A Method, Device and Medium for Analyzing the Dynamic Behavior of Vehicles on the Highway

Abstract

The present application discloses a method, device and medium for analyzing the dynamic behavior of vehicles on highways, belonging to the field of electrical digital data processing. The method includes: preprocessing the multi-source data collected in real time, and fusing the preprocessed multi-source data to form the original path information of the vehicle; fitting the original path information based on the road network topology structure and the shortest path algorithm to generate a continuous and complete vehicle driving trajectory; based on the vehicle driving trajectory, comparing the multi-source data in real time to determine whether the vehicle has abnormal behavior, and if so, continue to judge the corresponding abnormal type of the vehicle and generate early warning information corresponding to the abnormal type; according to the multi-source data of the section to be predicted on the highway, predicting the traffic flow of the section to be predicted in real time, and displaying the traffic flow and early warning information of the section to be predicted through the user interaction interface, so as to realize the dynamic behavior analysis of vehicles on the highway.

Description

Technical Field

[0001] This application relates to the technical field of electrical digital data processing, and particularly to a method, device, and medium for analyzing the dynamic behaviors of in-transit vehicles on expressways. Background Art

[0002] At present, with the completion of the national expressway network system, the intelligent transportation system faces the dual challenges of massive data processing and precise management. Currently, expressway toll collection and vehicle behavior monitoring mainly rely on ETC gantry transaction data and license plate recognition data. However, due to the high complexity of the road network, equipment recognition errors, and data island problems, it is difficult to ensure the integrity and accuracy of vehicle travel path restoration. For example, when a vehicle passes through a gantry, transaction data may be lost due to signal interference, or the license plate recognition device may misjudge the license plate information, resulting in breakpoints or deviations in path fitting.

[0003] In the prior art, path restoration is mostly based on a single data source, such as ETC transaction records, lacking a multi-source data fusion and dynamic correction mechanism, and it is difficult to handle scenarios where gantry data is missing or incorrect. In addition, the ability to detect abnormal behaviors in real time is insufficient. For example, shielding ETC devices, swapping toll cards, etc., rely on manual rules for auditing afterwards, with low efficiency, easy to cause loss of tolls, and unable to dynamically combine multi-source data to improve the accuracy of determination. Moreover, the existing system lacks real-time tracking of in-transit vehicles, and traffic flow prediction is mostly based on historical statistics, unable to dynamically adjust the prediction model by combining real-time path data, resulting in low efficiency in resource allocation for congested sections. Summary of the Invention

[0004] Embodiments of this application provide a method, device, and medium for analyzing the dynamic behaviors of in-transit vehicles on expressways to solve the above technical problems.

[0005] On the one hand, embodiments of this application provide a method for analyzing the dynamic behaviors of in-transit vehicles on expressways, including:

[0006] Preprocess the multi-source data collected in real time, and fuse the preprocessed multi-source data to form the original path information of the vehicle;

[0007] Based on the road network topology structure and the shortest path algorithm, fit the original path information to generate a continuous and complete vehicle driving trajectory;

[0008] Based on the vehicle driving trajectory, compare the multi-source data in real time to determine whether the vehicle has abnormal behaviors. If so, continue to judge the corresponding abnormal type of the vehicle and generate a warning message corresponding to the abnormal type;

[0009] Based on the multi-source data of the section to be predicted on the highway, the traffic flow of the section to be predicted is predicted in real time, and through the user interaction interface, the traffic flow and warning information of the section to be predicted are displayed, realizing the dynamic behavior analysis of the vehicles on the highway.

[0010] In one implementation of the present application, the multi-source data collected in real time is preprocessed, and the preprocessed multi-source data is fused to form the original path information of the vehicle, specifically including:

[0011] Through the sensors set on the highway, the multi-source data of the vehicles in each section is collected in real time; wherein, the multi-source data includes ETC gantry transaction data, ETC gantry license plate recognition data, toll station entrance and exit transaction data, and over-limit data;

[0012] The collected multi-source data is cleaned and fused; wherein, the data to be cleaned includes ETC gantry reverse label data, outliers, and abnormal spatio-temporal data;

[0013] According to the license plate number, vehicle unique identifier, and passing time, the multi-source data after cleaning and fusion is associated, and the original path information of the vehicle sorted by time is generated.

[0014] In one implementation of the present application, the collected multi-source data is cleaned and fused, specifically including:

[0015] According to the special situation identifier in the ETC gantry transaction data, the ETC gantry reverse label data in the multi-source data is determined, and the ETC gantry reverse label data is screened out;

[0016] In the multi-source data after screening out the ETC gantry reverse label data, abnormal transaction times or abnormal license plate recognition data are identified, and the abnormal transaction times or abnormal license plate recognition data are filtered; wherein, the abnormal transaction time is used to represent that the transaction time is ahead or greater than the configurable time threshold, and the abnormal license plate recognition data is used to represent that the recognized license plate credibility of the ETC gantry license plate recognition data is zero, the recognized license plate is empty, or the recognized license plate is the default license plate;

[0017] According to the ETC gantry license plate recognition data, the distance between adjacent gantries and the time difference of the vehicle between adjacent gantries are calculated, and based on the distance between adjacent gantries and the time difference, the license plate recognition data of abnormal spatio-temporal exceeding the preset speed threshold is determined to eliminate the license plate recognition data of abnormal spatio-temporal.

[0018] In one implementation of the present application, based on the road network topology structure and the shortest path algorithm, the original path information is fitted to generate a continuous and complete vehicle driving trajectory, specifically including:

[0019] Abstract the ETC gantries, toll stations, and billing units on the highway as nodes in a directed graph, and form directed edges between two ordered nodes to construct the road network topology of the highway;

[0020] According to the upstream and downstream relationship of the vehicle passing through the ETC gantries on the highway, determine whether the ETC gantry is an invalid node; wherein, the invalid nodes include node direction mutation, speed overlimit, or isolated nodes;

[0021] According to the shortest path algorithm and the adjacent relationship between nodes, fill in the missing gantry information on the path between two ETC gantries to fit the original path information and generate a continuous and complete vehicle driving trajectory.

[0022] In an implementation manner of the present application, based on the vehicle driving trajectory, compare the multivariate data in real time to determine whether the vehicle has abnormal behavior. If so, continue to determine the abnormal type corresponding to the vehicle, specifically including:

[0023] According to the vehicle driving trajectory, compare the ETC gantry transaction data and the ETC gantry license plate recognition data in the multivariate data to obtain a comparison result;

[0024] Determine that the vehicle has abnormal behavior according to the comparison result, and according to the ETC gantry transaction data and the ETC gantry license plate recognition data, determine that the abnormal type corresponding to the abnormal behavior of the vehicle is shielding the passing medium, having an entry but no exit, truck trailer swapping, different passing media at the entry and exit, or U / J-type vehicle behavior.

[0025] In an implementation manner of the present application, according to the ETC gantry transaction data and the ETC gantry license plate recognition data, determine that the abnormal type corresponding to the abnormal behavior of the vehicle is shielding the passing medium, having an entry but no exit, truck trailer swapping, different passing media at the entry and exit, or U / J-type vehicle behavior, specifically including:

[0026] If the comparison result is that there is no gantry transaction flow for the license plate recognition flow of multiple consecutive ETC gantries, determine that the abnormal type corresponding to the abnormal behavior is shielding the passing medium;

[0027] If the comparison result is that the vehicle has an entry record but no exit payment flow, determine that the abnormal type corresponding to the abnormal behavior is having an entry but no exit; wherein, the exit payment flow includes the toll station exit payment flow, the toll station exit supplementary payment flow, and the toll station exit diversion flow;

[0028] If the comparison result is that the difference between the number of axles and the weight at the toll station exit and the toll station entry during the same trip is greater than the deviation threshold, determine that the abnormal type corresponding to the abnormal behavior is truck trailer swapping;

[0029] If the types of the passing media of the inlet flow and the outlet flow are inconsistent in the comparison result, determine that the abnormal type corresponding to the abnormal behavior is different inlet and outlet passing media;

[0030] If the comparison result is that the vehicle has a detour and triggers the minimum fare threshold at the outlet, determine that the abnormal type corresponding to the abnormal behavior is the U / J vehicle behavior.

[0031] In an implementation manner of the present application, according to the multi-source data of the section to be predicted on the highway, the traffic flow of the section to be predicted is predicted in real time, which specifically includes:

[0032] Construct vehicle pools for ETC gantries and toll stations, encode the real-time collected ETC gantry transaction data and the inlet and outlet flows of the toll stations by nodes, and store them in the vehicle pools, recording the vehicle positions and passing times;

[0033] After the vehicle passes through the ETC gantry or the toll station, remove the ETC gantry transaction data and the inlet and outlet flows of the toll station from the vehicle pool of the upstream node, and add them to the vehicle pool of the current node; among them, the upstream nodes of the ETC gantry include the upstream toll station and the upstream gantry, and the upstream nodes of the toll station include the upstream gantry in the upstream direction and the upstream gantry in the downstream direction;

[0034] Calculate the gantry traffic flow according to the traffic flow of the upstream gantry, the inlet traffic flow of the toll station, the outlet traffic flow of the toll station, and the traffic flow of the current gantry, and calculate the toll station traffic flow according to the traffic flow of the upstream gantry in the upstream direction, the traffic flow of the downstream gantry in the upstream direction, the traffic flow of the upstream gantry in the downstream direction, and the traffic flow of the downstream gantry in the downstream direction.

[0035] In an implementation manner of the present application, after displaying the traffic flow and warning information of the section to be predicted through the user interaction interface, the method further includes:

[0036] Highlight the vehicles with abnormal behaviors, and display the corresponding abnormal types, location information, and processing suggestions on the user interaction interface;

[0037] For the vehicles with disputes over highway tolls, synchronize the billing path and the actual fitted path, and display the difference area between the billing path and the actual fitted path;

[0038] Display the predicted traffic flow of the section and the statistical information of abnormal behaviors according to the time period and section range, and receive a correction instruction for the fitted path to optimize the algorithm parameters of the shortest path algorithm.

[0039] On the other hand, the embodiment of the present application further provides a highway in-vehicle dynamic behavior analysis device, and the device includes:

[0040] At least one processor;

[0041] And a memory communicatively connected to the at least one processor;

[0042] Wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute a method for analyzing dynamic behaviors of vehicles on a highway as described above.

[0043] On the other hand, an embodiment of the present application further provides a non-volatile computer storage medium storing computer-executable instructions, and when the computer-executable instructions are executed, a method for analyzing dynamic behaviors of vehicles on a highway as described above is implemented.

[0044] The embodiment of the present application provides a method, device and medium for analyzing dynamic behaviors of vehicles on a highway, which at least include the following beneficial effects:

[0045] By collecting and preprocessing multi-source data in real time, noise and redundant information can be effectively removed, the accuracy and availability of the data can be improved, and information from different sources can be integrated to form a more comprehensive and accurate original vehicle path information; based on the road network topology structure and the shortest path algorithm, the original path information is fitted to generate a continuous and complete vehicle driving trajectory, which helps to track the vehicle driving process more accurately and provides a reliable basis for abnormal behavior detection and traffic flow prediction; by comparing multi-source data in real time, abnormal behaviors of vehicles can be detected in time and the types of abnormalities can be quickly judged; generating corresponding warning information helps the management department to take measures in time to prevent potential safety hazards and traffic violations and improve road safety; predicting the traffic flow in real time according to the multi-source data of the section to be predicted can provide timely traffic condition information for the traffic management department, which helps to optimize traffic flow management, reduce congestion and delays, and improve road traffic efficiency; by displaying the traffic flow and warning information of the section to be predicted through the user interface, the information is more intuitive and easy to understand, which not only improves the user experience, but also provides decision-making support for the management department and helps to formulate more scientific and reasonable traffic management strategies. Description of the Drawings

[0046] The drawings described herein are used to provide a further understanding of the present application, and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation of the present application. In the drawings:

[0047] Figure 1 It is a schematic flowchart of a method for analyzing dynamic behaviors of vehicles on a highway provided by an embodiment of the present application;

[0048] Figure 2A flowchart of another method for analyzing dynamic behavior of vehicles on a highway provided in an embodiment of the present application;

[0049] Figure 3 A schematic diagram of the internal structure of a device for analyzing the dynamic behavior of vehicles on a highway provided in an embodiment of the present application. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0051] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0052] Figure 1 A flowchart of a method for analyzing dynamic behavior of vehicles on a highway provided in an embodiment of the present application.

[0053] The analysis method involved in the embodiments of the present application can be implemented by a terminal device or a server, and the present application does not impose any special restrictions on this. For the convenience of understanding and description, the following embodiments are described in detail by taking a server as an example.

[0054] It should be noted that the server may be a single device or a system consisting of multiple devices, that is, a distributed server, and this application does not make any specific limitation on this.

[0055] like Figure 1 As shown, a method for analyzing dynamic behavior of vehicles on a highway provided by an embodiment of the present application includes:

[0056] 101. Preprocess the multivariate data collected in real time, and fuse the preprocessed multivariate data to form the original path information of the vehicle.

[0057] Collect the traffic flow data of each vehicle passing on the highway in real time, including ETC gantry transaction data, license plate recognition data, entrance flow data, exit flow data, and overload control data. Pre-process the traffic flow data to remove invalid interference data; associate and fuse the vehicle traffic flow by time according to the license plate and vehicle traffic identification to form the original path information sorted by time.

[0058] Specifically, in one embodiment of the present application, the multivariate data collected in real time is preprocessed, and the preprocessed multivariate data is fused to form the original path information of the vehicle, which specifically includes:

[0059] Sensors installed on the highway collect multi-dimensional data of vehicles on each road section in real time; the multi-dimensional data includes ETC gantry transaction data, ETC gantry plate recognition data, toll station entrance and exit transaction data, and overweight control data;

[0060] Clean and fuse the collected multivariate data; the cleaned data includes ETC gantry reverse mark data, outliers, and abnormal spatiotemporal data;

[0061] According to the license plate number, vehicle unique identification and travel time, the cleaned and fused multivariate data are associated, and the original path information of the vehicle sorted by time is generated.

[0062] In one embodiment, ETC gantry transaction data, license plate recognition data, toll station entry and exit transaction data, and overweight control data are collected in real time. The collected data is further processed to form the original path information of vehicle passage through data cleaning and multivariate data fusion.

[0063] Data cleaning includes compliance verification of the collected data, such as ETC gantry ETC gantry reverse label data, outlier filtering, time and space verification, etc. to eliminate abnormal data and ensure data accuracy.

[0064] In one embodiment of the present application, cleaning and fusing the collected multi-dimensional data specifically includes:

[0065] According to the special situation identification in the ETC gantry transaction data, the ETC gantry reverse label data in the multivariate data is determined, and the ETC gantry reverse label data is filtered out;

[0066] Identify abnormal transaction time or abnormal license plate recognition data in the multivariate data after filtering out the ETC gantry reverse mark data, and filter the abnormal transaction time or abnormal license plate recognition data; wherein, the abnormal transaction time is used to indicate that the transaction time is ahead of or greater than a configurable time threshold, and the abnormal license plate recognition data is used to indicate that the recognition license plate credibility of the ETC gantry license plate recognition data is zero, the recognition license plate is empty, or the recognition license plate is a default license plate;

[0067] Based on the ETC gantry license plate recognition data, the distance between adjacent gantries and the time difference of vehicles at adjacent gantries are calculated, and based on the distance and time difference between adjacent gantries, the abnormal time and space license plate recognition data that exceeds the preset speed threshold is determined to eliminate the abnormal time and space license plate recognition data.

[0068] In one embodiment, excluding the reverse label data of the ETC gantry, and judging according to the special situation identification of the ETC gantry transaction record, screening out abnormal data such as special situation 154 - reverse interference and 186 - reverse interference.

[0069] Filter out outliers, screening out situations where the transaction time is ahead of or greater than the current time (configurable time threshold), the recognition license plate credibility of the ETC gantry license plate recognition data is zero, the recognized license plate is empty, the recognized license plate is the default license plate, etc.

[0070] Perform spatio-temporal verification. If there is a situation where the recognized license plate of the ETC gantry license plate recognition data is incorrect, it is necessary to perform spatio-temporal verification on it. Combining the time and gantry position information, verify the validity of the ETC gantry license plate recognition data within a specific time and space range. Judge whether the license plate recognition data of the gantry is reasonable according to the time difference between the capture time of the license plate recognition data of the upstream gantry of the vehicle and the capture time of the current gantry license plate recognition, and the distance between the gantries.

[0071] Add the gantry vehicle information of the vehicle to the vehicle pool of this gantry as the basis for downstream nodes to predict traffic flow. Correlate and fuse the collected multi-source data through conditions such as license plate number, unique vehicle passing identifier, passing time, etc., to form the original path information sorted by time.

[0072] 102. Based on the road network topology structure and the shortest path algorithm, fit the original path information to generate a continuous and complete vehicle driving trajectory.

[0073] Specifically, in one embodiment of the present application, based on the road network topology structure and the shortest path algorithm, fitting the original path information to generate a continuous and complete vehicle driving trajectory specifically includes:

[0074] Abstract the ETC gantries, toll stations, and charging units on the highway as nodes in a directed graph, and form directed edges between two ordered nodes to construct the road network topology structure of the highway;

[0075] According to the upstream and downstream relationship of the vehicle passing through the ETC gantries on the highway, determine whether the ETC gantry is an invalid node; among them, the invalid nodes include nodes with sudden direction change, speed overlimit, or isolated nodes;

[0076] According to the shortest path algorithm and the adjacent relationship between nodes, fill in the missing gantry information on the path between two ETC gantries to achieve the fitting of the original path information and generate a continuous and complete vehicle driving trajectory.

[0077] In one embodiment, based on the basic data such as the connectivity relationships among ETC gantries, toll stations, and billing units within the province, the province's toll infrastructure is abstractly drawn as a directed road network topology map. The ETC gantries, toll stations, and billing units are regarded as points, and a directed edge is formed between two ordered points to construct the vehicle driving path, providing a basic information base for the path restoration algorithm.

[0078] Use the cleaned in-transit data, including toll station entrance flow, toll station exit flow, ETC gantry transaction flow, and ETC gantry license plate recognition flow. The toll station entrance flow is used as the starting point, the toll station exit flow is used as the ending point, and the ETC gantry transaction flow and the gantry license plate recognition flow are sorted by time and fused as passing points. Combining with the road network topology map and the path algorithm fitting, the accurate driving trajectory of the vehicle from the entrance station to the exit station is restored.

[0079] The gantry nodes passed by the vehicle should be ordered and continuous. During the path fitting process, according to the directionality between nodes, by recording the previous node and transaction time of each gantry node, it is judged whether the gantry node is an invalid node. For example, if the node direction changes suddenly, whether the speed calculated from the distance / time between a certain node and its front and back exceeds a reasonable range. If the node position deviates greatly, it may cause the intersection nodes to be unable to be correctly connected and thus be identified as invalid nodes. Through the topological structure of the road network, isolated nodes or inaccessible nodes are identified. At the same time, according to the node adjacent relationship and the shortest path planning, the missing gantry node information between two gantry nodes is complemented. By deleting the invalid nodes in the path and filling the missing nodes in the path, the integrity and continuity of the path are ensured.

[0080] After path fitting, a complete and continuous vehicle driving path will be obtained, including the main information of the original flow of the vehicle driving, such as transaction time, amount information, node information, etc., and the gantry information restored by fitting.

[0081] 103. Based on the vehicle driving trajectory, compare multiple data in real time to determine whether the vehicle has abnormal behavior. If so, continue to judge the corresponding abnormal type of the vehicle and generate warning information corresponding to the abnormal type.

[0082] Specifically, in one embodiment of the present application, based on the vehicle driving trajectory, compare multiple data in real time to determine whether the vehicle has abnormal behavior. If so, continue to judge the corresponding abnormal type of the vehicle, which specifically includes:

[0083] According to the vehicle driving trajectory, compare the ETC gantry transaction data and the ETC gantry license plate recognition data in the multiple data to obtain a comparison result;

[0084] Determine that the vehicle has abnormal behavior based on the comparison result, and determine that the abnormal type corresponding to the vehicle's abnormal behavior is shielding the passing medium, entering without exiting, truck trailer swapping, different passing media at the entrance and exit, or U / J vehicle behavior according to the ETC gantry transaction data and ETC gantry license plate recognition data.

[0085] In one embodiment, during the vehicle's travel, based on the collected multi-source data for comparison and analysis, determine in real time whether the vehicle has abnormal behaviors such as shielding the passing medium, entering without exiting, truck trailer swapping, swapping, different passing media at the entrance and exit, and U / J abnormal behavior, and timely discover abnormal vehicles for early warning and interception.

[0086] In one embodiment of the present application, determine that the abnormal type corresponding to the vehicle's abnormal behavior is shielding the passing medium, entering without exiting, truck trailer swapping, different passing media at the entrance and exit, or U / J vehicle behavior according to the ETC gantry transaction data and ETC gantry license plate recognition data, specifically including:

[0087] If the comparison result is that there are consecutive multiple ETC gantries with license plate recognition records but no gantry transaction records, determine that the abnormal type corresponding to the abnormal behavior is shielding the passing medium;

[0088] If the comparison result is that the vehicle has an entrance passing record but no exit payment record, determine that the abnormal type corresponding to the abnormal behavior is entering without exiting; where the exit payment record includes the toll station exit payment record, the toll station exit supplementary payment record, and the toll station exit leading-out record;

[0089] If the comparison result is that the difference between the number of axles and the weight at the toll station exit and the toll station entrance during the same trip is greater than the deviation threshold, determine that the abnormal type corresponding to the abnormal behavior is truck trailer swapping;

[0090] If the comparison result is that the passing medium of the entrance record is inconsistent with the passing medium type of the exit record, determine that the abnormal type corresponding to the abnormal behavior is different passing media at the entrance and exit;

[0091] If the comparison result is that the vehicle detours and triggers the minimum fare threshold at the exit, determine that the abnormal type corresponding to the abnormal behavior is U / J vehicle behavior.

[0092] In one embodiment, after the vehicle's passing path is fused and analyzed by the service, if it shows that there are consecutive multiple gantries (the number of gantries can be set) with license plate recognition records but no gantry transaction records for this vehicle, it is regarded as having a suspicion of shielding the passing medium.

[0093] "Entry without exit" means that a vehicle normally obtains a passing record (such as an ETC or CPC card) at the highway entrance, but no payment transaction is generated at the exit. There may be behaviors such as following a vehicle through the toll gate, privately opening the toll gate, or abnormal toll software that result in non-payment of tolls. After the vehicle's passing path is analyzed through the path integration service, if there is no transaction record at the provincial boundary exit gantry, no license plate recognition record at the provincial boundary exit gantry, no normal transaction record at the toll station exit, no supplementary fee transaction record at the toll station exit, and no outgoing transaction record at the toll station exit, it is considered suspected of "entry without exit".

[0094] Analyzing data of tractors, if the number of axles at the exit is more than that at the entrance or the weight difference between the entrance and the exit is very large during the same journey, it is considered suspected of truck trailer swapping or hitch changing.

[0095] If the passing media for the entry and exit transactions of a vehicle during the same journey are inconsistent, it is suspected of card swapping, such as entering with a CPC card and exiting with an OBU, or entering with CPC card A and exiting with CPC card B.

[0096] When the billing amount in the passing media of a vehicle is greater than the threshold of the "minimum toll amount" for the reachable path, the vehicle adopts the operation rule of "minimum toll amount" billing, circles within the road network for a long time, and triggers "minimum toll amount" charging at the exit to achieve the purpose of running a long distance and paying a short toll.

[0097] 104. Based on the multi-source data of the section to be predicted on the highway, the traffic flow of the section to be predicted is predicted in real time, and through the user interface, the traffic flow and warning information of the section to be predicted are displayed to achieve the dynamic behavior analysis of vehicles on the highway.

[0098] The original path information is processed by the path fitting service to delete incorrect nodes in the path and fill in missing nodes, obtaining a complete and continuous vehicle driving path, and the vehicle driving trajectory is displayed in combination with the front-end GIS map.

[0099] The vehicle information in the ETC gantry transaction and toll station transaction records collected is added to the vehicle pool of this gantry. The traffic road network topology structure composed of toll stations and gantries, the road between each node and its downstream node is regarded as a vehicle pool, and each vehicle pool contains vehicles on the way. After the vehicle passes through a node, the vehicle is added to the vehicle pool of this gantry as the basis for predicting the traffic flow of the downstream node, and at the same time, the vehicle data in the vehicle pool of the upstream node is deleted.

[0100] Specifically, in an embodiment of the present application, predicting the traffic flow of the section to be predicted on the highway in real time based on the multi-source data of the section to be predicted specifically includes:

[0101] Build vehicle pools for ETC gantries and toll stations, encode the ETC gantry transaction data collected in real time and the toll station access and egress flows by node, and store them in the vehicle pools, recording the vehicle positions and passing times;

[0102] After the vehicle passes through an ETC gantry or a toll station, remove the ETC gantry transaction data and the toll station access and egress flows from the vehicle pool of the upstream node and add them to the vehicle pool of the current node; among them, the upstream nodes of the ETC gantry include the upstream toll station and the upstream gantry, and the upstream nodes of the toll station include the upstream gantry in the upward direction and the upstream gantry in the downward direction;

[0103] Calculate the gantry traffic flow based on the traffic flow of the upstream gantry, the traffic flow at the toll station entrance, the traffic flow at the toll station exit, and the traffic flow of the current gantry, and calculate the toll station traffic flow based on the traffic flow of the upstream gantry in the upward direction, the traffic flow of the downstream gantry in the upward direction, the traffic flow of the upstream gantry in the downward direction, and the traffic flow of the downstream gantry in the downward direction.

[0104] In one embodiment, through the vehicle passing data collected, the number of in-transit vehicles and vehicle information traveling on the highway can be calculated, and the traffic flow of the section can be predicted in real time, etc., providing real-time data support for the traffic management department, helping the management department to reasonably allocate traffic resources, optimize the traffic flow, reduce congestion, and improve the road traffic efficiency.

[0105] For the traffic road network topology composed of toll stations and gantries, set up in-transit vehicle pools for toll stations and gantries. When preprocessing data, store the vehicle information of the toll station flow and the ETC gantry transaction flow according to the toll station code and the gantry code, and formulate a node traffic flow prediction algorithm to provide toll station and gantry traffic flow estimation services. The predicted traffic flow information can be provided for front-end display and provide external interfaces, helping the management department to reasonably allocate traffic resources and improve the road traffic efficiency.

[0106] Regard the road between each node and the downstream node as a vehicle pool, and each vehicle pool contains in-transit vehicles. After the vehicle passes through the node, add the vehicle to the vehicle pool of this gantry as the basis for predicting the traffic flow of the downstream node, and at the same time delete the vehicle data in the vehicle pool of the upstream node.

[0107] Without considering the hub interchange, generally there are two upstream nodes for the gantry: the upstream toll station and the upstream gantry, and generally there are also two upstream nodes for the toll station: the upstream gantry in the upward direction and the upstream gantry in the downward direction. From this, the traffic flow calculation formula for the gantry or toll station can be obtained:

[0108] Gantry traffic flow = upstream gantry traffic flow + (toll station entrance - toll station exit (vehicles passing through the upstream gantry)) - the traffic flow of this gantry.

[0109] Toll station traffic flow = Upstream gantry of the up direction - Downstream gantry of the up direction + Upstream gantry of the down direction - Downstream gantry of the down direction.

[0110] In an embodiment of the present application, after displaying the traffic flow and warning information of the road section to be predicted through the user interaction interface, it further includes:

[0111] Highlight the vehicles with abnormal behaviors, and display the corresponding abnormal types, location information and handling suggestions on the user interaction interface;

[0112] For vehicles with disputes over highway tolls, synchronize the charging path with the actual fitted path, and display the difference area between the charging path and the actual fitted path;

[0113] Display the predicted traffic flow of the road section and the statistical information of abnormal behaviors according to the time period and road section range, and receive the correction instruction for the fitted path to optimize the algorithm parameters of the shortest path algorithm.

[0114] In one embodiment, intuitively display the location information of ETC gantries and toll stations in this province and the vehicle driving trajectories based on the GIS map. First, for the query of vehicles on the way, display the information of vehicles on the way at ETC gantries and toll stations. The information of vehicles on the way can be queried by license plate number, vehicle type, and passing nodes.

[0115] For the query of vehicle historical paths, provide the query of vehicle historical passing records by license plate, entry time, and exit time, restore the vehicle passing trajectory according to the historical records, and perform path rendering on the map to intuitively display the charging path and the actual driving trajectory of the vehicle. When there is a toll dispute, it can provide clear driving path evidence for the vehicle owner to help resolve the toll dispute. Support the development of related services such as inspection and data analysis.

[0116] For the query of vehicle abnormal behavior classification, provide the query of abnormal driving records of vehicles by license plate, time, and abnormal behavior, and support the simultaneous display of the charging path and the actual driving path on the map. For the prediction of traffic flow of road sections, provide the query of predicted traffic flow of road sections, toll stations, and gantries to help the management department reasonably dispatch traffic resources in advance.

[0117] The present application can perform real-time path fitting processing on vehicles on the way, timely detect the abnormal behaviors of vehicles, can perform real-time monitoring and warning on vehicles, perform real-time prediction on the traffic flow of road sections, provide real-time data support for the traffic management department, present the vehicle driving trajectory to toll collectors and users in a friendly map-based manner, improve the user experience, and provide strong support for the intelligent management of highways.

[0118] Figure 2 It is a flow chart of another method for analyzing the dynamic behaviors of vehicles on the way on a highway provided by the embodiment of the present application. AsFigure 2 As shown, it collects multi-source data such as collection entrances, exits, gantries, and over-limit vehicle control, and receives this traffic flow. Then, it performs real-time fusion services on the passing traffic flow, estimates the real-time traffic volume, realizes the traffic volume estimation service, and further pushes and stores the estimated traffic volume into the vehicle pool of in-transit vehicles. At the same time, it also completes the path through comparison of passing paths, realizes the path inspection service, generates a unique traffic flow, and stores the unique traffic flow into a preset passing database.

[0119] In addition, this application also provides a user interaction interface, and there is a unified query interface on the user interaction interface, which includes a traffic flow query interface, an in-transit vehicle query, and a toll station traffic volume query.

[0120] The above is the method embodiment proposed by this application. Based on the same inventive concept, the embodiment of this application also provides a dynamic behavior analysis device for in-transit vehicles on expressways, and its structure is as Figure 3 shown.

[0121] Figure 3 This is the internal structure schematic diagram of a dynamic behavior analysis device for in-transit vehicles on expressways provided by the embodiment of this application. As Figure 3 shown, the device includes:

[0122] At least one processor;

[0123] And a memory communicatively connected to at least one processor;

[0124] Wherein, the memory stores instructions executable by at least one processor, and the instructions are executed by at least one processor to enable at least one processor to:

[0125] Preprocess the multi-source data collected in real time, and fuse the preprocessed multi-source data to form the original path information of the vehicle;

[0126] Based on the road network topology structure and the shortest path algorithm, fit the original path information to generate a continuous and complete vehicle driving trajectory;

[0127] Based on the vehicle driving trajectory, compare the multi-source data in real time to determine whether the vehicle has abnormal behavior. If so, continue to judge the abnormal type corresponding to the vehicle, and generate a warning message corresponding to the abnormal type;

[0128] According to the multi-source data of the section to be predicted on the expressway, predict the traffic volume of the section to be predicted in real time, and display the traffic volume and warning message of the section to be predicted through the user interaction interface, so as to realize the dynamic behavior analysis of in-transit vehicles on expressways.

[0129] The embodiments of this application also provide a non-volatile computer storage medium storing computer-executable instructions, which, when executed, can:

[0130] Preprocess the multi-source data collected in real time, and fuse the preprocessed multi-source data to form the original path information of the vehicle;

[0131] Based on the road network topology and the shortest path algorithm, fit the original path information to generate a continuous and complete vehicle driving trajectory;

[0132] Based on the vehicle driving trajectory, compare the multi-source data in real time to determine whether the vehicle has abnormal behavior. If so, continue to judge the corresponding abnormal type of the vehicle and generate a warning information corresponding to the abnormal type;

[0133] According to the multi-source data of the section to be predicted on the highway, predict the traffic flow of the section to be predicted in real time, and display the traffic flow and warning information of the section to be predicted through the user interaction interface, so as to realize the dynamic behavior analysis of the vehicles on the highway.

[0134] The above are only the embodiments of this application and are not used to limit this application. For those skilled in the art, various changes and modifications can be made to this application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this application shall be included within the scope of the claims of this application.

Claims

1. A method for analyzing the dynamic behavior of vehicles on the highway, characterized in that The method includes: Preprocessing the multi-source data collected in real time, and fusing the preprocessed multi-source data to form the original path information of the vehicle; Based on the road network topology structure and the shortest path algorithm, fitting the original path information to generate a continuous and complete vehicle driving trajectory; Based on the vehicle driving trajectory, comparing the multi-source data in real time to determine whether the vehicle has abnormal behavior. If so, continue to judge the abnormal type corresponding to the vehicle and generate a warning information corresponding to the abnormal type; According to the multi-source data of the section to be predicted on the highway, predicting the traffic flow of the section to be predicted in real time, and displaying the traffic flow and warning information of the section to be predicted through a user interaction interface, so as to realize the dynamic behavior analysis of the vehicles on the highway; Based on the road network topology structure and the shortest path algorithm, fitting the original path information to generate a continuous and complete vehicle driving trajectory, specifically including: Abstracting the ETC gantries, toll stations and charging units on the highway as nodes in a directed graph, and forming directed edges between two ordered nodes to construct the road network topology structure of the highway; Determining whether an ETC gantry is an invalid node according to the upstream and downstream relationships of the vehicle passing through the ETC gantry on the highway; wherein, the invalid nodes include node direction mutation, speed overlimit or isolated nodes; According to the shortest path algorithm and the adjacent relationship between nodes, filling in the missing gantry information in the path between two ETC gantries to realize the fitting of the original path information and generate a continuous and complete vehicle driving trajectory; According to the multi-source data of the section to be predicted on the highway, predicting the traffic flow of the section to be predicted in real time, specifically including: Constructing a vehicle pool for ETC gantries and toll stations, encoding the ETC gantry transaction data and the toll station access and exit flow data collected in real time according to nodes, and storing them in the vehicle pool, and recording the vehicle position and passing time; After the vehicle passes through an ETC gantry or a toll station, removing the ETC gantry transaction data and the toll station access and exit flow data from the vehicle pool of the upstream node and adding them to the vehicle pool of the current node; wherein, the upstream nodes of the ETC gantry include the upstream toll station and the upstream gantry, and the upstream nodes of the toll station include the upstream gantry in the upstream direction and the upstream gantry in the downstream direction; Calculating the gantry traffic flow according to the traffic flow of the upstream gantry, the traffic flow at the toll station entrance, the traffic flow at the toll station exit and the traffic flow of the current gantry, and calculating the toll station traffic flow according to the traffic flow of the upstream gantry in the upstream direction, the traffic flow of the downstream gantry in the upstream direction, the traffic flow of the upstream gantry in the downstream direction and the traffic flow of the downstream gantry in the downstream direction; 2. The dynamic behavior analysis method of in-transit vehicles on an expressway according to claim 1, wherein, Preprocessing the multi-source data collected in real time, and fusing the preprocessed multi-source data to form the original path information of the vehicle, specifically including: Real-time collecting the multi-source data of vehicles in each section through the sensors set on the highway; wherein, the multi-source data includes ETC gantry transaction data, ETC gantry identification data, toll station entrance and exit transaction data and over-limit data; Cleaning and fusing the collected multi-source data; wherein, the data to be cleaned includes ETC gantry reverse label data, outliers and abnormal spatio-temporal data; Associate the multi-source data after cleaning and fusion based on the license plate number, vehicle unique identifier, and passing time, and generate the original path information of the vehicle sorted by time.

3. The dynamic behavior analysis method of in - transit vehicles on expressways according to claim 2, characterized in that, Clean and fuse the collected multi-source data, specifically including: Determine the ETC gantry reverse label data in the multi-source data according to the special situation identifier in the ETC gantry transaction data, and filter out the ETC gantry reverse label data; Identify abnormal transaction times or abnormal license identification data in the multi-source data after filtering out the ETC gantry reverse label data, and filter the abnormal transaction times or abnormal license identification data; wherein, the abnormal transaction time is used to indicate that the transaction time is ahead or greater than the configurable time threshold, and the abnormal license identification data is used to indicate that the recognized license plate credibility of the ETC gantry license identification data is zero, the recognized license plate is empty, or the recognized license plate is the default license plate; Calculate the distance between adjacent gantries and the time difference of the vehicle between adjacent gantries according to the ETC gantry license identification data, and determine the license identification data of abnormal space-time exceeding the preset speed threshold based on the distance between adjacent gantries and the time difference, so as to eliminate the license identification data of abnormal space-time.

4. A method for analyzing the dynamic behavior of in - transit vehicles on an expressway according to claim 1, characterized in that, Based on the vehicle driving trajectory, compare the multi-source data in real time to determine whether the vehicle has abnormal behavior. If so, continue to judge the abnormal type corresponding to the vehicle, specifically including: Compare the ETC gantry transaction data and the ETC gantry license identification data in the multi-source data according to the vehicle driving trajectory to obtain a comparison result; Determine that the vehicle has abnormal behavior according to the comparison result, and determine that the abnormal type corresponding to the abnormal behavior of the vehicle is shielding the passing medium, having an entry without an exit, truck trailer swapping, different passing media at the entrance and exit, or U / J vehicle behavior according to the ETC gantry transaction data and the ETC gantry license identification data.

5. The dynamic behavior analysis method of in-route vehicles on an expressway according to claim 4, characterized in that Determine that the abnormal type corresponding to the abnormal behavior of the vehicle is shielding the passing medium, having an entry without an exit, truck trailer swapping, different passing media at the entrance and exit, or U / J vehicle behavior according to the ETC gantry transaction data and the ETC gantry license identification data, specifically including: If the comparison result is that there is no gantry transaction flow for the gantry license identification flow in multiple consecutive ETC gantries, determine that the abnormal type corresponding to the abnormal behavior is shielding the passing medium; If the comparison result is that the vehicle has an entrance passing record without an exit payment flow, determine that the abnormal type corresponding to the abnormal behavior is having an entry without an exit; wherein, the exit payment flow includes the toll station exit payment flow, the toll station exit supplementary payment flow, and the toll station exit leading-out flow; If the comparison result is that the difference between the number of axles and the weight at the toll station exit and the toll station entrance in the same trip is greater than the deviation threshold, determine that the abnormal type corresponding to the abnormal behavior is truck trailer swapping; If the comparison result is that the passing medium of the entrance flow is inconsistent with the type of the passing medium of the exit flow, determine that the abnormal type corresponding to the abnormal behavior is different passing media at the entrance and exit; If the comparison result is that the vehicle has a detour and triggers the minimum fare threshold at the exit, determine that the abnormal type corresponding to the abnormal behavior is U / J vehicle behavior.

6. The dynamic behavior analysis method of in - transit vehicles on an expressway according to claim 1, characterized in that, After displaying the traffic flow and warning information of the section to be predicted through the user interaction interface, the method further includes: Highlighting the vehicles with abnormal behaviors, and displaying the corresponding abnormal types, location information, and handling suggestions on the user interaction interface; For vehicles with disputes over highway tolls, synchronizing the billing path with the actual fitted path, and displaying the difference area between the billing path and the actual fitted path; Displaying the predicted traffic flow of the section and the statistical information of abnormal behaviors according to the time period and section range, and receiving a correction instruction for the fitted path to optimize the algorithm parameters of the shortest path algorithm.

7. An on-road vehicle dynamic behavior analysis device for expressways, characterized in that, The device includes: At least one processor; And a memory communicatively connected to the at least one processor; Wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute a method for analyzing the dynamic behaviors of vehicles on a highway as described in any one of claims 1-6.

8. A non-volatile computer storage medium storing computer-executable instructions, characterized in that, When the computer-executable instructions are executed, a method for analyzing the dynamic behaviors of vehicles on a highway as described in any one of claims 1-6 is implemented.

Images