Road traffic blocking identification and accident site positioning method

Abstract

The invention discloses a road traffic blocking identification and accident site positioning method. The method comprises the following steps: acquiring expressway vehicle running data in real time through an ETC door frame; data preprocessing and data correction are carried out by comparing timestamps of adjacent records; extracting the identification information of the vehicles with the same journey in the front and rear gantries, and calculating the average running speed of the vehicles on each journey; drawing a vehicle space-time diagram of each portal section; and taking an intersection point of the spatial-temporal trajectories of the fast vehicle and the slow vehicle at the starting moment and the ending moment of the abnormal time difference as a blocking ending spatial-temporal position judgment point. No extra monitoring equipment needs to be deployed, the data reliability problem and the real-time problem of the jump door frame data are solved only based on the ETC door frame data, and second-level road blocking and accident site positioning are achieved.

Description

Technical Field

[0001] This invention relates to the field of intelligent transportation technology, and more particularly to the field of traffic data analysis and processing, specifically a method and system for real-time traffic disruption detection and accident location using highway ETC gantry data and spatiotemporal maps. Background Technology

[0002] Currently, existing solutions for road traffic disruption identification and accident location typically require the deployment of multiple devices such as radar, cameras, and fiber optic sensors. These devices are not only expensive to procure, but also difficult and costly to maintain, which limits the widespread application of these technologies.

[0003] Traditional ETC data analysis methods struggle to quickly detect sudden road traffic disruptions. Their complex data analysis processes and slow processing speeds result in significant delays in response to detection results, hindering timely and effective information support for traffic management departments and impacting the efficiency of emergency response to sudden traffic incidents.

[0004] The raw ETC data has many problems. Redundant records are quite common, such as duplicate timestamps, which increases the burden of data processing and may interfere with analysis results. False detections also occur from time to time, such as vehicle jump-over records, which can affect the accuracy of the data. At the same time, there are also problems with missing data, such as incomplete transaction information due to equipment malfunctions, all of which seriously reduce the reliability of the data.

[0005] From a micro perspective, some ETC data analysis methods only clean and cluster the data without constructing a spatiotemporally correlated trajectory network. This can easily lead to discontinuities in gantry jump data and fail to systematically correct false detection data such as gantry jumps.

[0006] Some ETC data analysis methods do not incorporate spatiotemporal trajectory intersection location, making it impossible to detect abnormal trajectories, accurately locate blockage points, or accurately divide abnormal time periods, resulting in insufficient real-time performance and data reliability.

[0007] Meanwhile, some blocking identification models do not take into account the time difference between fast and slow trains, which can easily trigger false blocking behavior and affect the accurate location of the accident. Summary of the Invention

[0008] The technical problem to be solved by the present invention is to address the above-mentioned deficiencies of the prior art by providing a method and system for identifying road traffic disruptions and locating accident sites based on highway ETC gantry data and spatiotemporal maps. This method and system does not require additional monitoring equipment and solves the data reliability and real-time issues of gantry data based solely on ETC gantry data, achieving second-level road disruption and accident location.

[0009] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is as follows: A method for identifying road traffic disruptions and locating accident sites based on highway ETC gantry data and spatiotemporal maps includes the following steps: S1: Real-time acquisition of highway vehicle flow data via ETC gantry; the vehicle flow data includes at least vehicle identification information, ETC gantry location and name information, and entry / exit time; S2: Combine the geographical topology of the ETC gantry within the monitored highway section with the vehicle flow data to establish gantry section information; perform data preprocessing and correction by comparing the timestamps of adjacent records; extract vehicle identification information with the same journey from the front and rear gantries; and calculate the average speed of the vehicle on each journey by measuring the travel distance and travel time between each gantry segment. S3: Draw the vehicle spatiotemporal diagram for each gantry section; classify vehicles in each section of the vehicle spatiotemporal diagram into express and slow vehicles according to their speed; obtain the arrival time of adjacent vehicles to the next gantry and calculate the arrival time difference between adjacent vehicles; if the time difference exceeds a set threshold, it is judged as an abnormal time difference; take the intersection of the spatiotemporal trajectories of the last two normally operating express and slow vehicles at the start time of the abnormal time difference as the blocking start spatiotemporal position point; take the intersection of the spatiotemporal trajectories of the first two abnormally operating express and slow vehicles to pass through the next gantry at the end time of the abnormal time difference as the blocking end spatiotemporal position point.

[0010] In the above technical solution, in step S1, the vehicle identification information includes the vehicle license plate number, vehicle model, and vehicle sequence number when passing through a certain gantry.

[0011] In the above technical solution, in step S2, if the timestamp interval of the same vehicle at the same gantry is less than the first time interval, only one vehicle flow data is retained as valid data, while the other redundant data is deleted or marked.

[0012] In the above technical solution, in step S2, if the dimensions and content of the vehicle flow data of the same vehicle at the same gantry timestamp are completely consistent, one record is retained; otherwise, all records are retained.

[0013] In the above technical solution, in step S2, when the detection distance between the first and third gantry in a vehicle flow record is greater than the normal distance between the two gantry in the gantry topology diagram, and the record of the second gantry between the two gantry is missing, data correction is performed to insert the virtual passage time at the second gantry. ,in It is the distance from the first gantry to the second gantry; The average speed of 10 adjacent vehicles from the first gantry to the second gantry; The time of passage at the first gantry.

[0014] In the above technical solution, in step S3, the threshold is set to be 2-4 times the average time difference of all vehicles in the same time and space interval.

[0015] In the above technical solution, step S3 draws a spatiotemporal map of vehicles in each gantry segment by using the passage time of vehicles passing through two or more consecutive gantries and the distance between the gantries in each vehicle flow data.

[0016] In the above technical solution, in step S3, the intersection of the spatiotemporal trajectories of the last two normally operating express trains and slow trains at the start of the abnormal time difference is taken as the spatiotemporal position point of the blocking start, and the intersection of the spatiotemporal trajectories of the two abnormally operating express trains and slow trains that first pass through the next gantry at the end of the abnormal time difference is taken as the spatiotemporal position point of the blocking end.

[0017] In the above technical solution, in step S3, the last two normally operating express trains and slow trains at the start time of the abnormal time difference are determined, and the two abnormally operating express trains and slow trains that first pass through the next gantry at the end time of the abnormal time difference are determined. The intersection points of the spatiotemporal trajectories at the start time of the abnormal time difference and the intersection points of the spatiotemporal trajectories at the end time of the abnormal time difference are calculated according to the ideal running time and interval distance of each train.

[0018] In the above technical solution, step S3 is replaced by drawing a vehicle spatiotemporal map of each gantry section and finding the trajectory of the last vehicle before the time of road traffic closure in the spatiotemporal map. The location of the intersection of this trajectory with the spatiotemporal map trajectories of other vehicles is taken as the traffic closure location, and the time of the intersection is taken as the time of the closure.

[0019] Therefore, this invention utilizes the vehicle's passage through ETC gantries to create a spatiotemporal map of the vehicle's passage through different gantries. The vehicles in each section of the spatiotemporal map are divided into express and slow vehicles according to their speed. The arrival time of adjacent vehicles at the next gantry is obtained and the arrival time difference between adjacent vehicles is calculated. The intersection of the spatiotemporal trajectories of the last two normally operating express and slow vehicles at the start time of the abnormal time difference is taken as the spatiotemporal location point of the blockage. The intersection of the spatiotemporal trajectories of the first two abnormally operating express and slow vehicles to pass through the next gantry at the end time of the abnormal time difference is taken as the spatiotemporal location point of the blockage, thus achieving accurate and timely S-level positioning of traffic blockage.

[0020] Alternatively, this invention finds the trajectory of the last vehicle before the road traffic disruption occurred in the spatiotemporal map, and uses the location of the intersection of this trajectory with the spatiotemporal map trajectories of other vehicles as the location of the road traffic disruption and accident.

[0021] Both of the above solutions can achieve the goal of real-time detection of road traffic disruptions and location of accident sites without the huge investment required for installing radar, cameras, fiber optic sensors, Beidou displacement sensors, etc.

[0022] Based on the above method, the present invention also provides: An electronic device includes a processor, a memory, and a program stored in the memory and executable on the processor, wherein the program, when executed by the processor, performs the steps of any of the methods described above.

[0023] A computer-readable storage medium, characterized in that the storage medium stores a program, which, when executed by a processor, implements the steps of any of the methods described above.

[0024] Compared to the present invention, the beneficial effects produced by the present invention include at least one of the following: This invention provides a method for identifying road traffic disruptions and locating accident sites. It acquires real-time highway vehicle flow data via ETC gantries; preprocesses and corrects data by comparing timestamps of adjacent records; extracts vehicle identification information from preceding and following gantries with the same travel distance, calculates the average speed of vehicles on each segment, and draws a spatiotemporal map of vehicles for each gantry segment. The intersection of the spatiotemporal trajectories of fast and slow vehicles at the start and end times of abnormal time differences is used as the spatiotemporal location determination point at the end of the disruption. This method eliminates the need for additional monitoring equipment, addressing the reliability and real-time issues of gantry-skipping data solely based on ETC gantry data, achieving second-level road disruption and accident site location.

[0025] Significantly reduced hardware costs: Existing road traffic obstruction identification and accident location solutions often require the deployment of multiple devices such as radar, cameras, and fiber optic sensors. These devices are expensive to purchase and maintain, limiting their widespread application. This invention is entirely based on ETC gantry data, eliminating the need for additional monitoring equipment and reducing hardware investment by over 90%. This significantly lowers the application cost of the technology, eliminating the need for substantial funds for equipment procurement and maintenance, alleviating the financial burden on traffic management departments, and facilitating its wider adoption in more regions, thus expanding the coverage of road traffic obstruction identification and accident location technology.

[0026] Significantly Improved Real-Time Performance: Traditional ETC data analysis methods suffer from complex processes, slow processing speeds, and significant delays in response to sudden road traffic disruptions. This hinders timely and effective information support for traffic management departments, impacting emergency response efficiency. This invention utilizes a spatiotemporal graph algorithm to achieve second-level traffic disruption identification and location, reducing emergency response time to within 60 seconds. In the event of anomalies on highways, it can quickly detect road disruptions and locate accident sites. For example, in the event of a traffic accident, information can be rapidly relayed to traffic management departments, allowing rescue personnel to arrive at the scene more quickly, reducing congestion and losses, and significantly improving emergency response capabilities for sudden traffic incidents.

[0027] Data reliability is significantly improved: ETC raw data suffers from redundant records, false positives, and missing data, reducing data reliability. This invention proposes a strategy of redundancy removal, false positive filtering, and trip ID matching to complete the data, increasing data accuracy to 98%. Removing redundant data reduces the data processing burden and avoids interference with analysis results; filtering false positives ensures data accuracy; and trip ID matching completes missing data, guaranteeing data integrity. Accurate and reliable data provides a solid foundation for road traffic disruption identification and accident location, making detection and location results more precise, reducing misjudgments caused by data issues, and improving the scientific nature and accuracy of traffic management. Attached Figure Description

[0028] The present invention will be further described below with reference to the accompanying drawings and embodiments. In the accompanying drawings: Figure 1 This is a flowchart illustrating the entire process of an embodiment of the present invention; Figure 2 This is a schematic diagram of the method for identifying road traffic disruptions and locating accident sites based on highway ETC gantry data and spatiotemporal maps according to an embodiment of the present invention; Figure 3 This is a schematic diagram illustrating the distinction between express and slow trains based on a spatiotemporal graph according to an embodiment of the present invention; Figure 4 This is a spatiotemporal diagram for identifying the blocking and transition regions based on a spatiotemporal graph, according to an embodiment of the present invention. Detailed Implementation

[0029] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0030] Example 1 like Figure 1 and Figure 2As shown, this embodiment provides a method for identifying road traffic disruptions and locating accident sites based on highway ETC gantry data, comprising the following steps: Step 1: Obtain real-time highway vehicle flow data through ETC gantries. Under the premise of ensuring the security of ETC private network data, realize real-time access to ETC flow data. Vehicle flow data includes at least vehicle identification information (license plate, model, and other ID information), ETC gantry location and name information, and entry / exit time. Optionally, a data server can be deployed remotely or through a private network to ensure data real-time performance.

[0031] Step Two: Utilizing real-time acquired ETC transaction data and combining it with the gantry geographical topology, establish gantry segment information. By comparing the timestamps of adjacent records, for consecutively repeated records, only one is retained as valid data, while other redundant data is deleted or marked. Examine vehicle transaction records with the same trip ID in preceding and following gantries, extracting accurate vehicle identification information from correct transaction records such as license plate numbers. For abnormal data collected due to equipment malfunction, data will be supplemented and corrected based on the correct vehicle identification information. By measuring the vehicle's travel distance and corresponding time between each gantry segment, calculate the vehicle's average speed over each segment.

[0032] Step 3: Highway traffic disruption identification and accident location. Real-time vehicle flow data is used to draw a spatiotemporal map of vehicles in each gantry section. The traffic disruption identification algorithm and the accident location algorithm are combined to identify the traffic disruption and locate the accident location.

[0033] For vehicle traffic passing through discontinuous gantries, the records of subsequent gantries are searched (e.g., jumping from gantry n to gantry n+2) to ensure accurate identification and location of road traffic disruptions and accident sites.

[0034] As described in this invention, the method for identifying road traffic disruptions and locating accident sites based on highway ETC gantry data, in step two, the average speed V1 of the first segment of the journey is obtained using the formula "distance 1 / (passage time 2 - passage time 1)". Based on this same calculation formula, the average speed of the vehicle between each subsequent gantry segment can be further derived and labeled as V2, ..., Vn, respectively.

[0035] As described in this invention, the method for identifying road traffic disruptions and locating accident sites based on highway ETC gantry data involves drawing a spatiotemporal map of each flow by taking the time it takes for a vehicle to pass through two or more consecutive gantries (n gantries, n+1 gantries, n+2 gantries, etc.) and the distance between the gantries.

[0036] As described in this invention, the method for identifying road traffic disruptions and locating accident sites based on highway ETC gantry data includes the following steps: In step three, vehicles in each section are divided into two categories, fast vehicles and slow vehicles, according to their speed. The arrival times of adjacent vehicles at the next gantry are obtained and the arrival time difference between adjacent vehicles is calculated. The numbers of adjacent fast and slow vehicles before and after the abnormal time difference are identified.

[0037] As a preferred method for confirming abnormal time differences in this invention: compare the arrival time differences of adjacent vehicles, and set a threshold of 2-4 times the average time difference, with the optimal value being 3 times the average time difference.

[0038] As described in this invention, the method for identifying road traffic disruptions and locating accident sites based on highway ETC gantry data includes: in step three, finding the last two normally operating express and slow vehicles n and N at the beginning of the abnormal time period, calculating the intersection of their spatiotemporal trajectories according to their ideal operating time and interval distance, and defining this intersection as the spatiotemporal location point where the disruption begins.

[0039] As described in this invention, the method for identifying road traffic disruptions and locating accident sites based on highway ETC gantry data includes: in step three, finding the two abnormally running express and slow vehicles n+1 and N+1 that first pass through the next gantry at the end of the abnormal time period, calculating the intersection of their spatiotemporal trajectories according to their ideal running time and interval distance, and defining this point as the spatiotemporal location where the disruption ends.

[0040] After drawing the ETC gantry flow time-space diagram, the intersection point at time t1 is used as the highway traffic interruption time and accident location.

[0041] The estimated location of road traffic disruption and accident sites is the gantry interval where the intersection point at time t1 is located in the spatiotemporal graph.

[0042] During use, when anomalies occur on the highway (such as traffic accidents, landslides, and emergency stops), the spatiotemporal map of the flow data between each gantry can quickly identify whether the road is blocked and locate the accident site. This process does not require human intervention or other data assistance. If anomalies are displayed on the spatiotemporal map, an alarm will be triggered.

[0043] Example 2 A specific embodiment is provided, including the following steps: 1. Real-time highway vehicle flow data obtained through ETC gantries is as follows:

[0044] 2. Examples of timestamp comparison and selection Scene 1: The gantry G123 detected vehicle Min A12345 three times consecutively at 10:00:01, 10:01:03, and 10:03:05.

[0045] Processing rules: For the same vehicle with timestamp intervals of less than 5 minutes at the same gantry, only one of the timestamps will be retained as valid data, while the other redundant data will be deleted or marked.

[0046] The processing steps are as follows: Detection timestamp intervals: 10:00:01 and 10:01:03, 10:01:03 and 10:03:05, all ≤5min; Results: Only the first record (10:00:01) is retained, and the last two records are deleted to avoid redundant data affecting the calculation speed.

[0047] Scene 2: There are multiple identical timestamps in gantry G123, such as 10:00:01, 10:00:01, 10:00:01, and three consecutive identical data from the same vehicle.

[0048] Processing rules: Check whether data with similar timestamps are completely identical in other dimensions of the transaction data. If so, keep only one record; otherwise, keep all records.

[0049] The processing steps are as follows: Find transaction data with the same timestamp: 10:00:01, 10:00:01, 10:00:01. Examine other dimensions of this data.

[0050] 3. Example of False Detection Data Correction Scenario: Vehicle A1 jumps directly from gantry G1 (position x1) to G3 (position x3) without any record of G2 (x2) in between, and the distance between x1 and x3 is 8km (normally the distance from G1 to G2 is 5km, and the distance from G2 to G3 is 3km).

[0051] Correction steps: The detection was determined to be a false alarm due to the distance being 8km > 5km and there was no G2 record.

[0052] Insert virtual G2 record: Assume the average speed of the 10 adjacent vehicles from G1 to G2 is The time taken to travel through G2 is: ,in It is the distance from G1 to G2.

[0053] Example 3 This embodiment provides a complete example of the spatiotemporal graph construction process. It includes the following steps: 1. Basic data preparation; Scenario: The gantry topology of a certain highway section is G0123 (x=10km) → G0124 (x=15km), with a speed limit of 120km / h.

[0054] Transaction data: Vehicle A: G0123 (10:00:05) → G0124 (10:02:00); Vehicle B: G0123 (10:00:00) → G0124 (10:02:30); Vehicle C: G0123 (10:00:03) → G0124 (no time record) (Accident vehicle) 2. Mathematical modeling of the trajectory line; Vehicle A speed calculation: v A =(15km-10km) / (115s)=157km / h; Vehicle A's trajectory equation: S A =0.0435×(t-5)+10; t is the timestamp, in seconds.

[0055] The speed calculation for vehicle B is the same as above: v B =120km / h; Vehicle B trajectory equation: S B =0.0333×t+10; t is the timestamp, in seconds (s).

[0056] 3. Spatiotemporal diagram visualization, such as... Figure 3 As shown.

[0057] Horizontal axis: gantry position (km), range 10-15km; Vertical axis: Time (HH:MM:SS), range 10:00:00-10:05:00; Track line: Vehicle A: a diagonal line from (10km, 10:00:05) to (15km, 10:02:00); Vehicle B: The slope of the diagonal line from (10km, 10:00:00) to (15km, 10:02:30) is less than that of vehicle A (slower speed).

[0058] 4. Assume a scenario where location tracking is blocked; (1) Event: At 10:01:00, vehicle C was involved in a rear-end collision at a distance of 12.5km from G0123 to G0124. The accident caused vehicles behind to stop, forming a congestion wave.

[0059] Abnormal data: The normal average time difference before the accident was 20s; after the accident, the time difference between vehicle D arriving at G0124 and vehicle C suddenly increased to 120s (>3×20s).

[0060] (2) Calculation of the intersection of spatiotemporal trajectories: Step 1: Extract the normal trajectory before the accident; Express train n (vehicle A): S A =0.0435×(t-5)+10; Slow train N (vehicle B): S B =0.0333×t+10; Intersection point calculation: Solve the simultaneous equations to get: x = 10.71 km, t = 10:00:21 (the point at which the blockade begins).

[0061] Step 2: Extract abnormal trajectories after the accident; Assume the trajectory equation of express train n+1 (vehicle E): S E = ; Initial conditions: Passing through G0123 gantry at 10:00:10 (x=10km, t=10s). Speed ​​before the accident: 120km / h (0.0333km / s); Time to reach 12.5km: 85s; Speed ​​after resuming driving: Assume 60km / h.

[0062] Assume the trajectory equation of the slow car N+1 (vehicle F): S F = ; Initial conditions: Passing through gantry G0123 at 10:00:08 (x=10km, t=8 seconds); Speed ​​before the accident: 80 km / h (0.0222 km / s); Time to reach 12.5 km: 120.6 seconds. Speed ​​after resuming driving: Assume 40km / h.

[0063] Intersection point calculation: Solve the simultaneous equations to get: x = 13.5 km, t = 10:31:00 (empty point at the end of the blockade).

[0064] (3) Location results of the blocking interval: Time: 10:01:00 (start) to 10:31:00 (end), lasting 1800 seconds; Space: 10.71km (start) to 13.5km (end).

[0065] During use, when anomalies occur on the highway (such as traffic accidents, landslides, and emergency stops), the spatiotemporal map of the flow data between various gantries can quickly identify whether the road is blocked and locate the accident site. This process does not require human intervention or other data assistance. If an anomaly is displayed on the spatiotemporal map, an alarm is triggered. This invention improves alarm speed; time is life, and protecting people and property is paramount—every second saved is worthwhile.

[0066] Example 4 This embodiment calculates the average vehicle speed by using the time it takes for a vehicle to pass through an ETC gantry and the distance between the gantry; and draws a spatiotemporal diagram of the vehicle passing through different gantries.

[0067] Based on Example 1, the trajectory of the last vehicle before the road traffic disruption occurred can be found in the spatiotemporal map. The location of the intersection of this trajectory with the spatiotemporal map trajectories of other vehicles can be used as the location of the road traffic disruption and accident. This avoids the huge investment required to install radar, cameras, fiber optic sensors, Beidou displacement sensors, etc., and can achieve real-time detection of road traffic disruption and location of accident.

[0068] It should be understood that those skilled in the art can make improvements or modifications based on the above description, and all such improvements and modifications should fall within the protection scope of the appended claims.

Claims

1. A method for identifying road traffic disruptions and locating accident sites based on highway ETC gantry data and spatiotemporal maps, characterized in that... Includes the following steps: S1: Real-time acquisition of highway vehicle flow data via ETC gantry; the vehicle flow data includes at least vehicle identification information, ETC gantry location and name information, and entry / exit time; S2: Combine the geographical topology of the ETC gantry within the monitored highway section with the vehicle flow data to establish gantry section information; perform data preprocessing and correction by comparing the timestamps of adjacent records; extract vehicle identification information with the same journey from the front and rear gantries; and calculate the average speed of the vehicle on each journey by measuring the travel distance and travel time between each gantry segment. S3: Draw the vehicle spatiotemporal diagram for each gantry section; classify vehicles in each section of the vehicle spatiotemporal diagram into express and slow vehicles according to their speed; obtain the arrival time of adjacent vehicles to the next gantry and calculate the arrival time difference between adjacent vehicles; if the time difference exceeds a set threshold, it is judged as an abnormal time difference; take the intersection of the spatiotemporal trajectories of the last two normally operating express and slow vehicles at the start time of the abnormal time difference as the blocking start spatiotemporal position point; take the intersection of the spatiotemporal trajectories of the first two abnormally operating express and slow vehicles to pass through the next gantry at the end time of the abnormal time difference as the blocking end spatiotemporal position point.

2. The method for identifying road traffic disruptions and locating accident sites based on highway ETC gantry data and spatiotemporal maps according to claim 1, characterized in that... In step S1, the vehicle identification information includes the vehicle license plate number, vehicle type, and vehicle sequence number when passing through a gantry.

3. The method for identifying road traffic disruptions and locating accident sites based on highway ETC gantry data and spatiotemporal maps according to claim 1, characterized in that... In step S2, if the timestamp interval of the same vehicle at the same gantry is less than the first time interval, only one vehicle flow data is retained as valid data, while the other redundant data is deleted or marked.

4. The method for identifying road traffic disruptions and locating accident sites based on highway ETC gantry data and spatiotemporal maps according to claim 1, characterized in that... In step S2, when the detection distance between the first and third gantry in a vehicle flow record is greater than the normal distance between the two gantry in the gantry topology diagram, and the record of the second gantry between the two gantry is missing, data correction is performed and the virtual passage time at the second gantry is inserted. ,in It is the distance from the first gantry to the second gantry; The average speed of 10 adjacent vehicles from the first gantry to the second gantry; The time of passage at the first gantry.

5. The method for identifying road traffic disruptions and locating accident sites based on highway ETC gantry data and spatiotemporal maps according to claim 1, characterized in that... In step S3, the threshold is set to be 2-4 times the average time difference of all vehicles in the same time and space interval.

6. The method for identifying road traffic disruptions and locating accident sites based on highway ETC gantry data and spatiotemporal maps according to claim 1, characterized in that... Step S3 uses the passage time of a vehicle through two or more consecutive gantries and the distance between the gantries in each vehicle flow data to draw a spatiotemporal map of the vehicle in each gantry segment.

7. The method for identifying road traffic disruptions and locating accident sites based on highway ETC gantry data and spatiotemporal maps according to claim 1, characterized in that... In step S3, the last two normally operating express trains and slow trains at the start of the abnormal time difference are determined, and the two abnormally operating express trains and slow trains that first pass through the next gantry at the end of the abnormal time difference are determined. The intersection points of the spatiotemporal trajectories at the start of the abnormal time difference and the intersection points of the spatiotemporal trajectories at the end of the abnormal time difference are calculated according to the ideal running time and interval distance of each train.

8. The method for identifying road traffic disruptions and locating accident sites based on highway ETC gantry data and spatiotemporal maps according to claim 1, characterized in that... Step S3 is replaced by drawing a vehicle spatiotemporal map for each gantry section and finding the trajectory of the last vehicle before the time of road traffic closure in the spatiotemporal map. The location of the intersection of this trajectory with the spatiotemporal map trajectories of other vehicles is taken as the traffic closure location, and the time of the intersection is taken as the time of the closure.

9. An electronic device comprising a processor, a memory, and a program stored in the memory and executable on the processor, characterized in that: When the program is executed by the processor, it implements the steps of the method according to any one of claims 1-8.

10. A computer-readable storage medium, characterized in that, The storage medium stores a program, characterized in that: when the program is executed by a processor, it implements the steps of the method described in any one of claims 1-8.

Images