CN108399741A - A kind of intersection flow estimation method based on real-time vehicle track data - Google Patents
A kind of intersection flow estimation method based on real-time vehicle track data Download PDFInfo
- Publication number
- CN108399741A CN108399741A CN201810072445.9A CN201810072445A CN108399741A CN 108399741 A CN108399741 A CN 108399741A CN 201810072445 A CN201810072445 A CN 201810072445A CN 108399741 A CN108399741 A CN 108399741A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- time
- time interval
- departure
- basic time
- 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.)
- Granted
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
- G08G1/0125—Traffic data processing
- G08G1/0133—Traffic data processing for classifying traffic situation
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
Abstract
The present invention relates to a kind of intersection flow estimation methods based on real-time vehicle track data, include the following steps：1) research period [0, T] is divided into multiple continuous basic time intervals, and classified to basic time interval；2) according to sorted basic time interval, under the conditions of given arrival time, vehicle time of departure likelihood function is calculated according to the corresponding vehicle time of departure conditional probability of different basic time interval types, and calculate final likelihood function；3) vehicle arriving rate obtained in each basic time interval is solved to the likelihood function of vehicle time of departure.Compared with prior art, the present invention has many advantages, such as to adapt to low sample frequency, the data environment of sampling rate and historical data, strong robustness, real-time are high, accuracy is good without merging.
Description
Technical field
The present invention relates to field of traffic control, more particularly, to a kind of intersection flow based on real-time vehicle track data
Method of estimation.
Background technology
Chief component of the signalized intersections as city road network can be sent out often since the periodicity of traffic lights replaces
Raw traffic congestion, largely constrains the overall operation efficiency of City road traffic system.Period flow is handed over as evaluation
On the one hand one important indicator of prong operation can be used for estimating indirectly queue length, vehicle delay, stop frequency and stroke
On the other hand the indexs such as time can directly be fed back for signal timing optimization.
It is realized currently, being mainly based upon fixed point detector about the research of flow estimation both at home and abroad, prediction technique includes filter
The model analyzings method such as the mathematical statistics methods such as wave algorithm and parent map, Cell Transmission Model.Flow based on fixed point detector is estimated
The problem that meter method is primarily present implantation of device and maintenance cost is high, upload frequencies are low, and the detections such as obtained speed, flow
Index is cannot to embody the fluctuation and randomness of traffic flow based on the average value of detection step-length.Mathematical statistics method is usually
History detection data is realized, and model parameter needs real example data scaling mostly；Method based on parent map will be equally based on
Historical data is fitted the relationship of traffic flow parameter, general poor；And the method for the model analyzings such as Cell Transmission Model all exists
Ad hoc hypothesis, the relationship between traffic flow parameter are abstracted, such as simulation reaches distribution, homogeneity hypothesis etc., though
The stochastic behaviour of traffic flow so is considered, but is varied in different localities for the hypothesis of traffic flow parameter quantitative relationship, restricted application.
The research appearance that flow estimation is done using track is later, although the advantage that track data has precision high real-time strong, in reality
There is a problem of that Sparse, prediction error are big in the application of border since capture rate is low, and the existing stream using track data
Amount estimation method estimated accuracy under the conditions of self adaptive control can reduce.Therefore, a generality and with strong applicability is established
Period flow estimation method has important practical significance for the further application of track data.
Invention content
It is an object of the present invention to overcome the above-mentioned drawbacks of the prior art and provide one kind being based on real-time vehicle
The intersection flow estimation method of track data.
The purpose of the present invention can be achieved through the following technical solutions：
A kind of intersection flow estimation method based on real-time vehicle track data, includes the following steps：
1) research period [0, T] is divided into multiple continuous basic time intervals, and basic time interval is divided
Class；
2) according to sorted basic time interval, under the conditions of given arrival time, according between different basic times
Vehicle time of departure likelihood function is calculated every the corresponding vehicle time of departure conditional probability of type, and calculates final likelihood function；
3) vehicle arriving rate obtained in each basic time interval is solved to the likelihood function of vehicle time of departure.
In the step 1), the type at basic time interval includes：
Type I：[r(ai),ai), the bright moment to first sampling vehicle E.T.A of current period is opened from red light,
The vehicle reached in the basic time interval can be in corresponding effective green time τk=[g (ai),bi) in sail out of intersection,
In, r (ai) it is that red light opens bright moment, aiFor the E.T.A of vehicle i, biFor the estimated time of departure of vehicle i, g (ai) be
The green light of current period opens the bright moment；
Type II：[ai-1,ai), continuous two samplings vehicle E.T.A interval in current period has accordingly
Imitate green time τkFor [bi-1,bi)；
Type-iii：[ai-1,g(ai-1)+G), last vehicle program arrival time to the green of current period of current period
Lamp finish time, wherein G is the green light duration of current period, corresponding effective green time τkFor [bi-1,g(ai-1)
+G)。
The E.T.A a of the vehicle iiCalculation formula be：
For queuing vehicle：
Wherein, (ti,di) be vehicle i in the non-queuing tracing point information of t moment, vfFor free stream velocity, l is stop line
Position, vehicle i estimated times of departure biFor green light open it is bright after leave the stop line moment；
For non-queuing vehicle：
E.T.A with it is expected that the time of departure it is identical, for vehicle i green lights open it is bright after leave the stop line moment, i.e.,：
ai=bi。
The step 2) specifically includes following steps：
21) arrival of setting intersection vehicles meets nonhomogeneous Poisson distribution；
22) the joint probability density function L of all sampling vehicle E.T.A in the research period is obtaineda, and by its
As given arrival time condition；
23) under the conditions of given arrival time, the different basic time interval types corresponding vehicle time of departure is calculated
Conditional probability；
24) the vehicle time of departure is calculated according to the corresponding vehicle time of departure conditional probability of different basic time interval types
Likelihood function Lb；
25) final likelihood function L is calculated.
In the step 22), joint probability density function LaCalculating formula be：
Wherein, n is the sampling vehicle number in search time section, and p is vehicle sample rate in the research period, p λ (ai) it is sampling
The average arrival rate of vehicle i, λ (ai) it is aiThe instantaneous arrival rate of vehicle at moment, Λ are to reach intensity, and λ (t) is in t time intervals
Vehicle arriving rate, λkFor the vehicle arriving rate in k-th of basic time interval, TkFor k-th basic time interval it is lasting when
Long, K is basic time interval sum.
In the step 24), vehicle time of departure likelihood function LbCalculating formula be：
Vehicle time of departure likelihood function is：
Wherein, K1Indicate that the basic time interval of type I and Type II meets ai＜ biSet when situation, and K2For class
The basic time interval of type I and Type II meets ai=biWhen and type-iii basic time spacing case when set, hs
Saturation headway, M are sailed out of for vehiclekFor the maximum vehicle number reached in k-th of basic time interval,Between basic time
Every the non-sampled vehicle number of interior arrival, j is the vehicle reached in basic time interval.
The calculating formula of the final likelihood function L is：
Compared with prior art, the present invention has the following advantages：
1) discharge that known vehicle in the prior art uniformly reaches, history vehicle mode etc. is it is assumed that more practicability；
2) real-time, it can realize that the flow detection rolled based on the period, accuracy are high；
3) method is advanced, strong robustness, can adapt to the data environment that China adapts to low sample frequency, low sampling rate.
Description of the drawings
Fig. 1 is the method for the present invention flow chart.
Fig. 2 is vehicle space-time trajectory diagram.
Fig. 3 is that basic time interval defines schematic diagram, wherein figure (3a) is Class1, and figure (3b) is type 2, and figure (3c) is
Type 3.
Fig. 4 is embodiment intersection geometry schematic diagram.
Fig. 5 is embodiment vehicle space-time track schematic diagram.
Fig. 6 is estimated result comparison diagram, wherein figure (6a) is morning peak period estimated flow figure, and figure (6b) is early high
Peak time section flow mean absolute percentage error, figure (6c) are flat peak time section estimated flow figure, and figure (6d) is the flat period
Flow mean absolute percentage error.
Specific implementation mode
The present invention is described in detail with specific embodiment below in conjunction with the accompanying drawings.
Embodiment
The present invention is described in detail with specific embodiment below in conjunction with the accompanying drawings.The present embodiment is with technical solution of the present invention
Premised on implemented, give detailed embodiment and specific operating process, but protection scope of the present invention is not limited to
Following embodiments.
As shown in Figure 1, since signalized intersections signal period property is replaced, intersection can form multiply traffic shock wave.Work as red light
Qi Liang, vehicle are forced to stop, and sequentially add queuing；Green light opens bright moment, and vehicle sails out of intersection with saturation volume rate startup.It is based on
Vehicle can accurately be learned vehicle program arrival time and time of departure in the space-time trajectory diagram of intersection, and then performance period flows
The estimation of amount.
The present invention provides a kind of signalized intersections period flow estimation method based on track of vehicle data, including walks as follows
Suddenly：
1) the vehicle program arrival time based on real-time vehicle track data calculates with the time of departure, and step 1) specifically includes
Following steps：
11) as shown in Fig. 2, for queuing vehicle i t moment non-queuing tracing point information (ti,di), free stream velocity
vfAnd parking line position l, the calculation formula of vehicle i E.T.A are：
Wherein, aiFor vehicle i E.T.A, and vehicle i estimated times of departure biFor green light open it is bright after leave stop line
Moment.
12) non-its E.T.A of queuing vehicle i+1 is opened with it is expected that the time of departure is equal for vehicle i+1 green lights
The stop line moment is left after bright：
ai+2=bi+2；
2) basic time interval defines, and step 2) specifically comprises the steps of：
21) research period [0, T] is divided into continuous basic time interval
Wherein For the initial time at k-th of basic time interval,For the end at k-th of basic time interval
The only time.The bright moment is opened with each period traffic lights according to the E.T.A of all sampling vehicles in search time, is shared such as
The basic time interval of this three types is as shown in Figure 3.
Step 21) specifically includes following steps：
211) Class1：[r(ai),ai), from red light open the bright moment to first sampling vehicle of current period expect up to when
Between.Wherein r (ai) be current period red light open the bright moment.Correspondingly, the vehicle reached in the basic time interval can be
Corresponding effective green time [g (ai),bi) in sail out of intersection, wherein g (ai) be current period green light open the bright moment as scheme
Shown in 3a.
212) type 2：[ai-1,ai), continuous two samplings vehicle E.T.A interval in current period.It is corresponding
Effective green time be [bi-1,bi) as shown in Figure 3b.
213) type 3：[ai-1,g(ai-1)+G), last vehicle program arrival time of current period arrives current period
Green light finish time.Wherein, G is the green light duration of current period i-1.Its corresponding effective green time is [bi-1,g
(ai-1)+G) as shown in Figure 3c.
22) assume that intersection vehicles arrival meets nonhomogeneous Poisson distribution, then vehicle is average in each basic time interval
Arrival rate is represented by：
Wherein, λkFor the average traffic arrival rate at k-th of basic time interval, TkFor continuing for k-th basic time interval
Time is equal to
3) vehicle program arrival time likelihood function is estimated, step 3) specifically comprises the steps of：
Assuming that vehicle sample rate is p in the research period, then the average arrival rate for sampling vehicle is p λ (t).Based on nonhomogeneous
The characteristic of Poisson distribution, the joint probability density functions of all sampling vehicle E.T.A are in search time：
Wherein, n is the sampling vehicle number in search time section,
4) under the conditions of giving vehicle program arrival time, vehicle time of departure likelihood function is estimated, step 4) includes specifically
Following steps：
41) for k-th of basic time interval, non-sampled vehicle NkObedience mean value is (1-p) λkTkPoisson distribution.Together
When due to when saturation vehicle reaches away from limitation, the maximum vehicle number of arrival is in k-th of basic time intervalThen non-sampled vehicle NkProbability function be represented by：
Wherein,
According to three kinds in step 2 different types of basic time intervals, under the conditions of giving vehicle program arrival time, vehicle
There are three types of situations altogether for time of departure conditional probability.
Step 41) specifically comprises the following steps：
411) situation 1：For Class1 and type 2, if ai＜ bi, illustrate that it is queuing vehicle to sample vehicle i, then in correspondence
Basic time interval in, all non-sampled vehicles are queuing vehicle.Therefore, what is reached in the basic time interval is non-sampled
Vehicle number is：Wherein τkFor the effective green time at k-th of basic time interval.Then corresponding vehicle
Time of departure conditional probability is：
Wherein, hdTo sail out of saturation headway.
412) situation 2：For Class1 and type 2, if ai=bi, illustrate that it is non-queuing vehicle to sample vehicle i, then the
The non-sampled maximum vehicle number of arrival is in k basic time interval：Wherein τkIt is basic for k-th
The effective green time of time interval.Then corresponding vehicle time of departure conditional probability is：
413) situation 3：For type 3, illustrate that i-1 is last sampling vehicle in current period, then in k-th of base
The non-sampled maximum vehicle number of arrival is in this time interval：Wherein, τk=g (ai-1)+G-bi-1。
Then corresponding vehicle time of departure conditional probability is：
42) three kinds of situations being based in 41) step can be obtained in the case of given sampling vehicle E.T.A,
Vehicle time of departure likelihood function is：
Wherein, K1Indicate that basic time interval meets the set of situation 1, and K2Meet situation 2 and 3 for basic time interval
Set.Following likelihood function finally can be obtained：
5) vehicle arriving rate calculates in each basic time interval, specifically comprises the steps of：
Assuming that λ (ai)=λkWhenEqual to aiWhen, it can be obtained as follows about λkSingle order local derviation：
The embodiment of the present invention is as follows：
(1) data prediction
The present invention uses the northing mouth through vehicles track data convection current of intersection in Shenzhen major trunk roads Huang Ganglu and Fu
Amount estimation method carries out precision test, as shown in Figure 4.Verify the period be on 04 13rd, 2,017 7 points to 8:When 15 morning peaks
Section and 9:30 to the 12 points flat peak period includes six different timing schemes, corresponding track capturing rate and timing information altogether
As shown in table 1.Through track of vehicle data prediction, vehicle space-time trajectory diagram is obtained, as shown in figure 5, extracting vehicle program in turn
Arrival time and time of departure carry out period flow estimation, and using mean absolute error percentage (MAPE) to estimated result into
Row verification.
1 signal timing dial information of table and vehicle sample rate
(2) interpretation of result
Fig. 6 is the method for the present invention and Zheng et al. method 7 points to 8:15 morning peak periods and 9:30 to the 12 flat peaks of point
Period estimated result schematic diagram.
As shown in Figure 6 a, for the morning peak period, both of which can be good at the fluctuation of capture cycle flow, preferably
Realize flow estimation.Under period collection meter time interval, MAPE of the invention is 15.23%, and the MAPE of Zheng et al. is
16.17%.And with the increase at time collection meter interval, the MAPE of two methods declines, from 10-min, 30-min and hour
Collection meter time interval, PAPE of the invention is respectively 12.94%, 8.87%to8.85%, and the MAPE of Zheng et al. methods is
13.52%, 11.60%to 5.06%.
And in the flat peak period, the method that can be seen that the present invention from Fig. 6 c still is able to the change of fine step periodic stream amount
Change, and the estimated result of Zheng et al. methods is always greater than observed volume.In period, 10-min, 30-min and hour collection meter
Under time interval, MAPE of the invention is respectively 15.64%, 8.94%, 5.85%and 6.29%, and the methods of Zheng
MAPE is 20.12%, 19.63%, 19.11%and 18.94%.
The above results show that period flow estimation method proposed by the present invention is better than the estimation side of Zheng et al. propositions
Method.Also, the present invention needs not rely upon any historical data, has good robustness, has more extensive with scene.
Claims (7)
1. a kind of intersection flow estimation method based on real-time vehicle track data, which is characterized in that include the following steps：
1) research period [0, T] is divided into multiple continuous basic time intervals, and classified to basic time interval；
2) according to sorted basic time interval, under the conditions of given arrival time, according to different basic time intervals class
The corresponding vehicle time of departure conditional probability of type calculates vehicle time of departure likelihood function, and calculates final likelihood function；
3) vehicle arriving rate obtained in each basic time interval is solved to the likelihood function of vehicle time of departure.
2. a kind of intersection flow estimation method based on real-time vehicle track data according to claim 1, feature
It is, in the step 1), the type at basic time interval includes：
Type I：[r(ai),ai), the bright moment is opened to first sampling vehicle E.T.A of current period, in the base from red light
The vehicle reached in this time interval can be in corresponding effective green time τk=[g (ai),bi) in sail out of intersection, wherein r
(ai) it is that red light opens bright moment, aiFor the E.T.A of vehicle i, biFor the estimated time of departure of vehicle i, g (ai) it is current
The green light in period opens the bright moment；
Type II：[ai-1,ai), continuous two samplings vehicle E.T.A interval in current period is corresponding effectively green
Lamp time τkFor [bi-1,bi)；
Type-iii：[ai-1,g(ai-1)+G), the green light knot of last vehicle program arrival time of current period to current period
The beam moment, wherein G is the green light duration of current period, corresponding effective green time τkFor [bi-1,g(ai-1)+G)。
3. a kind of intersection flow estimation method based on real-time vehicle track data according to claim 2, feature
It is, the E.T.A a of the vehicle iiCalculation formula be：
For queuing vehicle：
Wherein, (ti,di) be vehicle i in the non-queuing tracing point information of t moment, vfFor free stream velocity, l is parking line position,
Vehicle i estimated times of departure biFor green light open it is bright after leave the stop line moment；
For non-queuing vehicle：
E.T.A with it is expected that the time of departure it is identical, for vehicle i green lights open it is bright after leave the stop line moment, i.e.,：
ai=bi。
4. a kind of intersection flow estimation method based on real-time vehicle track data according to claim 2, feature
It is, the step 2) specifically includes following steps：
21) arrival of setting intersection vehicles meets nonhomogeneous Poisson distribution；
22) the joint probability density function L of all sampling vehicle E.T.A in the research period is obtaineda, and as to
Fixed arrival time condition；
23) under the conditions of given arrival time, the corresponding vehicle time of departure condition of different basic time interval types is calculated
Probability；
24) likelihood of vehicle time of departure is calculated according to the corresponding vehicle time of departure conditional probability of different basic time interval types
Function Lb；
25) final likelihood function L is calculated.
5. a kind of intersection flow estimation method based on real-time vehicle track data according to claim 4, feature
It is, in the step 22), joint probability density function LaCalculating formula be：
Wherein, n is the sampling vehicle number in search time section, and p is vehicle sample rate in the research period, p λ (ai) it is sampling vehicle i
Average arrival rate, λ (ai) it is aiThe instantaneous arrival rate of vehicle at moment, Λ are to reach intensity, and λ (t) is the vehicle in t time intervals
Arrival rate, λkFor the vehicle arriving rate in k-th of basic time interval, TkFor the duration at k-th of basic time interval, K
For basic time interval sum.
6. a kind of intersection flow estimation method based on real-time vehicle track data according to claim 5, feature
It is, in the step 24), vehicle time of departure likelihood function LbCalculating formula be：
Vehicle time of departure likelihood function is：
Wherein, K1Indicate that the basic time interval of type I and Type II meets ai＜ biSet when situation, and K2For type I and
The basic time interval of Type II meets ai=biWhen and type-iii basic time spacing case when set, hsFor vehicle
Sail out of saturation headway, MkFor the maximum vehicle number reached in k-th of basic time interval,To be arrived in basic time interval
The non-sampled vehicle number reached, j are the vehicle reached in basic time interval.
7. a kind of intersection flow estimation method based on real-time vehicle track data according to claim 6, feature
It is, the calculating formula of the final likelihood function L is：
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2017109640399 | 2017-10-17 | ||
| CN201710964039 | 2017-10-17 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108399741A true CN108399741A (en) | 2018-08-14 |
| CN108399741B CN108399741B (en) | 2020-11-27 |
Family
ID=63094878
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810072445.9A Active CN108399741B (en) | 2017-10-17 | 2018-01-25 | Intersection flow estimation method based on real-time vehicle track data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108399741B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109243174A (en) * | 2018-09-05 | 2019-01-18 | 昆明理工大学 | A kind of mixing bicycle traffic wave calculation method based on spatial perception |
| CN109348423A (en) * | 2018-11-02 | 2019-02-15 | 同济大学 | A kind of arterial road coordinate control optimization method based on sample path data |
| CN109544915A (en) * | 2018-11-09 | 2019-03-29 | 同济大学 | A kind of queue length distribution estimation method based on sample path data |
| CN110288204A (en) * | 2019-06-04 | 2019-09-27 | 中国电建集团成都勘测设计研究院有限公司 | Concrete transportation construction efficiency measuring method |
| CN110782654A (en) * | 2019-02-22 | 2020-02-11 | 北京嘀嘀无限科技发展有限公司 | Traffic capacity estimation method and device for congestion area and data processing equipment |
| CN111183464A (en) * | 2019-06-13 | 2020-05-19 | 北京嘀嘀无限科技发展有限公司 | Estimating saturated flow at a signal intersection based on vehicle trajectory data |
| CN111739299A (en) * | 2020-07-20 | 2020-10-02 | 平安国际智慧城市科技股份有限公司 | Sparse-track vehicle queuing length determination method, device, equipment and medium |
| CN112201037A (en) * | 2020-09-27 | 2021-01-08 | 同济大学 | Intersection arrival rate estimation method based on sampling trajectory data |
| CN113506453A (en) * | 2021-09-10 | 2021-10-15 | 华砺智行(武汉)科技有限公司 | Bus priority signal control method, device, equipment and readable storage medium |
| CN114495490A (en) * | 2021-12-31 | 2022-05-13 | 联通智网科技股份有限公司 | Traffic condition prediction method, device terminal, and storage medium |
| CN115100875A (en) * | 2022-06-06 | 2022-09-23 | 东南大学 | Green wave traveling speed uncertainty quantification method based on internet vehicle track data |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104269055A (en) * | 2014-09-24 | 2015-01-07 | 四川省交通科学研究所 | Expressway traffic flow forecasting method based on time series |
| CN104282162A (en) * | 2014-09-29 | 2015-01-14 | 同济大学 | Adaptive intersection signal control method based on real-time vehicle track |
| CN104504897A (en) * | 2014-09-28 | 2015-04-08 | 北京工业大学 | Intersection traffic flow characteristic analysis and vehicle moving prediction method based on trajectory data |
| CN104637317A (en) * | 2015-01-23 | 2015-05-20 | 同济大学 | Intersection inductive signal control method based on real-time vehicle trajectory |
| CN105679025A (en) * | 2016-02-22 | 2016-06-15 | 北京航空航天大学 | Urban trunk road travel time estimation method based on variable weight mixed distribution |
| US20170186314A1 (en) * | 2015-12-28 | 2017-06-29 | Here Global B.V. | Method, apparatus and computer program product for traffic lane and signal control identification and traffic flow management |
| US9779621B1 (en) * | 2013-03-15 | 2017-10-03 | Waymo Llc | Intersection phase map |
-
2018
- 2018-01-25 CN CN201810072445.9A patent/CN108399741B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9779621B1 (en) * | 2013-03-15 | 2017-10-03 | Waymo Llc | Intersection phase map |
| CN104269055A (en) * | 2014-09-24 | 2015-01-07 | 四川省交通科学研究所 | Expressway traffic flow forecasting method based on time series |
| CN104504897A (en) * | 2014-09-28 | 2015-04-08 | 北京工业大学 | Intersection traffic flow characteristic analysis and vehicle moving prediction method based on trajectory data |
| CN104282162A (en) * | 2014-09-29 | 2015-01-14 | 同济大学 | Adaptive intersection signal control method based on real-time vehicle track |
| CN104637317A (en) * | 2015-01-23 | 2015-05-20 | 同济大学 | Intersection inductive signal control method based on real-time vehicle trajectory |
| US20170186314A1 (en) * | 2015-12-28 | 2017-06-29 | Here Global B.V. | Method, apparatus and computer program product for traffic lane and signal control identification and traffic flow management |
| CN105679025A (en) * | 2016-02-22 | 2016-06-15 | 北京航空航天大学 | Urban trunk road travel time estimation method based on variable weight mixed distribution |
Non-Patent Citations (3)
| Title |
|---|
| JIANFENG ZHENG ET AL.: "Estimating traffic volumes for signalized intersections using connected vehicle data", 《TRANSPORTATION RESEARCH PART C: EMERGING TECHNOLOGIES》 * |
| YANG CHENG ET AL.: "An exploratory Shockwave approach to estimating queue length using probe trajectories", 《JOURNAL OF INTELLIGENT TRANSPORTATION SYSTEMS》 * |
| 满玲玲等: "基于路段流量和交叉口转向交通量的动态微观OD矩阵估计研究", 《交通世界》 * |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109243174A (en) * | 2018-09-05 | 2019-01-18 | 昆明理工大学 | A kind of mixing bicycle traffic wave calculation method based on spatial perception |
| CN109243174B (en) * | 2018-09-05 | 2021-11-19 | 昆明理工大学 | Hybrid bicycle traffic wave calculation method based on spatial perception |
| CN109348423A (en) * | 2018-11-02 | 2019-02-15 | 同济大学 | A kind of arterial road coordinate control optimization method based on sample path data |
| CN109348423B (en) * | 2018-11-02 | 2020-04-07 | 同济大学 | Sampling trajectory data-based arterial road coordination control optimization method |
| CN109544915A (en) * | 2018-11-09 | 2019-03-29 | 同济大学 | A kind of queue length distribution estimation method based on sample path data |
| CN110782654A (en) * | 2019-02-22 | 2020-02-11 | 北京嘀嘀无限科技发展有限公司 | Traffic capacity estimation method and device for congestion area and data processing equipment |
| CN110288204A (en) * | 2019-06-04 | 2019-09-27 | 中国电建集团成都勘测设计研究院有限公司 | Concrete transportation construction efficiency measuring method |
| CN111183464A (en) * | 2019-06-13 | 2020-05-19 | 北京嘀嘀无限科技发展有限公司 | Estimating saturated flow at a signal intersection based on vehicle trajectory data |
| CN111739299B (en) * | 2020-07-20 | 2020-11-17 | 平安国际智慧城市科技股份有限公司 | Sparse-track vehicle queuing length determination method, device, equipment and medium |
| CN111739299A (en) * | 2020-07-20 | 2020-10-02 | 平安国际智慧城市科技股份有限公司 | Sparse-track vehicle queuing length determination method, device, equipment and medium |
| CN112201037A (en) * | 2020-09-27 | 2021-01-08 | 同济大学 | Intersection arrival rate estimation method based on sampling trajectory data |
| CN113506453A (en) * | 2021-09-10 | 2021-10-15 | 华砺智行(武汉)科技有限公司 | Bus priority signal control method, device, equipment and readable storage medium |
| CN113506453B (en) * | 2021-09-10 | 2022-02-22 | 华砺智行(武汉)科技有限公司 | Bus priority signal control method, device, equipment and readable storage medium |
| CN114495490A (en) * | 2021-12-31 | 2022-05-13 | 联通智网科技股份有限公司 | Traffic condition prediction method, device terminal, and storage medium |
| CN115100875A (en) * | 2022-06-06 | 2022-09-23 | 东南大学 | Green wave traveling speed uncertainty quantification method based on internet vehicle track data |
| CN115100875B (en) * | 2022-06-06 | 2023-05-16 | 东南大学 | Green wave traveling vehicle speed uncertainty quantification method based on internet-connected vehicle track data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108399741B (en) | 2020-11-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108399741A (en) | A kind of intersection flow estimation method based on real-time vehicle track data | |
| CN106355907B (en) | Signalized crossing queue length real-time estimation method based on track of vehicle | |
| CN109272756B (en) | Method for estimating queuing length of signal control intersection | |
| CN103996289B (en) | A kind of flow-speeds match model and Travel Time Estimation Method and system | |
| WO2018122803A1 (en) | Smart road traffic anomaly detection method | |
| CN111696348B (en) | Multifunctional intelligent signal control system and method | |
| Fang et al. | FTPG: A fine-grained traffic prediction method with graph attention network using big trace data | |
| CN108470461B (en) | Traffic signal controller control effect online evaluation method and system | |
| CN111739284B (en) | Traffic signal lamp intelligent timing method based on genetic algorithm optimization fuzzy control | |
| CN103295404B (en) | Road section pedestrian traffic signal control system based on pedestrian crossing clearance time | |
| CN103337161A (en) | Optimization method of intersection dynamic comprehensive evaluation and signal control system based on real-time simulation model | |
| CN106887141B (en) | Queuing theory-based continuous traffic node congestion degree prediction model, system and method | |
| Roshan et al. | Adaptive traffic control with TinyML | |
| CN107180270A (en) | Passenger flow forecasting and system | |
| CN106971535B (en) | A kind of urban traffic blocking index computing platform based on Floating Car GPS real time data | |
| CN110070734A (en) | Signalized intersections saturation headway estimation method based on gauss hybrid models | |
| CN108765985A (en) | The signalized intersections entrance driveway delay estimation method reached based on first car | |
| CN115601983A (en) | Method, device, equipment and storage medium for determining cycle duration of traffic signal lamp | |
| CN106846808B (en) | A kind of vehicle parking based on license plate data time number calculating method | |
| CN106846891B (en) | A kind of Public Parking berth multistep forecasting method decomposed based on sequence | |
| Zhao et al. | Traffic signal control with deep reinforcement learning | |
| CN109255948B (en) | Lane-dividing traffic flow proportion prediction method based on Kalman filtering | |
| CN109584564A (en) | A kind of letter prosecutor case being applicable in more equipment implements optimization method and its system and device | |
| CN115862315B (en) | Traffic light control method and device for smart city multi-source heterogeneous data stream | |
| Li et al. | Ddgnet: A dual-stage dynamic spatio-temporal graph network for pm 2.5 forecasting |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |