CN115862377B - Intelligent reservation parking method and system - Google Patents
Intelligent reservation parking method and system Download PDFInfo
- Publication number
- CN115862377B CN115862377B CN202310076757.8A CN202310076757A CN115862377B CN 115862377 B CN115862377 B CN 115862377B CN 202310076757 A CN202310076757 A CN 202310076757A CN 115862377 B CN115862377 B CN 115862377B
- Authority
- CN
- China
- Prior art keywords
- license plate
- information
- vehicle
- parking
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000007726 management method Methods 0.000 claims abstract description 36
- 238000003708 edge detection Methods 0.000 claims abstract description 24
- 230000004927 fusion Effects 0.000 claims abstract description 11
- 238000005516 engineering process Methods 0.000 claims description 16
- 238000010586 diagram Methods 0.000 claims description 14
- 238000001914 filtration Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 9
- 238000013139 quantization Methods 0.000 claims description 9
- 238000005259 measurement Methods 0.000 claims description 8
- 238000004891 communication Methods 0.000 claims description 7
- QVFWZNCVPCJQOP-UHFFFAOYSA-N chloralodol Chemical group CC(O)(C)CC(C)OC(O)C(Cl)(Cl)Cl QVFWZNCVPCJQOP-UHFFFAOYSA-N 0.000 claims description 4
- 230000001351 cycling effect Effects 0.000 claims description 4
- 238000001514 detection method Methods 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000003709 image segmentation Methods 0.000 claims description 3
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 238000011524 similarity measure Methods 0.000 description 2
- 230000002708 enhancing effect Effects 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 210000001503 joint Anatomy 0.000 description 1
- 238000003032 molecular docking Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000011426 transformation method Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Abstract
The invention discloses an intelligent reserved parking method and system, belongs to the technical field of parking management, and is used for solving the technical problems that the utilization rate of parking spaces in the existing parking lot is low, the parking lot management is disordered, users are difficult to reasonably plan own parking arrangement according to the existing parking service, and the parking space resources in the parking lot are difficult to utilize to the maximum extent. The method comprises the following steps: determining a plurality of pieces of residual parking space information based on a parking reservation order reserved by a user; carrying out license plate image positioning on a vehicle of a user through a Sobel edge detection operator to obtain license plate positioning information of the vehicle; matching character texture features of license plate images of vehicles to obtain license plate identification information of the vehicles; according to license plate identification information and the entrance position of the vehicle, carrying out distance identification on a plurality of pieces of residual parking space information to obtain information of a to-be-parked space; and planning an indoor parking route of the vehicle, and obtaining a navigation route of the vehicle through multi-source fusion positioning of various signals.
Description
Technical Field
The application relates to the field of parking management, in particular to an intelligent reservation parking method and system.
Background
The management mode of the traditional parking industry is also relatively backward at present, and a plurality of pain points exist. Although the number of parking lots matched with the vehicle is continuously increased, road construction is continuously increased, and the requirement of the rapid increase of motor vehicles can not be met. At the same time, the owner of the vehicle can therefore waste a lot of time and fuel consumption.
In recent years, with the rapid development of economy in China, the automobile conservation amount is greatly increased. The parking space of the garage is tense, and the searching of the parking space in the large garage is more troublesome. The reason for this problem is that, on the one hand, the parking facility is severely insufficient, the parking lot management is disordered, the parking facility is severely lagged behind the urban construction, and on the other hand, the parking information is not smooth, and the driver cannot reasonably arrange the travel and driving route of the driver according to the parking information.
Disclosure of Invention
The embodiment of the application provides an intelligent reserved parking method and system, which are used for solving the following technical problems: the utilization rate of parking spaces in the existing parking lot is low, the management of the parking lot is disordered, a user is difficult to reasonably plan own parking arrangement according to the existing parking service, and the parking space resources in the parking lot are difficult to utilize to the maximum extent.
The embodiment of the application adopts the following technical scheme:
In one aspect, an embodiment of the present application provides an intelligent parking reservation method, including: determining a plurality of pieces of residual parking space information based on a parking reservation order reserved by a user; carrying out license plate image positioning on the vehicle of the user through a preset Sobel edge detection operator to obtain license plate positioning information of the vehicle; according to the license plate positioning information, matching character texture features of the license plate image of the vehicle to obtain license plate identification information of the vehicle; according to the license plate identification information and the entrance position of the vehicle, carrying out distance identification on the plurality of pieces of residual parking space information to obtain information of a to-be-parked space; the entrance position of the vehicle is the entrance position of the vehicle entering the parking lot; and planning an indoor parking route of the vehicle according to the information of the to-be-parked space, and obtaining a navigation route of the vehicle through multi-source fusion positioning of various signals so as to intelligently park the vehicle.
According to the method and the device for parking the automobile through intelligent reservation, parking can be inquired, reserved or automatically reserved, paid and navigated, the automobile owners are helped to find the parking spaces and the automobile is helped to find the automobile rapidly, the utilization efficiency of the parking spaces in the parking lot is effectively improved, safe, convenient and efficient parking service can be provided for drivers, and maximization of the utilization rate of parking space resources and maximization of profit of the parking lot can be achieved.
In a possible implementation manner, based on a parking reservation order reserved by a user, a plurality of pieces of residual parking space information are determined, and the method specifically comprises the following steps: carrying out data statistics on the parking space states of vehicles in the parking lot to obtain parking space state information; wherein, the parking space state information includes: empty parking space information, reserved parking space information and full parking space information; acquiring reserved parking space information of the user; judging the vacant parking spaces according to the reserved parking space information of the user, so as to obtain reserved parking space information; matching the reserved parking space information with the reserved parking space information to determine the parking reservation order; according to the parking reservation order, updating the data of a parking space state database, and determining the plurality of pieces of residual parking space information; the parking space state database is stored in a parking resource management unit of the parking lot.
In a possible implementation manner, before license plate image positioning is performed on the vehicle of the user through a preset Sobel edge detection operator to obtain license plate positioning information of the vehicle, the method further includes: acquiring an image of a license plate of the vehicle through a camera at the entrance position of a parking lot to obtain a license plate image of the vehicle; carrying out standard average value gray scale processing on the license plate image to obtain a license plate gray scale image; according to the pixel gray value and the image contrast of the license plate gray image, gray linear conversion is carried out on the license plate gray image, and a converted license plate gray image is obtained; sorting signal sample values in the center of a long window based on the long window corresponding to a preset digital signal, and determining the median value of the sorted signal sample values as an output value of median filtering; wherein the long window is a window with odd length; and eliminating noise of the license plate gray level image according to the output value of the median filter to obtain an initial license plate gray level image.
In a possible implementation manner, a license plate image is positioned on a vehicle of the user through a preset Sobel edge detection operator to obtain license plate positioning information of the vehicle, which specifically includes: acquiring adjacent pixel values in the direction of each pixel point in the initial license plate gray level image; the directions of the pixel points are the up-down, left-right directions of the pixel points; the adjacent pixel values are respectively corresponding to a central pixel in the initial license plate gray level image and a central element in a preset image detection template through the Sobel edge detection operator, and each corresponding pixel is respectively subjected to convolution operation to obtain a first convolution value and a second convolution value; wherein the first convolution value corresponds to the center pixel and the second convolution value corresponds to the center element; performing numerical comparison on the first convolution value and the second convolution value to determine an edge detection output value; and extracting the image edge of the initial license plate gray level image according to the edge detection output value, and determining license plate positioning information of the vehicle through binarization processing of the initial license plate gray level image.
In a possible implementation manner, before matching the character texture features of the license plate image of the vehicle according to the license plate positioning information to obtain license plate identification information of the vehicle, the method further includes: according to the license plate positioning information, carrying out vertical projection on license plate characters in the license plate image to obtain a license plate vertical projection image; the license plate vertical projection image comprises a plurality of character images, pixel points are sequentially detected from left to right on the license plate vertical projection image, and the detected first pixel point which is not zero is determined to be the left boundary of the first character in the license plate vertical projection image; after the left boundary is obtained, determining the detected first pixel point which is zero as the right boundary of the first character in the license plate vertical projection diagram; sequentially cycling until a plurality of characters in the license plate vertical projection diagram are detected in a boundary area; and determining projection boundaries of the characters according to the left boundary and the right boundary.
In a possible implementation manner, according to the license plate positioning information, matching character texture features of a license plate image of the vehicle to obtain license plate identification information of the vehicle, specifically including: according to the projection limits of the characters, image segmentation and feature recognition are carried out on the license plate vertical projection image, and then character texture features of each character in the license plate image are obtained; comparing and calculating the character texture characteristics with character templates of a preset standard template library to obtain similarity measurement quantization indexes; and carrying out similarity judgment on the character texture features according to the similarity measurement quantization index, and determining license plate identification information of the vehicle.
In a possible implementation manner, according to the information of the to-be-parked space, the vehicle is subjected to indoor parking route planning, and the navigation route of the vehicle is obtained through multi-source fusion positioning of multiple signals, which specifically includes: acquiring target position information of the information to be parked and current position information of the vehicle; acquiring and fusing the intensity of the signal of the current position information according to a multi-source signal sensor in a parking lot, and determining a multi-source characteristic value of the signal corresponding to the current position information; wherein the multi-source signal comprises at least: bluetooth signals, wiFi signals, and LoRa signals; comparing the multi-source characteristic value with a preset signal standard characteristic value to determine the actual position information of the vehicle; and planning an indoor parking route of the vehicle through a preset navigation system according to the target position information and the actual position information, and determining a navigation route of the vehicle.
In a possible embodiment, the navigation system comprises: an indoor navigation system and an outdoor navigation system; the navigation system can be externally connected with a navigation APP; wherein, navigation APP includes at least: hundred degree map, high-german map and google map; the indoor navigation system and the outdoor navigation system are integrated with an automatic switching system, and are used for switching the navigation systems between the indoor environment and the outdoor environment; the navigation system also realizes communication association based on vehicle route planning with wireless communication technology, mobile terminal technology, GPS positioning technology and GIS technology.
In a possible implementation manner, after the vehicle is subjected to indoor parking route planning according to the information of the to-be-parked space and the navigation route of the vehicle is obtained through multi-source fusion positioning of multiple signals, the method further comprises: according to the information of the to-be-parked space, carrying out parking identification on the vehicle to obtain information of the parked space; acquiring the driving-in time information corresponding to the information of the parked space, and updating a parking space state database according to license plate identification information of the vehicle; obtaining the corresponding driving-out time information of the parking space information; according to the driving-in time information and the driving-out time information, calculating the parking cost of the vehicle to obtain order payment information; and transmitting the order payment information to the mobile terminal of the user.
On the other hand, the embodiment of the application also provides an intelligent reserved parking system, which is characterized in that the system comprises: the parking space reservation unit is used for determining a plurality of pieces of residual parking space information based on the parking reservation order reserved by the user; the vehicle information acquisition unit is used for acquiring license plate images of vehicles of the users through a preset Sobel edge detection operator to obtain license plate positioning information of the vehicles; according to the license plate positioning information, matching character texture features of the license plate image of the vehicle to obtain license plate identification information of the vehicle; the intelligent navigation unit is used for carrying out distance recognition on the plurality of pieces of residual parking space information according to the license plate recognition information and the entrance position of the vehicle to obtain information of a to-be-parked space; and planning an indoor parking route of the vehicle according to the information of the to-be-parked space, and obtaining a navigation route of the vehicle through multi-source fusion positioning of various signals so as to intelligently park the vehicle.
The embodiment of the application provides an intelligent reservation parking method and system, through intelligent reservation parking, inquiry, reservation or automatic reservation, payment and navigation can be carried out, a vehicle owner is helped to find a parking space and quickly find a vehicle, the use efficiency of the parking space in a parking lot is effectively improved, safe, convenient and efficient parking service can be provided for a driver, and maximization of the utilization rate of parking space resources and maximization of profit of the parking lot can be realized.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. In the drawings:
fig. 1 is a flowchart of an intelligent parking reservation method provided in an embodiment of the present application;
fig. 2 is a schematic structural diagram of an intelligent parking reservation overall system according to an embodiment of the present application;
fig. 3 is a schematic diagram of a license plate positioning process according to an embodiment of the present application;
Fig. 4 is a flowchart of a median filtering algorithm provided in an embodiment of the present application;
FIG. 5 is a flowchart of a license plate character segmentation method according to an embodiment of the present application;
fig. 6 is a functional schematic diagram of a charging system according to an embodiment of the present application;
fig. 7 is a schematic structural diagram of an intelligent parking reservation system according to an embodiment of the present application.
Detailed Description
In order to better understand the technical solutions in the present application, the following description will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, shall fall within the scope of the present application.
The embodiment of the application provides an intelligent parking reservation method, as shown in fig. 1, specifically comprising steps S101-S105:
it should be noted that, fig. 2 is a schematic structural diagram of an intelligent parking reservation overall system provided in an embodiment of the present application, and as shown in fig. 2, the intelligent parking reservation system further includes: the parking system comprises a parking resource management unit (1), a parking space reservation unit (2), a vehicle information acquisition unit (3), an intelligent navigation unit (4) and a charging management unit (5).
The parking resource management unit (1) comprises a user information management module (1 a), a parking space information acquisition module (1 b), a parking space information management module (1 c) and a judgment module (1 d). The user information management module (1 a) is used for managing the user information of the reserved parking space. The parking space information acquisition module (1 b) is used for acquiring state information of each parking space in the parking lot and sending the state information to the parking space information management module (1 b), wherein the state information of the parking space comprises whether the parking space is empty or not and the position information of the parking space.
The parking space information management module (1 c) generates a parking space state database according to the parking space state information acquired by the parking space information acquisition module (1 b), updates the parking space state database in real time according to a preset order and the acquired state information of each parking space, and distributes the rest parking space information.
The judgment module (1 d) judges whether the vehicle is a scheduled vehicle according to the license plate information, if the vehicle is a scheduled vehicle, the judgment module distributes an empty vehicle position closest to the entrance position to a user according to the entrance position of the user vehicle entering the parking lot, and sends a charging starting instruction to the charging management unit (5) based on the vehicle entrance time.
The parking space reservation unit (2) comprises a webpage reservation module (2 a) and an APP reservation module (2 b). The webpage reservation module (2 a) and the APP reservation module (2 b) comprise a user end and a management end. The user side comprises a main page, a parking lot planning map function and a function of recommending an optimal parking space. The management end is divided into four plates, namely parking space management, order management, message check, manager personal information management and the like.
The vehicle information acquisition unit (3) comprises a license plate positioning module (3 a) and a license plate recognition module (3 b), acquires license plate information of a vehicle which enters or exits the parking lot, and sends the license plate information to the parking resource management unit (1).
The intelligent navigation unit (4) comprises an outdoor navigation module (4 a) and an indoor navigation module (4 b), wherein the outdoor navigation module (4 a) is used for acquiring the position of a user and navigating the vehicle of the user to a parking lot according to the position of the user and the position of the parking lot to which a preset parking lot belongs. And the indoor navigation module (4 b) is used for navigating the user vehicle to the target parking space according to the user position and the target parking space position.
The charge management unit (5) comprises a vehicle storage unit, a vehicle taking unit and a vehicle checking unit, and the vehicle parking unit price and the vehicle entering time can be automatically generated according to the vehicle information during the vehicle storage. When the vehicle is fetched, the parking time and the required cost can be automatically displayed, and after the payment is completed, a paid instruction is sent to the parking resource management unit (1). The administrator can view all vehicle entry and exit record details.
S101, determining a plurality of pieces of residual parking space information based on a parking reservation order reserved by a user.
Specifically, the parking space state of the vehicle in the parking lot is subjected to data statistics to obtain parking space state information. Wherein, parking stall state information includes: empty space information, reserved space information and full space information.
Further, reservation parking space information of the user is acquired. And judging the vacant parking spaces according to the reserved parking space information of the user, so as to obtain reserved parking space information. And matching the reserved parking space information with reserved parking space information to determine a parking reservation order.
Further, according to the parking reservation order, the parking space state database is subjected to data updating, and a plurality of pieces of residual parking space information are determined. Wherein the parking space state database is stored in a parking resource management unit of the parking lot.
In one embodiment, as shown in fig. 2, the parking space information collection module (1 b) is configured to collect status information of each parking space in the parking lot, and send the status information to the parking space information management module (1 c), where the status information of the parking space includes whether the parking space is empty or not, and location information of the parking space. The parking space information management module (1 c) generates a parking space state database according to the parking space state information acquired by the parking space information acquisition module (1 b), updates the parking space state database in real time according to a preset order and the acquired state information of each parking space, and distributes the residual parking space information, namely a plurality of residual parking space information.
In one embodiment, as shown in fig. 2, the parking space reservation unit (2) includes a web page reservation module (2 a) and an APP reservation module (2 b). Specifically, the development of the website is performed by using Javascript. The home page of the website is registration or login information, and the option is to log into the system with the identity of the user or administrator. And then, the android studio is used for developing the website and APP, so that the butt joint of the user and the system is realized.
As a possible implementation, for APP, the user side part: there are three selection fields on the main page.
(1) The first is the main page, i.e. the input destination provided to the user.
(2) The second is user situation feedback and order situation viewing, in which the user can feed back his/her own advice to the APP and problems that occur during use, and see how much his/her own parking costs.
(3) And the third is a personal information column of the user or the administrator, wherein the user can register personal information in the selection column, and can start a notification function, a voice recognition function, a positioning function and an automatic fee deduction function, and all the functions are started by default and can be closed by the user. The APP comprises a parking lot map of the city, is connected with a navigation system, clearly plans a plurality of driving-in routes of the parking lot, and divides each parking space of the parking lot into small squares. In addition to the fixed parking spaces of the parking lot, the APP should also display some free compliant positions for automatic display after the parking spaces are full, and this information is imported by the developer to contact with the manager of each parking space. Simultaneously, the APP can recommend nearby parking spaces according to the destination of the user, the price of each parking space is written on the home page, the APP can recommend the optimal parking space according to the distance between the parking space and the destination, and the user can also select the parking space according to the price. When the user leaves the parking space, the charging system automatically deducts the corresponding fee.
As a possible implementation, the management end: the management end is divided into four plates.
(1) The first board should be for parking space management and view for parking space reservation, the board is similar to the first board on the user side, the only difference being that the user reserves through this board and the administrator looks through this board.
(2) The second plate is order management, and the reservation and use condition of a parking lot is checked by inputting the name of the parking lot, including order number, user name, user telephone, license plate number, reservation starting time and state (the order of the to-be-paid or is completed).
(3) The third plate is a message check, which can see the problem of user feedback.
(4) The fourth panel is manager personal information management.
At the management end, a parking space manager can start a reminding function through starting, when a user arrives at a parking space, the parking space manager can automatically start through a vehicle recognition system, if a license plate is not right facing the vehicle recognition system, an unrecognizable phenomenon possibly occurs, the manager is required to input the vehicle license plate on the APP, and if the user reserves, the railing machine is controlled manually to enable the user to enter.
S102, carrying out license plate image positioning on a vehicle of a user through a preset Sobel edge detection operator to obtain license plate positioning information of the vehicle.
Specifically, a license plate of a vehicle is acquired through a camera at the entrance position of a parking lot, so that a license plate image of the vehicle is obtained. And carrying out standard average value gray scale processing on the license plate image to obtain a license plate gray scale image. And according to the pixel gray value and the image contrast of the license plate gray image, carrying out gray linear conversion on the license plate gray image to obtain a converted license plate gray image.
In one embodiment, fig. 3 is a schematic diagram of a license plate positioning process provided in the embodiment of the present application, where, as shown in fig. 3, a license plate photo of a vehicle is a true color image, and is required to be converted into a gray image. Image graying can be adoptedUsing standard average method, g represents gray value after graying, the color of each pixel in the color image has R, G, B components, and each component has 255 median value, then there is。
In one embodiment, some extrinsic factors may result in insufficient license plate photo contrast, making license plate characters unclear. Thus, various methods of enhancing image contrast, such as gray scale linear transformation, linear filters, histogram modification, and the like, may be utilized. The gray level linear transformation method is simple, convenient and effective, and has the following formula:the method comprises the steps of carrying out a first treatment on the surface of the Wherein, the liquid crystal display device comprises a liquid crystal display device,
if a >1, the contrast of the output image increases;
If a <1, the contrast of the output image is reduced;
if a=1, b|=0, the gray values of all pixels will be shifted up or down, i.e. the whole image will be darkened;
if a=1, b=0, then the image is unchanged;
if a takes a negative value, the dark areas will darken and the bright areas will lighten.
Further, based on a long window corresponding to the preset digital signal, sorting signal sample values in the center of the long window, and determining the median value of the sorted signal sample values as the output value of median filtering. Wherein, the long window is a window with odd length. And eliminating noise of the license plate gray image according to the output value of the median filtering to obtain an initial license plate gray image.
In one embodiment, fig. 4 is a flowchart of a median filtering algorithm provided in an embodiment of the present application, as shown in fig. 4, for a digital signal sequenceWhen filtering, a long window with odd length L is defined first>Is a positive integer. The signal sample in the window is set at a certain momentWherein->Is the signal sample value located in the center of the window. After the L signal sample values are arranged in order from small to large, the median value of the signal sample values is defined as the output value of median filtering. The median filtering method is very effective in removing noise and can be used to protect edge information in image processing.
Further, adjacent pixel values in the direction of each pixel point in the initial license plate gray level image are obtained. The direction of each pixel point is up, down, left and right directions of each pixel point.
Further, through a Sobel edge detection operator, adjacent pixel values are respectively corresponding to a central pixel in an initial license plate gray level image and a central element in a preset image detection template, and each corresponding pixel is respectively subjected to convolution operation to obtain a first convolution value and a second convolution value. Wherein the first convolution value corresponds to the center pixel and the second convolution value corresponds to the center element.
Further, the first convolution value and the second convolution value are compared in numerical value to determine an edge detection output value. And extracting the image edge of the initial license plate gray level image according to the edge detection output value, and determining license plate positioning information of the vehicle through binarization processing of the initial license plate gray level image.
In one embodiment, the operator is detected by an edge based on a first derivative. The gray value weighted difference is calculated for adjacent pixels in the four directions of up, down, left and right of each pixel point in the image, then the calculus is obtained, and finally the gradient is obtained.
When the Sobel operator is used for detecting the edge of the image, each pixel in the image is convolved by the two templates, the center pixel is respectively corresponding to the center element of the template, and then convolution operation is carried out. After the calculation is completed, the calculation results corresponding to the two convolution kernels are compared, the larger value is the output bit of the point, namely the edge detection output value, and then an appropriate threshold value is selected to extract the edge.
As a possible implementation manner, when the image edge detection is performed on the initial license plate gray level image, the convolution operation in the horizontal direction is as follows:。
s103, matching character texture features of license plate images of the vehicles according to license plate positioning information to obtain license plate identification information of the vehicles.
Specifically, according to license plate positioning information, vertical projection is carried out on license plate characters in a license plate image, and a license plate vertical projection image is obtained. The license plate vertical projection drawing comprises a plurality of character drawings. And detecting pixel points of the license plate vertical projection image sequentially from left to right, and determining the detected first pixel point which is not zero as the left boundary of the first character in the license plate vertical projection image.
Further, after the left boundary is obtained, the detected first pixel point which is zero is determined as the right boundary of the first character in the license plate vertical projection diagram. And sequentially cycling until a plurality of characters in the license plate vertical projection diagram are detected in the boundary area. And determining projection boundaries of a plurality of characters according to the left boundary and the right boundary.
In one embodiment, fig. 5 is a flowchart of a license plate character segmentation method provided in the embodiment of the present application, as shown in fig. 5, pixels of each coordinate are sequentially detected from left to right in a transverse direction on a license plate vertical projection chart, and the detected pixel is taken as a left boundary of a first projection character when the first detected pixel is not zero. Continuing to detect to the right, detecting that the first projected pixel point is zero, and taking the pixel point as the right boundary of the first projected character. And sequentially cycling until a plurality of characters in the license plate vertical projection diagram are detected in the boundary area, and determining the projection limit of the plurality of characters.
Further, according to projection limits of a plurality of characters, image segmentation and feature recognition are carried out on the license plate vertical projection image, and then character texture features of each character in the license plate image are obtained. And comparing the character texture features with character templates of a preset standard template library to obtain a similarity measurement quantization index. And carrying out similarity judgment on the character texture features according to the similarity measurement quantization index, and determining license plate identification information of the vehicle.
In one embodiment, as shown in fig. 5, a template matching method is used by an api intelligent cloud interface in Python to perform a comparison between each template in the standard template library established after character segmentation, and the comparison process is to calculate the similarity between the two templates and quantify the similarity, namely a similarity measurement quantization index. And carrying out similarity judgment on the character texture features according to the similarity measurement quantization index, and determining license plate identification information of the vehicle.
In one embodiment, the first step of the template matching algorithm is to build a template library including twenty-six english letters of kanji (jingjin, lu, etc.), uppercase and arabic numerals 0-9, and the second step is to determine a similarity metric quantization index between the template and the sample, and the calculation formula is as follows:
where S represents the similarity measure between the sample and the template, I represents the sample, T represents the template, and W, H is the intermediate of the similarity measure.
And S104, carrying out distance recognition on a plurality of pieces of residual parking space information according to license plate recognition information and the entrance position of the vehicle to obtain information of the to-be-parked space. The entrance position of the vehicle is the entrance position of the vehicle entering the parking lot.
S105, planning an indoor parking route of the vehicle according to the information of the to-be-parked space, and obtaining a navigation route of the vehicle through multi-source fusion positioning of various signals so as to intelligently park the vehicle.
Specifically, target position information of information to be parked and current position information of a vehicle are acquired. And acquiring and fusing the intensity of the signals of the current position information according to the multi-source signal sensor in the parking lot, and determining the multi-source characteristic value of the signal corresponding to the current position information. Wherein the multi-source signal comprises at least: bluetooth signal, wiFi signal, and LoRa signal.
Further, the multisource characteristic values are compared with preset signal standard characteristic values, and actual position information of the vehicle is determined. And planning an indoor parking route of the vehicle through a preset navigation system according to the target position information and the actual position information, and determining a navigation route of the vehicle.
Wherein the navigation system comprises: indoor navigation system and outdoor navigation system. The navigation system can be externally connected with a navigation APP. Wherein, navigation APP includes at least: hundred degree map, high german map and google map. The indoor navigation system and the outdoor navigation system are integrated automatic switching systems, and are used for switching the navigation systems between the indoor environment and the outdoor environment. The navigation system also realizes communication association based on vehicle route planning with wireless communication technology, mobile terminal technology, GPS positioning technology and GIS technology.
In one embodiment, in an area covering the bluetooth active card, the bluetooth active card periodically broadcasts signals, and after the intelligent terminal receives the signals, the intelligent terminal generates a characteristic value of a sensor of the position of the intelligent terminal according to the strength of the signals and signals collected by other sensors through a preset local algorithm, and generates position information of the intelligent terminal according to the characteristic value. And the characteristic values of Bluetooth signals received by a user using the intelligent terminal at different positions are different, and the characteristic values generated by the preset comparison system are compared with the received characteristic values, so that the position is judged. The high-precision real-time positioning of various indoor complex environments can be realized by collecting various signals such as Bluetooth, wiFi and the like on site through a multisource fusion positioning algorithm, the optimal positioning precision can reach 1.5 meters, and the target parking space can be accurately identified due to dense parking spaces.
In one embodiment, the navigation system can access maps of hundred degrees, golds and the like to realize indoor and outdoor integrated seamless docking navigation. The outdoor navigation reaches the indoor environment and is automatically switched to the indoor map, and the path planning and the destination navigation based on the real-time position of the vehicle are realized based on the indoor positioning sensing equipment. The functions of path re-planning, peripheral inquiry, position sharing, reverse vehicle searching and the like can be supported by means of a wireless communication technology, a mobile terminal technology, a GPS positioning technology and a GIS technology.
Further, according to the information of the to-be-parked space, the vehicle is subjected to vehicle storage identification, and the information of the parked space is obtained. And acquiring the driving-in time information corresponding to the parking space information, and updating the parking space state database according to the license plate identification information of the vehicle. And obtaining the driving-out time information corresponding to the information of the parking space. And calculating the parking cost of the vehicle according to the driving-in time information and the driving-out time information to obtain order payment information. And transmits the order payment information to the user's mobile terminal.
In one embodiment, fig. 6 is a functional schematic diagram of a charging system provided in the embodiment of the present application, as shown in fig. 6, a charging management unit includes a vehicle storage, a vehicle taking, and a viewing, and main functions are implemented as follows:
(1) Storing: when a new vehicle is ready to be put in storage, a license plate number of the vehicle to be put in is input into a dialog box of an entry and exit record management interface, the charging unit price is clicked, the system automatically generates the parking unit price of the vehicle according to the queried vehicle information, then the system automatically generates the entry time of the vehicle by clicking the entry unit price, and the related information of the vehicle is imported into a database.
(2) Taking a vehicle: when the vehicle gets from the warehouse, the license plate number is input in the dialog box, if the vehicle is in warehouse, the system automatically displays the warehouse-out time, the parking time and the required cost, and if the vehicle is not in warehouse, the dialog box is displayed to remind that the taken vehicle is not in warehouse.
(3) Viewing: clicking on the button "view all" displays details of all vehicle entry and exit records, clicking on the button "view not exiting" displays details of all not exiting vehicle entry and exit records.
In addition, the embodiment of the application further provides an intelligent reserved parking system, as shown in fig. 7, the intelligent reserved parking system 700 includes:
and the parking space reserving unit 710 is configured to determine a plurality of pieces of remaining parking space information based on the parking reservation order reserved by the user.
The vehicle information acquisition unit 720 is configured to acquire a license plate image of a vehicle of a user through a preset Sobel edge detection operator, so as to obtain license plate positioning information of the vehicle. And according to the license plate positioning information, matching character texture features of the license plate image of the vehicle to obtain license plate identification information of the vehicle.
The intelligent navigation unit 730 performs distance recognition on a plurality of pieces of remaining parking space information according to license plate recognition information and the entrance position of the vehicle, and obtains information of a parking space to be parked. And planning an indoor parking route for the vehicle according to the information of the to-be-parked space, and obtaining a navigation route of the vehicle through multi-source fusion positioning of various signals so as to intelligently park the vehicle.
According to the method and the device for parking the automobile through intelligent reservation, parking can be inquired, reserved or automatically reserved, paid and navigated, the automobile owners are helped to find the parking spaces and the automobile is helped to find the automobile rapidly, the utilization efficiency of the parking spaces in the parking lot is effectively improved, safe, convenient and efficient parking service can be provided for drivers, and maximization of the utilization rate of parking space resources and maximization of profit of the parking lot can be achieved.
All embodiments in the application are described in a progressive manner, and identical and similar parts of all embodiments are mutually referred, so that each embodiment mainly describes differences from other embodiments. In particular, for apparatus, systems, devices, non-volatile computer storage medium embodiments, the description is relatively simple as it is substantially similar to method embodiments, with reference to the accompanying descriptive matter in which there are various embodiments of the method.
The foregoing describes specific embodiments of the present application. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and variations of the embodiments of the present application will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the embodiments of the present application should be included in the scope of the claims of the present application.
Claims (8)
1. An intelligent reserved parking method is characterized by comprising the following steps:
determining a plurality of pieces of residual parking space information based on a parking reservation order reserved by a user;
carrying out license plate image positioning on a vehicle of the user through a preset Sobel edge detection operator to obtain license plate positioning information of the vehicle, wherein the method specifically comprises the following steps:
acquiring adjacent pixel values in the direction of each pixel point in the initial license plate gray level image; the directions of the pixel points are the up-down, left-right directions of the pixel points;
the adjacent pixel values are respectively corresponding to a central pixel in the initial license plate gray level image and a central element in a preset image detection template through the Sobel edge detection operator, and each corresponding pixel is respectively subjected to convolution operation to obtain a first convolution value and a second convolution value; wherein the first convolution value corresponds to the center pixel and the second convolution value corresponds to the center element;
Performing numerical comparison on the first convolution value and the second convolution value to determine an edge detection output value;
extracting an image edge of the initial license plate gray level image according to the edge detection output value, and determining license plate positioning information of the vehicle through binarization processing of the initial license plate gray level image;
according to the license plate positioning information, matching character texture features of the license plate image of the vehicle to obtain license plate identification information of the vehicle;
according to the license plate identification information and the entrance position of the vehicle, carrying out distance identification on the plurality of pieces of residual parking space information to obtain information of a to-be-parked space; the entrance position of the vehicle is the entrance position of the vehicle entering the parking lot;
according to the information of the to-be-parked space, planning an indoor parking route of the vehicle, and obtaining a navigation route of the vehicle through multi-source fusion positioning of various signals so as to intelligently park the vehicle, wherein the method specifically comprises the following steps of:
acquiring target position information of the information to be parked and current position information of the vehicle;
acquiring and fusing the intensity of the signal of the current position information according to a multi-source signal sensor in a parking lot, and determining a multi-source characteristic value of the signal corresponding to the current position information; wherein the multi-source signal comprises at least: bluetooth signals, wiFi signals, and LoRa signals;
Comparing the multi-source characteristic value with a preset signal standard characteristic value to determine the actual position information of the vehicle;
and planning an indoor parking route of the vehicle through a preset navigation system according to the target position information and the actual position information, and determining a navigation route of the vehicle.
2. The method for intelligently reserving parking according to claim 1, wherein the determining of the plurality of pieces of remaining parking space information based on the parking reservation order reserved by the user specifically comprises:
carrying out data statistics on the parking space states of vehicles in the parking lot to obtain parking space state information; wherein, the parking space state information includes: empty parking space information, reserved parking space information and full parking space information;
acquiring reserved parking space information of the user;
judging the vacant parking spaces according to the reserved parking space information of the user, so as to obtain reserved parking space information; matching the reserved parking space information with the reserved parking space information to determine the parking reservation order;
according to the parking reservation order, updating the data of a parking space state database, and determining the plurality of pieces of residual parking space information; the parking space state database is stored in a parking resource management unit of the parking lot.
3. The method for intelligently reserving parking according to claim 1, wherein before license plate image positioning is performed on a vehicle of the user through a preset Sobel edge detection operator to obtain license plate positioning information of the vehicle, the method further comprises:
acquiring an image of a license plate of the vehicle through a camera at the entrance position of a parking lot to obtain a license plate image of the vehicle;
carrying out standard average value gray scale processing on the license plate image to obtain a license plate gray scale image;
according to the pixel gray value and the image contrast of the license plate gray image, gray linear conversion is carried out on the license plate gray image, and a converted license plate gray image is obtained;
sorting signal sample values in the center of a long window based on the long window corresponding to a preset digital signal, and determining the median value of the sorted signal sample values as an output value of median filtering; wherein the long window is a window with odd length;
and eliminating noise of the license plate gray level image according to the output value of the median filter to obtain an initial license plate gray level image.
4. The method for intelligently reserving parking according to claim 1, wherein before character texture feature matching is performed on a license plate image of the vehicle according to the license plate positioning information to obtain license plate identification information of the vehicle, the method further comprises:
According to the license plate positioning information, carrying out vertical projection on license plate characters in the license plate image to obtain a license plate vertical projection image; the license plate vertical projection drawing comprises a plurality of character drawings;
sequentially detecting pixel points from left to right of the license plate vertical projection graph, and determining the detected first pixel point which is not zero as the left boundary of the first character in the license plate vertical projection graph;
after the left boundary is obtained, determining the detected first pixel point which is zero as the right boundary of the first character in the license plate vertical projection diagram;
sequentially cycling until a plurality of characters in the license plate vertical projection diagram are detected in a boundary area;
and determining projection boundaries of the characters according to the left boundary and the right boundary.
5. The method for intelligently reserving parking according to claim 4, wherein character texture feature matching is performed on license plate images of the vehicle according to the license plate positioning information to obtain license plate identification information of the vehicle, specifically comprising the following steps:
according to the projection limits of the characters, image segmentation and feature recognition are carried out on the license plate vertical projection image, and then character texture features of each character in the license plate image are obtained;
Comparing and calculating the character texture characteristics with character templates of a preset standard template library to obtain similarity measurement quantization indexes;
and carrying out similarity judgment on the character texture features according to the similarity measurement quantization index, and determining license plate identification information of the vehicle.
6. The method for intelligently reserving parking according to claim 1, wherein the navigation system comprises: an indoor navigation system and an outdoor navigation system;
the navigation system can be externally connected with a navigation APP; wherein, navigation APP includes at least: hundred degree map, high-german map and google map;
the indoor navigation system and the outdoor navigation system are integrated with an automatic switching system, and are used for switching the navigation systems between the indoor environment and the outdoor environment;
the navigation system also realizes communication association based on vehicle route planning with wireless communication technology, mobile terminal technology, GPS positioning technology and GIS technology.
7. The method for intelligently reserving parking according to claim 1, wherein after planning an indoor parking route for the vehicle according to the information of the to-be-parked space and obtaining a navigation route for the vehicle through multi-source fusion positioning of multiple signals, the method further comprises:
According to the information of the to-be-parked space, carrying out parking identification on the vehicle to obtain information of the parked space;
acquiring the driving-in time information corresponding to the information of the parked space, and updating a parking space state database according to license plate identification information of the vehicle;
obtaining the corresponding driving-out time information of the parking space information;
according to the driving-in time information and the driving-out time information, calculating the parking cost of the vehicle to obtain order payment information; and transmitting the order payment information to the mobile terminal of the user.
8. An intelligent parking reservation system, the system comprising:
the parking space reservation unit is used for determining a plurality of pieces of residual parking space information based on the parking reservation order reserved by the user;
the vehicle information acquisition unit is used for acquiring license plate images of vehicles of the users through a preset Sobel edge detection operator to obtain license plate positioning information of the vehicles, and specifically comprises the following steps: acquiring adjacent pixel values in the direction of each pixel point in the initial license plate gray level image; the directions of the pixel points are the up-down, left-right directions of the pixel points; the adjacent pixel values are respectively corresponding to a central pixel in the initial license plate gray level image and a central element in a preset image detection template through the Sobel edge detection operator, and each corresponding pixel is respectively subjected to convolution operation to obtain a first convolution value and a second convolution value; wherein the first convolution value corresponds to the center pixel and the second convolution value corresponds to the center element; performing numerical comparison on the first convolution value and the second convolution value to determine an edge detection output value; extracting an image edge of the initial license plate gray level image according to the edge detection output value, and determining license plate positioning information of the vehicle through binarization processing of the initial license plate gray level image; according to the license plate positioning information, matching character texture features of the license plate image of the vehicle to obtain license plate identification information of the vehicle;
The intelligent navigation unit is used for carrying out distance recognition on the plurality of pieces of residual parking space information according to the license plate recognition information and the entrance position of the vehicle to obtain information of a to-be-parked space; according to the information of the to-be-parked space, planning an indoor parking route of the vehicle, and obtaining a navigation route of the vehicle through multi-source fusion positioning of various signals so as to perform an intelligent parking method of the vehicle, wherein the method specifically comprises the following steps: acquiring target position information of the information to be parked and current position information of the vehicle; acquiring and fusing the intensity of the signal of the current position information according to a multi-source signal sensor in a parking lot, and determining a multi-source characteristic value of the signal corresponding to the current position information; wherein the multi-source signal comprises at least: bluetooth signals, wiFi signals, and LoRa signals; comparing the multi-source characteristic value with a preset signal standard characteristic value to determine the actual position information of the vehicle; and planning an indoor parking route of the vehicle through a preset navigation system according to the target position information and the actual position information, and determining a navigation route of the vehicle.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310076757.8A CN115862377B (en) | 2023-02-08 | 2023-02-08 | Intelligent reservation parking method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310076757.8A CN115862377B (en) | 2023-02-08 | 2023-02-08 | Intelligent reservation parking method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115862377A CN115862377A (en) | 2023-03-28 |
CN115862377B true CN115862377B (en) | 2023-05-12 |
Family
ID=85657742
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310076757.8A Active CN115862377B (en) | 2023-02-08 | 2023-02-08 | Intelligent reservation parking method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115862377B (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103123684A (en) * | 2011-11-18 | 2013-05-29 | 江南大学 | License plate location method |
CN110853391A (en) * | 2019-11-11 | 2020-02-28 | 王新晓 | Intelligent shared parking system |
CN115082887A (en) * | 2022-07-14 | 2022-09-20 | 深圳市豪恩汽车电子装备股份有限公司 | Motor vehicle road auxiliary line detection system and image processing device and method thereof |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105976041B (en) * | 2016-05-16 | 2021-07-09 | 重庆理工大学 | Urban intelligent parking reservation system and method based on Internet of vehicles |
CN108831183A (en) * | 2018-06-06 | 2018-11-16 | 哈尔滨工业大学(威海) | Managing system of car parking based on machine vision |
CN112801141B (en) * | 2021-01-08 | 2022-12-06 | 吉林大学 | Heterogeneous image matching method based on template matching and twin neural network optimization |
-
2023
- 2023-02-08 CN CN202310076757.8A patent/CN115862377B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103123684A (en) * | 2011-11-18 | 2013-05-29 | 江南大学 | License plate location method |
CN110853391A (en) * | 2019-11-11 | 2020-02-28 | 王新晓 | Intelligent shared parking system |
CN115082887A (en) * | 2022-07-14 | 2022-09-20 | 深圳市豪恩汽车电子装备股份有限公司 | Motor vehicle road auxiliary line detection system and image processing device and method thereof |
Also Published As
Publication number | Publication date |
---|---|
CN115862377A (en) | 2023-03-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11263906B2 (en) | Automotive vehicle parking systems, methods, and apparatus | |
CN112419516B (en) | Information processing method, system, device and storage medium | |
US9275547B2 (en) | Prediction of free parking spaces in a parking area | |
CN109410623A (en) | Parking navigation method and device | |
CN104937650A (en) | System and method for locating available parking spaces | |
CN108230725A (en) | Method and apparatus are recommended in parking | |
CN110853391A (en) | Intelligent shared parking system | |
Cynthia et al. | IOT based smart parking management system | |
CN105528912A (en) | Indoor parking stall recommendation method and system | |
KR101746924B1 (en) | System and method of providing parking service for residential parking permit | |
CN111627245A (en) | Reverse vehicle searching system, method, computer device and storage medium | |
Somani et al. | Cross platform smart reservation based parking system | |
CN104537865A (en) | Vehicle management system and method for second-hand vehicle transaction parking lot | |
CN114554391A (en) | Parking lot vehicle searching method, device, equipment and storage medium | |
CN109544981A (en) | Image processing method, device, equipment and medium | |
CN115862377B (en) | Intelligent reservation parking method and system | |
CN112863229A (en) | System and method for realizing unattended operation based on parking equipment and technology | |
US11719553B2 (en) | Spotfinder | |
CN111243325A (en) | Parking multidimensional sensing investigation method and device, storage medium and terminal | |
CN113421452B (en) | Open parking lot recommendation system based on visual analysis | |
KR102266617B1 (en) | System for Integrated management of parking lot | |
Annirudh et al. | IoT based intelligent parking management system | |
CN115131986A (en) | Intelligent management method and system for closed parking lot | |
CN115588306A (en) | Parking space pushing method and device, computer readable storage medium and terminal | |
TWI670694B (en) | Roadside parking grid management system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20230328 Assignee: Zibo Yijia Internet of Things Technology Co.,Ltd. Assignor: SHANDONG University OF SCIENCE AND TECHNOLOGY Contract record no.: X2023980043516 Denomination of invention: An intelligent reservation parking method and system Granted publication date: 20230512 License type: Common License Record date: 20231017 |
|
EE01 | Entry into force of recordation of patent licensing contract |