Sy represents the total number of remaining vacancies, Tz represents the total number of parking spaces in the parking lot, Jr represents the total number of entries, Ls represents the total number of departures, and Bj represents the total number of fees paid.

7. The vehicle video analysis and management system based on parking lot entrance and exit according to claim 1 is characterized by: In the parking space statistics module, multiple monitoring probes are arranged in the parking lot to take pictures of all parking spaces to obtain reference photos, specifically: Step 1: Arrange multiple surveillance cameras in the parking lot so that the multiple surveillance cameras can capture all parking spaces; Step 2: Set the surveillance camera screenshot time interval, and capture video images from all surveillance camera videos at the same time according to the surveillance camera screenshot time interval; Step 3: Determine whether there are blurred images in all video images. If there are blurred images, lock the surveillance camera that took the image through the image and mark it as a re-shooting camera. Re-capture the video image of the re-shooting camera and determine whether the re-captured image is blurred. If the re-captured image is blurred, turn on the alarm to remind the management personnel to check the re-shooting camera.

8. The vehicle video analysis and management system based on the parking lot entrance and exit according to claim 7 is characterized by: Determine whether there are blurred images in all video images, specifically: Step 1: Get all video images, grayscale process all video images to get grayscale images, use Sobel operator to get the horizontal gradient and vertical gradient of each video image, and get the gradient amplitude of each video image through the horizontal gradient and vertical gradient; Step 2: Set a preset gradient amplitude threshold, determine the relationship between the gradient amplitude of each video image and the preset gradient amplitude threshold, and if the gradient amplitude of the video image is less than the preset gradient amplitude threshold, define the video image as a blurred image; The calculation method of the gradient amplitude is as follows: Wherein, Tf represents the gradient amplitude, Sp represents the horizontal gradient, and Ct represents the vertical gradient.

9. The vehicle video analysis and management system based on parking lot entrance and exit according to claim 1, characterized in that: In the parking space statistics module, the number of parking spaces is obtained by referring to the photos, specifically: Step 1: Obtain all reference images, identify parking space marking lines in all reference images, and if the parking space marking lines are complete, mark the parking space as an empty space; Step 2: Delete the empty parking spaces that are repeatedly identified among all the empty parking spaces, and count the empty parking spaces after repeated deletion to obtain the number of parking spaces.

10. The vehicle video analysis and management system based on parking lot entrance and exit according to claim 1, characterized in that: In the parking space statistics module, the final remaining parking spaces are obtained by the total number of remaining spaces and the number of parking spaces, specifically: Step 1: Get the total number of remaining vacancies, get the number of parking spaces, and get the remaining parking spaces by the total number of remaining vacancies and the number of parking spaces; Step 2: Determine whether the remaining parking spaces are an integer. If the remaining parking spaces are an integer, mark the remaining parking spaces as the final remaining parking spaces. If the remaining parking spaces are not an integer, take the integer part of the remaining parking spaces and mark it as the final remaining parking spaces. The calculation method of the remaining parking spaces is as follows: Among them, Zg represents the remaining parking spaces, Sy represents the total number of remaining spaces, and Tk represents the number of parking spaces. and are weights, , , .

Images