CN107610471A - Vehicle fake-license detection method and system - Google Patents
Vehicle fake-license detection method and system Download PDFInfo
- Publication number
- CN107610471A CN107610471A CN201610543659.0A CN201610543659A CN107610471A CN 107610471 A CN107610471 A CN 107610471A CN 201610543659 A CN201610543659 A CN 201610543659A CN 107610471 A CN107610471 A CN 107610471A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- information
- bayonet socket
- trace information
- fake
- 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
Abstract
The embodiment of the present invention provides a kind of vehicle fake-license detection method and system, bayonet socket is set to cross car table in the first database, the bayonet socket crosses car table and is used to store the newest driving trace information of vehicle, and driving trace information includes license plate number, the bayonet socket information currently passed through and spends the car time；In detection process, obtain the current source driving trace information of vehicle to be detected, crossed from bayonet socket and license plate number and the license plate number same target driving trace information in the driving trace information of source are extracted in car table, the bayonet socket information, card time excessively in source driving trace information and target travel trace information can determine that whether vehicle to be detected is fake license plate vehicle.The present invention only needs to complete the real-time detection to vehicle fake-license situation according to driving trace information can newest before the current source driving trace information of vehicle and the vehicle, bayonet socket crosses car table all only to be needed to store the newest driving trace information of the vehicle for each vehicle, real-time detection, the storage pressure of and can transport data stream can be realized.
Description
Technical field
The present invention relates to intelligent transportation field, more particularly to a kind of vehicle fake-license detection method and system.
Background technology
Fake-licensed car is commonly called as cloning car, refers to by forging or illegally extracting other number plate of vehicles and driving license etc.
The vehicle that road travels in formality.Because motor vehicle, number plate management are lack of standardization, deck behavior has what is growed in intensity
Trend, special number plate, army's board, alert board are applied mechanically from applying mechanically people-brand and developing into；From repacking, assembly car deck hair
Open up scrap car, steal rob car deck arrive again with cheat, the means of bribery re-fetch automotive number plate generation.
Fake license plate vehicle very disruptive transport market management order, the interests of legal vehicle are compromised, also to people's
Lives and properties and public safety cause serious threat, and certain destabilizing factor is brought to society.Cause
This is always the object of traffic monitoring department key point strike, and is forbidded strictly by country.However, administer deck
Maximum difficult point is, hard to tell whether it is true or false between fake-licensed car and true car, unless fake license plate vehicle " commiting a crime ", otherwise traffic police
It is difficult to check Vehicle Identify Number and Motor Number.How effectively to identify fake-licensed car and active alarm turns into traffic administration institute
One problem of door.
With the fast development of economy, Urban vehicles poputation is growing, and traffic data amount has reached
TB (TeraByte) or even PB (PetaByte) rank scale.Conventional computing system is in reply magnanimity traffic
During data, no matter from storage capacity, computing capability, or stability, time-consuming performance etc. are all not
Can meet demand.What the solution method proposed at present was mainly based upon Hadoop (Distributed Architecture) realizes board
Car test is surveyed, although the storage of mass data, calculating and inquiry problem can be solved, just because of storing sea
The data of amount, it is when all preserving data or preserving very long one section when being detected at present to information of vehicles
Between after, the data based on storage carry out analysis detection.This detection is present can not be in real time to the deck of vehicle
Situation is detected, and the problem of need to store larger detection data volume.
The content of the invention
Vehicle fake-license detection method and system provided in an embodiment of the present invention, mainly solving the technical problems that：
Solve under the existing scene based on huge traffic data, it is impossible to vehicle fake-license situation carry out in real time detection and
The problem of needing to store larger detection data volume.
In order to solve the above technical problems, the embodiment of the present invention provides a kind of vehicle fake-license detecting system, its feature
It is, including：Data-acquisition system and real-time distributed computing system；
The data-acquisition system is used to obtain the current source driving trace information of vehicle to be detected and issued described
Implement distributed computing system, the bayonet socket information that the source driving trace information includes license plate number, currently passed through
And spend the card time；
The real-time distributed computing system includes trajectory analysis module, for the bayonet socket mistake from the first database
Extraction include the target travel trace information of the license plate number in car table, according to the source driving trace information with
Bayonet socket information, card time excessively in the target travel trace information determine whether the vehicle to be detected is set
Board vehicle；The bayonet socket crosses the newest driving trace information of car table storage vehicle.
The embodiment of the present invention also provides a kind of vehicle fake-license detection method, including：
Obtain the current source driving trace information of vehicle to be detected, the source driving trace information include license plate number,
The bayonet socket information currently passed through and mistake card time；
The target travel trace information that extraction includes the license plate number in car table is crossed from the bayonet socket of the first database；
Bayonet socket information in the source driving trace information and the target travel trace information, when crossing card
Between determine whether the vehicle to be detected is fake license plate vehicle；The bayonet socket crosses the newest traveling of car table storage vehicle
Trace information.
The embodiment of the present invention also provides a kind of computer-readable storage medium, is stored with the computer-readable storage medium
Computer executable instructions, the computer executable instructions are used to perform foregoing vehicle fake-license detection method.
The beneficial effects of the invention are as follows：
Vehicle fake-license detection method, system and the storage medium provided according to embodiments of the present invention, in the first number
Bayonet socket is set to cross car table according in storehouse, the bayonet socket crosses car table and is used to store the newest driving trace information of vehicle, its
Middle driving trace information includes license plate number, the bayonet socket information currently passed through and spends the card time；Then in vehicle
In detection process, the current source driving trace information of vehicle to be detected is obtained, from the bayonet socket mistake of the first database
License plate number and the license plate number same target driving trace information in the driving trace information of source are extracted in car table, according to
Bayonet socket information, mistake card time in source driving trace information and target travel trace information can determine that to be detected
Whether vehicle is fake license plate vehicle.Namely only needed in the embodiment of the present invention according to the current source driving trace of vehicle
Newest driving trace information can completes the real-time inspection to vehicle fake-license situation before information and the vehicle
Survey；Namely during vehicle detection, bayonet socket crosses car table all only to be needed to store the vehicle most for each vehicle
New driving trace information, and all driving trace information of the vehicle or a whole period need not be stored
Interior information, can realize the real-time detection to vehicle fake-license situation, and and can greatlys save huge traffic data
The storage pressure of stream.
Brief description of the drawings
Fig. 1 is the vehicle fake-license detection method schematic flow sheet in the embodiment of the present invention one；
Fig. 2 is the vehicle fake-license detecting system structural representation in the embodiment of the present invention two；
Fig. 3 is another vehicle fake-license detecting system structural representation in the embodiment of the present invention two；
Fig. 4 is the vehicle fake-license detection method schematic flow sheet in the embodiment of the present invention three.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear
Chu, it is fully described by, it is clear that described embodiment is part of the embodiment in the present invention, rather than
Whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art are not making creation
Property work under the premise of the every other embodiment that is obtained, belong to the scope of protection of the invention.
Embodiment one：
The purpose of the present embodiment is to be lacked to solve conventional computing system existing for huge traffic data processing
Fall into, at the same overcome hadoop can not research and application fake-licensed car in real time technological deficiency, there is provided one kind is based in real time
Distribution (stream) formula computing system (storm) realizes that huge traffic data stream fake-licensed car monitors the side of alarm in real time
Method, solves that current system mass data storage pressure is big, detection time delay is big and detection efficiency is low well
The problem of.
In the present embodiment, first in the first database bayonet socket can be set to cross car table.First in the present embodiment
Database can be the database of Hadoop types, such as Hbase (Hadoop Database) database,
Certainly also it is not excluded for using other kinds of database.The bayonet socket set in the present embodiment in the first database
Car table is crossed to be used to store the newest driving trace information of vehicle, wherein driving trace information comprise at least license plate number,
The bayonet socket information currently passed through and mistake card time.Namely the bayonet socket in the present embodiment crosses car table for each vehicle
As long as store its newest driving trace information, it is not necessary to store all driving trace letters of vehicle
Driving trace information in breath or a period, transport data stream storage pressure can be substantially reduced, simultaneously
The efficiency of subsequent detection can also be lifted.Based on the setting, the vehicle fake-license detection method in the present embodiment is joined
As shown in Figure 1, including：
S101：The current source driving trace information of vehicle to be detected is obtained, the source traveling rail obtained in the step
Mark information includes license plate number, the bayonet socket information currently passed through and spends the card time.Wherein, bayonet socket information includes
For identifying the information of each bayonet socket, including but not limited to bayonet socket numbering, bayonet socket positional information；Spend the card time then
Refer to time when vehicle passes through bayonet socket.
S102：Extraction in car table, which is crossed, from the bayonet socket of the first database includes the license plate number in the driving trace information of source
Target travel trace information.
The step is specially that the license plate number in the driving trace information of source and bayonet socket are crossed into each driving trace in car table to believe
Each license plate number in breath is matched, when matching completely the same license plate number, then by corresponding to the license plate number
Driving trace information is as target travel trace information.
S103：Bayonet socket information, mistake in source driving trace information and the target travel trace information of extraction
The card time determines whether vehicle to be detected is fake license plate vehicle, such as：
Between two bayonet sockets corresponding to bayonet socket information in acquisition source driving trace information and target travel trace information
Minimum range Dmin, minimum time value is then calculated according to default maximum travelling speed Vmax
Tmin=Dmin/Vmax.
It's card time t2 pasts crossing in card time t1 and target travel trace information in the driving trace information of calculating source
Difference T=t1-t2 whether be less than minimum time value Tmin, in this way, show that the vehicle to be detected has deck suspicion
Doubt, be determined as fake-licensed car.
It should be appreciated that the minimum range Dmin in the present embodiment between two bayonet sockets can be therebetween
Air line distance, now can directly be calculated according to the latitude and longitude information of each bayonet socket or the two it
Between the minimum range that actually measures, now then need to measure and store in advance so that follow-up use is to inquire about.
Each bayonet socket can set unique bayonet socket to number in the present embodiment, namely by bayonet socket numbering can only
One each bayonet socket of identification.Also it can not be that each bayonet socket sets bayonet socket to number, and pass through each bayonet socket positional information of itself
Unique identification is carried out, therefore the position that different bayonet sockets are set is different.
S101 can specifically be performed by data-acquisition system.The acquisition source of source driving trace information in S101
Can be from the acquisition of the bayonet socket IMAQ end of each bayonet socket.In the present embodiment, adopting for subregion deployment can be used
Collection strategy, specifically：
It is larger for core space database data amounts such as picture urban districts, it can configure more collections in terms of acquisition strategies
Server gathers core space database simultaneously；For the small region of data volume, an acquisition server can be used
The mode of multi-region regional data base is gathered simultaneously.
The video or image that bayonet socket IMAQ end collects monitoring camera can be also carried out at image algorithm
Reason, including the function such as the identification of image preprocessing, Car license recognition, vehicle color, vehicle cab recognition, Bus- Speed Monitoring.
Result after the processing of bayonet socket IMAQ end has been structural data, including car plate, body color, model,
Bayonet socket numbering, bayonet socket the address location information such as driving lane even where vehicle.
In the step, vehicle to be detected can be obtained from each bayonet socket IMAQ end by data acquisition module and worked as
Preceding source driving trace Data Concurrent is to data interchange platform；
Data interaction platform can be responsible for the integrated of data, distributed storage and unified management, and it may include point
Cloth distribution subscription message (kafka) distribution module, for by source driving trace data conversion into message format
Source driving trace message issue real-time distributed computing system in next step.Now data interaction platform
Then information client side (kafka client) is subscribed to as distributed post.Kafka is a kind of distribution of high-throughput
Formula distribution subscription message system, the persistence of message is provided by O (1) disk data structure, is gulped down with height
The features such as amount of telling and prolonged stability.
In the present embodiment, kafka distribution modules, can be by each bayonet socket in distribution source driving trace message
The driving trace data of each car are issued as a piece of news, and load can be used in distribution procedure
Balanced mechanism is distributed, or using the data or same license plate number ensured as far as possible on same bayonet socket
The principle that data are dealt into same calculate node is distributed.And for each source driving trace during its specific distribution
Message can also be distributed to real-time distributed computing system (storm) according to time order and function order.
In the present embodiment, in addition to the source driving trace data that will be obtained from the bayonet socket IMAQ end of each bayonet socket
Store into the second database, and storage rule can use and partitioned storage is carried out in units of bayonet socket, or
, can also be in chronological sequence sequentially by each source driving trace data on the basis of carrying out partitioned storage in units of bayonet socket
It is stored in the second database.The data being stored in the second database can be used as preliminary data, in case going through
History is inquired about or otherwise calling.The second database in the present embodiment can also be Hadoop types
Database, such as HDFS (Hadoop Distributed File System, Hadoop distributed file system)
Database, also it is not excluded for using other kinds of database certainly.
In the present embodiment, cross in car table and extract comprising source traveling rail from the bayonet socket of the first database in S102
After the target travel trace information of license plate number in mark information, in addition to delete the target that bayonet socket is crossed in car table
Driving trace information, source driving trace information is stored in the bayonet socket and crosses car table, to ensure the bayonet socket process table
The driving trace information of middle storage is newest.
There is also the situation of target travel trace information corresponding to being not matched in S102, namely from first
The bayonet socket of database crosses in car table the target travel trace information not extracted comprising license plate number, now shows this
Do not counted also before license plate number in the driving trace information of source, directly by the source driving trace information deposit
Bayonet socket crosses car table, is thus crossed in bayonet socket in car table and adds the driving trace information of a license plate number.With
Different obtain of data counts, and the license plate number of the driving trace information can be caused to cover in bayonet socket process table will be more perfect.
In the present embodiment, before above-mentioned S102 is performed, the source that kafka distribution modules can also be sent
Driving trace information carries out ETL (Extract-Transform-Load) processing, because source data amount is very big,
Deal with very time-consuming, it is possible to data reduction is preferentially carried out, to improve follow-up data Treatment Analysis effect
Rate.Mass data ETL processing is exactly the source driving trace data that will be obtained at data acquisition server, is pressed
The process for being extracted, being changed and being loaded according to setting format content.It can specifically include：
Data pick-up, the process of data needed for acquisition from the driving trace information of source, data extraction process can mistake
Unwanted source data field or data record are filtered, such as filters out the nonstandard data of license plate number, remove
The unrelated field such as track where vehicle.Support multiple data sources (such as：FTP service, data warehouse etc.)
And a variety of data formats (formatted text file, database table etc.).
Data conversion, it is according to default data structure, the fields of one or more source datas is translated,
The operations such as matching, polymerization obtain the field of target data.Form conversion, field is supported to merge with splitting, number
According to translation, Data Matching, data aggregate.Such as be converted to the reticle of preset data structure the card time excessively
Formula.
Data load, and are into target data source data by data conversion, it is possible to directly added by data
Tool loads are carried into target database.Support plurality of target data-storage system, including Hadoop platform,
Relevant database etc..
The data volume of source driving trace information by above-mentioned processing can be reduced, and data format can be unified, because
The efficiency and accuracy rate of this subsequent detection matching process all can be higher.
In the present embodiment, except using above-mentioned driving trace, this dimension judges that vehicle whether there is deck phenomenon
Outside, information of vehicles this dimension when can be combined with vehicle registration is judged.Using the judgement of various dimensions
The accuracy of judgement can be lifted.Now, the also settable information of vehicles table of the first database in the present embodiment,
The information of vehicles table includes the vehicle management information of all vehicles obtained from vehicle management department, each vehicle
Management information all includes license plate number and information of vehicles, and wherein information of vehicles is including but not limited to license plate number, vehicle body
Color, vehicle.Source driving trace information in the present embodiment also includes information of vehicles.Entered according to information of vehicles
The process of row deck detection is as follows：
Extraction is (following comprising the license plate number in the driving trace information of source from the information of vehicles table of the first database
Stated with the target carriage trade mark) target vehicle management information, judge in the target vehicle management information
When information of vehicles mismatches with the information of vehicles in the driving trace information of source, judge vehicle to be detected for fake-licensed car.
That is, include the target of the above-mentioned target carriage trade mark when being not present in each vehicle management information in information of vehicles table
During management information, it is the license plate number of non-method to show the target carriage trade mark, is not registered, can be direct
Judge the vehicle to be detected for fake-licensed car.Meanwhile exist when in each vehicle management information in information of vehicles table
Include the objective management information of the above-mentioned target carriage trade mark, but in the objective management information information of vehicles (namely
The information registered during registration) with source driving trace information in information of vehicles it is inconsistent when, also judge that this is to be checked
Measuring car is fake-licensed car.
In the present embodiment, according to above-mentioned driving trace and/or information of vehicles judge vehicle for fake license plate vehicle it
Afterwards, the license plate number can be also stored into fake-licensed car table, and fake-licensed car table can also be set directly at the first number
According in storehouse.
In the present embodiment, it is exactly that will directly include the car that license plate number, which is stored to the most direct mode of fake-licensed car table,
The source driving trace information of the trade mark is stored in the fake-licensed car table, naturally it is also possible to car corresponding to directly individually storing
The trade mark.And storage when, when be according to track detection go out for fake-licensed car when, increase be identified as track
With not being inconsistent, such as can be represented with 1.When be according to information of vehicles detect for fake-licensed car when, increase mark
It is not inconsistent for information of vehicles matching, such as can be represented with 0.After so storing, during subsequent query,
Personnel query can be supported unconditionally to inquire about, now directly can entirely exported the fake-licensed car table, inquirer
Member is not only it is known which is fake-licensed car, it can also be seen that the reasons why being judged as fake-licensed car.Also support to look into
Inquiry personnel's input inquiry condition is inquired about, now matched from fake-licensed car table meet querying condition (such as
In certain time period, either a certain bayonet socket or a certain car plate etc.) data shown.
S102 and S103 in the present embodiment can be realized by real-time distributed computing system (storm).
Storm is a set of great expandability, quick surprising and possess the distributed computing system of increasing income of fault-tolerant ability,
Its height is absorbed in stream process field.Storm has outstanding performance in terms of event handling with incremental computations, can be with
Real-time mode is handled according to continually changing parameter logistic according to stream.Real-time distributed computing system (storm)
The message for receiving kafka distribution modules and issuing can be undertaken in systems, the above-mentioned vehicle of progress crosses bayonet socket time difference meter
Calculate, information of vehicles and vehicle administration office information of the time difference compared with minimum time value, in mistake car data contrast, simultaneously
Data after processing are carried out to be put in storage the functions such as preservation.
The scheme that the present embodiment provides can combine real-time inspection of the Hadoop+storm realizations to vehicle fake-license situation
Survey, it is relatively existing simple using board car detection mode is realized based on Hadoop, can solve mass data
Storage, calculating and inquiry problem, and can accomplishes detection, real-time report in real time, while can also reduce and deposit
Storage and calculating pressure, lift resource utilization.
Embodiment two：
A kind of vehicle fake-license detecting system is present embodiments provided, it is shown in Figure 2, including data acquisition system
System 21 and real-time distributed computing system (storm) 22；
Data-acquisition system 21 is used to obtain the current source driving trace information of vehicle to be detected and issues implementation point
Cloth computing system, when source driving trace information includes license plate number, the bayonet socket information currently passed through and crosses card
Between.Wherein, bayonet socket information includes being used for the information for identifying each bayonet socket, including but not limited to bayonet socket numbering, card
Mouth positional information；Spending the card time then refers to time when vehicle passes through bayonet socket.
Specifically, data-acquisition system 21 includes data acquisition module 211 and data interaction platform 212；
Data acquisition module 211 is used to obtain the current source traveling of vehicle to be detected from each bayonet socket IMAQ end
Track data simultaneously issues data interchange platform.In the present embodiment, for as core space database datas such as urban districts
Measure larger, more acquisition servers can be configured while gather core space database in terms of acquisition strategies；For
The small region of data volume, can be by the way of an acquisition server gathers multi-region regional data base simultaneously.
The video or image that bayonet socket IMAQ end in the present embodiment collects monitoring camera can also be carried out
Image algorithm processing, including the identification of image preprocessing, Car license recognition, vehicle color, vehicle cab recognition, speed
The functions such as detection.Result after the processing of bayonet socket IMAQ end has been structural data, including car plate, car
Body color, model, bayonet socket numbering, bayonet socket the address location information such as driving lane even where vehicle.Data
The source driving trace packet that acquisition module 211 is got contains above-mentioned data.
Data interchange platform 212 includes distributed post and subscribes to message (kafka) distribution module 2121, is used for
Source driving trace data conversion is issued into real-time distributed calculate into the source driving trace message of message format is
System.For source driving trace message of the source driving trace data conversion into message format to be issued in next step
Real-time distributed computing system.Now data interaction platform then subscribes to information client side as distributed post
(kafka client).Kafka is that a kind of distributed post of high-throughput subscribes to message system, is passed through O (1)
Disk data structure provide message persistence, there is high-throughput and prolonged stability.
To sum up, the data interchange platform 212 in the present embodiment is mainly used in storage, the management of data after collection
And inquiry.Storage and reading inquiry particularly for HDFS data, and kafka message distribution.
In the present embodiment, distributed post subscribes to message (kafka) distribution module 2121 and travels rail in distribution source
During mark message, the driving trace data of each car of each bayonet socket can be issued as a piece of news,
And can be distributed in distribution procedure using the mechanism of load balancing, or it is same using ensureing as far as possible
The principle that the data of data or same license plate number on bayonet socket are dealt into same calculate node is distributed.And its
It can also be distributed to during specific distribution for each source driving trace message according to time order and function order real-time distributed
Computing system.
Data interchange platform 212 also includes memory module 2122, for by from the bayonet socket IMAQ of each bayonet socket
Hold obtain source driving trace data the second databases of Cun Chudao in, and storage rule can use using bayonet socket as
Unit carries out partitioned storage, or in units of bayonet socket on the basis of progress partitioned storage, can also be in chronological sequence
Order is by each source driving trace data storage in the second database.The data being stored in the second database can
Using as preliminary data, in case historical query or otherwise calling.The second data in the present embodiment
Storehouse can also be the database of Hadoop types, such as HDFS (Hadoop Distributed File System,
Hadoop distributed file systems) database, also it is not excluded for using other kinds of database certainly.
Real-time distributed computing system 22 includes trajectory analysis module 221, for the bayonet socket from the first database
The target travel trace information that extraction includes license plate number in car table is crossed, according to source driving trace information and target line
Sail the bayonet socket information in trace information, the card time excessively determines whether vehicle to be detected is fake license plate vehicle；Bayonet socket mistake
The newest driving trace information of car table storage vehicle.
The first database in the present embodiment can be the database of Hadoop types, such as Hbase (Hadoop
Database) database, also it is not excluded for using other kinds of database certainly.Bayonet socket mistake in the present embodiment
As long as car table stores its newest driving trace information for each vehicle, it is not necessary to stores vehicle institute
Some driving trace information or the driving trace information in a period, can substantially reduce transport data stream
Pressure is stored, while the efficiency of subsequent detection can also be lifted.
Specifically, trajectory analysis module 221 is used to obtain source driving trace information and target travel trace information
In bayonet socket information corresponding to minimum range Dmin between two bayonet sockets, then according to default maximum travelling speed
Minimum time value Tmin=Dmin/Vmax is calculated in Vmax.
Trajectory analysis module 221 is additionally operable to cross card time t1 and target travel in the driving trace information of calculating source
Whether the difference T=t1-t2 for spending card time t2 in trace information is less than minimum time value Tmin, in this way, shows
There is deck suspicion in the vehicle to be detected, be determined as fake-licensed car.Most narrow spacing in the present embodiment between two bayonet sockets
It can be air line distance therebetween from Dmin, now can directly be counted according to the latitude and longitude information of each bayonet socket
The minimum range for obtaining or actually measuring therebetween is calculated, now then needs to measure and store in advance
Well so that follow-up use is inquiry.Each bayonet socket can set unique bayonet socket to number in the present embodiment, Ye Jitong
Cross each bayonet socket of bayonet socket numbering can unique identification.Also can not be that each bayonet socket sets bayonet socket to number, and by each
The positional information of bayonet socket itself carries out unique identification, therefore the position that different bayonet sockets are set is different.
In the present embodiment, trajectory analysis module 221 is crossed in car table to extract and included from the bayonet socket of the first database
After the target travel trace information of license plate number in the driving trace information of source, in addition to delete bayonet socket and cross in car table
The target travel trace information, source driving trace information is stored in the bayonet socket and crosses car table, to ensure the card
The driving trace information stored in journey of making a slip of the tongue table is newest.
Trajectory analysis module 221 is additionally operable to cross in car table from the bayonet socket of the first database and not extracted comprising car plate
Number target travel trace information when, now show before license plate number in the source driving trace information also not by
Counted, the source driving trace information deposit bayonet socket is directly crossed into car table, thus crosses in car table and increases in bayonet socket
The driving trace information of a license plate number is added.Counted with different obtain of data, in bayonet socket process table
The license plate number of driving trace information can be caused to cover will be more perfect.
Shown in Figure 3, real-time distributed computing system 22 also includes ETL in the present embodiment
(Extract-Transform-Load) data cleansing module 222, for subscribing to message in distributed post
(kafka) source driving trace message is issued real-time distributed computing system (storm) by distribution module 2121
After 22, before track analysis module 221 carries out trajectory analysis judgement according to the source driving trace message,
The source driving trace information sent to kafka distribution modules carries out ETL (Extract-Transform-Load)
Processing, because source data amount is very big, deal with very time-consuming, it is possible to data reduction is preferentially carried out,
To improve follow-up data Treatment Analysis efficiency.Mass data ETL processing is exactly will be at data acquisition server
The source driving trace data of acquisition, the process for being extracted, being changed and being loaded according to setting format content, tool
Body processing procedure will not be repeated here.
In the present embodiment, except using above-mentioned driving trace, this dimension judges that vehicle whether there is deck phenomenon
Outside, information of vehicles this dimension when can be combined with vehicle registration is judged.Using the judgement of various dimensions
The accuracy of judgement can be lifted.Now, the also settable information of vehicles table of the first database in the present embodiment,
The information of vehicles table includes the vehicle management information of all vehicles obtained from vehicle management department, each vehicle
Management information all includes license plate number and information of vehicles, and wherein information of vehicles is including but not limited to license plate number, vehicle body
Color, vehicle.Source driving trace information in the present embodiment also includes information of vehicles.Real-time distributed calculating
System 22 also includes information of vehicles analysis module 223, for being extracted from the information of vehicles table of the first database
Include the target vehicle pipe of the license plate number (being stated below with the target carriage trade mark) in the driving trace information of source
Information is managed, judges that the information of vehicles in the target vehicle management information is believed with the vehicle in the driving trace information of source
When breath mismatches, judge vehicle to be detected for fake-licensed car.That is, the analysis of information of vehicles analysis module 223 is worked as
The objective management information for including the above-mentioned target carriage trade mark is not present in each vehicle management information in information of vehicles table
When, it is the license plate number of non-method to show the target carriage trade mark, is not registered, and can directly judge that this is to be detected
Vehicle is fake-licensed car.Meanwhile include above-mentioned target when existing in each vehicle management information in information of vehicles table
The objective management information of license plate number, but the information of vehicles in the objective management information (namely is registered during registration
Information) with source driving trace information in information of vehicles it is inconsistent when, also judge the vehicle to be detected for deck
Car.
In the present embodiment, trajectory analysis module 221 is additionally operable to when judging vehicle to be detected for fake-licensed car, will
License plate number is stored in the fake-licensed car table in the first database, and is identified as path matching and is not inconsistent, such as can use 0
Represent；
And/or information of vehicles analysis module 223 is additionally operable to when judging vehicle to be detected for fake-licensed car, by car
The trade mark is stored in the fake-licensed car table in the first database, and is identified as information of vehicles matching and is not inconsistent, such as can be with
Represented with 1.
After so storing, during subsequent query, personnel query can be supported unconditionally to inquire about, also may be used
To support that personnel query input inquiry condition is inquired about, inquiry mode is versatile and flexible, can meet different use
The different demands at family.
Obviously, those skilled in the art should be understood that each module of the embodiments of the present invention or each step
It can be realized with general computing device, they can be concentrated on single computing device, or distribution
On the network that multiple computing devices are formed, alternatively, the program that they can be can perform with computing device
Code is realized, it is thus possible to be stored in computer-readable storage medium (ROM/RAM, magnetic disc, light
Disk) in performed by computing device, and in some cases, can be to be performed different from order herein
Shown or described step, either they are fabricated to respectively each integrated circuit modules or by they
In multiple modules or step be fabricated to single integrated circuit module to realize.So the present invention is not restricted to
Any specific hardware and software combines.
Embodiment three：
In order to be better understood from the present invention, the technical scheme of 4 pairs of embodiment of the present invention below in conjunction with the accompanying drawings
Implementation is described in further detail.
S401：Bayonet socket IMAQ end (such as monitoring camera) capture card mouth traffic flow video or picture,
Traffic block port video acquisition processing front end is pre- to video or image progress image algorithm processing, including image again
The functions such as processing, Car license recognition, vehicle color identification, vehicle cab recognition, Bus- Speed Monitoring.Knot after processing
Fruit includes：The information such as license plate number, vehicle color, vehicle, speed, runway.
S402：Data acquisition module passes through JDBC (Java Data Base Connectivity, java numbers
Being connected according to storehouse) mode obtains bayonet socket in result and system after all bayonet socket IMAQ end image procossings
Information, and be all aggregated into after generating file on data interchange platform.
S403：Data interchange platform is responsible for that data univesral distribution formula is stored and managed.It is required that according to bayonet socket
Number order and time sequencing arrive data (data of a vehicle are a source driving trace data) storage
In second database (HDFS databases).
S404：Data interchange platform will be passed through as kafkaclient by kafka message distributions module
The data of each car of each bayonet socket are distributed to storm systems with message format according to time order and function order
In.Often processing one car data excessively will send a kafka message, and (a kafka message is one
Source driving trace message), multiple messages can be continuously sent out always；Ensure the car of same bayonet socket when distributing simultaneously
Message is sent in same calculate node and analyzed as far as possible.
S405：After message is sent to storm systems, it is responsible for receiving kafka message by kafkaSpout.
S406：Kafka message is sent to ETL data cleansing modules and carries out data cleansing by kafkaSpout
Work.The major function of ETL data cleansing modules includes：Filter out the incomplete data of license plate number information,
Numbered according to bayonet socket by the useful field information of bayonet socket information completion, extraction, be integrated into a reference format
Data etc..Data format and content after cleaning integration are：License plate number | spend the car time | bayonet socket is numbered |
Bayonet socket dimension | bayonet socket longitude | body color | vehicle.
S407：The kafka message cleaned after integrating is separately sent to trajectory analysis by ETL data cleansing modules
Module (miniTimeBolt) and information of vehicles analysis module (BMCContrasBolt) carry out fake-licensed car point
Analysis detection.Wherein trajectory analysis module is using minimum time threshold value comparative approach, information of vehicles analysis mould
Block is using vehicle administration office's information comparison method.
S408：Trajectory analysis module passes through the He of embodiment one according to the message that ETL data cleansing modules are sent
Judgment mode shown in embodiment two judges whether stimulated the menstrual flow time difference of former and later two bayonet sockets of vehicle is less than
The minimum time threshold value of two bayonet sockets, to decide whether as suspicion fake license plate vehicle.If fake license plate vehicle,
Fake license plate vehicle information is sent to the first database (Hbase databases) fake-licensed car table
(toHbaseT2Bolt) in.Meanwhile source driving trace information data is completely sent in real time by this
The bayonet socket of first database (Hbase databases) is crossed in car table (toHbaseT1Bolt), with more new car
Trace information.
ToHbaseT1Bolt is responsible for this real-time kafka message (source driving trace information) data
The complete bayonet socket being all saved in Hbase is crossed in car table T1, is preserved entry ginseng and is shown in Table 1, wherein
Row major key Rowkey is designed as license plate number.
Table 1
S409：Information of vehicles analysis module is believed by the vehicle in the message that sends ETL data cleansing modules
Breath is compared with vehicle administration office's information of vehicles to determine whether suspicion fake-licensed car, and comparison process is referring to implementation
Shown in example one and embodiment two, it will not be repeated here.If fake license plate vehicle, fake license plate vehicle information is sent out
It is sent to the first database (Hbase databases) fake-licensed car table (toHbaseT2Bolt).
ToHbaseT2Bolt is responsible in the fake-licensed car table T2 that suspicion fake license plate vehicle information is saved in Hbase,
Row major key Rowkey is designed as license plate number.Meanwhile one field of increase be used for being identified as minimum time value (
That is trajectory analysis) contrast is mismatched or vehicle administration office's information of vehicles is compared and mismatched.Wherein, 0 represent most
Small time value contrast mismatches, and 1, which represents vehicle administration office's information of vehicles, compares mismatch.Entry is preserved referring to table 2
It is shown：
Table 2
S410：The querying condition such as input license plate number, excessively car period, bayonet socket numbering carries out fake license plate vehicle and looked into
Ask.If being not provided with querying condition, acquiescence exports all periods, all fake license plate vehicle information, if setting
Querying condition is put then to export to meet the fake license plate vehicle information of condition, including the control point position of process, time
Etc. information.
Real-time detection to vehicle fake-license situation is realized using the scheme for combining Hadoop+storm, with existing skill
Art is compared, and the real-time analysis for realizing fake license plate vehicle calculates, and has reached the effect of real-time monitoring Real-time Alarm,
The storage pressure of huge traffic data stream is greatlyd save simultaneously.
Above content is to combine the further description that specific embodiment is made to the embodiment of the present invention,
The specific implementation of the invention is not to be limited to these illustrations.For the general of the technical field of the invention
For logical technical staff, without departing from the inventive concept of the premise, can also make it is some it is simple deduce or
Replace, should all be considered as belonging to protection scope of the present invention.
Claims (11)
- A kind of 1. vehicle fake-license detecting system, it is characterised in that including：Data-acquisition system is divided with real-time Cloth computing system；The data-acquisition system is used to obtain the current source driving trace information of vehicle to be detected and issued described Implement distributed computing system, the bayonet socket information that the source driving trace information includes license plate number, currently passed through And spend the card time；The real-time distributed computing system includes trajectory analysis module, for the bayonet socket mistake from the first database Extraction include the target travel trace information of the license plate number in car table, according to the source driving trace information with Bayonet socket information, card time excessively in the target travel trace information determine whether the vehicle to be detected is set Board vehicle；The bayonet socket crosses the newest driving trace information of car table storage vehicle.
- 2. vehicle fake-license detecting system as claimed in claim 1, it is characterised in that the source travels rail Mark information also includes information of vehicles, and the real-time distributed computing system also includes information of vehicles analysis module, For target vehicle management letter of the extraction comprising the license plate number from the information of vehicles table of first database Breath, judge that the information of vehicles in the target vehicle management information is believed with the vehicle in the source driving trace information When breath mismatches, judge that the vehicle to be detected is fake-licensed car；The information of vehicles table includes the vehicle management information of all vehicles obtained from vehicle management department, institute State vehicle management packet and contain license plate number and information of vehicles.
- 3. vehicle fake-license detecting system as claimed in claim 1, it is characterised in that the trajectory analysis The bayonet socket information that module is used to obtain in the source driving trace information and the target travel trace information is corresponding Two bayonet sockets between minimum range, when obtaining minimum according to the minimum range and default maximum travelling speed Between be worth, judge in the source driving trace information and the target travel trace information cross the card time difference whether Less than the minimum time value, in this way, judge that the vehicle to be detected is fake-licensed car.
- 4. vehicle fake-license detecting system as claimed in claim 2, it is characterised in that the trajectory analysis Module is additionally operable to when judging the vehicle to be detected for fake-licensed car, by license plate number deposit first number According in the fake-licensed car table in storehouse, and it is identified as path matching and is not inconsistent；And/or the information of vehicles analysis module is additionally operable to when judging the vehicle to be detected for fake-licensed car, The license plate number is stored in the fake-licensed car table in first database, and is identified as information of vehicles matching not Symbol.
- 5. the vehicle fake-license detecting system as described in claim any one of 1-4, it is characterised in that described Trajectory analysis module is additionally operable to after extracting the target travel trace information, is deleted the bayonet socket and is crossed in car table The target travel trace information, the source driving trace information is stored in the bayonet socket and crosses car table；Or it is additionally operable to not extract comprising the license plate number crossing in car table from the bayonet socket of first database During target travel trace information, the source driving trace information is stored in the bayonet socket and crosses car table.
- 6. the vehicle fake-license detecting system as described in claim any one of 1-4, it is characterised in that described Data-acquisition system data include data acquisition module and data interaction platform；The data acquisition module is used to obtain the current source traveling of vehicle to be detected from each bayonet socket IMAQ end Track data simultaneously issues the data interchange platform；The data interchange platform includes distributed post and subscribes to message distribution module, for the source to be travelled The source driving trace message that track data is converted into message format issues the real-time distributed computing system.
- 7. vehicle fake-license detecting system as claimed in claim 6, it is characterised in that the data exchange Platform also includes memory module, for by the source driving trace data by units of bayonet socket carry out subregion deposit Storage principle is stored in the second database.
- 8. vehicle fake-license detecting system as claimed in claim 6, it is characterised in that first data Storehouse is Hbase databases, and second database is HDFS databases.
- 9. a kind of vehicle fake-license detection method, including：Obtain the current source driving trace information of vehicle to be detected, the source driving trace information include license plate number, The bayonet socket information currently passed through and mistake card time；The target travel trace information that extraction includes the license plate number in car table is crossed from the bayonet socket of the first database；Bayonet socket information in the source driving trace information and the target travel trace information, when crossing card Between determine whether the vehicle to be detected is fake license plate vehicle；The bayonet socket crosses the newest traveling of car table storage vehicle Trace information.
- 10. vehicle fake-license detection method as claimed in claim 9, it is characterised in that the source travels rail Mark information also includes information of vehicles, and methods described also includes：Target vehicle management of the extraction comprising the license plate number is believed from the information of vehicles table of first database Breath, judge that the information of vehicles in the target vehicle management information is believed with the vehicle in the source driving trace information When breath mismatches, judge that the vehicle to be detected is fake-licensed car；The information of vehicles table includes the vehicle management information of all vehicles obtained from vehicle management department, institute State vehicle management packet and contain license plate number and information of vehicles.
- 11. the vehicle fake-license detection method as described in claim 9 or 10, it is characterised in that methods described Also include：After extracting the target travel trace information, the target travel rail that the bayonet socket is crossed in car table is deleted Mark information, the source driving trace information is stored in the bayonet socket and crosses car table；Or the target line that is not extracted in car table and include the license plate number is being crossed from the bayonet socket of first database When sailing trace information, the source driving trace information is stored in the bayonet socket and crosses car table.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610543659.0A CN107610471A (en) | 2016-07-11 | 2016-07-11 | Vehicle fake-license detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610543659.0A CN107610471A (en) | 2016-07-11 | 2016-07-11 | Vehicle fake-license detection method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107610471A true CN107610471A (en) | 2018-01-19 |
Family
ID=61054792
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610543659.0A Pending CN107610471A (en) | 2016-07-11 | 2016-07-11 | Vehicle fake-license detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107610471A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108281003A (en) * | 2018-01-30 | 2018-07-13 | 中兴智能交通股份有限公司 | A kind of recognition methods of fake-licensed car and device |
| CN109711276A (en) * | 2018-12-06 | 2019-05-03 | 新华三技术有限公司 | A kind of deck detection method and device |
| CN110164136A (en) * | 2019-03-29 | 2019-08-23 | 重庆市城投金卡信息产业(集团)股份有限公司 | Fake license plate vehicle recognition method |
| CN110164138A (en) * | 2019-05-17 | 2019-08-23 | 湖南科创信息技术股份有限公司 | Based on bayonet to the recognition methods for the fake license plate vehicle for flowing to probability and system, medium |
| CN110570652A (en) * | 2019-07-30 | 2019-12-13 | 深圳市天彦通信股份有限公司 | vehicle fake plate detection reminding method and related product |
| CN110910648A (en) * | 2019-12-18 | 2020-03-24 | 航天信息股份有限公司 | Illegal vehicle reconnaissance method and system based on block chain |
| CN111008214A (en) * | 2019-10-22 | 2020-04-14 | 广州阳光耐特电子有限公司 | Intelligent visual vehicle information analysis system |
| CN111402574A (en) * | 2018-12-13 | 2020-07-10 | 阿里巴巴集团控股有限公司 | Vehicle detection method, device, equipment and storage medium |
| CN111461094A (en) * | 2020-06-23 | 2020-07-28 | 平安国际智慧城市科技股份有限公司 | Fake-licensed vehicle identification method and device based on monitoring video and computer equipment |
| CN111767776A (en) * | 2019-12-28 | 2020-10-13 | 西安宇视信息科技有限公司 | Abnormal license plate selection method and device |
| CN114882448A (en) * | 2022-04-01 | 2022-08-09 | 北京卓视智通科技有限责任公司 | Vehicle monitoring method and electronic equipment |
| CN110909567B (en) * | 2018-09-17 | 2023-06-30 | 杭州海康威视系统技术有限公司 | Method and device for intercepting driving failure personnel |
-
2016
- 2016-07-11 CN CN201610543659.0A patent/CN107610471A/en active Pending
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108281003A (en) * | 2018-01-30 | 2018-07-13 | 中兴智能交通股份有限公司 | A kind of recognition methods of fake-licensed car and device |
| CN110909567B (en) * | 2018-09-17 | 2023-06-30 | 杭州海康威视系统技术有限公司 | Method and device for intercepting driving failure personnel |
| CN109711276B (en) * | 2018-12-06 | 2021-04-30 | 新华三技术有限公司 | Fake plate detection method and device |
| CN109711276A (en) * | 2018-12-06 | 2019-05-03 | 新华三技术有限公司 | A kind of deck detection method and device |
| CN111402574A (en) * | 2018-12-13 | 2020-07-10 | 阿里巴巴集团控股有限公司 | Vehicle detection method, device, equipment and storage medium |
| CN110164136A (en) * | 2019-03-29 | 2019-08-23 | 重庆市城投金卡信息产业(集团)股份有限公司 | Fake license plate vehicle recognition method |
| CN110164138A (en) * | 2019-05-17 | 2019-08-23 | 湖南科创信息技术股份有限公司 | Based on bayonet to the recognition methods for the fake license plate vehicle for flowing to probability and system, medium |
| CN110570652A (en) * | 2019-07-30 | 2019-12-13 | 深圳市天彦通信股份有限公司 | vehicle fake plate detection reminding method and related product |
| CN111008214A (en) * | 2019-10-22 | 2020-04-14 | 广州阳光耐特电子有限公司 | Intelligent visual vehicle information analysis system |
| CN110910648A (en) * | 2019-12-18 | 2020-03-24 | 航天信息股份有限公司 | Illegal vehicle reconnaissance method and system based on block chain |
| CN111767776A (en) * | 2019-12-28 | 2020-10-13 | 西安宇视信息科技有限公司 | Abnormal license plate selection method and device |
| CN111767776B (en) * | 2019-12-28 | 2024-03-29 | 西安宇视信息科技有限公司 | Abnormal license plate selecting method and device |
| CN111461094A (en) * | 2020-06-23 | 2020-07-28 | 平安国际智慧城市科技股份有限公司 | Fake-licensed vehicle identification method and device based on monitoring video and computer equipment |
| CN114882448A (en) * | 2022-04-01 | 2022-08-09 | 北京卓视智通科技有限责任公司 | Vehicle monitoring method and electronic equipment |
| CN114882448B (en) * | 2022-04-01 | 2023-10-31 | 北京卓视智通科技有限责任公司 | Vehicle monitoring method and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107610471A (en) | Vehicle fake-license detection method and system | |
| CN108959466B (en) | Taxi passenger carrying hot spot visualization method and system based on BCS-DBSCAN | |
| CN104200669B (en) | Fake-licensed car recognition method and system based on Hadoop | |
| CN105206057B (en) | Detection method and system based on Floating Car resident trip hot spot region | |
| CN110225457B (en) | Method and device for supervising shared bicycle, server and readable storage medium | |
| CN104809887B (en) | A kind of retrograde detection method of vehicle on expressway and autoalarm | |
| CN107038168A (en) | A kind of user's commuting track management method, apparatus and system | |
| CN108513676A (en) | A kind of road conditions recognition methods, device and equipment | |
| CN108734129A (en) | mobile phone and vehicle location analysis method and system | |
| CN103578277B (en) | Deck suspicion car searching method and device thereof | |
| CN106323301A (en) | Road information obtaining method and device | |
| CN103295120B (en) | Logistics company transport power analyzes system and the method for transport power analysis thereof | |
| CN105825671B (en) | A kind of adjoint vehicle analysis method and system based on the full track collision of big data vehicle | |
| WO2018176191A1 (en) | Method and apparatus for identifying vehicle with fake registration plate | |
| CN113570864B (en) | Method and device for matching running path of electric bicycle and storage medium | |
| CN106297304A (en) | A kind of based on MapReduce towards the fake-licensed car recognition methods of extensive bayonet socket data | |
| CN107067736B (en) | Fake-licensed car analysis method and its system based on time road network | |
| CN107204117A (en) | The recognition methods of fake-licensed car | |
| CN112562330A (en) | Method and device for evaluating road operation index, electronic equipment and storage medium | |
| Garg et al. | Mining bus stops from raw GPS data of bus trajectories | |
| CN114841712B (en) | Method and device for determining illegal operation state of network appointment vehicle tour and electronic equipment | |
| CN114023076B (en) | Specific vehicle tracking method based on multi-source heterogeneous data | |
| CN109272760B (en) | Online detection method for abnormal data value of SCATS system detector | |
| CN106297301A (en) | A kind of vehicle fake-license inspection method and the vehicle fake-license detecting system of use the method | |
| CN111369790B (en) | Vehicle passing record correction method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180119 |
|
| WD01 | Invention patent application deemed withdrawn after publication |