CN106875692A - Vehicle integration early warning system and its method based on big data - Google Patents
Vehicle integration early warning system and its method based on big data Download PDFInfo
- Publication number
- CN106875692A CN106875692A CN201710186125.1A CN201710186125A CN106875692A CN 106875692 A CN106875692 A CN 106875692A CN 201710186125 A CN201710186125 A CN 201710186125A CN 106875692 A CN106875692 A CN 106875692A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- early warning
- integration
- data
- big 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
- 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
- G06F16/25—Integrating or interfacing systems involving database management systems
- G06F16/254—Extract, transform and load [ETL] procedures, e.g. ETL data flows in data warehouses
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Traffic Control Systems (AREA)
Abstract
Early warning system and its method are integrated the invention discloses a kind of vehicle based on big data, belongs to intelligent transportation, vehicle investigation and Data Mining.The system includes that the real-time car data of crossing of interaction successively integrates module, secondary identification cluster, big data real-time operation center and alarm module.This method is：1. integration Early-warning Model is set up（100）；2. vehicle characteristic information is extracted；3. vehicle integration is calculated；4. alarm is produced；5. terminate.Present system framework stability and high efficiency, handling capacity is big, being capable of real-time processing analysis magnanimity vehicles data；System architecture is opened, it is easy to compared with vehicle related system it is integrated, such as Data Integration module can extract vehicles data from different system, and early warning information can share to other systems and use；Early-warning Model is flexible and changeable, and integral term can be freely set according to the actual requirements, and early warning is carried out to all kinds of high-risk vehicles, and phenomenon of breaking laws and commit crime targetedly is hit in time, and promote social harmony stable development.
Description
Technical field
The invention belongs to intelligent transportation, vehicle investigation and Data Mining, and in particular to a kind of car based on big data
Integration early warning system and its method.
Background technology
As going deep into for reform and opening-up, living standards of the people improve constantly, vehicles number rapidly increases, urban modernization
Pace of construction is constantly accelerated, and the criminal and case involving public security related to traffic also rises year by year, particularly as being driven after accident or crime
The problems such as car is escaped, robber robs vehicle, vehicles peccancy and false-trademark fake license plate vehicle is increasingly highlighted, and huge choosing is brought to public security investigation
War.
Offender generally has premediation using vehicle crime, such as sets foot-point, and high risk zone is frequently occurred in the special time；
In order to escape public security organ's strike, camouflage transformation may be carried out to vehicle, such as deck, false-trademark vehicle and block；It is preceding as having
The personnel of section, are likely to recommit；Things of a kind come together, and the personnel being associated with the people having previous conviction go out than ordinary people
The probability of now crime will height.Therefore, it can combine indices, set up a kind of integral model, to being likely to occur illegal vehicle
Early warning is carried out, possible trouble is preventive from.
The average daily car data amount of crossing of general large size city is usually million or ten million rank, in face of such large-scale data
Amount, carries out vehicle analysis, it is clear that cannot complete by manual type, and the vehicle of routine is studied and judged system and cannot also be completed
Real-time processing and analysis.
Big data (Big Data) is commonly used to describe a large amount of destructurings or partly-structured data that these data exist
Relevant database can overspending time and money when being used to analyze.Big data analysis should compared to traditional data warehouse
With, with data volume it is big, query analysis are complicated the features such as.By some special techniques of application big data, such as distributed document
System, Parallel Processing and Analysis and cloud computing platform etc., to realize high-throughput, high concurrent, mass data is processed in effective time
Demand.
Therefore, in the urgent need to a kind of vehicle based on big data technology integrates method for early warning, targetedly strike is disobeyed in time
Method criminal phenomena, promote social harmony stable development.
The content of the invention
The purpose of the present invention is that the problem for overcoming prior art to exist, there is provided a kind of vehicle integration based on big data
Method for early warning and system.
The object of the present invention is achieved like this：
First, the vehicle based on big data integrates early warning system (abbreviation system)
The system includes that the real-time car data of crossing of interaction successively integrates module, secondary identification cluster, big data real-time operation
Center and alarm module.
2nd, the vehicle based on big data integrates method for early warning (abbreviation method)
This method comprises the following steps：
Start
1. integration Early-warning Model is set up
According to actual needs, by vehicle appearance characteristic attribute and non-appearance characteristic attribute, certain weights are assigned respectively, set
Early warning score line, creates one or more Early-warning Models, is saved in high-performance storehouse, then initializes the model；
2. vehicle characteristic information is extracted
The basic appearance information of vehicle is recognized by front end camera, secondary identification is recycled, to the further digging of vehicle pictures
Pick analysis, gets more detailed external appearance characteristic information, will be sent after recognition result structuring to message subscribing server；
3. vehicle integration is calculated
The Distributed Calculation engine vehicle characteristic information that 2. obtaining step extracts from message subscribing server, analyzing step
1. the Early-warning Model of middle foundation, travels through each early warning, is added up after calculating weighted value, and the early warning score line according to model specification is sentenced
Whether disconnected is suspect vehicle, is comprised the following steps that：
Whether A, judgment models, containing external appearance characteristic (310), are then to enter step B, otherwise jump to step C；
B, calculating external appearance characteristic integration
Compared with vehicle characteristic information with each external appearance characteristic in model, weighting point is calculated according to degree of conformity
Number, remembers 0 point when not meeting；
C, judgment models whether characteristic item containing non-appearance, be then enter step D, otherwise jump to step E；
D, calculating non-appearance characteristic-integration
Traversal non-appearance characteristic-integration, if being related to the item that high-risk personnel, violation data etc. need correlation inquiry,
Then the corresponding storehouse of correlation inquiry, when there is corresponding record, then it is assumed that match and calculate the weighted value of this, otherwise remembers 0 point；If
Integral term is detected on time, place, direct access and can be compared from vehicle characteristic information, is calculated when meeting
The weighted value of this, otherwise remembers 0 point；
E, judge integration whether exceed early warning score line, be then 4., otherwise to jump to step 5. into step
External appearance characteristic is sued for peace with the integration of non-appearance feature, obtains vehicle integration, and then the score line with the model is carried out
Compare, step is entered 4. during more than early warning score line, otherwise this analysis logic terminates, and can enter next vehicle characteristics point
Analysis；
4. alarm is produced
With reference to information of vehicles and integration detailed rules and regulations generation early warning information, send to message subscribing server, alarm module is subscribed to
After can immediately receive early warning information, produce corresponding alarm, other vehicle managements, vehicle investigation related system can also be subscribed to, shared
Early warning information；
5. terminate.
The present invention has following advantages and good effect：
1. system architecture stability and high efficiency, handling capacity is big, being capable of real-time processing analysis magnanimity vehicles data；
2. system architecture open, it is easy to compared with vehicle related system it is integrated, such as Data Integration module can be from difference
System extracts vehicles data, and early warning information can share to other systems and use；
3. Early-warning Model is flexible and changeable, and integral term can be freely set according to the actual requirements, and all kinds of high-risk vehicles are carried out
Early warning, targetedly hits phenomenon of breaking laws and commit crime in time, and promote social harmony stable development.
Brief description of the drawings
Fig. 1 is the block diagram of the system；
The step of Fig. 2 is this method is schemed.
In figure：
10-real-time car data of crossing integrates module；
20-secondary identification cluster,
21st, 22 ... 2m-the 1st, 2 ... m recognition nodes, m is natural number,≤m≤；
30-big data real-time operation center,
31-Kafka,
32-Spark,
33—SolrCloud；
40-alarm module 40.
Specific embodiment
Describe in detail with reference to the accompanying drawings and examples：
First, system
1st, it is overall
Such as Fig. 1, the system includes that the real-time car data of crossing of interaction successively integrates module 10, secondary identification cluster 20, big number
According to real-time operation center 30 and alarm module 40.
2nd, functional module
1) real-time car data of crossing integrates module 10
Using ETL technologies, the vehicles data of the headend equipments such as bayonet socket, ETC, electricity police is obtained in real time, be sent to secondary
Identification cluster carries out treatment 20.
2) secondary identification cluster 20
The distributed secondary identification cluster being made up of multiple recognition nodes (21-2m), recognizer by C/C++ realize, with
Just efficiently, real-time processing vehicles data, extract vehicle characteristic information, such as vehicle brand, whether there is annual test mark, number plate cover,
Driver's face is blocked, and recognition result then is sent into the Kafka31 into big data cluster 30.
3) big data real-time operation center 30
Big data real-time operation center 30 includes Kafka31, Spark32 and SolrCloud33 interactive successively.
(1)Kafka31
It is a kind of high-performance news release ordering system, up to million message throughput per second, is especially suitable for forwarded over car
The such large-scale data of record；
The component Main Function is to receive the vehicle characteristic information from secondary identification cluster 20 treatment；Receive Spark32
Early warning information after analysis, is transmitted to alarm module 40.
(2)Spark32
It is a kind of computing engines of the Universal-purpose quick for aiming at large-scale data treatment and designing.System start when from
Early-warning Model is obtained in SolrCloud33 and is initialized, more new model is notified by Early-warning Model management module again after startup.Pass through
Kafka Stream obtain vehicle characteristic information from Kafka31, by Spark Stream Parallel Processing and Analysis, according to early warning mould
Type, calculates the integration of external appearance characteristic and non-appearance feature, wherein can be related to association during calculating non-appearance characteristic-integration
Inquiry SolrCloud33, finally obtains vehicle integration, will exceed the information of vehicles of early warning score line, integration detailed rules and regulations and is formatted as
Early warning information is sent to Kafka31.
(3)SolrCloud33
It is a kind of distributed search scheme based on Solr and Zookeeper, there is provided high performance retrieval service.
It is used to store the data such as Early-warning Model, high-risk personnel, record of breaking rules and regulations, abnormal behaviour in the system, for Spark032
High-speed associative is inquired about.
4) alarm module 40
Kafka31 early warning informations are subscribed to, the corresponding alarm of generation after early warning information is obtained, sound is such as sent, is sent short message
Etc. mode；Other vehicle managements, vehicle investigation related system can also subscribe to Kafka31, share early warning information.
2nd, the vehicle based on big data integrates method for early warning (abbreviation method)
This method comprises the following steps：
0th, -000 is started
1. integration Early-warning Model -100 is set up
According to actual needs, by vehicle appearance characteristic attribute (including vehicle brand, number plate block, it is unlicensed, block face and
Whether there is annual test mark) and non-appearance characteristic attribute (including car owner whether high-risk personnel, there is record violating the regulations or abnormal behaviour), point
Certain weights are not assigned, early warning score line is set, one or more Early-warning Models are created, and are saved in high-performance storehouse, then
Initialize the model；
Example 1：It is on the rise using the vehicle crime rate for reequiping number plate in certain region a, crime time be at 11 points in evening extremely
Between 5:00 AM, suspect's majority is had previous conviction, and now needs a kind of integration Early-warning Model, and the suspect vehicle in the region is carried out
Early warning, (it is noted that being added according to actual conditions or deleting early warning, weights and early warning fraction are changed with reference to example as follows
Line)：
Example 2：Certain white Audi's car, three, license plate number end is 789, with great suspicion；Received in view of body color
Light is influenceed, and identification may be caused incorrect, preferential with the characteristic item for being not easy to occur identification mistake, improves weights, is now set up
Such as lower integral Early-warning Model：
2. vehicle characteristic information -200 is extracted
Basic appearance information (including body color, type of vehicle, brand number and the row of vehicle are recognized by front end camera
Sail speed)；Secondary identification is recycled, to the further mining analysis of vehicle pictures, more detailed external appearance characteristic information is got
(including vehicle brand, whether there is annual test mark, number plate are covered and driver's face is blocked), will send after recognition result structuring to disappearing
Breath Subscriber (such as Kafka)；
3. vehicle integration 300 is calculated
Distributed Calculation engine (such as Spark) vehicle characteristics that 2. obtaining step extracts from message subscribing server are believed
Breath, the Early-warning Model of analyzing step 1. middle foundation travels through each early warning, is added up after calculating weighted value, according to model specification
Early warning score line determines whether suspect vehicle, comprises the following steps that：
Whether A, judgment models, containing external appearance characteristic -310, are then to enter step B, otherwise jump to step C；
B, calculating external appearance characteristic integration -320
Compared with vehicle characteristic information with each external appearance characteristic in model, weighting point is calculated according to degree of conformity
Number, remembers 0 point when not meeting；
With reference to step 1. in the model of example 1, if occlusion number plate, external appearance characteristic integration be：8 (blocking number plate)+0
(unlicensed vehicle)=8 points；If number plate identification is normal, external appearance characteristic integration is：0 (blocking number plate)+0 (unlicensed vehicle)=0
Point；
With reference to step 1. in the model of example 2, if there is a grey Audi car, number plate digit is 789, then outward appearance
Characteristic-integration is：(body color)=22 point of 10 (number plate of vehicle)+7 (vehicle brand)+5 (type of vehicle)+0；If there is one
White Audi's car, number plate digit is 888, then external appearance characteristic integration is：(the car of 0 (number plate of vehicle)+7 (vehicle brand)+5
Type)+5 (body color)=17 point；
C, judgment models whether characteristic item containing non-appearance -330, be then enter step D, otherwise jump to step E；
D, calculating non-appearance characteristic-integration -340
Traversal non-appearance characteristic-integration, if being related to the item that high-risk personnel, violation data etc. need correlation inquiry,
Then the corresponding storehouse of correlation inquiry (SolrCloud), it is no when there is corresponding record, then it is assumed that match and calculate the weighted value of this
Then remember 0 point；If integral term is detected on time, place, direct access and can be compared from vehicle characteristic information
Compared with, the weighted value of this is calculated when meeting, otherwise remember 0 point；
With reference to step 1. in the model of example 1, owner information can be obtained according to car plate, then such as identification card number removes height
Inquired about in danger personnel storehouse and compared, if car owner is case-involving fugitive personnel, case-involving fugitive item remembers 50 points, if car owner and certain habitual offender
In the presence of close incidence relation, then 15 points of associate people note, by that analogy, vehicle fake-license, robber robs the items such as vehicle can also lead to
Correlation inquiry detection is crossed, weighted value is then calculated.According to front end camera capture time, place, it may be determined that vehicle whether
Suspicious time period, high risk zone occur.As front end camera belongs in the A of region, then the vehicle that the front end camera is captured is high-risk
The score of area item is 5 points.Certain vehicle elapsed time is 2017-01-01 13：11：53, it is clear that be not belonging to the suspicious time period
Interior, this obtains 0 point, and such as elapsed time is 2017-02-03 23：38：07, then belong in the suspicious time period, this obtains 3 points；
Step 1. in the model of example 2 be external appearance characteristic integral term, it is not necessary to pass through this step；
E, judge integration whether exceed early warning score line -350, be then 4., otherwise to jump to step 5. into step
External appearance characteristic is sued for peace with the integration of non-appearance feature, obtains vehicle integration, and then the score line with the model is carried out
Compare, more than (≤early warning score line) when enter step 4., otherwise this analysis logic terminate, next vehicle characteristics can be entered
Analysis；
4. alarm 400 is produced
With reference to information of vehicles and integration detailed rules and regulations generation early warning information, send to message subscribing server (such as Kafka), alarm
Module can immediately receive early warning information after subscribing to, produce corresponding alarm (as by the way of acoustics, optics and short message), other cars
Management, vehicle investigation related system can also subscribe to, share early warning information.
5. -500 are terminated.
Claims (6)
1. a kind of vehicle based on big data integrates early warning system, it is characterised in that：
Real-time car data of crossing including interaction successively integrates module（10）, secondary identification cluster（20）, in big data real-time operation
The heart（30）And alarm module（40）.
2. a kind of vehicle based on big data as described in claim 1 integrates early warning system, it is characterised in that：
Described real-time car data integration module 10 of crossing is a kind of using ETL technologies, and the front ends such as bayonet socket, ETC, electricity police are obtained in real time
The vehicles data of equipment, is sent to secondary identification cluster and is processed（20）.
3. a kind of vehicle based on big data as described in claim 1 integrates early warning system, it is characterised in that：
Described secondary identification cluster（20）The distributed secondary identification cluster being made up of multiple recognition nodes, recognizer is by C/
C++ is realized, so as to efficient, real-time processing vehicles data, extracts vehicle characteristic information, such as vehicle brand, whether there is annual test mark,
Number plate is covered, driver's face is blocked, and then sends to big data cluster recognition result（30）In Kafka31.
4. a kind of vehicle based on big data as described in claim 1 integrates early warning system, it is characterised in that：
Described big data real-time operation center（30）Including Kafka interactive successively（31）、Spark（32）And SolrCloud
（33）.
5. a kind of vehicle based on big data as described in claim 1 integrates early warning system, it is characterised in that：
Described alarm module（40）It is a kind of subscription Kafka31 early warning informations, obtains the corresponding alarm of generation after early warning information.
6. the vehicle based on vehicle integration early warning system described in claim 1-5 integrates pre- method, it is characterised in that including following
Step：
Start（000）
1. integration Early-warning Model is set up（100）
According to actual needs, by vehicle appearance characteristic attribute and non-appearance characteristic attribute, certain weights are assigned respectively, set early warning
Score line, creates one or more Early-warning Models, is saved in high-performance storehouse, then initializes the model；
2. vehicle characteristic information is extracted（200）
The basic appearance information of vehicle is recognized by front end camera, secondary identification is recycled, excavate further to vehicle pictures is divided
Analysis, gets more detailed external appearance characteristic information, will be sent after recognition result structuring to message subscribing server；
3. vehicle integration 300 is calculated
The Distributed Calculation engine vehicle characteristic information that 2. obtaining step extracts from message subscribing server, analyzing step 1. in
The Early-warning Model of foundation, travels through each early warning, is added up after calculating weighted value, and the early warning score line judgement according to model specification is
No is suspect vehicle, is comprised the following steps that：
Whether A, judgment models are containing external appearance characteristic（310）, it is then to enter step B, otherwise jump to step C；
B, calculating external appearance characteristic integration（320）
Compared with vehicle characteristic information with each external appearance characteristic in model, weighted score is calculated according to degree of conformity, no
0 point is remembered when meeting；
C, judgment models whether characteristic item containing non-appearance（330）, it is then to enter step D, otherwise jump to step E；
D, calculating non-appearance characteristic-integration（340）
Traversal non-appearance characteristic-integration, if being related to the item that high-risk personnel, violation data etc. need correlation inquiry, then closes
Corresponding storehouse is ask in joint investigation（SolrCloud）, when there is corresponding record, then it is assumed that match and calculate the weighted value of this, otherwise remember 0
Point；If integral term is detected on time, place, direct access and can be compared from vehicle characteristic information, accorded with
The weighted value of this is calculated during conjunction, 0 point is otherwise remembered；
E, judge integration whether exceed early warning score line（350）, it is then 4., otherwise to jump to step 5. into step
External appearance characteristic is sued for peace with the integration of non-appearance feature, obtains vehicle integration, and then the score line with the model is compared,
Enter step 4. during more than early warning score line, otherwise this analysis logic terminates, next vehicle characteristics analysis can be entered；
4. alarm is produced（400）
With reference to information of vehicles and integration detailed rules and regulations generation early warning information, send to message subscribing server, meeting after alarm module subscription
Early warning information is received immediately, corresponding alarm is produced, and other vehicle managements, vehicle investigation related system can also be subscribed to, and share early warning
Message；
5. terminate（500）.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710186125.1A CN106875692A (en) | 2017-03-27 | 2017-03-27 | Vehicle integration early warning system and its method based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710186125.1A CN106875692A (en) | 2017-03-27 | 2017-03-27 | Vehicle integration early warning system and its method based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106875692A true CN106875692A (en) | 2017-06-20 |
Family
ID=59173791
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710186125.1A Pending CN106875692A (en) | 2017-03-27 | 2017-03-27 | Vehicle integration early warning system and its method based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106875692A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107862264A (en) * | 2017-10-27 | 2018-03-30 | 武汉烽火众智数字技术有限责任公司 | A kind of vehicle secondary identifying system and its method for serving data analytical center |
| CN107977421A (en) * | 2017-11-24 | 2018-05-01 | 泰华智慧产业集团股份有限公司 | The method and device of fake-licensed car analysis is carried out based on big data |
| CN109783540A (en) * | 2019-01-08 | 2019-05-21 | 武汉烽火众智数字技术有限责任公司 | It is a kind of based on condition code to the analysis method and system of special group personnel |
| CN110322049A (en) * | 2019-06-03 | 2019-10-11 | 浙江图灵软件技术有限公司 | A kind of public security big data method for early warning |
| CN111783602A (en) * | 2020-06-24 | 2020-10-16 | 杭州海康威视***技术有限公司 | Vehicle analysis method and device, electronic equipment and machine-readable storage medium |
| CN112700072A (en) * | 2021-03-24 | 2021-04-23 | 同盾控股有限公司 | Traffic condition prediction method, electronic device, and storage medium |
| CN113239008A (en) * | 2020-12-10 | 2021-08-10 | 哈工大大数据集团四川有限公司 | Emergency big data studying and judging system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101261771A (en) * | 2008-03-14 | 2008-09-10 | 康华武 | An automatic checking method for vehicle identity on the road |
| CN104408934A (en) * | 2014-11-28 | 2015-03-11 | 深圳市华仁达技术有限公司 | Analysis method for vehicle involved in case based on traffic data |
| CN104732077A (en) * | 2015-03-12 | 2015-06-24 | 苏州讯创信息技术有限公司 | Multi-dimensionality evaluation model based high risk vehicle color warning method |
| CN104851284A (en) * | 2015-05-20 | 2015-08-19 | 浙江宇视科技有限公司 | Vehicle management method and device |
| US20150294422A1 (en) * | 2014-04-15 | 2015-10-15 | Maris, Ltd. | Assessing asynchronous authenticated data sources for use in driver risk management |
-
2017
- 2017-03-27 CN CN201710186125.1A patent/CN106875692A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101261771A (en) * | 2008-03-14 | 2008-09-10 | 康华武 | An automatic checking method for vehicle identity on the road |
| US20150294422A1 (en) * | 2014-04-15 | 2015-10-15 | Maris, Ltd. | Assessing asynchronous authenticated data sources for use in driver risk management |
| CN104408934A (en) * | 2014-11-28 | 2015-03-11 | 深圳市华仁达技术有限公司 | Analysis method for vehicle involved in case based on traffic data |
| CN104732077A (en) * | 2015-03-12 | 2015-06-24 | 苏州讯创信息技术有限公司 | Multi-dimensionality evaluation model based high risk vehicle color warning method |
| CN104851284A (en) * | 2015-05-20 | 2015-08-19 | 浙江宇视科技有限公司 | Vehicle management method and device |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107862264A (en) * | 2017-10-27 | 2018-03-30 | 武汉烽火众智数字技术有限责任公司 | A kind of vehicle secondary identifying system and its method for serving data analytical center |
| CN107977421A (en) * | 2017-11-24 | 2018-05-01 | 泰华智慧产业集团股份有限公司 | The method and device of fake-licensed car analysis is carried out based on big data |
| CN109783540A (en) * | 2019-01-08 | 2019-05-21 | 武汉烽火众智数字技术有限责任公司 | It is a kind of based on condition code to the analysis method and system of special group personnel |
| CN109783540B (en) * | 2019-01-08 | 2021-05-07 | 武汉烽火众智数字技术有限责任公司 | Method and system for analyzing specific group of people based on feature codes |
| CN110322049A (en) * | 2019-06-03 | 2019-10-11 | 浙江图灵软件技术有限公司 | A kind of public security big data method for early warning |
| CN111783602A (en) * | 2020-06-24 | 2020-10-16 | 杭州海康威视***技术有限公司 | Vehicle analysis method and device, electronic equipment and machine-readable storage medium |
| CN111783602B (en) * | 2020-06-24 | 2024-03-01 | 杭州海康威视***技术有限公司 | Vehicle analysis method, device, electronic equipment and machine-readable storage medium |
| CN113239008A (en) * | 2020-12-10 | 2021-08-10 | 哈工大大数据集团四川有限公司 | Emergency big data studying and judging system |
| CN112700072A (en) * | 2021-03-24 | 2021-04-23 | 同盾控股有限公司 | Traffic condition prediction method, electronic device, and storage medium |
| CN112700072B (en) * | 2021-03-24 | 2021-06-29 | 同盾控股有限公司 | Traffic condition prediction method, electronic device, and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106875692A (en) | Vehicle integration early warning system and its method based on big data | |
| Shah et al. | Crime forecasting: a machine learning and computer vision approach to crime prediction and prevention | |
| Laufs et al. | Security and the smart city: A systematic review | |
| Jiang et al. | Automatic soccer video event detection based on a deep neural network combined cnn and rnn | |
| CN103294775B (en) | Police service cloud image recognition vehicle administrating system based on geographic space-time constraint | |
| CN108052882A (en) | A kind of operating method of intelligent safety defense monitoring system | |
| CN110619277A (en) | Multi-community intelligent deployment and control method and system | |
| US20070237357A1 (en) | Visual sensing for large-scale tracking | |
| CN107506368A (en) | The determination method and device of one species case suspected vehicles | |
| CN103246876A (en) | Image feature comparison based counterfeit vehicle registration plate identification method | |
| CN109033440A (en) | A kind of video investigation multidimensional trajectory analysis method | |
| CN110177255B (en) | Case scheduling-based video information publishing method and system | |
| CN106971556B (en) | The recognition methods again of bayonet vehicle based on dual network structure | |
| CN110390031A (en) | Information processing method and device, vision facilities and storage medium | |
| CN101430827B (en) | Taxi wireless video monitoring system and method based on GPS | |
| US20180253814A1 (en) | System and method for incident validation and ranking using human and non-human data sources | |
| CN109615573B (en) | Foreign personnel flow channeling analysis method and system based on big data | |
| WO2018176191A1 (en) | Method and apparatus for identifying vehicle with fake registration plate | |
| CN108965804A (en) | A kind of video structural technology for city security protection | |
| CN106327876B (en) | A kind of fake-licensed car capture system and method based on automobile data recorder | |
| CN108665085A (en) | A kind of recessiveness emphasis people acquisition methods and system | |
| CN109325755A (en) | Electronics charge system based on automotive hub | |
| Siddiqui et al. | Towards efficient vehicle classification in intelligent transportation systems | |
| Yang et al. | SPDNet: A Real‐Time Passenger Detection Method Based on Attention Mechanism in Subway Station Scenes | |
| CN115393997A (en) | Automobile electronic unlocking method and device based on multi-dimensional data identification and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170620 |