A traffic state determination method based on coupling of ice-snow road surface characteristics and traffic flow

Abstract

The application provides a traffic state determination method based on coupling of ice and snow road surface characteristics and traffic flow, relates to the technical field of traffic, and comprises the following steps: acquiring time sequence aligned road detection data, traffic flow detection data and signal phase data; correcting a reference traffic parameter vector by using an ice and snow road flow coupling parameter vector to determine a corrected coupling vector, combining the traffic flow detection data and the signal phase data to determine a real traffic state vector of a current period; determining a traffic disturbance factor of the current period based on the real traffic state vector, constructing a traffic disturbance intensity parameter, combining the road detection data and a boundary constraint factor to determine a real road surface state vector of the current period; determining an incremental error function based on the real traffic state vector and the real road surface state vector, iteratively updating the ice and snow road flow coupling parameter vector until the corresponding updated incremental error function is not greater than a first threshold value, and determining a target state parameter.

Description

Technical Field

[0001] This invention relates to the field of transportation technology, and in particular to a method for determining traffic conditions based on the coupling of icy and snowy road surface characteristics and traffic flow. Background Technology

[0002] Traffic state estimation at signalized intersections is fundamental for traffic signal timing optimization, congestion identification, active traffic control, and operational safety analysis. Traffic state at signalized intersections typically includes traffic flow, average speed, traffic density, number of vehicles in queues, physical queue length, average control delay, saturation flow rate, and capacity for each approach lane. This estimation requires consideration of signal cycle, phase status, effective green light time, and start-up loss time. Existing traffic state identification methods usually pre-set traffic model parameters such as free-flow velocity, saturated headway, saturated flow rate, start-up loss time, and speed dispersion based on dry road conditions, and maintain these parameters unchanged during subsequent estimation. While some methods incorporate snowfall intensity, road surface temperature, road surface adhesion coefficient, or road surface cover, they typically only treat weather or road surface conditions as a one-way external correction to the traffic state model. Road surface conditions are still considered a fixed input that does not change with traffic flow within a single signal cycle.

[0003] However, road surface conditions change with snowfall and are continuously affected by vehicle movement, stopping and starting, acceleration, and braking. Vehicle movement itself alters road surface conditions, which in turn affect traffic flow. Existing traffic condition recognition methods struggle to reflect the actual evolution of icy and snowy road surfaces and intersection traffic flow, easily leading to traffic control delays and impacting road capacity. Summary of the Invention

[0004] In view of this, the present invention proposes a traffic state determination method based on the coupling of icy and snowy road surface characteristics and traffic flow.

[0005] The technical solution of this invention is implemented as follows: The first aspect of this invention provides a method for determining traffic state based on the coupling of icy and snowy road surface characteristics and traffic flow, comprising: Multiple types of sensor detection data within the target detection area are acquired, and data alignment is performed based on the timestamps of each type of sensor detection data to obtain intermediate detection data; the intermediate detection data includes time-aligned road surface detection data, traffic flow detection data, and signal phase data; The baseline traffic parameter vector is corrected using the ice and snow road flow coupling parameter vector to determine the corrected coupling vector. The actual traffic state vector for the current cycle is determined by combining the traffic flow detection data and the signal phase data. The ice and snow road flow coupling parameter vector includes a speed correction coefficient, a saturation headway correction coefficient, a saturation flow rate correction coefficient, a speed dispersion correction coefficient, and a start-up loss time correction coefficient. The baseline traffic parameter vector represents the traffic parameters under clean and dry road conditions. The traffic disturbance factor for the current period is determined based on the real traffic state vector, and the traffic disturbance intensity parameter is constructed based on the traffic disturbance factor. The real road surface state vector for the current period is determined by combining the road surface detection data and boundary constraint factors. The traffic disturbance factor includes the equivalent axle number converted by vehicle type, the number of stop-start times, the cumulative acceleration intensity, and the cumulative braking intensity. The boundary constraint factors include the adhesion coefficient, snow thickness, icing coverage, and snow compaction. An incremental error function is determined based on the real traffic state vector and the real road surface state vector. If the incremental error function is greater than a first threshold, the ice and snow road flow coupling parameter vector is iteratively updated based on the real road surface state vector until the corresponding updated incremental error function is not greater than the first threshold. The corresponding real traffic state vector and real road surface state vector are then used to determine the target state parameters.

[0006] Based on the above technical solutions, preferably, after data alignment based on the timestamps of various sensor detection data is completed to obtain intermediate detection data, the following steps are taken: Based on the road surface detection data, construct a road surface observation vector and a road surface state vector; Traffic observation vectors and traffic state vectors are constructed based on the traffic flow detection data; the road surface observation vectors and traffic observation vectors are observation data from the corresponding sensors; the road surface state vectors and traffic state vectors represent the actual physical state to be deduced.

[0007] Based on the above technical solutions, preferably, the step of using the ice and snow road flow coupling parameter vector to correct the baseline traffic parameter vector to determine the corrected coupling vector, and combining the traffic flow detection data and the signal phase data to determine the real traffic state vector for the current period, includes: Generate an ice and snow road flow coupling parameter vector based on the road surface state vector; The baseline traffic parameter vector is corrected using the ice and snow road flow coupling parameter vector to determine the corrected coupling vector. Based on the corrected coupling vector, the traffic flow detection data, and the signal phase data, the initial traffic observations for the current period are compensated to obtain the corresponding prior estimate of the traffic state. The traffic flow detection data includes vehicle arrivals; the signal phase data includes signal phase status and effective green light time. The prior estimate of traffic state is corrected based on the traffic observation vector of the current period to obtain the true traffic state vector.

[0008] Based on the above technical solutions, preferably, the reference traffic parameter vector includes a reference speed vector, a reference saturated headway vector, a reference saturated flow rate vector, a reference speed dispersion vector, and a reference start-up loss time vector; the step of using the ice and snow road-flow coupling parameter vector to correct the reference traffic parameter vector and determine the corrected coupling vector includes: The speed correction factor, saturated headway correction factor, saturated flow rate correction factor, speed dispersion correction factor, and start-up loss time correction factor are multiplied one by one with the corresponding vector in the reference traffic parameter vector to determine the correction coupling vector corresponding to each vector.

[0009] Based on the above technical solutions, preferably, before constructing traffic disturbance intensity parameters based on the traffic disturbance factors and determining the true road surface state vector for the current period by combining the road surface detection data and boundary constraint factors, the following steps are included: Determine weather change items and maintenance operation items based on the changes in road surface condition within the current signal cycle; The prior reference value of the road surface condition is determined based on the road surface condition vector of the previous signal cycle, the weather change item of the current cycle, and the maintenance operation item.

[0010] Based on the above technical solutions, preferably, the step of constructing traffic disturbance intensity parameters based on the traffic disturbance factor and determining the true road surface state vector for the current period by combining the road surface detection data and boundary constraint factors includes: Based on the traffic disturbance intensity parameters, the prior value of the road surface condition is corrected to obtain the prior estimate of the road surface condition. The prior estimate of the road surface state is updated using the road surface detection data, and the updated road surface state vector is constrained by the adhesion coefficient, snow thickness, ice coverage and snow compaction to obtain the true road surface state vector of the previous period.

[0011] Based on the above technical solutions, preferably, the step of determining the incremental error function based on the real traffic state vector and the real road surface state vector includes: The actual traffic state vector and the actual road surface state vector are normalized to obtain the corresponding traffic state normalization matrix and road surface state normalization matrix. An adaptive weighted summation process is performed on the traffic state normalization matrix and the road surface state normalization matrix to determine the incremental error function.

[0012] More preferably, a second aspect of the present invention provides a traffic state determination system based on the coupling of icy and snowy road surface characteristics and traffic flow, comprising: a data acquisition and alignment module, a traffic state determination module, a road surface state determination module, and an iterative update module; wherein, The data acquisition and alignment module is configured to acquire multiple types of sensor detection data within the target detection area, and perform data alignment based on the timestamps of various types of sensor detection data to obtain intermediate detection data; the intermediate detection data includes time-aligned road surface detection data, traffic flow detection data, and signal phase data; The traffic state determination module is configured to use the ice and snow road flow coupling parameter vector to correct the baseline traffic parameter vector to determine the corrected coupling vector, and combine the traffic flow detection data and the signal phase data to determine the real traffic state vector for the current period; the ice and snow road flow coupling parameter vector includes a speed correction coefficient, a saturation headway correction coefficient, a saturation flow rate correction coefficient, a speed dispersion correction coefficient, and a start-up loss time correction coefficient; the baseline traffic parameter vector represents the traffic parameters under clean and dry road conditions; The road surface condition determination module is configured to determine the traffic disturbance factor for the current period based on the real traffic state vector, construct traffic disturbance intensity parameters based on the traffic disturbance factor, and determine the real road surface condition vector for the current period by combining the road surface detection data and boundary constraint factors. The traffic disturbance factor includes equivalent axle number converted by vehicle type, number of stop-start cycles, cumulative acceleration intensity, and cumulative braking intensity. The boundary constraint factors include adhesion coefficient, snow thickness, icing coverage, and snow compaction. The iterative update module is configured to determine an incremental error function based on the real traffic state vector and the real road surface state vector. If the incremental error function is greater than a first threshold, the ice and snow road flow coupling parameter vector is iteratively updated based on the real road surface state vector until the corresponding updated incremental error function is not greater than the first threshold. The corresponding real traffic state vector and real road surface state vector are then used to determine the target state parameters.

[0013] More preferably, a third aspect of the present invention provides an electronic device, including a processor and a memory; the memory stores a computer program, wherein the computer program, when executed by the processor, implements the traffic state determination method based on the coupling of icy and snowy road surface characteristics and traffic flow as described in the first aspect.

[0014] More preferably, the fourth aspect of the present invention provides a non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the traffic state determination method based on the coupling of icy and snowy road surface characteristics and traffic flow as described in the first aspect.

[0015] The traffic state determination method based on the coupling of icy and snowy road surface characteristics and traffic flow, as proposed in this invention, has the following advantages over existing technologies: 1. Utilizing the coupled parameter vector of ice and snow road flow, and using dry road surface baseline parameters as a benchmark, the traffic model is positively corrected to recreate the suppressive effect of ice and snow degradation on parameters such as vehicle speed, saturation flow rate, and start-up loss time. Simultaneously, parameters such as vehicle type equivalent axle number, start-stop, and acceleration / deceleration intensity are extracted to construct traffic disturbance intensity, quantifying the reverse modification effects of vehicle flow compaction and brake polishing on snow accumulation, ice layer, and adhesion coefficient. Through incremental error function threshold control, alternating iterations are performed within a cycle to continuously update the real traffic state vector and the real road surface state vector until the evolution of both states tends to stabilize. This achieves periodic mutual correction between road surface state detection data and traffic flow detection data, effectively improving the accuracy and stability of traffic state estimation at intersections in cold winter regions. This provides accurate and reliable basic data support for intersection traffic operation, congestion warning, and adaptive signal timing optimization in icy and snowy environments.

[0016] 2. By uniformly collecting heterogeneous sensor data from road surface, traffic, and signal systems, standardized intermediate detection data is generated based on timestamp-time alignment. This eliminates data misalignment issues caused by sampling frequencies and time offsets from different sensors, ensuring consistent input data sources for coupled iterative calculations. Boundary constraint factors for adhesion coefficient, snow thickness, icing coverage, and compaction are introduced to impose physical range limitations on the derived road surface parameters. This avoids invalid calculation results that violate real-world physical laws, such as negative snow cover, excessive adhesion coefficients, and icing degrees exceeding the specified range, thus ensuring the reliability of the identification results. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart illustrating a traffic state determination method based on the coupling of icy and snowy road surface characteristics and traffic flow, provided in an embodiment of the present invention. Figure 2 A schematic diagram of a traffic state determination system based on the coupling of icy and snowy road surface characteristics and traffic flow, provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0019] The technical solutions of the present invention will be clearly and completely described below with reference to the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0020] In some embodiments, such as Figure 1 As shown, Figure 1 This is a flowchart illustrating a traffic state determination method based on the coupling of icy and snowy road surface characteristics and traffic flow, provided by an embodiment of the present invention. The traffic state determination method based on the coupling of icy and snowy road surface characteristics and traffic flow provided by the present invention includes: S110: Acquire multiple types of sensor detection data within the target detection area, and perform data alignment based on the timestamps of various types of sensor detection data to obtain intermediate detection data; the intermediate detection data includes time-aligned road surface detection data, traffic flow detection data, and signal phase data.

[0021] S120 uses the ice and snow road flow coupling parameter vector to correct the baseline traffic parameter vector and determine the corrected coupling vector. It combines traffic flow detection data and signal phase data to determine the real traffic state vector for the current cycle. The ice and snow road flow coupling parameter vector includes speed correction coefficient, saturation headway correction coefficient, saturation flow rate correction coefficient, speed dispersion correction coefficient, and start-up loss time correction coefficient. The baseline traffic parameter vector represents the traffic parameters under clean and dry road conditions.

[0022] S130 determines the traffic disturbance factor for the current period based on the real traffic state vector, and constructs traffic disturbance intensity parameters based on the traffic disturbance factor. Combines road surface detection data and boundary constraint factors to determine the real road surface state vector for the current period. The traffic disturbance factor includes the equivalent axle number converted by vehicle type, the number of stop and start times, the cumulative acceleration intensity, and the cumulative braking intensity. The boundary constraint factors include the adhesion coefficient, snow thickness, icing coverage, and snow compaction.

[0023] S140. Determine the incremental error function based on the real traffic state vector and the real road surface state vector. If the incremental error function is greater than the first threshold, iteratively update the ice and snow road flow coupling parameter vector based on the real road surface state vector until the corresponding updated incremental error function is not greater than the first threshold. Then, determine the target state parameters based on the corresponding real traffic state vector and the real road surface state vector.

[0024] In this embodiment, all raw sensor data from the intersection's zoned detection area are collected uniformly, including road surface detection data, traffic flow detection data, and signal phase data. Road surface detection data may include road surface adhesion coefficient, snow thickness, ice coverage, and road surface temperature. Traffic flow detection data may include traffic volume, vehicle speed, lane occupancy, vehicle trajectory, and vehicle type information. Signal phase data may include signal cycle, phase state, effective green light time, and start-up loss time. Using the signal cycle as a unified time scale, time alignment is achieved based on timestamp sliding window matching. Anomaly cleaning and missing data interpolation are then performed to output a standardized, time-synchronized intermediate detection dataset, providing a unified input basis for subsequent bidirectional coupling iterations.

[0025] Considering that the baseline traffic parameter vector for dry roads is a fixed calibration standard, while icy and snowy roads synchronously decrease vehicle speed and saturation flow rate, amplify headway, speed dispersion, and start-up loss time, a traffic model adapted to real-time icy and snowy conditions is obtained by scaling the baseline parameters element-by-element through the icy and snowy road flow coupling parameter vector. This model is then combined with aligned traffic flow observations and signal timing inputs to the traffic state transition model, and after correction, a complete real traffic state vector is output. Disturbance factors are extracted from the real traffic state vector to quantify vehicle behavior on icy and snowy roads, and then normalized and weighted to obtain the comprehensive traffic disturbance intensity. Furthermore, road surface changes are categorized into three superimposed types: weather, maintenance, and traffic flow disturbance, with physical boundary constraints applied. An updated real road surface state vector is obtained through filtering and correction.

[0026] An incremental error function is constructed that integrates real traffic state vectors and real road surface state vectors. If the incremental error function exceeds a first convergence threshold, it indicates that the road surface and traffic flow states have not yet matched the real synchronous evolution relationship. The ice and snow coupling parameters, traffic state, disturbance intensity, and road surface state are recalculated using the updated real road surface state. This process is iterated until the incremental error function converges. The stabilized real traffic state vector and real road surface state vector are then output as the final target state parameters.

[0027] In some embodiments, after data alignment is completed based on the timestamps of various types of sensor detection data to obtain intermediate detection data, the process includes: Construct road observation vectors and road state vectors based on road surface detection data; Traffic observation vectors and traffic state vectors are constructed based on traffic flow detection data; road surface observation vectors and traffic observation vectors are the observation data of the corresponding sensors; road surface state vectors and traffic state vectors represent the real physical state to be deduced.

[0028] In this embodiment, each approach lane of the signalized intersection is divided into a stop line influence zone and an upstream detection zone along the vehicle travel direction. The stop line influence zone is a pre-defined road segment extending upstream from the stop line to the approach lane, used to detect the road surface conditions and traffic flow conditions in areas where vehicles queue, stop and start, accelerate, brake, and are concentrated. The upstream detection zone is located upstream of the stop line influence zone and is used to detect the vehicle speed, vehicle type composition, and upstream icy / snowy road surface conditions before vehicles arrive at and enter the intersection.

[0029] Construct import channels In the Road surface observation vector within one signal period: ; In the formula, superscript Represents sensor observations, Characterized by the road surface adhesion coefficient, it is a dimensionless parameter; Characterizes snow thickness, measured in millimeters; Characterizes the degree of ice cover, with a value ranging from 0 to 1; Characterizes road surface temperature, measured in degrees Celsius.

[0030] Construct import channels In the Traffic observation vector within a signal period: ; In the formula, The average velocity over the period, For vehicle trajectory sets, A collection of car models. Traffic flow is represented by vehicles per hour. It represents lane occupancy as a dimensionless parameter or expressed as a percentage.

[0031] Construct road surface condition parameters, inlet road In the The road surface state vector within each signal period is: ; In the formula, This represents the snow compaction degree, with a value ranging from 0 to 1. The larger the value, the higher the degree of snow compaction.

[0032] Construct import channels In the Traffic state vector within a signal cycle: ; In the formula: This is the average speed, expressed in meters per second. Traffic density, expressed in vehicles / km / lane. This represents the number of vehicles in the queue, in units of vehicles. The physical length of the queue, in meters. Average control delay, in seconds per vehicle. The saturation flow rate is expressed in vehicles per hour per lane.

[0033] In some embodiments, the reference traffic parameter vector is corrected using the ice and snow road flow coupling parameter vector to determine the corrected coupling vector, and the real traffic state vector for the current period is determined by combining traffic flow detection data and signal phase data, including: Generate ice and snow road flow coupling parameter vectors based on road surface state vectors; The baseline traffic parameter vector is corrected using the ice and snow road flow coupling parameter vector to determine the corrected coupling vector. Based on the corrected coupling vector, traffic flow detection data, and signal phase data, the initial traffic observations for the current cycle are compensated to obtain the corresponding prior estimate of the traffic state. The traffic flow detection data includes vehicle arrivals; the signal phase data includes signal phase status and effective green light time. The prior estimate of traffic state is corrected based on the traffic observation vector of the current period to obtain the true traffic state vector.

[0034] In this embodiment, according to the first The road surface state vector of the next iteration generates the ice and snow road flow coupling parameter vector: ; In the formula: For speed correction factor, This is the saturation headway correction factor. This is the saturation flow rate correction factor. This is the velocity dispersion correction coefficient. This is a correction factor for startup loss time.

[0035] Let the baseline traffic parameter vector under non-icy / snowy conditions be: ; The modified coupling vector is determined by correcting the baseline traffic parameter vector using the ice and snow road flow coupling parameter vector. The updated traffic model parameters are input into the traffic state transition model to obtain the prior estimate of the traffic state for the current period: ; In the formula, The inputs to the traffic state transition model include at least vehicle arrivals, signal phase status, and effective green light time.

[0036] The prior estimate of traffic state is measured and corrected based on the traffic observation vector of the current period: ; In the formula, For traffic state observation functions, Correct the gain for traffic condition measurements.

[0037] In each iteration, the final traffic state of the previous signal cycle is used as the time prior of the traffic state transition model. The traffic model parameters are recalculated only based on the road surface state of the current iteration, thus avoiding repeated accumulation and updating of the same set of traffic observation data.

[0038] In some embodiments, the reference traffic parameter vector includes a reference speed vector, a reference saturated headway vector, a reference saturated flow rate vector, a reference speed dispersion vector, and a reference start-up loss time vector; the reference traffic parameter vector is corrected using the ice and snow roadflow coupling parameter vector to determine the corrected coupling vector, including: The speed correction factor, saturated headway correction factor, saturated flow rate correction factor, speed dispersion correction factor, and start-up loss time correction factor are multiplied one by one with the corresponding vector in the baseline traffic parameter vector to determine the correction coupling vector corresponding to each vector.

[0039] In this embodiment, the first element is obtained through element-wise operations. The traffic model parameters used in this iteration are: ; In the formula, This indicates that corresponding elements are multiplied.

[0040] In some embodiments, before constructing traffic disturbance intensity parameters based on traffic disturbance factors and determining the true road surface state vector for the current period by combining road surface detection data and boundary constraint factors, the process includes: Determine weather change items and maintenance operation items based on the changes in road surface condition within the current signal cycle; The prior reference value of the road surface condition is determined based on the road surface condition vector of the previous signal cycle, the weather change item of the current cycle, and the maintenance operation item.

[0041] In this embodiment, the changes in road surface condition within the current signal cycle are decomposed into weather change items, maintenance operation items, etc. Based on the road surface condition vector of the previous signal cycle, the weather change items of the current cycle, and the maintenance operation items, a priori value of the road surface condition without considering traffic disturbances is determined.

[0042] ; In the formula, For weather changes, For maintenance work items.

[0043] The weather change item is calculated based on at least two of the following: snowfall intensity, air temperature, road surface temperature, liquid water content, and wind speed. It characterizes the impact of new snowfall, snow melting, and refreezing on road surface conditions. The maintenance operation item is calculated based on at least one of the following: snow removal operation status, de-icing agent application rate, and operation time. It characterizes the impact of mechanical snow removal or snow melting operations on snow thickness, ice coverage, and road surface adhesion.

[0044] In some embodiments, a traffic disturbance intensity parameter is constructed based on a traffic disturbance factor, and the true road surface state vector for the current period is determined by combining road surface detection data and boundary constraint factors, including: Based on the traffic disturbance intensity parameters, the prior benchmark value of the road surface condition is corrected to obtain the prior estimate of the road surface condition; The prior estimate of the road surface condition is updated using road surface detection data, and the updated road surface condition vector is constrained by the adhesion coefficient, snow thickness, ice coverage and snow compaction to obtain the true road surface condition vector of the previous period.

[0045] In this embodiment, traffic disturbance factors include vehicle type equivalent axle count, number of stop-start cycles, cumulative acceleration intensity, and cumulative braking intensity.

[0046] The equivalent number of axles for a vehicle model is calculated using the following formula: ; In the formula, This represents the number of vehicles passing through the corresponding detection area during the current period. For the first The axle conversion factor for the vehicle model.

[0047] When the vehicle speed decreases from above the stop judgment speed to below the stop judgment speed, and then rises back above the start judgment speed within a preset time, it is recorded as a stop-start event. The total number of stop-start events in the current period is recorded as follows: .

[0048] The cumulative acceleration intensity is calculated according to the following formula: ; The cumulative braking intensity is calculated according to the following formula: ; In the formula, For the first The car in The longitudinal acceleration at each trajectory sampling time, This represents the trajectory sampling time interval.

[0049] Normalize each disturbance component to construct the traffic disturbance intensity for the current period: ; In the formula: and These are the normalized reference values, to The perturbation weights are non-negative, and .

[0050] Traffic disturbance intensity is used to characterize the combined effects of vehicle rolling, stopping and starting, driving and braking behavior on icy and snowy road surfaces during the current period, excluding road surface changes caused by snowfall, melting, refreezing or road maintenance operations.

[0051] Calculate the traffic disturbance term based on the traffic disturbance intensity: ; The components of the traffic disturbance term are calculated according to the following formula: ; In the formula: This is the snow thickness attenuation coefficient. This is the snow compaction coefficient. The ice layer abrasion coefficient, and The coefficient of adhesion is the adhesion response coefficient. The last term is used to represent the effect of repeated braking or driving of the vehicle causing the ice surface to polish and thus reducing the adhesion coefficient.

[0052] The first item was obtained based on traffic disturbance. Prior estimation of road surface condition in the next iteration: ; Perform measurement corrections based on road surface observation vectors: ; In the formula, For road surface condition observation function, Correct the gain for road surface condition measurement.

[0053] Boundary constraints are applied to the updated road surface condition to ensure that the adhesion coefficient, snow thickness, icing coverage, and snow compaction degree satisfy the following conditions: ; Within each cycle, the prior benchmark value of the road surface condition is calculated using the same road surface condition from the previous cycle, weather change items for the current cycle, and maintenance operation items. The traffic disturbance item is recalculated only based on the traffic disturbance intensity obtained in this iteration, thus avoiding the repeated accumulation of weather items and maintenance operation items within the same cycle.

[0054] In some embodiments, determining the incremental error function based on the real traffic state vector and the real road surface state vector includes: The real traffic state vector and the real road surface state vector are normalized to obtain the corresponding traffic state normalization matrix and road surface state normalization matrix. An adaptive weighted summation process is performed on the traffic state normalization matrix and the road surface state normalization matrix to determine the incremental error function.

[0055] In this embodiment, the traffic state normalization matrix and the road surface state normalization matrix can be represented as: ; Current cycle number The state increment error for the next iteration is: ; In the formula, This represents the incremental weight of the road surface condition.

[0056] The bidirectional coupling iteration of the current cycle stops when the following equation is satisfied: ; in, This is the preset convergence threshold.

[0057] When the state increment error has not reached the preset convergence threshold but the number of iterations has reached the maximum number of iterations. When the iteration stops, output the state estimation result that satisfies the physical boundary constraints for the last time.

[0058] When two consecutive state increments increase, a relaxed update method is used: ; In the formula, and All are greater than 0 and not greater than 1.

[0059] The traffic state vector at the time of stopping iteration is used as the traffic state estimation result of the current signal cycle, and the average speed, traffic density, number of vehicles in queue, physical queue length, average control delay, saturation flow rate and capacity of each approach lane or lane of each approach lane are output.

[0060] The maximum number of vehicles that can be released in the current signal cycle is determined by the following formula: ; In the formula, The unit is vehicles.

[0061] The current capacity of the approach lane or lane is determined by the following formula: ; In the formula, The unit is vehicles / hour / lane.

[0062] Let the number of vehicles arriving in the current period be... The actual number of vehicles leaving was The number of vehicles in the queue is then updated according to the following formula: ; in: ; The physical length of the queue is calculated using the following formula: ; In the formula, The average equivalent vehicle length is calculated based on the vehicle model composition, and the unit is meters. The average parking distance under icy and snowy conditions is expressed in meters.

[0063] Divide the current period into The average control delay is calculated over a time interval using the following formula: ; In the formula, For the first The number of vehicles queuing at the end of each time interval. The time interval is the average control delay, measured in seconds per vehicle.

[0064] In some embodiments, please refer to Figure 2 , Figure 2 This is a schematic diagram of a traffic state determination system based on the coupling of icy and snowy road surface characteristics and traffic flow, provided in an embodiment of the present invention. The present invention provides a traffic state determination system 200 based on the coupling of icy and snowy road surface characteristics and traffic flow, comprising: a data acquisition and alignment module 210, a traffic state determination module 220, a road surface state determination module 230, and an iterative update module 240; wherein,

[0065] The data acquisition and alignment module 210 is configured to acquire multiple types of sensor detection data within the target detection area and perform data alignment based on the timestamps of various types of sensor detection data to obtain intermediate detection data; the intermediate detection data includes time-aligned road surface detection data, traffic flow detection data, and signal phase data; The traffic state determination module 220 is configured to use the ice and snow road flow coupling parameter vector to correct the baseline traffic parameter vector and determine the corrected coupling vector, and combine traffic flow detection data and signal phase data to determine the real traffic state vector for the current period; the ice and snow road flow coupling parameter vector includes speed correction coefficient, saturation headway correction coefficient, saturation flow rate correction coefficient, speed dispersion correction coefficient, and start-up loss time correction coefficient; the baseline traffic parameter vector represents the traffic parameters under clean and dry road conditions; The road surface condition determination module 230 is configured to determine the traffic disturbance factor for the current period based on the real traffic state vector, and construct traffic disturbance intensity parameters based on the traffic disturbance factor. It then combines road surface detection data and boundary constraint factors to determine the real road surface state vector for the current period. The traffic disturbance factor includes the equivalent axle number converted by vehicle type, the number of stop-start cycles, the cumulative acceleration intensity, and the cumulative braking intensity. The boundary constraint factors include the adhesion coefficient, snow thickness, icing coverage, and snow compaction. The iterative update module 240 is configured to determine the incremental error function based on the real traffic state vector and the real road surface state vector. If the incremental error function is greater than the first threshold, the ice and snow road flow coupling parameter vector is iteratively updated based on the real road surface state vector until the corresponding updated incremental error function is not greater than the first threshold. The corresponding real traffic state vector and real road surface state vector are then used to determine the target state parameters.

[0066] In some embodiments, the traffic state determination system 200 based on the coupling of icy and snowy road surface characteristics and traffic flow further includes a vector construction module; the vector construction module is configured as follows: Construct road observation vectors and road state vectors based on road surface detection data; Traffic observation vectors and traffic state vectors are constructed based on traffic flow detection data; road surface observation vectors and traffic observation vectors are the observation data of the corresponding sensors; road surface state vectors and traffic state vectors represent the real physical state to be deduced.

[0067] In some embodiments, the traffic status determination module 220 is specifically configured as follows: Generate ice and snow road flow coupling parameter vectors based on road surface state vectors; The baseline traffic parameter vector is corrected using the ice and snow road flow coupling parameter vector to determine the corrected coupling vector. Based on the corrected coupling vector, traffic flow detection data, and signal phase data, the initial traffic observations for the current cycle are compensated to obtain the corresponding prior estimate of the traffic state. The traffic flow detection data includes vehicle arrivals; the signal phase data includes signal phase status and effective green light time. The prior estimate of traffic state is corrected based on the traffic observation vector of the current period to obtain the true traffic state vector.

[0068] In some embodiments, the reference traffic parameter vector includes a reference speed vector, a reference saturated headway vector, a reference saturated flow rate vector, a reference speed dispersion vector, and a reference start-up loss time vector; the traffic state determination module 220 is specifically configured as follows: The speed correction factor, saturated headway correction factor, saturated flow rate correction factor, speed dispersion correction factor, and start-up loss time correction factor are multiplied one by one with the corresponding vector in the baseline traffic parameter vector to determine the correction coupling vector corresponding to each vector.

[0069] In some embodiments, the traffic state determination system 200 based on the coupling of icy and snowy road surface characteristics and traffic flow further includes a road surface state prior determination module; the road surface state prior determination module is configured as follows: Determine weather change items and maintenance operation items based on the changes in road surface condition within the current signal cycle; The prior reference value of the road surface condition is determined based on the road surface condition vector of the previous signal cycle, the weather change item of the current cycle, and the maintenance operation item.

[0070] In some embodiments, the road surface condition determination module 230 is specifically configured as follows: Based on the traffic disturbance intensity parameters, the prior benchmark value of the road surface condition is corrected to obtain the prior estimate of the road surface condition; The prior estimate of the road surface condition is updated using road surface detection data, and the updated road surface condition vector is constrained by the adhesion coefficient, snow thickness, ice coverage and snow compaction to obtain the true road surface condition vector of the previous period.

[0071] In some embodiments, the iterative update module 240 is specifically configured as follows: The real traffic state vector and the real road surface state vector are normalized to obtain the corresponding traffic state normalization matrix and road surface state normalization matrix. An adaptive weighted summation process is performed on the traffic state normalization matrix and the road surface state normalization matrix to determine the incremental error function.

[0072] It should be noted that the traffic state determination system based on the coupling of ice and snow road surface characteristics and traffic flow provided in this application embodiment and the traffic state determination method based on the coupling of ice and snow road surface characteristics and traffic flow provided in this application embodiment are based on the same application concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the aforementioned traffic state determination method based on the coupling of ice and snow road surface characteristics and traffic flow, and the repeated parts will not be described again.

[0073] In some embodiments, please refer to Figure 3 , Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device 300 provided in this application includes a processor 310 and a memory 320; the memory 320 stores a computer program, wherein the computer program, when executed by the processor, implements the aforementioned traffic state determination method based on the coupling of icy and snowy road surface characteristics and traffic flow.

[0074] Specifically, processor 310 may include, for example, a general-purpose microprocessor, an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. Processor 310 may also include onboard memory for caching purposes. Processor 310 may be a single processing unit or multiple processing units for performing different actions of the method flow according to embodiments of this application.

[0075] The memory 320 may be any medium capable of containing, storing, transmitting, propagating, or transmitting instructions. For example, the memory 320 may include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, apparatuses, or propagation media. Specific examples of the memory 320 include: magnetic storage devices such as magnetic tape or hard disk drives (HDDs); optical storage devices such as optical discs (CD-ROMs); and may also be random access memory (RAM) or flash memory; and / or wired / wireless communication links.

[0076] This application also provides a non-transitory computer-readable storage medium storing a computer program thereon. When executed by a processor, this program implements the aforementioned traffic state determination method based on the coupling of icy and snowy road surface characteristics and traffic flow. This computer-readable medium may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into that device / apparatus / system. The aforementioned computer-readable medium carries one or more programs, which, when executed, implement the method according to the embodiments of this application.

[0077] According to embodiments of this application, a computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wired, optical fiber, radio frequency signals, etc., or any suitable combination thereof.

[0078] Those skilled in the art will understand that the features described in the various embodiments and / or claims of this application can be combined and / or combined in various ways, even if such combinations or combinations are not explicitly described in this application. All such combinations and / or combinations fall within the scope of this application. Therefore, the scope of this application should not be limited to the above embodiments, but should be defined not only by the appended claims, but also by the equivalents of the appended claims. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this invention should be included within the protection scope of this invention.

Claims

1. A method for determining traffic state based on the coupling of icy and snowy road surface characteristics and traffic flow, characterized in that, include: Acquire multiple types of sensor detection data within the target detection area, and align the data based on the timestamps of each type of sensor detection data to obtain intermediate detection data; The intermediate detection data includes time-aligned road surface detection data, traffic flow detection data, and signal phase data; The ice and snow road flow coupling parameter vector is used to correct the baseline traffic parameter vector to determine the corrected coupling vector. The traffic flow detection data and the signal phase data are combined to determine the real traffic state vector for the current period. The ice and snow road flow coupling parameter vector includes speed correction coefficient, saturation headway correction coefficient, saturation flow rate correction coefficient, speed dispersion correction coefficient, and start-up loss time correction coefficient. The baseline traffic parameter vector represents the traffic parameters under clean and dry road conditions; The traffic disturbance factor for the current period is determined based on the real traffic state vector, and the traffic disturbance intensity parameter is constructed based on the traffic disturbance factor. The real road surface state vector for the current period is determined by combining the road surface detection data and boundary constraint factors. The traffic disturbance factor includes the equivalent axle number converted by vehicle type, the number of stop-start times, the cumulative acceleration intensity, and the cumulative braking intensity. The boundary constraint factors include the adhesion coefficient, snow thickness, icing coverage, and snow compaction. An incremental error function is determined based on the real traffic state vector and the real road surface state vector. If the incremental error function is greater than a first threshold, the ice and snow road flow coupling parameter vector is iteratively updated based on the real road surface state vector until the corresponding updated incremental error function is not greater than the first threshold. The corresponding real traffic state vector and real road surface state vector are then used to determine the target state parameters.

2. The traffic state determination method based on the coupling of icy and snowy road surface characteristics and traffic flow as described in claim 1, characterized in that, After data alignment based on the timestamps of various sensor detection data to obtain intermediate detection data, the following is included: Based on the road surface detection data, construct a road surface observation vector and a road surface state vector; Traffic observation vectors and traffic state vectors are constructed based on the traffic flow detection data; the road surface observation vectors and traffic observation vectors are observation data from the corresponding sensors; the road surface state vectors and traffic state vectors represent the actual physical state to be deduced.

3. The traffic state determination method based on the coupling of icy and snowy road surface characteristics and traffic flow as described in claim 2, characterized in that, The process of using the ice and snow road flow coupling parameter vector to correct the baseline traffic parameter vector to determine the corrected coupling vector, and combining the traffic flow detection data and the signal phase data to determine the true traffic state vector for the current period, includes: Generate an ice and snow road flow coupling parameter vector based on the road surface state vector; The baseline traffic parameter vector is corrected using the ice and snow road flow coupling parameter vector to determine the corrected coupling vector. Based on the corrected coupling vector, the traffic flow detection data, and the signal phase data, the initial traffic observations for the current period are compensated to obtain the corresponding prior estimate of the traffic state. The traffic flow detection data includes vehicle arrivals; the signal phase data includes signal phase status and effective green light time. The prior estimate of traffic state is corrected based on the traffic observation vector of the current period to obtain the true traffic state vector.

4. The traffic state determination method based on the coupling of icy and snowy road surface characteristics and traffic flow as described in claim 1, characterized in that, The baseline traffic parameter vector includes a baseline speed vector, a baseline saturated headway vector, a baseline saturated flow rate vector, a baseline speed dispersion vector, and a baseline start-up loss time vector; the step of using the ice and snow road-flow coupling parameter vector to correct the baseline traffic parameter vector and determine the corrected coupling vector includes: The speed correction factor, saturated headway correction factor, saturated flow rate correction factor, speed dispersion correction factor, and start-up loss time correction factor are multiplied one by one with the corresponding vector in the reference traffic parameter vector to determine the correction coupling vector corresponding to each vector.

5. The traffic state determination method based on the coupling of icy and snowy road surface characteristics and traffic flow as described in claim 2, characterized in that, Before constructing traffic disturbance intensity parameters based on the traffic disturbance factors and determining the true road surface state vector for the current period by combining the road surface detection data and boundary constraint factors, the process includes: Determine weather change items and maintenance operation items based on the changes in road surface condition within the current signal cycle; The prior reference value of the road surface condition is determined based on the road surface condition vector of the previous signal cycle, the weather change item of the current cycle, and the maintenance operation item.

6. The traffic state determination method based on the coupling of icy and snowy road surface characteristics and traffic flow as described in claim 5, characterized in that, The step of constructing traffic disturbance intensity parameters based on the traffic disturbance factor, and determining the true road surface state vector for the current period by combining the road surface detection data and boundary constraint factors, includes: Based on the traffic disturbance intensity parameters, the prior value of the road surface condition is corrected to obtain the prior estimate of the road surface condition. The prior estimate of the road surface state is updated using the road surface detection data, and the updated road surface state vector is constrained by the adhesion coefficient, snow thickness, ice coverage and snow compaction to obtain the true road surface state vector of the previous period.

7. The traffic state determination method based on the coupling of icy and snowy road surface characteristics and traffic flow as described in claim 1, characterized in that, The step of determining the incremental error function based on the real traffic state vector and the real road surface state vector includes: The actual traffic state vector and the actual road surface state vector are normalized to obtain the corresponding traffic state normalization matrix and road surface state normalization matrix. An adaptive weighted summation process is performed on the traffic state normalization matrix and the road surface state normalization matrix to determine the incremental error function.

8. A traffic state determination system based on the coupling of icy and snowy road surface characteristics and traffic flow, characterized in that, include: The system includes a data acquisition and alignment module, a traffic state determination module, a road surface state determination module, and an iterative update module; among which... The data acquisition and alignment module is configured to acquire multiple types of sensor detection data within the target detection area, and perform data alignment based on the timestamps of various types of sensor detection data to obtain intermediate detection data; the intermediate detection data includes time-aligned road surface detection data, traffic flow detection data, and signal phase data; The traffic state determination module is configured to use the ice and snow road flow coupling parameter vector to correct the baseline traffic parameter vector to determine the corrected coupling vector, and combine the traffic flow detection data and the signal phase data to determine the real traffic state vector for the current period; the ice and snow road flow coupling parameter vector includes a speed correction coefficient, a saturation headway correction coefficient, a saturation flow rate correction coefficient, a speed dispersion correction coefficient, and a start-up loss time correction coefficient; the baseline traffic parameter vector represents the traffic parameters under clean and dry road conditions; The road surface condition determination module is configured to determine the traffic disturbance factor for the current period based on the real traffic state vector, construct traffic disturbance intensity parameters based on the traffic disturbance factor, and determine the real road surface condition vector for the current period by combining the road surface detection data and boundary constraint factors. The traffic disturbance factor includes equivalent axle number converted by vehicle type, number of stop-start cycles, cumulative acceleration intensity, and cumulative braking intensity. The boundary constraint factors include adhesion coefficient, snow thickness, icing coverage, and snow compaction. The iterative update module is configured to determine an incremental error function based on the real traffic state vector and the real road surface state vector. If the incremental error function is greater than a first threshold, the ice and snow road flow coupling parameter vector is iteratively updated based on the real road surface state vector until the corresponding updated incremental error function is not greater than the first threshold. The corresponding real traffic state vector and real road surface state vector are then used to determine the target state parameters.

9. An electronic device, characterized in that, It includes a processor and a memory; the memory stores a computer program, wherein the computer program, when executed by the processor, implements the traffic state determination method based on the coupling of icy and snowy road surface characteristics and traffic flow as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium, characterized in that, It stores a computer program, wherein when the computer program is executed by a processor, it implements the traffic state determination method based on the coupling of icy and snowy road surface characteristics and traffic flow as described in any one of claims 1 to 7.

Images