CN106530704B - A kind of Floating Car aggregation detection method based on multivariate data fusion - Google Patents
A kind of Floating Car aggregation detection method based on multivariate data fusion Download PDFInfo
- Publication number
- CN106530704B CN106530704B CN201611055330.6A CN201611055330A CN106530704B CN 106530704 B CN106530704 B CN 106530704B CN 201611055330 A CN201611055330 A CN 201611055330A CN 106530704 B CN106530704 B CN 106530704B
- Authority
- CN
- China
- Prior art keywords
- threshold
- floating car
- vehicle
- data
- bayonet
- 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.)
- Active
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
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
- G08G1/0112—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from the vehicle, e.g. floating car data [FCD]
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/065—Traffic control systems for road vehicles by counting the vehicles in a section of the road or in a parking area, i.e. comparing incoming count with outgoing count
Abstract
The invention discloses a kind of Floating Cars based on multivariate data fusion to assemble detection method, the area maps for needing to analyze are combined framework one efficient, reliable computing platform to a virtual grid, and using the GPS data and bayonet data of Floating Car by this method；By the use of multivariate data, it can guarantee to be accurately calculated, to improve the accuracy rate and efficiency of Floating Car aggregation detection.
Description
Technical field
The invention belongs to Floating Car monitoring fields more particularly to a kind of Floating Car based on multivariate data fusion to assemble detection
Method.
Background technique
It is numerous and confused all over the world to establish information-based traffic administration platform realization traffic information reality with the development of smart city
When monitor.Floating Car refers to the bus and taxi for being mounted with vehicle-mounted GPS positioning system, passes through GPS positioning satellite traffic pipe
Platform can periodically obtain the information such as the position, direction and speed of vehicle.With being continuously increased for Floating Car quantity, to floating
The monitoring and management of vehicle are particularly important.Wherein, the detection of Floating Car aggregation is movable to crime prevention occurs with great
Meaning, because Floating Car, which is largely assembled, to generate adverse effect to civil order.The prior art detects the technology of Floating Car aggregation
In, judgment basis is all based on floating car data, and timing judges the total quantity of Floating Car in certain area, but this unit number
It, cannot be well by Floating Car according to determining that often causing Floating Car to be assembled due to complicated road conditions detects inaccuracy
The congestion of Assembling Behavior and vehicle distinguishes；Meanwhile the prior art can not be timely in the energy at the beginning for Floating Car aggregation occur
Accurate judgement is made, is just known when often Floating Car aggregation occurs, it is difficult to which Floating Car aggregation event is effectively prevented
And processing.
Therefore in view of the drawbacks of the prior art, it is really necessary to propose a kind of technical solution to overcome skill of the existing technology
Art problem.
Summary of the invention
In view of this, it is necessory to provide a kind of aggregation that can in time, accurately analyze Floating Car based on polynary
The Floating Car of data fusion assembles detection method, so as to effectively prevent simultaneously to handle Floating Car aggregation event in time, ensures public
Traffic order and civil order are effectively run altogether.
In order to overcome the drawbacks of the prior art, technical scheme is as follows:
A kind of Floating Car aggregation detection method based on multivariate data fusion, comprising the following steps:
Step S1: the virtual grid space that area maps to be analyzed on map are made of to one multiple grids, and set
Fixed following parameter: Grid QoS vehicle vehicle number threshold value Cluster_Threshold { k11,k12...knn, for representing each net
The maximum vehicle number that lattice pass through within the Δ t period；Road vehicle congestion threshold average value u and road vehicle congestion threshold variance yields
σ2, for characterizing the jam situation on every section；License plate repetition rate threshold Repeat_Threshold, when for representing current
Between in segment mesh in license plate number and a upper time segment mesh license plate number repetitive rate；Floating Car quantity accounts for the threshold of vehicle fleet
Value Float_Threshold accounts for the percentage of total vehicle number for representing Floating Car in section；Road speeds threshold value Speed_
Threshold, for representing the minimum speed of the smooth passage of vehicle；
Step S2: from obtaining each grid floating car data and bayonet number corresponding within the Δ t period in database
According to floating car data is longitude, latitude and the time that GPS terminal equipment uploads, and bayonet data are to pass through each bayonet
It's the vehicle time pasts vehicle identification number code；
Step S3: the floating car data of each grid is carried out calculating analysis and judges whether that Floating Car aggregation, which occurs, to be disliked
It doubts, if it is not, then step S2 is back to, if it is, triggering executes step S4；Wherein, while when reaching the following conditions just sentence
Determine Floating Car and assemble suspicion:
Continuous N number of period all meets following formula:
Wherein, CarDetail is the floating car data read in from database, and CarDetail [i] [j] is current time
Duan Zhong, the vehicle number of the i-th row jth column grid, Cluster_Threshold [i] [j] are the i-th row jth column Grid QoS vehicle vehicles
Number threshold value；It is linear function that the floating car data of continuous N number of period, which is passed through linear regression fit, obtains slope k, and k > 0；
License plate number the repetitive rate repeat, repeat for calculating time adjacent segments in N number of period are more than license plate repetitive rate
Threshold value Repeat_Threshold, wherein repeat calculation formula is as follows:
Wherein, S1It is all vehicles of this period, S2It was all vehicles of a upper period, repeat is license plate number
Code repetitive rate, Repeat_Threshold are license plate repetition rate threshold；
Step S4: the vehicle of Floating Car aggregation suspicion will be currently at according to Density Clustering to together, and institute is clustered with this
Assemble influence area as Floating Car in the place of covering；
Step S5: it is gathered around according to whether section corresponding to bayonet data calculating Floating Car aggregation influence area traffic occurs
It is stifled, if there is traffic congestion, step S6 is executed, it is no to then follow the steps S7；Wherein, while when meeting the following conditions it decides that out
Existing traffic congestion:
RoadVehicle is the vehicle number obtained on current road segment from bayonet, and u is road vehicle congestion threshold average value, σ2
It is road vehicle congestion threshold variance yields；
The speed speed that the section is calculated according to bayonet data, when speed has been more than road speeds threshold value Speed_
When Threshold, that is, current section is determined for congestion, the calculation method of speed speed is as follows:
Wherein, n is all vehicle numbers on this section, t1It is the time by this bayonet, t2It is by being counted with current
It calculates the time of the connected upper bayonet in section, s is road section length, and Speed_Threshold is road speeds threshold value；
Step S6: the ratio shared by Floating Car that is calculated by the following formula has been more than the threshold that Floating Car quantity accounts for vehicle fleet
Value Float_Threshold:
Wherein, denominator LinkCarData is vehicle number all on section, and molecule ClusterInfo is in current road segment
The upper Floating Car vehicle number for participating in aggregation, FloatPercent is a value between [0,1], and Float_Threshold is
Floating Car quantity accounts for the threshold value of vehicle fleet；
If whether ratio shared by Floating Car has been more than threshold value Float_ that Floating Car quantity accounts for vehicle fleet
Threshold is then judged to occurring Floating Car aggregation, executes step S7, be otherwise determined as false triggering, be back to step S2；
Step S7: being judged to occurring Floating Car aggregation, the region for sounding an alarm and storing aggregation information of vehicles, assembling
With the temporal information of aggregation, the data that step S2 calculates future time piece are repeated.
Preferably, wherein in step S3, N is that user is customized.
Compared with prior art, the big data frame of Storm is used in the present invention for the traffic space-time data of magnanimity
Structure can satisfy large capacity key industry to provide basic primitive and security mechanism required by fault tolerant distributed computing
The application demand of business；Meanwhile framework one is combined efficiently, reliably using the GPS data of Floating Car and bayonet data
Computing platform；The use of multivariate data can guarantee to be accurately calculated, and improve the accuracy rate and effect of Floating Car aggregation detection
Rate.
Detailed description of the invention
Fig. 1 is that the Floating Car merged the present invention is based on multivariate data assembles the flow diagram of detection method.
Fig. 2 is the vehicle condition figure of the aggregation situation of Hangzhou section Floating Car.
Following specific embodiment will further illustrate the present invention in conjunction with above-mentioned attached drawing.
Specific embodiment
Below with reference to attached drawing to it is provided by the invention based on multivariate data fusion Floating Car aggregation detection method make into
One step explanation.
Currently, there are the determinations of threshold value not enough to have accuracy for the method for analysis Floating Car aggregation；Calculate Floating Car aggregation
The problems such as data source is single.In traditional research traffic congestion method, a large amount of aggregations of some Floating Cars are often ignored
It is this important origin cause of formation generated by traffic congestion, the aggregation of Floating Car cannot be distinguished well with congestion, calculated
Congestion can also be counted together in the method for vehicle aggregation, so that result can have mistake.To find out its cause, essentially consisting in existing
There is technology to be based only upon floating car data detection Floating Car aggregation, causes precision that can not further increase.
In view of the above technical defects, the central scope of technical solution of the present invention is: by the area maps for needing to analyze to one
A virtual grid, the vehicle number by detecting the whether continuous N number of period Floating Car of each grid are above the floating set
The max-thresholds and quantity of vehicle quantity are in increasing trend, and from second period, each period and a upper time
There are certain repetitive rates for section license plate number.The generation for whether having Floating Car aggregation suspicion herein is determined with this.When having detected
When Floating Car assembles suspicion, check whether traffic congestion has occurred herein.If traffic congestion has occurred, the aggregation of Floating Car is living
Dynamic may be as caused by traffic congestion.Whether the percentage that the quantity of all vehicles is accounted for by the quantity of Floating Car is more than Floating Car
Quantity accounts for the threshold value of vehicle fleet to judge.The threshold value that Floating Car quantity if more than accounts for vehicle fleet then can determine whether to float
The aggregation of vehicle；If being not above the threshold value that Floating Car quantity accounts for vehicle fleet, can determine whether as there is no Floating Cars to assemble.
If the generation assembled is unrelated with congestion there is no traffic congestion, can directly judge be Floating Car aggregation.
Referring to Fig. 1, it show the distance block diagram of the Floating Car aggregation detection method the present invention is based on multivariate data fusion, packet
Include following steps:
Step S1: the virtual grid space that area maps to be analyzed on map are made of to one multiple grids, and set
Fixed following parameter: Grid QoS vehicle vehicle number threshold value Cluster_Threshold { k11,k12...knn, for representing each net
The maximum vehicle number of lattice passed through within the Δ t time；Road vehicle congestion threshold average value u and road vehicle congestion threshold variance yields
σ2, for characterizing the jam situation on every section, road vehicle congestion threshold average value u is the threshold value on every section, be by
The threshold value determined by k-means that the historical data in section obtains, road vehicle congestion threshold variance yields σ2It is according to history number
According to what is obtained, being vehicle gets on the bus a several variance currently calculating section in the period；License plate repetition rate threshold Repeat_
Threshold can be by user's self-defining for representing the license plate number of current slot and the repetitive rate of a upper period；
Floating Car quantity accounts for the threshold value Float_Threshold of vehicle fleet, account for total vehicle number for representing Floating Car in section hundred
Divide ratio, is obtained by statistical history data；Road speeds threshold value Speed_Threshold, for representing vehicle smoothly minimum speed
Degree, by user's self-defining.
Step S2: from obtaining each grid floating car data and bayonet number corresponding within the Δ t period in database
According to floating car data is longitude, latitude and the time that GPS terminal equipment uploads, and bayonet data are to pass through each bayonet
It's the vehicle time pasts vehicle identification number code；The data of reading mainly have uplink time, license plate number, longitude, latitude and the process of Floating Car
The license plate number of bayonet, bayonet longitude, bayonet latitude, spends the vehicle time and crosses vehicle direction composition bayonet number.
The floating car data of reading is added among corresponding grid according to longitude and latitude.By the bayonet data of reading according to every
The bayonet number of a bayonet and direction are added among GateFlowrate, and GateFlowrate is the data knot for saving information of vehicles
Structure.
Step S3: the floating car data of each grid is carried out calculating analysis and judges whether that Floating Car aggregation, which occurs, to be disliked
It doubts, if it is not, then step S2 is back to, if it is, triggering executes step S4；Wherein, each grid is calculated, by following
Actual vehicle addition number is compared by formula with the addition number of the vehicle number threshold value of grid, is recorded in whether present period surpasses
Given threshold value is crossed.Whether aggregation suspicion condition is reached for current grid computing, specific suspicion condition of assembling is
Decide that Floating Car assembles suspicion when reaching the following conditions simultaneously:
Continuous N number of period all meets following formula:
Wherein, CarDetail is the floating car data read in from database, and CarDetail [i] [j] is current time
Duan Zhong, the vehicle number of the i-th row jth column grid, Cluster_Threshold [i] [j] are the vehicle number thresholds of the i-th row jth column grid
Value；
By linear regression fit it is linear function by the floating car data of continuous N number of period, obtains slope k, and k >
0；
The license plate number repetitive rate repeat for calculating time adjacent segments in N number of period is more than license plate repetition rate threshold
Repeat_Threshold, wherein repeat calculation formula is as follows:
Wherein, S1It is all vehicles of this period, S2It was all vehicles of a upper period, repeat is license plate number
Code repetitive rate, Repeat_Threshold are license plate repetition rate threshold；
Step S4: the vehicle for being currently at Floating Car aggregation suspicion state is gathered according to Density Clustering to together, and with this
Assemble influence area as Floating Car in the place that class is covered；
Step S5: it is gathered around according to whether section corresponding to bayonet data calculating Floating Car aggregation influence area traffic occurs
It is stifled, if there is traffic congestion, step S6 is executed, it is no to then follow the steps S7；Wherein, while when meeting the following conditions it decides that out
Existing traffic congestion:
RoadVehicle is the vehicle number obtained on current road segment from bayonet, and u is road vehicle congestion threshold average value, σ2
It is road vehicle congestion threshold variance yields；
The speed speed that the section is calculated according to bayonet data, when speed has been more than road speeds threshold value Speed_
When Threshold, that is, current section is determined for congestion, the calculation method of speed speed is as follows:
Wherein, n is all vehicle numbers on this section, t1It is the time by this bayonet, t2It is by being counted with current
It calculates the time of the connected upper bayonet in section, s is road section length, and Speed_Threshold is road speeds threshold value；
Step S6: it is calculated by the following formula whether ratio shared by Floating Car has been more than that Floating Car quantity accounts for vehicle fleet
Threshold value Float_Threshold, if it exceeds i.e. be judged to occurring Floating Car aggregation, be otherwise determined as false triggering, be back to
Step S2；
Wherein, denominator LinkCarData is vehicle number all on section, and molecule ClusterInfo is in current road segment
The upper Floating Car vehicle number for participating in aggregation, FloatPercent is a value between [0,1]；
Step S7: being judged to occurring Floating Car aggregation, the region for sounding an alarm and storing aggregation information of vehicles, assembling
With the temporal information of aggregation, the data that step S2 calculates future time piece are repeated.
It is described in detail for [118.35,29.18]-[120.5,30.55] by Hangzhou longitude and latitude range below:
The concentration range for setting Floating Car is [118.35,29.18]-[120.5,30.55], and the precision searched for is
0.01, zoning within this range is divided into virtual grid.The Floating Car GPS data got is read from historical data base
The calculating of threshold value is carried out with bayonet data.
The threshold value of Floating Car Cluster_Threshold is added maximum with the vehicle number of eight grids of surrounding for each grid
Value, the threshold value in section includes u and σ2.U is by k-means historical data to be polymerized to 3 classes, and what is obtained is larger a kind of biggish
The threshold value of possibility, σ2For the variance of road vehicle quantity.
Calculative data are read in from database, the data of GPS data and bayonet including Floating Car.By following
Whether the Floating Car vehicle number that formula calculates in grid is greater than the vehicle number threshold value of grid:
By calculate can obtain from the 11:00-12:30 period in being with longitude and latitude (119.667,30.019)
The heart, the quantity of a period Floating Car of continuous N (5) is 1852 in the overlay area that radius is 500 meters, 2003,2120,
2451,2520, meet it is above-mentioned be more than Floating Car history vehicle number threshold condition.And continuous 5 period vehicles
Number is all at incremental trend, it is possible thereby to determine the suspicion herein with Floating Car aggregation.This section is learnt from database
History threshold value u is 1008, σ2It is 327, is then obtained according to formula:
It obtains as the probability that Floating Car is assembled being 0.99 greater than 0.9 given (being customized by the user).Floating Car institute simultaneously
The percentage FloatPercent accounted for is greater than the threshold value Float_Threshold that given Floating Car quantity accounts for vehicle fleet.And
And learn that the repetitive rate of Floating Car license plate in two neighboring interval is above license plate repetition rate threshold Repeat_ according to statistics
Threshold (0.6), it is possible thereby to judge currently then to issue early warning just as the coherent condition of Floating Car and be recorded in data
Among library.Vehicle 8:00-14:15 situation of change as shown in Fig. 2, vehicle is largely gathered in one piece as can be seen from Fig. 2,
Vehicle, which has occurred, when 12:30 significantly increases.This method has the characteristics that reliability and high efficiency, overcomes conventional method
The single problem of data source can be so that result be more accurate.Aggregation caused by considering because of congestion can allow result more to have
There is reliability, compensates for the deficiency in conventional method.And for converting calculating that probability is more for Floating Car quantity
Accurately.
The above description of the embodiment is only used to help understand the method for the present invention and its core ideas.It should be pointed out that pair
For those skilled in the art, without departing from the principle of the present invention, the present invention can also be carried out
Some improvements and modifications, these improvements and modifications also fall within the scope of protection of the claims of the present invention.
The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present invention.
Various modifications to these embodiments will be readily apparent to those skilled in the art, as defined herein
General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, of the invention
It is not intended to be limited to the embodiments shown herein, and is to fit to and the principles and novel features disclosed herein phase one
The widest scope of cause.
Claims (2)
1. a kind of Floating Car based on multivariate data fusion assembles detection method, which comprises the following steps:
Step S1: the virtual grid space that area maps to be analyzed on map are made of to one multiple grids, and set such as
Lower parameter: Grid QoS vehicle vehicle number threshold value Cluster_Threshold { k11,k12...knn, exist for representing each grid
The maximum vehicle number passed through in the Δ t period；Road vehicle congestion threshold average value u and road vehicle congestion threshold variance yields σ2, use
Jam situation on every section of characterization；License plate repetition rate threshold Repeat_Threshold, for representing current slot
The repetitive rate of license plate number and license plate number in upper time segment mesh in grid；Floating Car quantity accounts for the threshold value of vehicle fleet
Float_Threshold accounts for the percentage of total vehicle number for representing Floating Car in section；Road speeds threshold value Speed_
Threshold, for representing the minimum speed of the smooth passage of vehicle；
Step S2: it from each grid floating car data corresponding within the Δ t period and bayonet data are obtained in database, floats
Motor-car data are longitude, latitude and the time that GPS terminal equipment uploads, and bayonet data are the vehicle board by each bayonet
It's the vehicle time pasts number；
Step S3: carrying out calculating analysis and judge whether that Floating Car aggregation suspicion occurs to the floating car data of each grid,
If it is not, then step S2 is back to, if it is, triggering executes step S4；Wherein, while when reaching the following conditions it decides that floating
Motor-car assembles suspicion:
Continuous N number of period all meets following formula:
Wherein, CarDetail is the floating car data read in from database, and CarDetail [i] [j] is in current slot,
The vehicle number of i-th row jth column grid, Cluster_Threshold [i] [j] are the i-th row jth column Grid QoS vehicle vehicle number thresholds
Value；It is linear function that the floating car data of continuous N number of period, which is passed through linear regression fit, obtains slope k, and k > 0；
License plate number the repetitive rate repeat, repeat for calculating time adjacent segments in N number of period are more than license plate repetition rate threshold
Repeat_Threshold, wherein repeat calculation formula is as follows:
Wherein, S1It is all vehicles of this period, S2It was all vehicles of a upper period, repeat is license plate number weight
Multiple rate, Repeat_Threshold are license plate repetition rate threshold；
Step S4: the vehicle of Floating Car aggregation suspicion will be currently at according to Density Clustering to together, and clustered and covered with this
Place as Floating Car assemble influence area；
Step S5: Floating Car is calculated according to bayonet data and assembles whether section corresponding to influence area traffic congestion occurs, such as
There is traffic congestion in fruit, executes step S6, no to then follow the steps S7；Wherein, while when meeting the following conditions it decides that and hands over
Logical congestion:
RoadVehicle is the vehicle number obtained on current road segment from bayonet, and u is road vehicle congestion threshold average value, σ2It is road
Vehicle congestion threshold variance yields；
The speed speed that the section is calculated according to bayonet data, when speed has been more than road speeds threshold value Speed_
When Threshold, that is, current section is determined for congestion, the calculation method of speed speed is as follows:
Wherein, n is all vehicle numbers on this section, t1It is the time by this bayonet, t2It is by calculating road with current
The time of a upper bayonet of Duan Xianglian, s are road section lengths, and Speed_Threshold is road speeds threshold value；
Step S6: it is calculated by the following formula whether ratio shared by Floating Car has been more than threshold that Floating Car quantity accounts for vehicle fleet
Value Float_Threshold:
Wherein, denominator LinkCarData is vehicle number all on section, and molecule ClusterInfo is joined on current road segment
With the Floating Car vehicle number of aggregation, FloatPercent is a value between [0,1], and Float_Threshold is to float
Vehicle quantity accounts for the threshold value of vehicle fleet；
If ratio shared by Floating Car has been more than the threshold value Float_Threshold that Floating Car quantity accounts for vehicle fleet, sentence
It is set to and Floating Car aggregation occurs, executes step S7, be otherwise determined as false triggering, be back to step S2；
Step S7: being judged to occurring Floating Car aggregation, sounds an alarm and stores aggregation information of vehicles, the region assembled and gather
The temporal information of collection repeats the data that step S2 calculates future time piece.
2. the Floating Car according to claim 1 based on multivariate data fusion assembles detection method, which is characterized in that wherein
In step S3, N is that user is customized.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611055330.6A CN106530704B (en) | 2016-11-25 | 2016-11-25 | A kind of Floating Car aggregation detection method based on multivariate data fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611055330.6A CN106530704B (en) | 2016-11-25 | 2016-11-25 | A kind of Floating Car aggregation detection method based on multivariate data fusion |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106530704A CN106530704A (en) | 2017-03-22 |
| CN106530704B true CN106530704B (en) | 2019-01-25 |
Family
ID=58357267
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611055330.6A Active CN106530704B (en) | 2016-11-25 | 2016-11-25 | A kind of Floating Car aggregation detection method based on multivariate data fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106530704B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107766808B (en) * | 2017-09-30 | 2021-06-29 | 北京泓达九通科技发展有限公司 | Method and system for clustering moving tracks of vehicle objects in road network space |
| CN107749164B (en) * | 2017-11-23 | 2020-08-11 | 浪潮软件科技有限公司 | Vehicle aggregation analysis method and device |
| CN110032131A (en) * | 2018-01-12 | 2019-07-19 | 中科院微电子研究所昆山分所 | Electric vehicle state monitoring processing system and monitoring system based on Storm |
| CN108648444B (en) * | 2018-04-18 | 2020-05-05 | 北京交通大学 | Signalized intersection operation evaluation method based on grid model |
| KR102654838B1 (en) * | 2018-10-30 | 2024-04-05 | 현대자동차주식회사 | Apparatus and method for analyzing driving data, and vehicle system |
| CN109544932B (en) * | 2018-12-19 | 2021-03-19 | 东南大学 | Urban road network flow estimation method based on fusion of taxi GPS data and gate data |
| CN109686090B (en) * | 2019-01-17 | 2020-03-27 | 中南大学 | Virtual traffic flow calculation method based on multi-source data fusion |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4175312B2 (en) * | 2004-09-17 | 2008-11-05 | 株式会社日立製作所 | Traffic information prediction device |
| CN102568209B (en) * | 2012-02-21 | 2014-03-12 | 福建工程学院 | Commercial vehicle gathering event early warning method based on floating vehicle technology |
| CN102750826B (en) * | 2012-06-26 | 2014-08-13 | 浙江大学 | Identification method of driver response behaviors under group induction information |
| CN103198672A (en) * | 2013-03-27 | 2013-07-10 | 大连海事大学 | Method for laying urban road network traffic flow detectors |
-
2016
- 2016-11-25 CN CN201611055330.6A patent/CN106530704B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN106530704A (en) | 2017-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106530704B (en) | A kind of Floating Car aggregation detection method based on multivariate data fusion | |
| CN105376260B (en) | A kind of exception flow of network monitoring system based on density peaks cluster | |
| Wang et al. | GSNet: Learning spatial-temporal correlations from geographical and semantic aspects for traffic accident risk forecasting | |
| Ahmed et al. | The viability of using automatic vehicle identification data for real-time crash prediction | |
| Ahmed et al. | Bayesian updating approach for real-time safety evaluation with automatic vehicle identification data | |
| Xia et al. | A clustering approach to online freeway traffic state identification using ITS data | |
| Jiang et al. | Investigating macro-level hotzone identification and variable importance using big data: A random forest models approach | |
| Lu et al. | Vulnerability analysis of transportation network under scenarios of sea level rise | |
| CN104021672B (en) | A kind of method and apparatus obtaining traffic congestion index | |
| WO2021051609A1 (en) | Method and apparatus for predicting fine particulate matter pollution level, and computer device | |
| WO2018122803A1 (en) | Smart road traffic anomaly detection method | |
| CN105206057B (en) | Detection method and system based on Floating Car resident trip hot spot region | |
| CN103150900A (en) | Traffic jam event automatic detecting method based on videos | |
| CN105869398B (en) | A kind of unimpeded degree judgment method of road traffic based on K-means clusters | |
| CN101710448A (en) | Road traffic state detecting device based on omnibearing computer vision | |
| CN113870564B (en) | Traffic jam classification method and system for closed road section, electronic device and storage medium | |
| CN106384507A (en) | Travel time real-time estimation method based on sparse detector | |
| CN112767695A (en) | Real-time prediction method and system for traffic accident risk at signalized intersection | |
| Orsini et al. | A conflict-based approach for real-time road safety analysis: Comparative evaluation with crash-based models | |
| CN109740195A (en) | A kind of appraisal procedure of extreme value typhoon wind velocity distributing paremeter model and design typhoon wind speed based on weather station observation data | |
| Gore et al. | Congestion index and reliability-based freeway level of service | |
| JP2002190090A (en) | Traffic flow abnormal condition detector and its method (spectrum) | |
| CN113283548B (en) | Vehicle safety scoring method, device, equipment and storage medium | |
| CN108376292A (en) | A kind of crowd's method for predicting, system and equipment | |
| Park et al. | Innovative single-loop speed estimation model with advanced loop data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20170322 Assignee: Hangzhou Cheng Road Polytron Technologies Inc Assignor: Hangzhou Electronic Science and Technology Univ Contract record no.: 2019330000034 Denomination of invention: Floating car aggregation detection method based on multivariate data fusion Granted publication date: 20190125 License type: Common License Record date: 20190319 |
|
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20170322 Assignee: TAIZHOU SUNJOY AUTOMOBILE PRODUCT Co.,Ltd. Assignor: HANGZHOU DIANZI University Contract record no.: X2020330000020 Denomination of invention: Floating car aggregation detection method based on multivariate data fusion Granted publication date: 20190125 License type: Common License Record date: 20200422 |
|
| EE01 | Entry into force of recordation of patent licensing contract |