A profiling method for vehicles suspected of occupying emergency lanes based on highway ETC and license plate recognition data

Abstract

The present invention is applicable to the field of highway traffic management, and provides a method for profiling vehicles suspected of occupying emergency lanes based on highway ETC and license plate recognition data, the method comprising: obtaining basic vehicle data and preprocessing the basic data; identifying the traffic operation conditions of the road section in the current time period; analyzing the emergency lane occupancy conditions in traffic congestion and smooth traffic scenarios, respectively, and generating a portrait of a vehicle suspected of occupying the emergency lane to overtake. The present invention realizes the identification and tracking of traffic violations of highway vehicles occupying emergency lanes, and more efficiently and accurately realizes the portrait labeling work of individual-level vehicles on the highway. The present invention can realize the analysis of the driving patterns of on-the-road vehicles, and efficiently identify the suspected occupation of the emergency lane. On the basis of ensuring the scientific nature of the algorithm, it realizes the automation of traffic management.

Description

Technical Field

[0001] The present invention belongs to the field of highway traffic management, and in particular relates to a method for profiling vehicles suspected of occupying emergency lanes based on highway ETC and license plate recognition data. Background Art

[0002] At present, with the continuous increase in highway traffic volume, traffic management faces many challenges. Among them, illegal occupation of emergency lanes is a prominent problem, which not only affects the passage of emergency rescue vehicles, but may also cause traffic accidents and increase road congestion. In order to accurately understand the legality of highway vehicle operation and optimize highway traffic management, it is necessary to conduct behavioral analysis and portrait labeling of on-the-way vehicles on the highway. Because the highway is equipped with ETC gantries and camera devices at the entrances and exits of service areas, the data collected can be used as an important basis for analyzing the on-the-way behavior of vehicles. For example, the specific on-the-way trajectory of the vehicle can be located by combining the license plate, the time and place of the vehicle passing. Therefore, the effective integration and analysis of the highway collected data can form a monitoring of the on-the-way behavior of vehicles, thereby constructing a technical method for automatically monitoring the portraits of vehicles suspected of occupying the emergency lane.

[0003] At present, the monitoring and management of emergency lanes on highways mainly rely on manual inspections and video surveillance systems. These methods have certain limitations: manual inspections are inefficient, the long length of highways makes it difficult for manual inspections to cover all sections, and the inspection frequency is limited, making it impossible to detect and deal with illegal occupation of emergency lanes in real time. In addition, although road video surveillance systems can provide real-time monitoring, they require a lot of additional installation costs and human resources for monitoring and analysis. Summary of the invention

[0004] The purpose of the present invention is to provide a method for profiling vehicles suspected of occupying emergency lanes based on highway ETC and license plate recognition data, aiming to solve the technical problems existing in the prior art identified in the background technology.

[0005] The present invention is implemented as follows: a method for profiling vehicles suspected of occupying emergency lanes based on highway ETC and license plate recognition data, the method comprising: Obtain vehicle basic data and pre-process the basic data; Identify the traffic conditions of the road section in the current period and classify them into traffic congestion and smooth traffic. Analyze the occupancy of emergency lanes in traffic congestion scenarios and generate a profile of vehicles suspected of occupying the emergency lane to overtake; Analyze the occupancy of the emergency lane in a smooth traffic scenario and generate a portrait of vehicles suspected of occupying the emergency lane and parking.

[0006] As a further solution of the present invention, the obtaining of vehicle basic data and preprocessing of the basic data specifically includes: Obtain basic data from the highway ETC flow database and the highway service area entrance and exit sign recognition database; Filter out the main fields from the basic data and clean up the outliers and missing values.

[0007] As a further solution of the present invention, the main fields include: The transaction time, gantry Hex value, transaction status, ETC card number, and CPC card number of the ETC flow data; the vehicle passing time and the gantry Hex value of the service area camera’s license plate recognition data at the entrance and exit of the highway service area.

[0008] As a further solution of the present invention, the obtaining of vehicle basic data and preprocessing of the basic data specifically includes: Set the detection time interval t , the average vehicle travel time of the road section between two adjacent ETC gantries is counted, and the average time difference of each vehicle passing through the upstream and downstream ETC gantries in the current period is calculated; The average vehicle travel time is as follows: ; in Indicates the detection time interval t The first detected i Vehicles passing through the road section The travel time; Indicates the detection time interval t The first i The time point when a vehicle passes through the downstream gantry k; Indicates that the vehicle i Path backtracking to get through the upstream gantry l time point; Indicates the detection time interval t The road section within Average vehicle travel time; n Represents the detection time interval t The total number of detected vehicles during the period.

[0009] According to the current detection time interval of the road section t Average vehicle travel time The theoretical average travel time of the section calculated by combining the theoretical average driving speed during congested driving on the expressway and the section length is used as the threshold for the section to be divided into traffic congestion scenario and traffic smooth scenario. The traffic operation status of the section in the current period is determined and classified into traffic congestion scenario and traffic smooth scenario.

[0010] The theoretical average travel time is: ; in Indicates the theoretical average vehicle travel time of the road section; Indicates road section kl Mileage length; Indicates road section The theoretical average driving speed during congested highway driving.

[0011] As a further solution of the present invention, the analysis of the emergency lane occupancy in the traffic congestion scenario to generate a vehicle portrait suspected of occupying the emergency lane for overtaking specifically includes: Determine whether there are vehicles with the abnormal feature of last-in-first-out in the traffic flow, that is, the vehicles that pass through the upstream ETC gantry later pass through the downstream ETC gantry earlier than the number of vehicles ahead by a percentage threshold; If there is a last-in-first-out abnormal feature, calculate the single-vehicle travel time of the vehicle with the abnormal feature within the road section and compare it with the statistically obtained average travel time of the current road section; If the single vehicle travel time is less than the average travel time of the road section minus the allowable floating deviation value, that is, a calculated allowable deviation range, it means that the vehicle's driving speed is significantly higher than the overall traffic speed, generating a portrait of suspected overtaking in the emergency lane.

[0012] As a further solution of the present invention, the analysis of the emergency lane occupancy in the traffic flow scenario to generate a portrait of a vehicle suspected of occupying the emergency lane specifically includes: The single-vehicle travel time of each vehicle on the road section is measured and compared with the statistically average travel time of the current road section; If the travel time of a single vehicle is greater than the average travel time of the road section plus the allowable floating deviation value, the vehicle speed is judged to be lower than the overall traffic speed, which is defined as the presence of abnormal travel time characteristics; Determine whether vehicles with abnormal characteristics have entered the highway service area and generate corresponding vehicle portraits.

[0013] As a further solution of the present invention, the step of determining whether a vehicle with abnormal characteristics has entered a highway service area and generating a corresponding vehicle portrait specifically includes: Determine whether the road section contains a service area, and if so, read the camera information at the entrance and exit of the service area; If the road section does not include a service area, a portrait of the vehicle suspected of occupying the emergency lane for parking is directly generated; If the road section includes a service area, but the license plate recognition data of the camera at the entrance and exit of the service area does not contain the license plate information of the vehicle entering or leaving, a portrait of the vehicle suspected of occupying the emergency lane to park is generated; If the road section includes a service area, and the license plate recognition data from the camera at the entrance and exit of the service area shows that the vehicle has entered the service area, A time threshold is set, and the difference between the average vehicle travel time of the road section and the vehicle rest time in the service area shown by the license plate recognition data is calculated. If the time difference is greater than the time threshold, a portrait of a vehicle suspected of occupying the emergency lane is generated.

[0014] The beneficial effects of the present invention are: 1. The present invention is based on highway collection equipment, giving full play to the potential advantages of traffic big data collected by ETC gantries and cameras, realizing the identification and tracking of traffic violations of highway vehicles occupying emergency lanes, and realizing the portrait labeling work of individual vehicles on the highway more efficiently and accurately.

[0015] 2. The present invention provides an effective algorithm framework that can analyze the driving patterns of vehicles on the road and efficiently identify suspected behaviors of occupying emergency lanes. On the basis of ensuring the scientific nature of the algorithm, it realizes the automation of traffic management and contributes to the construction of intelligent transportation systems on highways. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 Flowchart of the method for profiling vehicles suspected of occupying the emergency lane based on highway ETC and license plate recognition data. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0018] The present invention is based on the data collected by the ETC gantries and the camera equipment at the entrances and exits of the service areas of the highway. According to the characteristics of the average vehicle travel time of the road sections between adjacent gantries, the present invention divides the road sections into two scenarios: traffic congestion and smooth traffic, and analyzes the behaviors of vehicles occupying the emergency lane generated in different scenarios. For the scenario of traffic congestion, combined with the characteristics of "last in, first out" and the fact that the travel time of a single vehicle is significantly less than the average vehicle travel time of the road section, it is determined that the vehicle has the behavior of suspected occupation of the emergency lane for overtaking; for the scenario of smooth traffic, combined with the characteristics that the travel time of a single vehicle is significantly higher than the average vehicle travel time of the road section and has not entered the service area of ​​this road section, it is determined that the vehicle has the behavior of suspected occupation of the emergency lane for parking. Finally, a vehicle portrait label suspected of occupying the emergency lane is generated for vehicles on the highway.

[0019] like Figure 1As shown, the method for profiling vehicles suspected of occupying emergency lanes based on highway ETC and license plate recognition data includes: Basic data acquisition and preprocessing: Based on the information of highway ETC flow data and highway service area entrance and exit license plate recognition data, the data fields shown in Tables 1 and 2 are extracted, mainly including data on vehicle passing time, vehicle passing location and vehicle license plate information. These data are cleaned of outliers, such as filling in missing values ​​and eliminating outliers, as the data basis for subsequent steps.

[0020] Table 1 Main fields of ETC flow data

[0021] Table 2 Main fields of license plate recognition data from cameras at the entrance and exit of a highway service area

[0022] Identification of traffic conditions in road sections: The road section between two adjacent ETC gantries is recorded as a road section, and a detection time interval is set t , usually take every 5 minutes of traffic flow as a round of detection objects, and count the average vehicle travel time of the section, that is, calculate the difference between the time point when each vehicle passes through the downstream ETC gantry and the time point when it passes through the upstream ETC gantry, and calculate the average value. According to the average travel time of the section, the speed limit of the section and the length of the section, calculate the threshold value for dividing the section into traffic congestion scenario and traffic flow scenario. Finally, determine whether the section belongs to traffic congestion scenario or traffic flow scenario.

[0023] Analysis of vehicle portraits occupying emergency lanes: ① For traffic congestion scenarios, when congestion occurs on a highway section, it will cause the traffic on the section to slow down or even stagnate. There are cases where vehicles occupy the emergency lane to overtake in order to quickly pass through the congested area, so it is necessary to consider the situation where vehicles occupy the emergency lane to overtake in order to quickly pass through the congested area. Therefore, in the driving mode of congestion, vehicles usually follow the "first in, first out" principle, and vehicles that significantly violate the "first in, first out" principle, that is, vehicles with obvious "last in, first out" abnormal characteristics are screened and further judged.

[0024] For changes in the order of the gantry , specifically: ; in, Indicates i Vehicles in the detection time interval t Passing section kl The order of changes; Indicates iVehicles in the detection time interval t Internal through downstream gantry k The passing order of all vehicles in the Indicates i Vehicles in the detection time interval t Internal through the upstream gantry l The passing order of all vehicles in the and Respectively represent the detection time interval t Internal through downstream gantry k and upstream gantry l The set of passing times of all vehicles.

[0025] Then, the single-vehicle travel time of the vehicle identified as having abnormal characteristics in the road section is calculated and compared with the statistically average vehicle travel time of the current road section. Since the traffic condition will be affected by many factors, such as vehicle type, weather conditions, road conditions, etc., an allowable floating deviation value is set autonomously to take the above variables into account. If the single-vehicle travel time is less than the average vehicle travel time of the road section minus the allowable floating deviation value, it means that the vehicle's driving speed is significantly higher than the overall traffic speed, and a vehicle portrait suspected of occupying the emergency lane for overtaking is generated.

[0026] ② For the traffic flow scenario, when the expressway section is unobstructed, the traffic flow on the section will maintain a speed level near the lane speed limit, that is, a higher speed. Therefore, the situation where vehicles occupy the emergency lane for temporary parking will have a significant difference in travel time.

[0027] First, the single-vehicle travel time of each vehicle is measured and compared with the statistically average vehicle travel time of the current section. If the single-vehicle travel time is greater than the average travel time of the section plus the allowable floating deviation value, it means that the vehicle speed is significantly lower than the overall traffic speed, that is, the travel time is abnormal. Vehicles with abnormal travel time are judged whether to enter the highway service area, where: 1) If the road section includes a service area but the license plate recognition data of the camera at the entrance and exit of the service area does not contain the license plate information of the vehicle entering or leaving, a portrait of the vehicle suspected of occupying the emergency lane is generated; 2) If the road section includes a service area and the service area entrance sign recognition data shows that the vehicle has entered the service area, but the difference in the passing time of the upstream and downstream ETCs of the road section and the difference in the rest time of the vehicle in the service area shown by the sign recognition data is greater than a manually set threshold, a portrait of a vehicle suspected of occupying the emergency lane is generated; 3) If the road section does not include a service area, the vehicle is suspected of occupying the emergency lane and a vehicle portrait is generated.

[0028] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0029] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0030] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

[0031] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for profiling vehicles suspected of occupying emergency lanes based on highway ETC and license plate recognition data, characterized in that: The method comprises: Obtain vehicle basic data and pre-process the basic data; Identify the traffic conditions of the road section in the current period and classify them into traffic congestion and smooth traffic. Analyze the occupancy of emergency lanes in traffic congestion scenarios and generate a profile of vehicles suspected of occupying the emergency lane to overtake; Analyze the occupancy of the emergency lane in a smooth traffic scenario and generate a portrait of vehicles suspected of occupying the emergency lane and parking.

2. The method according to claim 1, characterized in that The obtaining of vehicle basic data and preprocessing of the basic data specifically includes: Obtain basic data from the highway ETC flow database and the highway service area entrance and exit sign recognition database; Filter out the main fields from the basic data and clean up the outliers and missing values.

3. The method according to claim 2, characterized in that The main fields include: The transaction time, gantry Hex value, transaction status, ETC card number, and CPC card number of the ETC flow data; the vehicle passing time and the gantry Hex value of the service area camera’s license plate recognition data at the entrance and exit of the highway service area.

4. The method according to claim 2, characterized in that: The obtaining of vehicle basic data and preprocessing of the basic data specifically includes: Set the detection time interval t , the average vehicle travel time of the road section between two adjacent ETC gantries is counted, and the average time difference of each vehicle passing through the upstream and downstream ETC gantries in the current period is calculated; According to the current detection time interval of the road section t Average vehicle travel time The theoretical average travel time of the section calculated by combining the theoretical average driving speed during congested driving on the expressway and the section length is used as the threshold for the section to be divided into traffic congestion scenario and traffic smooth scenario. The traffic operation status of the section in the current period is determined and classified into traffic congestion scenario and traffic smooth scenario.

5. The method according to claim 4, characterized in that The analysis of the emergency lane occupancy in the traffic congestion scenario to generate a vehicle portrait suspected of occupying the emergency lane for overtaking specifically includes: Determine whether there are vehicles with the abnormal feature of last-in-first-out in the traffic flow, that is, the vehicles that pass through the upstream ETC gantry later pass through the downstream ETC gantry earlier than the number of vehicles ahead by a percentage threshold; If there is a last-in-first-out change through the gantry order , calculate the single vehicle travel time of vehicles with abnormal characteristics within the road section and the average travel time of the current section obtained by statistics Make a comparison; If the single vehicle travel time is less than the average travel time of the road section minus the allowable floating deviation value , that is, a calculation allowable deviation range, it means that the vehicle’s speed is significantly higher than the overall traffic speed, generating a portrait of suspected overtaking in the emergency lane.

6. The method according to claim 5, characterized in that The analysis of the emergency lane occupancy in the traffic flow scenario to generate a vehicle portrait suspected of occupying the emergency lane for parking specifically includes: The road section travel time for each vehicle Measure and compare the average travel time of the current road section obtained by statistics Make a comparison; If the single vehicle travel time is greater than the average travel time of the road section plus the allowable floating deviation value , then the vehicle speed is judged to be lower than the overall traffic speed, which is defined as the presence of abnormal travel time characteristics; Determine whether vehicles with abnormal characteristics have entered the highway service area and generate corresponding vehicle portraits.

7. The method according to claim 6, characterized in that The determining whether a vehicle with abnormal characteristics enters a highway service area and generating a corresponding vehicle portrait specifically includes: Determine whether the road section contains a service area, and if so, read the camera information at the entrance and exit of the service area; If the road section does not include a service area, a portrait of the vehicle suspected of occupying the emergency lane for parking is directly generated; If the road section includes a service area, but the license plate recognition data of the camera at the entrance and exit of the service area does not contain the license plate information of the vehicle entering or leaving, a portrait of the vehicle suspected of occupying the emergency lane to park is generated; If the road section includes a service area, and the license plate recognition data from the camera at the entrance and exit of the service area shows that the vehicle has entered the service area, A time threshold is set, and the difference between the average vehicle travel time of the road section and the vehicle rest time in the service area shown by the license plate recognition data is calculated. If the time difference is greater than the time threshold, a portrait of a vehicle suspected of occupying the emergency lane is generated.

8. The method according to claim 4, characterized in that The average vehicle travel time of the road section is as follows: ； in Indicates the detection time interval t The first detected i Vehicles passing through the road section The travel time; Indicates the detection time interval t The first i The time point when a vehicle passes through the downstream gantry k; Indicates that the vehicle i Path backtracking to get through the upstream gantry l time point; Indicates the detection time interval t The road section within Average vehicle travel time; n represents the detection time interval t The total number of detected vehicles during the period.

9. The method according to claim 8, characterized in that The theoretical average travel time of the road section is as follows: ； in Indicates the theoretical average vehicle travel time of the road section; Indicates road section kl Mileage length; Indicates road section The theoretical average driving speed during congested highway driving.

10. The method according to claim 5, characterized in that The gantry order changes , specifically: ； in, Indicates i Vehicles in the detection time interval t Passing section kl The order of changes; Indicates i Vehicles in the detection time interval t Internal through downstream gantry k The passing order of all vehicles in the Indicates i Vehicles in the detection time interval t Internal through the upstream gantry l The passing order of all vehicles in the and Respectively represent the detection time interval t Internal through downstream gantry k and upstream gantry l The set of passing times of all vehicles.

Images