License plate-free vehicle parking lot identification method, system, device and readable storage medium

Abstract

The present disclosure provides a license plate-free vehicle parking lot identification method, system, device and readable storage medium, relating to the technical field of license plate recognition, which comprises: obtaining a first license plate recognition result; performing multi-angle image acquisition on the first vehicle to obtain first multi-angle image data; performing vehicle feature recognition on the first vehicle to generate a first vehicle label; obtaining a second license plate recognition result; when the second license plate recognition result is a recognition failure, obtaining second multi-angle image data and generating a second vehicle label; comparing and matching the second vehicle label and the first vehicle label, calculating the parking duration, and performing parking fee management according to the calculation result. Through the present disclosure, the technical problem of low parking lot entry and exit control efficiency caused by low license plate-free vehicle recognition accuracy in the prior art can be solved, the goal of improving license plate-free vehicle recognition accuracy is achieved, and the technical effect of improving parking lot entry and exit control efficiency is achieved.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of license plate recognition, in particular to a license plate-free vehicle parking lot recognition method, system, device and readable storage medium. BACKGROUND

[0002] A license plate-free vehicle refers to a motor vehicle without a license plate or with a license plate that is not hung. The license plate-free vehicle cannot be identified by the existing technology temporarily, and thus situations such as no fine for illegal parking of the license plate-free vehicle and no charge for parking of the license plate-free vehicle occur. There is a need for a method for detecting the license plate-free vehicle by using image analysis and fusing the result of the license plate, so as to correctly output the license plate-free vehicle, and to provide help for the automation of the parking lot entrance and exit charge.

[0003] In summary, in the prior art, there is a technical problem that the low recognition accuracy of the license plate-free vehicle leads to low efficiency of the parking lot entrance and exit control. SUMMARY

[0004] The present disclosure provides a license plate-free vehicle parking lot recognition method, system, device and readable storage medium, to solve the technical problem that the low recognition accuracy of the license plate-free vehicle leads to low efficiency of the parking lot entrance and exit control in the prior art.

[0005] According to a first aspect of the present disclosure, a license plate-free vehicle parking lot identification method based on image analysis is provided, comprising: performing license plate recognition on a first vehicle entering a first parking lot by a license plate recognition system at an entrance of the first parking lot, to obtain a first license plate recognition result; when the first license plate recognition result is a recognition failure, starting an intelligent camera at the entrance of the first parking lot, and performing multi-angle image acquisition on the first vehicle by the intelligent camera to obtain first multi-angle image data; performing vehicle feature recognition on the first vehicle according to the first multi-angle image data, generating a first vehicle label according to the vehicle feature recognition result, the first vehicle label having a first generation time identifier, and controlling an entrance barrier at the entrance to be opened according to the first vehicle label; performing license plate recognition on a second vehicle leaving the first parking lot by a license plate recognition system at an exit of the first parking lot, to obtain a second license plate recognition result; when the second license plate recognition result is a recognition failure, performing multi-angle image acquisition on the second vehicle by an intelligent camera at the exit of the first parking lot to obtain second multi-angle image data, and generating a second vehicle label according to the second multi-angle image data, the second vehicle label having a second generation time identifier, wherein the image acquisition angle of the second multi-angle image data is the same as that of the first multi-angle image data; comparing and matching the second vehicle label and the first vehicle label to obtain a matching result, performing parking duration calculation according to the matching result in combination with the first generation time identifier and the second generation time identifier, and performing parking fee management according to the calculation result.

[0006] According to a second aspect of the present disclosure, a no-plate vehicle parking lot identification system based on image analysis is provided, comprising: a first license plate identification result obtaining module, configured to perform license plate identification on a first vehicle entering a first parking lot by a license plate identification system at an entrance of the first parking lot, and obtain a first license plate identification result; a first multi-angle image data obtaining module, configured to, when the first license plate identification result is identification failure, start an intelligent camera at the entrance of the first parking lot, perform multi-angle image acquisition on the first vehicle by the intelligent camera, and obtain first multi-angle image data; a first vehicle label obtaining module, configured to perform vehicle feature identification on the first vehicle according to the first multi-angle image data, generate a first vehicle label according to a vehicle feature identification result, the first vehicle label being provided with a first generation time identifier, and control an entrance barrier at the entrance to be opened according to the first vehicle label; a second license plate identification result obtaining module, configured to perform license plate identification on a second vehicle leaving the first parking lot by a license plate identification system at an exit of the first parking lot, and obtain a second license plate identification result; a second multi-angle image data obtaining module, configured to, when the second license plate identification result is identification failure, perform multi-angle image acquisition on the second vehicle by an intelligent camera at the exit of the first parking lot, obtain second multi-angle image data, and generate a second vehicle label according to the second multi-angle image data, the second vehicle label being provided with a second generation time identifier, wherein the image acquisition angle of the second multi-angle image data is the same as that of the first multi-angle image data; and a parking duration obtaining module, configured to compare and match the second vehicle label and the first vehicle label, obtain a matching result, perform parking duration calculation according to the matching result in combination with the first generation time identifier and the second generation time identifier, and perform parking fee management according to a calculation result.

[0007] According to a third aspect of the present disclosure, a computer device is provided, comprising a memory and a processor, the memory storing a computer program, and the processor being capable of executing the method according to any one of the first aspect.

[0008] According to a fourth aspect of the present disclosure, a computer readable storage medium is provided, storing a computer program, the computer program being executed by a processor to implement the method according to any one of the first aspect.

[0009] The one or more technical solutions provided in the disclosure have at least the following technical effects or advantages: according to the disclosure, a license plate recognition system at an entrance of a first parking lot is used to recognize a license plate of a first vehicle entering the first parking lot, and a first license plate recognition result is obtained; when the first license plate recognition result is a recognition failure, a smart camera at the entrance of the first parking lot is started, and multi-angle image data of the first vehicle is obtained through the smart camera; vehicle feature recognition is performed on the first vehicle according to the first multi-angle image data, a first vehicle label is generated according to a vehicle feature recognition result, the first vehicle label has a first generation time identifier, and the entrance gate at the entrance is controlled to be opened according to the first vehicle label; a license plate recognition system at an exit of the first parking lot is used to recognize a license plate of a second vehicle exiting the first parking lot, and a second license plate recognition result is obtained; when the second license plate recognition result is a recognition failure, multi-angle image data of the second vehicle is obtained through a smart camera at the exit of the first parking lot, and a second vehicle label is generated according to the second multi-angle image data, the second vehicle label has a second generation time identifier, and the image acquisition angle of the second multi-angle image data is the same as that of the first multi-angle image data; the second vehicle label and the first vehicle label are compared and matched, a matching result is obtained, parking duration is calculated according to the matching result and in combination with the first generation time identifier and the second generation time identifier, and parking fee management is performed according to a calculation result, thereby solving the technical problem in the prior art that the parking lot exit control efficiency is low due to low recognition accuracy of license plate-free vehicles, achieving the goal of improving the recognition accuracy of license plate-free vehicles, and achieving the technical effect of improving the parking lot exit control efficiency.

[0010] It should be understood that the content described in this part is not intended to indicate key or important features of the embodiments of the disclosure, nor is it used to limit the scope of the disclosure. Other features of the disclosure will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the disclosure or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are only exemplary, and other drawings can be obtained by those skilled in the art without creative effort on the basis of the provided drawings.

[0012] Figure 1 A flowchart of a license plate-free vehicle parking lot recognition method based on image analysis provided by the embodiments of the disclosure is shown in the figure.

[0013] Figure 2A flowchart of a process of generating a first vehicle label in a no-plate vehicle parking lot identification method based on image analysis according to an embodiment of the present disclosure is shown in FIG. 1.

[0014] Figure 3 A logic diagram of a parking lot license plate identification system in a no-plate vehicle parking lot identification method based on image analysis according to an embodiment of the present disclosure is shown in FIG. 2.

[0015] Figure 4 A structure diagram of a no-plate vehicle parking lot identification system based on image analysis according to an embodiment of the present disclosure is shown in FIG. 3.

[0016] Figure 5 A structure diagram of a computer device according to an embodiment of the present disclosure is shown in FIG. 4.

[0017] Label explanation: first license plate identification result obtaining module 11, first multi-angle image data obtaining module 12, first vehicle label obtaining module 13, second license plate identification result obtaining module 14, second multi-angle image data obtaining module 15, parking duration obtaining module 16, computer device 100, processor 101, memory 102, bus 103. DETAILED DESCRIPTION

[0018] Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, which include various details of the embodiments of the present disclosure to assist in understanding, and should be considered as merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Also, in order to be clear and concise, descriptions of well-known functions and structures are omitted in the following description.

[0019] Embodiment One

[0020] The no-plate vehicle parking lot identification method based on image analysis according to an embodiment of the present disclosure is described with reference to FIGS. 1-4. Figure 1 , Figure 2 and Figure 3 The method comprises:

[0021] The method according to an embodiment of the present disclosure comprises:

[0022] The first vehicle license plate is identified by a license plate identification system at the entrance of the first parking lot, and a first license plate identification result is obtained.

[0023] The first parking lot is a parking lot to be identified. An entrance license plate recognition system of the first parking lot is acquired. The first vehicle entering the first parking lot is recognized by the entrance license plate recognition system of the first parking lot, and a first license plate recognition result is obtained. When the first license plate is obtained, the first license plate recognition result is successful. When the first license plate is not obtained, the first license plate recognition result is failed.

[0024] When the first license plate recognition result is failed, a smart camera at the entrance of the first parking lot is started. The first vehicle is imaged by the smart camera at multiple angles, and first multi-angle image data is obtained.

[0025] When the first license plate recognition result is failed, a smart camera at the entrance of the first parking lot is started. The smart camera is used for image acquisition. Further, the first vehicle is imaged by the smart camera at multiple angles, and first multi-angle image data is obtained. The multiple angles include front, back, left and right angles of the vehicle body.

[0026] According to the first multi-angle image data, vehicle feature recognition of the first vehicle is performed. A first vehicle label is generated according to the vehicle feature recognition result. The first vehicle label has a first generation time identifier. The entrance gate at the entrance is opened according to the first vehicle label.

[0027] The first multi-angle image data is marked with a shooting angle, and each shooting angle is marked and associated with the image in the first multi-angle image data to obtain an angle marking result. The first multi-angle image data is processed by grayscale processing to obtain a first grayscale image. Further, the first grayscale image is divided into pixel points according to a predetermined pixel segmentation size to obtain a first segmented pixel region. For example, the predetermined pixel segmentation size can be a 3x3 square, a circle, etc. Further, the first segmented pixel region is encoded according to a predetermined encoding rule. The first vehicle is calculated according to the encoding result to obtain a first vehicle feature value. The first vehicle label is generated according to the vehicle feature value. Further, the first vehicle label has a first generation time identifier, which is used to identify the first vehicle storage time. The entrance gate at the entrance is opened according to the first vehicle label.

[0028] The second vehicle leaving the first parking lot is recognized by the exit license plate recognition system of the first parking lot, and a second license plate recognition result is obtained.

[0029] The exit of the first parking lot is provided with a license plate recognition system, which is the same license plate recognition system as the license plate recognition system provided at the entrance of the first parking lot. The license plate recognition system at the exit of the first parking lot recognizes the license plate of the second vehicle driving out of the first parking lot to obtain a second license plate recognition result. When the second license plate is obtained, the second license plate recognition result is successful recognition. When the second license plate is not obtained, the second license plate recognition result is failed recognition.

[0030] When the second license plate recognition result is failed recognition, the intelligent camera at the exit of the first parking lot collects multi-angle image data of the second vehicle, and generates a second vehicle label according to the second multi-angle image data, the second vehicle label having a second generation time identifier, wherein the second multi-angle image data has the same image collection angle as the first multi-angle image data.

[0031] When the second license plate recognition result is failed recognition, the intelligent camera at the exit of the first parking lot collects multi-angle image data of the second vehicle. The multi-angle includes front, back, left and right angles of the vehicle body. The second multi-angle image data is marked with a shooting angle, and each shooting angle is associated with an image in the second multi-angle image data to obtain an angle marking result. The second multi-angle image data is subjected to grayscale processing to obtain a second grayscale image. Further, the second grayscale image is divided into pixel points according to a predetermined pixel segmentation size to obtain a second segmented pixel region. The second segmented pixel region is encoded according to a predetermined encoding rule, and the second vehicle is calculated according to the encoding result to obtain a second vehicle feature value, and the second vehicle label is generated according to the vehicle feature value. Further, the second vehicle label has a second generation time identifier for identifying the time when the second vehicle exits the parking lot. Further, the second multi-angle image data has the same image collection angle as the first multi-angle image data.

[0032] The second vehicle label and the first vehicle label are compared and matched to obtain a matching result, and the parking duration is calculated according to the matching result, the first generation time identifier and the second generation time identifier, and the parking fee management is performed according to the calculation result.

[0033] According to the second vehicle label and the first vehicle label, the second vehicle feature value and the first vehicle feature value are extracted. The number of coding results of 1 in the second vehicle feature value and the number of coding results of 1 in the first vehicle feature value are compared and analyzed to obtain a first comparison deviation. Further, if the first comparison deviation is within a predetermined deviation threshold range, indicating that the first comparison deviation is small, the first vehicle and the second vehicle are associated to obtain a matching result. Further, according to the matching result, the first generation time identifier and the second generation time identifier are extracted. Wherein, according to the matching result, the first vehicle and the second vehicle are the same vehicle. The first vehicle warehousing time and the second vehicle delivery time are extracted. Further, according to the first generation time identifier and the second generation time identifier, the parking time is calculated to obtain a first parking time. Further, the unit time parking fee of the first parking lot is obtained. According to the unit time parking fee multiplied by the first parking time, the parking fee is calculated to obtain a first parking fee. Further, according to the first parking fee, the parking fee management is carried out.

[0034] Wherein, through the embodiment, the technical problem of low parking lot entry and exit control efficiency caused by low accuracy of license plateless vehicle recognition in the prior art can be solved, the goal of improving the accuracy of license plateless vehicle recognition is achieved, and the technical effect of improving the parking lot entry and exit control efficiency is achieved.

[0035] The method provided by the embodiment of the present disclosure further comprises:

[0036] The first multi-angle image data is marked with a shooting angle to obtain an angle marking result.

[0037] The first multi-angle image data is subjected to grayscale processing to obtain a first grayscale image.

[0038] The first grayscale image is subjected to pixel point segmentation according to a predetermined pixel segmentation size to obtain a first segmented pixel region.

[0039] The first segmented pixel region is subjected to pixel point coding according to a predetermined coding rule, and the first vehicle label is generated according to the coding result.

[0040] The first multi-angle image data is marked with a shooting angle, and each shooting angle is associated with an image in the first multi-angle image data to obtain an angle marking result.

[0041] Further, the grayscale processing is a process of converting a color image into a grayscale image. The grayscale image only contains one channel, and the channel value represents the grayscale value. In the grayscale processing, the RGB value of each pixel is combined into a single grayscale value. Common grayscale methods include: weighted average method: the red, green, and blue color channels are weighted and averaged according to different weights to obtain a grayscale value. Average value method: the values of the red, green, and blue color channels are added and divided by 3 to obtain a grayscale value. Further, the first multi-angle image data is subjected to grayscale processing to obtain a first grayscale image.

[0042] Further, the first grayscale image is subjected to pixel segmentation according to a predetermined pixel segmentation size to obtain a first segmented pixel region. For example, the predetermined pixel segmentation size can be a 3x3 square, a circle, etc.

[0043] Further, the first segmented pixel region is subjected to pixel coding according to a predetermined coding rule, and the first vehicle feature value is calculated according to the coding result, to obtain a first vehicle feature value, which is the number of coding results of 1. When the pixel grayscale value of each pixel in the first segmented pixel region except the center pixel is greater than the center grayscale value, the coding result of the pixel is 1. When the pixel grayscale value of each pixel in the first segmented pixel region except the center pixel is less than or equal to the center grayscale value, the coding result of the pixel is 0. Further, the first vehicle label is generated according to the vehicle feature value.

[0044] According to the first multi-angle image data, the vehicle feature of the first vehicle is identified, and the first vehicle label is generated according to the vehicle feature identification result, so as to improve the accuracy of the license plate-free vehicle identification and improve the efficiency of the parking lot management.

[0045] The method provided by the embodiments of the present disclosure further includes:

[0046] The center grayscale value of the center pixel of the first segmented pixel region is obtained;

[0047] The pixel grayscale values of the plurality of pixels in the first segmented pixel region except the center pixel are obtained;

[0048] The predetermined coding rule is obtained, and the predetermined coding rule is as follows:

[0049]

[0050] L i The coding result of the i-th pixel in the plurality of pixels except the center pixel;

[0051] According to the predetermined encoding rule, the first segmented pixel region is pixel point encoded, and the first vehicle label is generated according to the encoding result.

[0052] A center gray value of a center pixel point of the first segmented pixel region is obtained. The center pixel point can be obtained by measuring the center point. Further, a plurality of pixel point gray values of a plurality of pixel points in the first segmented pixel region except the center pixel point are obtained.

[0053] Further, a predetermined encoding rule is obtained, and the predetermined encoding rule is as follows:

[0054]

[0055] L i is the encoding result of the i-th pixel point of the plurality of pixel points in the first segmented pixel region except the center pixel point. Further, when the pixel point gray value of the plurality of pixel points in the first segmented pixel region except the center pixel point is greater than the center gray value, L i is 1. When the pixel point gray value of the plurality of pixel points in the first segmented pixel region except the center pixel point is less than or equal to the center gray value, L i is 0. i L i is the encoding result of the i-th pixel point of the plurality of pixel points in the first segmented pixel region except the center pixel point. Further, when the pixel point gray value of the plurality of pixel points in the first segmented pixel region except the center pixel point is greater than the center gray value, L i is 1. When the pixel point gray value of the plurality of pixel points in the first segmented pixel region except the center pixel point is less than or equal to the center gray value, L i is 0. i L i is the encoding result of the i-th pixel point of the plurality of pixel points in the first segmented pixel region except the center pixel point. Further, when the pixel point gray value of the plurality of pixel points in the first segmented pixel region except the center pixel point is greater than the center gray value, L i is 1. When the pixel point gray value of the plurality of pixel points in the first segmented pixel region except the center pixel point is less than or equal to the center gray value, L i is 0. i L i is the encoding result of the i-th pixel point of the plurality of pixel points in the first segmented pixel region except the center pixel point. Further, when the pixel point gray value of the plurality of pixel points in the first segmented pixel region except the center pixel point is greater than the center gray value, L i is 1. When the pixel point gray value of the plurality of pixel points in the first segmented pixel region except the center pixel point is less than or equal to the center gray value, L i is 0.

[0056] Further, based on big data, the encoding rule is indexed and searched to obtain historical image encoding records. According to the historical image encoding records, the predetermined encoding rule is set. Further, the first segmented pixel region is pixel point encoded according to the predetermined encoding rule, the first vehicle is feature value calculated according to the encoding result, the first vehicle feature value is obtained, the first vehicle feature value is the number of encoding results being 1, and the first vehicle label is generated according to the vehicle feature value.

[0057] According to the predetermined encoding rule, the first segmented pixel region is pixel point encoded, and the first vehicle label is generated according to the encoding result, which realizes the purpose of improving the accuracy of license plate-free vehicle recognition and achieves the technical effect of improving the efficiency of parking lot access control.

[0058] The method provided by the embodiments of the present disclosure further includes:

[0059] According to the encoding result, the first vehicle is feature value calculated to obtain a first vehicle feature value, and the first vehicle feature value is the number of encoding results being 1.

[0060] According to the vehicle feature value, the first vehicle label is generated.

[0061] According to the encoding result, the characteristic value of the first vehicle is calculated, that is, the encoding result of the first vehicle is judged, and the characteristic value of the first vehicle is obtained, which is the number of encoding results being 1. Further, the first vehicle label is generated according to the vehicle characteristic value. The second vehicle label is generated in the same way as the first vehicle label. According to the encoding result, the characteristic value of the second vehicle is calculated, and the characteristic value of the second vehicle is obtained, which is the number of encoding results being 1.

[0062] The first vehicle label is generated according to the encoding result, which improves the accuracy of license plate-free vehicle recognition and improves the efficiency of parking lot access control.

[0063] The method provided by the embodiments of the present disclosure further comprises:

[0064] According to the second vehicle label and the first vehicle label, the second vehicle characteristic value and the first vehicle characteristic value are extracted;

[0065] The second vehicle characteristic value and the first vehicle characteristic value are compared and analyzed to obtain a first comparison deviation;

[0066] If the first comparison deviation is within a predetermined deviation threshold range, the association relationship between the first vehicle and the second vehicle is established, and the matching result is obtained.

[0067] According to the second vehicle label and the first vehicle label, the number of encoding results being 1 in the second vehicle characteristic value and the number of encoding results being 1 in the first vehicle characteristic value are extracted. The number of encoding results being 1 in the second vehicle characteristic value and the number of encoding results being 1 in the first vehicle characteristic value are compared and analyzed to obtain a first comparison deviation. Further, if the first comparison deviation is within a predetermined deviation threshold range, it means that the first comparison deviation is small, and the association relationship between the first vehicle and the second vehicle is established, and the matching result is obtained.

[0068] The second vehicle label and the first vehicle label are compared and matched to obtain a matching result, which improves the accuracy of license plate-free vehicle recognition and improves the efficiency of parking lot access control.

[0069] The method provided by the embodiments of the present disclosure further comprises:

[0070] According to the matching result, the first generation time identifier and the second generation time identifier are extracted;

[0071] According to the first generation time identifier and the second generation time identifier, the parking duration is calculated to obtain a first parking duration;

[0072] The unit time parking fee of the first parking lot is obtained;

[0073] According to the unit time parking fee and the first parking duration, a first parking fee is calculated.

[0074] According to the first parking fee, parking fee management is performed.

[0075] According to the matching result, the first vehicle and the second vehicle are the same vehicle. The first vehicle entry time and the second vehicle exit time are extracted. Further, according to the first generation time identifier and the second generation time identifier, a parking duration is calculated to obtain a first parking duration. Further, the unit time parking fee of the first parking lot is obtained. According to the unit time parking fee multiplied by the first parking duration, a parking fee is calculated to obtain a first parking fee. Further, according to the first parking fee, parking fee management is performed.

[0076] According to the matching result, the first vehicle and the second vehicle are the same vehicle. The first vehicle entry time and the second vehicle exit time are extracted. Further, according to the first generation time identifier and the second generation time identifier, a parking duration is calculated to obtain a first parking duration. Further, the unit time parking fee of the first parking lot is obtained. According to the unit time parking fee multiplied by the first parking duration, a parking fee is calculated to obtain a first parking fee. Further, according to the first parking fee, parking fee management is performed.

[0077] The method provided by the embodiment of the present disclosure further includes:

[0078] When the first license plate recognition result is a recognition failure, an image of the license plate region of the first vehicle is collected to obtain a first license plate region image;

[0079] The first license plate region image is subjected to license plate defect recognition to obtain a defect recognition result.

[0080] According to the defect recognition result, the first license plate recognition result is compensated and corrected.

[0081] When the first license plate recognition result is a recognition failure, an image of the license plate region of the first vehicle is collected to obtain a first license plate region image. Further, the first license plate region image is subjected to license plate defect recognition to obtain a defect recognition result. According to the defect recognition result, the first license plate recognition result is compensated and corrected. The license plate has stains, damage, etc. that cause recognition failure. The license plate recognition result can be updated to recognition success by cleaning or manual input of the license plate number.

[0082] According to the defect recognition result, the first license plate recognition result is compensated and corrected. The target of improving the recognition accuracy of vehicles without license plates is achieved, and the technical effect of improving the parking lot entry and exit control efficiency is achieved.

[0083] Embodiment two

[0084] Based on the same inventive concept as the image analysis-based license plate-free vehicle parking lot recognition method in the foregoing embodiments, reference is made to Figure 4 For illustration, the disclosure also provides an image analysis-based license plate-free vehicle parking lot recognition system, which comprises:

[0085] A first license plate recognition result obtaining module, which is configured to perform license plate recognition on a first vehicle entering a first parking lot by a license plate recognition system at an entrance of the first parking lot, and obtain a first license plate recognition result;

[0086] A first multi-angle image data obtaining module, which is configured to, when the first license plate recognition result is a recognition failure, start an intelligent camera at the entrance of the first parking lot, perform multi-angle image acquisition on the first vehicle by the intelligent camera, and obtain first multi-angle image data;

[0087] A first vehicle label obtaining module, which is configured to perform vehicle feature recognition on the first vehicle according to the first multi-angle image data, generate a first vehicle label according to a vehicle feature recognition result, the first vehicle label being provided with a first generation time identifier, and control an entrance barrier at the entrance to be opened according to the first vehicle label;

[0088] A second license plate recognition result obtaining module, which is configured to perform license plate recognition on a second vehicle leaving the first parking lot by a license plate recognition system at an exit of the first parking lot, and obtain a second license plate recognition result;

[0089] A second multi-angle image data obtaining module, which is configured to, when the second license plate recognition result is a recognition failure, perform multi-angle image acquisition on the second vehicle by an intelligent camera at the exit of the first parking lot, obtain second multi-angle image data, and generate a second vehicle label according to the second multi-angle image data, the second vehicle label being provided with a second generation time identifier, wherein the second multi-angle image data has the same image acquisition angle as the first multi-angle image data;

[0090] A parking duration obtaining module, which is configured to compare and match the second vehicle label and the first vehicle label, obtain a matching result, perform parking duration calculation according to the matching result in combination with the first generation time identifier and the second generation time identifier, and perform parking fee management according to a calculation result.

[0091] Further, the system further comprises:

[0092] An angle marking result obtaining module is configured to mark the first multi-angle image data with a shooting angle and obtain an angle marking result.

[0093] A first gray image obtaining module is configured to perform gray processing on the first multi-angle image data and obtain a first gray image.

[0094] A first segmented pixel region obtaining module is configured to perform pixel segmentation on the first gray image according to a predetermined pixel segmentation size and obtain a first segmented pixel region.

[0095] A first vehicle label obtaining module is configured to perform pixel coding on the first segmented pixel region according to a predetermined coding rule and generate the first vehicle label according to a coding result.

[0096] Further, the system further comprises:

[0097] A center gray value obtaining module is configured to obtain a center gray value of a center pixel of the first segmented pixel region.

[0098] A plurality of pixel gray value obtaining module is configured to obtain a plurality of pixel gray values of a plurality of pixels other than the center pixel in the first segmented pixel region.

[0099] A predetermined coding rule obtaining module is configured to obtain the predetermined coding rule, which is as follows:

[0100]

[0101] A coding result obtaining module is configured to perform L i coding on the first segmented pixel region according to the predetermined coding rule and generate the first vehicle label according to a coding result.

[0102] A first vehicle label processing module is configured to perform pixel coding on the first segmented pixel region according to the predetermined coding rule and generate the first vehicle label according to a coding result.

[0103] Further, the system further comprises:

[0104] A first vehicle feature value obtaining module is configured to perform feature value calculation on a first vehicle according to the coding result and obtain a first vehicle feature value, which is a number of the coding result being 1.

[0105] a first vehicle label obtaining module, configured to generate the first vehicle label according to the vehicle feature value.

[0106] Further, the system further comprises:

[0107] a second vehicle feature value obtaining module, configured to extract a second vehicle feature value and a first vehicle feature value according to the second vehicle label and the first vehicle label;

[0108] a first comparison deviation obtaining module, configured to perform comparison analysis on the second vehicle feature value and the first vehicle feature value, and obtain a first comparison deviation;

[0109] a matching result obtaining module, configured to establish an association relationship between the first vehicle and the second vehicle if the first comparison deviation is within a predetermined deviation threshold range, and obtain the matching result.

[0110] Further, the system further comprises:

[0111] a second generation time identifier obtaining module, configured to extract the first generation time identifier and the second generation time identifier according to the matching result;

[0112] a first parking duration obtaining module, configured to perform parking duration calculation according to the first generation time identifier and the second generation time identifier, and obtain a first parking duration;

[0113] a unit time parking fee obtaining module, configured to obtain a unit time parking fee of the first parking lot;

[0114] a first parking fee obtaining module, configured to perform parking fee calculation according to the unit time parking fee and the first parking duration, and obtain a first parking fee;

[0115] a parking fee management module, configured to perform parking fee management according to the first parking fee.

[0116] Further, the system further comprises:

[0117] a first license plate region image obtaining module, configured to, when the first license plate recognition result is a recognition failure, perform image acquisition on a license plate region of the first vehicle, and obtain a first license plate region image;

[0118] The defect identification result obtaining module is configured to perform license plate defect identification on the first license plate region image to obtain a defect identification result.

[0119] The compensation correction module is configured to perform compensation correction on the first license plate identification result according to the defect identification result.

[0120] The license plate-free vehicle parking lot identification method based on image analysis in the foregoing embodiment one is also applicable to the license plate-free vehicle parking lot identification system based on image analysis in the present embodiment. Those skilled in the art can clearly understand the license plate-free vehicle parking lot identification system based on image analysis in the present embodiment according to the foregoing detailed description of the license plate-free vehicle parking lot identification method based on image analysis. Therefore, for the sake of brevity of the description, no further detailed description is given herein. As the device disclosed in the embodiments corresponds to the method disclosed in the embodiments, the device is described more simply. For relevant parts, refer to the description of the method.

[0121] Embodiment three

[0122] Figure 5 is a schematic diagram according to the third embodiment of the present disclosure, as shown in Figure 5 The computer device 100 in the present disclosure can include a processor 101 and a memory 102.

[0123] The memory 102 is configured to store programs. The memory 102 can include volatile memory (e.g., random-access memory (RAM), such as static random-access memory (SRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDR SDRAM), etc.) and non-volatile memory (e.g., flash memory). The memory 102 is configured to store computer programs (e.g., application programs, functional modules, etc. for implementing the above method), computer instructions, etc. The computer programs, computer instructions, etc. described above can be stored in one or more memories 102 in a partitioned manner. The computer programs, computer instructions, data, etc. described above can be invoked by the processor 101.

[0124] The computer program, computer instruction, etc. described above can be stored in one or more memories 102 in a partitioned manner. And the computer program, computer instruction, etc. described above can be invoked by the processor 101.

[0125] The processor 101 is configured to execute the computer program stored in the memory 102 to implement each step in the method described in the above embodiments.

[0126] For details, please refer to the related description in the above method embodiments.

[0127] The processor 101 and the memory 102 can be an independent structure, or an integrated structure. When the processor 101 and the memory 102 are independent structures, the memory 102 and the processor 101 can be coupled and connected through the bus 103.

[0128] The computer device of the embodiment can execute the technical solutions in the above method, and the specific implementation process and technical principles are the same, which will not be repeated here.

[0129] According to the embodiments of the present disclosure, the present disclosure also provides a computer readable storage medium, and the computer readable storage medium stores a computer program, and the computer program is executed to implement the steps provided by any of the above embodiments.

[0130] It should be understood that the steps can be reordered, added, or deleted using the various forms of flow shown above. For example, the steps described in the present disclosure can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions of the present disclosure can be achieved, which is not limited herein.

[0131] The above specific embodiments do not constitute a limitation on the protection scope of the present disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for license plate-free vehicle parking lot identification based on image analysis, characterized by, The method comprises: license plate recognition of a first vehicle entering the first parking lot through a license plate recognition system at an entrance of the first parking lot to obtain a first license plate recognition result; when the first license plate recognition result is a recognition failure, starting an intelligent camera at the entrance of the first parking lot, and collecting multi-angle image data of the first vehicle through the intelligent camera; vehicle feature recognition of the first vehicle according to the first multi-angle image data, generating a first vehicle label according to a vehicle feature recognition result, the first vehicle label having a first generation time identifier, and controlling an entrance barrier at the entrance to be opened according to the first vehicle label; license plate recognition of a second vehicle leaving the first parking lot through a license plate recognition system at an exit of the first parking lot to obtain a second license plate recognition result; when the second license plate recognition result is a recognition failure, collecting second multi-angle image data of the second vehicle through an intelligent camera at the exit of the first parking lot, and generating a second vehicle label according to the second multi-angle image data, the second multi-angle image data having the same image collection angle as the first multi-angle image data, and the second vehicle label having a second generation time identifier; comparing and matching the second vehicle label and the first vehicle label to obtain a matching result, calculating a parking duration according to the matching result in combination with the first generation time identifier and the second generation time identifier, and performing parking fee management according to a calculation result; the vehicle feature recognition of the first vehicle according to the first multi-angle image data, and the generation of the first vehicle label according to a vehicle feature recognition result, comprising: angle marking of the first multi-angle image data to obtain an angle marking result; gray scale processing of the first multi-angle image data to obtain a first gray scale image; pixel point segmentation of the first gray scale image according to a predetermined pixel segmentation size to obtain a first segmented pixel region; pixel point coding of the first segmented pixel region according to a predetermined coding rule to generate the first vehicle label according to a coding result, the step comprising obtaining a center gray scale value of a center pixel point of the first segmented pixel region; obtaining a plurality of pixel point gray scale values of a plurality of pixel points in the first segmented pixel region except the center pixel point; obtaining the predetermined coding rule, the predetermined coding rule being as follows: ; is the encoding result of the i-th pixel point among the plurality of pixel points except the center pixel point. pixel point coding of the first segmented pixel region according to the predetermined coding rule to generate the first vehicle label according to a coding result; the generation of the first vehicle label according to the coding result, comprising: feature value calculation of the first vehicle according to the coding result to obtain a first vehicle feature value, the first vehicle feature value being a number of the coding result being 1; generating the first vehicle label according to the vehicle feature value.

2. The method of claim 1, wherein, the comparing and matching of the second vehicle label and the first vehicle label to obtain a matching result, comprising: extracting a second vehicle feature value and a first vehicle feature value according to the second vehicle tag and the first vehicle tag; performing comparison analysis on the second vehicle feature value and the first vehicle feature value to obtain a first comparison deviation; if the first comparison deviation is within a predetermined deviation threshold range, establishing an association relationship between the first vehicle and the second vehicle to obtain the matching result.

3. The method of claim 1, wherein, The parking duration calculation according to the matching result, the first generation time identifier and the second generation time identifier, and the parking fee management according to the calculation result, include: extracting the first generation time identifier and the second generation time identifier according to the matching result; performing parking duration calculation according to the first generation time identifier and the second generation time identifier to obtain a first parking duration; obtaining the unit time parking fee of the first parking lot; performing parking fee calculation according to the unit time parking fee and the first parking duration to obtain a first parking fee; performing parking fee management according to the first parking fee.

4. The method of claim 1, wherein, After obtaining the first license plate recognition result by the license plate recognition system at the entrance of the first parking lot, it further includes: When the first license plate recognition result is recognition failure, the first license plate area image is obtained by image acquisition of the license plate area of the first vehicle; performing license plate defect recognition on the first license plate area image to obtain a defect recognition result; compensating and correcting the first license plate recognition result according to the defect recognition result.

5. A system for license plate free vehicle parking lot identification based on image analysis, characterized in that, The system for implementing the image analysis based license plate free vehicle parking lot identification method of any one of claims 1-4, the system comprising: a first license plate recognition result obtaining module, the first license plate recognition result obtaining module being configured to obtain a first license plate recognition result by performing license plate recognition on a first vehicle entering the first parking lot through a license plate recognition system at the entrance of the first parking lot; a first multi-angle image data obtaining module, the first multi-angle image data obtaining module being configured to, when the first license plate recognition result is recognition failure, start an intelligent camera at the entrance of the first parking lot, and obtain first multi-angle image data by performing multi-angle image acquisition on the first vehicle through the intelligent camera; a first vehicle tag obtaining module, the first vehicle tag obtaining module being configured to perform vehicle feature recognition on the first vehicle according to the first multi-angle image data, generate a first vehicle tag according to the vehicle feature recognition result, the first vehicle tag having a first generation time identifier, and control an entrance barrier at the entrance to be opened according to the first vehicle tag; a second license plate recognition result obtaining module, the second license plate recognition result obtaining module being configured to obtain a second license plate recognition result by performing license plate recognition on a second vehicle leaving the first parking lot through a license plate recognition system at the exit of the first parking lot; A second multi-angle image data obtaining module is configured to, when the second license plate recognition result is a recognition failure, collect multi-angle images of the second vehicle by using an intelligent camera at an exit of the first parking lot to obtain second multi-angle image data, and generate a second vehicle tag according to the second multi-angle image data, the second vehicle tag being provided with a second generation time identifier, wherein the second multi-angle image data has the same image collection angle as the first multi-angle image data; A parking duration obtaining module is configured to compare and match the second vehicle tag and the first vehicle tag to obtain a matching result, calculate a parking duration according to the matching result and in combination with the first generation time identifier and the second generation time identifier, and perform parking fee management according to a calculation result. 6.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-5 when the computer program is executed by the processor. The computer program is executed by the processor to implement the steps of the method of any one of claims 1-4.

7. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1-4.

Images