CN114566051A - Highway switching area severe conflict recognition method based on logistic model - Google Patents
Highway switching area severe conflict recognition method based on logistic model Download PDFInfo
- Publication number
- CN114566051A CN114566051A CN202210271371.8A CN202210271371A CN114566051A CN 114566051 A CN114566051 A CN 114566051A CN 202210271371 A CN202210271371 A CN 202210271371A CN 114566051 A CN114566051 A CN 114566051A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- factors
- obtaining
- acceleration
- conflict
- 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
- 238000000034 method Methods 0.000 title claims abstract description 27
- 230000007704 transition Effects 0.000 claims abstract description 20
- 230000001133 acceleration Effects 0.000 claims description 22
- 238000006243 chemical reaction Methods 0.000 claims description 19
- 238000003064 k means clustering Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000007619 statistical method Methods 0.000 claims description 3
- 238000012546 transfer Methods 0.000 description 5
- 239000006185 dispersion Substances 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
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
-
- 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
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/07—Controlling traffic signals
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to the technical field of traffic safety, and discloses a highway transition area severe conflict recognition method based on a logistic model. According to the method for identifying the severe conflict of the expressway transition area based on the logistic model, disclosed by the invention, the influence degree of multiple factors on the severe conflict of the vehicles is analyzed so as to identify the severe conflict of the expressway transition area and improve the traffic safety and efficiency of the transition area.
Description
Technical Field
The invention relates to the technical field of traffic safety, in particular to a method for identifying severe conflicts in a highway transfer area based on a logistic model.
Background
The highway switching area is used as a typical bottleneck road section for reconstruction and extension of the highway, the road condition is complex, the highway switching area is positioned at a central separation zone, the curvature radius is small, the traffic conflict identification is difficult, and the traffic safety problem is prominent.
According to the investigation, the current common methods for identifying serious conflicts are mainly: the collision time, the post-intrusion time and the collision time difference are suitable for rear-end collisions in the process of identifying the collision types, can better identify traffic collisions, and are widely applied. However, these methods are directed to specific types of traffic conflicts, and do not consider the influence of parameters such as vehicle acceleration on the traffic conflicts. Meanwhile, serious conflict recognition research on a special scene of the expressway transition area is lacked, the considered factors are not comprehensive, the fusion of factors such as single cars, traffic flows and roads is not considered, and the influence degree of the transition on the serious conflict of the transition area is reduced.
Disclosure of Invention
Aiming at the defects of the technology, the invention provides a method for identifying severe conflict of a highway transfer area based on a logistic model, which analyzes the influence degree of multiple factors on severe conflict of vehicles to identify severe conflict of the highway transfer area and improve the safety and efficiency of traffic of the transfer area.
In order to achieve the purpose, the method for identifying severe conflict of the expressway transition area based on the logistic model comprises the following steps of:
A) obtaining continuous track data of vehicle running in a plurality of conversion areas on the highway by using a radar, and obtaining real-time data of the vehicle through coordinate conversion processing;
B) setting an argument XmIndependent variable XmDecomposing and obtaining vehicle factors, traffic flow factors and road factors, obtaining the vehicle factors and the traffic flow factors from the real-time data obtained in the step A), obtaining the vehicle factors including average speed and acceleration, obtaining the road factors by calculating road information of a conversion area, performing discretization processing by using a K-means clustering method, defining discretization judgment, and obtaining each independent variable XmN is a natural number, and then respective variables X are takenmDefines the remaining discrete values as corresponding independent variables XmDummy variable Xm(n-1)Fitting through a logistic model to obtain each independent variable XmRegression coefficient beta corresponding to nth discrete valuem(n-1)N is more than or equal to 2, and the probability P (y) of serious conflict event is obtainedi)，
g(yi)＝α+β11X11+...+βm(n-1)Xm(n-1)
In the formula, yiFor a serious collision event of the vehicle with the number i, alpha is intercept and is a constant;
C) carrying out statistical analysis on the real-time data of the vehicle obtained in the step A) to obtain the average speed and the acceleration of the vehicle, and classifying the average speed and the acceleration by adopting a K-means clustering method to form clustering combinations of the average speed and the acceleration in different intervals;
D) according to the average of each cluster combination in the step C)Substituting the speed and the acceleration into the step B) for calculation to obtain the probability P (y) of serious conflict events correspondingly occurring in different cluster combinationsi) If P (y)i) And if the threshold value is larger than the preset serious conflict threshold value, the cluster combination of the vehicles in the transition area is indicated to have serious conflict.
Preferably, in the step B), the vehicle factors further include a vehicle type and a speed standard deviation, the traffic flow factor includes a traffic volume, an average vehicle speed of all vehicles, a speed standard deviation of all vehicles, and a standard deviation of vehicle acceleration, and the road factor includes a radius of a circular curve of a transition area, an accumulated driving angle per unit length, and a curvature change reflecting a lane turn.
Preferably, in the step D), the severe collision threshold is 0.8.
Compared with the prior art, the invention has the following advantages:
1. analyzing the conflict rate and the road section accident rate in each clustering interval based on the correlation to obtain a severe conflict threshold value of the conversion area, then fusing factors such as a single vehicle, a traffic flow and a road to establish a two-item logistic model, analyzing the influence degree of multiple factors on the severe conflict of the vehicle so as to identify the severe conflict of the expressway conversion area, reducing the severe conflict of the expressway conversion area and further improving the traffic safety and efficiency of the conversion area;
2. the binomial Logistic model is a discrete probability model, and negative influence of some extreme variable values on the model can be eliminated by variable discretization, so that the applicability of a model result is better;
3. the severe conflict influence factors are quantitatively determined through a binomial Logistic model, so that the severe conflict is more comprehensively considered in the process of identifying the severe conflict, and omission is avoided.
Detailed Description
The present invention will be described in further detail with reference to specific examples.
A highway transfer area severe conflict recognition method based on a logistic model comprises the following steps:
A) the method comprises the steps that continuous track data of vehicle running of a plurality of conversion areas on a highway are obtained through a radar, real-time data of the vehicle are obtained through coordinate conversion processing, the positioning accuracy of a high-accuracy radar target is +/-0.25 m, the speed accuracy is +/-0.28 m/s, the radar is erected at the starting point of the conversion area during observation, the coordinate conversion is facilitated, economic and high speed is investigated on the spot, and data collection is shown in table 1;
TABLE 1
B) Setting an argument XmIndependent variable XmDecomposing and obtaining vehicle factors, traffic flow factors and road factors, obtaining the vehicle factors and the traffic flow factors from the real-time data obtained in the step A), obtaining the vehicle factors including average speed and acceleration, calculating the road factors from road information of a conversion area, carrying out discretization processing by using a K-means clustering method, defining discretization judgment, and obtaining each independent variable XmThe vehicle factors further include vehicle type and speed standard deviation, the traffic flow factors include traffic volume, average vehicle speed of all vehicles, speed standard deviation of all vehicles and standard deviation of vehicle acceleration, the road factors include conversion zone circular curve radius, unit length accumulated driving corner and curvature change reflecting lane turning, the conversion zone circular curve radius is respectively 160, 230, 260, 320 and 400m, the conversion zone circular curve radius can be regarded as small (200m <), medium (200-300 m) and large (> 300m) for dispersion, in addition, the unit length accumulated driving corner can be regarded as 0.36, 0.27, 0.22, 0.18 and 0.14 degree/m, and can be regarded as small (< 0.2 degree/m), medium (> 0.2-0.3 degree/m) and large (> 0.3 degree/m) for dispersion, and the specific results are as shown in table 2:
TABLE 2
To avoid LError accumulation effect occurs in the logistic model, the following 5 independent variables with small influence are excluded in the model fitting process and respectively refer to the speed standard deviation of the vehicle, the average speed of the traffic flow, the speed standard deviation of the traffic flow, the standard deviation of the vehicle running acceleration of the traffic flow and the radius of a circular curve in a transition area, the remaining independent variables have obvious influence on serious conflict risk, and then the respective variable X is usedmDefines the remaining discrete values as corresponding independent variables XmDummy variable Xm(n-1)See table 3:
TABLE 3
Then fitting through a logistic model to obtain each independent variable XmRegression coefficient beta corresponding to nth discrete valuem(n-1)N is not less than 2, and the fitting result is shown in Table 4:
TABLE 4
Obtaining probability P (y) of occurrence of severe collision eventi)，
g(yi)＝α+β11X11+...+βm(n-1)Xm(n-1)
In the formula, yiFor a serious collision event of the vehicle with the number i, alpha is intercept and is a constant;
C) carrying out statistical analysis on the real-time data of the vehicle obtained in the step A) to obtain the average speed and the acceleration of the vehicle, and classifying the average speed and the acceleration by adopting a K-means clustering method to form clustering combinations of the average speed and the acceleration in different intervals, which is shown in a table 5;
TABLE 5
D) Substituting the average speed and the acceleration of each cluster combination in the step C) into the step B) for calculation to obtain the probability P (y) of the occurrence of serious conflict events corresponding to different cluster combinationsi) See table 6:
TABLE 6
If P (y)i) If the value is greater than the preset serious conflict threshold, that is, it indicates that there is a serious conflict in the cluster combination of the vehicles in the transition area, in this embodiment, the serious conflict threshold is 0.8, and the result indicates that: average speed is [45.50,85.68 ]]km/h and acceleration of [ -3.53, -1.31]m/s2 or an average speed of [27.65,34.96 ]]km/h and acceleration of 1.77,3.04]m/s2, and when the vehicles have serious conflict in a certain section of the transition area, the vehicles are serious conflict vehicles. The number of vehicles with serious conflicts is 392 by statistics, which accounts for 29.79% of the total number of the vehicles.
The method for identifying severe conflicts of the expressway transition areas based on the logistic model comprises the steps of analyzing conflict rate and road section accident rate in each clustering interval based on correlation to obtain severe conflict threshold values of the transition areas, then fusing factors such as single vehicles, traffic flow and roads to establish a binomial logistic model, analyzing the influence degree of multiple factors on severe conflicts of the vehicles, identifying severe conflicts of the expressway transition areas in due course, reducing severe conflicts of the expressway transition areas, and further improving traffic safety and efficiency of the transition areas; the binomial Logistic model is a discrete probability model, and negative effects of certain extreme variable values on the model can be eliminated by variable discretization, so that the applicability of a model result is better; in addition, the serious conflict influence factors are quantitatively determined through a binomial Logistic model, so that the serious conflict is considered more comprehensively in the process of identifying the serious conflict, and omission is avoided.
Claims (3)
1. A highway switching area severe conflict recognition method based on a logistic model is characterized by comprising the following steps: the method comprises the following steps:
A) obtaining continuous track data of vehicle running in a plurality of conversion areas on the highway by using a radar, and obtaining real-time data of the vehicle through coordinate conversion processing;
B) setting an argument XmIndependent variable XmDecomposing and obtaining vehicle factors, traffic flow factors and road factors, obtaining the vehicle factors and the traffic flow factors from the real-time data obtained in the step A), obtaining the vehicle factors including average speed and acceleration, obtaining the road factors by calculating road information of a conversion area, performing discretization processing by using a K-means clustering method, defining discretization judgment, and obtaining each independent variable XmN is a natural number, and then respective variables X are takenmDefines the remaining discrete values as corresponding independent variables XmDummy variable Xm(n-1)Fitting through a logistic model to obtain each independent variable XmRegression coefficient beta corresponding to nth discrete valuem(n-1)N is more than or equal to 2, and the probability P (y) of serious conflict event is obtainedi)，
g(yi)＝α+β11X11+...+βm(n-1)Xm(n-1)
In the formula, yiFor a serious collision event of the vehicle with the number i, alpha is intercept and is a constant;
C) carrying out statistical analysis on the real-time data of the vehicle obtained in the step A) to obtain the average speed and the acceleration of the vehicle, and classifying the average speed and the acceleration by adopting a K-means clustering method to form clustering combinations of the average speed and the acceleration in different intervals;
D) substituting the average speed and the acceleration of each cluster combination in the step C) into the step B) for calculation to obtain the probability P (y) of serious conflict events correspondingly occurring in different cluster combinationsi) If P (y)i) And if the threshold value is larger than the preset serious conflict threshold value, the cluster combination of the vehicles in the transition area is indicated to have serious conflict.
2. The method for identifying severe conflicts in highway turnarounds based on logistic model according to claim 1, characterized in that: in the step B), the vehicle factors further include vehicle type and speed standard deviation, the traffic flow factors include traffic volume, average vehicle speed of all vehicles, speed standard deviation of all vehicles and standard deviation of vehicle acceleration, and the road factors include radius of a circular curve in a conversion area, accumulated running rotation angle per unit length and curvature change reflecting lane turning.
3. The method for identifying severe conflicts in highway transition areas based on a logistic model as defined in claim 1, wherein the method comprises the following steps: in step D), the severe collision threshold is 0.8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210271371.8A CN114566051A (en) | 2022-03-18 | 2022-03-18 | Highway switching area severe conflict recognition method based on logistic model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210271371.8A CN114566051A (en) | 2022-03-18 | 2022-03-18 | Highway switching area severe conflict recognition method based on logistic model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114566051A true CN114566051A (en) | 2022-05-31 |
Family
ID=81719631
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210271371.8A Pending CN114566051A (en) | 2022-03-18 | 2022-03-18 | Highway switching area severe conflict recognition method based on logistic model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114566051A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117852191A (en) * | 2024-01-15 | 2024-04-09 | 青岛海特新材料船艇有限公司 | Three-dimensional model design method and system based on motor car console |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107958269A (en) * | 2017-11-28 | 2018-04-24 | 江苏大学 | A kind of driving risk factor Forecasting Methodology based on hidden Markov model |
| CN112487617A (en) * | 2020-11-19 | 2021-03-12 | 平安科技（深圳）有限公司 | Collision model-based risk prevention method, device, equipment and storage medium |
| CN112508392A (en) * | 2020-12-02 | 2021-03-16 | 云南省交通规划设计研究院有限公司 | Dynamic evaluation method for traffic conflict risk of hidden danger road section of mountain area double-lane highway |
| CN112767695A (en) * | 2021-01-07 | 2021-05-07 | 哈尔滨工业大学 | Real-time prediction method and system for traffic accident risk at signalized intersection |
-
2022
- 2022-03-18 CN CN202210271371.8A patent/CN114566051A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107958269A (en) * | 2017-11-28 | 2018-04-24 | 江苏大学 | A kind of driving risk factor Forecasting Methodology based on hidden Markov model |
| CN112487617A (en) * | 2020-11-19 | 2021-03-12 | 平安科技（深圳）有限公司 | Collision model-based risk prevention method, device, equipment and storage medium |
| CN112508392A (en) * | 2020-12-02 | 2021-03-16 | 云南省交通规划设计研究院有限公司 | Dynamic evaluation method for traffic conflict risk of hidden danger road section of mountain area double-lane highway |
| CN112767695A (en) * | 2021-01-07 | 2021-05-07 | 哈尔滨工业大学 | Real-time prediction method and system for traffic accident risk at signalized intersection |
Non-Patent Citations (3)
| Title |
|---|
| 丘积: "高速公路转换区严重冲突识别与分析高速公路转换区严重冲突识别与分析", 《中国安全科学学报》, pages 184 - 191 * |
| 于帅: "基于气象条件与交通流交互作用的高速公路事故风险分析及预测", 《中国博士学位论文全文数据库（工程科技Ⅱ辑）》, no. 3, pages 1 - 6 * |
| 顾欣: "高速公路互通立交合流区交通冲突预测模型研究", 《中国博士学位论文全文数据库（工程科技Ⅱ辑）》, no. 20220215 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117852191A (en) * | 2024-01-15 | 2024-04-09 | 青岛海特新材料船艇有限公司 | Three-dimensional model design method and system based on motor car console |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112508392B (en) | Dynamic evaluation method for traffic conflict risk of hidden danger road section of mountain area double-lane highway | |
| CN113486822B (en) | Surrounding vehicle track prediction method and system based on driving intention | |
| CN111599181A (en) | Typical natural driving scene recognition and extraction method for intelligent driving system test | |
| CN110428621B (en) | Track data-based monitoring and early warning method for dangerous driving behavior of floating car | |
| CN113744563B (en) | Road-vehicle risk real-time estimation method based on track data | |
| CN113127466B (en) | Vehicle track data preprocessing method and computer storage medium | |
| CN111243338A (en) | Vehicle acceleration-based collision risk evaluation method | |
| CN114169444B (en) | Driving style classification method considering risk potential field distribution under vehicle following working condition | |
| CN114566051A (en) | Highway switching area severe conflict recognition method based on logistic model | |
| CN114241754B (en) | Real-time control method based on accident precursor characteristics of highway confluence influence area | |
| CN115588310A (en) | Vehicle collision risk prediction method based on trajectory data | |
| CN111882923A (en) | Intelligent networking automobile behavior identification method | |
| CN114566050B (en) | Tunnel robot inspection speed control method for traffic operation safety | |
| CN114999181A (en) | ETC system data-based highway vehicle speed abnormity identification method | |
| CN113808394B (en) | Cross-street channel safety evaluation method based on risk combination mode | |
| CN112036709B (en) | Random forest based rainfall weather expressway secondary accident cause analysis method | |
| CN115798207A (en) | Signal intersection rear-end collision recognition method based on LiDAR point cloud | |
| Ma et al. | Naturalistic driving behavior analysis under typical normal cut-in scenarios | |
| CN112365716B (en) | Urban elevated expressway dynamic security evaluation method based on GPS data | |
| CN113643531B (en) | Intersection lane saturation flow rate calculation method based on small time zone division statistics | |
| CN113807009B (en) | Segmentation extraction method for microscopic lane change track | |
| Wen et al. | Analysis of vehicle driving styles at freeway merging areas using trajectory data | |
| CN117351726B (en) | Highway event early warning system and comprehensive perception method | |
| CN116246468B (en) | Multi-element space-time data-based distracted driving risk road section identification and control method | |
| CN116383556A (en) | Intersection turning opening position calculation method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB03 | Change of inventor or designer information |
Inventor after: Zhu Shunying Inventor after: Chen Qiucheng Inventor after: Wang Daiyang Inventor after: Wang Hong Inventor after: Qiu Ji Inventor after: Wang Fupeng Inventor after: Wang Hongtao Inventor after: Sun Weimin Inventor after: Wu Jingan Inventor before: Wang Daiyang Inventor before: Wang Hong Inventor before: Qiu Ji Inventor before: Zhu Shunying Inventor before: Chen Qiucheng Inventor before: Wang Fupeng Inventor before: Wang Hongtao Inventor before: Sun Weimin Inventor before: Wu Jingan |
|
| CB03 | Change of inventor or designer information |