CN111260954A - Parking capacity estimation and parking space recommendation method based on image processing - Google Patents
Parking capacity estimation and parking space recommendation method based on image processing Download PDFInfo
- Publication number
- CN111260954A CN111260954A CN202010360115.7A CN202010360115A CN111260954A CN 111260954 A CN111260954 A CN 111260954A CN 202010360115 A CN202010360115 A CN 202010360115A CN 111260954 A CN111260954 A CN 111260954A
- Authority
- CN
- China
- Prior art keywords
- parking
- vehicle
- parking space
- frame
- time
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
- G08G1/141—Traffic control systems for road vehicles indicating individual free spaces in parking areas with means giving the indication of available parking spaces
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07B—TICKET-ISSUING APPARATUS; FARE-REGISTERING APPARATUS; FRANKING APPARATUS
- G07B15/00—Arrangements or apparatus for collecting fares, tolls or entrance fees at one or more control points
- G07B15/02—Arrangements or apparatus for collecting fares, tolls or entrance fees at one or more control points taking into account a variable factor such as distance or time, e.g. for passenger transport, parking systems or car rental systems
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- Finance (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to a parking capacity estimation and berth recommendation method based on image processing, which comprises the following steps: s1, identifying vehicle information entering a parking lot, and storing the vehicle information in a database; s2, judging whether the current vehicle is in the initial parking state or not according to the recognized vehicle information, and if so, executing a step S3; if not, directly providing a proper parking space; s3, comparing the recognized vehicle information with the remaining parking space data to obtain a proper parking space of the current vehicle, and providing the obtained parking space for the vehicle; s4, judging whether the vehicle reaches the provided parking space, if so, executing a step S5; s5, recording a parking picture of the vehicle in real time by a camera device arranged at the parking place, and storing a video formed by the recorded parking picture in a database so as to estimate the parking capacity of the vehicle; and S6, after the camera device arranged at the parking place acquires that the vehicle completely enters the provided parking place, the recommendation of the parking place of the vehicle is completed.
Description
Technical Field
The invention relates to the technical fields of deep learning, computer vision, image processing and the like, in particular to a parking capacity estimation and berth recommendation method based on image processing.
Background
With the continuous development of social economy and the continuous improvement of the living standard of people, automobiles are owned by more and more families. The problem that brings along is that the demand of parking area constantly increases, but the vast majority of present parking areas are only to waiting to park the vehicle to the random allocation of surplus parking stall number, lack the parking ability to the vehicle and divide, and then can't recommend suitable parking stall for the person who parks, often can cause the parking area to park the drawback such as the resource can not be well utilized and the person who parks experiences badly.
For example, patent publication No. CN106504579A discloses a parking management method for an indoor parking lot, which includes the following steps: (1) collecting position information and digital number information of each parking space in the parking lot, manufacturing the position information and the digital number information into an electronic map, and storing the electronic map in a controller; (2) the method comprises the steps that an infrared detector is utilized to timely acquire information whether vehicles are parked in parking lots or not, and the information is input into a controller; (3) the controller displays the information whether the vehicle is parked in each parking space in the parking lot through the display system; (4) the touch unit of the vacant parking space on the touch display screen is touched, and the controller receives the touch information and instructs a vacant parking space warning system arranged on the vacant parking space to send warning information; (5) after the vehicle stops at the vacant parking space, the vacant parking space warning system is automatically closed; the method can facilitate drivers and passengers to accurately and quickly find the vacant parking spaces. Although the method can enable the parking personnel to quickly find the vacant parking spaces, the problems that the parking capacity of the vehicle is not divided, the proper parking spaces cannot be recommended to the parking personnel, the parking resources of the parking lot cannot be well utilized, the parking experience of the parking personnel is poor and the like still exist.
However, with the continuous forward progress of technologies such as deep learning, machine vision, image processing and the like, the parking behavior of a person who parks can be well recognized by using the key technologies, so that the parking capacity is estimated, a proper parking space is recommended, and the problems can be finally solved.
Therefore, it is improved to the above technical problems.
Disclosure of Invention
The invention aims to provide a parking capacity estimation and parking space recommendation method based on image processing aiming at the defects of the prior art, which can estimate the parking capacity of a vehicle by utilizing technologies such as deep learning, machine vision, image processing and the like, recommend a proper parking space, improve user experience and reasonably utilize parking resources.
In order to achieve the purpose, the invention adopts the following technical scheme:
a parking capacity estimation and berth recommendation method based on image processing comprises the following steps:
s1, identifying vehicle information entering a parking lot, and storing the vehicle information in a database;
s2, judging whether the current vehicle is in the initial parking state or not according to the recognized vehicle information, and if so, executing a step S3; if not, directly providing a proper parking space;
s3, comparing the recognized vehicle information with the remaining parking space data to obtain a proper parking space of the current vehicle, and providing the obtained parking space for the vehicle;
s4, judging whether the vehicle reaches the provided parking space, if so, executing a step S5;
s5, recording a parking picture of the vehicle in real time by a camera device arranged at the parking place, and storing a video formed by the recorded parking picture in a database so as to estimate the parking capacity of the vehicle;
and S6, after the camera device arranged at the parking place acquires that the vehicle completely enters the provided parking place, the recommendation of the parking place of the vehicle is completed.
Further, the step S2 of directly providing a suitable parking space specifically includes: and if the current vehicle is not the initial parking, combining the historical parking capacity of the vehicle stored in the database to provide a proper parking space.
Further, the information of the vehicle in the step S3 includes a license plate, a logo, and a model of the vehicle; the remaining parking space data comprise a parking difficulty coefficient of the remaining parking space and a parking number corresponding to the parking difficulty coefficient, and the parking difficulty coefficient comprises a parking space with large parking difficulty, a parking space with large parking difficulty and a parking space with small parking difficulty.
Further, step S6 is preceded by:
after the camera device arranged at the parking place identifies that the vehicle reaches the provided parking place, a timing module is started and timing is started;
and judging whether the time recorded in the timing module reaches the preset time, if so, providing the parking space lower than the current parking difficulty coefficient for the vehicle again through voice prompt.
Further, the estimating of the parking capability of the vehicle in the step S5 specifically includes:
s51, training a convolutional neural network model for detecting a vehicle frame and a parking space frame in advance;
s52, inputting the parking video of the vehicle to be detected into the trained convolutional neural network model for detection to obtain detected vehicle information;
s53, estimating the parking capacity of the vehicle according to the obtained vehicle information, wherein the estimation is represented as:
wherein the content of the first and second substances,Score i indicating a parking capability;、、is a weighting coefficient;arepresenting the parking difficulty coefficient of the remaining parking spaces;w、Lrespectively representing the width and length of the vehicle;T p representing a preset parking time;t 1 indicating the time to start parking;t 2 indicating the time to end the stop.
Further, the step S52 specifically includes:
s521, detecting the first time in the parking video through the trained convolutional neural network model at each preset intervaljFrame vehicle frame information andjframing parking space frame information;
s522, calculating the detected firstjFrame intersection ratio of vehicle frame and parking space frameIOUExpressed as:
wherein the content of the first and second substances,representing the intersection of the predicted vehicle frame and the predicted parking space frame;representing a union of the predicted vehicle frame and the predicted parking space frame;area(C j )representing a vehicle frame;area(P j )showing a parking space frame;C j represents a vehicle;P j indicating a parking space;
s523, judging the result obtained by calculationIOUIf the value is greater than zero, if so, the value will beIOUValue put inS i Performing the following steps; wherein the content of the first and second substances,denotes the firstiN in one videoIOUA value of (d);
s524, putting the time point of each detection intoT i Performing the following steps; wherein the content of the first and second substances,,T i of (1) andS i the elements in (1) correspond one to one;
s525. pairS i The data in (1) is analyzed to obtain an analysis result.
Further, the step S5 of estimating the parking capability of the vehicle further includes generating the parking capability for each parking of the vehicleScore i Storing in a database, and determining all parking capabilities of vehicles in the databaseScore i And calculating an average value as a reference value recommended by the parking space during the next parking, wherein the reference value is represented as:
wherein the content of the first and second substances, corerepresents the average of all the stopping ability of the vehicle history.
Further, the step S1 includes recording the time when the vehicle enters.
Further, the step S6 is followed by:
and S7, when the vehicle is identified to run out of the parking lot, recording the time of the vehicle running out, determining the parking time of the vehicle by combining the vehicle entering time, and charging for parking the vehicle according to the determined parking time.
Further, step S4 is preceded by:
the vehicle is provided with a parking route through the display screen.
Compared with the prior art, the method and the system can estimate the parking capacity of the vehicle by utilizing technologies such as deep learning, machine vision and image processing, recommend a proper parking space, improve user experience and reasonably utilize parking resources.
Drawings
FIG. 1 is a flowchart illustrating a parking capacity estimation and berth recommendation method based on image processing according to an embodiment;
FIG. 2 is a schematic flowchart illustrating a parking capacity estimation and berth recommendation method based on image processing according to an embodiment;
FIG. 3 is a schematic diagram of a parking capacity estimation algorithm according to an embodiment;
fig. 4 is a schematic structural diagram of a vehicle frame and parking space frame detection convolutional neural network according to an embodiment.
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.
The invention aims to provide a parking capacity estimation and berth recommendation method based on image processing aiming at the defects of the prior art.
Example one
The embodiment provides a parking capacity estimation and berth recommendation method based on image processing, as shown in fig. 1-2, comprising the steps of:
s1, identifying vehicle information entering a parking lot, and storing the vehicle information in a database;
s2, judging whether the current vehicle is in the initial parking state or not according to the recognized vehicle information, and if so, executing a step S3; if not, directly providing a proper parking space;
s3, comparing the recognized vehicle information with the remaining parking space data to obtain a proper parking space of the current vehicle, and providing the obtained parking space for the vehicle;
s4, judging whether the vehicle reaches the provided parking space, if so, executing a step S5;
s5, recording a parking picture of the vehicle in real time by a camera device arranged at the parking place, and storing a video formed by the recorded parking picture in a database so as to estimate the parking capacity of the vehicle;
and S6, after the camera device arranged at the parking place acquires that the vehicle completely enters the provided parking place, the recommendation of the parking place of the vehicle is completed.
In the parking area, at first carry out the division of parking degree of difficulty coefficient with all parking stalls, specific division mode is: for the three-dimensional parking garage, the parking space length and width are set strictly, and the parking difficulty is higher for a common driver, so that the parking difficulty grade is set to be high; for non-three-dimensional parking garage, if a certain parking space widthW<W T Dividing the parking difficulty level of the parking space into parking difficulties; if a certain parking space widthW≥W T (whereinW T A preset parking space width threshold value representing a parking difficulty level), then the parking difficulty level of the parking space is divided into a small parking difficulty level, and information of each parking space in the parking lot and a parking difficulty coefficient of each parking space are stored in a parking space databaseBIn (1).
The method comprises the following steps that M camera devices are arranged in a parking lot, and vacant parking spaces in the parking lot can be obtained through the arranged camera devices, wherein the camera devices can be cameras, one camera is arranged at each parking space or two adjacent parking spaces, or one camera is arranged in each area, the number of the cameras can be set according to actual conditions, as long as videos of vehicles parked in each parking space and each parking space can be monitored, and one camera is preferably arranged at each parking space; at least one camera is also arranged at the entrance and exit of the parking lot.
The embodiment adopts a vehicleC i And entering the parking lot for explanation.
In step S1, vehicle information entering the parking lot is identified and stored in a database.
When the vehicle is runningC i When entering the parking lot, the camera arranged at the entrance of the parking lot identifies the license plate, the logo and the model of the vehicle, and stores the identified vehicle information in the database of the vehicleAIn (1).
In step S2, it is determined whether the current vehicle is the first stop based on the recognized vehicle information, and if so, step S3 is executed; if not, directly providing a proper parking space.
Camera acquisition to vehicleC i After the information is stored in the databaseAIf the historical parking information of the vehicle exists, the historical parking information is combined with the vehicle stored in the databaseC i To provide the appropriate parking space for the vehicle; if the vehicle is not found, the vehicle is judged to be parked in the parking lot for the first time.
In step S3, the recognized vehicle information is compared with the remaining space data to obtain a space suitable for the current vehicle, and the obtained space is provided to the vehicle.
Obtain a vehicleC i After the first parking, the parking system is based on the databaseAThe data of the vehicle, such as the size and the length of the vehicleLVehicle widthwAnd the information is combined with the parking difficulty coefficient of the rest parking spaces in the parking lot to recommend a parking position suitable for the vehicle typeP i (ii) a Wherein the parking difficulty coefficient comprises a parking space with large parking difficulty, a parking space with small parking difficulty and a parking space with large parking difficulty.
In this embodiment, when a suitable parking space is determinedP i In time, the vehicle is driven by the display screenC i Providing parking route and planning shortest parking route, the parking route is prompted by indication display screen, and vehicle enters parking position according to promptP i 。
In step S4, it is determined whether the vehicle has reached the provided space, and if so, step S5 is executed.
Through being arranged in the parking spaceP i The camera acquires whether a vehicle arrives at the parking space, if so, the acquired information of the vehicle is sent to the system, the system compares the vehicle information acquired by the camera with the information provided for a certain vehicle by the parking space to judge whether the vehicle is a recommended vehicle,that is, whether the vehicle arriving at the parking space is the same vehicle as the vehicle recommended for the parking space when the vehicle enters the parking space is determined, if yes, step S5 is executed; if not, voice prompt is carried out through a loudspeaker arranged at the parking space, and the vehicle is enabled to arrive at the appointed parking space.
In step S5, the camera device disposed at the parking space records the parking picture of the vehicle in real time, and stores the video formed by the recorded parking picture in the database to estimate the parking capability of the vehicle.
Fig. 3 is a schematic diagram illustrating a parking capacity estimation algorithm.
In a vehicleC i Driving into parking positionP i In the process, the parking picture of the vehicle is recorded in real time through the monitoring camera above the parking space, and the video is transmittedV i And saving to the local. The video is analyzed by a parking capacity estimation algorithm at the later stage, and the parking capacity of the time is estimatedS i 。
Wherein estimating the stopping ability of the vehicle specifically comprises:
s51, training a convolutional neural network model for detecting a vehicle frame and a parking space frame in advance; the method specifically comprises the following steps:
fig. 4 is a schematic diagram of a vehicle frame and parking space frame detection convolutional neural network structure.
The design and training of a convolutional neural network model for detecting the vehicle frame and the parking space frame are as follows:
(1) training data and test data are prepared in an early stage: collecting videos through parking lot video monitoring, extracting N video frame images with vehicle pictures and parking space pictures, and marking the position information of a vehicle frame and a parking space frame by using a marking tool;
(2) in order to make network training more sufficient, data enhancement needs to be performed on the pictures, the data is increased by scaling, translating, overturning and rotating the N pictures, the data is increased to 32 times of the original data, and the data set is as follows: 2: 2, dividing the ratio into a training set, a verification set and a test set;
(3) and (3) network structure design: the detection network includes 24 convolutional layers and 2 fully-connected layers. The convolutional layer is used for extracting image features, and the full-link layer is used for predicting image position and class probability values. Multiple downsampling layers are employed. Setting the loss function as:
wherein the content of the first and second substances,to predict the coordinates of the upper left corner of the vehicle's frame,predicting the coordinates of the lower right corner of the vehicle frame;to actually label the coordinates of the upper left corner of the vehicle frame,marking the coordinates of the lower right corner of the vehicle frame for actual;in order to predict the coordinates of the upper left corner of the parking space frame,predicting the coordinates of the lower right corner of the parking space frame;the coordinates of the upper left corner of the parking space frame are actually marked,marking the coordinates of the lower right corner of the parking space frame for the actual parking space;
(4) model training, namely sending training data into a convolutional neural network, setting BatchSize input by the network to be 64, randomly initializing connection weight W and bias b of each layer, and setting learning rate η;
(5) and (3) testing a model: inputting the test set data into the trained frame detection model, detecting whether a frame exists or not, and if so, outputting the position information of the frame of the vehicle(coordinates of upper left corner and lower right corner) and parking space frame position information(upper left and lower right coordinates).
S52, inputting the parking video of the vehicle to be detected into the trained convolutional neural network model for detection to obtain detected vehicle information; the method specifically comprises the following steps:
s521, detecting the first time in the parking video through the trained convolutional neural network model at each preset intervaljFrame vehicle frame information andjframing parking space frame information;
detecting the first in the video by adopting the trained vehicle frame and parking space frame detection modeljFrame vehicle frame information: (x c0j ,y c0j )、(x c1j ,y c1j ) (representing the coordinates of the upper left corner and the lower right corner) andjframe parking space frame information: (x p0j ,y p0j )、(x p1j ,y p1j ) (upper left and lower right coordinates).
S522, calculating the detected firstjFrame intersection ratio of vehicle frame and parking space frameIOUExpressed as:
wherein the content of the first and second substances,representing the intersection of the predicted vehicle frame and the predicted parking space frame;representing a union of the predicted vehicle frame and the predicted parking space frame;area(C j )representing a vehicle frame;area(P j )showing a parking space frame;C j represents a vehicle;P j indicating a parking space;
s523, judging the result obtained by calculationIOUIf the value is greater than zero, if so, the value will beIOUValue put inS i Performing the following steps; wherein the content of the first and second substances,denotes the firstiN in one videoIOUA value of (d);
in this embodiment, if the preset interval time is 10 seconds, the detection is performed every 10 seconds, and the calculation is performedIOUIf the value is greater than zero, then it will beTheValue put inS i In (1).
S524, putting the time point of each detection intoT i Performing the following steps; wherein the content of the first and second substances,,T i of (1) andS i the elements in (1) correspond one to one;
s525. pairS i Analyzing the data to obtain an analysis result; the specific analysis is as follows:
(1) go throughS i If found, the element(s) in (1)S i The element in (1) finally approaches to 1 or equals to 1, and the index k of the element which approaches to 1 or the index k of the element which equals to 1 is found;
(2) find by index kT i At the corresponding time pointT k I.e. byT k For the time when the vehicle stopst 2 ;
(3) Go throughS i Find the index m of the first element greater than 0;
(4) find by index mT i At the corresponding time pointT m I.e. byT m For the time when the vehicle starts to stopt 1 ;
From the above analysis, it is found that the total time taken for the vehicle to stop ist 2 -t 1 。
S53, estimating the parking capacity of the vehicle according to the obtained vehicle information;
and estimating the parking capacity of the vehicle according to the constraint relation, wherein the estimation is represented as:
wherein the content of the first and second substances,Score i indicating a parking capability;、、is a weighting coefficient;arepresenting the parking difficulty coefficient of the remaining parking spaces;w、Lrespectively representing the width and length of the vehicle;T p indicating a preset parking time, if the parking is completed within a reference parking durationT p Is 0.Score i A larger value indicates a stronger stopping ability.
The estimation of the parking capability of the vehicle in step S5 further includes the step of generating the parking capability for each parking of the vehicleScore i Storing the data in vehicle database, and storing the vehicles in the databaseC i All parking capabilities ofScore i And calculating an average value as a reference value recommended by the parking space during the next parking, wherein the reference value is represented as:
wherein the content of the first and second substances, coreindicating vehiclesC i Historical average of all stopping ability.
Parking ability score generated at each parkingScore i And storing the parking capacity scores into a database, and scoring and averaging all the historical parking capacities of the vehicle to obtain a reference value recommended by the parking space at the next parking.
If it isRecommending parking stalls with small parking difficulty; if it isRecommending parking spaces in the parking difficulty; if it isAnd recommending parking spaces with high parking difficulty. Wherein the content of the first and second substances,d 2 representing a first preset threshold value of parking difficulty;d 3 a second preset threshold indicative of the difficulty of parking.
This embodiment can be after the vehicle gets into the parking area at every turn, can be to the video of parkking of record vehicle, then carry out the analysis to the video of parkking, obtain the ability of parkking at every turn of this vehicle for provide the reference for the following recommended parking stall.
In this embodiment, the vehicle is identified by the camera device arranged at the parking spaceC i After the parking space is provided, starting a timing module and starting timing;
and judging whether the time recorded in the timing module reaches the preset time, if so, providing the parking space lower than the current parking difficulty coefficient for the vehicle again through voice prompt.
A monitoring camera and a voice prompt loudspeaker are installed above each parking space in the parking lot. At first entry of vehicleDuring this parking area, through the monitoring camera real time monitoring vehicle's of this parking stall top parking condition. If the fact that the vehicle starts to drive into the parking space is found, the camera identifies the license plate information of the vehicle, the system starts to time through the timing module, and if the parking time exceeds the parking time preset by the systemT p If the current vehicle is not parked, the current driver is shown to be difficult to park the vehicle in the provided parking space, and the user is reminded according to the remaining situation of the existing parking space. And a parking space which is lower than the current parking grade difficulty is newly planned for the user. The reminding form is prompted by a voice prompt loudspeaker above the parking space, and a parking route of a new parking space is provided for the parking space through an indication display screen (the indication display screen is provided with a license plate number of the parking space).
In step S6, when the image pickup device provided at the parking space acquires the vehicleC i After completely entering the provided parking space, the vehicle is finishedC i And recommending the parking space.
When being arranged in a parking spaceP i And after the camera acquires that the vehicle completely enters the parking space and stops the vehicle, storing the acquired video in the system.
When the vehicle is runningC i When the vehicle enters the parking lot and parks at each later time, the vehicle is identified through a camera at an entrance, and if the identified information is stored in a database with the information beforeAAnd if the information of the vehicle is matched, a proper parking space is recommended through corresponding calculation according to the historical parking capacity of the vehicle.
Compared with the prior art, the method and the device can estimate the parking capacity of the vehicle by utilizing technologies such as deep learning, machine vision and image processing, recommend a proper parking space, improve user experience and reasonably utilize parking resources.
Example two
The parking capacity estimation and berth recommendation method based on image processing provided by the embodiment is different from the first embodiment in that:
the system in this embodiment is also used to charge the vehicle for parking.
In bookIn an embodiment, step S1 of the first embodiment further includes recording the vehicleC i Time of entry to facilitate subsequent calculation of a charge for the vehicle.
Further included after step S6 is:
s7, when the vehicle is identifiedC i Recording vehicles when leaving parking lotC i Time of departure, combined with vehiclesC i Determining vehicle time of entryC i According to the determined parking time length to the vehicleC i And (5) carrying out parking charge.
When the vehicle needs to leave, the vehicle is driven out from the current parking space to reach the exit of the parking lot, the camera arranged at the exit of the parking lot identifies the current vehicle and records the leaving time, the system calculates the parking time of the vehicle in the parking lot by combining the entering time of the vehicle, and the vehicle is charged for parking according to the charging standard of the parking lot.
In this embodiment, this system with can be connected with user's mobile terminal, and install the APP of this system in user's mobile terminal, then take time when the payment parking, if the user has opened "face payment function" in APP, then the parking charging system carries out face identification to the driver, can carry out face payment when face identification, accomplishes the parking charge of this time.
The rest of the contents are similar to those of the embodiments, and are not described in detail herein.
This embodiment provides the parking charge to the vehicle, improves parking system more, is close to the parking area of reality more.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. A parking capacity estimation and berth recommendation method based on image processing is characterized by comprising the following steps:
s1, identifying vehicle information entering a parking lot, and storing the vehicle information in a database;
s2, judging whether the current vehicle is in the initial parking state or not according to the recognized vehicle information, and if so, executing a step S3; if not, directly providing a proper parking space;
s3, comparing the recognized vehicle information with the remaining parking space data to obtain a proper parking space of the current vehicle, and providing the obtained parking space for the vehicle;
s4, judging whether the vehicle reaches the provided parking space, if so, executing a step S5;
s5, recording a parking picture of the vehicle in real time by a camera device arranged at the parking place, and storing a video formed by the recorded parking picture in a database so as to estimate the parking capacity of the vehicle;
and S6, after the camera device arranged at the parking place acquires that the vehicle completely enters the provided parking place, the recommendation of the parking place of the vehicle is completed.
2. The image-processing-based parking capacity estimation and berth recommendation method according to claim 1, wherein the step S2 of directly providing the appropriate parking space specifically comprises: and if the current vehicle is not the initial parking, combining the historical parking capacity of the vehicle stored in the database to provide a proper parking space.
3. The image-processing-based parking capacity estimation and berth recommendation method according to claim 1, wherein the vehicle information in step S3 includes license plate, logo, model; the remaining parking space data comprise a parking difficulty coefficient of the remaining parking space and a parking number corresponding to the parking difficulty coefficient, and the parking difficulty coefficient comprises a parking space with large parking difficulty, a parking space with large parking difficulty and a parking space with small parking difficulty.
4. The image-processing-based parking capacity estimation and berth recommendation method according to claim 3, wherein the step S6 is preceded by the steps of:
after the camera device arranged at the parking place identifies that the vehicle reaches the provided parking place, a timing module is started and timing is started;
and judging whether the time recorded in the timing module reaches the preset time, if so, providing the parking space lower than the current parking difficulty coefficient for the vehicle again through voice prompt.
5. The image-processing-based parking capacity estimation and berth recommendation method according to claim 4, wherein the estimating of the parking capacity of the vehicle in step S5 specifically comprises:
s51, training a convolutional neural network model for detecting a vehicle frame and a parking space frame in advance;
s52, inputting the parking video of the vehicle to be detected into the trained convolutional neural network model for detection to obtain detected vehicle information;
s53, estimating the parking capacity of the vehicle according to the obtained vehicle information, wherein the estimation is represented as:
wherein the content of the first and second substances,Score i indicating a parking capability;、、is a weighting systemCounting;arepresenting the parking difficulty coefficient of the remaining parking spaces;w、Lrespectively representing the width and length of the vehicle;T p representing a preset parking time;t 1 indicating the time to start parking;t 2 indicating the time to end the stop.
6. The image-processing-based parking capacity estimation and berth recommendation method according to claim 5, wherein the step S52 is specifically as follows:
s521, detecting the first time in the parking video through the trained convolutional neural network model at each preset intervaljFrame vehicle frame information andjframing parking space frame information;
s522, calculating the detected firstjFrame intersection ratio of vehicle frame and parking space frameIOUExpressed as:
wherein the content of the first and second substances,representing the intersection of the predicted vehicle frame and the predicted parking space frame;representing a union of the predicted vehicle frame and the predicted parking space frame;area(C j )representing a vehicle frame;area(P j )showing a parking space frame;C j represents a vehicle;P j indicating a parking space;
s523, judging the result obtained by calculationIOUIf the value is greater than zero, if so, the value will beIOUValue put inS i Performing the following steps; wherein the content of the first and second substances,denotes the firstiN in one videoIOUA value of (d);
s524, putting the time point of each detection intoT i Performing the following steps; wherein the content of the first and second substances,,T i of (1) andS i the elements in (1) correspond one to one;
s525. pairS i The data in (1) is analyzed to obtain an analysis result.
7. The image-processing-based parking capacity estimation and berth recommendation method according to claim 5, wherein the step of estimating the parking capacity of the vehicle in step S5 further comprises generating the parking capacity for each parking of the vehicleScore i Storing in a database, and determining all parking capabilities of vehicles in the databaseScore i And calculating an average value as a reference value recommended by the parking space during the next parking, wherein the reference value is represented as:
8. The image-processing-based parking capacity estimation and berth recommendation method according to claim 1, further comprising recording the time of vehicle entering in step S1.
9. The image-processing-based parking capacity estimation and berth recommendation method according to claim 8, further comprising, after step S6:
and S7, when the vehicle is identified to run out of the parking lot, recording the time of the vehicle running out, determining the parking time of the vehicle by combining the vehicle entering time, and charging for parking the vehicle according to the determined parking time.
10. The image-processing-based parking capacity estimation and berth recommendation method according to claim 9, wherein the step S4 is preceded by the steps of:
the vehicle is provided with a parking route through the display screen.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010360115.7A CN111260954B (en) | 2020-04-30 | 2020-04-30 | Parking capacity estimation and parking space recommendation method based on image processing |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010360115.7A CN111260954B (en) | 2020-04-30 | 2020-04-30 | Parking capacity estimation and parking space recommendation method based on image processing |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111260954A true CN111260954A (en) | 2020-06-09 |
CN111260954B CN111260954B (en) | 2020-08-14 |
Family
ID=70951682
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010360115.7A Active CN111260954B (en) | 2020-04-30 | 2020-04-30 | Parking capacity estimation and parking space recommendation method based on image processing |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111260954B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111982137A (en) * | 2020-06-30 | 2020-11-24 | 北京百度网讯科技有限公司 | Method, device, equipment and storage medium for generating route planning model |
CN112820141A (en) * | 2021-01-14 | 2021-05-18 | 浙江吉利控股集团有限公司 | Parking space detection method and system |
CN113516852A (en) * | 2021-07-22 | 2021-10-19 | 珠海小可乐科技有限公司 | Multi-parking-space multi-target vehicle parking identification method and system |
CN117133144A (en) * | 2023-07-12 | 2023-11-28 | 中交一公局第六工程有限公司 | Smart city parking lot parking space prediction method and system based on Internet of things |
WO2024116239A1 (en) * | 2022-11-28 | 2024-06-06 | 日本電気株式会社 | Parking lot reservation system, information processing device, information processing method, and recording medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102622909A (en) * | 2012-04-10 | 2012-08-01 | 北京工业大学 | Method for guiding path corresponding to parking space of cab driving target area in parking lot |
CN107680401A (en) * | 2017-10-17 | 2018-02-09 | 长沙理工大学 | Parking space satisfaction evaluation method based on interval two-type fuzzy set |
CN108922231A (en) * | 2018-07-09 | 2018-11-30 | 胡佂宇 | Intelligent parking space based on block chain |
CN109191891A (en) * | 2018-09-05 | 2019-01-11 | 胡峰源 | The parking position monitoring system shot based on planar bar code technology and unmanned plane |
CN109191896A (en) * | 2018-10-17 | 2019-01-11 | 南京邮电大学 | Personalized parking stall recommended method and system |
CN109410630A (en) * | 2018-09-05 | 2019-03-01 | 西安艾润物联网技术服务有限责任公司 | Parking stall method for pushing and Related product based on driver information |
US10343631B2 (en) * | 2016-12-28 | 2019-07-09 | Uber Technologies, Inc. | Decreasing autonomous vehicle power consumption |
-
2020
- 2020-04-30 CN CN202010360115.7A patent/CN111260954B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102622909A (en) * | 2012-04-10 | 2012-08-01 | 北京工业大学 | Method for guiding path corresponding to parking space of cab driving target area in parking lot |
US10343631B2 (en) * | 2016-12-28 | 2019-07-09 | Uber Technologies, Inc. | Decreasing autonomous vehicle power consumption |
CN107680401A (en) * | 2017-10-17 | 2018-02-09 | 长沙理工大学 | Parking space satisfaction evaluation method based on interval two-type fuzzy set |
CN108922231A (en) * | 2018-07-09 | 2018-11-30 | 胡佂宇 | Intelligent parking space based on block chain |
CN109191891A (en) * | 2018-09-05 | 2019-01-11 | 胡峰源 | The parking position monitoring system shot based on planar bar code technology and unmanned plane |
CN109410630A (en) * | 2018-09-05 | 2019-03-01 | 西安艾润物联网技术服务有限责任公司 | Parking stall method for pushing and Related product based on driver information |
CN109191896A (en) * | 2018-10-17 | 2019-01-11 | 南京邮电大学 | Personalized parking stall recommended method and system |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111982137A (en) * | 2020-06-30 | 2020-11-24 | 北京百度网讯科技有限公司 | Method, device, equipment and storage medium for generating route planning model |
US11698262B2 (en) | 2020-06-30 | 2023-07-11 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method and apparatus for generating route planning model, and storage medium |
CN112820141A (en) * | 2021-01-14 | 2021-05-18 | 浙江吉利控股集团有限公司 | Parking space detection method and system |
CN113516852A (en) * | 2021-07-22 | 2021-10-19 | 珠海小可乐科技有限公司 | Multi-parking-space multi-target vehicle parking identification method and system |
WO2024116239A1 (en) * | 2022-11-28 | 2024-06-06 | 日本電気株式会社 | Parking lot reservation system, information processing device, information processing method, and recording medium |
CN117133144A (en) * | 2023-07-12 | 2023-11-28 | 中交一公局第六工程有限公司 | Smart city parking lot parking space prediction method and system based on Internet of things |
CN117133144B (en) * | 2023-07-12 | 2024-03-12 | 中交一公局第六工程有限公司 | Smart city parking lot parking space prediction method and system based on Internet of things |
Also Published As
Publication number | Publication date |
---|---|
CN111260954B (en) | 2020-08-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111260954B (en) | Parking capacity estimation and parking space recommendation method based on image processing | |
WO2020248386A1 (en) | Video analysis method and apparatus, computer device and storage medium | |
CN111009151B (en) | Parking space recommendation method, storage medium and terminal device | |
JP5368105B2 (en) | Parking management system | |
CN111429726B (en) | Monitoring video illegal parking vehicle detection and management method and corresponding system | |
WO2019223655A1 (en) | Detection of non-motor vehicle carrying passenger | |
CN107316010A (en) | A kind of method for recognizing preceding vehicle tail lights and judging its state | |
CN110853391A (en) | Intelligent shared parking system | |
CN111353369B (en) | Application method and system of urban road side parking high-level video in auxiliary criminal investigation | |
CN109741628B (en) | Intelligent parking route planning method | |
CN104239847B (en) | Driving warning method and electronic device for vehicle | |
CN114419924B (en) | AI application control management system based on wisdom city | |
CN107845263A (en) | A kind of Internet of Things management platform applied to parking lot | |
CN112347864A (en) | Method, device, equipment and system for sensing and inducing rail transit passenger flow | |
CN105909116A (en) | Vehicle door control method, device and system | |
CN110175533A (en) | Overpass traffic condition method of real-time, device, terminal and storage medium | |
CN110175654A (en) | A kind of update method and system of track road sign | |
JP2022003548A (en) | Recognition system and program for the same | |
CN106355329A (en) | Method and system for testing sign aligning ability of driver | |
CN113407871A (en) | Boarding point recommendation method and device, electronic equipment and readable storage medium | |
WO2023246720A1 (en) | Roadside parking detection method, roadside parking system, and electronic device | |
CN116167536B (en) | Intelligent parking management method based on time period learning optimization | |
CN110046535B (en) | Intelligent travel time prediction system, method and storage medium based on machine learning | |
CN115131986A (en) | Intelligent management method and system for closed parking lot | |
CN112362076B (en) | Intelligent display method and related device for navigation information of non-recommended road section |
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 |