CN106097720A - A kind of traffic block port license plate identification accuracy evaluation methodology - Google Patents
A kind of traffic block port license plate identification accuracy evaluation methodology Download PDFInfo
- Publication number
- CN106097720A CN106097720A CN201610379877.5A CN201610379877A CN106097720A CN 106097720 A CN106097720 A CN 106097720A CN 201610379877 A CN201610379877 A CN 201610379877A CN 106097720 A CN106097720 A CN 106097720A
- Authority
- CN
- China
- Prior art keywords
- car
- license plate
- identification accuracy
- data
- accuracy evaluation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2471—Distributed queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention belongs to big data analysis field, particularly to a kind of traffic block port license plate identification accuracy evaluation methodology.nullFirst the present invention crosses collect in distributed data base HBase that car data stores data cluster，License plate identification accuracy evaluation algorithms is sent in distributed computing system MapReduce by distributed data base HBase with crossing car data，Distributed computing system MapReduce performs described license plate identification accuracy evaluation algorithms，Described distributed computing system MapReduce will identify that the car plate of mistake and described car data of crossing export to relational database Oracle，The car plate identifying mistake in described relational database Oracle and described car data excessively is read by web application，By the quantity of described Car license recognition mistake compared with the total sample number participating in identification，Ratio is the performance indications of license plate identification accuracy，The accuracy of Car license recognition can be passed judgment on exactly by the evaluation methodology of this license plate identification accuracy，And largely avoid the consuming of cost of labor、Efficiency is higher.
Description
Technical field
The invention belongs to big data analysis field, particularly to a kind of traffic block port license plate identification accuracy evaluation methodology.
Background technology
Hadoop is opening for large data sets distributed storage and distributed arithmetic on cluster of a Java language exploitation
The software frame in source, this software frame has provided the user the distributed basis framework that system bottom details is transparent, and Hadoop carries
The distributed programmed model of confession allows user to develop concurrent application in the case of not knowing about distributed system low-level details,
Therefore user can utilize Hadoop easily organizational computing machine resource, thus builds the Distributed Computing Platform of oneself, and
Can make full use of calculating and the storage capacity of cluster, the data completing magnanimity process.
Bayonet socket Car license recognition mistake is generally divided into two kinds, is respectively and the object identification of non-car plate becomes license plate number and car plate know
Not mistake；Error type I typically is caused railing, billboard etc. are identified as car plate by licence plate recognition method self-defect；Second
Class mistake is common in character-recognition errors similar in license plate number.
Accuracy for traffic block port licence plate recognition method is evaluated relying primarily on inspection of manually inspecting and sample at present
Looking into, both approaches greatly consumes manpower and time when carrying out license plate identification accuracy evaluation, therefore, needs proposition one badly
Plant and can reduce manpower and the license plate identification accuracy evaluation methodology of time waste.
Summary of the invention
The present invention is in order to overcome above-mentioned the deficiencies in the prior art, it is provided that a kind of traffic block port license plate identification accuracy is evaluated
Method, in the present invention, the license plate identification accuracy evaluation methodology of proposition can pass judgment on the accuracy of Car license recognition exactly, and
Largely avoid the consuming of cost of labor, efficiency higher.
For achieving the above object, present invention employs techniques below measure:
A kind of traffic block port license plate identification accuracy evaluation methodology, specifically includes following steps:
S1, bayonet camera are crossed collect in distributed data base HBase that car data stores data cluster；
License plate identification accuracy evaluation algorithms and described car data of crossing are sent to by S2, described distributed data base HBase
In distributed computing system MapReduce of Hadoop；
S3, described distributed computing system MapReduce perform described license plate identification accuracy evaluation algorithms；
S4, described distributed computing system MapReduce will identify that the car plate of mistake and described car data of crossing export extremely
In relational database Oracle；
S5, read the car plate and described identifying mistake in described relational database Oracle by web application
Cross car data, and the described car plate identifying mistake and described car data of crossing are illustrated on webpage；
S6, by the quantity of described Car license recognition mistake with participate in identify total sample number compared with, ratio is Car license recognition
The performance indications of accuracy.
Preferably, the license plate identification accuracy evaluation algorithms in step S3 specifically includes following steps:
S31, each car is crossed car data all arrange according to spending the car time, and according to the described card crossed in car data
Mouth longitude and bayonet socket latitude draw the particular location of bayonet socket；
S32, take out the same license plate number of present any two difference bayonet socket position, and calculate same license plate number through two
It's the car time the pasting time difference of individual different bayonet socket, then by apart distance, the root between the particular location of two different bayonet sockets
According to the described ratio at a distance of distance with described time difference, estimate the road speed of this car；
If S33 estimated speed exceedes setting speed, then the Car license recognition mistake of this car.
Preferably, described car data of crossing at least included car time, bayonet socket numbering, bayonet socket longitude, bayonet socket latitude, car plate
Number, car plate picture.
Preferably, before operating procedure S33, if described time difference exceedes two traffic block ports that distance in city is farthest
The maximum duration required when normal vehicle operation, then this car is not involved in calculating.
Further, described distance apart is manhatton distance.
Further, described Car license recognition mistake includes the object identification of non-car plate becomes license plate number and license plate number identification wrong
By mistake.
Further, described setting speed is 200～250Km/h.
The beneficial effects of the present invention is:
1), the present invention is by taking out the same license plate number of present any two difference bayonet socket position, and calculates same car
The trade mark is through it's the car time the pasting time difference of two different bayonet sockets, between the described particular location of two different bayonet sockets
At a distance of distance, according to the described ratio at a distance of distance with described time difference, estimate the road speed of this car, estimated speed
When exceeding setting speed, then the Car license recognition mistake of this car.Can be exactly by the evaluation methodology of this license plate identification accuracy
Pass judgment on the accuracy of Car license recognition, and it is higher to largely avoid the consuming of cost of labor, efficiency, and this method uses letter
Single, easily operated.
2) if described time difference two traffic block ports exceeding distance in city farthest are required when normal vehicle operation
The maximum duration wanted, then this car is not involved in calculating, and substantially increases the efficiency of the Car license recognition of the present invention；Described at a distance of road
Journey is manhatton distance, makes the obtained accuracy at a distance of distance higher.
Accompanying drawing explanation
Fig. 1 is the structure principle chart of the present invention；
Fig. 2 is the concrete structure flow chart of the traffic block port license plate identification accuracy evaluation methodology of the present invention；
Fig. 3 is the structure flow chart of the license plate identification accuracy evaluation algorithms of the present invention.
Detailed description of the invention
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, complete
Describe, it is clear that described embodiment is only a part of embodiment of the present invention rather than whole embodiments wholely.Based on
Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under not making creative work premise
Embodiment, broadly falls into the scope of protection of the invention.
As shown in Figure 1, 2, a kind of traffic block port license plate identification accuracy evaluation methodology, specifically include following steps:
S1, bayonet camera are crossed collect in distributed data base HBase that car data stores large data sets group；
License plate identification accuracy evaluation algorithms and described car data of crossing are sent to by S2, described distributed data base HBase
In distributed computing system MapReduce of Hadoop；
S3, described distributed computing system MapReduce perform described license plate identification accuracy evaluation algorithms；
S4, described distributed computing system MapReduce will identify that the car plate of mistake and described car data of crossing export extremely
In relational database Oracle；
S5, read the car plate and described identifying mistake in described relational database Oracle by web application
Cross car data, and the described car plate identifying mistake and described car data of crossing are illustrated on webpage；
S6, by the quantity of described Car license recognition mistake with participate in identify total sample number compared with, ratio is Car license recognition
The performance indications of accuracy.
License plate identification accuracy evaluation algorithms in step S3 specifically includes following steps:
When S31, practical operation, generally taking a period of time is unit, take here one day for unit, each car is crossed car
Data all arrange according to the car time excessively, and draw bayonet socket according to the described bayonet socket longitude crossed in car data and bayonet socket latitude
Particular location；
S32, take out the same license plate number of present any two difference bayonet socket position, and calculate same license plate number through two
It's the car time the pasting time difference of individual different bayonet socket, then by apart distance, the root between the particular location of two different bayonet sockets
According to the described ratio at a distance of distance with described time difference, estimate the road speed of this car；
If S33 estimated speed exceedes setting speed, then the Car license recognition mistake of this car.
3 concrete steps that license plate identification accuracy evaluation algorithms is described below in conjunction with the accompanying drawings:
S31, each car is crossed car data all according to described cross the car time arrange, as shown in table 1, table 1 is one
The car data of crossing of car crosses the arrangement of car time sequencing according to described, and according to the described bayonet socket longitude crossed in car data and bayonet socket latitude
Degree draws the particular location of bayonet socket；
S32, take out the same license plate number of present any two difference bayonet socket position, and calculate same license plate number through two
It's the car time the pasting time difference of individual different bayonet socket, it's the car time the pasting time difference is T2-T1, then by two different bayonet sockets
Distance apart between particular location, described is manhatton distance at a distance of distance, estimates any two not by manhatton distance
Distance apart between same bayonet socket (bayonet socket numbering is respectively A1, A2), then the manhatton distance between A1-A2 is:
Dm=do ((lng1, lat1), (lng1, lat2))+do ((lng2, lat2), (lng1, lat2)), wherein do table
Showing the Euclidean distance between any two difference bayonet socket, according to table 1, lng1, lat1 is respectively bayonet socket numbering A1
Bayonet socket longitude, bayonet socket latitude；Lng2, lat2 are respectively the bayonet socket longitude of bayonet socket numbering A2, bayonet socket latitude；
According to the described ratio at a distance of distance with described time difference, estimate the road speed of this car, then estimate speed
Degree V=dm/ (T2-T1)；
Further, if described time difference exceedes two farthest traffic block ports of distance in city when normal vehicle operation
Required maximum duration, then this car is not involved in calculating；
Normal vehicle operation refers to vehicle and travels on highway less than required maximum speed.
If S33 estimated speed is more than 210Km/h, then the Car license recognition mistake of this car.
Table 1:
| Spend the car time | Bayonet socket is numbered | Bayonet socket longitude | Bayonet socket latitude | License plate number | Car plate picture | … |
| T1 | A1 | Lng1 | Lat1 | License1 | url1 | |
| T2 | A2 | Lng2 | Lat2 | License1 | url2 | |
| T3 | A3 | Lng3 | Lat3 | License1 | url3 | |
| … | … | … | … | … | … | … |
The actual F-Zero that can run of urban transportation condition institute limiting vehicle is the most relatively low, the most described setting
Speed is 200～250Km/h.
Further, described Car license recognition mistake includes the object identification of non-car plate becomes license plate number and license plate number identification wrong
By mistake.
The evaluation methodology of this license plate identification accuracy can pass judgment on the accuracy of Car license recognition exactly, and greatly avoids
The consuming of cost of labor, efficiency are higher, and this method uses simple, easily operated, can be widely used in traffic
In field.
Claims (7)
1. a traffic block port license plate identification accuracy evaluation methodology, it is characterised in that specifically include following steps:
S1, bayonet camera are crossed collect in distributed data base HBase that car data stores data cluster；
License plate identification accuracy evaluation algorithms and described car data of crossing are sent to by S2, described distributed data base HBase
In distributed computing system MapReduce of Hadoop；
S3, described distributed computing system MapReduce perform described license plate identification accuracy evaluation algorithms；
S4, described distributed computing system MapReduce will identify that the car plate of mistake and described car data of crossing export to relation
In data base Oracle；
S5, by web application read in described relational database Oracle identify mistake car plate and described cross car
Data, and the described car plate identifying mistake and described car data of crossing are illustrated on webpage；
S6, by the quantity of described Car license recognition mistake with participate in identify total sample number compared with, it is accurate that ratio is Car license recognition
The performance indications of property.
2. a kind of traffic block port license plate identification accuracy evaluation methodology as claimed in claim 1, it is characterised in that in step S3
License plate identification accuracy evaluation algorithms specifically include following steps:
S31, each car is crossed car data all arrange according to spending the car time, and according to the described bayonet socket warp crossed in car data
Degree and bayonet socket latitude draw the particular location of bayonet socket；
S32, take out the same license plate number of present any two difference bayonet socket position, and calculate same license plate number through two not
With it's the car time the pasting time difference of bayonet socket, then by the distance apart between the particular location of two different bayonet sockets, according to institute
State the ratio at a distance of distance with described time difference, estimate the road speed of this car；
If S33 estimated speed exceedes setting speed, then the Car license recognition mistake of this car.
3. a kind of traffic block port license plate identification accuracy evaluation methodology as claimed in claim 2, it is characterised in that: described car excessively
Data at least included car time, bayonet socket numbering, bayonet socket longitude, bayonet socket latitude, license plate number, car plate picture.
4. a kind of traffic block port license plate identification accuracy evaluation methodology as claimed in claim 2, it is characterised in that: operating procedure
Before S33, if two traffic block ports that described time difference exceedes distance in city farthest are required when normal vehicle operation
Maximum duration, then this car be not involved in calculate.
5. traffic block port license plate identification accuracy evaluation methodology as claimed in claim 2 a kind of, it is characterised in that: described apart
Distance is manhatton distance.
6. a kind of traffic block port license plate identification accuracy evaluation methodology as claimed in claim 2, it is characterised in that: described car plate
Identify that mistake includes the object identification of non-car plate becomes license plate number and license plate number identification mistake.
7. a kind of traffic block port license plate identification accuracy evaluation methodology as claimed in claim 2, it is characterised in that: described setting
Speed is 200～250Km/h.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610379877.5A CN106097720A (en) | 2016-05-27 | 2016-05-27 | A kind of traffic block port license plate identification accuracy evaluation methodology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610379877.5A CN106097720A (en) | 2016-05-27 | 2016-05-27 | A kind of traffic block port license plate identification accuracy evaluation methodology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106097720A true CN106097720A (en) | 2016-11-09 |
Family
ID=57230709
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610379877.5A Pending CN106097720A (en) | 2016-05-27 | 2016-05-27 | A kind of traffic block port license plate identification accuracy evaluation methodology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106097720A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106056912A (en) * | 2016-07-29 | 2016-10-26 | 浙江银江研究院有限公司 | Bayonet operation state quantitative evaluation method and system |
| CN107862019A (en) * | 2017-10-31 | 2018-03-30 | 泰华智慧产业集团股份有限公司 | A kind of method and device for vehicle of being hidden by day and come out at night based on big data analysis |
| CN112036401A (en) * | 2020-07-14 | 2020-12-04 | 中山大学 | License plate image attribute calibration-based license plate recognition all-in-one machine evaluation method and device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7016901B2 (en) * | 2001-07-31 | 2006-03-21 | Ideal Scanners & Systems, Inc. | System and method for distributed database management of graphic information in electronic form |
| CN104035954A (en) * | 2014-03-18 | 2014-09-10 | 杭州电子科技大学 | Hadoop-based recognition method for fake-licensed car |
| CN104050813A (en) * | 2014-06-30 | 2014-09-17 | 浙江宇视科技有限公司 | Vehicle plate turning detecting method and device |
| CN104200669A (en) * | 2014-08-18 | 2014-12-10 | 华南理工大学 | Fake-licensed car recognition method and system based on Hadoop |
| CN105447487A (en) * | 2015-08-27 | 2016-03-30 | 中山大学 | Evaluation method and system for vehicle license plate identification system |
-
2016
- 2016-05-27 CN CN201610379877.5A patent/CN106097720A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7016901B2 (en) * | 2001-07-31 | 2006-03-21 | Ideal Scanners & Systems, Inc. | System and method for distributed database management of graphic information in electronic form |
| CN104035954A (en) * | 2014-03-18 | 2014-09-10 | 杭州电子科技大学 | Hadoop-based recognition method for fake-licensed car |
| CN104050813A (en) * | 2014-06-30 | 2014-09-17 | 浙江宇视科技有限公司 | Vehicle plate turning detecting method and device |
| CN104200669A (en) * | 2014-08-18 | 2014-12-10 | 华南理工大学 | Fake-licensed car recognition method and system based on Hadoop |
| CN105447487A (en) * | 2015-08-27 | 2016-03-30 | 中山大学 | Evaluation method and system for vehicle license plate identification system |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106056912A (en) * | 2016-07-29 | 2016-10-26 | 浙江银江研究院有限公司 | Bayonet operation state quantitative evaluation method and system |
| CN106056912B (en) * | 2016-07-29 | 2018-10-09 | 浙江银江研究院有限公司 | A kind of bayonet operating status quantitative estimation method and system |
| CN107862019A (en) * | 2017-10-31 | 2018-03-30 | 泰华智慧产业集团股份有限公司 | A kind of method and device for vehicle of being hidden by day and come out at night based on big data analysis |
| CN107862019B (en) * | 2017-10-31 | 2021-01-01 | 泰华智慧产业集团股份有限公司 | Method and device for analyzing vehicles coming out at daytime and night based on big data |
| CN112036401A (en) * | 2020-07-14 | 2020-12-04 | 中山大学 | License plate image attribute calibration-based license plate recognition all-in-one machine evaluation method and device |
| CN112036401B (en) * | 2020-07-14 | 2024-03-26 | 中山大学 | License plate recognition integrated machine evaluation method and device based on license plate image attribute calibration |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020151089A1 (en) | Automatic city land identification system integrating industrial big data and building form | |
| CN104330089B (en) | A kind of method that map match is carried out using history gps data | |
| CN102097002B (en) | Method and system for acquiring bus stop OD based on IC card data | |
| CN111243277A (en) | Commuting vehicle space-time trajectory reconstruction method and system based on license plate recognition data | |
| CN102024152B (en) | Method for recognizing traffic sings based on sparse expression and dictionary study | |
| CN104197945B (en) | Global voting map matching method based on low-sampling-rate floating vehicle data | |
| CN108734129A (en) | mobile phone and vehicle location analysis method and system | |
| WO2017051411A1 (en) | Near real-time modeling of pollution dispersion | |
| CN105513370B (en) | The traffic zone division methods excavated based on sparse license plate identification data | |
| CN106610981A (en) | Verification and upgrading method and system for road information in electronic map | |
| CN104916133B (en) | Road altitude information extraction method and system based on traffic track data | |
| CN110555992B (en) | Taxi driving path information extraction method based on GPS track data | |
| CN106920402A (en) | A kind of time series division methods and system based on the magnitude of traffic flow | |
| CN107240264B (en) | A kind of non-effective driving trace recognition methods of vehicle and urban road facility planing method | |
| CN105606110B (en) | The lookup method and device of reachable path based on depth-first traversal | |
| CN106097720A (en) | A kind of traffic block port license plate identification accuracy evaluation methodology | |
| CN105336164A (en) | Error checkpoint positional information automatic identification method based on big data analysis | |
| CN104732765A (en) | Real-time urban road saturability monitoring method based on checkpoint data | |
| CN105390013A (en) | Method for predicting bus arrival time based on bus IC card | |
| CN106097717A (en) | The signalized intersections average transit time method of estimation merged based on two class floating car datas | |
| CN107564290A (en) | A kind of urban road intersection saturation volume rate computational methods | |
| CN105355047B (en) | The Data Fusion method of many Vehicle Detection source dynamic time granularities | |
| CN109767615A (en) | Road network traffic flow key flow direction and critical path analysis method | |
| CN104298832A (en) | Road network traffic flow analytical method based on RFID technology | |
| CN107368480A (en) | A kind of interest point data type of error positioning, repeat recognition methods and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161109 |
|
| RJ01 | Rejection of invention patent application after publication |