CN107909825A - A kind of Gaussian process returns saturation volume rate detection method - Google Patents
A kind of Gaussian process returns saturation volume rate detection method Download PDFInfo
- Publication number
- CN107909825A CN107909825A CN201711068208.7A CN201711068208A CN107909825A CN 107909825 A CN107909825 A CN 107909825A CN 201711068208 A CN201711068208 A CN 201711068208A CN 107909825 A CN107909825 A CN 107909825A
- Authority
- CN
- China
- Prior art keywords
- mrow
- data
- time data
- msub
- car
- 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
- G08G1/065—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)
- Traffic Control Systems (AREA)
Abstract
A kind of Gaussian process returns saturation volume rate detection method, comprises the following steps:1) original excessively car time data during interested period of some track of intersection at stop line is obtained;2) it is original to cross the pretreatment of car time data, obtained car time data;3) utilize timing scheme and cross car time data, calculate instantaneous delivery data and cross car time data in the cycle;4) Gaussian process homing method is utilized, car time data is crossed based on instantaneous flow rate data and in the cycle, is fitted instantaneous flow rate curve;5) maximum of instantaneous flow rate curve, the detected value as saturation volume rate are solved.Compared with prior art, the present invention fully excavates at intersection parking line and crosses in car moment big data the discrete traffic flow information included, and the saturation volume rate detected value of acquisition is more accurate.
Description
Technical field
The present invention relates to traffic control engineering, big data analysis application, machine learning application field, more particularly to saturated flow
Rate detection method and Gaussian process homing method.
Background technology
As Chinese national economy persistently increases rapidly, metropolitan central area expansion, the increase of transport need amount, traffic
Congestion problems are increasingly severe.It is the effective ways for alleviating traffic congestion using rational signal timing plan, and designs rationally
Signal timing plan be unable to do without the fundamental characteristics parameter of discrete traffic flow:Saturation volume rate.Saturation volume rate refers in green light, connects
Continuous maximum flow rate of the wagon flow by stop line.Most common saturation volume rate detection method is at present:It will break off a friendship between intersection
It is through-flow to regard continuum traffic flow as, flow rate is calculated by counting the traffic flow flow at 5 minutes (or longer interval), then with one day
In detected value of the maximum flow rate as saturation volume rate.The shortcomings that this method is the temporal properties for ignoring discrete traffic flow,
Cause the detection accuracy of saturation volume rate relatively low.It is general with the development of vehicle testing techniques, especially video-based vehicle detection
And it has been not technical bottleneck to obtain traffic flow big data.The traffic flow data of magnanimity, as crossed car data at stop line, is
The temporal properties of analysis discrete traffic flow provide possibility, are also provided certainly to obtain more accurate saturation volume rate detected value
May.
The content of the invention
The problem of in order to overcome the accuracy of existing track saturation volume rate detection method relatively low, the present invention is by fully excavating
Information in traffic flow big data, proposes that a kind of higher the utilizing of accuracy crosses car data calculating signalized intersections and satisfy at stop line
With the detection method of flow rate.
The technical solution adopted by the present invention to solve the technical problems is:
A kind of Gaussian process returns saturation volume rate detection method, and the detection method comprises the following steps:
1) original excessively car time data during interested period of some track of intersection at stop line is obtained,
At the time of i.e. each car is by the stop line;
2) it is original to cross the pretreatment of car time data, obtained car time data { pn, wherein, pnPass through parking for n-th car
At the time of line, n=1,2 ..., N, N are the data amount check in the data acquisition system, and process is as follows:
2.1) obvious abnormal data is rejected;
2.2) it is the second in one day by the original Time form transformation for crossing car time data;
2.3) car time data is subjected to descending sort, i.e. { pnIn data must meet pn< pn+1;
3) utilize timing scheme and cross car time data { pn, calculate instantaneous delivery data { fnAnd the cycle in cross car when
Carve data { ρn, process is as follows:
3.1) according to timing scheme and car time data { p excessivelynCar time data { ρ is crossed in calculating cyclen, i.e. vehicle
Which after green light starts passes through stop line, and each period index { c for crossing car time data secondn, i.e., same
The vehicle passed through in cycle is identified by identical label, and calculation formula is as follows:
ρn=mod (pn,C),
Wherein, mod () represents that modulus calculates, and int () represents that rounding calculates, and C is cycle length;
3.2) car time data { ρ is crossed according in the cyclenCalculate time headway data { hn, calculation formula is as follows:
hn=ρn-ρn-1;
3.3) according to period index { cnFind time headway data { hnIn first headstock passing through in each cycle
When away from and being modified to it, correction formula is as follows:
hfirst=ρfirst- green light start time;
3.4) according to time headway data { hnCalculate instantaneous flow rate data { fn, unit:/ hour, formula are as follows:
4) Gaussian process homing method is utilized, based on instantaneous flow rate data { fnAnd the cycle in cross car time data { ρn,
Instantaneous flow rate curve is fitted, process is as follows:
4.1) by maximizing logarithm marginal likelihood function, the hyper parameter for selecting optimal Gaussian process to return to:Scale is joined
Number l, signal varianceAnd noise varianceThe optimization problem is described as follows:
Wherein,It is by instantaneous flow rate data { fnComposition column vector,It is
By crossing car time data { ρ in the cyclenThe variance matrix that is calculated, expression formula is as follows
k(ρ1,ρ2) it is variance function, expression formula is as follows:
I is unit matrix, | | the determinant of representing matrix;
4.2) hyper parameter is returned to using optimal Gaussian process, obtains the instantaneous flow rate curve after green light is let passTable
It is as follows up to formula:
Wherein, any time after ρ lets pass for green light, κ (ρ)=[k (ρ, ρ1),k(ρ,ρ2),…,k(ρ,ρN)];
5) instantaneous flow rate curve is solvedMaximum, as the detected value of saturation volume rate, i.e. saturation volume rate is
The present invention technical concept be:Regard the discrete traffic flow rate of signalized intersections as a Gaussian random process;Base
In actual measurement big data, i.e., car time data is crossed at stop line, Gaussian random process is obtained by Gaussian process regression fit
Mean function is as instantaneous traffic flow rate curve;According to the definition of saturation volume rate, the maximum of instantaneous traffic flow rate curve is made
For the detected value of saturation volume rate.
Beneficial effects of the present invention are:The information included in traffic flow big data is fully excavated, is obtained than existing method more
The detected value of accurate saturation volume rate.
Brief description of the drawings
Fig. 1 shows that Gaussian process returns the instantaneous flow rate data that saturation volume rate detection method is produced in calculating process again
{fn, instantaneous flow rate curveWith the detected value of saturation volume rate.
Embodiment
The invention will be further described below in conjunction with the accompanying drawings.
With reference to Fig. 1, a kind of Gaussian process returns saturation volume rate detection method, comprises the following steps:
1) original excessively car time data during interested period of some track of intersection at stop line is obtained,
At the time of i.e. each car is by the stop line;
2) it is original to cross the pretreatment of car time data, obtained car time data { pn, wherein, pnPass through parking for n-th car
At the time of line, n=1,2 ..., N, N are the data amount check in the data acquisition system, and process is as follows:
2.1) obvious abnormal data is rejected, the data being collected into during red light are such as proposed according to timing scheme;
2.2) it is the second in one day by the original Time form transformation for crossing car time data, such as:13:00:00 is converted to
Second in one day is 13*3600=46800 seconds;
2.3) car time data is subjected to descending sort, i.e. { pnIn data must meet pn< pn+1;
3) utilize timing scheme and cross car time data { pn, calculate instantaneous delivery data { fnAnd the cycle in cross car when
Carve data { ρn, process is as follows:
3.1) according to timing scheme and car time data { p excessivelynCar time data { ρ is crossed in calculating cyclen, i.e. vehicle
Which after green light starts passes through stop line, and each period index { c for crossing car time data secondn, i.e., same
The vehicle passed through in cycle is identified by identical label, and calculation formula is as follows:
ρn=mod (pn,C),
Wherein, mod () represents that modulus calculates, and int () represents that rounding calculates, and C is cycle length;
3.2) car time data { ρ is crossed according in the cyclenCalculate time headway data { hn, calculation formula is as follows:
hn=ρn-ρn-1;
3.3) according to period index { cnFind time headway data { hnIn pass through in each cycle first headstock when
Away from, and it is modified, correction formula is as follows:
hfirst=ρfirst- green light start time;
3.4) according to time headway data { hnCalculate instantaneous flow rate data { fn, unit:/ hour, formula are as follows:
4) Gaussian process homing method is utilized, based on instantaneous flow rate data { fnAnd the cycle in cross car time data { ρn,
Instantaneous flow rate curve is fitted, process is as follows:
4.1) by maximizing logarithm marginal likelihood function, the hyper parameter for selecting optimal Gaussian process to return to:Scale is joined
Number l, signal varianceAnd noise varianceThe optimization problem is described as follows:
Wherein,It is by instantaneous flow rate data { fnComposition column vector,It is
By crossing car time data { ρ in the cyclenThe variance matrix that is calculated, expression formula is as follows:
k(ρ1,ρ2) it is variance function, expression formula is as follows:
I is unit matrix, | | the determinant of representing matrix;
4.2) hyper parameter is returned to using optimal Gaussian process, obtains the instantaneous flow rate curve after green light is let passTable
It is as follows up to formula:
Wherein, any time after ρ lets pass for green light, κ (ρ)=[k (ρ, ρ1),k(ρ,ρ2),…,k(ρ,ρN)];
5) instantaneous flow rate curve is solvedMaximum, as the detected value of saturation volume rate, i.e. saturation volume rate is
The present embodiment with the actual measurement of the north orientation south Through Lane of Quzhou City of Zhejiang Province Qu Hua roads-butterfly road intersection car number
Saturation volume rate detection method is returned, is comprised the following steps according to for embodiment, a kind of Gaussian process:
1) obtain Quzhou City of Zhejiang Province Qu Hua roads-butterfly road intersection north orientation south Through Lane at stop line
On 2 9th, 2016 10:00:00 to 13:00:Original car time data, i.e. each car excessively in 00 period pass through the stop line
At the time of;
2) it is original to cross the pretreatment of car time data, obtained car time data { pn, wherein, pnPass through parking for n-th car
At the time of line, n=1,2 ..., N, N are the data amount check in the data acquisition system, and process is as follows:
2.1) obvious abnormal data is rejected, the data being collected into during red light are such as proposed according to timing scheme;
2.2) it is the second in one day by the original Time form transformation for crossing car time data, such as:13:00:00 is converted to
Second in one day is 13*3600=46800 seconds;
2.3) car time data is subjected to descending sort, i.e. { pnIn data must meet pn< pn+1;
3) utilize timing scheme and cross car time data { pn, calculate instantaneous delivery data { fnAnd the cycle in cross car when
Carve data { ρn, process is as follows:
3.1) according to timing scheme and car time data { p excessivelynCar time data { ρ is crossed in calculating cyclen, i.e. vehicle
Which after green light starts passes through stop line, and each period index { c for crossing car time data secondn, i.e., same
The vehicle passed through in cycle is identified by identical label, and calculation formula is as follows:
ρn=mod (pn,C),
Wherein, mod () represents that modulus calculates, and int () represents that rounding calculates, and C is cycle length;
3.2) car time data { ρ is crossed according in the cyclenCalculate time headway data { hn, calculation formula is as follows:
hn=ρn-ρn-1;
3.3) according to period index { cnFind time headway data { hnIn pass through in each cycle first headstock when
Away from, and it is modified, correction formula is as follows:
hfirst=ρfirst- green light start time;
3.4) according to time headway data { hnCalculate instantaneous flow rate data { fn, unit:/ hour, formula are as follows:
4) Gaussian process homing method is utilized, based on instantaneous flow rate data { fnAnd the cycle in cross car time data { ρn,
Instantaneous flow rate curve is fitted, process is as follows:
4.1) by maximizing logarithm marginal likelihood function, the hyper parameter for selecting optimal Gaussian process to return to:Scale is joined
Number l, signal varianceAnd noise varianceThe optimization problem is described as follows:
Wherein,It is by instantaneous flow rate data { fnComposition column vector,It is
By crossing car time data { ρ in the cyclenThe variance matrix that is calculated, expression formula is as follows:
k(ρ1,ρ2) it is variance function, expression formula is as follows:
I is unit matrix, | | the determinant of representing matrix;
4.2) hyper parameter is returned to using optimal Gaussian process, obtains the instantaneous flow rate curve after green light is let passTable
It is as follows up to formula:
Wherein, any time after ρ lets pass for green light, κ (ρ)=[k (ρ, ρ1),k(ρ,ρ2),…,k(ρ,ρN)];
5) instantaneous flow rate curve is solvedMaximum, as the detected value of saturation volume rate, i.e. saturation volume rate is:
Using the actual measurement of the north orientation south Through Lane of Quzhou City of Zhejiang Province Qu Hua roads-butterfly road intersection car data as implement
Example, has obtained the saturation volume rate in track as 1570 per hour, as shown in Figure 1 with above method.
Described above is the excellent results that one embodiment that the present invention provides shows, it is clear that the present invention not only fits
Above-described embodiment is closed, can on the premise of without departing from essence spirit of the present invention and without departing from content involved by substantive content of the present invention
Many variations are done to it to be carried out.
Claims (1)
1. a kind of Gaussian process returns saturation volume rate detection method, it is characterised in that:The detection method comprises the following steps:
1) obtain original excessively car time data during interested period of some track of intersection at stop line, i.e., it is every
At the time of car is by the stop line;
2) it is original to cross the pretreatment of car time data, obtained car time data { pn, wherein, pnPass through stop line for n-th car
Moment, n=1,2 ..., N, N are the data amount check in the data acquisition system, and process is as follows:
2.1) obvious abnormal data is rejected;
2.2) it is the second in one day by the original Time form transformation for crossing car time data;
2.3) car time data is subjected to descending sort, i.e. { pnIn data must meet pn< pn+1;
3) utilize timing scheme and cross car time data { pn, calculate instantaneous delivery data { fnAnd the cycle in cross car moment number
According to { ρn, process is as follows:
3.1) according to timing scheme and car time data { p excessivelynCar time data { ρ is crossed in calculating cyclen, i.e., vehicle is green
Which after lamp starts passes through stop line, and each period index { c for crossing car time data secondn, i.e., in the same cycle
The interior vehicle passed through is identified by identical label, and calculation formula is as follows:
ρn=mod (pn,C),
<mrow>
<msub>
<mi>c</mi>
<mi>n</mi>
</msub>
<mo>=</mo>
<mi>int</mi>
<mrow>
<mo>(</mo>
<mfrac>
<msub>
<mi>p</mi>
<mi>n</mi>
</msub>
<mi>C</mi>
</mfrac>
<mo>)</mo>
</mrow>
<mo>+</mo>
<mn>1</mn>
<mo>,</mo>
</mrow>
Wherein, mod () represents that modulus calculates, and int () represents that rounding calculates, and C is cycle length;
3.2) car time data { ρ is crossed according in the cyclenCalculate time headway data { hn, calculation formula is as follows:
hn=ρn-ρn-1;
3.3) according to period index { cnFind time headway data { hnIn first time headway passing through in each cycle,
And it is modified, correction formula is as follows:
hfirst=ρfirst- green light start time;
3.4) according to time headway data { hnCalculate instantaneous flow rate data { fn, unit:/ hour, formula are as follows:
<mrow>
<msub>
<mi>f</mi>
<mi>n</mi>
</msub>
<mo>=</mo>
<mfrac>
<mn>3600</mn>
<msub>
<mi>h</mi>
<mi>n</mi>
</msub>
</mfrac>
<mo>;</mo>
</mrow>
4) Gaussian process homing method is utilized, based on instantaneous flow rate data { fnAnd the cycle in cross car time data { ρn, fitting
Instantaneous flow rate curve, process are as follows:
4.1) by maximizing logarithm marginal likelihood function, the hyper parameter for selecting optimal Gaussian process to return to:Scale parameter l,
Signal varianceAnd noise varianceThe optimization problem is described as follows:
<mrow>
<munder>
<mrow>
<mi>m</mi>
<mi>a</mi>
<mi>x</mi>
</mrow>
<mrow>
<mi>l</mi>
<mo>,</mo>
<msubsup>
<mi>&sigma;</mi>
<mi>f</mi>
<mn>2</mn>
</msubsup>
<mo>,</mo>
<msubsup>
<mi>&sigma;</mi>
<mi>n</mi>
<mn>2</mn>
</msubsup>
</mrow>
</munder>
<mrow>
<mo>(</mo>
<mo>-</mo>
<mfrac>
<mn>1</mn>
<mn>2</mn>
</mfrac>
<msup>
<mi>f</mi>
<mi>T</mi>
</msup>
<msup>
<mrow>
<mo>(</mo>
<mrow>
<mi>K</mi>
<mo>+</mo>
<msubsup>
<mi>&sigma;</mi>
<mi>n</mi>
<mn>2</mn>
</msubsup>
<mi>I</mi>
</mrow>
<mo>)</mo>
</mrow>
<mrow>
<mo>-</mo>
<mn>1</mn>
</mrow>
</msup>
<mi>f</mi>
<mo>-</mo>
<mfrac>
<mn>1</mn>
<mn>2</mn>
</mfrac>
<mi>l</mi>
<mi>o</mi>
<mi>g</mi>
<mo>|</mo>
<mi>K</mi>
<mo>+</mo>
<msubsup>
<mi>&sigma;</mi>
<mi>n</mi>
<mn>2</mn>
</msubsup>
<mi>I</mi>
<mo>|</mo>
<mo>-</mo>
<mfrac>
<mi>N</mi>
<mn>2</mn>
</mfrac>
<mi>l</mi>
<mi>o</mi>
<mi>g</mi>
<mn>2</mn>
<mi>&pi;</mi>
<mo>)</mo>
</mrow>
<mo>,</mo>
</mrow>
Wherein,It is by instantaneous flow rate data { fnComposition column vector,It is by week
Car time data { ρ is crossed in phasenThe variance matrix that is calculated, expression formula is as follows:
k(ρ1,ρ2) it is variance function, expression formula is as follows:
<mrow>
<mi>k</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>&rho;</mi>
<mn>1</mn>
</msub>
<mo>,</mo>
<msub>
<mi>&rho;</mi>
<mn>2</mn>
</msub>
<mo>)</mo>
</mrow>
<mo>=</mo>
<msubsup>
<mi>&sigma;</mi>
<mi>f</mi>
<mn>2</mn>
</msubsup>
<mi>exp</mi>
<mrow>
<mo>(</mo>
<mo>-</mo>
<mfrac>
<msup>
<mrow>
<mo>(</mo>
<msub>
<mi>&rho;</mi>
<mn>1</mn>
</msub>
<mo>-</mo>
<msub>
<mi>&rho;</mi>
<mn>2</mn>
</msub>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mrow>
<mn>2</mn>
<msup>
<mi>l</mi>
<mn>2</mn>
</msup>
</mrow>
</mfrac>
<mo>)</mo>
</mrow>
<mo>,</mo>
</mrow>
I is unit matrix, | | the determinant of representing matrix;
4.2) hyper parameter is returned to using optimal Gaussian process, obtains the instantaneous flow rate curve after green light is let passExpression formula
It is as follows:
<mrow>
<mover>
<mi>f</mi>
<mo>^</mo>
</mover>
<mrow>
<mo>(</mo>
<mi>&rho;</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mi>&kappa;</mi>
<mrow>
<mo>(</mo>
<mi>&rho;</mi>
<mo>)</mo>
</mrow>
<mo>&CenterDot;</mo>
<mi>K</mi>
<mo>&CenterDot;</mo>
<mi>f</mi>
</mrow>
Wherein, any time after ρ lets pass for green light, κ (ρ)=[k (ρ, ρ1),k(ρ,ρ2),…,k(ρ,ρN)];
5) instantaneous flow rate curve is solvedMaximum, as the detected value of saturation volume rate, i.e. saturation volume rate is:
<mrow>
<munder>
<mrow>
<mi>m</mi>
<mi>a</mi>
<mi>x</mi>
</mrow>
<mi>&rho;</mi>
</munder>
<mover>
<mi>f</mi>
<mo>^</mo>
</mover>
<mrow>
<mo>(</mo>
<mi>&rho;</mi>
<mo>)</mo>
</mrow>
<mo>.</mo>
</mrow>
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711068208.7A CN107909825B (en) | 2017-11-03 | 2017-11-03 | Method for detecting regression saturation flow rate in Gaussian process |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711068208.7A CN107909825B (en) | 2017-11-03 | 2017-11-03 | Method for detecting regression saturation flow rate in Gaussian process |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107909825A true CN107909825A (en) | 2018-04-13 |
CN107909825B CN107909825B (en) | 2020-08-25 |
Family
ID=61843358
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711068208.7A Active CN107909825B (en) | 2017-11-03 | 2017-11-03 | Method for detecting regression saturation flow rate in Gaussian process |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107909825B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109389826A (en) * | 2018-12-14 | 2019-02-26 | 武汉理工大学 | A kind of real-time computing technique of signalized intersections saturation volume rate |
CN109712393A (en) * | 2019-01-10 | 2019-05-03 | 浙江工业大学 | Intelligent transportation Time segments division method based on Gaussian process regression algorithm |
CN110070734A (en) * | 2019-05-14 | 2019-07-30 | 东南大学 | Signalized intersections saturation headway estimation method based on gauss hybrid models |
CN113643531A (en) * | 2021-07-20 | 2021-11-12 | 东北大学 | Intersection lane saturation flow rate calculation method based on small time zone division statistics |
CN114882696A (en) * | 2020-10-28 | 2022-08-09 | 华为技术有限公司 | Method and device for determining road capacity and storage medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH07252035A (en) * | 1994-02-08 | 1995-10-03 | Lg Ind Syst Co Ltd | Group management control method for elevator |
CN101339698A (en) * | 2008-08-12 | 2009-01-07 | 北京工业大学 | Correction method of bicycle influencing turning vehicle saturation flow rate at signal crossing |
CN102855755A (en) * | 2012-09-06 | 2013-01-02 | 哈尔滨工业大学 | Method for establishing urban trunk platoon dispersion model based on running speed forecasting |
KR101333498B1 (en) * | 2012-08-24 | 2013-11-28 | 서울시립대학교 산학협력단 | Traffic signal control algorithm on isolated intersection based on tarvel time |
CN104575034A (en) * | 2015-01-19 | 2015-04-29 | 浙江大学 | Single-point intersection signal timing parameter optimization method based on bayonet data |
CN105788301A (en) * | 2016-03-22 | 2016-07-20 | 上海理工大学 | Special lane left-turn intersection pre-stop line and pre-signal setting method |
CN106846804A (en) * | 2017-03-03 | 2017-06-13 | 浙江大学 | The real-time saturation volume rate method of estimation in intersection based on hidden Markov chain |
-
2017
- 2017-11-03 CN CN201711068208.7A patent/CN107909825B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH07252035A (en) * | 1994-02-08 | 1995-10-03 | Lg Ind Syst Co Ltd | Group management control method for elevator |
CN101339698A (en) * | 2008-08-12 | 2009-01-07 | 北京工业大学 | Correction method of bicycle influencing turning vehicle saturation flow rate at signal crossing |
KR101333498B1 (en) * | 2012-08-24 | 2013-11-28 | 서울시립대학교 산학협력단 | Traffic signal control algorithm on isolated intersection based on tarvel time |
CN102855755A (en) * | 2012-09-06 | 2013-01-02 | 哈尔滨工业大学 | Method for establishing urban trunk platoon dispersion model based on running speed forecasting |
CN104575034A (en) * | 2015-01-19 | 2015-04-29 | 浙江大学 | Single-point intersection signal timing parameter optimization method based on bayonet data |
CN105788301A (en) * | 2016-03-22 | 2016-07-20 | 上海理工大学 | Special lane left-turn intersection pre-stop line and pre-signal setting method |
CN106846804A (en) * | 2017-03-03 | 2017-06-13 | 浙江大学 | The real-time saturation volume rate method of estimation in intersection based on hidden Markov chain |
Non-Patent Citations (3)
Title |
---|
刘意 等: "信号交叉口直行车道饱和流率研究", 《交通运输工程与信息学报》 * |
康军: "高斯过程回归短时交通流预测方法", 《交通运输***工程与信息》 * |
王殿海 等: "累计曲线法计算饱和流率和相位损失时间", 《交通运输工程学报》 * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109389826A (en) * | 2018-12-14 | 2019-02-26 | 武汉理工大学 | A kind of real-time computing technique of signalized intersections saturation volume rate |
CN109389826B (en) * | 2018-12-14 | 2021-03-16 | 武汉理工大学 | Real-time calculation method for saturation flow rate of signalized intersection |
CN109712393A (en) * | 2019-01-10 | 2019-05-03 | 浙江工业大学 | Intelligent transportation Time segments division method based on Gaussian process regression algorithm |
CN110070734A (en) * | 2019-05-14 | 2019-07-30 | 东南大学 | Signalized intersections saturation headway estimation method based on gauss hybrid models |
CN110070734B (en) * | 2019-05-14 | 2022-01-28 | 东南大学 | Signalized intersection saturated headway estimation method based on Gaussian mixture model |
CN114882696A (en) * | 2020-10-28 | 2022-08-09 | 华为技术有限公司 | Method and device for determining road capacity and storage medium |
CN114882696B (en) * | 2020-10-28 | 2023-11-03 | 华为技术有限公司 | Road capacity determination method, device and storage medium |
CN113643531A (en) * | 2021-07-20 | 2021-11-12 | 东北大学 | Intersection lane saturation flow rate calculation method based on small time zone division statistics |
Also Published As
Publication number | Publication date |
---|---|
CN107909825B (en) | 2020-08-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107909825A (en) | A kind of Gaussian process returns saturation volume rate detection method | |
CN102254443B (en) | Intermittent bus lane control system | |
CN102157064B (en) | Method for designing signal intersection of bus lanes | |
CN101510355B (en) | Method for determining traffic lane length of crossing inlet road for forbidding lane exchange | |
CN104134349A (en) | Bus road condition processing system and method based on traffic multi-source data fusion | |
CN104318788A (en) | Method for improving space resource utilization efficiency of intersection entrance lane | |
CN103903433A (en) | Real-time dynamic judgment method and device for road traffic state | |
CN103606269A (en) | Control method for improving traffic efficiency of freeway construction area | |
CN104318789A (en) | Method for improving green light time availability of each phase of signalized intersection entrance lane | |
CN105679024A (en) | Road intersection queuing length calculation method | |
CN105279981A (en) | Tidal lane driving direction dynamic control method | |
CN103116992B (en) | Four-road annular intersection design method based on single entrance release | |
CN105405301A (en) | Right-turn signal induction control method for eliminating straight-right-turn convergence conflict | |
CN105809993A (en) | Method for calculating intersection signal lamp timing based on vehicle stop line passing time | |
CN106803347A (en) | Urban intersection traffic state judging method based on RFID data | |
CN107578620A (en) | Computational methods, system and the device of road passage capability based on track level system | |
CN104778839A (en) | Urban road downstream directional traffic state judgment method based on video detector | |
CN105448093B (en) | A kind of intersection V/C is than acquisition methods and system | |
CN106683406A (en) | Bus lane passage bottleneck detection method based on bus-mounted GPS (global positioning system) data | |
CN102956109A (en) | Method for judging requirement for arranging external left turn lane at entrance lane of signal intersection | |
CN106023602A (en) | Mountainous city signal intersection delay calculation method | |
Li et al. | An algorithm for e-bike equivalents at signalized intersections based on traffic conflict events number | |
Abdel-Aty et al. | Application of variable speed limits and ramp metering to improve safety and efficiency of freeways | |
Dong et al. | Multiobjective evaluation of left-turn waiting areas at signalized intersections in China | |
CN105513355B (en) | A kind of crossing key V/C than acquisition methods and system |
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 | ||
CB02 | Change of applicant information |
Address after: Hangzhou City, Zhejiang province 310004 City Road No. 576 building 6 Fei Jia Tang Applicant after: AEROSPACE SCIENCE AND TECHNOLOGY GUANGXIN INTELLIGENT TECHNOLOGY Co.,Ltd. Address before: Hangzhou City, Zhejiang province 310004 City Road No. 576 building 6 Fei Jia Tang Applicant before: ZHEJIANG GUANGXIN INTELLIGENT BUILDING ACADEMY Co.,Ltd. |
|
CB02 | Change of applicant information | ||
GR01 | Patent grant | ||
GR01 | Patent grant |