CN105448099A - Motor vehicle fake license identification method based on big data - Google Patents
Motor vehicle fake license identification method based on big data Download PDFInfo
- Publication number
- CN105448099A CN105448099A CN201510929267.3A CN201510929267A CN105448099A CN 105448099 A CN105448099 A CN 105448099A CN 201510929267 A CN201510929267 A CN 201510929267A CN 105448099 A CN105448099 A CN 105448099A
- Authority
- CN
- China
- Prior art keywords
- data
- motor vehicle
- vehicle
- fake license
- identification method
- 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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a motor vehicle fake license identification method based on big data. The HDFS can be used for the storage and the management of the vehicle data, and the computer network can be used to connect the storage nodes used for storing the vehicle information of different servers, and then the MapReduce distributed data processing capability can be adopted, and in addition, the fake license comparison analysis task can be sent to various cluster nodes to realize the comparison calculation. The processing of the massive vehicle data can be realized, and the problem of the exponential growth of the vehicle information can be solved, and then the requirements on the high-efficiency storage and access can be satisfied. The motor vehicle fake license identification method is advantageous in that the high-performance server is not necessary, and the fake-licensed vehicles can be identified effectively and accurately in the big data environment by using the cheap server; the motor vehicle fake license identification method is not only suitable for the motor vehicle fake license analyzing system, but also suitable for other similar vehicle comparison analyzing systems.
Description
Technical field
The present invention relates to a kind of motor vehicle deck recognition methods based on large data.
Background technology
All the time, unlicensed motor vehicles is of common occurrence throughout the country, has had a strong impact on traffic safety order, has invaded legitimate rights or interests of others, is an outstanding and insoluble problem in present road traffic offence.The identification of unlicensed motor vehicles mainly by concentrating bayonet socket, mistake car information that electronic police waited car information acquisition system to gather, using the number-plate number, car plate kind as analysis condition, using public security department's benchmark vehicle information bank as analysis rule, to compare filtration according to following 3 kinds of analysis principles:
1, the principle of two kinds of body colors can not be had according to the vehicle of a number-plate number;
2, the principle of two kinds of type of vehicle can not be had according to the vehicle of a number-plate number;
3, " simultaneously " or " in very short time " principle at two different crossings can not be appeared at according to the vehicle of a number-plate number.
Current most of unlicensed motor vehicles identification adopts the mode of data centralization comparison, and specific implementation schematic diagram as shown in Figure 1.Adopt fairly simple on technology realizes in this way, only need each real-time car information and the public security department's benchmark information of vehicles excessively gathered be compared.But the drawback of this mode is also apparent, first the increasing extent along with bayonet socket, electronic police covering is wide, and the swift and violent growth of road traveling vehicle, car information of the crossing exponentially level producing, accumulate increases, the data capacity stored reaches PB rank, the thing followed also can exponentially level increase for the hardware cost storing these and cross car information, and in the scope that project funds is certain, this mode can not meet the demand of efficient storage and access.Secondly unlicensed motor vehicles analysis needs to process each vehicle through bayonet socket, and the quantity of operand and parallel processing is very large, the high concurrent reading and writing demand adopting data centralization alignments to be difficult to meet deck to analyze.
Summary of the invention
The present invention relates to a kind of motor vehicle deck recognition methods under bayonet socket crosses car mass data environment, adopt Distributed Parallel Computing, unlicensed motor vehicles can be identified efficiently and accurately.
A kind of motor vehicle deck recognition methods based on large data of the present invention, comprises the following steps:
The car data excessively of the bayonet socket that step 1, former termination enter, electronic police, as input value, being mapped to different block by Map function by crossing car data, distributing to each server cluster and processing;
In step 2, each server cluster, each clustered node processes the task of corresponding data block respectively, and compared with public security department benchmark information of vehicles respectively by the car data of being correlated with of each block, corresponding each block produces intermediate result data collection respectively;
Step 3, using each intermediate result data collection as input value, carry out de-redundancy merger by Reduce function, if namely there are more than two or two number plate kinds, data that brand number is identical, be then merged into one, otherwise do not merge;
Step 4, by merge after result be saved in unlicensed motor vehicles storehouse.
The present invention adopts framework based on Hadoop, and the most crucial design of Hadoop is exactly HDFS and MapReduce.HDFS is a kind of distributed memory system, and be used for being deployed on cheap hardware, the data for magnanimity provide distributed storage organization; MapReduce is a kind of programming model, for the concurrent operation of large-scale dataset, it is a framework large operation being split as multiple little operation, what user's needs made is exactly that decision splits into how many parts, and definition operation itself, the present invention is to the large-scale operation of data set, each node be distributed on network carries out computing, and each node periodically can return the work and up-to-date state that it completes, thus achieves the Distributed Parallel Computing function of large data.
Accompanying drawing explanation
Fig. 1 is conventional truck deck analysis principle schematic diagram;
Fig. 2 is MapReduce workflow schematic diagram;
Fig. 3 is workflow schematic diagram of the present invention.
Below in conjunction with the drawings and specific embodiments, the invention will be further described.
Embodiment
The present invention uses HDFS store and management to cross car data, connected being dispersed in memory node different server storing car information by computer network, utilize the ability of MapReduce distributed data processing, deck compare of analysis share tasks to each clustered node, realize parallel contrast conting.
MapReduce process data procedures is mainly divided into 2 stages: Map stage and Reduce stage, by Map function, unlicensed motor vehicles is analysed and compared share tasks on each server cluster, each clustered node is analysed and compared, after producing intermediate result, receive intermediate result by Reduce method again, after carrying out duplicate removal process, export final fake license plate vehicle analysis result.
As shown in Figure 2, a kind of motor vehicle deck recognition methods based on large data of the present invention, comprises the following steps:
The car data excessively of the bayonet socket that step 1, former termination enter, electronic police, as input value, being mapped to different block by Map function by crossing car data, distributing to each server cluster and processing;
In step 2, each server cluster, each clustered node processes the task of corresponding data block respectively, and compared with public security department benchmark information of vehicles respectively by the car data of being correlated with of each block, corresponding each block produces intermediate result data collection respectively;
Step 3, using each intermediate result data collection as input value, carry out de-redundancy merger by Reduce function, if namely there are more than two or two number plate kinds, data that brand number is identical, be then merged into one, otherwise do not merge;
Step 4, by merge after result be saved in unlicensed motor vehicles storehouse.
The present invention adopts framework based on Hadoop.The most crucial design of Hadoop is exactly HDFS and MapReduce.HDFS is a kind of distributed memory system, and be used for being deployed on cheap hardware, the data for magnanimity provide distributed storage organization; MapReduce is a kind of programming model, for the concurrent operation of large-scale dataset, it is a framework large operation being split as multiple little operation, what user's needs made is exactly that decision splits into how many parts, and definition operation itself, the present invention is to the large-scale operation of data set, each node be distributed on network carries out computing, and each node periodically can return the work and up-to-date state that it completes, thus achieves the Distributed Parallel Computing function of large data.
The above, it is only present pre-ferred embodiments, not technical scope of the present invention is imposed any restrictions, thus every above embodiment is done according to technical spirit of the present invention any trickle amendment, equivalent variations and modification, all still belong in the scope of technical solution of the present invention.
Claims (1)
1., based on a motor vehicle deck recognition methods for large data, it is characterized in that comprising the following steps:
The car data excessively of the bayonet socket that step 1, former termination enter, electronic police, as input value, being mapped to different block by Map function by crossing car data, distributing to each server cluster and processing;
In step 2, each server cluster, each clustered node processes the task of corresponding data block respectively, and compared with public security department benchmark information of vehicles respectively by the car data of being correlated with of each block, corresponding each block produces intermediate result data collection respectively;
Step 3, using each intermediate result data collection as input value, carry out de-redundancy merger by Reduce function, if namely there are more than two or two number plate kinds, data that brand number is identical, be then merged into one, otherwise do not merge;
Step 4, by merge after result be saved in unlicensed motor vehicles storehouse.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510929267.3A CN105448099A (en) | 2015-12-14 | 2015-12-14 | Motor vehicle fake license identification method based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510929267.3A CN105448099A (en) | 2015-12-14 | 2015-12-14 | Motor vehicle fake license identification method based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105448099A true CN105448099A (en) | 2016-03-30 |
Family
ID=55558223
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510929267.3A Pending CN105448099A (en) | 2015-12-14 | 2015-12-14 | Motor vehicle fake license identification method based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105448099A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109872541A (en) * | 2019-03-07 | 2019-06-11 | 青岛海信网络科技股份有限公司 | A kind of information of vehicles analysis method and device |
| CN111179603A (en) * | 2018-11-09 | 2020-05-19 | 杭州海康威视数字技术股份有限公司 | Vehicle identification method and device, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040069845A1 (en) * | 2002-08-22 | 2004-04-15 | Keith Goldstein | Transaction card fabrication control system and method |
| CN101373517A (en) * | 2007-08-22 | 2009-02-25 | 北京万集科技有限责任公司 | Method and system for recognizing license plate |
| CN101901543A (en) * | 2010-07-16 | 2010-12-01 | 上海宝康电子控制工程有限公司 | Intelligent transportation integrated management system |
| CN104035954A (en) * | 2014-03-18 | 2014-09-10 | 杭州电子科技大学 | Hadoop-based recognition method for fake-licensed car |
-
2015
- 2015-12-14 CN CN201510929267.3A patent/CN105448099A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040069845A1 (en) * | 2002-08-22 | 2004-04-15 | Keith Goldstein | Transaction card fabrication control system and method |
| CN101373517A (en) * | 2007-08-22 | 2009-02-25 | 北京万集科技有限责任公司 | Method and system for recognizing license plate |
| CN101901543A (en) * | 2010-07-16 | 2010-12-01 | 上海宝康电子控制工程有限公司 | Intelligent transportation integrated management system |
| CN104035954A (en) * | 2014-03-18 | 2014-09-10 | 杭州电子科技大学 | Hadoop-based recognition method for fake-licensed car |
Non-Patent Citations (1)
| Title |
|---|
| 王涛等: "交通流大数据中的套牌车并行检测算法", 《湖北工程学院学报》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111179603A (en) * | 2018-11-09 | 2020-05-19 | 杭州海康威视数字技术股份有限公司 | Vehicle identification method and device, electronic equipment and storage medium |
| CN109872541A (en) * | 2019-03-07 | 2019-06-11 | 青岛海信网络科技股份有限公司 | A kind of information of vehicles analysis method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10789231B2 (en) | Spatial indexing for distributed storage using local indexes | |
| Johanson et al. | Big automotive data: Leveraging large volumes of data for knowledge-driven product development | |
| Mullesgaard et al. | Efficient skyline computation in MapReduce | |
| CN107515878B (en) | Data index management method and device | |
| CN107391502B (en) | Time interval data query method and device and index construction method and device | |
| CN110019267A (en) | A kind of metadata updates method, apparatus, system, electronic equipment and storage medium | |
| Yu et al. | RTIC-C: A big data system for massive traffic information mining | |
| CN104462222A (en) | Distributed storage method and system for checkpoint vehicle pass data | |
| CN105608155A (en) | Massive data distributed storage system | |
| CN111026874A (en) | Data processing method and server of knowledge graph | |
| CN106126601A (en) | A kind of social security distributed preprocess method of big data and system | |
| CN111209352A (en) | Data processing method and device, electronic equipment and storage medium | |
| US10929370B2 (en) | Index maintenance management of a relational database management system | |
| CN103780508A (en) | Software wave filtering method and system of CAN bus messages and electronic control unit | |
| CN111258978A (en) | Data storage method | |
| CN111953757A (en) | Information processing method based on cloud computing and intelligent device interaction and cloud server | |
| Moharm et al. | Big data in ITS: Concept, case studies, opportunities, and challenges | |
| CN104618304A (en) | Data processing method and data processing system | |
| CN105491078A (en) | Data processing method and device in SOA system, and SOA system | |
| CN105448099A (en) | Motor vehicle fake license identification method based on big data | |
| Ali | Big data-driven smart policing: big data-based patrol car dispatching | |
| Bhuyan et al. | Crime predictive model using big data analytics | |
| CN111369790B (en) | Vehicle passing record correction method, device, equipment and storage medium | |
| CN112734525A (en) | Multi-source data processing method, system, equipment and readable storage medium | |
| Ghosh et al. | Predictability and fairness in social sensing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20160330 |