CN120014839B - A low-speed vehicle graded warning method for highway scenarios - Google Patents
A low-speed vehicle graded warning method for highway scenariosInfo
- Publication number
- CN120014839B CN120014839B CN202510475495.1A CN202510475495A CN120014839B CN 120014839 B CN120014839 B CN 120014839B CN 202510475495 A CN202510475495 A CN 202510475495A CN 120014839 B CN120014839 B CN 120014839B
- Authority
- CN
- China
- Prior art keywords
- speed
- vehicle
- low
- data
- vehicles
- 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.)
- Active
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
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING SYSTEMS, e.g. PERSONAL CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B31/00—Predictive alarm systems characterised by extrapolation or other computation using updated historic data
-
- 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
- G08G1/015—Detecting movement of traffic to be counted or controlled with provision for distinguishing between two or more types of vehicles, e.g. between motor-cars and cycles
-
- 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
- G08G1/052—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed
-
- 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)
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Emergency Management (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
Abstract
本发明公开了一种面向高速公路场景下的低速车辆分级预警方法，方法为：对各ETC门架数据进行采集并进行融合得到待处理数据集；根据不同车辆类型的车辆在不同区段的条件下的行驶速度进行区段通行速度特征识别得到区间通行速度特征数据集；计算车辆经过服务区的时间差并更新轨迹数据中通行时长数据；计算车辆通行速度并与相同条件下的道路通行速度比较判断是否低速车辆；构建偏小型隶属度函数计算当前车辆隶属度；基于影响驾驶行为安全因素相互间比例标度表计算得到影响驾驶行为安全因素的权重向量；基于车辆隶属度和影响驾驶行为安全因素的权重向量计算车辆区段驾驶行为评分，以便划分不同预警等级。本发明准确识别低速车辆并分级预警。
The present invention discloses a low-speed vehicle graded warning method for highway scenarios, the method is: collect and fuse the data of each ETC gantry to obtain a data set to be processed; identify the section speed characteristics according to the driving speed of vehicles of different types under different sections to obtain the interval speed characteristic data set; calculate the time difference of vehicles passing through the service area and update the travel time data in the trajectory data; calculate the vehicle speed and compare it with the road speed under the same conditions to determine whether it is a low-speed vehicle; construct a relatively small membership function to calculate the current vehicle membership; calculate the weight vector of the factors affecting driving behavior safety based on the scale table of the mutual proportions of the factors affecting driving behavior safety; calculate the vehicle section driving behavior score based on the vehicle membership and the weight vector of the factors affecting driving behavior safety, so as to divide different warning levels. The present invention accurately identifies low-speed vehicles and provides graded warnings.
Description
Technical Field
The invention relates to the technical field of expressway management, in particular to a low-speed vehicle grading early warning method oriented to expressway scenes.
Background
The existence of the expressway low-speed vehicles seriously affects the overall traffic efficiency, and particularly in the traffic peak period, the influence is more remarkable, and large-scale traffic jam is often caused. More serious, the low-speed vehicles are extremely easy to cause serious traffic accidents such as continuous rear-end collision and the like. To effectively solve this problem, it is particularly critical to build a rapid and accurate low-speed vehicle identification system. The system can provide data support for the fine management of the road network, can also remarkably improve the response speed of emergency management departments, and provides basis for formulating scientific emergency strategies, so that the life and property safety of drivers and passengers is better ensured.
The existing low-speed vehicle identification methods depend on technologies such as video monitoring, manual inspection and vehicle-mounted positioning, but the application of the methods faces a series of problems:
1. The manual inspection is low in efficiency and time-consuming, a large amount of manpower and material resources are needed to be input in the manual inspection, the manual inspection is limited by experience and attention of inspection staff, and real-time monitoring of all-weather and all-road sections is difficult to realize. On long-distance highways, it takes a long time to patrol vehicles, and it is difficult to find and handle low-speed vehicles in time. In addition, under severe weather conditions, the efficiency and safety of manual inspection can be greatly reduced.
2. The video monitoring has a visual field blind area, the existing video monitoring system is limited by the installation position and angle of a camera, and all lanes and road sections are difficult to cover. In special road sections such as curves, ramps and the like, the monitoring effect is often not ideal. Meanwhile, the recognition accuracy of video monitoring is obviously reduced at night or in rainy and foggy weather. The monitoring blind area between the cameras also presents difficulties in continuous tracking of the low-speed vehicle.
3. The vehicle-mounted positioning coverage is low, and obvious limitation exists in the dependence on a vehicle-mounted positioning system to identify the low-speed vehicle. First, not all vehicles are equipped with positioning devices, particularly partially older vehicles and freight vehicles. Secondly, the positioning signals are easy to be interfered in special road sections such as tunnels, mountain areas and the like, so that data loss or deviation is caused. In addition, the data standards of positioning equipment of different manufacturers are not uniform, and difficulties are brought to data integration.
4. The vehicle enters and exits the service area to cause misjudgment, namely, when the vehicle normally enters the service area, the speed change of the vehicle is easy to be misjudged by the system to be running at a low speed. The existing identification algorithm is often difficult to distinguish vehicles which normally enter a service area from vehicles which truly run at a low speed, so that the false alarm rate is high.
Disclosure of Invention
The invention aims to provide a low-speed vehicle grading early warning method oriented to a highway scene, which is based on multi-source data such as transaction data collected by an ETC portal frame, snapshot records and the like of a service area, and utilizes statistical algorithm evaluation indexes and the like to construct a low-speed vehicle grading early warning algorithm to realize grading early warning of the low-speed vehicle, so that high-efficiency and accurate early warning information of the low-speed vehicle on the highway is provided for traffic management departments and emergency rescue departments.
The technical scheme adopted by the invention is as follows:
a low-speed vehicle grading early warning method oriented to expressway scenes comprises the following steps:
step 1, data acquisition and preprocessing, namely acquiring and fusing all ETC portal data in real time to obtain a data set to be processed, wherein the acquired data comprises ETC system transaction data, ETC service area data and highway section QD;
Step 2, excavating traffic speed characteristics of expressway sections, namely carrying out section traffic speed characteristic identification according to the running speeds of vehicles of different vehicle types of the expressway under the conditions of different sections, and excavating the traffic speed characteristics of the vehicles to obtain a section traffic speed characteristic data set;
Step 3, processing the abnormal data of the service area, namely obtaining the data of the service area And vehicle track dataCalculating a time difference of the vehicle passing through the service area and updating the vehicle track dataThe passing time length data of the service area is eliminated to the track data of the vehicleInterference in time;
step 4, low-speed vehicle discrimination based on vehicle track data Calculating to obtain corresponding vehicle passing speedWill correspond to the passing speed of the vehicleRoad traffic speed under the same condition as the section traffic speed characteristic data setComparing to judge whether the current vehicle belongs to the low-speed vehicle;
And 5, grading and scoring early warning of the low-speed vehicle, namely constructing a small membership function as a membership function of the low-speed vehicle to calculate the current vehicle membership, calculating weight vectors influencing driving behavior safety factors based on a scale table of the driving behavior safety factors, and calculating the driving behavior scores of the current vehicle section based on the current vehicle membership and the weight vectors influencing the driving behavior safety factors so as to divide different early warning grades based on the section driving behavior scores.
Further, the step 2 specifically includes the following steps:
step 2-1, classifying the data sets according to the hours to obtain the integral road segment speeds of different time periods;
In particular, the data sets may thus be divided into 24 classes.
And 2-2, on the basis of the hour classification, carrying out fine division on the data according to the vehicle types vehclass, so that the problem of different passing speeds of different vehicle types can be effectively solved.
Step 2-3, according to the space regularity, the data set is based on the vehicle track dataThe classification results in different segment traffic data sets, thereby deeply mining the spatial regularity of the vehicle.
Specifically, the driving behavior of the expressway vehicle may be different in traffic speed in different sections due to external conditions such as the number of lanes, road conditions, and the like. Thus, according to the space regularity, the data set is based on the vehicle track dataThe traffic data sets are classified into different sections, so that the spatial regularity of the vehicle is deeply excavated.
And 2-4, extracting the passing time of the vehicle in the target zone through the divided zone passing data set, extracting the passing distance of the target zone through the portal distance matrix D, and calculating the running speeds of all vehicles in the data set by using a sensorless speed measurement model.
In particular, wherein the portal distance matrix D is an elementFor the distance between the i portal and the j portal, if the two portals are communicated, dis is the distance between the two portals, if the two portals are the same node, 0, and the distance between the non-communicated nodes is infThe expression of (2) is as follows:
(1);
step 2-5, deleting outlier abnormal data except the upper edge and the lower edge based on a data cleaning model of the box diagram;
step 2-6, calculating the average value of all the vehicle driving speeds as the passing speed of the road Thereby more accurately and effectively approaching the true value, and the passing speed of the roadThe calculation formula of (2) is as follows:
;
Wherein the method comprises the steps of Representing vehicles travelling on the road section,Representing the total vehicle for that road segment.
Step 2-7, adding the traffic speed of the road into the traffic speed characteristic data set of the expressway sectionIn order to further eliminate the influence of the vehicle entering the service area, the influence of the service area is eliminated through the following snapshot technology and ETC data fusion technology.
Further, the step 4 specifically includes the following steps:
Step 4-1, extracting vehicle track data And transaction data, calculating a sector passing speed of the vehicle;
Step 4-2, the section passing speed of the vehicle is calculatedData set of traffic speed characteristics of sectionRoad traffic speed under corresponding conditionsComparing, judging whether low-speed driving behavior exists, if so, recording the traffic information of the low-speed driving to execute the step 4-3, otherwise, executing the step 4-3;
Specifically, the average value of all the vehicle driving speeds is calculated as the passing speed of the road in step 4-2 ;
And 4-3, judging whether the traversal of all the vehicle tracks is completed, if so, outputting a recording result, and otherwise, executing the step 4-1.
Further, the step 5 specifically includes the following steps:
Step 5-1, constructing a small membership function as a membership function of the low-speed vehicle, wherein the membership function of the low-speed vehicle has the following expression:
wherein, the Representing a vehicle passing speed; The road traffic speed which is the same as the current situation in the highway section traffic speed characteristic data set;
step 5-2, calculating and obtaining the low-speed membership of the current vehicle ;
Step 5-3, constructing a judgment matrix R based on a scale table of the factors affecting the driving behavior safety, wherein each element value in the judgment matrix R represents the scale of the factors affecting the driving behavior safety;
Step 5-4, normalizing the column vector of the judgment matrix R to obtain a normalized judgment matrix Calculating the normalized judgment matrixObtaining a row vector from the mean of the row vectors of (2)As a weight vector for driving behavior safety factors of the line.
And 5-5, calculating the section driving behavior score of the current vehicle according to the weights of different driving behavior safety factors, wherein the expression of the section driving behavior score of the specific area is as follows:
;
wherein, the Representing a segment driving behavior score for the vehicle, a is a collection of vehicles for dangerous driving behaviors occurring within the segment,For the membership of the driving behaviour of the vehicle a,The driving behavior of the vehicle a is weighted.
And 5-6, dividing the vehicle journey into different early warning grades according to the section driving behavior scores of the vehicle.
Further, the membership grade standard of the low-speed vehicle in the step 5 is that the membership grade standard is a first section, when the driving speed of the motor vehicle is greater than 80% of the road traffic level, the membership grade is considered to be 0, a second section, when the driving speed of the motor vehicle is less than or equal to 80% of the road traffic speed and greater than 60% of the road traffic speed, the membership grade of the driving behavior is calculated, when the driving speed of the motor vehicle is less than or equal to 60% of the road traffic speed and greater than 40% of the road traffic speed, the membership grade of the driving behavior is calculated, and a fourth section, when the driving speed of the motor vehicle is less than or equal to 40% of the road traffic speed, the membership grade is 1.
By adopting the technical scheme, the invention combines ETC portal data, road network topological structure, service area snapshot data and the like through intelligent data processing and algorithm, judges the detained vehicles in real time and carries out accurate identification. And according to factors such as conditions of different vehicle types, road sections and the like, a flexible low-speed time threshold is designed, so that the low-speed vehicle can be accurately identified under different road sections. After the vehicles are detained and identified, the system automatically generates early warning information, and timely sends an alarm to traffic management departments and emergency rescue workers, so that support is provided for accurate rescue and safety guarantee.
Compared with the prior art, the invention has the advantages that 1) a great amount of false alarms are avoided by utilizing the service area information, the filtering of the low-speed vehicle which enters the service area and is mistakenly identified is realized by utilizing the fusion of the service area snapshot record and the ETC transaction record, and the problem of mistaken identification of the low-speed vehicle caused by the fact that the vehicle enters the service area is solved. 2) The method has the advantages of low calculation amount and low calculation amount compared with a neural network and other deep learning algorithms, and the method is suitable for early warning of low-speed vehicles in real time due to the extremely low calculation amount. 3) Compared with the deep learning method, the statistical method has strong interpretability, and can provide clear theoretical basis for management staff.
Drawings
The invention is described in further detail below with reference to the drawings and detailed description;
FIG. 1 is a flow chart of the present invention for identifying the traffic speed characteristics of a section;
FIG. 2 is a flow chart of the low speed driving behavior recognition according to the present invention;
FIG. 3 is a schematic diagram of a smaller S-function;
fig. 4 is a schematic diagram of a front 10 low-speed risk behavioural vehicle.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application.
As shown in one of fig. 1 to 4, the invention discloses a low-speed vehicle grading early warning method oriented to a highway scene, which specifically comprises the following steps:
step 1) data acquisition and preprocessing, namely acquiring and fusing all ETC portal data in real time by utilizing a big data technology, wherein the data acquisition and preprocessing comprises the following data:
ETC system transaction data, which is a vehicle passing record collected by the ETC charging system on the expressway, comprising information of entering and exiting the toll station. Can be defined as vehicle track data The portal track formed by the vehicle through the segment QD is referred to asThe definition expression is as follows:
;
Wherein the method comprises the steps of Representing vehicle trajectory dataIs used for the starting point of (a),Representing vehicle trajectory dataIs a terminal point of (c).
ETC service area data, namely a snapshot discipline of the vehicle entering and exiting the service area, comprising vehicle license plate information, time of the vehicle entering and exiting the service area, longitude and latitude of the service area and service area name.
;
;
Wherein, the Representing the entire service area data set,Snapshot data representing the service area s,For the minimum snap shot unit data of the service area s,Representing the number of unit data of the snapshot; Representing a license plate; is the trip id of the vehicle; indicating the time of entry into the service area; Showing the time of the service area;
highway section QD, namely, portal frames of the highway, entrance and exit of toll station (including entrance and exit of cross province) are commonly called as nodes, two adjacent nodes form a highway section QD, namely, a section for short, and the expression form is shown as follows
;
Wherein QD is highway section, node1 is section start point, node2 is section end point.
And 2) excavating traffic speed characteristics of the expressway section, namely establishing a section traffic speed characteristic identification algorithm according to the running speeds of vehicles of different vehicle types of the expressway under the conditions of different sections, excavating traffic speed characteristics of the vehicles in the section traffic speed characteristic identification algorithm, and obtaining a section traffic speed characteristic data set.
Because the driving behaviors have space regularity and time variability, the dangerous degree that the vehicles run on different sections of the expressway with the same driving behaviors is different, and the speed limit is also different for different types of vehicles, and the corresponding speed limit information is not invariable, the invention establishes a section passing speed characteristic recognition algorithm according to the running speeds of vehicles of different vehicle types on the expressway under the conditions of different sections, and mines the passing speed characteristics of the vehicles in the section passing speed characteristic data set to obtain the driving behavior characteristics of the vehicles more flexibly. The specific process is as follows:
1) Because the travel of the expressway is constrained by time, the expressway mainly comprises factors such as the early and late peaks, weather conditions and the like, the data sets are classified according to the hours, so that the time characteristics are extracted more effectively, and the data can be classified into 24 types. Road segment speeds for different time periods as a whole.
2) According to national regulations, vehicles currently traveling on highways are classified into 18 categories, and specific classifications are shown in table 1.
Table 1 vehicle classification table
Different vehicle types have different passing speeds on the same road, so that on the basis of dividing a data set based on hours, data are divided according to the vehicle types vehclass, and the problem of different passing speeds of different vehicle types can be effectively solved by finely dividing the vehicle types.
3) The traffic speed of different sections may also be different due to the problems of external conditions such as the number of lanes, road conditions, etc. of the expressway vehicle driving behavior. Thus, according to the space regularity, the data set is based on the vehicle track dataThe traffic data sets are classified into different sections, so that the spatial regularity of the vehicle is deeply excavated.
4) According to the divided data set and the portal distance matrix D, the passing time of the vehicles in the target section is extracted through the data set, the passing distance of the target section is extracted through the distance matrix D, and the running speeds of all the vehicles in the data set are calculated by using a sensorless speed measuring model.
The process of calculating QD distance with Goldmap API includes first extracting communicated portal in adjacent matrix G,) The accurate portal position is obtained by using the portal positioning method,. The portal geographical location is entered into the hadamard map API to obtain the actual travel distance of the highway QDs.
In order to effectively store and determine the actual travel distance of QDs, the present invention constructs a gantry distance matrix D,For the distance between the i portal and the j portal, if the two portals are communicated, dis is the distance between the two portals, if the two portals are the same node, 0, and the distance between the non-communicated nodes is inf, wherein the calculation formula is shown in the following formula 1, and a matrix is constructed as shown in the table 2.
(1);
TABLE 2 distance matrix
5) In order to calculate the average speed of the road, an arithmetic average method is used to effectively remove the maximum value in the data set, so that the speed is calculated more accurately, and the average speed formula for calculating different vehicle types is shown as follows.
;
Wherein, the For vehicle typeThe average speed of the vehicle p in the middle,For vehicle typeIs a combination of the total number of vehicles,For vehicle typeAverage speed of (c);
TABLE 3 average travel speeds for different vehicle types
For the estimation of the road traffic speed, the average speed of the vehicle passing through the section in a certain time range is generally taken as an estimated value, so that the estimation accuracy can be effectively improved by reducing the abnormal value. However, the above-mentioned method can only effectively remove larger abnormal values, and cannot effectively remove the vehicle running speed similar to the situation of stopping in a service area and the like.
The data cleaning model based on the box diagram is characterized in that outlier abnormal data except the upper edge and the lower edge are required to be deleted, so that excessive or insufficient speed caused by unexpected situations or entering into a service area can be effectively removed, and then the average value of all vehicle driving speeds is calculated by using the following formula as the passing speed of a roadThereby more accurately and effectively approaching the true value.
;
Wherein the method comprises the steps ofRepresenting vehicles travelling on the road section,Representing the total vehicle for that road segment.
Adding the traffic speed of the road to the highway section traffic speed feature data setIn order to further eliminate the influence of the vehicle entering the service area, the influence of the service area is eliminated through the following snapshot technology and ETC data fusion technology.
Step 3) processing abnormal data of service area, namely obtaining the data of the service areaAnd vehicle track dataCalculating a time difference of the vehicle passing through the service area and updating the vehicle track dataThe passing time length data of the service area is eliminated to the track data of the vehicleInterference in time;
Specifically, service area is extracted from service area data Is matched through the service areaIs a vehicle of (2)Track data of (a) to calculate a vehicleTime difference between entering and exiting service area, updating vehicleThrough the service areaSection of the placeAnd updating the time difference to the traffic duration (excluding the service area residence time)In the track passing duration data of the vehicle, the interference on the calculation of the speed of the vehicle is avoided.
And 4) judging that the low-speed vehicle has great influence on road safety in the low-speed driving of the expressway. The invention thus proposes a highway low-speed driving behavior feature recognition algorithm,
1) Based on vehicle trajectory dataAnd the portal distance matrix D established above to obtain the zone running distance of the vehicleAnd journey passing time, calculating the section running speed of the vehicle by using the sensorless speed measurement modelThe calculation formula is shown below.
;
2) Speed of vehicle passingAnd (3) withUnder the same traffic conditionsAnd comparing to judge whether the overspeed driving behavior exists in the vehicle. When (when)If so, judging that the low-speed driving behavior exists and recording the current traffic information, otherwise, 0.8And if so, judging that the vehicle does not have low-speed driving behavior.
3) Judging the vehicle track data after traversingAnd outputting the low-speed information of the vehicle.
Step 5) grading and scoring early warning of the low-speed vehicle, wherein the method adopts the larger and smaller types of the S-shaped membership function as a driving behavior risk degree quantization model, the function diagram is shown in figure 2, and the low-speed running uses the smaller type membership function.
As shown in FIG. 3, the membership function is divided into four parts, the first part is smoother, the second part starts to fall steeply, the third part falls slowly, and the fourth part is parallel to the x-axis. The reason for selecting the membership function of the type is summarized in that when the speed is in a reasonable interval range, the membership function is not basically affiliated to dangerous driving behaviors, the penalty factor is smaller at the moment, and when the speed is continuously reduced, the penalty factor is increased, the curve is steeper, the function value is continuously increased, and finally the value reaches 1. Meanwhile, the membership function quantifies the dangerous degree of dangerous driving to the interval range of [0,1], so that the risk level quantification of driving behaviors is effectively realized.
Through the above highway vehicle running characteristic analysis, the membership function is specifically determined by combining the membership function selected above, and the low-speed membership of the vehicle is calculated and calculated:
;
wherein, the The highway section traffic speed feature data set is the same road traffic speed as the current situation.
As shown in the formula, the membership function for low-speed driving behavior is divided into four parts. The latest outbound traffic method determines that the low-speed running is not classified, and only the vehicles lower than the specified speed limit are uniformly processed, so that the invention establishes a classification standard according to the overspeed running rule. The method includes a first section for considering normal level when the driving speed of the motor vehicle is greater than 80% of the road traffic level, a second section for calculating the membership of the driving behavior when the driving speed of the motor vehicle is less than or equal to 80% of the road traffic speed and greater than 60% of the road traffic speed, a third section for calculating the membership of the driving behavior when the driving speed of the motor vehicle is less than or equal to 60% of the road traffic speed and greater than 40% of the road traffic speed, and a fourth section for calculating the membership of the driving behavior when the traffic speed of the motor vehicle is less than or equal to 40% of the road traffic speed.
The importance degree of the compared indexes has great influence on the driving safety influence level and the values of elements in the matrix while constructing the judgment matrix.
Table 4 scale table
According to the scale table after layering of driving safety, comparing importance between the bottommost elements, the present invention establishes a judgment matrix r=rij (n×n), as shown in table 5:
Table 5 judgment matrix
Where f1, f2, f3,..fwdarw, fn represent various factors affecting driving behavior safety after classification, and the elements in the matrixThe value of the factor is determined by expert through a scale tableAnd factorsThe importance of the two results in a corresponding importance scale (e.g.,Factor ratioThe factors are obviously importantThe scale value of (c) is 5,Scale value of 1/5). The table classifies the importance scale of an element into 1-9, the larger the importance scale, the more important the element is relative to another element. In order to further determine the weight of the vehicle and facilitate calculation, the column vector of the matrix R is normalized to obtain a matrix after normalizationThe results are shown in Table 6. Finally calculate the matrixThe mean value of the middle row vectors of (2) to obtain row vectorsAs shown in the following formula, as a weight vector of an element.
Table 6 judgment matrix after normalization
Wherein, the The values representing the elements of row 2 and column 1 of the judgment matrix, i.e. in Table 5A value; Representing judgment matrix Line 1The values of the elements of the columns, i.e. in Table 5A value;
(2)
wherein, the Values representing elements of the 1 st row and 1 st column of the normalized judgment matrix; Normalized judgment matrix Values of elements of row 1 and column 1;
after determining the weights of the different driving behaviors, the driving safety of a certain journey of the vehicle needs to be calculated according to the calculated weights. The invention provides a section driving behavior scoring model, and a calculation formula is shown as the following formula.
;
Wherein, the Representing a segment driving behavior score for the vehicle, a is a collection of vehicles for dangerous driving behaviors occurring within the segment,For the membership of the driving behaviour of the vehicle a,Is the driving behavior weight of the vehicle a in the formula (2).
The present invention classifies the low-speed runs into 4 categories, the classification meaning is shown in table 7 below.
TABLE 7 definition of vehicle driving behavior
| Identification mark | Meaning of |
| 1 | The current journey of the vehicle is a normal journey |
| 2 | The current journey of the vehicle is a slight low-speed journey |
| 3 | The current journey of the vehicle is a medium low-speed risk journey |
| 4 | The current journey of the vehicle is a heavy low-speed risk journey |
In order to effectively verify the validity and reliability of the model, the present invention converts the above scoring results into 4 types in the table using the following formula:
;
where x represents the score obtained by the above evaluation model and C (x) represents the classification result.
And the grading classification early warning of the low-speed vehicles is realized through different grading results.
The algorithm effect evaluation is carried out on the sections from 9 in 2024 to 12 in 2024, and 2862 low-speed behaviors of 124 vehicles are monitored, wherein the first 10 serious low-speed risk vehicles are shown in fig. 4.
The invention is particularly suitable for automatically identifying low-speed risk vehicles and carrying out safety early warning under severe weather (such as typhoons, heavy rain and the like) scenes.
By adopting the technical scheme, the invention combines ETC portal data, road network topological structure, service area snapshot data and the like through intelligent data processing and algorithm, judges the detained vehicles in real time and carries out accurate identification. And according to factors such as conditions of different vehicle types, road sections and the like, a flexible low-speed time threshold is designed, so that the low-speed vehicle can be accurately identified under different road sections. After the vehicles are detained and identified, the system automatically generates early warning information, and timely sends an alarm to traffic management departments and emergency rescue workers, so that support is provided for accurate rescue and safety guarantee.
Compared with the prior art, the invention has the advantages that 1) a great amount of false alarms are avoided by utilizing the service area information, the filtering of the low-speed vehicle which enters the service area and is mistakenly identified is realized by utilizing the fusion of the service area snapshot record and the ETC transaction record, and the problem of mistaken identification of the low-speed vehicle caused by the fact that the vehicle enters the service area is solved. 2) The method has the advantages of low calculation amount and low calculation amount compared with a neural network and other deep learning algorithms, and the method is suitable for early warning of low-speed vehicles in real time due to the extremely low calculation amount. 3) Compared with the deep learning method, the statistical method has strong interpretability, and can provide clear theoretical basis for management staff.
It will be apparent that the described embodiments are some, but not all, embodiments of the application. Embodiments of the application and features of the embodiments may be combined with each other without conflict. The components of the embodiments of the present application generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the detailed description of the embodiments of the application is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Claims (6)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510475495.1A CN120014839B (en) | 2025-04-16 | 2025-04-16 | A low-speed vehicle graded warning method for highway scenarios |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510475495.1A CN120014839B (en) | 2025-04-16 | 2025-04-16 | A low-speed vehicle graded warning method for highway scenarios |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN120014839A CN120014839A (en) | 2025-05-16 |
| CN120014839B true CN120014839B (en) | 2025-07-18 |
Family
ID=95664365
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202510475495.1A Active CN120014839B (en) | 2025-04-16 | 2025-04-16 | A low-speed vehicle graded warning method for highway scenarios |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN120014839B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN121214714A (en) * | 2025-12-01 | 2025-12-26 | 贵州智通天下信息技术有限公司 | Road early warning method and system integrating ETC and vehicle terminal data |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118629215A (en) * | 2024-08-05 | 2024-09-10 | 浙江之江智能交通科技有限公司 | Method, system and computer equipment for active control of slow vehicles in highway classification |
| CN118747957A (en) * | 2024-06-25 | 2024-10-08 | 浙江鸿程计算机系统有限公司 | A method for identifying low-speed vehicles on highways |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110190972A1 (en) * | 2010-02-02 | 2011-08-04 | Gm Global Technology Operations, Inc. | Grid unlock |
| US9988047B2 (en) * | 2013-12-12 | 2018-06-05 | Magna Electronics Inc. | Vehicle control system with traffic driving control |
| CN109035819B (en) * | 2018-07-27 | 2020-12-22 | 南通大学 | A regional traffic situation perception method based on fog computing |
| CN111615053B (en) * | 2020-05-22 | 2022-06-17 | 英华达（上海）科技有限公司 | Internet of vehicles system and method for dynamically marking risk areas |
| CN114725543B (en) * | 2022-03-25 | 2025-10-10 | 上汽大众汽车有限公司 | A power battery thermal management method and system based on driver intention recognition |
| CN114999181B (en) * | 2022-05-11 | 2023-12-19 | 山东高速建设管理集团有限公司 | Highway vehicle speed abnormality identification method based on ETC system data |
| CN116331104A (en) * | 2022-12-26 | 2023-06-27 | 北京清丰智行科技有限公司 | A pedestrian warning method and system for low-speed electric unmanned vehicles in parks based on fuzzy control |
| CN117133115A (en) * | 2023-07-12 | 2023-11-28 | 福建理工大学 | A method for detecting potentially dangerous vehicles beyond visual range behind highways |
| CN117351726B (en) * | 2023-12-06 | 2024-03-12 | 山东科技大学 | A highway incident early warning system and comprehensive sensing method |
| CN118343153A (en) * | 2024-04-12 | 2024-07-16 | 江西通慧科技集团股份有限公司 | Vehicle curve safety warning monitoring method, device and system |
| CN118443038A (en) * | 2024-04-16 | 2024-08-06 | 武汉理工大学 | Vehicle lane change obstacle avoidance trajectory planning method, system, electronic equipment and storage medium |
-
2025
- 2025-04-16 CN CN202510475495.1A patent/CN120014839B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118747957A (en) * | 2024-06-25 | 2024-10-08 | 浙江鸿程计算机系统有限公司 | A method for identifying low-speed vehicles on highways |
| CN118629215A (en) * | 2024-08-05 | 2024-09-10 | 浙江之江智能交通科技有限公司 | Method, system and computer equipment for active control of slow vehicles in highway classification |
Also Published As
| Publication number | Publication date |
|---|---|
| CN120014839A (en) | 2025-05-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113436432A (en) | Method for predicting short-term traffic risk of road section by using road side observation data | |
| KR102477885B1 (en) | Safety analysis management server for evaluating autonomous driving roads | |
| WO2020244288A1 (en) | Method and apparatus for evaluating truck driving behaviour based on gps trajectory data | |
| CN109191861B (en) | A system and method for detecting abnormal behavior of expressway toll evasion vehicles based on video detector | |
| CN114999181A (en) | ETC system data-based highway vehicle speed abnormity identification method | |
| CN114091581B (en) | Sparse track-based vehicle operation behavior type identification method | |
| CN120014839B (en) | A low-speed vehicle graded warning method for highway scenarios | |
| CN116092037B (en) | Vehicle Type Recognition Method Fused with Trajectory Space-Semantic Features | |
| CN117037464A (en) | Highway fatigue driving early warning management method based on multi-source data fusion analysis | |
| CN106910334A (en) | A kind of method and device that section situation is predicted based on big data | |
| CN120573114A (en) | A safe driving assessment method and system based on Beidou navigation | |
| CN119418527A (en) | Vehicle guidance method and system for unmanned highway | |
| CN119169825A (en) | A 5G-based smart city construction traffic intelligent monitoring and control system | |
| CN116246229B (en) | Riding state monitoring system and method based on Internet of vehicles | |
| CN120726807B (en) | Highway road condition intelligent monitoring and early warning system based on multisource sensor fusion | |
| CN115440071B (en) | Automatic driving illegal parking detection method | |
| CN116753938A (en) | Vehicle test scene generation method, device, storage medium and equipment | |
| CN120340256B (en) | Traffic conflict recognition method and system for road interleaving area | |
| CN120183189A (en) | A method for identifying and managing vehicle risk overspeeding areas | |
| CN119741835A (en) | A profiling method for vehicles suspected of occupying emergency lanes based on highway ETC and license plate recognition data | |
| CN113128847A (en) | Entrance ramp real-time risk early warning system and method based on laser radar | |
| CN117575326A (en) | Portal frame and emergency data-based vehicle safety index evaluation method | |
| CN117133115A (en) | A method for detecting potentially dangerous vehicles beyond visual range behind highways | |
| CN114822042A (en) | Information security test management system and method for vehicle-mounted terminal detection | |
| CN113112803A (en) | Urban traffic road traffic flow data acquisition and analysis processing system based on video monitoring |
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 |