Expressway traffic flow detection and evaluation method, system, equipment and medium

Abstract

The invention relates to the technical field of traffic control, in particular to a highway traffic flow detection and evaluation method, system and device and a medium. According to the method, firstly, a video detector, a radar detector and a coil detector are used for cooperatively collecting parameters such as vehicle type distribution, vehicle speed distribution and vehicle head distance, and then a vehicle flow heterogeneous index including a cart influence coefficient, a vehicle speed difference coefficient and a car-following safety degree is calculated based on the data; further analyzing a traffic flow operation state to obtain a traffic capacity attenuation characteristic, and finally evaluating the traffic efficiency of different road sections. And the operation quality of the mixed traffic flow can be reflected more comprehensively and accurately.

Description

Technical Field

[0001] The present application relates to the technical field of traffic control, and in particular to a method, system, device and medium for detecting and evaluating highway traffic flow. Background Art

[0002] As my country's highway network continues to improve and the number of vehicles continues to grow, it has become normal for large and small vehicles to mix. The performance differences between different models have led to problems such as uneven distribution of traffic speed and complex following behaviors, which has brought severe challenges to the efficiency and safe operation of highways.

[0003] The existing technology only considers the static characteristics of a single space-time section and fails to reflect the dynamic interaction between different vehicle types. It is difficult to accurately characterize the operating quality of mixed traffic flows, and this situation needs to be further improved. Summary of the invention

[0004] In order to solve the problem that the existing traffic detection fails to reflect the dynamic interaction between different types of vehicles and is difficult to accurately characterize the operating quality of mixed traffic flow, the present application provides a highway traffic flow detection and evaluation method, system, device and medium, which adopts the following technical solutions: In a first aspect, the present application provides a method for detecting and evaluating highway traffic flow, comprising the following steps: Collecting vehicle operation data by means of a video detector, a radar detector and a coil detector, wherein the vehicle operation data includes vehicle type distribution, vehicle speed distribution and vehicle head distance; Calculating a traffic heterogeneity index according to the vehicle operation data, wherein the traffic heterogeneity index includes a large vehicle impact coefficient, a vehicle speed difference coefficient, and a following safety degree; According to the traffic heterogeneity index, the traffic flow operation state is determined to obtain the traffic capacity attenuation characteristics under the mixed traffic conditions of different vehicle types; Based on the traffic capacity attenuation characteristics, traffic efficiency evaluation results of different sections are determined.

[0005] By adopting the above-mentioned technical scheme, the present application first utilizes video detectors, radar detectors and coil detectors to collaboratively collect parameters such as vehicle type distribution, vehicle speed distribution and vehicle head spacing, and then calculates the traffic heterogeneity index including large vehicle impact coefficient, vehicle speed difference coefficient and following safety based on these data, and then analyzes the traffic flow operation status to obtain the traffic capacity attenuation characteristics, and finally realizes the evaluation of the traffic efficiency of different road sections; it can more comprehensively and accurately reflect the operation quality of mixed traffic flow.

[0006] Optionally, a traffic flow heterogeneity index is calculated according to the vehicle operation data, wherein the traffic flow heterogeneity index includes a large vehicle influence coefficient, a vehicle speed difference coefficient, and a following safety degree, and specifically includes the following steps: Determine the proportion of large vehicles according to the distribution of vehicle models, and calculate the large vehicle impact coefficient according to the proportion of large vehicles; The speed difference coefficient is calculated based on the dispersion degree between the actual driving speed and the average speed of different vehicle models; The following safety degree is calculated based on the ratio of the actual headway between adjacent vehicles to the safe headway.

[0007] By adopting the above technical solution, this application first calculates the large vehicle impact coefficient based on the vehicle type distribution data to reflect the basic impact of large vehicles on traffic flow, and obtains the speed difference coefficient reflecting the stability of traffic flow by analyzing the degree of dispersion of the actual driving speed and the average speed of different vehicle types; finally, the following safety degree is introduced to quantify the safety degree of vehicle following behavior through the ratio of the actual head distance to the safe head distance.

[0008] Optionally, determining the proportion of large vehicles according to the distribution of vehicle models, and calculating the large vehicle impact coefficient according to the proportion of large vehicles, specifically includes the following steps: Based on the vehicle type classification standard, vehicles are divided into large vehicles, medium vehicles and small vehicles; Count the cumulative number of various types of vehicles passing through during the inspection period, and calculate the proportion of large vehicles in the total traffic flow; Determine the weight coefficient of large vehicle impact based on the number of lanes and the lateral distribution characteristics of large vehicles; The large vehicle impact coefficient is calculated according to the proportion of the large vehicle number and the large vehicle impact weight coefficient.

[0009] By adopting the above technical solution, the traditional method only considers the proportion of large vehicles and ignores their spatial distribution characteristics, resulting in a large deviation between the evaluation results and the actual situation. For example, in a four-lane highway section, even with the same 25% large vehicle proportion, when large vehicles are concentrated in the two outer lanes, their impact on traffic flow is much more serious than when they are evenly distributed in each lane. The present application first divides vehicles into three categories: large, medium and small according to the vehicle type classification standard, and then counts the number of each type of vehicle passing through during the detection period to obtain the basic value of the large vehicle proportion, and then analyzes the lateral distribution law of large vehicles to determine the weight coefficient, and finally combines the quantity proportion with the distribution weight to obtain a more accurate large vehicle impact coefficient.

[0010] Optionally, the large vehicle impact weight coefficient is determined according to the number of lanes and the lateral distribution characteristics of large vehicles, which specifically includes the following steps: According to the lane type, the lanes are divided into emergency lanes, outermost lanes, middle lanes and innermost lanes to obtain the lane function classification results; Based on the lane function classification results, the proportion of large vehicles occupying time on each lane is counted to obtain lane occupancy characteristics; Determining a reference weight value for each lane according to the lane function classification result and the lane occupancy characteristics; Based on the lane occupancy characteristics, the distribution of large vehicles in adjacent lanes is calculated to obtain an interference coefficient between lanes; The large vehicle impact weight coefficient is calculated according to the reference weight value and the lane-to-lane interference coefficient.

[0011] By adopting the above technical solution, when large vehicles occupy the two outermost lanes at the same time, it will not only directly affect the traffic efficiency of these two lanes, but also significantly reduce the service level of the adjacent middle lane through the "ripple effect", thereby reducing the traffic capacity of the entire section; the present application first classifies the lanes according to their functional characteristics, then counts the characteristics of the large vehicle occupancy time of each lane, and then determines the benchmark weight value based on the functional positioning, analyzes the large vehicle distribution correlation between adjacent lanes to obtain the interference coefficient, and finally combines the benchmark weight with the interference effect to calculate the final impact weight coefficient; thus, a systematic evaluation of the impact of large vehicles is achieved.

[0012] Optionally, the vehicle speed difference coefficient is calculated based on the degree of dispersion between the actual driving speed and the average speed of different vehicle models, which specifically includes the following steps: According to the vehicle speed distribution data, the average driving speed of large vehicles, medium-sized vehicles and small vehicles is calculated respectively to obtain the speed characteristics of each vehicle type; Based on the speed characteristics of each vehicle type, a weighted average speed of the entire vehicle flow is calculated to obtain a reference speed value; According to the speed characteristics of each vehicle type and the reference speed value, the speed deviation of each vehicle type is calculated to obtain a speed dispersion characteristic; Determining a speed fluctuation weight coefficient based on the speed discrete characteristics and the proportion of each vehicle type; A vehicle speed difference coefficient is calculated according to the speed discrete characteristic and the speed fluctuation weight coefficient.

[0013] By adopting the above technical solution, the present application first calculates the average speed characteristics of large, medium and small vehicles respectively, and then determines the weighted average reference speed based on the number of each vehicle model, then analyzes the degree of deviation between the actual speed of each vehicle model and the reference speed to obtain discrete characteristics, and then determines the fluctuation weight coefficient according to the vehicle model composition ratio, and finally combines the speed discrete characteristics with the fluctuation weight to obtain the final difference coefficient; thereby scientifically evaluating the speed stability in mixed traffic flow.

[0014] Optionally, the vehicle operation data further includes traffic flow, queue length and vehicle occupancy rate; determining the traffic flow operation state according to the traffic flow heterogeneity index to obtain the traffic capacity attenuation characteristics under the mixed traffic conditions of different vehicle types, specifically including the following steps: Calculating a mixed traffic influence coefficient according to the traffic heterogeneity index; determining road saturation based on the traffic flow and vehicle occupancy; According to the mixed traffic influence coefficient and the road saturation, a traffic capacity attenuation characteristic is obtained; The capacity attenuation characteristic is corrected according to the queue length variation trend.

[0015] By adopting the above technical solution, the existing method only evaluates based on static indicators, ignoring the dynamic evolution characteristics of traffic flow, resulting in the evaluation results being unable to reflect the actual operating conditions; the present application first calculates the mixed traffic impact coefficient based on the traffic heterogeneity index, and then determines the road saturation degree in combination with the traffic flow and vehicle occupancy rate, and then obtains the preliminary capacity attenuation characteristics, and finally introduces the dynamic change trend of the queue length for correction, thereby realizing a capacity evaluation system that is closer to reality.

[0016] Optionally, based on the traffic capacity attenuation characteristics, determining the traffic efficiency evaluation results of different sections specifically includes the following steps: According to the capacity attenuation characteristics, obtaining a section-improved capacity index and a section-reduced capacity index; Obtain the benchmark traffic capacity of the section based on the road geometry characteristics and traffic operation environment; By combining the section improvement capacity index, section reduction capacity index and section benchmark capacity, the traffic efficiency evaluation results of different sections are obtained.

[0017] By adopting the above technical solution, this application first quantifies the improvement and reduction indicators of each section based on the capacity attenuation characteristics, then determines the benchmark capacity according to the road geometry characteristics and the operating environment, and finally comprehensively evaluates these three types of indicators to obtain a more accurate section traffic efficiency; by considering the influencing factors in both positive and negative directions, a differentiated evaluation of section traffic efficiency is achieved.

[0018] In a second aspect, the present application provides a highway traffic flow detection and evaluation system, comprising: A vehicle operation data acquisition module is used to collect vehicle operation data through a video detector, a radar detector and a coil detector, wherein the vehicle operation data includes vehicle type distribution, vehicle speed distribution and vehicle head distance; A traffic flow heterogeneity index calculation module, used to calculate the traffic flow heterogeneity index according to the vehicle operation data, wherein the traffic flow heterogeneity index includes a large vehicle influence coefficient, a vehicle speed difference coefficient and a following safety degree; A traffic capacity attenuation characteristic acquisition module is used to determine the traffic flow operation state according to the traffic flow heterogeneity index, and obtain the traffic capacity attenuation characteristics under the mixed traffic conditions of different vehicle types; The traffic efficiency evaluation result determination module is used to determine the traffic efficiency evaluation results of different sections based on the traffic capacity attenuation characteristics.

[0019] In a third aspect, the present application provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned highway traffic flow detection and evaluation method when executing the computer program.

[0020] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-mentioned highway traffic flow detection and evaluation method.

[0021] In summary, the present application includes at least one of the following beneficial technical effects: 1. This application first uses video detectors, radar detectors and coil detectors to collaboratively collect parameters such as vehicle type distribution, vehicle speed distribution and head-to-head distance, and then calculates the vehicle flow heterogeneity index including large vehicle influence coefficient, vehicle speed difference coefficient and following safety degree based on these data, and then analyzes the traffic flow operation state to obtain the traffic capacity attenuation characteristics, and finally realizes the evaluation of the traffic efficiency of different road sections; it can more comprehensively and accurately reflect the operation quality of mixed traffic flow; 2. The traditional method only considers the proportion of large vehicles and ignores their spatial distribution characteristics, resulting in a large deviation between the evaluation results and the actual situation. For example, in a four-lane highway section, even if the same 25% large vehicle proportion is used, when large vehicles are concentrated in the two outer lanes, their impact on traffic flow is much more serious than when they are evenly distributed in each lane. This application first divides vehicles into three categories: large, medium and small according to the vehicle classification standard, and then calculates the number of vehicles of each type passing during the detection period to obtain the basic value of the large vehicle proportion, then analyzes the lateral distribution law of large vehicles to determine the weight coefficient, and finally combines the quantity proportion with the distribution weight to obtain a more accurate large vehicle impact coefficient. 3. This application first calculates the average speed characteristics of large, medium and small vehicles respectively, and then determines the weighted average reference speed based on the number of each model. Then, the degree of deviation between the actual speed of each model and the reference speed is analyzed to obtain the discrete characteristics, and then the fluctuation weight coefficient is determined according to the proportion of model composition. Finally, the speed discrete characteristics are combined with the fluctuation weight to obtain the final difference coefficient; thereby scientifically evaluating the speed stability in mixed traffic flow. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is a flow chart of a method for detecting and evaluating highway traffic flow according to an embodiment of the present application; Figure 2 It is a flowchart of step S200 in a method for detecting and evaluating highway traffic flow in an embodiment of the present application; Figure 3It is a flowchart of step S210 in a method for detecting and evaluating highway traffic flow in an embodiment of the present application; Figure 4 It is a flowchart of step S213 in a method for detecting and evaluating highway traffic flow in an embodiment of the present application; Figure 5 It is a flowchart of step S220 in a method for detecting and evaluating highway traffic flow in an embodiment of the present application; Figure 6 It is a flowchart of step S300 in a method for detecting and evaluating highway traffic flow according to an embodiment of the present application; Figure 7 It is a flowchart of step S400 in a method for detecting and evaluating highway traffic flow in an embodiment of the present application; Figure 8 This is a module diagram of a highway traffic flow detection and evaluation system according to an embodiment of the present application; Fig. 9 It is a diagram of the internal structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification and appended claims of the present application, the singular expressions "one", "a kind of", "said", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations comprising one or more listed items.

[0024] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0025] The embodiments of the present application are further described in detail below in conjunction with the drawings in the specification.

[0026] In the first aspect, the present application provides a method for detecting and evaluating highway traffic flow, referring to Figure 1 , including the following steps: S100, collecting vehicle operation data through a video detector, a radar detector, and a coil detector, where the vehicle operation data includes vehicle type distribution, vehicle speed distribution, and vehicle head distance.

[0027] Among them, this embodiment adopts the method of three different types of detectors working together. The video detector is mainly used for vehicle type recognition and vehicle counting, and realizes vehicle feature extraction through deep learning algorithm; the radar detector uses the Doppler effect principle to obtain the real-time driving speed of the vehicle; the coil detector is buried in the road surface to collect basic data such as vehicle passing time and occupancy time.

[0028] Specifically, the system collects data every 5 minutes. For vehicle type distribution, vehicles are divided into large vehicles, medium-sized vehicles and small vehicles according to their length; for vehicle speed distribution, the instantaneous speed of each vehicle when it passes through the detection section is recorded; for the distance between vehicle heads, it is calculated by the time difference between adjacent vehicles combined with the vehicle speed.

[0029] S200. Calculate a traffic flow heterogeneity index based on vehicle operation data, where the traffic flow heterogeneity index includes a large vehicle impact coefficient, a vehicle speed difference coefficient, and a following safety degree.

[0030] Among them, the traffic heterogeneity index is a comprehensive indicator reflecting the complexity of traffic flow, taking into account the influence of three dimensions: vehicle type composition, speed distribution and vehicle spacing. The large vehicle impact coefficient mainly considers the impact of large vehicles on space and dynamic characteristics; the vehicle speed difference coefficient reflects the speed difference between different vehicle types; and the following safety degree represents the safety margin between adjacent vehicles.

[0031] Specifically, the system first counts the proportion of large vehicles and calculates the large vehicle impact coefficient based on their lateral distribution characteristics; then it analyzes the speed distribution characteristics of different vehicle models and quantifies the speed difference through discrete units; finally, it compares the actual head-on distance with the theoretical safe distance to obtain the following safety degree.

[0032] S300: Determine the traffic flow operation status according to the traffic heterogeneity index, and obtain the traffic capacity attenuation characteristics under the mixed traffic conditions of different vehicle types.

[0033] Among them, based on the traffic heterogeneity index threshold method, the operating status is divided into three types: stable flow, unstable flow and congested flow.

[0034] Specifically, when the traffic heterogeneity index is in different ranges, it corresponds to different operating states: an index less than 0.3 indicates stable flow, 0.3-0.7 indicates unstable flow, and greater than 0.7 indicates congested flow.

[0035] S400: Determine the traffic efficiency evaluation results of different sections based on the traffic capacity attenuation characteristics.

[0036] Among them, the traffic efficiency evaluation adopts a segmentation and time period evaluation method, dividing the road into several characteristic sections, considering the section characteristics and operating environment of each section, and establishing differentiated evaluation standards.

[0037] In one embodiment, referring to Figure 2 In step S200, the traffic heterogeneity index is calculated according to the vehicle operation data. The traffic heterogeneity index includes the large vehicle influence coefficient, the vehicle speed difference coefficient and the following safety degree, which specifically includes the following steps: S210. Determine the proportion of large vehicles according to the distribution of vehicle models, and calculate the large vehicle impact coefficient according to the proportion of large vehicles.

[0038] S220: Calculate a vehicle speed difference coefficient based on the degree of dispersion between the actual driving speeds and average speeds of different vehicle models.

[0039] S230: Calculate the following safety degree according to the ratio of the actual headway distance between adjacent vehicles to the safe headway distance.

[0040] In this embodiment, the safety level of traffic flow is evaluated by comparing the relationship between the actual headway and the theoretical safety distance. The safe headway increases with the increase of vehicle speed, and different vehicle type combinations have different safety distance requirements.

[0041] Specifically, the system calculates the actual headway between adjacent vehicles based on the detection data, and determines the safe headway standard based on the front and rear vehicle models and speeds. For example, when the front vehicle is a large vehicle and the rear vehicle is a small vehicle, if the actual headway is 60 meters and the safe headway under the current working condition is 40 meters, the following safety degree is 1.5, indicating a sufficient safety margin. By statistically analyzing the following characteristics of multiple vehicle pairs, a following safety degree index that can characterize the overall safety level is obtained.

[0042] In one embodiment, referring to Figure 3 In step S210, the proportion of large vehicles is determined according to the distribution of vehicle types, and the large vehicle influence coefficient is calculated according to the proportion of large vehicles, which specifically includes the following steps: S211. Based on the vehicle classification standard, vehicles are divided into large vehicles, medium-sized vehicles and small vehicles.

[0043] In this embodiment, a multi-level classification method based on vehicle dimensions is adopted to extract vehicle characteristic parameters through video image processing technology. The system pre-establishes a vehicle type recognition model including multi-dimensional features such as vehicle length, vehicle height, and vehicle width to achieve fast and accurate classification of different types of vehicles.

[0044] S212. Count the cumulative number of vehicles of various types passing through during the detection period, and calculate the proportion of large vehicles in the total traffic flow.

[0045] By setting different time windows, short-term fluctuation characteristics and long-term change trends can be obtained at the same time. The system counts each type of vehicle passing through in each statistical period and calculates the corresponding composition ratio.

[0046] Specifically, the system records the passing time and vehicle type information of each vehicle, taking 15 minutes as the basic statistical cycle. For example, during the period from 8:00 to 8:15, a total of 450 vehicles were detected in a section, including 145 large vehicles, 85 medium-sized vehicles, and 220 small vehicles. The proportion of large vehicles in this period is 32.2%.

[0047] S213. Determine the large vehicle impact weight coefficient based on the number of lanes and the lateral distribution characteristics of large vehicles.

[0048] Among them, this embodiment adopts a lane-by-lane weighted evaluation method to consider the difference in the impact of the distribution of large vehicles in different lanes on traffic flow. By analyzing the lateral distribution of large vehicles, a weight calculation model considering lane position and adjacent lane interference is established.

[0049] S214. Calculate the large vehicle impact coefficient based on the proportion of large vehicles and the large vehicle impact weight coefficient.

[0050] In this embodiment, a nonlinear combination model is used to calculate the large vehicle influence coefficient, and a coupling relationship between the large vehicle proportion and the influence weight is established to obtain an evaluation result that is more in line with reality.

[0051] Specifically, a piecewise function is used to calculate the influence coefficient of large vehicles. When the proportion of large vehicles is less than 20%, the influence coefficient is mainly determined by the proportion; when the proportion of large vehicles is between 20% and 50%, the influence of the weight coefficient gradually increases; when the proportion of large vehicles exceeds 50%, the influence of the weight coefficient reaches the maximum. For example, the proportion of large vehicles in a certain section is 35%, and the weight coefficient is 1.35. After nonlinear combination calculation, the final large vehicle influence coefficient is 0.65.

[0052] In one embodiment, referring to Figure 4 In step S213, the weight coefficient of large vehicle impact is determined according to the number of lanes and the lateral distribution characteristics of large vehicles, which specifically includes the following steps: S2131. According to lane types, the lanes are divided into an emergency lane, an outermost lane, a middle lane, and an innermost lane to obtain a lane function classification result.

[0053] Among them, this embodiment adopts a lane classification method based on traffic functions, taking into account the usage characteristics and management requirements of different lanes. The emergency lane is mainly used in emergency situations; the outermost lane is the main truck lane; the middle lane is a mixed traffic lane; and the innermost lane is a fast overtaking lane.

[0054] Specifically, for a four-lane highway section, the lanes are numbered from right to left as emergency lane, lane 1 (outermost), lane 2 (middle), and lane 3 (innermost). For example, a standard road section is 5 kilometers long, each lane is 3.75 meters wide, and the emergency lane is 2.5 meters wide. The function of each lane is clearly defined through traffic markings and signs. The system pre-establishes a classification database based on lane numbers and functional characteristics.

[0055] S2132. Based on the lane function classification results, the proportion of time occupied by large vehicles on each lane is counted to obtain lane occupancy characteristics.

[0056] Among them, this embodiment adopts the time occupancy analysis method, and records the cumulative time that large vehicles occupy each lane through the detector. The system sets 5 minutes as the basic statistical cycle, records the passing time and stay period of large vehicles on each lane, and calculates the occupancy time ratio.

[0057] Specifically, coil detectors or video detectors are used to collect vehicle data and calculate the time occupancy rate of large vehicles in each lane. For example, in a 5-minute period, the total observation time of Lane 1 is 300 seconds, and the cumulative occupancy time of large vehicles is 120 seconds, so the occupancy rate of large vehicles in this lane is 40%. Similarly, the occupancy rates of other lanes are calculated to form a complete lane occupancy characteristic spectrum.

[0058] S2133. Determine a baseline weight value for each lane based on the lane function classification result and lane occupancy characteristics.

[0059] Among them, this embodiment comprehensively considers the functional attributes, design speed and traffic capacity of the lane, sets differentiated benchmark weights for different lanes, and reflects the differences in the degree of impact of large vehicles on each lane.

[0060] Specifically, the system sets the reference weight range according to the lane characteristics: emergency lane 1.5-2.0, outermost lane 1.2-1.5, middle lane 1.0-1.2, innermost lane 0.8-1.0. For example, the reference weight values ​​of each lane in a certain section are: emergency lane 1.8, lane 1 1.3, lane 2 1.1, lane 3 0.9.

[0061] S2134. Based on the lane occupancy characteristics, calculate the distribution of large vehicles in adjacent lanes to obtain the lane interference coefficient.

[0062] In this embodiment, an interference assessment method based on adjacent relations is used to analyze the coupling effect of large vehicles distributed on adjacent lanes. By establishing an interference model between lanes, the interference degree under different distribution combinations is calculated.

[0063] Specifically, when there are large vehicles in two adjacent lanes at the same time, the interference coefficient will increase with the increase of the occupancy rate of large vehicles in the two lanes. For example, if the occupancy rate of large vehicles in lane 1 and lane 2 is 40% and 25% respectively, the interference coefficient between the two lanes may reach 1.4; and when the occupancy rate of large vehicles in lane 2 and lane 3 is 25% and 10% respectively, the interference coefficient may be 1.2.

[0064] S2135. Calculate the large vehicle impact weight coefficient based on the benchmark weight value and the lane interference coefficient.

[0065] In this embodiment, a weighted comprehensive calculation method is adopted to nonlinearly combine the reference weight value of each lane with the corresponding interference coefficient.

[0066] In one embodiment, referring to Figure 5 In step S220, the speed difference coefficient is calculated based on the degree of dispersion between the actual driving speed and the average speed of different vehicle models, which specifically includes the following steps: S221. Calculate the average driving speeds of large vehicles, medium vehicles and small vehicles respectively based on the vehicle speed distribution data to obtain the speed characteristics of each vehicle type.

[0067] In this embodiment, a classification statistical analysis method is used to collect vehicle speed data through a multi-point radar detector. The system sets an independent data processing channel for each vehicle type and uses a sliding time window method to extract speed features.

[0068] S222. Calculate the weighted average speed of the entire vehicle flow based on the speed characteristics of each vehicle type to obtain a reference speed value.

[0069] In this embodiment, a weighted calculation method that takes into account the number of vehicles and vehicle model characteristics is adopted to determine the reference speed by establishing a multi-level weight system.

[0070] Specifically, the system first counts the proportion of each type of vehicle within 15 minutes, and then calculates the weighted value based on their average speed. For example, in a certain period of time, small cars account for 50%, medium-sized cars account for 30%, and large cars account for 20%. After considering the correction coefficient of vehicle type characteristics, the calculated weighted average speed of the entire vehicle flow is 88km / h, which is used as the evaluation benchmark value.

[0071] S223. Calculate the speed deviation of each vehicle type according to the speed characteristics of each vehicle type and the reference speed value to obtain a speed dispersion characteristic.

[0072] Among them, this embodiment calculates the deviation degree of the actual speed of each vehicle model, establishes a hierarchical deviation calculation model, and reflects the speed differences within and between vehicle models.

[0073] S224. Determine a speed fluctuation weight coefficient based on the speed discrete characteristics and the proportion of each vehicle type.

[0074] In this embodiment, the weight coefficient is determined according to the number distribution of each vehicle type and the speed dispersion degree. When the number of a certain type of vehicle is large and the speed dispersion degree is large, its weight coefficient will be increased accordingly.

[0075] S225. Calculate the vehicle speed difference coefficient according to the speed discrete characteristic and the speed fluctuation weight coefficient.

[0076] Specifically, the system uses a piecewise function to calculate the difference coefficient. When the speed deviation is less than 10km / h, the impact of the fluctuation weight is mainly considered; when the deviation is between 10-20km / h, the two have equivalent effects; when the deviation exceeds 20km / h, the discrete characteristics play a dominant role.

[0077] In one embodiment, the vehicle operation data also includes traffic flow, queue length and vehicle occupancy rate; Figure 6 In step S300, the traffic flow operation state is determined according to the traffic heterogeneity index, and the traffic capacity attenuation characteristics under the mixed traffic conditions of different vehicle types are obtained, which specifically includes the following steps: S310. Calculate the mixed traffic influence coefficient according to the traffic heterogeneity index.

[0078] In this embodiment, the large vehicle impact coefficient, the vehicle speed difference coefficient and the car-following safety degree are combined to obtain the mixed traffic impact coefficient.

[0079] S320: Determine road saturation based on traffic flow and vehicle occupancy rate.

[0080] In this embodiment, the road saturation is evaluated by combining traffic flow and occupancy rate. Traffic flow refers to the number of vehicles passing through a section per unit time, and the unit is vehicles per hour; vehicle occupancy rate refers to the ratio of the time that the detector is occupied by vehicles to the total observation time, expressed as a percentage.

[0081] Specifically, the flow rate and occupancy rate are calculated with a statistical cycle of 15 minutes. For example, 900 vehicles pass through a section within 15 minutes, and the detector is occupied by vehicles for 225 seconds out of the 900 seconds of observation time. The flow rate conversion value during this period is 3,600 vehicles / hour, and the occupancy rate is 25%. Through the combined analysis of these two parameters, the actual operating status of the road can be judged more accurately.

[0082] S330: Obtain a traffic capacity attenuation characteristic according to the mixed traffic influence coefficient and the road saturation.

[0083] In this embodiment, the system establishes a three-level attenuation evaluation standard: when the mixed traffic influence coefficient is less than 0.5 and the saturation is less than 0.8, it is slight attenuation; when one of the two indicators reaches the warning value, it is moderate attenuation; when both indicators exceed the warning value, it is severe attenuation.

[0084] S340. Correct the traffic capacity attenuation characteristics according to the queue length change trend.

[0085] In this embodiment, a dynamic correction method based on queuing theory is adopted to correct the attenuation assessment result by monitoring the spatiotemporal evolution characteristics of the queue length, so that assessment deviations can be discovered and handled in a timely manner, thereby improving the reliability of the results.

[0086] In one embodiment, referring to Figure 7 In step S400, based on the traffic capacity attenuation characteristics, the traffic efficiency evaluation results of different sections are determined, which specifically includes the following steps: S410. According to the capacity attenuation characteristics, obtain the section improvement capacity index and the section reduction capacity index.

[0087] S420. Obtain the benchmark traffic capacity of the section according to the geometric characteristics of the road and the traffic operating environment.

[0088] S430. Combining the section improvement capacity index, the section reduction capacity index and the section baseline capacity, the traffic efficiency evaluation results of different sections are obtained.

[0089] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0090] In the second aspect, the present application provides a highway traffic flow detection and evaluation system. The highway traffic flow detection and evaluation system of the present application is described below in combination with the above-mentioned highway traffic flow detection and evaluation method.

[0091] Reference Figure 8 , a highway traffic flow detection and evaluation system, comprising: The vehicle operation data acquisition module is used to collect vehicle operation data through video detectors, radar detectors and coil detectors. The vehicle operation data includes vehicle type distribution, vehicle speed distribution and vehicle head distance; The traffic flow heterogeneity index calculation module is used to calculate the traffic flow heterogeneity index based on vehicle operation data. The traffic flow heterogeneity index includes the large vehicle impact coefficient, vehicle speed difference coefficient and following safety degree; The traffic capacity attenuation characteristic acquisition module is used to determine the traffic flow operation status according to the traffic heterogeneity index and obtain the traffic capacity attenuation characteristics under the mixed traffic conditions of different vehicle types; The traffic efficiency evaluation result determination module is used to determine the traffic efficiency evaluation results of different sections based on the traffic capacity attenuation characteristics.

[0092] In one embodiment, the traffic heterogeneity index calculation module includes: A large vehicle impact coefficient calculation unit is used to determine the proportion of large vehicles according to the distribution of vehicle models, and calculate the large vehicle impact coefficient according to the proportion of large vehicles; A vehicle speed difference coefficient calculation unit, used to calculate the vehicle speed difference coefficient based on the degree of dispersion between the actual driving speed and the average speed of different vehicle models; The following safety calculation unit is used to calculate the following safety based on the ratio of the actual headway between adjacent vehicles to the safe headway.

[0093] In one embodiment, the vehicle influence coefficient calculation unit includes: A vehicle type classification module is used to classify vehicles into large vehicles, medium vehicles and small vehicles based on vehicle type classification standards; The large vehicle ratio calculation module is used to count the cumulative number of various types of vehicles passing through during the detection period and calculate the ratio of large vehicles in the total traffic flow; A weight coefficient determination module is used to determine the weight coefficient of large vehicle impact according to the number of lanes and the lateral distribution characteristics of large vehicles; The influence coefficient calculation module is used to calculate the large vehicle influence coefficient based on the proportion of large vehicles and the large vehicle influence weight coefficient.

[0094] In one embodiment, the weight coefficient determination module includes: A lane classification unit is used to divide the lane into an emergency lane, an outermost lane, a middle lane and an innermost lane according to the lane type, and obtain a lane function classification result; An occupancy feature statistical unit is used to count the proportion of large vehicles occupying time on each lane based on the lane function classification results to obtain lane occupancy features; A reference weight determination unit, used to determine a reference weight value of each lane according to the lane function classification result and the lane occupancy characteristics; An interference coefficient calculation unit, used to calculate the distribution of large vehicles in adjacent lanes based on lane occupancy characteristics to obtain an interference coefficient between lanes; The weight coefficient calculation unit is used to calculate the large vehicle impact weight coefficient based on the reference weight value and the lane interference coefficient.

[0095] In one embodiment, the vehicle speed difference coefficient calculation unit includes: The speed feature acquisition module is used to calculate the average driving speed of large vehicles, medium-sized vehicles and small vehicles respectively according to the vehicle speed distribution data, and obtain the speed characteristics of each vehicle type; The reference speed calculation module is used to calculate the weighted average speed of the entire vehicle flow based on the speed characteristics of each vehicle type to obtain a reference speed value; The discrete feature calculation module is used to calculate the speed deviation of each vehicle model according to the speed feature of each vehicle model and the reference speed value to obtain the speed discrete feature; A weight coefficient determination module is used to determine the speed fluctuation weight coefficient based on the speed discrete characteristics and the proportion of each vehicle type; The difference coefficient calculation module is used to calculate the vehicle speed difference coefficient according to the speed discrete characteristics and the speed fluctuation weight coefficient.

[0096] In one embodiment, the vehicle operation data also includes traffic flow, queue length and vehicle occupancy rate; the traffic capacity attenuation feature acquisition module includes: A mixed traffic influence coefficient calculation unit is used to calculate the mixed traffic influence coefficient according to the traffic heterogeneity index; A road saturation determination unit, used for determining the road saturation based on the traffic flow and the vehicle occupancy rate; An attenuation characteristic calculation unit, used for obtaining a capacity attenuation characteristic according to a mixed traffic influence coefficient and a road saturation; The characteristic correction unit is used to correct the capacity attenuation characteristic according to the queue length change trend.

[0097] In one embodiment, the traffic efficiency evaluation result determination module includes: A capacity index acquisition unit, used to acquire a section-enhanced capacity index and a section-reduced capacity index according to the capacity attenuation characteristics; A benchmark capacity determination unit is used to obtain the benchmark traffic capacity of a section according to the road geometry characteristics and traffic operation environment; The efficiency evaluation unit is used to combine the section improvement capacity index, the section reduction capacity index and the section benchmark capacity to obtain the traffic efficiency evaluation results of different sections.

[0098] In one embodiment, the present application provides an electronic device, which may be a server, and its internal structure diagram may be as follows: Fig. 9As shown. The electronic device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the electronic device is used to store data. The network interface of the electronic device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for detecting and evaluating highway traffic flow is implemented.

[0099] Those skilled in the art will understand that Fig. 9 The structure shown in the figure is merely a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the electronic device to which the scheme of the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0100] In one embodiment, an electronic device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0101] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the above-mentioned computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0102] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereto. Therefore, any equivalent changes made according to the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method for detecting and evaluating highway traffic flow, characterized in that: The steps include: Collecting vehicle operation data by means of a video detector, a radar detector and a coil detector, wherein the vehicle operation data includes vehicle type distribution, vehicle speed distribution and vehicle head distance; Calculating a traffic heterogeneity index according to the vehicle operation data, wherein the traffic heterogeneity index includes a large vehicle impact coefficient, a vehicle speed difference coefficient, and a following safety degree; According to the traffic heterogeneity index, the traffic flow operation state is determined to obtain the traffic capacity attenuation characteristics under the mixed traffic conditions of different vehicle types; Based on the traffic capacity attenuation characteristics, traffic efficiency evaluation results of different sections are determined.

2. The highway traffic flow detection and evaluation method according to claim 1, characterized in that: Calculating a traffic flow heterogeneity index according to the vehicle operation data, wherein the traffic flow heterogeneity index includes a large vehicle influence coefficient, a vehicle speed difference coefficient, and a following safety degree, specifically includes the following steps: Determine the proportion of large vehicles according to the distribution of vehicle models, and calculate the large vehicle impact coefficient according to the proportion of large vehicles; The speed difference coefficient is calculated based on the dispersion degree between the actual driving speed and the average speed of different vehicle models; The following safety degree is calculated based on the ratio of the actual headway between adjacent vehicles to the safe headway.

3. The highway traffic flow detection and evaluation method according to claim 2 is characterized in that: Determine the proportion of large vehicles according to the distribution of vehicle models, and calculate the large vehicle impact coefficient according to the proportion of large vehicles, specifically including the following steps: Based on the vehicle type classification standard, vehicles are divided into large vehicles, medium vehicles and small vehicles; Count the cumulative number of various types of vehicles passing through during the inspection period, and calculate the proportion of large vehicles in the total traffic flow; Determine the weight coefficient of large vehicle impact based on the number of lanes and the lateral distribution characteristics of large vehicles; The large vehicle impact coefficient is calculated according to the proportion of the large vehicle number and the large vehicle impact weight coefficient.

4. The highway traffic flow detection and evaluation method according to claim 3 is characterized in that: According to the number of lanes and the lateral distribution characteristics of large vehicles, the weight coefficient of large vehicle impact is determined, which specifically includes the following steps: According to the lane type, the lanes are divided into emergency lanes, outermost lanes, middle lanes and innermost lanes to obtain the lane function classification results; Based on the lane function classification results, the proportion of large vehicles occupying time on each lane is counted to obtain lane occupancy characteristics; Determining a reference weight value for each lane according to the lane function classification result and the lane occupancy characteristics; Based on the lane occupancy characteristics, the distribution of large vehicles in adjacent lanes is calculated to obtain an interference coefficient between lanes; The large vehicle impact weight coefficient is calculated according to the reference weight value and the lane-to-lane interference coefficient.

5. The highway traffic flow detection and evaluation method according to claim 3 is characterized in that: The vehicle speed difference coefficient is calculated based on the degree of dispersion between the actual driving speed and the average speed of different vehicle models, which specifically includes the following steps: According to the vehicle speed distribution data, the average driving speed of large vehicles, medium-sized vehicles and small vehicles is calculated respectively to obtain the speed characteristics of each vehicle type; Based on the speed characteristics of each vehicle type, a weighted average speed of the entire vehicle flow is calculated to obtain a reference speed value; According to the speed characteristics of each vehicle type and the reference speed value, the speed deviation of each vehicle type is calculated to obtain a speed dispersion characteristic; Determining a speed fluctuation weight coefficient based on the speed discrete characteristics and the proportion of each vehicle type; A vehicle speed difference coefficient is calculated according to the speed discrete characteristic and the speed fluctuation weight coefficient.

6. The highway traffic flow detection and evaluation method according to claim 1, characterized in that: The vehicle operation data also includes traffic flow, queue length and vehicle occupancy rate; according to the traffic heterogeneity index, the traffic flow operation state is determined to obtain the traffic capacity attenuation characteristics under the mixed traffic conditions of different vehicle types, specifically The steps include: Calculating a mixed traffic influence coefficient according to the traffic heterogeneity index; determining road saturation based on the traffic flow and vehicle occupancy; According to the mixed traffic influence coefficient and the road saturation, a traffic capacity attenuation characteristic is obtained; The capacity attenuation characteristic is corrected according to the queue length variation trend.

7. The highway traffic flow detection and evaluation method according to claim 1, characterized in that: Based on the traffic capacity attenuation characteristics, determining the traffic efficiency evaluation results of different sections specifically includes the following steps: According to the capacity attenuation characteristics, obtaining a section-improved capacity index and a section-reduced capacity index; Obtain the benchmark traffic capacity of the section based on the road geometry characteristics and traffic operation environment; By combining the section improvement capacity index, section reduction capacity index and section benchmark capacity, the traffic efficiency evaluation results of different sections are obtained.

8. A highway traffic flow detection and evaluation system, characterized in that: include: A vehicle operation data acquisition module is used to collect vehicle operation data through a video detector, a radar detector and a coil detector, wherein the vehicle operation data includes vehicle type distribution, vehicle speed distribution and vehicle head distance; A traffic flow heterogeneity index calculation module, used to calculate the traffic flow heterogeneity index according to the vehicle operation data, wherein the traffic flow heterogeneity index includes a large vehicle influence coefficient, a vehicle speed difference coefficient and a following safety degree; A traffic capacity attenuation characteristic acquisition module is used to determine the traffic flow operation state according to the traffic flow heterogeneity index, and obtain the traffic capacity attenuation characteristics under the mixed traffic conditions of different vehicle types; The traffic efficiency evaluation result determination module is used to determine the traffic efficiency evaluation results of different sections based on the traffic capacity attenuation characteristics.

9. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the highway traffic flow detection and evaluation method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the highway traffic flow detection and evaluation method described in any one of claims 1 to 7 are implemented.

Images