CN107967817A - Intelligent managing system for parking lot and method based on multi-path camera deep learning - Google Patents
Intelligent managing system for parking lot and method based on multi-path camera deep learning Download PDFInfo
- Publication number
- CN107967817A CN107967817A CN201711144185.3A CN201711144185A CN107967817A CN 107967817 A CN107967817 A CN 107967817A CN 201711144185 A CN201711144185 A CN 201711144185A CN 107967817 A CN107967817 A CN 107967817A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- parking
- parking lot
- module
- server
- 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.)
- Pending
Links
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
- G08G1/144—Traffic control systems for road vehicles indicating individual free spaces in parking areas with means giving the indication of available parking spaces on portable or mobile units, e.g. personal digital assistant [PDA]
-
- 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
-
- 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
- G08G1/145—Traffic control systems for road vehicles indicating individual free spaces in parking areas where the indication depends on the parking areas
- G08G1/148—Management of a network of parking areas
-
- 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
- G08G1/149—Traffic control systems for road vehicles indicating individual free spaces in parking areas coupled to means for restricting the access to the parking space, e.g. authorization, access barriers, indicative lights
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Business, Economics & Management (AREA)
- Finance (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
Present disclose provides a kind of intelligent managing system for parking lot of multi-path camera deep learning, including：Server end, including：Data acquisition module, the vehicle in parking lot and the video and/or view data in each orientation of Parking bit boundary are gathered by using multi-path camera；Network transmission module, for the automobile video frequency collected and/or view data to be uploaded to hind computation module；And hind computation module, for the processing of parking vehicle information, including：Deep learning model training submodule and vehicle behavior judging submodule.The advantages that disclosure improves neural network recognization rate and stability, and adaptable strong, easy to install, cheap, anti-electromagnetic interference capability is strong.
Description
Technical field
This disclosure relates to parking lot intelligent management field, more particularly to a kind of parking based on multi-path camera deep learning
Field intelligent management system and method.
Background technology
In recent years, as the fast development in city, vehicle population increase rapidly, the management in parking lot and stopping for car owner
Car problem is increasingly prominent, such as people are frequently encountered can not find suitable parking lot and parking stall in a short time, or
Situations such as empty parking space or outlet can not be found in strange parking lot, this causes parking to become one and take very much, make us head
The thing of pain, significantly reduces the life efficiency of people.
And it is current, the management in parking lot still mainly uses artificial or semi-artificial management mode, and most parking
All there is no navigation system, it based on indicator light, can only lean on car owner oneself to fish for room, this not only increases mainly with road sign
Add and sought a time, and be easy to cause inner part of parking lot congestion, or even got into an accident.Meanwhile occur in docking process
The abnormal conditions such as vehicle is stolen, destroys, scratches, colliding also occur often, but its caused dispute and evidence obtaining difficulty also tend to
Make car owner and manager's headache.
Disclosure
(1) technical problems to be solved
Present disclose provides a kind of intelligent managing system for parking lot and method of multi-path camera deep learning, with least portion
Decompose technical problem certainly set forth above.
(2) technical solution
According to one aspect of the disclosure, there is provided a kind of parking lot intelligent management system of multi-path camera deep learning
System, including：Server end, the server end include：Data acquisition module, by using multi-path camera collection parking lot
The video and/or view data in each orientation of vehicle and Parking bit boundary；Network transmission module, for that will gather
To automobile video frequency and/or view data be uploaded to hind computation module；And hind computation module, for parking vehicle information
Processing, including：Deep learning model training submodule, by the multi-path camera in advance to different brands, vehicle models
The view data in each orientation, parking lot road, parking stall region video and/or view data, and for abnormal row
It is acquired for the video and/or view data of judgement, gained video and/or image data are carried out marshalling carries out deep learning
Training, deep neural network model is generated after training；And vehicle behavior judging submodule, according to the nerve net generated after training
Network model is monitored and judges to vehicle behavior.
In the disclosure some embodiments, the hind computation module includes：Vehicle parking submodule, for based on multichannel
The deep neural network of camera realizes automatic identification and the management of parking position, including according to user's requesting query parking lot
Parking condition, judge the vehicle stopped state and confirm stop after start Fare determined by travel time；Vehicle location and navigation submodule
Block, using Car license recognition and computer vision as core, after vehicle enters passage, multi-cam Real-time captured video signal will
Real-time video information is transmitted in system and is handled, by directly measuring car plate size and/or by passage and both sides
Label is measured indirectly, is obtained relative position and distance of the vehicle from different cameras, is obtained the car of specific license plate number
In the position in parking lot, so as to obtain the positional information of vehicle in all passages in parking lot at different moments and provide navigation letter
Breath；And abnormal behaviour analysis submodule, early warning is carried out to the abnormal conditions occurred in parking lot.
In the disclosure some embodiments, the vehicle parking submodule of the hind computation module includes：Data model is instructed
Practice sub- sub-module, the vehicle marked in the training part gathered data sample of the vehicle parking submodule is overall and its special
Sign, and by multi-layer C NN convolutional neural networks, for the global and local parking stall in parking lot train to obtain comprising various brands,
The deep neural network model of each orientative feature of vehicle models；Activity recognition predicts sub- sub-module, the vehicle parking submodule
The identification division of block includes two components of global and local, uses the depth nerve net based on multi-path camera of training gained
Network, obtains the positional information and the local parking information of each parking stall of global vehicle, if both matching degrees exceed certain threshold value
Think credible result and export as a result, the partial component of identification division judges whether vehicle correctly stops according to vehicle with parking stall feature
It is put in specified parking stall；
The abnormal behaviour analysis submodule of the hind computation module includes：Data model trains sub- sub-module, by more
Road camera carries out image data acquiring to normal behaviour in target area and improper behavior from different perspectives, will collect
Multiple image as a sample, and using data sample as training data input, train to obtain by deep neural network
The model of deep neural network；Activity recognition predicts sub- sub-module, and the new data that parking lot multi-path camera is gathered inputs instruction
Practice in gained deep neural network model, and judge its behavior pattern；If being judged as improper behavior, the datagram is sent
Picture and relevant information are inquired about to administrator with standby user.
In the disclosure some embodiments, the data acquisition module includes：Hardware interface submodule, for including shooting
The calling of head；Human-computer interaction submodule, for often locating camera real time monitoring image information, vehicle parking in each parking stall
What state record information, empty parking space information and early warning information recorded transfers and shows.
In the disclosure some embodiments, the intelligent managing system for parking lot, further includes client, the client
Including：Empty parking space enquiry module, for inquiring about parking lot empty parking space quantity and position；Parking stall positions and road guide module, uses
In the positioning of acquisition empty parking space and road guide information；Parking timing payment module, for checking the parking duration to park cars
And Parking Fee, and realize self-service online payment.
In the disclosure some embodiments, the hind computation module includes super calculating cluster server, the super calculation cluster
Server includes multinuclear and many-core parallel server, for providing：Service is calculated, including：The depth of video and/or view data
Study and vehicle characteristics extraction, compare；Storage service, including：The real-time storage of monitor video, and go out in network transmission process
When existing packet loss or network failure, the interim storage of monitor video；And resources regulation service, including：The money of computer cluster
Source is allocated, and avoids the occurrence of the situation that process is blocked, is lined up.
According to another aspect of the disclosure, there is provided a kind of parking lot intelligent management side of multi-path camera deep learning
Method, comprises the following steps：When server background computing module vehicle parking submodule receives the parking inquiry request of user,
Vacancy of parking lots inquiry is carried out, and information is pushed to user；The vehicle parking submodule of server background computing module judges
Whether the vehicle for reaching Entrance allows access into；Server background computing module is the vehicle distribution for allowing access into parking lot
Parking stall, vehicle location and d navigation submodule provide empty parking space navigation information, and abnormal behaviour analyzes submodule BOB(beginning of block) to vehicle
Abnormal behavior situation is monitored；Server background server vehicle parking submodule detects whether reach the vehicle for specifying parking stall
Park on request, and start Fare determined by travel time after vehicle stops well；If server receives the end cutoff command of user's submission, after
The vehicle location of platform computing module and navigation submodule provide outlet navigation information to the user；At server identification parking exit
Vehicle license plate number information, and carry out Parking Fee clearing.
In the disclosure some embodiments, the process of vacancy of parking lots inquiry includes：Server receives user and passes through visitor
The inquiry request that the empty parking space enquiry module at family end is sent, calls the vehicle parking submodule inquiry periphery of hind computation module pre-
Determine the parking condition in the parking lot of the intelligent managing system for parking lot equipped with multi-path camera deep learning in scope, and by empty wagons
Position information is to client push.
In the disclosure some embodiments, the parking lot intelligent management, further comprises：Stop when vehicle enters
During parking lot, server identifies the license plate number of the vehicle first, and verification is compared with entering the vehicle license plate number in parking lot,
At the same time by directly measuring car plate size and/or measured indirectly by passage and both sides label, obtain vehicle and
The relative distance of each camera is so as to judge the real time position of vehicle, wherein direct beasurement base principle of computer vision is by car plate
Size calculates the distance of vehicle and camera, indirectly measurement then advance Measurement channel and both sides label and camera away from
From, and pushed away the location information of vehicle by the distance of the relation of vehicle and label measuring and calculating vehicle and camera, last server
The client of user is sent to, guiding vehicle drives to corresponding parking stall.
In the disclosure some embodiments, the processing step that vehicle enters behind parking lot includes：When user reaches parking lot
During entrance, server is by the camera in data acquisition module, automobile video frequency, image letter of the extraction request into parking lot
Breath, hind computation module is sent to by network transmission module, using the deep neural network model identification generated after training simultaneously
Compare whether the vehicle meets type of vehicle standard into the parking lot；Standard compliant vehicle allows access into, and distributes sky
Parking stall；Otherwise it is rejected for entry into and gives information alert, manual identified is carried out to the vehicle at this time, if manual identified result is to meet
Standard is parked, then manual identified result and the vehicle video and/or view data are imported into hind computation module intensified learning；If
Manual identified result is not meet the standard of parking；If the vehicle allows access into parking lot, server will allow to client push
Entry instruction, and the vehicle location to client and road guide module push empty parking space navigation information, guide the vehicle to drive towards
The parking stall of server-assignment, after vehicle enters parking lot, server just calls the abnormal behaviour of hind computation module to analyze
Submodule BOB(beginning of block) detects in parking lot whether abnormal conditions occur in real time, and when there are abnormal conditions, server will be to administrator
Warning message is pushed after user reaches and specifies empty parking space with user, and server can be real by the camera in data acquisition module
When capture the boundary line on the parking stall and the stand of vehicle, and call the vehicle parking submodule block analysis of hind computation module
Judge whether the vehicle has been parked in specified region, if user is parked as requested, by the parking stall Status Change
To have taken, and the amount information that the duration of parking and needs are paid is sent to client, user is stopped by client
The car module that pays fees by the hour is inquired about；If vehicle is not parked by regulation, alarm is sent, or installs and has in parking lot
The loudspeaker of prompt facility, reminds user to park again, if not parking again as requested within a specified time still, server
The situation for exception and is sent to system manager by the parking stall Status Change, while gives the certain punishment of user；When
When user's pick-up is left, if server receives the end cutoff command of client submission, positioned to the empty parking space of client
And road guide module provides real-time navigation information, guiding user leaves parking lot；When user reaches parking exit, service
Device will identify vehicle license plate number and calculate vehicle parking expense, and pushes information to client and be used to provide on-line payment.
(3) beneficial effect
It can be seen from the above technical proposal that parking lot intelligent management system of the disclosure based on multi-path camera deep learning
System and method at least have the advantages that one of them：
(1) relative to traditional deep neural network based on single camera, as a result of the depth of multi-path camera
Automatic identification and the management of neural fusion parking position are spent, gained video and/or image data are organized into groups, then will
Training input of each group of data as deep neural network, so that neural network recognization rate and stability are more effectively improved, and
Solve due to vehicle park angle, the influence for the generation such as object blocks, daytime or night uneven illumination are even；
(2) being accurately positioned, manage and navigating for vehicle in parking lot is realized by multi-path camera, and to docking process
The analysis and early warning for the abnormal conditions such as the vehicle of middle appearance is stolen, destroys, scratches, colliding, therefore adaptable strong, installation makes
With it is convenient, cheap, anti-electromagnetic interference capability is strong the advantages that.
Brief description of the drawings
Fig. 1 is the intelligent managing system for parking lot structure diagram based on deep learning of the embodiment of the present disclosure；
Fig. 2 is the parking lot multi-path camera data acquisition schematic diagram of the embodiment of the present disclosure；
Fig. 3 is that the server end hind computation vehicle module of the embodiment of the present disclosure parks submodule flow chart；
Fig. 4 is the positioning of server end hind computation vehicle module and the d navigation submodule flow chart of the embodiment of the present disclosure；
Fig. 5 is that the server end hind computation module abnormal behaviour of the embodiment of the present disclosure analyzes submodule flow chart；
Fig. 6 is the parking lot intelligent management flow based on multi-path camera deep learning algorithm of the embodiment of the present disclosure
Figure.
Embodiment
The disclosure a kind of intelligent managing system for parking lot and management method based on multi-path camera deep learning, it is described
The system includes server end and client, and server end is by data acquisition module, network transmission module, hind computation module three
Part forms；Client is by empty parking space enquiry module, empty parking space positioning and road guide module and parking timing payment module
Formed etc. three parts.Video of the server end first by the various brands of data collecting module collected, each orientation of vehicle models
And/or image, and parking lot road, video and/or the view data such as regional edge boundary line on parking stall, and by institute's gathered data
For system deep learning training, deep neural network model is generated, user realizes that information is handed over using client and server
Mutually.The disclosure can efficiently solve the problems such as being accurately positioned, manage and navigate of current Parking position.
For the purpose, technical scheme and advantage of the disclosure are more clearly understood, below in conjunction with specific embodiment, and reference
Attached drawing, is further described the disclosure.
Disclosure some embodiments will be done with reference to appended attached drawing in rear and more comprehensively describe to property, some of but not complete
The embodiment in portion will be illustrated.In fact, the various embodiments of the disclosure can be realized in many different forms, and should not be construed
To be limited to this several illustrated embodiment；Relatively, there is provided these embodiments cause the disclosure to meet applicable legal requirement.
In first exemplary embodiment of the disclosure, there is provided a kind of parking based on multi-path camera deep learning
Field intelligent management system.Fig. 1 is parking lot intelligent management system of the first embodiment of the present disclosure based on multi-path camera deep learning
The structure diagram of system.As shown in Figure 1, intelligent managing system for parking lot bag of the disclosure based on multi-path camera deep learning
Include：Server end 10 and client 20.The server end 10 include data acquisition module 101, network transmission module 102 and after
Platform computing module 103, client 20 include empty parking space enquiry module 201, empty parking space positioning and road guide module 202 and stop
Car pays fees by the hour module 203.
Individually below to each group of intelligent managing system for parking lot of the present embodiment based on multi-path camera deep learning
Into being partly described in detail.
In the intelligent managing system for parking lot server end 10 based on multi-path camera deep learning：
Data acquisition module 101 by using multi-path camera collection be used for deep neural network training various brands,
The video and/or view data in each orientation of vehicle models and Parking bit boundary, and for comparison request into
Enter the video and/or view data of the vehicle in parking lot etc..Data acquisition module 101 includes two submodules：Submodule one is
Hardware interface submodule, including calling of camera etc., the camera used in the disclosure is either parking lot management side
In the existing video monitoring system of monitoring camera or city that parking lot periphery is set, generally low-light (level) figure is used
As sensor, HD video being supported, realizing the network low-bandwidth transmission of HD image, support monitors round the clock, its main feature
Have：Support wireless network, possess the feature that low in energy consumption, fever is low, delay is short, resolution is high；Submodule two is human-computer interaction
Module, is mainly used for every place's camera real time monitoring image information, vehicle parking state record information, sky in each parking stall
The information record such as parking space information and early warning being transferred and showing.
Network transmission module 102 is used to the automobile video frequency collected and/or view data being uploaded to hind computation module
103, and comparison result is sent to 20 module of client in real time and including in the operation interface of data acquisition module 101.Should
Module can be transmitted realization by private line network and internet, and private line network transmission is stablized, strong security, is used suitable for protection
Family privacy；Internet is widely distributed, and cheap, is widely used in various situations, and is used for the encipherment protection of internet
Family privacy situation is, it is necessary to add encryption and decryption device.
Hind computation module 103 is the core of the disclosure, the processing for parking lot information of vehicles.Hind computation mould
Block 103 is mainly made of super cluster server of calculating, it mainly includes multinuclear and many-core parallel server, and cluster server provides meter
The service of calculation, storage service, resources regulation service and transmission service.Wherein, calculating service is mainly used for video and/or image information
Deep learning and vehicle characteristics extraction, compare；Storage service is mainly used for two aspect storages, on the one hand stores monitoring in real time
Video, when on the one hand being responsible for packet loss or network failure occur in network transmission process, interim storage video；Resources regulation service
It is mainly used for the resource allocation of computer cluster, avoids the occurrence of the situation that process is blocked, is lined up.
Hind computation module 103 includes three submodules：Vehicle parking submodule, vehicle location and d navigation submodule and
Abnormal behaviour analysis submodule etc..Wherein：
Vehicle parking submodule mainly using the deep neural network based on multi-path camera realize parking position from
Dynamic identification and management.As shown in Fig. 2, being different from traditional deep neural network based on single camera, the disclosure uses more
Road camera is carried out at the same time collection, and all cameras are divided into one in the video obtained by synchronization collection and/or image data
Group is organized into groups, then is inputted each group of data as the training of deep neural network, so as to effectively improve neural network recognization
Rate and stability, and solve due to vehicle park angle, the shadow for the generation such as object blocks, daytime or night uneven illumination are even
Ring.As shown in figure 3, vehicle parking submodule is broadly divided into training and identification two parts.Training part collection mass data sample
In the vehicle entirety and its feature that mark, it is global and local for parking lot then by multi-layer C NN convolutional neural networks
Train to obtain comprising various brands, the deep neural network model of each orientative feature of vehicle models in parking stall.Identification division includes
Two components of global and local, can be used the deep neural network based on multi-path camera of training gained, obtain global vehicle
Positional information and each parking stall local parking information, credible result and defeated is thought if both matching degrees exceed certain threshold value
Go out result.The partial component of identification division can judge whether vehicle correctly docks at specified parking stall according to vehicle and parking stall feature.
Vehicle location and d navigation submodule are using Car license recognition and principle of computer vision as core.Car license recognition is on the market
Mature technology, be widely used to parking lot management, can highly precisely identify vehicle.Since camera position is fixed, because
This can obtain the actual position of vehicle according to the relative distance of vehicle and camera, realize parking navigation.Vehicle and camera
Distance can be obtained by directly measuring and measuring two ways indirectly.In directly measuring, since vehicle license plate size has unification
Standard, therefore the car plate size that can be shot according to principle of computer vision by camera calculates vehicle and camera
Distance；Indirectly in measurement, since passage both sides is comprising all kinds of marks such as parking stall, line, each mark can be measured in advance
With the distance of camera, vehicle location is realized further according to the relative position of vehicle and each mark.Vehicle location and navigation it is specific
Implement as shown in figure 4, to realize navigation feature using multi-cam, the system can be arranged as required to image in programming and distribution
The position of head and number, such as bidirectional camera shooting head can be laid in straight channel, in fork on the road, multi-cam can be set.When vehicle into
After entering passage, multi-cam can Real-time captured video signal, real-time video information is transmitted in system and is handled.System can
By directly measuring car plate size and/or being measured indirectly by passage and both sides label, obtain the vehicle with not
With the relative position and distance of camera.Specific license plate number vehicle can be obtained in this way in the position in parking lot, so as to obtain
Obtain the positional information of vehicle in all passages in parking lot at different moments.
Abnormal behaviour analysis submodule can be to what is occurred in parking lot, and such as artificial theft, destroy, and vehicle is scratched, collided
Abnormal conditions carry out early warning.As shown in figure 5, abnormal behaviour analysis submodule is broadly divided into data model training and Activity recognition
Predict two parts.Training part is first by multi-path camera from different perspectives to normal behaviour in target area and improper
Behavior carries out image data acquiring, using the segment video (i.e. multiple image) collected as a sample, and by mass data
Sample is inputted as training data, trains to obtain the model of deep neural network by deep neural network.Identification division will stop
In the new data input training gained deep neural network model of parking lot multi-path camera collection, and judge its behavior pattern.If
It is judged as improper behavior, then sends the data image and relevant information to administrator, inquired about with standby user.
It is each to various brands, vehicle models in advance by data acquisition module 101 using multi-path camera above in each module
The view data in a orientation, parking lot road, video and/or the view data such as region on parking stall, and for abnormal behaviour
The video and/or view data of judgement are acquired, and are transmitted to progress deep learning training in hind computation module 103, instruction
The process that deep neural network model is generated after white silk is pretreatment.
The client 20 of the intelligent managing system for parking lot based on multi-path camera deep learning can be intelligent hand
The equipment such as machine or tablet computer, wherein smart mobile phone and tablet computer expert are downloaded frequently with Android or IOS operating system
And have registered with receive, the software of propelling data informational function, client 20 can real-time query, receive server end 10 count
The result transmitted after calculation.User can timely and accurately be inquired about by the modules of client 20 parking lot empty parking space quantity and
The information such as position, empty parking space positioning and road guide, while user can also pass through 20 parking timing payment module 203 of client
The parking duration and Parking Fee that park cars is checked at any time, and selection is paid online by the way that module progress is self-service when picking up the car
Take, save user time, improve out line efficiency.Manager can also set the pay charge way such as Bao Tian, monthly payment according to actual conditions, or
Good user is recorded to parking and gives the preferential measures such as discount.
So far, intelligent managing system for parking lot of the first embodiment of the present disclosure based on multi-path camera deep learning has been introduced
Finish.
In second exemplary embodiment of the disclosure, there is provided a kind of parking based on multi-path camera deep learning
Field intelligent management.Fig. 6 is the parking lot intelligent management based on multi-path camera deep learning algorithm of the embodiment of the present disclosure
Method flow diagram, as shown in fig. 6, a kind of parking lot intelligent management side based on multi-path camera deep learning that the disclosure proposes
Method, is realized especially by following steps：
Step S1, when server receives the parking inquiry request of user, carries out vacancy of parking lots inquiry, and by information
It is pushed to user.
When user has parking demand, server receives user and passes through the clients such as smart mobile phone or tablet computer 20
Empty parking space enquiry module 201 sends inquiry request, and the vehicle parking submodule periphery for calling hind computation module 103 is equipped with this
The parking condition in the parking lot of system, and by parking space information, such as taken, is idle and distributed and treat that information is pushed away to client 20
Send, shown after 20 receive information of client with graphics context mode to user.
Whether step S2, the vehicle that server is determined up to Entrance allow access into.
When user reaches Entrance, server by the camera in data acquisition module 101, extraction ask into
Enter automobile video frequency, the image information in parking lot, hind computation module 103 is sent to by network transmission module 102, utilizes training
The deep neural network model generated afterwards identifies and compares whether the vehicle meets type of vehicle standard into the parking lot.Symbol
The vehicle of standardization allows access into, and distributes empty parking space；Otherwise it is rejected for entry into and gives information alert, the vehicle is carried out at this time
Manual identified, if manual identified result is to meet the standard of parking, by manual identified result and the vehicle video and/or picture number
According to importing 103 intensified learning of hind computation module；If manual identified result is not meet the standard of parking.Especially, it is described artificial
Identification can be completed by parking lot management personnel.
Step S3, server are the vehicle distribution parking stall for allowing access into parking lot, there is provided empty parking space navigation information, and start
Vehicle behavior abnormal conditions are monitored.
If the vehicle allows access into parking lot, server will push to client 20 and allow access into instruction, and to client
20 vehicle location and road guide module push empty parking space navigation information, guide the vehicle to drive towards the parking of server-assignment
Position.Above-mentioned steps further comprise：Server identifies the license plate number of the vehicle first, and with entering the vehicle license plate in parking lot
Number verification is compared.At the same time according to principle of computer vision, the car plate size obtained according to multi-cam calculates vehicle
Relative position with each camera is so as to judge the real time position of vehicle.The location information of vehicle is pushed to use by last server
The client 20 at family, guiding vehicle drive to corresponding parking stall.
After vehicle enters parking lot, server just calls the abnormal behaviour of hind computation module 103 to analyze submodule and opens
Begin whether abnormal conditions occur in detection parking lot in real time, when there are abnormal conditions, such as vehicle drives in the wrong direction, and server will be to
Administrator pushes warning message with user.Above-mentioned when there are abnormal conditions, server can be such as artificial to steal to occurring in parking lot
Surreptitiously, destroy, the abnormal conditions such as vehicle is scratched, collided carry out early warning.Once vehicle is during parking lot is passed in and out, or is parking car
Situations such as scratching, collide is likely to occur during position, or artificial destruction, stealing are likely to occur during vehicle parking situations such as, is taken
Business device will push warning information to client 20, and associated video data of putting on record, and evidence is provided to solve a case.
Step S4, server detect whether the vehicle up to specified parking stall is parked on request, and start after vehicle stops well
Fare determined by travel time.
After user, which reaches, specifies empty parking space, server can be captured in real time by the camera in data acquisition module 101
The boundary line on the parking stall and the stand of vehicle, and call the vehicle parking submodule block analysis of hind computation module 103 to sentence
Whether the disconnected vehicle has been parked in specified region, if user is parked as requested, by the parking stall, Status Change is
It has been taken that, and the information such as amount of money that the duration of parking and needs are paid is sent to client 20, user is passed through client
20 parking timing payment module 203 is inquired about；If vehicle is not parked by regulation, alarm is sent, or in parking lot
Interior loudspeaker of the installation with prompt facility, reminds user to park again, if not stopping again as requested within a specified time still
Put, then the situation for exception and is sent to system manager by the parking stall Status Change by server, while gives user one
Fixed punishment.
Step S5, the user that server terminates cutoff command to submission provides outlet navigation information, and identifies exit car
License plate number is used with settlement of parking fee.
When user, which picks up the car, to be left, if server receives the end cutoff command of the submission of client 20, to client
20 empty parking space positioning and road guide module 202 provide real-time navigation information, and guiding user leaves parking lot, so as to reduce use
Find the time of outlet in family.When user reaches parking exit, server will identify vehicle license plate number and calculate vehicle parking
Expense, user may be selected the manually parking timing payment module 203 of payment or client 20 and carry out on-line payment.If server connects
The end cutoff command of the submission of client 20 is can not receive, then identifies vehicle license plate number at parking exit and charges to user.When
It by the Status Change of parking stall shared by the vehicle is empty parking space that user, which is completed after paying dues,.
In order to achieve the purpose that brief description, in above-described embodiment one, any technical characteristic narration for making same application is all
And in this, without repeating identical narration.
So far, the parking lot intelligent management of second embodiment of the present disclosure multi-path camera deep learning algorithm has been introduced
Finish.
The intelligent managing system for parking lot and management method based on multi-path camera deep learning that the disclosure provides, its
Purpose is to realize being accurately positioned, manage and navigating for vehicle in parking lot using multi-path camera, and to going out in docking process
The analysis and early warning for the abnormal conditions such as existing vehicle is stolen, destroys, scratches, colliding.It is adaptable it is strong, easy to install,
Cheap, the advantages that anti-electromagnetic interference capability is strong.The disclosure need not as earth-magnetism navigation technology to parking lot ground into
The extra construction of row, it is not required that allot positioning card to user as bluetooth location technology as radio frequency is positioned, can realize nothing substantially
People manages.It not only has a good real-time, and the mutual cooperation verification between multi-cam improves system redundancy and accurate
Property, earth-magnetism navigation technology also is far below with obvious price advantage, cost, since positioning card, its cost need not be configured
Also below radio frequency positioning and bluetooth location technology.The disclosure can use under outer indoors, different weather state of temperature.The system
Also can be used as utility car management system, such as shared vehicle, and the shared bicycle with nameplate number mark, shared electricity
Motor-car etc..
So far, attached drawing is had been combined the embodiment of the present disclosure is described in detail.It should be noted that in attached drawing or say
In bright book text, the implementation that does not illustrate or describe is form known to a person of ordinary skill in the art in technical field, and
It is not described in detail.In addition, the above-mentioned definition to each element and method be not limited in mentioning in embodiment it is various specific
Structure, shape or mode, those of ordinary skill in the art simply can be changed or replaced to it.
It should also be noted that, the direction term mentioned in embodiment, for example, " on ", " under ", "front", "rear", " left side ",
" right side " etc., is only the direction of refer to the attached drawing, is not used for limiting the protection domain of the disclosure.Through attached drawing, identical element by
Same or like reference numeral represents.When understanding of this disclosure may be caused to cause to obscure, conventional structure will be omitted
Or construction.
And the shape and size of each component do not reflect actual size and ratio in figure, and only illustrate the embodiment of the present disclosure
Content.In addition, in the claims, any reference symbol between bracket should not be configured to the limit to claim
System.
Furthermore word "comprising" does not exclude the presence of element or step not listed in the claims.Before element
Word "a" or "an" does not exclude the presence of multiple such elements.
In addition, unless specifically described or the step of must sequentially occur, there is no restriction in above institute for the order of above-mentioned steps
Row, and can change or rearrange according to required design.And above-described embodiment can based on design and reliability consideration, that
This mix and match is used using or with other embodiment mix and match, i.e., the technical characteristic in different embodiments can be freely combined
Form more embodiments.
Algorithm and display be not inherently related to any certain computer, virtual system or miscellaneous equipment provided herein.
Various general-purpose systems can also be used together with teaching based on this.As described above, required by constructing this kind of system
Structure be obvious.In addition, the disclosure is not also directed to any certain programmed language.It should be understood that it can utilize various
Programming language realizes content of this disclosure described here, and the description done above to language-specific is to disclose this public affairs
The preferred forms opened.
The disclosure can be by means of including the hardware of some different elements and by means of properly programmed computer
Realize.The all parts embodiment of the disclosure can be with hardware realization, or to be run on one or more processor
Software module is realized, or is realized with combinations thereof.It will be understood by those of skill in the art that can be in practice using micro-
Processor or digital signal processor (DSP) are some or all in the relevant device according to the embodiment of the present disclosure to realize
The some or all functions of component.The disclosure be also implemented as a part for performing method as described herein or
Whole equipment or program of device (for example, computer program and computer program product).Such journey for realizing the disclosure
Sequence can store on a computer-readable medium, or can have the form of one or more signal.Such signal can
Obtained with being downloaded from internet website, either provide on carrier signal or provided in the form of any other.
Those skilled in the art, which are appreciated that, to carry out adaptively the module in the equipment in embodiment
Change and they are arranged in one or more equipment different from the embodiment.Can be the module or list in embodiment
Member or component be combined into a module or unit or component, and can be divided into addition multiple submodule or subelement or
Sub-component.In addition at least some in such feature and/or process or unit exclude each other, it can use any
Combination is disclosed to all features disclosed in this specification (including adjoint claim, summary and attached drawing) and so to appoint
Where all processes or unit of method or equipment are combined.Unless expressly stated otherwise, this specification (including adjoint power
Profit requires, summary and attached drawing) disclosed in each feature can be by providing the alternative features of identical, equivalent or similar purpose come generation
Replace.Also, in if the unit claim of equipment for drying is listed, several in these devices can be by same hard
Part item embodies.
Similarly, it will be appreciated that in order to simplify the disclosure and help to understand one or more of each open aspect,
Above in the description to the exemplary embodiment of the disclosure, each feature of the disclosure is grouped together into single implementation sometimes
In example, figure or descriptions thereof.However, the method for the disclosure should be construed to reflect following intention：I.e. required guarantor
The disclosure of shield requires features more more than the feature being expressly recited in each claim.It is more precisely, such as following
Claims reflect as, open aspect is all features less than single embodiment disclosed above.Therefore,
Thus the claims for following embodiment are expressly incorporated in the embodiment, wherein each claim is in itself
Separate embodiments all as the disclosure.
Particular embodiments described above, has carried out further in detail the purpose, technical solution and beneficial effect of the disclosure
Describe in detail bright, it should be understood that the foregoing is merely the specific embodiment of the disclosure, be not limited to the disclosure, it is all
Within the spirit and principle of the disclosure, any modification, equivalent substitution, improvement and etc. done should be included in the guarantor of the disclosure
Within the scope of shield.
Claims (10)
1. a kind of intelligent managing system for parking lot of multi-path camera deep learning, including：
Server end, the server end include：
Data acquisition module, by using multi-path camera collection parking lot vehicle and Parking bit boundary it is each
The video and/or view data in orientation；
Network transmission module, for the automobile video frequency collected and/or view data to be uploaded to hind computation module；And
Hind computation module, for the processing of parking vehicle information, including：
Deep learning model training submodule, by the multi-path camera in advance to different brands, each orientation of vehicle models
View data, parking lot road, parking stall region video and/or view data, and for abnormal behaviour judge
Video and/or view data are acquired, and gained video and/or image data are carried out marshalling carries out deep learning training, instruction
Deep neural network model is generated after white silk；And
Vehicle behavior judging submodule, is monitored and judges to vehicle behavior according to the neural network model generated after training.
2. intelligent managing system for parking lot according to claim 1, wherein, the hind computation module includes：
Vehicle parking submodule, for the deep neural network based on multi-path camera realize parking position automatic identification and
Management, including the parking condition according to user's requesting query parking lot, judge the vehicle stopped state and after confirming to stop
Start Fare determined by travel time；
Vehicle location and d navigation submodule, using Car license recognition and computer vision as core, after vehicle enters passage, more shootings
Head Real-time captured video signal, real-time video information is transmitted in system and is handled, big by directly measuring car plate size
It is small and/or measured indirectly by passage and both sides label, obtain the vehicle and different cameras relative position and away from
From position of the vehicle in parking lot of specific license plate number being obtained, so as to obtain vehicle in all passages in parking lot at different moments
Positional information simultaneously provides navigation information；And
Abnormal behaviour analyzes submodule, and early warning is carried out to the abnormal conditions occurred in parking lot.
3. intelligent managing system for parking lot according to claim 2, wherein,
The vehicle parking submodule of the hind computation module includes：
Data model trains sub- sub-module, the car marked in the training part gathered data sample of the vehicle parking submodule
Entirety and its feature, and by multi-layer C NN convolutional neural networks, train and wrapped for the global and local parking stall in parking lot
Deep neural network model containing various brands, each orientative feature of vehicle models；
Activity recognition predicts sub- sub-module, and the identification division of the vehicle parking submodule includes two components of global and local,
Using the deep neural network based on multi-path camera of training gained, the positional information of global vehicle and the office of each parking stall are obtained
Portion's parking information, credible result is thought if both matching degrees exceed certain threshold value and is exported as a result, the part of identification division
Component judges whether vehicle correctly docks at specified parking stall according to vehicle and parking stall feature；
The abnormal behaviour analysis submodule of the hind computation module includes：
Data model trains sub- sub-module, by multi-path camera from different perspectives to normal behaviour in target area and it is non-just
Chang Hangwei carries out image data acquiring, using the multiple image collected as a sample, and using data sample as training number
According to input, train to obtain the model of deep neural network by deep neural network；
Activity recognition predicts sub- sub-module, the new data input training gained depth nerve net that parking lot multi-path camera is gathered
In network model, and judge its behavior pattern；If being judged as improper behavior, the data image and relevant information are sent to pipe
Reason person, is inquired about with standby user.
4. intelligent managing system for parking lot according to claim 1, the data acquisition module includes：
Hardware interface submodule, for the calling including camera；
Human-computer interaction submodule, for often locating camera real time monitoring image information, vehicle parking state in each parking stall
What record information, empty parking space information and early warning information recorded transfers and shows.
5. intelligent managing system for parking lot according to claim 1, further includes client,
The client includes：
Empty parking space enquiry module, for inquiring about parking lot empty parking space quantity and position；
Empty parking space positions and road guide module, for obtaining empty parking space positioning and road guide information；
Parking timing payment module, for checking the parking duration and Parking Fee that park cars, and realizes and self-service pays online
Take.
6. intelligent managing system for parking lot according to claim 1, the hind computation module includes super calculation cluster service
Device, the super calculation cluster server includes multinuclear and many-core parallel server, for providing：
Service is calculated, including：The extraction of the deep learning and vehicle characteristics of video and/or view data, compare；
Storage service, including：The real-time storage of monitor video, and occur packet loss or network failure in network transmission process
When, the interim storage of monitor video；And
Resources regulation service, including：The resource allocation of computer cluster, avoids the occurrence of the situation that process is blocked, is lined up.
A kind of 7. parking lot intelligent management of multi-path camera deep learning, using such as any one of claim 1 to 6 institute
The intelligent managing system for parking lot for the multi-path camera deep learning stated, comprises the following steps：
When server background computing module vehicle parking submodule receives the parking inquiry request of user, it is empty to carry out parking lot
Position inquiry, and information is pushed to user；
Whether the vehicle that the vehicle parking submodule of server background computing module is determined up to Entrance allows access into；
Server background computing module is the vehicle distribution parking stall for allowing access into parking lot, and vehicle location and d navigation submodule provide
Empty parking space navigation information, and abnormal behaviour analysis submodule BOB(beginning of block) is monitored vehicle behavior abnormal conditions；
The vehicle parking submodule of server background computing module detects whether the vehicle up to specified parking stall is parked on request, and
Start Fare determined by travel time after vehicle stops well；
Vehicle license plate number information at server identification parking exit, carries out Parking Fee clearing.
8. parking lot intelligent management according to claim 7, the server background computing module provides a user
Navigation information, including：
If server receives the inquiry request that user is sent by the empty parking space enquiry module of client, hind computation is called
It is furnished with the parking lot intelligent management of multi-path camera deep learning in the vehicle parking submodule inquiry periphery preset range of module
The parking condition in the parking lot of system, and by empty parking space and navigation information to client push；
If server receives the end cutoff command of client submission, the vehicle location of hind computation module and d navigation submodule
Outlet navigation information is provided to the client.
9. parking lot intelligent management according to claim 7, including：
When vehicle enters parking lot, server identifies the license plate number of the vehicle first, and with entering the vehicle car in parking lot
Verification is compared in the trade mark, while by directly measuring car plate size and/or by passage and both sides label into the ranks
Measurement is connect, vehicle is obtained with the relative distance of each camera so as to judge the real time position of vehicle, wherein direct beasurement base meter
Calculation machine visual theory is calculated the distance of vehicle and camera by car plate size, measures then advance Measurement channel and both sides indirectly
Label and camera distance, and will by the distance of the relation of vehicle and label measuring and calculating vehicle and camera, last server
The location information of vehicle is pushed to the client of user, and guiding vehicle drives to corresponding parking stall.
10. parking lot intelligent management according to claim 7, wherein, vehicle enters the processing step behind parking lot
Including：
When user reaches Entrance, server enters parking by the camera in data acquisition module, extraction request
The automobile video frequency of field, image information, are sent to hind computation module by network transmission module, utilize the depth generated after training
Neural network model identifies and compares whether the vehicle meets type of vehicle standard into the parking lot；Standard compliant vehicle
Allow access into, and distribute empty parking space；Otherwise it is rejected for entry into and gives information alert, manual identified is carried out to the vehicle at this time, if
Manual identified result and the vehicle video and/or view data are then imported backstage by manual identified result to meet the standard of parking
Computing module intensified learning；If manual identified result is not meet the standard of parking；
If the vehicle allows access into parking lot, server will allow access into instruction to client push, and to the vehicle of client
Positioning and road guide module push empty parking space navigation information, guide the vehicle to drive towards the parking stall of server-assignment, work as vehicle
Into after parking lot, server just calls the abnormal behaviour of hind computation module to analyze submodule BOB(beginning of block) and detects in real time in parking lot
Whether abnormal conditions are occurred, when there are abnormal conditions, server will push warning message to administrator and user
After user, which reaches, specifies empty parking space, server can capture the parking stall in real time by the camera in data acquisition module
Boundary line and vehicle stand, and call whether the vehicle parking submodule block analysis of hind computation module judges the vehicle
It has been parked in specified region, if user is parked as requested, by the parking stall Status Change to have taken, and will have stopped
The amount information that the duration and needs of car are paid is sent to client, make user by the parking timing payment module of client into
Row inquiry；If vehicle is not parked by regulation, alarm, or installation the amplifying with prompt facility in parking lot are sent
Device, reminds user to park again, if not parking again as requested within a specified time still, server is by the parking stall state
It is changed to abnormal and the situation is sent to system manager, while gives the certain punishment of user；
When user, which picks up the car, to be left, if server receives the end cutoff command of client submission, to the sky of the client
Parking stall positions and road guide module provides real-time navigation information, and guiding user leaves parking lot；Go out when user reaches parking lot
Mouthful when, server, which will identify, vehicle license plate number and calculates vehicle parking expense, and push information to client be used for provide
Line is paid.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711144185.3A CN107967817A (en) | 2017-11-17 | 2017-11-17 | Intelligent managing system for parking lot and method based on multi-path camera deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711144185.3A CN107967817A (en) | 2017-11-17 | 2017-11-17 | Intelligent managing system for parking lot and method based on multi-path camera deep learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107967817A true CN107967817A (en) | 2018-04-27 |
Family
ID=62001150
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711144185.3A Pending CN107967817A (en) | 2017-11-17 | 2017-11-17 | Intelligent managing system for parking lot and method based on multi-path camera deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107967817A (en) |
Cited By (43)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108550277A (en) * | 2018-06-04 | 2018-09-18 | 济南浪潮高新科技投资发展有限公司 | A kind of parking stall identification and querying method based on picture depth study |
| CN108765973A (en) * | 2018-06-01 | 2018-11-06 | 智慧互通科技有限公司 | A kind of Roadside Parking management system based on the complementation of offside visual angle |
| 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 |
| CN108831178A (en) * | 2018-05-23 | 2018-11-16 | 上海移为通信技术股份有限公司 | A kind of intelligent parking lot shutdown system and method |
| CN108921095A (en) * | 2018-07-03 | 2018-11-30 | 安徽灵图壹智能科技有限公司 | A kind of parking occupancy management system neural network based, method and parking stall |
| CN109191890A (en) * | 2018-08-10 | 2019-01-11 | 重庆唯哲科技有限公司 | The garage auxiliary driving method and auxiliary system read based on depth |
| CN109272751A (en) * | 2018-08-31 | 2019-01-25 | 西安艾润物联网技术服务有限责任公司 | A kind of vehicles management method and relevant apparatus |
| CN109559551A (en) * | 2018-12-07 | 2019-04-02 | 肖修军 | A kind of city intelligent parking management system based on big data |
| CN109584613A (en) * | 2018-12-19 | 2019-04-05 | 东软睿驰汽车技术（沈阳）有限公司 | A kind of position information share method and device of free parking space |
| CN109606356A (en) * | 2018-12-29 | 2019-04-12 | 百度在线网络技术（北京）有限公司 | It parks control method, device, electronic equipment and storage medium |
| CN109686109A (en) * | 2019-01-02 | 2019-04-26 | 江苏警官学院 | A kind of parking lot security monitoring management system based on artificial intelligence |
| CN110148308A (en) * | 2019-05-21 | 2019-08-20 | 北京百度网讯科技有限公司 | Vehicle positioning system in parking garage |
| CN110232584A (en) * | 2019-04-11 | 2019-09-13 | 深圳市城市交通规划设计研究中心有限公司 | Parking lot site selecting method, device, computer readable storage medium and terminal device |
| CN110288837A (en) * | 2019-07-12 | 2019-09-27 | 云宝宝大数据产业发展有限责任公司 | A kind of separated stop board recognition methods of multiple-camera collaboration and device |
| CN110379177A (en) * | 2019-07-12 | 2019-10-25 | 程广卫 | A kind of stereo garage video detection parking stall counts and car searching method |
| CN110598704A (en) * | 2019-09-26 | 2019-12-20 | 中电万维信息技术有限责任公司 | License plate recognition non-inductive payment system based on deep learning |
| CN110634302A (en) * | 2019-11-14 | 2019-12-31 | 广东优世联合控股集团股份有限公司 | Parking lot retrograde vehicle detection system based on BIM |
| IT201800007632A1 (en) * | 2018-08-02 | 2020-02-02 | Park Smart Srl | Highly innovative distributed system for the management of delimited areas |
| CN111047910A (en) * | 2020-01-03 | 2020-04-21 | 贺楚龙 | Control method for preventing traffic accidents in intelligent parking lot |
| WO2020077873A1 (en) * | 2018-10-15 | 2020-04-23 | 平安科技（深圳）有限公司 | Indoor parking lot navigation method and device, computer apparatus, and storage medium |
| CN111060116A (en) * | 2019-12-04 | 2020-04-24 | 江西洪都航空工业集团有限责任公司 | Grassland self-drawing system based on vision |
| CN111145545A (en) * | 2019-12-25 | 2020-05-12 | 西安交通大学 | Road traffic behavior unmanned aerial vehicle monitoring system and method based on deep learning |
| CN111415468A (en) * | 2019-01-08 | 2020-07-14 | 绍兴图聚光电科技有限公司 | Shared bicycle supervision method and supervision device |
| CN111554096A (en) * | 2019-02-12 | 2020-08-18 | 丰田自动车株式会社 | Parking management device |
| CN111915898A (en) * | 2020-07-24 | 2020-11-10 | 杭州金通科技集团股份有限公司 | Parking monitoring AI electronic post house |
| CN112289069A (en) * | 2020-10-20 | 2021-01-29 | 上海汽车电器总厂有限公司 | Parking space guiding system and method |
| CN112382126A (en) * | 2020-11-13 | 2021-02-19 | 广东飞达交通工程有限公司 | Parking space occupation analysis method based on video |
| CN112489441A (en) * | 2020-11-30 | 2021-03-12 | 高新兴智联科技有限公司 | Parking lot access method and access system based on double-base-plate license plate recognition |
| CN112581748A (en) * | 2020-12-20 | 2021-03-30 | 宋彦震 | Garage traffic-out pedestrian safety prompting system based on convolutional neural network |
| CN112863229A (en) * | 2020-12-30 | 2021-05-28 | 中兴智能交通股份有限公司 | System and method for realizing unattended operation based on parking equipment and technology |
| CN113008569A (en) * | 2019-12-19 | 2021-06-22 | 丰田自动车株式会社 | Model diagnosis device and model diagnosis system |
| EP3806064A4 (en) * | 2018-05-25 | 2021-06-30 | Hangzhou Hikvision Digital Technology Co., Ltd. | Method and apparatus for detecting parking space usage condition, electronic device, and storage medium |
| CN113194138A (en) * | 2021-04-28 | 2021-07-30 | 昭通亮风台信息科技有限公司 | Travel management method and system based on AI deep learning |
| CN113240931A (en) * | 2021-03-31 | 2021-08-10 | 深圳左邻永佳科技有限公司 | Parking method, parking device, computer equipment and storage medium |
| CN113362643A (en) * | 2021-07-09 | 2021-09-07 | 姜江 | Method, system and device for positioning and inducing vehicle based on image AI |
| CN113706916A (en) * | 2020-10-29 | 2021-11-26 | 董笑天 | A wisdom parking management system for parking area |
| CN114220292A (en) * | 2021-12-17 | 2022-03-22 | 谭苏梦源 | Method and system for realizing intelligent parking |
| CN114566009A (en) * | 2022-02-24 | 2022-05-31 | 上海欣诣科技有限公司 | Charging and billing method for electric automobile |
| CN114582159A (en) * | 2022-02-11 | 2022-06-03 | 中交公规土木大数据信息技术（北京）有限公司 | Road service zone grading intelligent parking guiding method, system, equipment and medium |
| CN114882734A (en) * | 2022-07-12 | 2022-08-09 | 车位管家(深圳)科技有限公司 | Parking lot safety monitoring management system based on artificial intelligence |
| CN115019550A (en) * | 2022-07-18 | 2022-09-06 | 江苏明奕达物联网科技有限公司 | Intelligent parking guidance system |
| CN116030542A (en) * | 2023-02-15 | 2023-04-28 | 东莞市杰瑞智能科技有限公司 | Unmanned charge management method for parking in road |
| CN117576946A (en) * | 2024-01-16 | 2024-02-20 | 福建龙投信息技术有限公司 | Intelligent parking safety supervision method and system |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101656023A (en) * | 2009-08-26 | 2010-02-24 | 西安理工大学 | Management method of indoor car park in video monitor mode |
| CN103310660A (en) * | 2013-06-27 | 2013-09-18 | 苏州创智宏云信息科技有限公司 | Intelligent carport monitoring system in parking lot |
| CN103377562A (en) * | 2012-04-28 | 2013-10-30 | 复旦大学无锡研究院 | Large parking lot intelligent management and parking space guidance system |
| CN103473950A (en) * | 2012-06-06 | 2013-12-25 | 刘鉵 | Parking lot parking space monitoring method |
| CN104200698A (en) * | 2014-05-09 | 2014-12-10 | 深圳市中科利亨车库设备有限公司 | Method and system for vehicle parking and pick-up safety management of stereo garage |
| CN104240511A (en) * | 2014-10-23 | 2014-12-24 | 梁崇彦 | Stereo garage parking lot management system with vehicle parameter detection and remote management functions |
| CN104766494A (en) * | 2015-04-22 | 2015-07-08 | 成都逸泊科技有限公司 | Distributed type time-staggered parking system |
| CN104778855A (en) * | 2014-01-15 | 2015-07-15 | 北京同步科技有限公司 | Intelligent parking lot management system and management method |
| CN106097766A (en) * | 2016-08-22 | 2016-11-09 | 成都景触科技有限公司 | A kind of scenic spot vehicle management system |
| CN106128153A (en) * | 2016-07-14 | 2016-11-16 | 中兴智能交通股份有限公司 | A kind of stall navigation system and air navigation aid |
| CN106128151A (en) * | 2016-07-08 | 2016-11-16 | 京东方科技集团股份有限公司 | A kind of intelligent parking system |
| CN106157688A (en) * | 2016-08-25 | 2016-11-23 | 华南师范大学 | The parking space detection method with big data and system is learnt based on the degree of depth |
| CN106846892A (en) * | 2017-03-07 | 2017-06-13 | 重庆邮电大学 | Parking lot vehicle cooperative intelligent shutdown system and method based on machine vision |
| CN107093328A (en) * | 2017-06-06 | 2017-08-25 | 重庆邮电大学 | Parking ground navigation system and method based on machine vision |
| CN206470954U (en) * | 2017-02-20 | 2017-09-05 | 厦门中诚国信电子科技有限公司 | A kind of parking lot intelligent barrier gate system |
| CN107146468A (en) * | 2017-07-12 | 2017-09-08 | 中国地质大学（武汉） | The recognition methods of parking position and system and management method and system |
| US20170294121A1 (en) * | 2016-04-12 | 2017-10-12 | Ford Global Technologies, Llc | Detecting available parking spaces |
-
2017
- 2017-11-17 CN CN201711144185.3A patent/CN107967817A/en active Pending
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101656023A (en) * | 2009-08-26 | 2010-02-24 | 西安理工大学 | Management method of indoor car park in video monitor mode |
| CN103377562A (en) * | 2012-04-28 | 2013-10-30 | 复旦大学无锡研究院 | Large parking lot intelligent management and parking space guidance system |
| CN103473950A (en) * | 2012-06-06 | 2013-12-25 | 刘鉵 | Parking lot parking space monitoring method |
| CN103310660A (en) * | 2013-06-27 | 2013-09-18 | 苏州创智宏云信息科技有限公司 | Intelligent carport monitoring system in parking lot |
| CN104778855A (en) * | 2014-01-15 | 2015-07-15 | 北京同步科技有限公司 | Intelligent parking lot management system and management method |
| CN104200698A (en) * | 2014-05-09 | 2014-12-10 | 深圳市中科利亨车库设备有限公司 | Method and system for vehicle parking and pick-up safety management of stereo garage |
| CN104240511A (en) * | 2014-10-23 | 2014-12-24 | 梁崇彦 | Stereo garage parking lot management system with vehicle parameter detection and remote management functions |
| CN104766494A (en) * | 2015-04-22 | 2015-07-08 | 成都逸泊科技有限公司 | Distributed type time-staggered parking system |
| US20170294121A1 (en) * | 2016-04-12 | 2017-10-12 | Ford Global Technologies, Llc | Detecting available parking spaces |
| CN106128151A (en) * | 2016-07-08 | 2016-11-16 | 京东方科技集团股份有限公司 | A kind of intelligent parking system |
| CN106128153A (en) * | 2016-07-14 | 2016-11-16 | 中兴智能交通股份有限公司 | A kind of stall navigation system and air navigation aid |
| CN106097766A (en) * | 2016-08-22 | 2016-11-09 | 成都景触科技有限公司 | A kind of scenic spot vehicle management system |
| CN106157688A (en) * | 2016-08-25 | 2016-11-23 | 华南师范大学 | The parking space detection method with big data and system is learnt based on the degree of depth |
| CN206470954U (en) * | 2017-02-20 | 2017-09-05 | 厦门中诚国信电子科技有限公司 | A kind of parking lot intelligent barrier gate system |
| CN106846892A (en) * | 2017-03-07 | 2017-06-13 | 重庆邮电大学 | Parking lot vehicle cooperative intelligent shutdown system and method based on machine vision |
| CN107093328A (en) * | 2017-06-06 | 2017-08-25 | 重庆邮电大学 | Parking ground navigation system and method based on machine vision |
| CN107146468A (en) * | 2017-07-12 | 2017-09-08 | 中国地质大学（武汉） | The recognition methods of parking position and system and management method and system |
Non-Patent Citations (3)
| Title |
|---|
| GIUSEPPE AMATO: "Car parking occupancy detection using smart camera networks and Deep Learning", 《 2016 IEEE SYMPOSIUM ON COMPUTERS AND COMMUNICATION (ISCC)》 * |
| XUEZHI XIANG: "Real-Time Parking Occupancy Detection for Gas Stations Based on Haar-AdaBoosting and CNN", 《IEEE SENSORS JOURNAL》 * |
| 甘凯今: "融合整体与局部特征的车辆型号识别方法", 《现代电子技术》 * |
Cited By (52)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108831178A (en) * | 2018-05-23 | 2018-11-16 | 上海移为通信技术股份有限公司 | A kind of intelligent parking lot shutdown system and method |
| EP3806064A4 (en) * | 2018-05-25 | 2021-06-30 | Hangzhou Hikvision Digital Technology Co., Ltd. | Method and apparatus for detecting parking space usage condition, electronic device, and storage medium |
| US11455805B2 (en) | 2018-05-25 | 2022-09-27 | Hangzhou Hikvision Digital Technology Co., Ltd. | Method and apparatus for detecting parking space usage condition, electronic device, and storage medium |
| CN108765973B (en) * | 2018-06-01 | 2022-04-19 | 智慧互通科技股份有限公司 | Roadside parking management system based on opposite side visual angle complementation |
| CN108765973A (en) * | 2018-06-01 | 2018-11-06 | 智慧互通科技有限公司 | A kind of Roadside Parking management system based on the complementation of offside visual angle |
| CN108550277A (en) * | 2018-06-04 | 2018-09-18 | 济南浪潮高新科技投资发展有限公司 | A kind of parking stall identification and querying method based on picture depth study |
| 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 |
| CN108921095A (en) * | 2018-07-03 | 2018-11-30 | 安徽灵图壹智能科技有限公司 | A kind of parking occupancy management system neural network based, method and parking stall |
| WO2020026098A1 (en) * | 2018-08-02 | 2020-02-06 | Park Smart S.R.L. | High innovation distributed system for the management of demarcated areas |
| IT201800007632A1 (en) * | 2018-08-02 | 2020-02-02 | Park Smart Srl | Highly innovative distributed system for the management of delimited areas |
| CN109191890A (en) * | 2018-08-10 | 2019-01-11 | 重庆唯哲科技有限公司 | The garage auxiliary driving method and auxiliary system read based on depth |
| CN109272751A (en) * | 2018-08-31 | 2019-01-25 | 西安艾润物联网技术服务有限责任公司 | A kind of vehicles management method and relevant apparatus |
| WO2020077873A1 (en) * | 2018-10-15 | 2020-04-23 | 平安科技（深圳）有限公司 | Indoor parking lot navigation method and device, computer apparatus, and storage medium |
| CN109559551A (en) * | 2018-12-07 | 2019-04-02 | 肖修军 | A kind of city intelligent parking management system based on big data |
| CN109584613A (en) * | 2018-12-19 | 2019-04-05 | 东软睿驰汽车技术（沈阳）有限公司 | A kind of position information share method and device of free parking space |
| CN109606356A (en) * | 2018-12-29 | 2019-04-12 | 百度在线网络技术（北京）有限公司 | It parks control method, device, electronic equipment and storage medium |
| CN109686109A (en) * | 2019-01-02 | 2019-04-26 | 江苏警官学院 | A kind of parking lot security monitoring management system based on artificial intelligence |
| CN111415468A (en) * | 2019-01-08 | 2020-07-14 | 绍兴图聚光电科技有限公司 | Shared bicycle supervision method and supervision device |
| CN111554096A (en) * | 2019-02-12 | 2020-08-18 | 丰田自动车株式会社 | Parking management device |
| CN110232584B (en) * | 2019-04-11 | 2022-08-02 | 深圳市城市交通规划设计研究中心有限公司 | Parking lot site selection method and device, computer readable storage medium and terminal equipment |
| CN110232584A (en) * | 2019-04-11 | 2019-09-13 | 深圳市城市交通规划设计研究中心有限公司 | Parking lot site selecting method, device, computer readable storage medium and terminal device |
| CN110148308A (en) * | 2019-05-21 | 2019-08-20 | 北京百度网讯科技有限公司 | Vehicle positioning system in parking garage |
| CN110379177A (en) * | 2019-07-12 | 2019-10-25 | 程广卫 | A kind of stereo garage video detection parking stall counts and car searching method |
| CN110288837A (en) * | 2019-07-12 | 2019-09-27 | 云宝宝大数据产业发展有限责任公司 | A kind of separated stop board recognition methods of multiple-camera collaboration and device |
| CN110598704A (en) * | 2019-09-26 | 2019-12-20 | 中电万维信息技术有限责任公司 | License plate recognition non-inductive payment system based on deep learning |
| CN110634302A (en) * | 2019-11-14 | 2019-12-31 | 广东优世联合控股集团股份有限公司 | Parking lot retrograde vehicle detection system based on BIM |
| CN111060116A (en) * | 2019-12-04 | 2020-04-24 | 江西洪都航空工业集团有限责任公司 | Grassland self-drawing system based on vision |
| CN113008569A (en) * | 2019-12-19 | 2021-06-22 | 丰田自动车株式会社 | Model diagnosis device and model diagnosis system |
| CN111145545A (en) * | 2019-12-25 | 2020-05-12 | 西安交通大学 | Road traffic behavior unmanned aerial vehicle monitoring system and method based on deep learning |
| CN111047910A (en) * | 2020-01-03 | 2020-04-21 | 贺楚龙 | Control method for preventing traffic accidents in intelligent parking lot |
| CN111915898B (en) * | 2020-07-24 | 2022-07-08 | 杭州金通科技集团股份有限公司 | Parking monitoring AI electronic post house |
| CN111915898A (en) * | 2020-07-24 | 2020-11-10 | 杭州金通科技集团股份有限公司 | Parking monitoring AI electronic post house |
| CN112289069A (en) * | 2020-10-20 | 2021-01-29 | 上海汽车电器总厂有限公司 | Parking space guiding system and method |
| CN113706916A (en) * | 2020-10-29 | 2021-11-26 | 董笑天 | A wisdom parking management system for parking area |
| CN112382126A (en) * | 2020-11-13 | 2021-02-19 | 广东飞达交通工程有限公司 | Parking space occupation analysis method based on video |
| CN112489441B (en) * | 2020-11-30 | 2022-08-09 | 高新兴智联科技有限公司 | Parking lot access method and access system based on double-base license plate recognition |
| CN112489441A (en) * | 2020-11-30 | 2021-03-12 | 高新兴智联科技有限公司 | Parking lot access method and access system based on double-base-plate license plate recognition |
| CN112581748A (en) * | 2020-12-20 | 2021-03-30 | 宋彦震 | Garage traffic-out pedestrian safety prompting system based on convolutional neural network |
| CN112863229A (en) * | 2020-12-30 | 2021-05-28 | 中兴智能交通股份有限公司 | System and method for realizing unattended operation based on parking equipment and technology |
| CN112863229B (en) * | 2020-12-30 | 2022-12-13 | 中兴智能交通股份有限公司 | System and method for realizing unattended operation based on parking equipment and technology |
| CN113240931A (en) * | 2021-03-31 | 2021-08-10 | 深圳左邻永佳科技有限公司 | Parking method, parking device, computer equipment and storage medium |
| CN113194138A (en) * | 2021-04-28 | 2021-07-30 | 昭通亮风台信息科技有限公司 | Travel management method and system based on AI deep learning |
| CN113362643A (en) * | 2021-07-09 | 2021-09-07 | 姜江 | Method, system and device for positioning and inducing vehicle based on image AI |
| CN114220292A (en) * | 2021-12-17 | 2022-03-22 | 谭苏梦源 | Method and system for realizing intelligent parking |
| CN114582159A (en) * | 2022-02-11 | 2022-06-03 | 中交公规土木大数据信息技术（北京）有限公司 | Road service zone grading intelligent parking guiding method, system, equipment and medium |
| CN114566009A (en) * | 2022-02-24 | 2022-05-31 | 上海欣诣科技有限公司 | Charging and billing method for electric automobile |
| CN114882734A (en) * | 2022-07-12 | 2022-08-09 | 车位管家(深圳)科技有限公司 | Parking lot safety monitoring management system based on artificial intelligence |
| CN115019550A (en) * | 2022-07-18 | 2022-09-06 | 江苏明奕达物联网科技有限公司 | Intelligent parking guidance system |
| CN116030542A (en) * | 2023-02-15 | 2023-04-28 | 东莞市杰瑞智能科技有限公司 | Unmanned charge management method for parking in road |
| CN116030542B (en) * | 2023-02-15 | 2023-11-21 | 东莞市杰瑞智能科技有限公司 | Unmanned charge management method for parking in road |
| CN117576946A (en) * | 2024-01-16 | 2024-02-20 | 福建龙投信息技术有限公司 | Intelligent parking safety supervision method and system |
| CN117576946B (en) * | 2024-01-16 | 2024-03-19 | 福建龙投信息技术有限公司 | Intelligent parking safety supervision method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107967817A (en) | Intelligent managing system for parking lot and method based on multi-path camera deep learning | |
| CN107945566A (en) | Curb parking management system and method based on multiple target tracking and deep learning | |
| CN205788779U (en) | A kind of Roadside Parking management system | |
| CN102521986B (en) | Control method for automatic detection system for fake plate vehicle | |
| CN108460472B (en) | Intelligent application management system of automobile in internet | |
| CN104981377B (en) | The control using single many parking spaces of multiple photographic head uses | |
| RU2607043C1 (en) | Control over one parking space use for several vehicles by applying plurality of cameras | |
| AU2013293034B2 (en) | An automated vehicle parking management system | |
| US10726718B1 (en) | Method for managing vehicle parking within a parking structure | |
| US20140140578A1 (en) | Parking enforcement system and method of parking enforcement | |
| CN109711562A (en) | A kind of Automobile Service competition for orders method and system based on accurate acquisition vehicle failure analysis | |
| CN105261234A (en) | Unattended intelligent parking management system and method in open area | |
| CN106327915A (en) | Parking lot intelligent antitheft system and vehicle antitheft method based on mobile terminal | |
| CN108986534A (en) | Based on Car license recognition parking management method and system | |
| CN109155105A (en) | For detecting the method for parking cars and collecting parking fee | |
| CN107464446B (en) | Inspection method and device for vertical parking space parking information | |
| US20130182110A1 (en) | Method, device and integrated system for payment of parking fees based on cameras and license plate recognition technology | |
| CN101814202A (en) | Vehicle toll supervision method | |
| CN112671834A (en) | Parking data processing system | |
| CN105046967A (en) | Control system for parking management | |
| CN110310378A (en) | A kind of open type parking ground parking charge method and system based on double mirror | |
| CN112053567A (en) | Roadside parking management method and electronic equipment | |
| CN110335490A (en) | A kind of method and system of curb parking timing | |
| CN103794051A (en) | Cloned vehicle detecting system and corresponding detecting method based on parking information | |
| CN205158653U (en) | Free region unmanned on duty's intelligent system for parking management |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180427 |
|
| WD01 | Invention patent application deemed withdrawn after publication |