CN106803348A - A kind of overpass vehicle travel time Forecasting Approach for Short-term based on bayonet socket - Google Patents
A kind of overpass vehicle travel time Forecasting Approach for Short-term based on bayonet socket Download PDFInfo
- Publication number
- CN106803348A CN106803348A CN201710192848.2A CN201710192848A CN106803348A CN 106803348 A CN106803348 A CN 106803348A CN 201710192848 A CN201710192848 A CN 201710192848A CN 106803348 A CN106803348 A CN 106803348A
- Authority
- CN
- China
- Prior art keywords
- overpass
- data
- travel time
- measurement period
- bayonet socket
- 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
- G08G1/0104—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
- G08G1/01—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)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention belongs to overpass field of traffic, and in particular to a kind of overpass vehicle travel time Forecasting Approach for Short-term based on bayonet socket.Institute of the invention comprising the step of be：1), tollgate devices are installed at the Entrance ramp and exit ramp of overpass and are debugged；2) bayonet socket data, are obtained；3), the license board information in the bayonet socket data for being obtained, matches to overpass exit ramp with the data record of Entrance ramp；4) overpass vehicle average travel time in single measurement period, is calculated；5) overpass vehicle travel time predicted value, is calculated.The transport information that the present invention can be obtained according to tollgate devices, the accurate Accurate Prediction for realizing overpass vehicle average travel time in real time, and then the traffic and variation tendency in future are provided for traveler, induction traveler selects rational travel time, trip route, improves the space-time inhomogeneities of traffic flow distribution.
Description
Technical field
The invention belongs to overpass field of traffic, and in particular to a kind of overpass vehicle travel time based on bayonet socket
Forecasting Approach for Short-term.
Background technology
The increase of number of vehicles, a series of problems, such as traffic congestion, traffic accident, traffic pollution is brought to city, and
The proposition of intelligent transportation system, exactly in order to efficiently solve above mentioned problem.Development intelligent transportation system, most basic, most critical
Problem be the real-time dynamic data for how gathering road traffic, so as to the upper system and module that facilitate intelligent transportation enter line number
According to treatment, analysis and prediction, the real-time monitoring of transport information is realized.Current existing traffic data collection mode have a lot, compared with
For ripe real time traffic data acquisition method has two kinds：The first is sensor-based real time traffic data acquisition method,
Comprising actively monitoring method and passive detection method.Sensor includes piezoelectric transducer, buried coil checker, microwave thunder
Up to, ultrasonic wave, image first-class, the traffic information that can be gathered and calculate includes speed, vehicle flowrate, lane occupancy, vehicle
Classification information etc..Although the principle of various sensors is different with applicable situation, mostly exist to installation site and environment according to
Rely, and face the problems such as initial investment is huge, maintenance cost is high, coverage rate is small, data precision is relatively low, real-time is poor, have compared with
Big limitation.Second is the real time traffic data acquisition method based on Floating Car.Floating Car is and is mounted with GPS and wireless
The taxi and bus of communication module, when Floating Car is travelled on road surface, periodically gather the gps data of itself and send
To server end, the drive route of Floating Car is estimated by map matching technology by server, and then obtain floating vehicle
Journey time, travel speed and by the average speed of road.Relative to first method, although the method in cost and
All made moderate progress in coverage rate, and equipment is easy to maintain, will not be disturbed other irrelevant factors by weather, pedestrian etc., but still
Larger one-time investment, data precision is needed also to be limited by map matching technology.In view of communications cost, floating vehicle
The frequency acquisition of gps data is often all relatively low, and generally in 15min or so, and server end is due to lacking traffic contextual information
Also it is only capable of that invalid data is screened and filtered using gps data, this just brings very to data prediction and map match
Big difficulty, reduces the real-time of data while server burden is increased.
The content of the invention
The purpose of the present invention is to overcome above-mentioned the deficiencies in the prior art, there is provided a kind of efficient quick based on the overhead of bayonet socket
Road vehicle journey time Forecasting Approach for Short-term；The transport information that the present invention can be obtained according to tollgate devices, it is accurate real-time
The Accurate Prediction of overpass vehicle average travel time is realized, and then for traveler provides the traffic in future and changes
Gesture, induction traveler selects rational travel time, trip route, improves the space-time inhomogeneities of traffic flow distribution.
To achieve the above object, present invention employs following technical scheme：
A kind of overpass vehicle travel time Forecasting Approach for Short-term based on bayonet socket, it is characterised in that including following step
Suddenly：
1), tollgate devices are installed at the Entrance ramp and exit ramp of overpass and are debugged；
2) bayonet socket data, are obtained；
The bayonet socket data at least include bayonet socket numbering, bayonet socket positional information, bayonet socket place ring road type, by bayonet socket
Corresponding time when license board information and each vehicle are by bayonet socket；
3), according to license board information, overpass exit ramp is matched with the data record of Entrance ramp；Matched
Cheng Wei：
The license board information that each bayonet socket is detected Entrance ramp corresponding with this section of overpass and exit ramp are carried out one by one
Information matches, if the existing Entrance ramp that can be matched of the license board information, has the exit ramp that can be matched, then the license board information again
Corresponding bayonet socket data retain；If license board information only has the Entrance ramp that can be matched or the exit ramp that can only match,
Then the bayonet socket data corresponding to the license board information are rejected；
4) measurement period, is set, overpass vehicle average travel time in single measurement period is calculated；Sub-step
It is as follows：
(4a), according to step 3) the middle data record for retaining, vehicle is by gateway ring road in the single measurement period of calculating
Time difference, obtain the journey time of each vehicle on overpass in single measurement period；
(4b), the stroke to each vehicle on overpass in the single measurement period that is obtained in all of sub-step (4a)
Time averages, and obtains overpass vehicle average travel time in single measurement period；
5) overpass vehicle travel time predicted value, is calculated；Sub-step is as follows：
(5a), the data using the current statistic cycle and historical data build state vector A：
A=[t (i), t (i-1), t (i-2), t (i-3), th (i), th (i-1), th (i-2), th (i-3)]
Wherein：
T (i) is i-th overpass vehicle average travel time of measurement period；
T (i-1) is the overpass vehicle average travel time of (i-1) individual measurement period；
T (i-2) is the overpass vehicle average travel time of (i-2) individual measurement period；
T (i-3) is the overpass vehicle average travel time of (i-3) individual measurement period；
Th (i) is i-th overpass vehicle average travel time of measurement period in historical data；
Th (i-1) is the overpass vehicle average travel time of (i-1) individual measurement period in historical data；
Th (i-2) is the overpass vehicle average travel time of (i-2) individual measurement period in historical data；
Th (i-3) is the overpass vehicle average travel time of (i-3) individual measurement period in historical data；
(5b), according to below equation, obtain correspondence group data in real time data and historical data apart from d：
Wherein, djIt is the distance of jth group data in real time data and historical data；The value of d is smaller, then real time data and should
The matching degree of group historical data is higher；
(5c), the result of calculation according to sub-step (5b), chooses and 10 groups of historical datas of real time data matching degree highest；
(5d), according to the historical data obtained in sub-step (5c), overpass vehicle travel time is calculated by following formula
Predicted value：
Wherein：
T (i+1) is the overpass vehicle travel time predicted value of (i+1) individual measurement period；
thj(i+1) be jth group data in 10 groups of historical datas choosing in sub-step (5c) (i+1) individual measurement period
Overpass vehicle average travel time.
Step 4) in measurement period be 5 minutes.
The beneficial effects of the present invention are：
1), by such scheme, data acquisition cost, throwing high present invention, avoiding conventional traffic acquisition mode because of great number
Cannot accurately realize that overpass traffic judges in real time caused by the defect such as money burden and low real time data acquisition
Problem.The present invention by tollgate devices acquisition transport information, and based on historical data, search in the historical data with it is current
The similar historic state of real-time status, and the historic state matched with current real-time status is applied to status predication, so that
The prediction of overpass vehicle travel time is accurately and real-time realized, its calculation is simple and convenient, range of application is very
Extensively, and obviously it is of great significance for analyzing the traffic circulation state tool of overpass.
Brief description of the drawings
Fig. 1 is method of the present invention FB(flow block).
Specific embodiment
For ease of understanding, following description is made to specific workflow of the invention here in connection with Fig. 1：
As shown in Figure 1, the overpass vehicle travel time Forecasting Approach for Short-term based on bayonet socket of the invention is included
The step of be：
(1), tollgate devices are installed at the Entrance ramp and exit ramp of overpass and are debugged；
(2) bayonet socket data, are obtained；
(3), the license board information in the bayonet socket data for being obtained, to overpass exit ramp and the number of Entrance ramp
Matched according to record；
(4), with 5 minutes for a measurement period, overpass vehicle average travel time in single measurement period is calculated；
(5) overpass vehicle travel time predicted value, is calculated.
The step 2) in, the bayonet socket data at least include ring road class where bayonet socket numbering, bayonet socket positional information, bayonet socket
Corresponding time when type, the license board information by bayonet socket and each vehicle are by bayonet socket.
The step 3) in, specific matching process is：The license board information that each bayonet socket is detected and this section of overpass phase
The Entrance ramp and exit ramp answered carry out information matches one by one.If the existing Entrance ramp that can be matched of the license board information, and
There is the exit ramp that can be matched, then the bayonet socket data corresponding to the license board information retain；If license board information only has what can be matched
Entrance ramp or the exit ramp that can only match, then the bayonet socket data rejecting corresponding to the license board information.
The step 4) in, the sub-step for calculating overpass vehicle average travel time in single measurement period is as follows：
(4a), according to step 3) the middle data record for retaining, vehicle is by gateway ring road in the single measurement period of calculating
Time difference, obtain the journey time of each vehicle on overpass in single measurement period；
(4b), the stroke to each vehicle on overpass in the single measurement period that is obtained in all of sub-step (4a)
Time averages, and obtains overpass vehicle average travel time in single measurement period.
The step 5) in, the sub-step for calculating overpass vehicle travel time predicted value is as follows：
(5a), the data using the current statistic cycle and historical data build state vector A：
A=[t (i), t (i-1), t (i-2), t (i-3), th (i), th (i-1), th (i-2), th (i-3)]
Wherein：
T (i) is i-th overpass vehicle average travel time of measurement period；
T (i-1) is the overpass vehicle average travel time of (i-1) individual measurement period；
T (i-2) is the overpass vehicle average travel time of (i-2) individual measurement period；
T (i-3) is the overpass vehicle average travel time of (i-3) individual measurement period；
Th (i) is i-th overpass vehicle average travel time of measurement period in historical data；
Th (i-1) is the overpass vehicle average travel time of (i-1) individual measurement period in historical data；
Th (i-2) is the overpass vehicle average travel time of (i-2) individual measurement period in historical data；
Th (i-3) is the overpass vehicle average travel time of (i-3) individual measurement period in historical data.
(5b), according to below equation, obtain correspondence group data in real time data and historical data apart from d：
Wherein, djIt is the distance of jth group data in real time data and historical data；The value of d is smaller, then real time data and should
The matching degree of group historical data is higher；
(5c), the result of calculation according to sub-step (5b), chooses and 10 groups of historical datas of real time data matching degree highest；
(5d), according to the historical data obtained in sub-step (5c), overpass vehicle travel time is calculated by following formula
Predicted value：
Wherein：
T (i+1) is the overpass vehicle travel time predicted value of (i+1) individual measurement period；
thj(i+1) be jth group data in 10 groups of historical datas choosing in sub-step (5c) (i+1) individual measurement period
Overpass vehicle average travel time.
Further to deepen the understanding of the present invention, there is provided herein following examples, make further with to the present invention
It is specific to discuss：
Embodiment 1：
Entrance ramp a and exit ramp b in test section carry out the installation and debugging of tollgate devices, Entrance ramp a and
The distance between exit ramp b is 3.4km.
1) sampling period, is taken for 8:00:00-8:05:The bayonet socket data of 00 Entrance ramp a and exit ramp b, by car
Board information matches, have 6 cars to sail test section into from Entrance ramp a, and test section is rolled away from from exit ramp b；The corresponding time
It is respectively：
Vehicle 1：By the time 8 of Entrance ramp a:00:00, by the time 8 of exit ramp b:03:55；
Vehicle 2：By the time 8 of Entrance ramp a:00:06, by the time 8 of exit ramp b:04:00；
Vehicle 3：By the time 8 of Entrance ramp a:00:11, by the time 8 of exit ramp b:04:10；
Vehicle 4：By the time 8 of Entrance ramp a:00:45, by the time 8 of exit ramp b:04:30；
Vehicle 5：By the time 8 of Entrance ramp a:01:00, by the time 8 of exit ramp b:04:58；
Vehicle 6：By the time 8 of Entrance ramp a:01:03, by the time 8 of exit ramp b:04:59.
Test section is calculated in the sampling period 8:00:00-8:05:00 journey time：
T=(235+234+239+225+238+230)/6=233.5s
2) first three sampling period 7, is obtained:55:00-8:00:00、7:50:00-7:55:00、7:45:00-7:50:00
Journey time be respectively：235.9s, 236.3s, 238.8s.
3) sampling period 8, is retrieved in the historical data:00:00-8:05:00、7:55:00-8:00:00、7:50:00-7:
55:00、7:45:00-7:50:00 journey time, calculates the matching degree of real time data and historical data, chooses and number in real time
According to matching degree preceding 10 groups of historical datas higher.This 10 groups of historical datas are in the sampling period 8:05:00-8:10:During 00 stroke
Between be respectively：231.8s, 231.3s, 230.1s, 231.7s, 230.9s, 231.5s, 230.2s, 231.7s, 229.7s,
230.5s。
4) predicted value of journey time：
(231.8+231.3+230.1+231.7+230.9+231.5+230.2+231.7+229.7+23 0.5)/10=
230.94s
Sampling period 8 is obtained by prediction:05:00-8:10:00 journey time is 230.94s.
The sampling period 8 is calculated by the bayonet socket data for obtaining:05:00-8:10:00 traveled distance time is
233.1s, is 0.93% with the error of predicted value, and error amount is in allowed band.
Claims (2)
1. a kind of overpass vehicle travel time Forecasting Approach for Short-term based on bayonet socket, it is characterised in that comprise the following steps：
1), tollgate devices are installed at the Entrance ramp and exit ramp of overpass and are debugged；
2) bayonet socket data, are obtained；
The bayonet socket data at least include ring road type, the car plate by bayonet socket where bayonet socket numbering, bayonet socket positional information, bayonet socket
Corresponding time when information and each vehicle are by bayonet socket；
3), according to license board information, overpass exit ramp is matched with the data record of Entrance ramp；Matching process
For：
The license board information that each bayonet socket is detected Entrance ramp corresponding with this section of overpass and exit ramp carry out information one by one
Matching, if the existing Entrance ramp that can be matched of the license board information, there is the exit ramp that can be matched again, then license board information institute is right
The bayonet socket data answered retain；If license board information only has the Entrance ramp that can be matched or the exit ramp that can only match, should
Bayonet socket data corresponding to license board information are rejected；
4) measurement period, is set, overpass vehicle average travel time in single measurement period is calculated；Sub-step is such as
Under：
(4a), according to step 3) in the data record that retains, calculate vehicle in single measurement period by gateway ring road when
Between it is poor, obtain the journey time of each vehicle on overpass in single measurement period；
(4b), the journey time to each vehicle on overpass in the single measurement period that is obtained in all of sub-step (4a)
Average, obtain overpass vehicle average travel time in single measurement period；
5) overpass vehicle travel time predicted value, is calculated；Sub-step is as follows：
(5a), the data using the current statistic cycle and historical data build state vector A：
A=[t (i), t (i-1), t (i-2), t (i-3), th (i), th (i-1), th (i-2), th (i-3)]
Wherein：
T (i) is i-th overpass vehicle average travel time of measurement period；
T (i-1) is the overpass vehicle average travel time of (i-1) individual measurement period；
T (i-2) is the overpass vehicle average travel time of (i-2) individual measurement period；
T (i-3) is the overpass vehicle average travel time of (i-3) individual measurement period；
Th (i) is i-th overpass vehicle average travel time of measurement period in historical data；
Th (i-1) is the overpass vehicle average travel time of (i-1) individual measurement period in historical data；
Th (i-2) is the overpass vehicle average travel time of (i-2) individual measurement period in historical data；
Th (i-3) is the overpass vehicle average travel time of (i-3) individual measurement period in historical data；
(5b), according to below equation, obtain correspondence group data in real time data and historical data apart from d：
Wherein, djIt is the distance of jth group data in real time data and historical data；The value of d is smaller, then real time data and the group are gone through
The matching degree of history data is higher；
(5c), the result of calculation according to sub-step (5b), chooses and 10 groups of historical datas of real time data matching degree highest；
(5d), according to the historical data obtained in sub-step (5c), overpass vehicle travel time is calculated by following formula and is predicted
Value：
Wherein：
T (i+1) is the overpass vehicle travel time predicted value of (i+1) individual measurement period；
thj(i+1) be jth group data in 10 groups of historical datas choosing in sub-step (5c) (i+1) individual measurement period height
Frame road vehicle average travel time.
2. a kind of overpass vehicle travel time Forecasting Approach for Short-term based on bayonet socket according to claim 1, it is special
Levy and be：Step 4) in measurement period be 5 minutes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710192848.2A CN106803348A (en) | 2017-03-28 | 2017-03-28 | A kind of overpass vehicle travel time Forecasting Approach for Short-term based on bayonet socket |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710192848.2A CN106803348A (en) | 2017-03-28 | 2017-03-28 | A kind of overpass vehicle travel time Forecasting Approach for Short-term based on bayonet socket |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106803348A true CN106803348A (en) | 2017-06-06 |
Family
ID=58981739
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710192848.2A Pending CN106803348A (en) | 2017-03-28 | 2017-03-28 | A kind of overpass vehicle travel time Forecasting Approach for Short-term based on bayonet socket |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106803348A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107085944A (en) * | 2017-06-28 | 2017-08-22 | 北京数行健科技有限公司 | A kind of traffic data processing system and method |
| CN109377759A (en) * | 2018-11-28 | 2019-02-22 | 南京莱斯信息技术股份有限公司 | A kind of method of fleet's journey time in acquisition discrete traffic flow |
| CN109658697A (en) * | 2019-01-07 | 2019-04-19 | 平安科技（深圳）有限公司 | Prediction technique, device and the computer equipment of traffic congestion |
| CN113053114A (en) * | 2021-03-12 | 2021-06-29 | 广西计算中心有限责任公司 | Dynamic prediction and inspection method for exit station and exit time of illegal vehicles on highway |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102034350A (en) * | 2009-09-30 | 2011-04-27 | 北京四通智能交通系统集成有限公司 | Short-time prediction method and system of traffic flow data |
| CN103177570A (en) * | 2012-12-25 | 2013-06-26 | 北京交通发展研究中心 | Method for predicting traffic jam indexes for rush hours in morning and evening |
| CN103927872A (en) * | 2014-04-28 | 2014-07-16 | 武汉大学 | Method for predicting multi-period travel time distribution based on floating vehicle data |
| CN104952251A (en) * | 2015-06-18 | 2015-09-30 | 安徽四创电子股份有限公司 | Urban viaduct traffic state sensing method based on bayonet and HADOOP technology |
| CN104952259A (en) * | 2015-06-18 | 2015-09-30 | 安徽四创电子股份有限公司 | Traffic event duration time calculation method based on traffic scene radar |
| CN105118294A (en) * | 2015-09-25 | 2015-12-02 | 山东易构软件技术股份有限公司 | Short-time traffic flow prediction method based on state pattern |
| CN105931463A (en) * | 2016-06-27 | 2016-09-07 | 安徽四创电子股份有限公司 | Method for calculating road traffic performance index based on traffic surface radar |
| CN105931462A (en) * | 2016-06-27 | 2016-09-07 | 安徽四创电子股份有限公司 | Tunnel emergency determining method based on license plate identification |
| CN106056923A (en) * | 2016-06-27 | 2016-10-26 | 安徽四创电子股份有限公司 | Road traffic state discrimination method based on traffic scene radar |
-
2017
- 2017-03-28 CN CN201710192848.2A patent/CN106803348A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102034350A (en) * | 2009-09-30 | 2011-04-27 | 北京四通智能交通系统集成有限公司 | Short-time prediction method and system of traffic flow data |
| CN103177570A (en) * | 2012-12-25 | 2013-06-26 | 北京交通发展研究中心 | Method for predicting traffic jam indexes for rush hours in morning and evening |
| CN103927872A (en) * | 2014-04-28 | 2014-07-16 | 武汉大学 | Method for predicting multi-period travel time distribution based on floating vehicle data |
| CN104952251A (en) * | 2015-06-18 | 2015-09-30 | 安徽四创电子股份有限公司 | Urban viaduct traffic state sensing method based on bayonet and HADOOP technology |
| CN104952259A (en) * | 2015-06-18 | 2015-09-30 | 安徽四创电子股份有限公司 | Traffic event duration time calculation method based on traffic scene radar |
| CN105118294A (en) * | 2015-09-25 | 2015-12-02 | 山东易构软件技术股份有限公司 | Short-time traffic flow prediction method based on state pattern |
| CN105931463A (en) * | 2016-06-27 | 2016-09-07 | 安徽四创电子股份有限公司 | Method for calculating road traffic performance index based on traffic surface radar |
| CN105931462A (en) * | 2016-06-27 | 2016-09-07 | 安徽四创电子股份有限公司 | Tunnel emergency determining method based on license plate identification |
| CN106056923A (en) * | 2016-06-27 | 2016-10-26 | 安徽四创电子股份有限公司 | Road traffic state discrimination method based on traffic scene radar |
Non-Patent Citations (6)
| Title |
|---|
| SIMON OH: "Improvement of Search Strategy With K-Nearest Neighbors Approach for Traffic State Prediction", 《IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS》 * |
| 屈莉: "基于浮动车数据非参数回归短时交通速度预测", 《计算机工程与设计》 * |
| 张涛: "基于K近邻非参数回归的短时交通流预测方法", 《系统工程理论与实践》 * |
| 梁秀霞: "非参数回归算法在短时交通流预测中的应用", 《自动化仪表》 * |
| 王翔: "基于K最近邻算法的高速公路短时行程时间预测", 《中国公路学报》 * |
| 翁剑成: "基于非参数回归的快速路行程速度短期预测算法", 《公路交通科技》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107085944A (en) * | 2017-06-28 | 2017-08-22 | 北京数行健科技有限公司 | A kind of traffic data processing system and method |
| CN109377759A (en) * | 2018-11-28 | 2019-02-22 | 南京莱斯信息技术股份有限公司 | A kind of method of fleet's journey time in acquisition discrete traffic flow |
| CN109377759B (en) * | 2018-11-28 | 2021-02-26 | 南京莱斯信息技术股份有限公司 | Method for acquiring train journey time in discontinuous traffic flow |
| CN109658697A (en) * | 2019-01-07 | 2019-04-19 | 平安科技（深圳）有限公司 | Prediction technique, device and the computer equipment of traffic congestion |
| CN109658697B (en) * | 2019-01-07 | 2021-09-24 | 平安科技（深圳）有限公司 | Traffic congestion prediction method and device and computer equipment |
| CN113053114A (en) * | 2021-03-12 | 2021-06-29 | 广西计算中心有限责任公司 | Dynamic prediction and inspection method for exit station and exit time of illegal vehicles on highway |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102737510B (en) | Real-time traffic condition acquisition method based on mobile intelligent terminal | |
| CN102855759B (en) | Automatic collecting method of high-resolution satellite remote sensing traffic flow information | |
| CN103500503B (en) | A kind of accurate road condition analyzing method and system based on mass-rent pattern | |
| CN105023428B (en) | Traffic information appraisal procedure and device | |
| CN104778834B (en) | Urban road traffic jam judging method based on vehicle GPS data | |
| CN106803348A (en) | A kind of overpass vehicle travel time Forecasting Approach for Short-term based on bayonet socket | |
| CN104408917B (en) | Based on smart mobile phone acceleration transducer real-time traffic method of estimation | |
| CN102637365B (en) | System and method for realizing urban traffic intelligence by utilizing i-RFID (interactive-radio frequency identification) | |
| CN103714603B (en) | Based on the bus passenger flow statistical system of infrared distance sensor | |
| CN105303832B (en) | Overpass road section traffic volume congestion index computational methods based on microwave vehicle detector | |
| CN101615340A (en) | Real-time information processing method in the bus dynamic dispatching | |
| CN104392606B (en) | Bus location mileage-based road condition detection method and system | |
| CN104750963B (en) | Intersection delay duration method of estimation and device | |
| CN104867192A (en) | Automobile driving path identification system based on automotive electronic identification, and method thereof | |
| CN101303802A (en) | Method and system for on-line automatically beforehand judgment of overloading wagon | |
| CN101739824A (en) | Data fusion technology-based traffic condition estimation method | |
| CN103440422A (en) | Bus behind-schedule recovering method based on arrival time predication with time window | |
| CN106680212B (en) | A kind of rectilinear telemetering motor vehicle tail system based on road reflection | |
| CN108038929A (en) | A kind of ETC automatic checkout systems and method with weighing system | |
| CN103198713A (en) | Traffic accident reduction vehicle regulation and control method based on traffic data and weather data | |
| CN106530749A (en) | Signal control intersection queuing length estimation method based on single section low frequency detection data | |
| CN104064049B (en) | A kind of intelligent transportation road capacity note broadcasting system | |
| CN110285877A (en) | Train real time location tracking and speed calculation method based on Spark Streaming | |
| CN101404120A (en) | Method and apparatus for judging floating vehicle travelling state | |
| CN102722984A (en) | Real-time road condition monitoring method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170606 |