CN107977421A - The method and device of fake-licensed car analysis is carried out based on big data - Google Patents
The method and device of fake-licensed car analysis is carried out based on big data Download PDFInfo
- Publication number
- CN107977421A CN107977421A CN201711189930.6A CN201711189930A CN107977421A CN 107977421 A CN107977421 A CN 107977421A CN 201711189930 A CN201711189930 A CN 201711189930A CN 107977421 A CN107977421 A CN 107977421A
- Authority
- CN
- China
- Prior art keywords
- car
- fake
- license plate
- licensed
- data
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/5838—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/5846—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using extracted text
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/5866—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Library & Information Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
This application discloses a kind of method and device that fake-licensed car analysis is carried out based on big data, the method comprising the steps of：HADOOP big data platforms are built, distributed message server KAFKA and distributed data base HBASE is installed on the basis of HADOOP big data platforms；Intelligent capture apparatus caught car picture, after parsing corresponding structured text information, sent to distributed message server KAFKA；Distributed message server KAFKA receives the structured text information that intelligent capture apparatus is sent and is stored under same TOPIC；Fake-licensed car is analyzed；And car record will be crossed and be sent to alarm module, the details and picture address that alarm module crosses car record in a manner of short message by two are sent on the cell-phone number specified.The present invention only needs the car data of crossing that bayonet is shot to achieve that fake-licensed car identifies independent of vehicle administration office's database.
Description
Technical field
The present invention relates to big data analysis and technical field of control over intelligent traffic, is to be related to a kind of be based on greatly specifically
Data carry out the method and device of fake-licensed car analysis.
Background technology
Recently as the improvement of people's living standards, the quantity of automobile is more and more, cut-off in March, 2017 whole nation machine
Motor-car ownership breaks through 300,000,000, and nearly annual in 5 years increases by 14,000,000.Identification difficulty of more automobiles to fake-licensed car is also more
Come bigger, substantial amounts of fake-licensed car brings substantial amounts of interference for the investigation of public security organ.With more and more cases with
Vehicle is related, and vehicle has become essential instrument in offender's crime, life, and most offender's car
Can all use fake license during crime, quickly recognizing fake-licensed car, to be clear up a criminal case dash forward with the key for arresting suspect
Breakpoint.It may also be said that the dynamic that fake-licensed car has just grasped suspect is grasped.
It is existing to fake-licensed car know method for distinguishing by vehicle contrast, the method depend on vehicle administration office database, it is necessary to
The correct information of registered vehicle is read from vehicle administration office, when front end tollgate devices are captured to information of vehicles, identifies car plate, car
The information such as type, read correct vehicle according to license plate number from vehicle administration office's database, are determined as fake-licensed car if vehicle difference.This
The limitation of method is the data for needing to rely on vehicle administration office, but many counties or prefecture-level city cannot coordinate the number of vehicle administration office well
According to；The other is the accuracy rate to vehicle cab recognition is relied on, but identification of the vehicle cab recognition program to vehicle is accurate on the market at present
Rate is not high, to shooting the height of photo, angle, bright dark etc. more demanding.Still an alternative is that installed on motor vehicle
Rfid chips, include the information such as the license plate number, vehicle, Motor Number of vehicle in this chip, when with the motor-driven of rfid chips
When garage is sailed at monitoring device, mounted equipment can read the information such as license plate number, vehicle in rfid chips, be clapped with bayonet
The license plate number taken the photograph is compared, if the license plate number of tollgate devices identification is identical with the license plate number read in rfid chips, non-set
Board car, if it is different, the vehicle then shot is exactly fake license plate vehicle, such a method needed to install rfid chips on motor vehicle at that time,
Also need to build the base station for reading rfid chips, input cost is higher, and enforcement difficulty is larger.Number of patent application is
201410407364 method is the then form of storage result by MapReduce batch quantity analysis fake-licensed cars, it is well known that
MapReduce is batch processing frame, is suitable for the requirement that processing data amount is big but timeliness is not high, but for the knowledge of fake-licensed car
Do not need to identify in real time, and notify the position of fake-licensed car at once, otherwise fake license plate vehicle is gone for again after disappearing, and difficulty is not with knowing
Other fake-licensed car is the same, and all the method are not appropriate for the use of reality scene.
The problem of difficulty is big, timeliness is low is being identified to fake-licensed car in upper type, is more causing criminal to be without restraint,
Hang fake license to swindle by false pretences everywhere, break laws and commit crime.
Therefore it provides it is a kind of efficiently in real time and the method for progress fake-licensed car detection easily implemented is that this area is urgently to be resolved hurrily
Problem.
The content of the invention
The technical problems to be solved by the invention are to provide a kind of method analyzed in real time based on big data progress fake-licensed car
And system, solve the problems, such as that fake-licensed car identification difficulty is big instantly, timeliness is low.
In order to solve the above technical problems, the present invention provides a kind of method that fake-licensed car analysis is carried out based on big data, bag
Include step：
HADOOP big data platforms are built, distributed message server is installed on the basis of HADOOP big data platforms
KAFKA and distributed data base HBASE, creates two tables in distributed data base HBASE, with license plate number in one of table
Other information in addition to license plate number and car plate color are stored as ROWKEY, COLUMN information with car plate color, which is used to delay
Deposit the last of all license plate numbers and cross car record；Another table is fake-licensed car information result table, with fake-licensed car cross the car time,
License plate number and bayonet numbering be ROWKEY, COLUMN information storage except fake-licensed car cross the car time, license plate number and bayonet numbering with
Outer other information, the table are used to store the fake-licensed car information analyzed；
Intelligent capture apparatus caught car picture, after parsing corresponding structured text information, sends to distribution and disappears
Server KAFKA is ceased, the structured text information includes license plate number, car plate color, crosses car time and camera site；
The structured text information that intelligent capture apparatus is sent that distributed message server KAFKA receives is stored in same
Under TOPIC；
Fake-licensed car is analyzed：Message is read under the same TOPIC of the distributed message server KAFKA to memory
In, and extract license plate number, car plate color from current message, cross car time and camera site, first by the license plate number and car of extraction
Board color inquires about the data for whether having identical ROWKEY, if inquiring not as ROWKEY from the HBASE tables created
Have data, then by this data using license plate number and car plate color as ROWKEY, using cross the car time, taking location information as
COLUMN information, is stored in the table of HBASE, and recent as the car plate crosses car record；If having inquired data, adjust
The data that inquire are taken out, and extracted car time and camera site field, this car record of crossing twice is the car plate nearest two
Secondary crosses car record, crosses the coordinate that the camera site that car records checks in camera site from bayonet information table respectively twice according to this
A(x1,y1), B (x2,y2), and with Euclidean distance calculation formula：
The Euclidean distance for crossing car place twice is calculated, then spends car time t according to cross car data twice1And t2, meter
Calculate time difference t1-t2, according to formula speed=distance/time, i.e. v=d (A, B)/(t1-t2), draw from bayonet A to bayonet B
Theoretical velocity；
If speed V is less than or equal to threshold speed set in advance, then it is assumed that vehicle is normal, and by this from distributed message
Car data of crossing in the message read in server KAFKA is stored in HBASE tables using license plate number and car plate color as ROWKEY
In, the data of an identical ROWKEY are changed, recent as the license plate number crosses car record；If the speed is more than pre-
The threshold speed first set, then judge this car for doubtful fake-licensed car, this two are crossed car record respectively to cross car time, license plate number
It is saved in bayonet numbering as ROWKEY in the fake-licensed car analysis result table created in HBASE；
And the car record of crossing is sent to alarm module, alarm module crosses car record in a manner of short message by this two
Details and picture address be sent on the cell-phone number specified.
Preferably, the inquiry of fake-licensed car result is further included：The inquiry of fake-licensed car result is in the web system based on B/S frameworks
Middle inquiry, is equipped with time started, end time, wherein license plate number, license plate number in the browser page data qualification of web system
Support is searched for generally, with No. * replace multidigit, withThe mode of number replacement one is searched for generally；
During inquiry after the input page data qualification of browser foreground, system is combined according to starting and end time
Scan, then from the fake-licensed car analysis result table, the deck car data of inquiry scope this period；If inputting license plate number,
Then result is filtered according to license plate number and is illustrated in browser page.
The invention also discloses a kind of device that fake-licensed car analysis is carried out based on big data, put down based on HADOOP big datas
Platform, including messenger service module, memory module, intelligent capture apparatus, fake-licensed car analysis module and alarm module, wherein,
The intelligence capture apparatus, couples with messenger service mould distributed message server KAFKA phases in the block, uses
In catching car picture, after parsing corresponding structured text information, send to distributed message server KAFKA, it is described
Structured text information includes license plate number, car plate color, crosses car time and camera site；
The messenger service module, is distributed message server KAFKA, respectively with the intelligent capture apparatus and deck
Car analysis module mutually couples, and is stored in for structured text information of the reception from the transmission of intelligent capture apparatus same
Under TOPIC；
The memory module, is distributed data base HBASE, is mutually coupled with the fake-licensed car analysis module, for
The caching of information of vehicles and the storage to fake-licensed car information are crossed, two tables are created in distributed data base HBASE, one of them
Other letters in addition to license plate number and car plate color are stored as ROWKEY, COLUMN information using license plate number and car plate color in table
Breath, another table be fake-licensed car information result table, with fake-licensed car spend the car time, license plate number and bayonet number be ROWKEY,
COLUMN information stores the other information crossed in addition to car time, license plate number and bayonet are numbered except fake-licensed car, which is used to store
The fake-licensed car information analyzed；
The fake-licensed car analysis module, mutually couples with messenger service module, memory module and the alarm module respectively, uses
In the information newly issued from the acquisition of messenger service module in real time, identical license plate number, identical car with what is cached in memory module
Upper one of board color crosses car data and compares, and carries out fake-licensed car analysis, if the memory module that fake-licensed car is then sent saves,
Otherwise identical license plate number, the upper a data of car plate color cached in caching is replaced：
Message is read under the same TOPIC of the distributed message server KAFKA into memory, and from currently to disappear
License plate number, car plate color are extracted in breath, crosses car time and camera site, first using the license plate number of extraction and car plate color as
ROWKEY, inquires about the data for whether having identical ROWKEY from the HBASE tables created, if inquiring no data,
By this data using license plate number and car plate color as ROWKEY, to cross car time, taking location information as COLUMN information,
It is stored in the table of HBASE, recent as the car plate crosses car record；If having inquired data, transfer out and inquire
Data, and extracted car time and camera site field, this twice cross car record be the car plate recently twice cross car note
Record, the coordinate A (x that the camera site that car records checks in camera site from bayonet information table respectively are crossed according to this twice1,y1), B
(x2,y2), and with Euclidean distance calculation formula：
The Euclidean distance for crossing car place twice is calculated, then spends car time t according to cross car data twice1And t2, meter
Calculate time difference t1-t2, according to formula speed=distance/time, i.e. v=d (A, B)/(t1-t2), draw from bayonet A to bayonet B
Theoretical velocity；
If speed V is less than or equal to threshold speed set in advance, then it is assumed that vehicle is normal, and by this from distributed message
Car data of crossing in the message read in server KAFKA is stored in HBASE tables using license plate number and car plate color as ROWKEY
In, the data of an identical ROWKEY are changed, recent as the license plate number crosses car record；If the speed is more than pre-
The threshold speed first set, then judge this car for doubtful fake-licensed car, this two are crossed car record respectively to cross car time, license plate number
It is saved in bayonet numbering as ROWKEY in the fake-licensed car analysis result table created in HBASE, car note is crossed by described
Record is sent to alarm module；
The alarm module, mutually couples with the fake-licensed car analysis module, receives what the fake-licensed car analysis module was sent
Two datas, the details and picture address for crossing car record by this two in a manner of short message are sent to the cell-phone number specified
On.
Preferably, the enquiry module of fake-licensed car result is further included, is mutually coupled with the memory module, fake-licensed car result is looked into
Ask module to inquire about in the web system based on B/S frameworks, when being equipped with beginning in the browser page data qualification of web system
Between, the end time, license plate number, wherein license plate number support search for generally, with No. * replace multidigit, withThe mode of number replacement one into
Row is searched for generally；
During inquiry after the input page data qualification of browser foreground, system is combined according to starting and end time
Scan, then from the fake-licensed car analysis result table, the deck car data of inquiry scope this period；If inputting license plate number,
Then result is filtered according to license plate number and is illustrated in browser page.
Compared with prior art, the method for the present invention that fake-licensed car analysis is carried out based on big data, has reached as follows
Effect：
The present invention only needs the car data of crossing that bayonet is shot to achieve that fake-licensed car is identified independent of vehicle administration office's database,
The principle used is to appear in impossible two places within a short period of time, then the vehicle is doubtful fake-licensed car；
Fake-licensed car discriminance analysis is efficient in the present invention, and this method is based on HADOOP big data platforms, is disappeared using distribution
Cease server KAFKA and distributed database HBASE.When what front end was shot crosses after car data is transmitted through coming at once with regard to that can judge to be somebody's turn to do
Whether car is accused of fake-licensed car；
Fake-licensed car identification timeliness of the present invention is high, and this method framework is based on HADOOP big data platforms, the mistake of front end shooting
Car data is directly transmitted through to analyze, and draws analysis result in real time, and can real-time informing people's police；
Fake-licensed car identification cost is low in the present invention, based on HADOOP big data platforms, without other hardware costs.Serious forgiveness
Height, can be deployed on cheap server；
Solving a case to public security department has great reference significance, efficient, real-time using this method identification fake-licensed car, to public affairs
Peace solves a case and has great help, improves case handling efficiency.
Brief description of the drawings
Attached drawing described herein is used for providing a further understanding of the present invention, forms the part of the present invention, this hair
Bright schematic description and description is used to explain the present invention, does not form inappropriate limitation of the present invention.In the accompanying drawings：
Fig. 1 is the method flow diagram for carrying out fake-licensed car analysis in embodiment 1 based on big data；
Fig. 2 is data flow schematic diagram in embodiment 1；
Fig. 3 is the apparatus structure schematic diagram for carrying out fake-licensed car analysis in embodiment 2 based on big data；
Fig. 4 is the device work flow diagram for carrying out fake-licensed car analysis in embodiment 2 based on big data；
Wherein, 301- messenger services module；302- memory modules；303- intelligence capture apparatus；304- fake-licensed cars analyze mould
Block；305- alarm modules.
Embodiment
Some vocabulary has such as been used to censure specific components among specification and claim.Those skilled in the art should
It is understood that hardware manufacturer may call same component with different nouns.This specification and claims are not with name
The difference of title is used as the mode for distinguishing component, but is used as the criterion of differentiation with the difference of component functionally.Such as logical
The "comprising" of piece specification and claim mentioned in is an open language, therefore should be construed to " include but do not limit
In "." substantially " refer in receivable error range, those skilled in the art can be described within a certain error range solution
Technical problem, basically reaches the technique effect.In addition, " coupling " word is herein comprising any direct and indirect electric property coupling
Means.Therefore, if one first device of described in the text is coupled to a second device, representing the first device can directly electrical coupling
The second device is connected to, or the second device is electrically coupled to indirectly by other devices or coupling means.Specification
Subsequent descriptions for implement the present invention better embodiment, so it is described description be by illustrate the present invention rule for the purpose of,
It is not limited to the scope of the present invention.Protection scope of the present invention is when subject to appended claims institute defender.
The present invention is described in further detail below in conjunction with attached drawing, but it is not as a limitation of the invention.
Embodiment 1：
With reference to Fig. 1, a kind of method that fake-licensed car analysis is carried out based on big data, including following step are present embodiments provided
Suddenly：
Step 101：HADOOP big data platforms are built, distributed message is installed on the basis of HADOOP big data platforms
Server KAFKA and distributed data base HBASE, creates two tables in distributed data base HBASE, in one of table with
License plate number stores other information in addition to license plate number and car plate color with car plate color as ROWKEY, COLUMN information, another
A table is fake-licensed car information result table, is ROWKEY, COLUMN information with cross car time, license plate number and the bayonet numbering of fake-licensed car
The other information crossed in addition to car time, license plate number and bayonet are numbered except fake-licensed car is stored, which is used to store the set analyzed
Information vehicle license plate；
Step 102：Intelligent capture apparatus caught car picture, after parsing corresponding structured text information, sent extremely
Distributed message server KAFKA, the structured text information include license plate number, car plate color, spend car time and shooting position
Put；
Step 103：Distributed message server KAFKA receives the structured text information storage that intelligent capture apparatus is sent
Under same TOPIC；
Step 104：Fake-licensed car is analyzed：Message is read under the same TOPIC of the distributed message server KAFKA
Into memory, and extract license plate number, car plate color from current message, cross car time and camera site, first by the car plate of extraction
Number and car plate color as ROWKEY, the data for whether having identical ROWKEY are inquired about from the HBASE tables created, if looking into
No data are ask, then by this data using license plate number and car plate color as ROWKEY, to cross car time, taking location information
As COLUMN information, it is stored in the table of HBASE, recent as the car plate crosses car record；If having inquired data,
Then transfer out the data inquired, and extracted car time and camera site field, this twice cross car record be the car plate most
Car of crossing closely twice records, and crosses the camera site that car records twice according to this and checks in camera site from bayonet information table respectively
Coordinate A (x1,y1), B (x2,y2), and with Euclidean distance calculation formula：
The Euclidean distance for crossing car place twice is calculated, then spends car time t according to cross car data twice1And t2, meter
Calculate time difference t1-t2, according to formula speed=distance/time, i.e. v=d (A, B)/(t1-t2), draws from bayonet A to bayonet B
Theoretical velocity；
If speed V is less than or equal to threshold speed set in advance, then it is assumed that vehicle is normal, and by this from distributed message
Car data of crossing in the message read in server KAFKA is stored in HBASE tables using license plate number and car plate color as ROWKEY
In, the data of an identical ROWKEY are changed, recent as the license plate number crosses car record；If the speed is more than pre-
The threshold speed first set, then judge this car for doubtful fake-licensed car, this two are crossed car record respectively to cross car time, license plate number
It is saved in bayonet numbering as ROWKEY in the fake-licensed car analysis result table created in HBASE；
Step 105：The car record of crossing is sent to alarm module, alarm module crosses car in a manner of short message by this two
The details and picture address of record are sent on the cell-phone number specified.
Further include the inquiry of step 106 fake-licensed car result：The inquiry of fake-licensed car result is in the web system based on B/S frameworks
Middle inquiry, is equipped with time started, end time, wherein license plate number, license plate number in the browser page data qualification of web system
Support is searched for generally, with No. * replace multidigit, withThe mode of number replacement one is searched for generally；
During inquiry after the input page data qualification of browser foreground, system is combined according to starting and end time
Scan, then from the fake-licensed car analysis result table, the deck car data of inquiry scope this period；If inputting license plate number,
Then result is filtered according to license plate number and is illustrated in browser page.
In application process, car picture and the structured text information parsed are crossed by what front end tollgate devices were shot first
It is sent in real time in distributed message server KAFKA, structured text information includes at least license plate number, car plate color, crosses car
The information such as time, camera site.
Fake-licensed car analysis program read car data from KAFKA first, is taken out license plate number, car plate color, crosses car
The information such as time and camera site.Program will read data using license plate number+car plate color as ROWKEY from the table of HBASE,
If having read data, data are taken out and are compared with this data, vehicle is that appear within a short period of time can not if judging
The two places of energy, then vehicle is doubtful fake-licensed car.Then this two information are sent to alarm module, the last short message of alarm module
Form by this two doubtful fake-licensed car data sendings to the mobile phone of people's police, and this two information are deposited into HBASE's
In.
The program of identification fake-licensed car specifically includes the following steps：
1) according to the numbering of the camera site of two datas, the coordinate of camera site is inquired from bayonet information table, is counted
The Euclidean distance of two coordinates is calculated, because the program is generally deployed in county or prefecture-level city, therefore it is ellipse that can ignore the earth
The fact, therefore the formula calculated is the distance of two-dimensional space, it is assumed that bayonet A (x1,y1), B (x2,y2), distance calculation formula is such as
Under：
Thus the Euclidean distance d of two bayonets is obtained, by the car time difference (t excessively of Euclidean distance divided by two datas1-t2),
Obtain theoretical velocity v, the v=d/ (t by bayonet A to bayonet B1-t2)。
2) if v is more than the threshold value of setting, then the doubtful fake-licensed car of this two cars is thought.System then crosses car data hair by this two
The alarm module sent, on the mobile phone that people's police are then notified in the form of short message.In addition system by this two data with cross car when
Between+license plate number+bayonet numbering is saved in HBASE distributed data bases as ROWKEY, easy to rapidly and efficiently inquire about later.
If 3) v be less than or equal to setting threshold value, then it is assumed that road speed v is reasonable, system can by this data with license plate number+
Car plate color is stored in HBASE tables, the data before replacing, the newest of the car plate is used as using this data as ROWKEY
Cross car data.
If 4) can not find out data in table using license plate number+car plate color as ROWKEY in this step, system by this
Bar information is stored in HBASE tables with license plate number+car plate color, and car time and shooting position were wherein included at least in this information
Put.
As shown in Fig. 2, data flow is as follows：
1) HADOOP big data platforms are built first, and distributed message clothes are installed on HADOOP big data platform bases
Be engaged in device KAFKA and distributed data base HBASE.
2) two tables are created in distributed data base HBASE, analyzes and uses for fake-licensed car, one of table is with license plate number
As ROWKEY, the storage of COLUMN information other information, this table in addition to license plate number and car plate color are used to store+car plate color
The last driving recording of all license plate numbers.Another fake-licensed car information result table is numbered with crossing car time+license plate number+bayonet
As ROWKEY, the other information in addition to car time, license plate number, bayonet numbering is crossed is stored in COLUMN information, this table is used for
Store the fake-licensed car information analyzed.Because HBASE bottoms employ the file memory format of HFILE, HFILE be in itself according to
A kind of storage format of ROWKEY pre-sortings, so HBASE is directed to the inquiry for specifying ROWKEY and range query efficiency compares
Height, the range query of HBASE realize that Scan, which can be specified, starts ROWKEY and end ROWKEY, HBASE using Scan
Retrieve the data of specified range.
3) fake-licensed car analysis program is disposed, and is started.
4) it is daily to cross capture and parsing of the car data by front end intelligence capture apparatus, by car picture recognition at least
Comprising license plate number, car plate color, cross the structured text information such as car time, camera site.
5) the car information of crossing that headend equipment is identified is sent in distributed message server KAFKA specifically in real time
In TOPIC.Message can be evenly distributed on different servers by the subregion in TOPIC as far as possible, balanced big data quantity
With concurrent pressure, issue and the efficiency consumed are improved.Different classes of message can be issued in different TOPIC, be easy to
Different consumer spendings.KAFKA has the characteristic of high-throughput, can also be supported even if very common hardware KAFKA per second
Millions of message.And the persistence for the disk data structure offer message for passing through O (1), this structure can be TB grades with logarithm
Message keep stability.
6) car analysis program provides a consumer first, it is in real time from the same TOPIC of message server KAFKA
Lower consumption message, that is, read message into memory.And license plate number, car plate color are extracted from current message, crosses car time, shooting
The information such as position.System first can be using license plate number+car plate color of extraction as ROWKEY, from the HBASE tables created
It is middle to inquire about the data for whether having identical ROWKEY, if inquiring no data, this data is made with license plate number+car plate color
For ROWKEY, to cross the other information such as car time, camera site as COLUMN information, it is stored in the table of HBASE, as the car
The recent of board crosses car record.If having inquired data, the data inquired are taken out, and extracted car time and shooting
The fields such as position, then this twice cross car record be exactly the car plate recently twice cross car record.According to this shooting twice
Position checks in the coordinate A (x of camera site from bayonet information table respectively1,y1), B (x2,y2).And calculated with Euclidean distance public
Formula：
The Euclidean distance for crossing car place twice is calculated.Then car time t is crossed according to mistake car data twice1,t2, meter
Calculate time difference t1-t2, according to formula speed=distance/time, i.e. v=d (A, B)/(t1-t2),
Draw the theoretical velocity from bayonet A to bayonet B.If the speed is less than or equal to threshold speed set in advance, recognize
It is normal for vehicle, and new this is crossed into car data and is stored in using license plate number+car plate color as ROWKEY in HBASE tables, because
There is uniqueness for ROWKEY, can so replace the data of an identical ROWKEY, nearest one as the license plate number
It is secondary to cross car record.If the speed is more than threshold speed set in advance, judge this car for doubtful fake-licensed car.System by this two
Bar crosses car record and the set created in HBASE is saved in as ROWKEY to cross car time+license plate number+bayonet numbering respectively
In board car analysis result table, then system can be sent to this two data alarm module, and alarm module will in a manner of short message
On the cell-phone number specified that this two details for crossing car record and picture address are sent.
7) inquiry of fake-licensed car result, fake-licensed car result queries system are the web system based on B/S frameworks, the first page
There are time started, end time, license plate number in data qualification.Wherein license plate number support search for generally (replace multidigit with No. *, with
The mode of number replacement one), when the conditional information of front page layout input is passed to backstage, system is according to starting and end time
Combination S can, then from fake-licensed car analysis result table, the deck car data of inquiry scope this period, if user have input car
The trade mark, then filter result according to license plate number and show user.
Embodiment 2：
With reference to Fig. 3, a kind of device that fake-licensed car analysis is carried out based on big data is present embodiments provided, which is based on
HADOOP big data platforms, including messenger service module 301, memory module 302, intelligent capture apparatus 303, fake-licensed car analysis mould
Block 304 and alarm module 305.
The intelligence capture apparatus 303, with the distributed message server KAFKA phases in the messenger service module 301
Coupling, for catching car picture, after parsing corresponding structured text information, sends to distributed message server
KAFKA, the structured text information include license plate number, car plate color, cross car time and camera site；
The messenger service module 301, is distributed message server KAFKA, respectively with the intelligent capture apparatus 303
Mutually coupled with fake-licensed car analysis module 304, for receiving the structured text information storage sent from intelligent capture apparatus 303
Under same TOPIC；
The memory module 302, is distributed data base HBASE, is coupled with 304 phase of fake-licensed car analysis module, is used
In the storage to the caching of mistake information of vehicles and to fake-licensed car information, two tables are created in distributed data base HBASE, its
In in a table using license plate number and car plate color as the storage of ROWKEY, COLUMN information in addition to license plate number and car plate color other
Information, another table is fake-licensed car information result table, with fake-licensed car cross the car time, license plate number and bayonet numbering be
ROWKEY, COLUMN information store the other information crossed in addition to car time, license plate number and bayonet are numbered except fake-licensed car, which uses
In the fake-licensed car information that storage analyzes；
The fake-licensed car analysis module 304, respectively with the messenger service module 301, memory module 302 and alarm module
305 phases couple, for obtaining the information newly issued from messenger service module 301 in real time, with having cached in memory module 302
Identical license plate number, upper one car data excessively of identical car plate color compare, and carry out fake-licensed car analysis, if what fake-licensed car was then sent
Memory module 302 saves, and otherwise replaces identical license plate number, the upper a data of car plate color cached in caching：
Message is read under the same TOPIC of the distributed message server KAFKA into memory, and from currently to disappear
License plate number, car plate color are extracted in breath, crosses car time and camera site, first using the license plate number of extraction and car plate color as
ROWKEY, inquires about the data for whether having identical ROWKEY from the HBASE tables created, if inquiring no data,
By this data using license plate number and car plate color as ROWKEY, to cross car time, taking location information as COLUMN information,
It is stored in the table of HBASE, recent as the car plate crosses car record；If having inquired data, transfer out and inquire
Data, and extracted car time and camera site field, this twice cross car record be the car plate recently twice cross car note
Record, the coordinate A (x that the camera site that car records checks in camera site from bayonet information table respectively are crossed according to this twice1,y1), B
(x2,y2), and with Euclidean distance calculation formula：
The Euclidean distance for crossing car place twice is calculated, then spends car time t according to cross car data twice1And t2, meter
Calculate time difference t1-t2, according to formula speed=distance/time, i.e. v=d (A, B)/(t1-t2), draw from bayonet A to bayonet B
Theoretical velocity；
If speed V is less than or equal to threshold speed set in advance, then it is assumed that vehicle is normal, and by this from distributed message
Car data of crossing in the message read in server KAFKA is stored in HBASE tables using license plate number and car plate color as ROWKEY
In, the data of an identical ROWKEY are changed, recent as the license plate number crosses car record；If the speed is more than pre-
The threshold speed first set, then judge this car for doubtful fake-licensed car, this two are crossed car record respectively to cross car time, license plate number
It is saved in bayonet numbering as ROWKEY in the fake-licensed car analysis result table created in HBASE, car note is crossed by described
Record is sent to alarm module 305；
The alarm module 305, couples with 304 phase of fake-licensed car analysis module, receives the fake-licensed car analysis module
304 two datas sent, the details and picture address for crossing car record by this two in a manner of short message are sent to specified
Cell-phone number on.
The enquiry module of fake-licensed car result is further included, is coupled with 302 phase of memory module, the inquiry mould of fake-licensed car result
Block is inquired about in the web system based on B/S frameworks, and time started, knot are equipped with the browser page data qualification of web system
Beam time, license plate number, wherein license plate number support search for generally, with No. * replace multidigit, withThe mode of number replacement one carries out mould
Paste search；
During inquiry after the input page data qualification of browser foreground, system is combined according to starting and end time
Scan, then from the fake-licensed car analysis result table, the deck car data of inquiry scope this period；If inputting license plate number,
Then result is filtered according to license plate number and is illustrated in browser page.
It is as shown in Figure 4 for the device that fake-licensed car analysis is carried out based on big data in this implementation, workflow：
1st, intelligence capture apparatus in front end is parsed the picture of capture, by car picture recognition into including at least car plate
Number, car plate color, cross car time, the structured text information such as camera site.
2nd, the car information of crossing that headend equipment is identified is sent in distributed message server KAFKA specifically in real time
In TOPIC.Message can be evenly distributed on different servers by the subregion in TOPIC as far as possible, balanced big data quantity
With concurrent pressure, issue and the efficiency consumed are improved.Different classes of message can be issued in different TOPIC, be easy to
Different consumer spendings.
3rd, fake-licensed car analysis module is used as a consumer first, it is in real time from the same of message server KAFKA
Message is consumed under TOPIC, that is, reads message into memory.And when license plate number, car plate color are extracted from current message, crossing car
Between, the information such as camera site.And the last car of crossing of the car plate is obtained from HBASE tables according to license plate number and car plate color and is remembered
Record.That crosses that car records twice according to this crosses car time and camera site, judges whether to be accused of fake-licensed car, and principle is when shorter
The interior vehicle for appearing in impossible two places has fake-licensed car suspicion.New this is crossed into car number if non-fake-licensed car is judged as
License plate number+car plate color is stored in HBASE tables as ROWKEY according to this, because ROWKEY has uniqueness, can so be replaced
The data of a upper identical ROWKEY, recent as the license plate number cross car record.If judging, this car is accused of deck
Car, system are crossed car record by this two and are saved in respectively using crossing car time+license plate number+bayonet numbering as ROWKEY in HBASE
In the fake-licensed car analysis result table created, then this two data can be sent to alarm module, alarm module by system
On the cell-phone number specified that the details and picture address for crossing car record by this two in a manner of short message are sent.
4th, user's login system, starting and end time is inputted in fake-licensed car query interface, from HBASE fake-licensed cars point
The fake-licensed car in this period is inquired in analysis result table and is shown on the page, and user can also input a mould on the page
The license plate number of paste, multidigit is replaced with No. *, withFuzzy query is carried out to license plate number instead of the mode of one, system can filter out symbol
The fake-licensed car of conjunction condition is illustrated on the page.
Compared with prior art, the method and apparatus of the present invention that fake-licensed car analysis is carried out based on big data, is reached
Following effect：
The present invention only needs the car data of crossing that bayonet is shot to achieve that fake-licensed car is identified independent of vehicle administration office's database,
The principle used is to appear in impossible two places within a short period of time, then the vehicle is doubtful fake-licensed car；
Fake-licensed car discriminance analysis is efficient in the present invention, and this method is based on HADOOP big data platforms, and use is distributed
Message server KAFKA and distributed database HBASE.When at once crossing for front end shooting can just judge after car data is transmitted through coming
Whether the car is accused of fake-licensed car；
Fake-licensed car identification timeliness of the present invention is high, and this method framework is based on HADOOP big data platforms, the mistake of front end shooting
Car data is directly transmitted through to analyze, and draws analysis result in real time, and can real-time informing people's police；
Fake-licensed car identification cost is low in the present invention, based on HADOOP big data platforms, without other hardware costs.Serious forgiveness
Height, can be deployed on cheap server；
Solving a case to public security department has great reference significance, efficient, real-time using this method identification fake-licensed car, to public affairs
Peace solves a case and has great help, improves case handling efficiency.
Some preferred embodiments of the present invention have shown and described in described above, but as previously described, it should be understood that the present invention
Be not limited to form disclosed herein, be not to be taken as the exclusion to other embodiment, and available for various other combinations,
Modification and environment, and above-mentioned teaching or the technology or knowledge of association area can be passed through in the scope of the invention is set forth herein
It is modified., then all should be in this hair and changes and modifications made by those skilled in the art do not depart from the spirit and scope of the present invention
In the protection domain of bright appended claims.
Claims (4)
- A kind of 1. method that fake-licensed car analysis is carried out based on big data, it is characterised in that including step：HADOOP big data platforms are built, distributed message server KAFKA is installed on the basis of HADOOP big data platforms With distributed data base HBASE, two tables are created in distributed data base HBASE, with license plate number and car in one of table Board color stores other information in addition to license plate number and car plate color as ROWKEY, COLUMN information, which is used to cache institute There is the last of license plate number to cross car record；Another table is fake-licensed car information result table, and car time, car plate are crossed with fake-licensed car Number and bayonet numbering to be the storage of ROWKEY, COLUMN information spend the car time, in addition to license plate number and bayonet are numbered except fake-licensed car Other information, the table are used to store the fake-licensed car information analyzed；Intelligent capture apparatus caught car picture, after parsing corresponding structured text information, sends to distributed message and takes Be engaged in device KAFKA, and the structured text information includes license plate number, car plate color, crosses car time and camera site；The structured text information that intelligent capture apparatus is sent that distributed message server KAFKA receives is stored in same Under TOPIC；Fake-licensed car is analyzed：Message is read under the same TOPIC of the distributed message server KAFKA into memory, and License plate number, car plate color are extracted from current message, crosses car time and camera site, first by the license plate number of extraction and car plate face Color is inquired about the data for whether having identical ROWKEY from the HBASE tables created, is not counted if inquiring as ROWKEY According to then by this data using license plate number and car plate color as ROWKEY, to spend the car time, taking location information is used as COLUMN Information, is stored in the table of HBASE, and recent as the car plate crosses car record；If having inquired data, transfer out and look into Data ask, and extracted car time and camera site field, this car record of crossing twice is the mistake of the car plate twice recently Car records, and crosses the coordinate A (x that the camera site that car records checks in camera site from bayonet information table respectively twice according to this1, y1), B (x2,y2), and with Euclidean distance calculation formula：<mrow> <mi>d</mi> <mrow> <mo>(</mo> <mi>A</mi> <mo>,</mo> <mi>B</mi> <mo>)</mo> </mrow> <mo>=</mo> <msqrt> <mrow> <msup> <mrow> <mo>(</mo> <msub> <mi>x</mi> <mn>1</mn> </msub> <mo>-</mo> <msub> <mi>x</mi> <mn>2</mn> </msub> <mo>)</mo> </mrow> <mn>2</mn> </msup> <mo>+</mo> <msup> <mrow> <mo>(</mo> <msub> <mi>y</mi> <mn>1</mn> </msub> <mo>-</mo> <msub> <mi>y</mi> <mn>2</mn> </msub> <mo>)</mo> </mrow> <mn>2</mn> </msup> </mrow> </msqrt> </mrow>The Euclidean distance for crossing car place twice is calculated, then spends car time t according to cross car data twice1And t2, calculate Time difference t1-t2, according to formula speed=distance/time, i.e. v=d (A, B)/(t1-t2), draw the reason from bayonet A to bayonet B By speed；If speed V is less than or equal to threshold speed set in advance, then it is assumed that vehicle is normal, and by this from distributed message service Car data of crossing in the message read in device KAFKA is stored in HBASE tables using license plate number and car plate color as ROWKEY, is changed Fall the data of a upper identical ROWKEY, recent as the license plate number crosses car record；Set in advance if the speed is more than Fixed threshold speed, then judge this car for doubtful fake-licensed car, this two are crossed car record respectively to cross car time, license plate number and card Mouth numbering is saved in as ROWKEY in the fake-licensed car analysis result table created in HBASE；And the car record of crossing is sent to alarm module, alarm module crosses the detailed of car record in a manner of short message by this two Details condition and picture address are sent on the cell-phone number specified.
- 2. the method according to claim 1 that fake-licensed car analysis is carried out based on big data, it is characterised in that further include deck The inquiry of car result：The inquiry of fake-licensed car result is inquired about in the web system based on B/S frameworks, in the browser page of web system Time started, end time, license plate number are equipped with the data qualification of face, wherein license plate number is supported to search for generally, more with * replacements Position, withThe mode of number replacement one is searched for generally；During inquiry after the input page data qualification of browser foreground, system according to starting and end time combination S can, Then from the fake-licensed car analysis result table, the deck car data of inquiry scope this period；If input license plate number, basis License plate number filters result and is illustrated in browser page.
- A kind of 3. device that fake-licensed car analysis is carried out based on big data, it is characterised in that based on HADOOP big data platforms, including Messenger service module, memory module, intelligent capture apparatus, fake-licensed car analysis module and alarm module, wherein,The intelligence capture apparatus, couples with messenger service mould distributed message server KAFKA phases in the block, for catching Car picture was caught, after parsing corresponding structured text information, was sent to distributed message server KAFKA, the structure Change text message to include license plate number, car plate color, cross car time and camera site；The messenger service module, is distributed message server KAFKA, is divided respectively with the intelligent capture apparatus and fake-licensed car Analysis module mutually couples, and is stored in for receiving the structured text information sent from intelligent capture apparatus under same TOPIC；The memory module, is distributed data base HBASE, is mutually coupled with the fake-licensed car analysis module, for crossing car The caching of information and the storage to fake-licensed car information, create two tables in distributed data base HBASE, in one of table Other information in addition to license plate number and car plate color are stored as ROWKEY, COLUMN information using license plate number and car plate color, separately One table is fake-licensed car information result table, is ROWKEY, COLUMN letter with cross car time, license plate number and the bayonet numbering of fake-licensed car Breath storage is used to store what is analyzed except the other information crossed in addition to car time, license plate number and bayonet are numbered of fake-licensed car, the table Fake-licensed car information；The fake-licensed car analysis module, mutually couples with messenger service module, memory module and the alarm module, for reality respectively When slave messenger service module obtain the information newly issued, identical license plate number, identical car plate face with what is cached in memory module Upper one of color crosses car data and compares, and fake-licensed car analysis is carried out, if the memory module that fake-licensed car is then sent saves, otherwise Replace identical license plate number, the upper a data of car plate color cached in caching：Message is read under the same TOPIC of the distributed message server KAFKA into memory, and from current message Extract license plate number, car plate color, cross car time and camera site, first using the license plate number of extraction and car plate color as ROWKEY, The data for whether having identical ROWKEY are inquired about from the HBASE tables created, if inquiring no data, by this number License plate number and car plate color are as ROWKEY according to this, and to spend the car time, taking location information is used as COLUMN information, deposit In the table of HBASE, recent as the car plate crosses car record；If having inquired data, the number inquired is transferred out According to, and extracted car time and camera site field, this twice cross car record be the car plate recently twice cross car record, root The camera site for crossing car record twice according to this checks in the coordinate A (x of camera site from bayonet information table respectively1,y1), B (x2, y2), and with Euclidean distance calculation formula：<mrow> <mi>d</mi> <mrow> <mo>(</mo> <mi>A</mi> <mo>,</mo> <mi>B</mi> <mo>)</mo> </mrow> <mo>=</mo> <msqrt> <mrow> <msup> <mrow> <mo>(</mo> <msub> <mi>x</mi> <mn>1</mn> </msub> <mo>-</mo> <msub> <mi>x</mi> <mn>2</mn> </msub> <mo>)</mo> </mrow> <mn>2</mn> </msup> <mo>+</mo> <msup> <mrow> <mo>(</mo> <msub> <mi>y</mi> <mn>1</mn> </msub> <mo>-</mo> <msub> <mi>y</mi> <mn>2</mn> </msub> <mo>)</mo> </mrow> <mn>2</mn> </msup> </mrow> </msqrt> </mrow>The Euclidean distance for crossing car place twice is calculated, then spends car time t according to cross car data twice1And t2, calculate Time difference t1-t2, according to formula speed=distance/time, i.e. v=d (A, B)/(t1-t2), draw the reason from bayonet A to bayonet B By speed；If speed V is less than or equal to threshold speed set in advance, then it is assumed that vehicle is normal, and by this from distributed message service Car data of crossing in the message read in device KAFKA is stored in HBASE tables using license plate number and car plate color as ROWKEY, is changed Fall the data of a upper identical ROWKEY, recent as the license plate number crosses car record；Set in advance if the speed is more than Fixed threshold speed, then judge this car for doubtful fake-licensed car, this two are crossed car record respectively to cross car time, license plate number and card Mouth numbering is saved in as ROWKEY in the fake-licensed car analysis result table created in HBASE, and car record hair is crossed by described It is sent to alarm module；The alarm module, mutually couples with the fake-licensed car analysis module, receives two that the fake-licensed car analysis module is sent Data, the details and picture address for crossing car record by this two in a manner of short message are sent on the cell-phone number specified.
- 4. the device according to claim 3 that fake-licensed car analysis is carried out based on big data, it is characterised in that further include deck The enquiry module of car result, mutually couples with the memory module, and the enquiry module of fake-licensed car result is in the web based on B/S frameworks Inquired about in system, time started, end time, wherein license plate number, car are equipped with the browser page data qualification of web system The trade mark support search for generally, with No. * replace multidigit, withThe mode of number replacement one is searched for generally；During inquiry after the input page data qualification of browser foreground, system according to starting and end time combination S can, Then from the fake-licensed car analysis result table, the deck car data of inquiry scope this period；If input license plate number, basis License plate number filters result and is illustrated in browser page.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711189930.6A CN107977421A (en) | 2017-11-24 | 2017-11-24 | The method and device of fake-licensed car analysis is carried out based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711189930.6A CN107977421A (en) | 2017-11-24 | 2017-11-24 | The method and device of fake-licensed car analysis is carried out based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107977421A true CN107977421A (en) | 2018-05-01 |
Family
ID=62011381
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711189930.6A Pending CN107977421A (en) | 2017-11-24 | 2017-11-24 | The method and device of fake-licensed car analysis is carried out based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107977421A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108960048A (en) * | 2018-05-23 | 2018-12-07 | 国政通科技股份有限公司 | A kind of searching method and system for the missing tourist in scenic spot based on big data |
| CN109243180A (en) * | 2018-11-20 | 2019-01-18 | 武汉兰芯数据定向传媒有限公司 | A kind of investigation system of illegal vehicle |
| CN110517503A (en) * | 2019-08-28 | 2019-11-29 | 武汉烽火众智数字技术有限责任公司 | Corpse vehicle analysis and early warning method and device based on big data |
| CN110909567A (en) * | 2018-09-17 | 2020-03-24 | 杭州海康威视系统技术有限公司 | Method and device for capturing lost driving personnel |
| CN111079940A (en) * | 2019-11-29 | 2020-04-28 | 武汉烽火众智数字技术有限责任公司 | Decision tree model establishing method and using method for real-time fake-licensed car analysis |
| CN112735144A (en) * | 2020-12-28 | 2021-04-30 | 浙江大华技术股份有限公司 | Fake plate identification method and device, computer equipment and storage medium |
| CN113114754A (en) * | 2021-04-08 | 2021-07-13 | 天津天地伟业智能安全防范科技有限公司 | Transplanting and docking method and device, electronic equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104035954A (en) * | 2014-03-18 | 2014-09-10 | 杭州电子科技大学 | Hadoop-based recognition method for fake-licensed car |
| CN104200669A (en) * | 2014-08-18 | 2014-12-10 | 华南理工大学 | Fake-licensed car recognition method and system based on Hadoop |
| CN106021276A (en) * | 2016-04-28 | 2016-10-12 | 泰华智慧产业集团股份有限公司 | Method and system for checkpoint vehicle search based on distributed full-text retrieval system |
| US20160358462A1 (en) * | 2015-06-05 | 2016-12-08 | Yeon Technologies Co., Ltd. | Method and system for vehicle data integration |
| CN106781497A (en) * | 2017-01-06 | 2017-05-31 | 武汉烽火众智数字技术有限责任公司 | Online vehicle running state detection method and system based on the analysis of point of proximity position |
| CN106875692A (en) * | 2017-03-27 | 2017-06-20 | 武汉烽火众智数字技术有限责任公司 | Vehicle integration early warning system and its method based on big data |
-
2017
- 2017-11-24 CN CN201711189930.6A patent/CN107977421A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104035954A (en) * | 2014-03-18 | 2014-09-10 | 杭州电子科技大学 | Hadoop-based recognition method for fake-licensed car |
| CN104200669A (en) * | 2014-08-18 | 2014-12-10 | 华南理工大学 | Fake-licensed car recognition method and system based on Hadoop |
| US20160358462A1 (en) * | 2015-06-05 | 2016-12-08 | Yeon Technologies Co., Ltd. | Method and system for vehicle data integration |
| CN106021276A (en) * | 2016-04-28 | 2016-10-12 | 泰华智慧产业集团股份有限公司 | Method and system for checkpoint vehicle search based on distributed full-text retrieval system |
| CN106781497A (en) * | 2017-01-06 | 2017-05-31 | 武汉烽火众智数字技术有限责任公司 | Online vehicle running state detection method and system based on the analysis of point of proximity position |
| CN106875692A (en) * | 2017-03-27 | 2017-06-20 | 武汉烽火众智数字技术有限责任公司 | Vehicle integration early warning system and its method based on big data |
Non-Patent Citations (1)
| Title |
|---|
| 李雨: "卡口过车信息挖掘技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108960048A (en) * | 2018-05-23 | 2018-12-07 | 国政通科技股份有限公司 | A kind of searching method and system for the missing tourist in scenic spot based on big data |
| CN108960048B (en) * | 2018-05-23 | 2021-05-25 | 国政通科技股份有限公司 | Big data-based search method and system for scenic spot missing tourists |
| CN110909567A (en) * | 2018-09-17 | 2020-03-24 | 杭州海康威视系统技术有限公司 | Method and device for capturing lost driving personnel |
| CN109243180A (en) * | 2018-11-20 | 2019-01-18 | 武汉兰芯数据定向传媒有限公司 | A kind of investigation system of illegal vehicle |
| CN109243180B (en) * | 2018-11-20 | 2021-05-14 | 武汉兰芯数据定向传媒有限公司 | A system for investigating and punishing illegal vehicles |
| CN110517503A (en) * | 2019-08-28 | 2019-11-29 | 武汉烽火众智数字技术有限责任公司 | Corpse vehicle analysis and early warning method and device based on big data |
| CN111079940A (en) * | 2019-11-29 | 2020-04-28 | 武汉烽火众智数字技术有限责任公司 | Decision tree model establishing method and using method for real-time fake-licensed car analysis |
| CN111079940B (en) * | 2019-11-29 | 2023-03-31 | 武汉烽火众智数字技术有限责任公司 | Decision tree model establishing method and using method for real-time fake-licensed car analysis |
| CN112735144A (en) * | 2020-12-28 | 2021-04-30 | 浙江大华技术股份有限公司 | Fake plate identification method and device, computer equipment and storage medium |
| CN113114754A (en) * | 2021-04-08 | 2021-07-13 | 天津天地伟业智能安全防范科技有限公司 | Transplanting and docking method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107977421A (en) | The method and device of fake-licensed car analysis is carried out based on big data | |
| CN104200671B (en) | A kind of virtual bayonet socket management method based on large data platform and system | |
| CN103246876B (en) | Image feature comparison based counterfeit vehicle registration plate identification method | |
| CN103927880B (en) | A kind of Car license recognition comparison method and device | |
| CN104794901B (en) | Parking lot VATS Vehicle Anti-Theft System and parking lot vehicles management method | |
| CN108492580B (en) | Method and system for judging suspected vehicle | |
| CN204117361U (en) | Based on the Intelligent Parking Peccancy Monitoring System of 360 degree of panoramic cameras | |
| CN115225678A (en) | Driver identity online monitoring method and device and storage medium | |
| CN110163167B (en) | Directional real-time tracking method and system in waiting hall | |
| CN105678879A (en) | Visitor's vehicle management method and system | |
| CN107749856A (en) | Identify the method and system illegally driven | |
| CN101635092A (en) | Identification system and method of unlicensed motor vehicles | |
| CN103927879A (en) | System and method for monitoring illegality of key transport vehicle | |
| CN107730896A (en) | Licence plate recognition method and device | |
| CN102194132A (en) | Detection and identification system and method for accompanying vehicle | |
| CN107563893A (en) | A kind of vehicle insurance Claims Resolution method, client, server and system | |
| CN103500517A (en) | Method and device for detecting parking places of parking lot | |
| CN105913656A (en) | Distributed statistics based method and system for frequently passing vehicles | |
| CN106780886A (en) | A kind of vehicle identification system and vehicle are marched into the arena, appearance recognition methods | |
| CN105448105A (en) | Patrol police vehicle-based monitoring system | |
| CN106710225A (en) | Identification method and monitoring platform for illegal operation related with vehicle license plate | |
| CN109325755A (en) | Electronics charge system based on automotive hub | |
| WO2016113977A1 (en) | Traffic violation management system and traffic violation management method | |
| CN109615900A (en) | Parking navigation charge system and method based on big data | |
| CN103106400B (en) | A kind of method for detecting human face and device |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180501 |
|
| RJ01 | Rejection of invention patent application after publication |