CN116740944B - Driving safety early warning method, device and storage medium in road tunnel - Google Patents

Driving safety early warning method, device and storage medium in road tunnel Download PDF

Info

Publication number
CN116740944B
CN116740944B CN202311003583.9A CN202311003583A CN116740944B CN 116740944 B CN116740944 B CN 116740944B CN 202311003583 A CN202311003583 A CN 202311003583A CN 116740944 B CN116740944 B CN 116740944B
Authority
CN
China
Prior art keywords
vehicle
data
track data
tunnel
road
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
Application number
CN202311003583.9A
Other languages
Chinese (zh)
Other versions
CN116740944A (en
Inventor
杨榆璋
陈金宏
刘晔
赵伟
罗方
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Yunnan Communications Investment & Construction Group Co ltd
Original Assignee
Yunnan Communications Investment & Construction Group Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Yunnan Communications Investment & Construction Group Co ltd filed Critical Yunnan Communications Investment & Construction Group Co ltd
Priority to CN202311003583.9A priority Critical patent/CN116740944B/en
Publication of CN116740944A publication Critical patent/CN116740944A/en
Application granted granted Critical
Publication of CN116740944B publication Critical patent/CN116740944B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0125—Traffic data processing
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/86—Combinations of radar systems with non-radar systems, e.g. sonar, direction finder
    • G01S13/867—Combination of radar systems with cameras
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/88—Radar or analogous systems specially adapted for specific applications
    • G01S13/91—Radar or analogous systems specially adapted for specific applications for traffic control
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G06T7/277—Analysis of motion involving stochastic approaches, e.g. using Kalman filters
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/766—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using regression, e.g. by projecting features on hyperplanes
    • 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
    • G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
    • G08G1/0141—Measuring and analyzing of parameters relative to traffic conditions for specific applications for traffic information dissemination
    • 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
    • G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
    • G08G1/0145—Measuring and analyzing of parameters relative to traffic conditions for specific applications for active traffic flow control
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10016—Video; Image sequence
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30241—Trajectory
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/08—Detecting or categorising vehicles
    • 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

Abstract

The application provides a traffic safety early warning method, equipment and a storage medium in a road tunnel, which belong to the technical field of tunnel traffic control and comprise the steps of acquiring radar data and video data in the tunnel; the radar data includes vehicle first trajectory data; the video data is input into a model algorithm to obtain second track data of the vehicle; correcting the track data based on the first track data and the second track data of the vehicle to obtain corrected track data of the vehicle; and evaluating irregular behavior rates of road section units based on the corrected vehicle track data and executing a risk plan. By combining the advantages of the radar data acquisition equipment and the video data acquisition equipment, accurate vehicle track data are obtained, and safety early warning accuracy is improved.

Description

Driving safety early warning method, device and storage medium in road tunnel
Technical Field
The application relates to the technical field of tunnel traffic control, in particular to a traffic safety early warning method, traffic safety early warning equipment and a storage medium in a road tunnel.
Background
Relatively narrow tunnel and complex traffic running condition, and once accidents happen, cliff-like decline of traffic efficiency is caused, even serious casualties are caused, and rescue difficulty is extremely high; secondly, ventilation conditions in the longitudinal depth of the tunnel are poor, smoke is often accompanied, vibration occurs, a single video detection system cannot play an ideal effect, and a single radar system cannot achieve the purpose of intelligent traffic control due to the problems of wall reflection of the tunnel, loss of detailed information of specific events and the like.
Patent with bulletin number of CN113850995B discloses an event detection method, device and system based on tunnel radar data fusion, wherein a decision-level fusion is carried out through a fusion algorithm of detection frame crossing ratio based on radar data detection targets and video data detection targets to obtain a target fusion result; according to the target fusion result, traffic event detection judgment is carried out to obtain a traffic event detection result; and judging whether a traffic event occurs or not by analyzing the fused traffic characteristic information, outputting the type of the traffic event to perform event early warning, and improving the detection precision of the traffic event. However, the patent does not explicitly disclose a way to fuse video data with radar data to improve the accuracy of data detection.
Disclosure of Invention
The application aims to provide a traffic safety early warning method, equipment and a storage medium in a road tunnel, which are used for obtaining accurate vehicle track data by combining the advantages of radar data acquisition equipment and video data acquisition equipment, so that the safety early warning accuracy is improved.
The application provides a traffic safety pre-warning method in a road tunnel, which comprises the following steps: acquiring radar data and video data in a tunnel; the radar data includes vehicle first trajectory data; the video data is input into a model algorithm to obtain second track data of the vehicle; correcting the track data based on the first track data and the second track data of the vehicle to obtain corrected track data of the vehicle; and evaluating irregular behavior rates of road section units based on the corrected vehicle track data and executing a risk plan.
Further, the first track data and the second track data of the vehicle comprise a vehicle number and a forward speed and a lateral speed of the vehicle on a road surface based on a time stamp.
Further, the correcting the track data based on the first track data and the second track data of the vehicle to obtain corrected track data of the vehicle includes:
；
wherein, the liquid crystal display device comprises a liquid crystal display device,and->The speed of the vehicle in the x and y directions at the moment t is the node i, and the x direction is the vehicle advancing direction; the y direction is the transverse movement direction of the vehicle; />And->The speed of the vehicle along the x and y directions at the time t is the first track data of the node i; />And->The speed of the vehicle along the x and y directions at the time t is the second track data of the node i;and->The distance that the vehicle travels in the x direction at the time t and the limit distance that the vehicle travels in the x direction are the nodes i; />Andthe distance of the vehicle running in the y direction at the time t and the limit distance of the vehicle running in the y direction are the nodes i; />And->The minimum resolution of the video data acquisition device at the node i in the x and y directions is obtained; />And->Is the minimum resolution in the x and y directions of the radar at node i.
Further, based on TTCs of adjacent vehicles in the tunnel, the irregular behavior rate of the road section is periodically estimated;
；
the irregular behaviour rate R is the ratio of the medium to the severe sum of the road segment units to the light, medium and severe sum.
Further, the video data is tracked through KCF prediction and tracking and Kalman filtering to obtain track data; when a vehicle is blocked, tracking the blocked vehicle by adopting Kalman filtering tracking; and when the vehicle is missed, adopting KCF predictive tracking to track the missed vehicle.
Further, the method further comprises the step of obtaining a congestion risk index of the vehicle through a 3D convolutional neural network model based on the video data; obtaining traffic flow data in the tunnel based on KCF predictive tracking and Kalman filtering tracking; mining historical traffic flow data similar to the traffic flow data through a KNN calculation model and predicting traffic flow data of road section units in a preset future time; according to the predicted traffic flow data, predicting the accident rate through a conditional logistic regression model; when the predicted accident rate P is more than or equal to 0.5, the accident risk index is first-order; the accident risk index is second-order when the predicted accident rate P is less than 0.5; and determining risk early warning and executing corresponding risk plans according to different scenes, congestion risk indexes, accident risk indexes and/or irregular behavior rates of the tunnel.
Further, the risk plan includes: four-stage planning: issuing traffic real-time information and reminding information; three-stage planning: on the basis of a four-level plan, ramp control, toll station current limiting and warning or prohibition information release are added; secondary protocol: on the basis of a three-level plan, the coordination control of the tunnel and the intersection of the adjacent tunnels is increased; first-level planning: on the basis of the secondary plan, the coordination control of the tunnel and the peripheral road network is increased.
Further, according to the traffic operation prediction data and the maximum queuing length dataSolving the following equation expression to obtain the toll station current limit value +.>：
；
In the above-mentioned method, the step of,the number of vehicles in the accident road section at the initial moment; />The average vehicle density in the road section at the initial time; />Distance from the incident location to the upstream section; />The number of vehicles driven out from the accident site at the representative moment t; m is the original number of lanes of the road section; />The average blocking vehicle density, i.e., the number of vehicles is converted to an average vehicle density equivalent to the queuing length.
The application also provides traffic safety early warning equipment in the road tunnel, which comprises: a memory and a processor; the memory is used for storing a computer program; the processor is configured to execute the computer program for implementing the above method.
The application also provides a computer readable storage medium storing a computer program for implementing the above method when the computer program is executed by a processor.
The method, the device and the storage medium for the traffic safety pre-warning in the road tunnel provided by the application are well known that the accurate parameter acquisition is the basis for making the traffic safety pre-warning, the accuracy of the ultrasonic detection of the moving object with low speed is poor, the camera is easy to shield the moving object with long detection distance, and the detection effect is poor due to the influence of automobile tail gas, dust and vibration in the tunnel. Compared with the prior art, the method combines the first track data generated by the radar data, corrects the first track data and the second track data by the second track data calculated by the video data to obtain corrected vehicle track data, combines the advantages of the radar data acquisition equipment and the video data acquisition equipment in the above manner to obtain accurate vehicle track data, and improves the safety early warning accuracy; secondly, the application sets different risk plans aiming at various scenes and provides a calculation mode of the current limiting value in the risk plans.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present application, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a traffic safety early warning method in a road tunnel provided by an embodiment of the application;
FIG. 2 is a diagram of a convolutional layer of a 3D convolutional neural network model according to an embodiment of the present application;
FIG. 3 is a schematic diagram of a result calculated by a 3D convolutional neural network model according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application;
reference numerals: 10-memory; 11-a processor; 12-a display; 13-a power supply assembly; 14-an audio component; 15-communication component.
Detailed Description
The technical solutions of the present application will be clearly and completely described in connection with the embodiments, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments. 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.
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, 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, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, based on the embodiments of the application, which are apparent to those of ordinary skill in the art without inventive faculty, are intended to be within the scope of the application. Thus, the following detailed description of the embodiments of the application, as presented in the figures, 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, based on the embodiments of the application, which are apparent to those of ordinary skill in the art without inventive faculty, are intended to be within the scope of the application.
In the present application, unless explicitly specified and limited otherwise, the terms "mounted," "connected," "secured," and the like are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communicated with the inside of two elements or the interaction relationship of the two elements. The specific meaning of the above terms in the present application can be understood by those of ordinary skill in the art according to the specific circumstances. Furthermore, the terms "first," "second," "third," and the like are used merely to distinguish between descriptions and should not be construed as indicating or implying relative importance.
In the present application, unless expressly stated or limited otherwise, a first feature may include first and second features directly contacting each other, either above or below a second feature, or through additional features contacting each other, rather than directly contacting each other. Moreover, the first feature being above, over, and on the second feature includes the first feature being directly above and obliquely above the second feature, or simply indicating that the first feature is higher in level than the second feature. The first feature being below, beneath, and beneath the second feature includes the first feature being directly below and obliquely below the second feature, or simply indicates that the first feature is less level than the second feature.
The application provides a traffic safety early warning method in a road tunnel, as shown in figure 1, comprising the following steps: acquiring radar data and video data in a tunnel; the radar data includes vehicle first trajectory data; the video data is input into a model algorithm to obtain second track data of the vehicle; correcting the track data based on the first track data and the second track data of the vehicle to obtain corrected track data of the vehicle; and evaluating irregular behavior rates of road section units based on the corrected vehicle track data and executing a risk plan.
It can be understood that the radar data are acquired through an ultrasonic radar and/or a millimeter wave radar, the video data are acquired based on a high-definition camera and/or a high-speed camera, and the radar and the camera are arranged on the same section and jointly measure traffic flow data or track data of the same road section unit.
Specifically, the first track data and the second track data of the vehicle comprise a vehicle number and the forward speed and the transverse speed of the vehicle on the road surface based on the time stamp.
；
Wherein, the liquid crystal display device comprises a liquid crystal display device,and->The speed of the vehicle in the x and y directions at the moment t is the node i, and the x direction is the vehicle advancing direction; the y direction is the transverse movement direction of the vehicle; />And->The speed of the vehicle along the x and y directions at the time t is the first track data of the node i; />And->The speed of the vehicle along the x and y directions at the time t is the second track data of the node i;and->The distance that the vehicle travels in the x direction at the time t and the limit distance that the vehicle travels in the x direction are the nodes i; />Andthe distance of the vehicle running in the y direction at the time t and the limit distance of the vehicle running in the y direction are the nodes i; />And->The minimum resolution of the video data acquisition device at the node i in the x and y directions is obtained;/>and->Is the minimum resolution in the x and y directions of the radar at node i.
It should be noted that a single camera and radar form a group, which is arranged in the tunnel, and a plurality of groups of cameras and radars are required to be arranged in the tunnel, and each group is a node; wherein the method comprises the steps ofFor the extreme position of the vehicle operation, i.e. the length of the road section unit,/->Calculating a distance traveled in the x-direction at time t for the vehicle from the specified position; />For the extreme position of the vehicle running, i.e. the width of the road segment unit, i.e. the total width of the lane perpendicular to the direction of travel of the vehicle,/->Calculating a distance offset in the y direction at time t for a specified side; />And->And +.>And->For the minimum resolution that can be calculated on the basis of the video data or radar data, i.e. at which the radar data or video data is valid, the value is determined on the basis of the physical parameters of the camera and the radar. In the present application->And->The values are the same, and->And->The values are the same.
Evaluating irregular behavior rates of road segment units and executing a risk plan based on the corrected vehicle trajectory data, comprising: periodically evaluating irregular behavior rates of road segments based on TTC (Time To Collision) of neighboring vehicles within the tunnel;
；
the irregular behavior rate is the ratio of the medium and serious sum to the light, medium and serious sum of road section units, and represents the proportion of the irregular behavior in the tunnel; for example, slightly 5 times, moderately 1 time, and severely 1 time, the irregular behavior ratio is (1+1)/(5+1+1).
Specifically, each evaluation period is periodically evaluated to be 2min in duration, the interval time between every two adjacent periods is 5min, TTCs can be generated between every two vehicles at each moment in the radar detection range, in order to ensure the validity of data, the TTCs of the two adjacent vehicles before and after each 0.5s are calculated in one evaluation period, and the minimum TTC obtained in one period is recorded as the TTCs of the two adjacent vehicles in the period.
In the above, value 1 ，value 2 And value 3 The corresponding value can be set based on a specific tunnel, which can be set by an expert scoring method, or can be determined based on the corresponding relation between the value and the accident rate, wherein the value is in the application 1 1.2s, value 2 3.0s, value 3 4.2s.
The calculation formula of TCC is as follows:
；
；
in the above formula, wherein,is the distance between the x and y directions at node i; />And->The speeds of the first vehicle and the second vehicle in the x and y directions at node i.
The TTC indicates that braking measures are not taken on the premise that the current speed of the first vehicle and the current speed of the second vehicle are kept unchanged, and the time from the occurrence of the accident is shortened.
The video data is input into a model algorithm to obtain second track data of the vehicle, which comprises the following steps: the video data is subjected to KCF predictive tracking and Kalman filtering tracking to obtain second track data; when the vehicle is blocked, tracking the blocked vehicle by adopting Kalman filtering tracking to form second track data; and when the vehicle is missed, adopting KCF predictive tracking to track the missed vehicle, and forming second track data. Specifically, the KCF prediction tracking has high tracking precision under the condition that the target scale is unchanged, and the prediction speed block is circularly acquired through a tracker template, so that the response corresponding to each sampling area is obtained through optimization processing, but when the KCF predicts the position of a shielding missed detection target, error information is introduced into the tracker due to continuous updating of the tracking template due to a process from incomplete information to information loss to gradual recovery of the information during shielding, so that tracking failure is caused; therefore, kalman filtering tracking is introduced, and Kalman filtering is used for predicting the target position, so that mismatching caused by continuous updating of a tracking template can be avoided.
The traffic safety early warning method in the road tunnel provided by the application further comprises the steps of obtaining the congestion risk index of the vehicle through a 3D convolutional neural network model based on the video data; obtaining traffic flow data in the tunnel based on KCF predictive tracking and Kalman filtering tracking; mining historical traffic flow data similar to the traffic flow data through a KNN calculation model and predicting traffic flow data of road section units in a preset future time; according to the predicted traffic flow data, predicting the accident rate through a conditional logistic regression model; when the predicted accident rate P is more than or equal to 0.5, the accident risk index is first-order; the accident risk index is second-order when the predicted accident rate P is less than 0.5; and determining risk early warning and executing corresponding risk plans according to different scenes, congestion risk indexes, accident risk indexes and/or irregular behavior rates of the tunnel.
In the application, the 3D convolutional neural network model uses the convolutional depth d=1, namely the video frame number of each convolutional participation operation is 4, and each convolutional layer uses the convolutional check of 1X3X3The convolution is carried out on (k frame image), the convolution step length of the convolution kernel is 1, the precision requirement of video feature extraction can be met by adopting 4 convolution layers and 3 pooling layers, the specific convolution layer structure is shown in fig. 2, the pictures are preprocessed, 5000 pictures are used as training sets, 2300 pictures are used as verification sets, the calculated result based on the 3D convolution neural network model provided by the application is shown in fig. 3, and P in the figure is shown in the figure r In order to judge the probability, namely the probability of judging in the states of smoothness, creep and congestion, in the calculation mode, the standard defining the smoothness is that no more than 6 vehicles exist in the map; the standard of the jogging is that the number of the pictures exceeds 6 but not more than 10 vehicles; the congestion standard is that more than 10 vehicles are in the map, and the 3D convolutional neural network model provided by the application can be well matched with the condition of a real state label, so that the model is effective. In this embodiment, the congestion risk index includes four levels, and the matching relationship thereof is shown in table 1.
Table 1 congestion risk index classification
Congestion magnitude Congestion risk index
[0，4） Four-stage
[4，6） Three stages
[6，8） Second-level
[8，10） First level
That is, the congestion value is four-level when 0-4 vehicles are used, three-level when the congestion value is greater than or equal to 4 and less than 6 vehicles are used, two-level when the congestion value is greater than or equal to 6 and less than 8 vehicles are used, and one-level when the congestion value is greater than or equal to 8 vehicles is used, and it should be noted that the congestion risk index is the number of vehicles appearing in the video shot aiming at the present application, and a proper congestion value can be selected as the grading of the congestion risk index based on the actual condition of the video.
The traffic flow data in the tunnel comprises queuing length, vehicle flow, vehicle density, vehicle speed, road occupancy and the like.
The scene of the tunnel includes:
(1) Traffic accident scene, acquiring traffic flow data based on the radar data and the video data, wherein the traffic flow data comprises positions, congestion risk indexes, the number of occupied lanes, vehicle flow, vehicle density and vehicle speed; predicting traffic parameters based on the traffic flow data, wherein the predicted traffic parameters comprise vehicle flow, vehicle speed, vehicle density and queuing length within 5 minutes in the future; the risk plan is determined based on the queuing length, and a congestion risk index.
In this scenario, the risk plans include a primary plan, a secondary plan, a tertiary plan, and a quaternary plan.
(2) A non-event scene, acquiring traffic flow data based on the radar data and the video data, wherein the traffic flow data comprises vehicle speed, congestion risk index, vehicle flow, travel time and vehicle density; predicting traffic parameters based on the traffic flow data, wherein the predicted traffic parameters comprise vehicle flow, vehicle speed and vehicle density within 5 minutes in the future; determining an accident risk index based on the predicted traffic parameters; the risk plan is determined based on the congestion risk index and the accident risk index.
In this scenario, the risk plans include a primary plan, a secondary plan, a tertiary plan, and a quaternary plan.
(3) Special task scenes including travel demands, wherein the traffic flow data includes vehicle flow and path selection; and predicting traffic parameters based on the traffic flow, the path selection and the travel demand, predicting the traffic flow of the travel demand time period, and determining the risk plan based on the congestion risk index and the predicted traffic flow.
In this scenario, the risk plan includes a three-level plan and a four-level plan.
It should be noted that, in the special task scenario, the government authorities issue corresponding travel demands and travel demand time period information. And selecting a corresponding path based on the road decision.
(4) And acquiring traffic flow data based on the radar data and the video data, wherein the traffic flow data comprises a congestion risk index and an irregular behavior rate, and determining the risk plan based on the congestion risk index and the irregular behavior rate.
In scenario (4), the risk plans include a three-level plan and a four-level plan.
The specific contents of the risk plan include:
four-stage planning: issuing traffic real-time information and reminding information;
three-stage planning: on the basis of a four-level plan, ramp control, toll station current limiting and warning or prohibition information release are added;
secondary protocol: on the basis of a three-level plan, the coordination control of the tunnel and the intersection of the adjacent tunnels is increased;
first-level planning: on the basis of the secondary plan, the coordination control of the tunnel and the peripheral road network is increased.
It can be understood that the influencing plan selection factors corresponding to the above-mentioned scenes determine under what conditions to execute the risk plans one to four based on the weight coefficients, or set the corresponding plan selection modes based on expert scoring. Specifically, the risk plan selection for scenario 1 is shown in table 2:
note that the above L, L, L2 and L3 are queuing lengths, and may be selected based on the specific situation of the tunnel, where L1 is 10m, L2 is 20m and L3 is 40m. And secondly, selecting a plan corresponding to different conditions, and adjusting based on the expert scoring suggestions.
The risk plan selection for scenario 2 is shown in table 3:
and secondly, selecting a plan corresponding to different conditions, and adjusting based on the expert scoring suggestions.
The risk plan selection for scenario 3 is shown in table 4:
it should be noted that V1 and V2 are vehicle flows, and are selected based on the specific conditions of the tunnel, the tunnel in the present application is one-way two lanes, V1 is 2 vehicles/second, and V2 is 5 vehicles/second. And secondly, selecting a plan corresponding to different conditions, and adjusting based on the expert scoring suggestions.
The risk plan selection for scenario 4 is shown in table 5:
it should be noted that R is the irregular behavior rate. And secondly, selecting a plan corresponding to different conditions, and adjusting based on the expert scoring suggestions.
The application also provides a toll station current limiting and algorithm method, in particular to a method for predicting data and maximum queuing length data according to traffic operationSolving the following equation expression to obtain the toll station current limit value +.>：
；
In the above-mentioned method, the step of,the number of vehicles in the accident road section at the initial moment; />The average vehicle density in the road section at the initial time; />Distance from the incident location to the upstream section; />The number of vehicles driven out from the accident site at the representative moment t; m is the original number of lanes of the road section; />The average plug density, i.e., the average vehicle density as a function of the number of vehicles converted to an equivalent queuing length.
Fig. 4 is a schematic structural diagram of an electronic device according to an exemplary embodiment of the present application. The electronic device of the embodiment may be an active traffic management and control device. As shown in fig. 4, the electronic device includes: a memory 10 and a processor 11.
Memory 10 for storing a computer program. A processor 11 coupled to the memory 10 for executing a computer program stored in the memory 10 for:
acquiring radar data and video data in a tunnel; the radar data includes vehicle first trajectory data; the video data is input into a model algorithm to obtain second track data of the vehicle; correcting the track data based on the first track data and the second track data of the vehicle to obtain corrected track data of the vehicle; and evaluating irregular behavior rates of road section units based on the corrected vehicle track data and executing a risk plan.
Further, as shown in fig. 4, the electronic device further includes: a display 12, a power supply component 13, an audio component 14, a communication component 15, and other components. Only some of the components are schematically shown in fig. 4, which does not mean that the computer device only comprises the components shown in fig. 4. In addition, some of the components shown in FIG. 4 are optional components, not necessarily optional components, depending on the product form of the computer device. The computer device in this embodiment may be implemented as a terminal device such as a desktop computer, a notebook computer, or a smart phone, or may be a server such as a conventional server or a cloud server.
Correspondingly, the embodiment of the application also provides a computer readable storage medium storing a computer program, which when being executed by a processor, causes the processor to realize the driving safety early warning method logic in the road tunnel.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the application.

Claims (7)

1. The traffic safety early warning method in the road tunnel is characterized by comprising the following steps of:
acquiring radar data and video data in a tunnel;
the radar data includes vehicle first trajectory data;
the video data is input into a model algorithm to obtain second track data of the vehicle;
correcting the track data based on the first track data and the second track data of the vehicle to obtain corrected track data of the vehicle;
evaluating irregular behavior rates of road section units based on the corrected vehicle track data and executing a risk plan;
the first track data and the second track data of the vehicle comprise a vehicle number and the forward speed and the transverse speed of the vehicle on the road surface based on the time stamp;
the correcting the track data based on the first track data and the second track data of the vehicle to obtain corrected track data of the vehicle comprises the following steps:
wherein v is i,t,x And v i,t,y The speed of the vehicle in the x and y directions at the moment t is the node i, and the x direction is the vehicle advancing direction; the y direction is the transverse movement direction of the vehicle; v 1,i,t,x And v 1,i,t,y The speed of the vehicle along the x and y directions at the time t is the first track data of the node i; v 2,i,t,x And v 2,i,t,y The speed of the vehicle along the x and y directions at the time t is the second track data of the node i; l (L) i,t,x And l i,t,x,0 The distance that the vehicle travels in the x direction at the time t and the limit distance that the vehicle travels in the x direction are the nodes i; l (L) i,t,y And l i,t,y,0 The distance of the vehicle running in the y direction at the time t and the limit distance of the vehicle running in the y direction are the nodes i; f (f) i,v,x And f i,v,y The minimum resolution of the video data acquisition device at the node i in the x and y directions is obtained; f (f) i,r,x And f i,r,y The minimum resolution in the x and y directions for the radar at node i;
wherein l i,t,x,0 The limit position of the vehicle running, namely the length of the road section unit;
l i,t,y,0 the limit position of the vehicle running, namely the width of the road section unit, namely the total width of the lanes perpendicular to the running direction of the vehicle;
based on TTCs of two adjacent vehicles in the tunnel, periodically evaluating irregular behavior rate of the road section;
the irregular behavior rate is the ratio of the sum of the moderate and severe event times of the road section unit to the sum of the slight, moderate and severe event times;
in the above, value 1 1.2s, value 2 3.0s, value 3 4.2s.
2. The traffic safety precaution method in a road tunnel according to claim 1, characterized in that,
video data is tracked through KCF prediction and Kalman filtering to obtain second track data; when the vehicle is blocked, tracking the blocked vehicle by adopting Kalman filtering tracking to form second track data; and when the vehicle is missed, adopting KCF predictive tracking to track the missed vehicle, and forming second track data.
3. The traffic safety pre-warning method in a road tunnel according to claim 2, further comprising obtaining a congestion risk index of a vehicle through a 3D convolutional neural network model based on the video data;
obtaining traffic flow data in the tunnel based on KCF predictive tracking and Kalman filtering tracking;
mining historical traffic flow data similar to the traffic flow data through a KNN calculation model and predicting traffic flow data of road section units in a preset future time;
according to the predicted traffic flow data, predicting the accident rate through a conditional logistic regression model;
when the predicted accident rate P is more than or equal to 0.5, the accident risk index is first-order;
the accident risk index is second-order when the predicted accident rate P is less than 0.5;
and determining risk early warning and executing corresponding risk plans according to different scenes, congestion risk indexes, accident risk indexes and/or irregular behavior rates of the tunnel.
4. The traffic safety precaution method in a road tunnel according to claim 3, characterized in that,
the risk plan includes:
four-stage planning: issuing traffic real-time information and reminding information;
three-stage planning: on the basis of a four-level plan, ramp control, toll station current limiting and warning or prohibition information release are added;
secondary protocol: on the basis of a three-level plan, the coordination control of the tunnel and the intersection of the adjacent tunnels is increased;
first-level planning: on the basis of the secondary plan, the coordination control of the tunnel and the peripheral road network is increased.
5. The traffic safety precaution method in a road tunnel according to claim 4, characterized in that the traffic running prediction data and the maximum queuing length data L are used for the traffic running prediction max (t) solving the following equation expression to obtain the toll station current limiting value Q i (t)：
N c ＝K 0 ·L 0
In the above, N c The number of vehicles in the accident road section at the initial moment; k (K) 0 The average vehicle density in the road section at the initial time; l (L) 0 Distance from the incident location to the upstream section; q (Q) u (t) represents the number of vehicles driven out from the accident site at the moment t; m is the original number of lanes of the road section; k (K) j The average plug density, i.e., the average vehicle density as a function of the number of vehicles converted to an equivalent queuing length.
6. A traffic safety precaution device in a road tunnel, comprising:
a memory and a processor;
the memory is used for storing a computer program;
the processor for executing the computer program for implementing the method of any of claims 1-5.
7. A computer readable storage medium storing a computer program for implementing the method of any one of claims 1-5 when the computer program is executed by a processor.
CN202311003583.9A 2023-08-10 2023-08-10 Driving safety early warning method, device and storage medium in road tunnel Active CN116740944B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311003583.9A CN116740944B (en) 2023-08-10 2023-08-10 Driving safety early warning method, device and storage medium in road tunnel

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311003583.9A CN116740944B (en) 2023-08-10 2023-08-10 Driving safety early warning method, device and storage medium in road tunnel

Publications (2)

Publication Number Publication Date
CN116740944A CN116740944A (en) 2023-09-12
CN116740944B true CN116740944B (en) 2023-10-27

Family

ID=87917200

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311003583.9A Active CN116740944B (en) 2023-08-10 2023-08-10 Driving safety early warning method, device and storage medium in road tunnel

Country Status (1)

Country Link
CN (1) CN116740944B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117094474B (en) * 2023-10-18 2024-02-20 济南瑞源智能城市开发有限公司 Intelligent tunnel risk perception method, device and medium based on holographic perception

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106373394A (en) * 2016-09-12 2017-02-01 深圳尚桥交通技术有限公司 Vehicle detection method and system based on video and radar
CN106710240A (en) * 2017-03-02 2017-05-24 公安部交通管理科学研究所 Passing vehicle tracking and speed measuring method integrating multiple-target radar and video information
CN109948523A (en) * 2019-03-18 2019-06-28 中国汽车工程研究院股份有限公司 A kind of object recognition methods and its application based on video Yu millimetre-wave radar data fusion
CN112541953A (en) * 2020-12-29 2021-03-23 江苏航天大为科技股份有限公司 Vehicle detection method based on radar signal and video synchronous coordinate mapping
CN113850995A (en) * 2021-09-14 2021-12-28 华设设计集团股份有限公司 Event detection method, device and system based on tunnel radar vision data fusion
CN116168531A (en) * 2022-11-29 2023-05-26 上海腾盛智能安全科技股份有限公司 Tunnel safety management method, device, equipment and medium based on radar and video
CN116229728A (en) * 2022-12-23 2023-06-06 西安电子科技大学 Road traffic monitoring system of 4D millimeter wave radar and video sensor array

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11248925B2 (en) * 2016-07-28 2022-02-15 Toyota Motor Engineering & Manufacturing North America, Inc. Augmented road line detection and display system
US10928508B2 (en) * 2019-04-12 2021-02-23 Ford Global Technologies, Llc Camera and radar fusion

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106373394A (en) * 2016-09-12 2017-02-01 深圳尚桥交通技术有限公司 Vehicle detection method and system based on video and radar
CN106710240A (en) * 2017-03-02 2017-05-24 公安部交通管理科学研究所 Passing vehicle tracking and speed measuring method integrating multiple-target radar and video information
CN109948523A (en) * 2019-03-18 2019-06-28 中国汽车工程研究院股份有限公司 A kind of object recognition methods and its application based on video Yu millimetre-wave radar data fusion
CN112541953A (en) * 2020-12-29 2021-03-23 江苏航天大为科技股份有限公司 Vehicle detection method based on radar signal and video synchronous coordinate mapping
CN113850995A (en) * 2021-09-14 2021-12-28 华设设计集团股份有限公司 Event detection method, device and system based on tunnel radar vision data fusion
CN116168531A (en) * 2022-11-29 2023-05-26 上海腾盛智能安全科技股份有限公司 Tunnel safety management method, device, equipment and medium based on radar and video
CN116229728A (en) * 2022-12-23 2023-06-06 西安电子科技大学 Road traffic monitoring system of 4D millimeter wave radar and video sensor array

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
Fusion of LiDAR and camera sensor data for environment sensing in driverless vehicles;Varuna De Silva;《IEEE Sensors Journal》;1-21 *
基于雷达与相机融合的车辆检测与跟踪技术研究;毛克靖;《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》(第7期);C034-543 *

Also Published As

Publication number Publication date
CN116740944A (en) 2023-09-12

Similar Documents

Publication Publication Date Title
US20200258389A1 (en) Cellular network-based assisted driving method and traffic control unit
CN112700072B (en) Traffic condition prediction method, electronic device, and storage medium
EP4152204A1 (en) Lane line detection method, and related apparatus
CN116740944B (en) Driving safety early warning method, device and storage medium in road tunnel
Weng et al. Rear‐end crash potential estimation in the work zone merging areas
CN113920740B (en) Vehicle-road cooperative driving system and method combining vehicle association degree and game theory
CN113291321A (en) Vehicle track prediction method, device, equipment and storage medium
CN104318327A (en) Predictive parsing method for track of vehicle
WO2021196041A1 (en) Selection method for key target, apparatus, and system
CN109815555B (en) Environment modeling capability evaluation method and system for automatic driving vehicle
CN113127466B (en) Vehicle track data preprocessing method and computer storage medium
CN114049382A (en) Target fusion tracking method, system and medium in intelligent network connection environment
US20220237919A1 (en) Method, Apparatus, and Computing Device for Lane Recognition
CN113867367B (en) Processing method and device for test scene and computer program product
CN109887321B (en) Unmanned vehicle lane change safety judgment method and device and storage medium
CN111613056A (en) Traffic abnormal event detection method and device
CN115359443A (en) Traffic accident detection method and device, electronic device and storage medium
CN114368394A (en) Method and device for attacking V2X equipment based on Internet of vehicles and storage medium
CN113963550A (en) Ambiguous path identification method and device and electronic equipment
CN113207080B (en) Data cooperative transmission method and device in VANET and electronic equipment
EP4220581A1 (en) Estimation of risk exposure for autonomous vehicles
EP4219261A1 (en) Estimation of risk exposure for autonomous vehicles
CN114283575B (en) Signal lamp intersection queuing length estimation method based on video monitoring data
EP4219262A1 (en) In-vehicle system for estimation of risk exposure for an autonomous vehicle
CN114446053B (en) Uncontrolled intersection safety evaluation method for intelligent networked vehicle track error

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