CN107564276A - A kind of traffic incidents detection method based on traffic behavior mutation - Google Patents
A kind of traffic incidents detection method based on traffic behavior mutation Download PDFInfo
- Publication number
- CN107564276A CN107564276A CN201710545628.3A CN201710545628A CN107564276A CN 107564276 A CN107564276 A CN 107564276A CN 201710545628 A CN201710545628 A CN 201710545628A CN 107564276 A CN107564276 A CN 107564276A
- Authority
- CN
- China
- Prior art keywords
- traffic
- mrow
- variation
- average
- sample sequence
- 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
Abstract
The invention discloses a kind of traffic incidents detection method based on traffic behavior mutation, comprise the following steps：Road section selected and the bicycle essential information of period are extracted under S1 car networking environment；S2 is counted the average speed of road section selected, average space headway, the speed coefficient of variation and space headway by measurement period from the coefficient of variation；The grand micro-parameter of S3 fusion traffic flows carries out traffic behavior fuzzy discrimination；S4 establishes mean change-point model, using the difference of the measured value of traffic behavior and predicted value as sample sequence, searches for height with least variance method, detects traffic events.The present invention makes full use of the basic parameter of bicycle in traffic flow, consider speed deviation and space headway discreteness from microcosmic angle, their changing rule when studying traffic flow change, fusion both macro and micro parameter differentiates to traffic behavior, the mutation for the traffic behavior being finally based on after grand micro-parameter fusion carries out automatic traffic event detection, and the traffic incidents detection technology that car networking environment is adapted to for research provides new approaches.
Description
Technical field
The invention belongs to automatic traffic event detection field, and in particular to a kind of be mutated using traffic behavior carries out traffic thing
The method of part detection.
Background technology
Traffic events frequently result in road the traffic capacity drastically decline or transport need extremely raise, it is to cause traffic
One of an important factor for congestion, and have important influence to traffic safety, trip planning and environmental pollution etc..Therefore, accurately
Timely automatic traffic event detection algorithm is one of key technology in incident management system.
With the continuous development of car networking environmental construction and perfect, vehicle supervision department can obtain in real time under new environment
More, more accurately information of vehicles (such as speed, position, track, acceleration) is taken, makes full use of these information to enrich pair
The description of road traffic condition.And traditional traffic incidents detection method is divided into based on fixed car test according to the source difference of data
The traffic incidents detection method of device, the traffic incidents detection method based on mobile vehicle checker and the traffic events based on data fusion
Detection method.The essence of traffic event automatic detection method based on fixed vehicle checker is the change by place traffic flow parameter
To judge the generation of traffic events, the Detection results of this method depend on the traffic flow data of fixed vehicle checker collection quality and
The selection of traffic flow character parameter.Research now both at home and abroad to the traffic incidents detection method based on fixed vehicle checker is completeer
It is kind, compare following four major class of detection method for having representative：The method of pattern-recognition, the method for statistical analysis, based on traffic flow mould
The method of type and the method for artificial intelligence.Mobile vehicle checker is different with fixed vehicle checker, its collection be not flow, occupation rate and
These preset parameters of average speed, but these runtime parameters such as journey time and the travel speed in section can be obtained.It is based on
The traffic incidents detection method of data fusion is then to make full use of fixed car detector and the parameter of mobile vehicle checker collection to carry out
Event detection.
These traditional automatic traffic event detection algorithms are mainly to obtain the average speed, close in section by vehicle checker
The Macro-traffic Flow such as degree, flow parameter carries out traffic incidents detection.These traditional Macro-traffic Flow parameters can only be macroscopical, average
Reflection traffic flow operation conditions, and on microcosmic, the discreteness of traffic flow parameter is objective reality, and it is often handed over by macroscopic view
The average of through-flow parameter is masked, so as to have ignored influence of the otherness of individual vehicle to traffic flow stability.Therefore, only
Only carrying out automatic traffic event detection by Macro-traffic Flow parameter can cause that verification and measurement ratio is relatively low, rate of false alarm is higher.In car networking
Under environment, abundant information of vehicles how is made full use of, the discreteness of microscopic traffic flow parameter is considered, merges grand microscopic traffic flow
Parameter, study a kind of rationally effective Algorithm for Traffic Incidents Detection becomes urgent need to improve the performance of automatic traffic event detection
Solve the problems, such as.
The content of the invention
In view of this, it is an object of the invention to provide it is a kind of based on traffic behavior mutation traffic incidents detection method,
So as to improve the performance of traffic incidents detection.
To reach above-mentioned purpose, the present invention provides following technical scheme, a kind of traffic events based on traffic behavior mutation
Detection method, comprise the following steps：
Road section selected and the bicycle essential information of period are extracted under S1 car networking environment；
S2 is by the average speed of measurement period statistics road section selected, averagely between space headway, the speed coefficient of variation and headstock
Apart from the coefficient of variation；
The grand micro-parameter of S3 fusion traffic flows carries out traffic behavior fuzzy discrimination；
S4 establishes mean change-point model, using the difference of the measured value of traffic behavior and predicted value as sample sequence, with minimum
Variance method searches for height, detects traffic events.
Further, the step S3 includes following sub-step：
S31 establishes fuzzy evaluation set of factors U；
S32 establishes fuzzy evaluation collection V；
S33 establishes single factor test fuzzy evaluation, that is, establishes a FUZZY MAPPING from U to V；
S34 Comprehensive Evaluations, suitable Fuzzy Arithmetic Operators are selected to carry out Comprehensive Evaluation.
Further, according to four average speed, average space headway, the speed coefficient of variation and the space headway coefficient of variation friendships
The time series that the time series progress fuzzy comprehensive evoluation of through-flow characteristic parameter obtains traffic behavior measured value is { Xi| i=1,
2 ..., n }, according to four average speed, average space headway, the speed coefficient of variation and the space headway coefficient of variation traffic flow spies
The time series of sign parameter carries out the time series of traffic status prediction value that fuzzy comprehensive evoluation obtainsThen sample sequenceN represents total sample number；
Define sample sequence population variance S be：In formula,For the average of sample sequence；
Sample sequence is divided into two sections, the population variance of sample sequence is after division
In formula,The average of two sections of sample sequence before and after the sample respectively divided, then
If E (S)=E (Sk), then without generation traffic events；E if (S) ＞ E (Sk), then there occurs traffic events, wherein, E
(S), E (Sk) population variance S and S are represented respectivelykExpectation, k represent sample decomposition point.
Further, make
S*=min (Sk), k=2,3 ..., n-1
According to the principle of cluster, S*At the time of being that traffic events occur at the time of corresponding, work as S-S*＞ R, that is, think traffic
Event occurs, and wherein R is given threshold.
Further, for given threshold R, the level of signifiance as requested determines that statistical theory has
Wherein, P () represents probability, and u represents that sample it is expected
In formula, σ2For the variance of sample sequence, α is given significance, is thus obtained
Then
R=σ2(2lg(lgn)+lg(lg(lgn))-lgπ+uα), wherein uαRepresent the standard normal under level of significance α
Distribution Value.
The beneficial effects of the present invention are：
The present invention makes full use of the basic parameter of bicycle in traffic flow, considers from microcosmic angle between speed deviation and headstock
Away from discreteness, their changing rule when research traffic flow changes, fusion both macro and micro parameter differentiates to traffic behavior,
The mutation for the traffic behavior being finally based on after grand micro-parameter fusion carries out automatic traffic event detection, and car networking is adapted to for research
The traffic incidents detection technology of environment provides new approaches.
Brief description of the drawings
In order that the purpose of the present invention, technical scheme and beneficial effect are clearer, the present invention provides drawings described below and carried out
Explanation：
Fig. 1 is the flow chart of the inventive method.
Embodiment
Below in conjunction with accompanying drawing, the preferred embodiments of the present invention are described in detail.
The generation of traffic events can cause interruption and the interval of traffic flow, have impact on the Travel vehicle of traffic events upstream vehicle
Speed and space headway, while the speed coefficient of variation and the space headway coefficient of variation have difference in traffic events upstream and downstream in traffic flow
Situation of change.In a word, the generation of traffic events can produce tremendous influence to traffic flow, traffic flow character parameter occur different
Normal change.And traffic behavior is then differentiated by traffic flow character parameter, it is whole road grid traffic operation conditions
Comprehensive embodiment.Therefore, if only only from traffic flow macroparameter, and the otherness pair of traffic flow micro-parameter is ignored
The influence of traffic flow, then can cause that the verification and measurement ratio of traffic incidents detection is relatively low, rate of false alarm is higher.
Therefore, based on the grand micro-parameter of traffic flow under car networking environment, the discrete feature of micro-parameter is taken into full account, is ground
Study carefully multi-parameter traffic behavior comprehensive distinguishing model, and then based on catastrophe theory, feature is used as using traffic state judging result
Parameter, mean change-point model is established, using the difference of the measured value of traffic behavior and predicted value as sample sequence, with least variance method
Height is searched for, devises the traffic incidents detection method based on traffic behavior mutation.Specifically include following steps：
S1：Road section selected and the bicycle essential information of period are extracted under car networking environment；
S2：Calculate the coefficient of variation and the following distance coefficient of variation of section car speed；
Velocity mutation coefficient：
In formulaRepresent instantaneous velocity of l upper i-th car in section in t；nl(t) car of t on the l of section is represented
Quantity；Represent the speed average of all vehicles of t on the l of section；VSDl(t) all vehicles of t on the l of section are represented
Velocity standard it is poor；VCVl(t) the speed coefficient of variation of t on the l of section is represented.
Following distance variation lines：
In formulaRepresent space headway of l upper i-th car in section in t；nl(t) car of t on the l of section is represented
Quantity；Represent the space headway average of all vehicles of t on the l of section；FDSDl(t) represent that t owns on the l of section
The space headway standard deviation of vehicle；FDCVl(t) the space headway coefficient of variation of t on the l of section is represented.
S3：Merge the grand micro-parameter of traffic flow and carry out traffic behavior fuzzy discrimination；Including following sub-step
1) fuzzy evaluation set of factors U is established.U={ v, d, vcv, fdcv }, wherein v, d, vcv, fdcv represent average respectively
Speed, average space headway, the speed coefficient of variation and the space headway coefficient of variation.
2) fuzzy evaluation collection V is established.
Traffic behavior is divided into Three Estate, i.e. V=(v1,v2,v3), wherein v1,v2,v3Represent unimpeded respectively, walk or drive slowly,
Congestion.
3) single factor test fuzzy evaluation is established,
Establish a FUZZY MAPPING from U to V.Thus single factor judgment matrix R, R=[R are obtained1,R2,R3,R4]T, its
Middle vectorial R1,R2,R3,R4Respectively R1=(r11,r12,r13), R2=(r21,r22,r23), R3=(r31,r32,r33), R1=(r41,
r42,r43), they represent average speed, average space headway, the speed coefficient of variation and the space headway coefficient of variation to commenting respectively
The degree of membership of valency grade.
4) Comprehensive Evaluation, suitable Fuzzy Arithmetic Operators are selected to carry out Comprehensive Evaluation.Utilize selected Fuzzy Arithmetic Operators
Factor weight vector W and Judgement Matrix R are synthesized to the fuzzy overall evaluation result vector S for being respectively evaluated object, i.e.,
Wherein represent Fuzzy Arithmetic Operators, s1,s2,s3Represent respectively and correspond to unimpeded, jogging, the significance level of congestion.
By to s1,s2,s3Value relatively finally determines traffic behavior, rijRepresent degree of membership of i-th of evaluation factor to j-th of comment.
S4：Mean change-point model is established, using the difference of the measured value of traffic behavior and predicted value as sample sequence, with minimum
Variance method searches for height, detects traffic events.
The basic thought of mean change-point model is:Threshold value q, q for determination are natural numbers, and it represents to dash forward in sample sequence
Become the upper limit of number, as long as therefore q is obtained sufficiently large can meeting condition.But in the application of reality, due to sample
Number n is very huge, therefore Comparatively speaking q is the number of a very little.Thus, the discrete model of mean change-point model is：
ai, eiThe average and random error of i-th of sample are represented respectively；miI sample before expression；biThe constant assumed that.
In formula, random error e1,e2,...,eNIt is assumed to be the variances sigma such as independent2, it is desired for 0.If bj+1≠bj, then it is assumed that
mjIt is a height.
Minimum variance searches for height, detects traffic events；
If based on four average speed, average space headway, the speed coefficient of variation and the space headway coefficient of variation traffic flows
The time series that the time series progress fuzzy comprehensive evoluation of characteristic parameter obtains traffic behavior is { Xi| i=1,2 ..., n },
The predicted value for being predicted to obtain by the time series of aforementioned four traffic flow character parameter carries out what fuzzy comprehensive evoluation obtained
The time series of traffic behavior isSample sequence can then be investigated
{xi| i=1,2 ..., n }
In formula,The sample sequence illustrates traffic behavior measured value in optimal data binding time interval
With the difference of predicted value, it is the comprehensive embodiment of traffic behavior mutation.
Define sample sequence population variance be
In formula,For the average of sample sequence.In order to differentiate whether there occurs traffic events in the sample sequence, by the sample
Originally two sections are divided into, the population variance of sample sequence is after definition division
In formula,The average of two sections of sample sequence before and after the sample respectively divided.By being derived by
Obvious S >=SkIf there are E (S)=E (S without traffic events occur in sample sequencek)；If sample sequence
In there occurs traffic events, then E (S) ＞ E (Sk) there is conspicuousness, hypothesis inspection is then carried out according to corresponding hypothesis testing method
Test.
In order to more accurately detect the specific moment of traffic events, order
S*=min (Sk), k=2,3 ..., n-1
It can be seen from the principle of cluster, S*At the time of being that traffic events occur at the time of corresponding.Significance test uses
Following method, i.e. given threshold R, work as S-S*＞ R, that is, think traffic events.
For threshold value R, the level of signifiance as requested determines.Statistical theory has
In formula, σ2For the variance of sample sequence, α is given significance, it is hereby achieved that
It may thereby determine that
R=σ2(2lg(lgn)+lg(lg(lgn))-lgπ+uα)
The present invention makes full use of the basic parameter of bicycle in traffic flow, considers from microcosmic angle between speed deviation and headstock
Away from discreteness, their changing rule when research traffic flow changes, fusion both macro and micro parameter differentiates to traffic behavior,
The mutation for the traffic behavior being finally based on after grand micro-parameter fusion carries out automatic traffic event detection, and car networking is adapted to for research
The traffic incidents detection technology of environment provides new approaches.
Finally illustrate, preferred embodiment above is merely illustrative of the technical solution of the present invention and unrestricted, although logical
Cross above preferred embodiment the present invention is described in detail, it is to be understood by those skilled in the art that can be
Various changes are made to it in form and in details, without departing from claims of the present invention limited range.
Claims (5)
- A kind of 1. traffic incidents detection method based on traffic behavior mutation, it is characterised in that：Comprise the following steps：Road section selected and the bicycle essential information of period are extracted under S1 car networking environment；S2 by the average speed of measurement period statistics road section selected, average space headway, the speed coefficient of variation and space headway from The coefficient of variation；The grand micro-parameter of S3 fusion traffic flows carries out traffic behavior fuzzy discrimination；S4 establishes mean change-point model, using the difference of the measured value of traffic behavior and predicted value as sample sequence, with minimum variance Method searches for height, detects traffic events.
- A kind of 2. traffic incidents detection method based on traffic behavior mutation according to claim 1, it is characterised in that：Institute Stating step S3 includes following sub-step：S31 establishes fuzzy evaluation set of factors U；S32 establishes fuzzy evaluation collection V；S33 establishes single factor test fuzzy evaluation, that is, establishes a FUZZY MAPPING from U to V；S34 Comprehensive Evaluations, suitable Fuzzy Arithmetic Operators are selected to carry out Comprehensive Evaluation.
- A kind of 3. traffic incidents detection method based on traffic behavior mutation according to claim 1, it is characterised in that：Root According to average speed, average space headway, four traffic flow character parameters of the speed coefficient of variation and the space headway coefficient of variation when Between sequence to carry out fuzzy comprehensive evoluation to obtain the time series of traffic behavior measured value be { Xi| i=1,2 ..., n }, according to flat Equal speed, average space headway, the time sequence of four traffic flow character parameters of the speed coefficient of variation and the space headway coefficient of variation Row carry out the time series of traffic status prediction value that fuzzy comprehensive evoluation obtainsThen sample sequenceN represents total sample number；Define sample sequence population variance S be：In formula,For the average of sample sequence；Sample sequence is divided into two sections, the population variance of sample sequence is after divisionIn formula,The average of two sections of sample sequence before and after the sample respectively divided, then<mrow> <mi>S</mi> <mo>=</mo> <msub> <mi>S</mi> <mi>k</mi> </msub> <mo>+</mo> <mfrac> <mn>1</mn> <mi>n</mi> </mfrac> <mrow> <mo>(</mo> <mi>k</mi> <mo>-</mo> <mn>1</mn> <mo>)</mo> </mrow> <mrow> <mo>(</mo> <mi>n</mi> <mo>-</mo> <mi>k</mi> <mo>+</mo> <mn>1</mn> <mo>)</mo> </mrow> <msup> <mrow> <mo>(</mo> <msub> <mover> <mi>x</mi> <mo>&OverBar;</mo> </mover> <mrow> <mi>k</mi> <mn>1</mn> </mrow> </msub> <mo>-</mo> <msub> <mover> <mi>x</mi> <mo>&OverBar;</mo> </mover> <mrow> <mi>k</mi> <mn>2</mn> </mrow> </msub> <mo>)</mo> </mrow> <mn>2</mn> </msup> </mrow>If E (S)=E (Sk), then without generation traffic events；E if (S) ＞ E (Sk), then there occurs traffic events, wherein, E (S), E(Sk) population variance S and S are represented respectivelykExpectation, k represent sample decomposition point.
- A kind of 4. traffic incidents detection method based on traffic behavior mutation according to claim 3, it is characterised in that：Order S*=min (Sk), k=2,3 ..., n-1According to the principle of cluster, S*At the time of being that traffic events occur at the time of corresponding, work as S-S*＞ R, that is, think traffic events Occur, wherein R is given threshold.
- A kind of 5. traffic incidents detection method based on traffic behavior mutation according to claim 4, it is characterised in that：It is right In given threshold R, the level of signifiance as requested determines that statistical theory has<mfenced open = "" close = ""> <mtable> <mtr> <mtd> <mrow> <munder> <mi>lim</mi> <mrow> <mi>n</mi> <mo>&RightArrow;</mo> <mi>&infin;</mi> </mrow> </munder> <mi>P</mi> <mrow> <mo>(</mo> <mfrac> <mrow> <mi>S</mi> <mo>-</mo> <msup> <mi>S</mi> <mo>*</mo> </msup> </mrow> <msup> <mi>&sigma;</mi> <mn>2</mn> </msup> </mfrac> <mo>></mo> <mn>2</mn> <mi>lg</mi> <mo>(</mo> <mi>lg</mi> <mi> </mi> <mi>n</mi> <mo>)</mo> </mrow> <mo>+</mo> <mi>lg</mi> <mrow> <mo>(</mo> <mi>lg</mi> <mo>(</mo> <mrow> <mi>lg</mi> <mi> </mi> <mi>n</mi> </mrow> <mo>)</mo> <mo>)</mo> </mrow> <mo>-</mo> <mi>lg</mi> <mi>&pi;</mi> <mo>+</mo> <mi>u</mi> <mo>)</mo> </mrow> </mtd> </mtr> <mtr> <mtd> <mrow> <mo>=</mo> <mn>1</mn> <mo>-</mo> <mi>exp</mi> <mrow> <mo>(</mo> <mo>-</mo> <mn>2</mn> <msup> <mi>e</mi> <mrow> <mo>-</mo> <mfrac> <mi>u</mi> <mn>2</mn> </mfrac> </mrow> </msup> <mo>)</mo> </mrow> </mrow> </mtd> </mtr> <mtr> <mtd> <mrow> <mo>=</mo> <mi>&alpha;</mi> </mrow> </mtd> </mtr> </mtable> </mfenced>Wherein, P () represents probability, and u represents that sample it is expectedIn formula, σ2For the variance of sample sequence, α is given significance, is thus obtained<mrow> <msub> <mi>u</mi> <mi>&alpha;</mi> </msub> <mo>=</mo> <mo>-</mo> <mn>2</mn> <mi>lg</mi> <mrow> <mo>(</mo> <mo>-</mo> <mfrac> <mn>1</mn> <mn>2</mn> </mfrac> <mi>lg</mi> <mo>(</mo> <mn>1</mn> <mo>-</mo> <mi>&alpha;</mi> <mo>)</mo> </mrow> <mo>)</mo> </mrow>ThenR=σ2(2lg(lgn)+lg(lg(lgn))-lgπ+uα), wherein uαRepresent the standardized normal distribution under level of significance α Value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710545628.3A CN107564276A (en) | 2017-07-06 | 2017-07-06 | A kind of traffic incidents detection method based on traffic behavior mutation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710545628.3A CN107564276A (en) | 2017-07-06 | 2017-07-06 | A kind of traffic incidents detection method based on traffic behavior mutation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107564276A true CN107564276A (en) | 2018-01-09 |
Family
ID=60973503
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710545628.3A Pending CN107564276A (en) | 2017-07-06 | 2017-07-06 | A kind of traffic incidents detection method based on traffic behavior mutation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107564276A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112767698A (en) * | 2021-01-19 | 2021-05-07 | 东南大学 | Self-adaptive traffic incident detection method based on small step adjustment |
| CN112819031A (en) * | 2021-01-04 | 2021-05-18 | 中国汽车技术研究中心有限公司 | Vehicle-mounted weight prediction method and system, electronic device and medium |
| CN113628434A (en) * | 2020-05-06 | 2021-11-09 | 深圳市万普拉斯科技有限公司 | Traffic state monitoring method and device, computer equipment and readable storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102426783B (en) * | 2011-08-30 | 2013-11-13 | 同济大学 | Low flow road traffic incident detection method based on vehicle tracking |
| CN105632174A (en) * | 2016-01-04 | 2016-06-01 | 江苏科技大学 | Traffic event detection system based on semantic technology and method for the same |
| CN106067248A (en) * | 2016-05-30 | 2016-11-02 | 重庆大学 | A kind of traffic status of express way method of estimation considering speed dispersion characteristic |
| CN106297285A (en) * | 2016-08-17 | 2017-01-04 | 重庆大学 | Freeway traffic running status fuzzy synthetic appraisement method based on changeable weight |
| CN106529076A (en) * | 2016-11-28 | 2017-03-22 | 东南大学 | Two-stage parameter calibration method for highway traffic safety simulation analysis |
| CN106781452A (en) * | 2016-11-25 | 2017-05-31 | 上海市政工程设计研究总院（集团）有限公司 | A kind of traffic event automatic detection method |
| US20170161410A1 (en) * | 2015-12-04 | 2017-06-08 | International Business Machines Corporation | System and method for simulating traffic flow distributions with approximated vehicle behavior near intersections |
-
2017
- 2017-07-06 CN CN201710545628.3A patent/CN107564276A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102426783B (en) * | 2011-08-30 | 2013-11-13 | 同济大学 | Low flow road traffic incident detection method based on vehicle tracking |
| US20170161410A1 (en) * | 2015-12-04 | 2017-06-08 | International Business Machines Corporation | System and method for simulating traffic flow distributions with approximated vehicle behavior near intersections |
| CN105632174A (en) * | 2016-01-04 | 2016-06-01 | 江苏科技大学 | Traffic event detection system based on semantic technology and method for the same |
| CN106067248A (en) * | 2016-05-30 | 2016-11-02 | 重庆大学 | A kind of traffic status of express way method of estimation considering speed dispersion characteristic |
| CN106297285A (en) * | 2016-08-17 | 2017-01-04 | 重庆大学 | Freeway traffic running status fuzzy synthetic appraisement method based on changeable weight |
| CN106781452A (en) * | 2016-11-25 | 2017-05-31 | 上海市政工程设计研究总院（集团）有限公司 | A kind of traffic event automatic detection method |
| CN106529076A (en) * | 2016-11-28 | 2017-03-22 | 东南大学 | Two-stage parameter calibration method for highway traffic safety simulation analysis |
Non-Patent Citations (2)
| Title |
|---|
| LIAO XIAO-YONG等: "Fuzzy Evaluation of Traffic Flow Stability Based on the Discreteness of Traffic Parameters", 《THE 29TH CHINESE CONTROL AND DECISION CONFERENCE》 * |
| 龙琼等: "基于尖点突变理论模型的交通事故检测", 《土木工程学报》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113628434A (en) * | 2020-05-06 | 2021-11-09 | 深圳市万普拉斯科技有限公司 | Traffic state monitoring method and device, computer equipment and readable storage medium |
| CN112819031A (en) * | 2021-01-04 | 2021-05-18 | 中国汽车技术研究中心有限公司 | Vehicle-mounted weight prediction method and system, electronic device and medium |
| CN112767698A (en) * | 2021-01-19 | 2021-05-07 | 东南大学 | Self-adaptive traffic incident detection method based on small step adjustment |
| CN112767698B (en) * | 2021-01-19 | 2022-03-11 | 东南大学 | Self-adaptive traffic incident detection method based on small step adjustment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lin et al. | Data mining and complex network algorithms for traffic accident analysis | |
| CN106530715B (en) | Road net traffic state prediction technique based on fuzzy Markov process | |
| CN104574968B (en) | Determining method for threshold traffic state parameter | |
| CN104809879A (en) | Expressway road traffic state estimation method based on dynamic Bayesian network | |
| CN104809877A (en) | Expressway site traffic state estimation method based on feature parameter weighted GEFCM algorithm | |
| CN107507421A (en) | Method for rapidly judging traffic state and device | |
| CN107437339A (en) | Variable information advices plate control method for coordinating and system under a kind of information guidance | |
| CN107564276A (en) | A kind of traffic incidents detection method based on traffic behavior mutation | |
| CN107180534B (en) | The express highway section average speed estimation method of support vector regression fusion | |
| CN108682149A (en) | The linear causation analysis method in highway accident stain section based on binary logistic regression | |
| Rossi et al. | Fuzzy logic-based incident detection system using loop detectors data | |
| CN105869398A (en) | Road traffic open degree judging method based on K-means cluster | |
| CN105931459A (en) | Variable speed limit control strategy optimization method for isolated bottleneck section of expressway | |
| CN103456163A (en) | City expressway interchange traffic capacity and running status discrimination method and system | |
| CN106384507A (en) | Travel time real-time estimation method based on sparse detector | |
| CN102819956B (en) | Detecting method for road traffic accident on basis of single-section annular coil detector | |
| Bao | A multi-index fusion clustering strategy for traffic flow state identification | |
| Xie et al. | A hybrid temporal-spatio forecasting approach for passenger flow status in chinese high-speed railway transport hub | |
| CN116597642A (en) | Traffic jam condition prediction method and system | |
| Sun et al. | Traffic congestion pattern detection using an improved mcmaster algorithm | |
| CN103914984A (en) | Urban road traffic state analyzing method based on unit-section collaboration | |
| CN107134131A (en) | The computational methods and system of a kind of current coefficient that is obstructed of highway | |
| CN106529118A (en) | Two-tuple linguistic AHP based intelligent automobile human-simulated steering control performance evaluation method | |
| CN117238126A (en) | Traffic accident risk assessment method under continuous flow road scene | |
| Yang et al. | Support vector machines for incident detection in urban signalized arterial street networks |
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 |
Application publication date: 20180109 |
|
| RJ01 | Rejection of invention patent application after publication |