An intelligent guidance system for vehicles passing through toll lanes

Abstract

The present invention relates to the technical field of traffic guidance, and specifically discloses an intelligent guidance system for vehicle traffic in a toll lane, comprising: a vehicle queuing information acquisition module, used for acquiring the current queuing vehicle information of each toll lane in the toll station based on lane monitoring of each toll lane in the toll station; a vehicle travel time prediction module, used for predicting the required travel time of each toll lane relative to the current queuing vehicle information based on the queuing vehicle information of each toll lane and historical travel records; a travel guidance scheme generation module, used for obtaining the current travel guidance scheme of the toll station based on the required travel time of each toll lane in the toll station relative to the current queuing vehicle information and the prepared queuing vehicle information; and used for monitoring the vehicle queuing situation of each lane in the toll station and predicting the travel time of each lane, so as to realize intelligent guidance of all vehicles that are about to pass through the toll station.

Description

Technical Field

[0001] The invention relates to the technical field of traffic guidance, and in particular to an intelligent guidance system for vehicles passing through a toll lane. Background Art

[0002] At present, with the continuous growth of traffic volume, the efficient operation of toll lanes has become crucial. The intelligent guidance system for vehicles passing through toll lanes is designed to improve toll collection efficiency, reduce traffic congestion and enhance user experience. In the traditional toll collection mode, vehicles need to queue up in front of the toll booth to pay, which not only wastes time but also easily causes traffic congestion. In order to solve these problems, the intelligent guidance system came into being. The intelligent guidance system realizes automatic identification, classification and guidance of vehicles through cameras, display screens and communication equipment, thereby improving the traffic efficiency of toll lanes.

[0003] However, the existing intelligent guidance system for toll lane vehicles only estimates the congestion of each lane through manual visual inspection, and guides the vehicles about to enter the toll lane queue to the relatively less congested toll lane through display screens or other guidance methods. This guidance system that makes decisions based on manual visual inspection relies heavily on manual experience, and the accuracy of the decision cannot be guaranteed, which may lead to low overall traffic efficiency of all toll lanes in the toll station.

[0004] Therefore, the present invention proposes an intelligent guidance system for vehicles passing through a toll lane. Summary of the invention

[0005] The present invention provides an intelligent guidance system for vehicle traffic in toll lanes, which is used to monitor the vehicle queue conditions in each lane of a toll station and predict the passage time of each lane in combination with historical passage records, and combine the information of all vehicles about to enter the toll lane to achieve intelligent guidance of all vehicles about to pass through the toll station, so that the accuracy of the guidance decision is guaranteed and the overall passage efficiency of all toll lanes of the toll station is improved.

[0006] The present invention provides an intelligent guidance system for vehicles passing through a toll lane, comprising:

[0007] A vehicle queue information acquisition module, used to acquire current queue vehicle information of each toll lane in the toll station based on lane monitoring of each toll lane in the toll station;

[0008] A vehicle travel time prediction module is used to predict the required travel time of each toll lane relative to the current queued vehicle information based on the queued vehicle information and historical travel records of each toll lane;

[0009] The traffic guidance scheme generating module is used to obtain the current traffic guidance scheme of the toll station based on the required passage time of each toll lane in the toll station relative to the current queue vehicle information and the prepared queue vehicle information.

[0010] Preferably, the vehicle queue information acquisition module includes:

[0011] A monitoring acquisition submodule, used for acquiring lane monitoring videos based on lane monitoring of each toll lane in the toll station;

[0012] An information reading submodule, used to obtain the appearance feature information and dynamic queuing distance of each queuing vehicle in the lane monitoring video of each toll lane;

[0013] The information interception submodule is used to determine the appearance feature information and dynamic queuing distance of all vehicles that are not passing through each toll lane from the appearance feature information and dynamic queuing distance of all vehicles queuing in each toll lane that have been currently acquired, as the current queuing vehicle information of each toll lane in the toll station.

[0014] Preferably, the vehicle travel time prediction module includes:

[0015] An information acquisition submodule, for acquiring appearance feature information and dynamic queuing distance of all currently queuing vehicles in each toll lane based on the queuing vehicle information of each toll lane;

[0016] A queuing vehicle type determination submodule, used to determine the types of all currently queuing vehicles in each toll lane based on appearance feature information of all currently queuing vehicles in each toll lane;

[0017] The historical traffic record parsing submodule is used to obtain, from the historical traffic records of each toll lane, the sub-historical traffic records of each historically passed vehicle of each type of currently queued vehicle in each toll lane relative to the current charging method, wherein the sub-historical traffic records of the vehicle include the charging processing time and dynamic queue distance of the vehicle, and the dynamic queue distances of all previous queued vehicles of the vehicle;

[0018] The travel time prediction submodule is used to predict the required travel time of each toll lane relative to the current queue vehicle information based on the dynamic queue distance of all current queue vehicles in each toll lane and the sub-historical travel record of each historical passing vehicle of each current queue vehicle type relative to the current toll collection method.

[0019] Preferably, the travel time prediction submodule includes:

[0020] A vehicle queue generating unit, configured to generate all waiting-to-pass vehicle queues of each historically passed vehicle of each current queuing vehicle type based on all front queuing vehicles in the sub-historical passing records of each historically passed vehicle of each current queuing vehicle type relative to the current charging method;

[0021] A following speed determination unit, for determining, based on the dynamic queue distance of each historical passing vehicle of each current queue vehicle type and the corresponding dynamic queue distances of all previous queue vehicles, a following speed of each remaining historical passing vehicle except the first historical passing vehicle in each queue of vehicles to be communicated with relative to the corresponding queue of vehicles to be communicated;

[0022] A processing time prediction unit, for determining a predicted toll processing time for each current queue vehicle type relative to a current toll collection method based on the toll processing time of all historical passing vehicles of each current queue vehicle type;

[0023] The travel time prediction unit is used to predict the required travel time of each toll lane relative to the current queue vehicle information based on the dynamic queue distance of all current queue vehicles in each toll lane, the predicted toll processing time of each current queue vehicle type relative to the current toll collection method, and the following speed of each historical passing vehicle except the first historical passing vehicle in each queue of vehicles to be passed of each current queue vehicle type relative to the corresponding queue of vehicles to be communicated.

[0024] Preferably, the travel time prediction unit includes:

[0025] The vehicle queue generation subunit is used to generate all queues of vehicles to be passed and all partially passed vehicle queues of each current queued vehicle based on all queued vehicles of each toll lane currently acquired, and determine the following speed of each current queued vehicle relative to each partially passed vehicle queue based on the dynamic queue distance of all queued vehicles of each toll lane currently acquired;

[0026] a following speed prediction subunit, for determining a predicted following speed of each current queue vehicle relative to each queue of vehicles to be communicated, based on the following speed of each remaining historical passing vehicle relative to the corresponding queue of vehicles to be communicated and the following speed of each current queue vehicle relative to each partially passed queue of vehicles, except for the first historical passing vehicle in each queue of vehicles to be communicated of each historical passing vehicle of each current queue vehicle type;

[0027] The travel time prediction subunit is used to predict the required travel time of each toll lane relative to the current queue vehicle information based on the predicted following speed of each current queue vehicle relative to each queue of vehicles to be passed and the corresponding predicted toll processing time of all previous queue vehicle types relative to the current toll collection method.

[0028] Preferably, the line speed prediction subunit includes:

[0029] The prediction model acquisition terminal is used to obtain the following speed prediction model;

[0030] The following speed prediction terminal is used to input the following speed of each current queue vehicle relative to all partially passed vehicle queues and the following speeds of all historical passing vehicles except the first historical passing vehicle in all waiting vehicle queues of all historical passing vehicles corresponding to the current queue vehicle type relative to the corresponding waiting vehicle queue into the following speed prediction model to obtain the predicted following speed of each current queue vehicle relative to each waiting vehicle queue.

[0031] Preferably, the travel time prediction subunit includes:

[0032] A following distance determination terminal is used to determine the following distance of each current queued vehicle in each toll lane relative to each queue of vehicles to be passed;

[0033] A following time prediction terminal is used to use the ratio of the following distance of each current queue vehicle in each toll lane relative to each queue of vehicles to be passed and the predicted following speed of the corresponding current queue vehicle relative to the corresponding queue of vehicles to be passed as the predicted passing time of each current queue vehicle in each toll lane relative to each queue of vehicles to be passed;

[0034] The total travel time prediction terminal is used to take the sum of the predicted travel time of each current queue vehicle in each toll lane relative to the corresponding queues of all vehicles to be passed, the predicted charging processing time of the corresponding current queue vehicle type relative to the current charging method, and the predicted charging processing time of all corresponding previous queue vehicle types relative to the current charging method as the required travel time of each toll lane relative to the current queue vehicle information.

[0035] Preferably, the traffic guidance scheme generating module includes:

[0036] A submodule for obtaining information of a pre-queuing vehicle, for obtaining information of vehicles in a pre-queuing vehicle at a toll station based on lane monitoring of each toll lane in the toll station;

[0037] The traffic guidance scheme generating submodule is used to obtain the current traffic guidance scheme of the toll station based on the required travel time of each toll lane in the toll station relative to the current queue vehicle information and the prepared queue vehicle information.

[0038] Preferably, the traffic guidance scheme generation submodule includes:

[0039] A model acquisition unit, used to acquire a guidance scheme generation model;

[0040] The scheme generating unit is used to input the required passing time of each toll lane in the toll station relative to the current queue vehicle information and the prepared queue vehicle information into the guidance scheme generating model to obtain the current passing guidance scheme of the toll station.

[0041] Preferably, it also includes:

[0042] The guide light strip control module is used to control the light strips on the toll side of each toll lane in the toll station to display according to the current traffic guidance plan.

[0043] Compared with the prior art, the beneficial effects of the present invention are as follows: by monitoring the vehicle queue situation in each lane of the toll station and predicting the passage time of each lane in combination with historical passage records, and combining the information of all vehicles about to enter the toll lane, intelligent guidance of all vehicles about to pass through the toll station can be achieved, so that the accuracy of the guidance decision is guaranteed and the overall passage efficiency of all toll lanes of the toll station is improved.

[0044] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures specifically pointed out in this application document.

[0045] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0047] Figure 1 A schematic diagram of internal functional modules of an intelligent guidance system for vehicles passing through a toll lane according to an embodiment of the present invention;

[0048] Figure 2 Schematic diagram of internal functional submodules of the vehicle queue information acquisition module in an embodiment of the present invention;

[0049] Figure 3 Schematic diagram of internal functional submodules of a vehicle travel time prediction module in an embodiment of the present invention;

[0050] Figure 4A schematic diagram of internal functional submodules of a traffic guidance scheme generation module in an embodiment of the present invention;

[0051] Figure 5 This is a real-life example diagram of a toll station where the intelligent guidance system for vehicle traffic in a toll lane in an embodiment of the present invention is applied. DETAILED DESCRIPTION

[0052] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0053] Embodiment 1:

[0054] The present invention provides an intelligent guidance system for vehicles passing through a toll lane, referring to Figure 1 ,include:

[0055] A vehicle queue information acquisition module, used to acquire current queue vehicle information of each toll lane in the toll station based on lane monitoring of each toll lane in the toll station;

[0056] A vehicle travel time prediction module is used to predict the required travel time of each toll lane relative to the current queued vehicle information based on the queued vehicle information and historical travel records of each toll lane;

[0057] The traffic guidance scheme generating module is used to obtain the current traffic guidance scheme of the toll station based on the required passage time of each toll lane in the toll station relative to the current queue vehicle information and the prepared queue vehicle information.

[0058] In this embodiment, the lane monitoring is a monitoring device installed on the toll lane.

[0059] In this embodiment, the historical traffic record includes the duration record of each charging method of each toll lane, as well as information such as the type of vehicles released during the duration of different charging methods, the charging processing time, and the distance and time of their queuing.

[0060] In this embodiment, the required travel time of each toll lane relative to the current queue vehicle information is: the total time required for all vehicles currently queuing in each toll lane to complete the passage under the vehicle queue corresponding to the current queue vehicle information.

[0061] In this embodiment, the information of the vehicles in the standby queue includes the appearance feature information of all vehicles that are about to enter each lane of the toll station, the real-time distance between the vehicles and the toll gate, etc.

[0062] In this embodiment, the current traffic guidance scheme is mainly a guidance scheme based on the queue priority order of different lanes in the toll station. For example, the recommended priority order of lane queues is: the third lane, the second lane, and the first lane. Subsequently, the light strips on the third lane, the second lane, and the first lane can be controlled to display green, yellow, and red respectively to indicate vehicle drivers, thereby achieving the guidance purpose.

[0063] The beneficial effects of the above technology are: by monitoring the vehicle queues in each lane of the toll station and predicting the travel time of each lane in combination with historical traffic records, and combining the information of all vehicles about to enter the toll lane, intelligent guidance of all vehicles about to pass through the toll station can be achieved, so that the accuracy of the guidance decision is guaranteed and the overall traffic efficiency of all toll lanes of the toll station is improved.

[0064] Embodiment 2:

[0065] Based on Example 1, the vehicle queue information acquisition module refers to Figure 2 ,include:

[0066] A monitoring acquisition submodule, used for acquiring lane monitoring videos based on lane monitoring of each toll lane in the toll station;

[0067] An information reading submodule, used to obtain the appearance feature information and dynamic queuing distance of each queuing vehicle in the lane monitoring video of each toll lane;

[0068] The information interception submodule is used to determine the appearance feature information and dynamic queuing distance of all vehicles that are not passing through each toll lane from the appearance feature information and dynamic queuing distance of all vehicles queuing in each toll lane that have been currently acquired, as the current queuing vehicle information of each toll lane in the toll station.

[0069] In this embodiment, the appearance feature information includes the license plate number and the vehicle model (including: large car, medium car, small car).

[0070] In this embodiment, the dynamic queuing distance refers to the real-time interval distance between the vehicle and the toll gate, and the interval distance here refers to the path length required for the vehicle to drive to the toll gate.

[0071] In this embodiment, the queued vehicles are all vehicles that have queued in all toll lanes acquired by lane monitoring.

[0072] In this embodiment, the non-passing vehicles are vehicles that have not passed in front of each toll lane.

[0073] The beneficial effects of the above technologies are: the situation of each toll lane can be fully and in real time grasped, providing a rich data source for subsequent information processing. Appearance feature information can be used for vehicle identification and classification, and dynamic queue distance helps to understand the position status of the vehicle in the toll lane, providing accurate data support for intelligent guidance and management. It can also update the queue situation in a timely manner, so that the management system always has the latest vehicle queue status, so as to make more accurate decisions and guidance. In general, this technical solution can improve the monitoring and management level of vehicles at toll stations, improve toll collection efficiency, reduce traffic congestion, and provide more intelligent and efficient services for vehicle passage.

[0074] Embodiment 3:

[0075] Based on Example 1, the vehicle travel time prediction module refers to Figure 3 ,include:

[0076] An information acquisition submodule, for acquiring appearance feature information and dynamic queuing distance of all currently queuing vehicles in each toll lane based on the queuing vehicle information of each toll lane;

[0077] A queuing vehicle type determination submodule, used to determine the types of all currently queuing vehicles in each toll lane based on appearance feature information of all currently queuing vehicles in each toll lane;

[0078] The historical traffic record parsing submodule is used to obtain, from the historical traffic records of each toll lane, the sub-historical traffic records of each historically passed vehicle of each type of currently queued vehicle in each toll lane relative to the current charging method, wherein the sub-historical traffic records of the vehicle include the charging processing time and dynamic queue distance of the vehicle, and the dynamic queue distances of all previous queued vehicles of the vehicle;

[0079] The travel time prediction submodule is used to predict the required travel time of each toll lane relative to the current queue vehicle information based on the dynamic queue distance of all current queue vehicles in each toll lane and the sub-historical travel record of each historical passing vehicle of each current queue vehicle type relative to the current toll collection method.

[0080] In this embodiment, the types of vehicles currently queuing are the types of vehicles currently queuing (not passing yet) in each toll lane, and the types here can be distinguished by vehicle brand series names or vehicle models.

[0081] In this embodiment, the historical passing vehicles are vehicles that have passed through the toll lane.

[0082] In this embodiment, the current charging method is the charging method currently adopted by a single toll lane. The charging methods here can be divided into manual charging and ETC charging, among which manual charging can also be differentiated according to different on-duty personnel.

[0083] In this embodiment, the sub-historical passage record of the historical passing vehicle relative to the current charging method is the passage record of the historical passing vehicle when passing through the toll lane under the current charging method.

[0084] In this embodiment, the toll processing time of the vehicle is the time required for the toll gate to process the vehicle, which is calculated based on the duration between the time when the vehicle stops at the toll gate and the time when the vehicle starts from the toll gate.

[0085] In this embodiment, all vehicles in the queue in front of the vehicle are all vehicles that are queued in the same toll lane as the vehicle and are in front of the vehicle as of the current moment.

[0086] The beneficial effects of the above technology are as follows: the information acquisition submodule can obtain the appearance feature information and dynamic queue distance of all vehicles currently queuing in each toll lane, providing a detailed data basis for subsequent analysis and processing. The appearance feature information can be used for vehicle identification and classification, and the dynamic queue distance reflects the position of the vehicle in the toll lane, which helps to grasp the vehicle status of the toll lane as a whole. The queue vehicle type determination submodule determines the types of all vehicles currently queuing in each toll lane based on the appearance feature information. It is very important to clarify the type of vehicle for targeted toll processing and prediction of travel time. Different types of vehicles may have differences in toll methods and travel speeds. The historical traffic record parsing submodule obtains the sub-historical traffic records of each historical passing vehicle of each current queue vehicle type relative to the current toll method from the historical traffic records of each toll lane, including information such as toll processing time, dynamic queue distance, and dynamic queue distance of all vehicles in front of the vehicle. This enables the system to fully draw on historical experience and provide a strong basis for predicting the travel time of the current queue vehicle. The travel time prediction submodule predicts the required travel time for each toll lane relative to the current queue vehicle information based on the dynamic queue distance of the current queue vehicle and the sub-historical travel records of the historically passing vehicles. This prediction can provide an important reference for the management of toll stations and vehicle guidance, helping toll stations to prepare in advance, optimize the toll collection process, and improve the overall travel efficiency. It can also allow vehicle drivers to have a more accurate expectation of waiting time.

[0087] Embodiment 4:

[0088] Based on Example 3, the travel time prediction submodule includes:

[0089] A vehicle queue generating unit, configured to generate all waiting-to-pass vehicle queues of each historically passed vehicle of each current queuing vehicle type based on all front queuing vehicles in the sub-historical passing records of each historically passed vehicle of each current queuing vehicle type relative to the current charging method;

[0090] A following speed determination unit, for determining, based on the dynamic queue distance of each historical passing vehicle of each current queue vehicle type and the corresponding dynamic queue distances of all previous queue vehicles, a following speed of each remaining historical passing vehicle except the first historical passing vehicle in each queue of vehicles to be communicated with relative to the corresponding queue of vehicles to be communicated;

[0091] A processing time prediction unit, for determining a predicted toll processing time for each current queue vehicle type relative to a current toll collection method based on the toll processing time of all historical passing vehicles of each current queue vehicle type;

[0092] The travel time prediction unit is used to predict the required travel time of each toll lane relative to the current queue vehicle information based on the dynamic queue distance of all current queue vehicles in each toll lane, the predicted toll processing time of each current queue vehicle type relative to the current toll collection method, and the following speed of each historical passing vehicle except the first historical passing vehicle in each queue of vehicles to be passed of each current queue vehicle type relative to the corresponding queue of vehicles to be communicated.

[0093] In this embodiment, each queue of vehicles to be passed by historical vehicles is a queue with each preceding queue vehicle of the historical vehicles as the first vehicle and the historical vehicles as the last vehicle, and includes a plurality of consecutive vehicles on the toll lane where the historical vehicles are located.

[0094] In this embodiment, based on the dynamic queue distance of each historical passing vehicle of each current queue vehicle type and the corresponding dynamic queue distances of all previous queue vehicles, the following speed of each remaining historical passing vehicle except the first historical passing vehicle in each queue of vehicles to be communicated with relative to the corresponding queue of vehicles to be communicated is determined, and is obtained by reading the following speed reading model that has been pre-trained;

[0095] The following speed reading model is obtained by pre-training using the dynamic queuing distances of a large number of vehicles and the corresponding dynamic queuing distances of all front-queuing vehicles (as the model input in the training sample) and the following speed of each historical passing vehicle except the first historical passing vehicle in each vehicle queue to be communicated relative to the corresponding vehicle queue to be communicated (as the model output in the training sample) calculated manually based on the aforementioned information.

[0096] In this embodiment, the following speed of historically passing vehicles relative to the corresponding queue of vehicles to be communicated represents: when the first vehicle in the queue of vehicles to be communicated passes through the gate of the toll gate, the remaining vehicles in the queue of vehicles to be communicated except the first vehicle follow and move forward a distance of one vehicle length, and the average driving speed during this distance.

[0097] In this embodiment, based on the toll processing time of all historical passing vehicles of each current queue type, the predicted toll processing time of each current queue type relative to the current toll collection method is determined, that is:

[0098] The outliers in the toll processing time of all historical passing vehicles of each current queue type are removed and then averaged, so as to obtain the predicted toll processing time of each current queue type relative to the current toll collection method.

[0099] In this embodiment, the predicted toll processing time of the current queue vehicle type relative to the current toll collection method is the toll processing time required for the current queue vehicle type to pass through the toll lane using the current toll collection method.

[0100] The beneficial effects of the above technology are: generating all the waiting vehicle queues for each historical passing vehicle of each current queuing vehicle type, providing a specific vehicle sequence reference for subsequent analysis, and helping to more accurately understand the relationship and traffic status between vehicles. The determination of the following speed helps to more accurately predict the driving dynamics of vehicles in the queue, taking into account the mutual influence between vehicles. Determine the predicted toll processing time for each current queuing vehicle type relative to the current charging method. This makes the prediction of the toll processing time more scientific and reasonable, and provides important parameters for the prediction of the overall travel time. The travel time prediction unit comprehensively considers multiple factors such as the dynamic queue distance, predicted toll processing time, and following speed of all current queuing vehicles in each toll lane, and predicts the required travel time for each toll lane relative to the current queuing vehicle information. This multi-factor comprehensive prediction method improves the accuracy of the travel time prediction, provides a reliable basis for toll station management and vehicle guidance, and helps to optimize the toll collection process, improve traffic efficiency, reduce vehicle waiting time, and improve the overall operation effect of the transportation system.

[0101] Embodiment 5:

[0102] Based on the fourth embodiment, the travel time prediction unit includes:

[0103] The vehicle queue generation subunit is used to generate all queues of vehicles to be passed and all partially passed vehicle queues of each current queued vehicle based on all queued vehicles of each toll lane currently acquired, and determine the following speed of each current queued vehicle relative to each partially passed vehicle queue based on the dynamic queue distance of all queued vehicles of each toll lane currently acquired;

[0104] a following speed prediction subunit, for determining a predicted following speed of each current queue vehicle relative to each queue of vehicles to be communicated, based on the following speed of each remaining historical passing vehicle relative to the corresponding queue of vehicles to be communicated and the following speed of each current queue vehicle relative to each partially passed queue of vehicles, except for the first historical passing vehicle in each queue of vehicles to be communicated of each historical passing vehicle of each current queue vehicle type;

[0105] The travel time prediction subunit is used to predict the required travel time of each toll lane relative to the current queue vehicle information based on the predicted following speed of each current queue vehicle relative to each queue of vehicles to be passed and the corresponding predicted toll processing time of all previous queue vehicle types relative to the current toll collection method.

[0106] In this embodiment, each queue of vehicles waiting to pass of the current queue vehicle is a queue with each preceding queue vehicle of the current queue vehicle that has not passed so far as the first vehicle and the current queue vehicle as the last vehicle, and includes a plurality of consecutive vehicles on the toll lane where the current queue vehicle is located.

[0107] In this embodiment, each partially passed vehicle queue of the current queue vehicle is a queue with each passed preceding queue vehicle of the current queue vehicle as the first vehicle and the current queue vehicle as the last vehicle, and includes a plurality of consecutive vehicles on the toll lane where the current queue vehicle is located.

[0108] In this embodiment, based on the currently acquired dynamic queue distance of all queuing vehicles in each toll lane, the following speed of each current queuing vehicle relative to each partially passed vehicle queue is determined, which is obtained by reading the following speed reading model that has been pre-trained.

[0109] In this embodiment, the predicted following speed of the current queue vehicle relative to each queue of vehicles to be communicated represents the average driving speed of the current queue vehicle during the driving distance when the first vehicle in the queue of vehicles to be communicated passes through the gate of the toll gate and the current queue vehicle moves forward a distance of one vehicle length.

[0110] The beneficial effects of the above technology are as follows: the vehicle queue generation subunit generates all the waiting vehicle queues and all the partially passed vehicle queues for each current queue vehicle based on all the queued vehicles in the current toll lane, which comprehensively covers the vehicle conditions of different traffic states. At the same time, the following speed of each current queue vehicle relative to the partially passed vehicle queue is determined, providing more abundant information for subsequent analysis. The following speed prediction subunit combines the following speed of historical passing vehicles and the following speed of the current queue vehicle relative to the partially passed vehicle queue to determine the predicted following speed of each current queue vehicle relative to each waiting vehicle queue. This comprehensive consideration of historical and current situations improves the accuracy of following speed prediction and can better reflect the vehicle dynamics in actual traffic. The prediction method adopted by the travel time prediction subunit fully considers the two key factors of vehicle following speed and toll processing time, making the prediction of travel time more accurate, providing a reliable decision-making basis for toll station management and vehicle guidance, helping to improve toll collection efficiency, reduce vehicle waiting time, and improve the operating efficiency of the entire transportation system.

[0111] Embodiment 6:

[0112] Based on Embodiment 5, the following speed prediction subunit includes:

[0113] The prediction model acquisition terminal is used to obtain the following speed prediction model;

[0114] The following speed prediction terminal is used to input the following speed of each current queue vehicle relative to all partially passed vehicle queues and the following speeds of all historical passing vehicles except the first historical passing vehicle in all waiting vehicle queues of all historical passing vehicles corresponding to the current queue vehicle type relative to the corresponding waiting vehicle queue into the following speed prediction model to obtain the predicted following speed of each current queue vehicle relative to each waiting vehicle queue.

[0115] In this embodiment, the following speed prediction model is a model that can output the predicted following speed of each current queue vehicle relative to each queue of vehicles to be communicated based on the following speed of each current queue vehicle relative to all partially passed vehicle queues and the following speeds of all historical passing vehicles except the first historical passing vehicle in all queues of vehicles to be communicated corresponding to the type of the current queue vehicle relative to the corresponding queue of vehicles to be communicated.

[0116] The model is obtained by pre-training using the following speeds of a large number of vehicles relative to all parts of the vehicle queues that have passed, the following speeds of all historical passing vehicles except the first historical passing vehicle in all the vehicle queues to be passed corresponding to the current queue vehicle type relative to the corresponding vehicle queues to be passed (as the model input in the training samples), and the predicted following speeds of the corresponding vehicles relative to each vehicle queue to be passed manually predicted based on the above information (as the model output in the training samples) as training samples.

[0117] The beneficial effects of the above technology are: the following speed prediction model is obtained through the prediction model acquisition end, and a professional model is introduced to deal with the following speed prediction problem, which improves the scientificity and accuracy of the prediction. The following speed prediction end takes the following speed of the current queued vehicle relative to some of the passed vehicle queues and the following speed of the historical passing vehicles other than the corresponding vehicle type relative to the corresponding vehicle queue to be communicated as input, and comprehensively considers multiple current and historical factors to make the prediction result more reliable. By using the following speed prediction model to process the input of various following speed information, it is possible to accurately predict the predicted following speed of each current queued vehicle relative to each vehicle queue to be passed, providing key data for the prediction of subsequent travel time, which helps toll stations better manage and guide vehicles, improve toll collection efficiency, and reduce traffic congestion.

[0118] Embodiment 7:

[0119] Based on Example 6, the travel time prediction subunit includes:

[0120] A following distance determination terminal is used to determine the following distance of each current queued vehicle in each toll lane relative to each queue of vehicles to be passed;

[0121] A following time prediction terminal is used to use the ratio of the following distance of each current queue vehicle in each toll lane relative to each queue of vehicles to be passed and the predicted following speed of the corresponding current queue vehicle relative to the corresponding queue of vehicles to be passed as the predicted passing time of each current queue vehicle in each toll lane relative to each queue of vehicles to be passed;

[0122] The total travel time prediction terminal is used to take the sum of the predicted travel time of each current queue vehicle in each toll lane relative to the corresponding queues of all vehicles to be passed, the predicted charging processing time of the corresponding current queue vehicle type relative to the current charging method, and the predicted charging processing time of all corresponding previous queue vehicle types relative to the current charging method as the required travel time of each toll lane relative to the current queue vehicle information.

[0123] In this embodiment, the following distance of each current queue vehicle in each toll lane relative to each queue of vehicles to be passed represents the distance that the current queue vehicle moves forward when the first vehicle in the queue of vehicles to be communicated passes through the gate of the toll gate. This distance is approximately but greater than the distance of one vehicle length, generally the distance from the front of the front vehicle to the front of the adjacent rear vehicle.

[0124] In this embodiment, the predicted passing time of the current queue vehicle relative to each queue of vehicles to be passed represents the predicted time required for the current queue vehicle to travel through the following distance of each current queue vehicle relative to each queue of vehicles to be passed in each toll lane.

[0125] The beneficial effects of the above technology are as follows: the following distance determination end can determine the following distance of the current queued vehicle in each toll lane relative to each queue of vehicles to be passed, providing a key data basis for subsequent predictions. Accurate following distance helps to more accurately analyze the positional relationship and dynamic changes between vehicles. The following time prediction end uses the ratio of following distance to predicted following speed as the predicted travel time, and this calculation method is scientific and reasonable. Based on the actual following distance and the accurately predicted following speed, the travel time of the current queued vehicle relative to each queue of vehicles to be passed can be predicted more accurately, providing an important component for the prediction of the overall travel time. The total travel time prediction end adopts a comprehensive consideration method, which fully covers the driving time of the vehicle in the queue and the toll processing time, making the prediction of the total travel time more accurate and reliable. This technical solution provides strong support for vehicle management and guidance at toll stations by accurately determining the following distance, scientifically predicting the following time, and comprehensively considering the total travel time, which helps to improve toll collection efficiency, reduce vehicle waiting time, optimize traffic flow, and improve the overall operation efficiency and service quality of the transportation system.

[0126] Embodiment 8:

[0127] Based on Example 1, the traffic guidance scheme generation module refers to Figure 4 ,include:

[0128] A submodule for obtaining information of a pre-queuing vehicle, for obtaining information of vehicles in a pre-queuing vehicle at a toll station based on lane monitoring of each toll lane in the toll station;

[0129] The traffic guidance scheme generating submodule is used to obtain the current traffic guidance scheme of the toll station based on the required travel time of each toll lane in the toll station relative to the current queue vehicle information and the prepared queue vehicle information.

[0130] The beneficial effects of the above technology are as follows: the pre-queue information acquisition submodule obtains the pre-queue vehicle information through lane monitoring of each toll lane in the toll station, which can grasp the situation of vehicles that are about to enter the toll area in advance, and provide forward-looking data support for the management and guidance of the toll station. The traffic guidance plan generation submodule combines the required passage time of each toll lane relative to the current queue vehicle information and the pre-queue vehicle information, and can comprehensively consider the current and future vehicle conditions to generate a more accurate traffic guidance plan. In this way, vehicles can be effectively allocated to different toll lanes, congestion can be avoided, and toll collection efficiency can be improved. By obtaining the pre-queue vehicle information in advance and generating a reasonable traffic guidance plan, the vehicle's passage process at the toll station can be optimized, the vehicle waiting time can be reduced, and the passage efficiency of the entire toll station can be improved, which also helps to ease the traffic pressure on the surrounding roads. Accurate traffic guidance plans can provide drivers with clearer guidance, improve user experience, and improve the service quality of toll stations.

[0131] Embodiment 9:

[0132] On the basis of Example 8, the traffic guidance scheme generation submodule includes:

[0133] A model acquisition unit, used to acquire a guidance scheme generation model;

[0134] The scheme generating unit is used to input the required passing time and the prepared queuing vehicle information of each toll lane in the toll station relative to the current queuing vehicle information into the guidance scheme generating model to obtain the current passing guidance scheme of the toll station.

[0135] In this embodiment, the guidance plan generation model is obtained in advance using the required travel time and prepared queue vehicle information of each toll lane in a large number of toll stations relative to the current queue vehicle information (as the input of training samples), and the guidance decision plan manually determined based on the aforementioned information (as the output of training samples) as training samples.

[0136] The beneficial effects of the above technology are as follows: the model acquisition unit acquires the guidance scheme generation model, and generates the traffic guidance scheme with the help of a professional model, which can improve the scientificity and accuracy of the scheme. The model can better handle complex traffic data after training, thereby providing a more reliable decision-making basis for the toll station. The scheme generation unit inputs the required travel time of each toll lane relative to the current queue vehicle information and the information of the prepared queue vehicles into the model. This method of comprehensively considering the current queue situation and the future prepared queue situation makes the generated traffic guidance scheme more accurate. It can comprehensively consider the actual traffic conditions of the toll station, reasonably allocate vehicles to different toll lanes, and improve the toll collection efficiency. By using the current traffic guidance scheme generated by the guidance scheme generation model, the traffic flow of the toll station can be effectively optimized. Guide vehicles to pass through the toll station quickly and orderly, reduce congestion, shorten vehicle waiting time, and improve overall traffic efficiency. At the same time, it also helps to improve the service quality of the toll station and provide drivers with a better travel experience.

[0137] Embodiment 10:

[0138] Based on Example 1, Figure 5 , also includes:

[0139] The guide light strip control module is used to control the light strips on the toll side of each toll lane in the toll station to display according to the current traffic guidance plan.

[0140] In this embodiment, Figure 5 A real-life picture of a toll station using an intelligent guidance system for vehicles passing through toll lanes guided by light strips.

[0141] The beneficial effect of the above technology is that the forward traffic guidance plan is displayed to the vehicle about to enter the toll lane through the light strip to achieve intelligent guidance.

[0142] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. An intelligent vehicle guidance system for toll lanes, characterized in that: include: A vehicle queue information acquisition module, used to acquire current queue vehicle information of each toll lane in the toll station based on lane monitoring of each toll lane in the toll station; A vehicle travel time prediction module is used to predict the required travel time of each toll lane relative to the current queued vehicle information based on the queued vehicle information and historical travel records of each toll lane; A traffic guidance scheme generating module, for obtaining a current traffic guidance scheme of a toll station based on the required travel time of each toll lane in the toll station relative to the current queue vehicle information and the prepared queue vehicle information; Among them, the vehicle travel time prediction module includes: An information acquisition submodule, for acquiring appearance feature information and dynamic queuing distance of all currently queuing vehicles in each toll lane based on the queuing vehicle information of each toll lane; A queuing vehicle type determination submodule, used to determine the types of all currently queuing vehicles in each toll lane based on appearance feature information of all currently queuing vehicles in each toll lane; The historical traffic record parsing submodule is used to obtain, from the historical traffic records of each toll lane, the sub-historical traffic records of each historically passed vehicle of each type of currently queued vehicle in each toll lane relative to the current charging method, wherein the sub-historical traffic records of the vehicle include the charging processing time and dynamic queue distance of the vehicle, and the dynamic queue distances of all previous queued vehicles of the vehicle; A travel time prediction submodule is used to predict the required travel time of each toll lane relative to the current queue vehicle information based on the dynamic queue distance of all current queue vehicles of each toll lane and the sub-historical travel record of each historical passing vehicle of each current queue vehicle type relative to the current toll collection method; Among them, the travel time prediction submodule includes: A vehicle queue generating unit, configured to generate all waiting-to-pass vehicle queues of each historically passed vehicle of each current queuing vehicle type based on all front queuing vehicles in the sub-historical passing records of each historically passed vehicle of each current queuing vehicle type relative to the current charging method; A following speed determination unit, for determining, based on the dynamic queue distance of each historical passing vehicle of each current queue vehicle type and the corresponding dynamic queue distances of all previous queue vehicles, a following speed of each remaining historical passing vehicle except the first historical passing vehicle in each queue of vehicles to be communicated with relative to the corresponding queue of vehicles to be communicated; A processing time prediction unit, for determining a predicted toll processing time for each current queue vehicle type relative to a current toll collection method based on the toll processing time of all historical passing vehicles of each current queue vehicle type; A travel time prediction unit is used to predict the required travel time of each toll lane relative to the current queue vehicle information based on the dynamic queue distance of all current queue vehicles of each toll lane, the predicted toll processing time of each current queue vehicle type relative to the current toll collection method, and the following speed of each historical passing vehicle other than the first historical passing vehicle in each queue of vehicles to be passed of each current queue vehicle type relative to the corresponding queue of vehicles to be communicated; The travel time prediction unit includes: The vehicle queue generation subunit is used to generate all queues of vehicles to be passed and all partially passed vehicle queues of each current queued vehicle based on all queued vehicles of each toll lane currently acquired, and determine the following speed of each current queued vehicle relative to each partially passed vehicle queue based on the dynamic queue distance of all queued vehicles of each toll lane currently acquired; a following speed prediction subunit, for determining a predicted following speed of each current queue vehicle relative to each queue of vehicles to be communicated, based on the following speed of each remaining historical passing vehicle relative to the corresponding queue of vehicles to be communicated and the following speed of each current queue vehicle relative to each partially passed queue of vehicles, except for the first historical passing vehicle in each queue of vehicles to be communicated of each historical passing vehicle of each current queue vehicle type; The travel time prediction subunit is used to predict the required travel time of each toll lane relative to the current queue vehicle information based on the predicted following speed of each current queue vehicle relative to each queue of vehicles to be passed and the corresponding predicted toll processing time of all previous queue vehicle types relative to the current toll collection method.

2. The intelligent guidance system for vehicles passing through toll lanes according to claim 1 is characterized in that: The vehicle queue information acquisition module includes: A monitoring acquisition submodule, used for acquiring lane monitoring videos based on lane monitoring of each toll lane in the toll station; An information reading submodule, used to obtain the appearance feature information and dynamic queuing distance of each queuing vehicle in the lane monitoring video of each toll lane; The information interception submodule is used to determine the appearance feature information and dynamic queuing distance of all vehicles that are not passing through each toll lane from the appearance feature information and dynamic queuing distance of all vehicles queuing in each toll lane that have been currently acquired, as the current queuing vehicle information of each toll lane in the toll station.

3. The intelligent guidance system for vehicles passing through toll lanes according to claim 1 is characterized in that: The following speed prediction subunit includes: The prediction model acquisition terminal is used to obtain the following speed prediction model; The following speed prediction terminal is used to input the following speed of each current queue vehicle relative to all partially passed vehicle queues and the following speeds of all historical passing vehicles except the first historical passing vehicle in all waiting vehicle queues of all historical passing vehicles corresponding to the current queue vehicle type relative to the corresponding waiting vehicle queue into the following speed prediction model to obtain the predicted following speed of each current queue vehicle relative to each waiting vehicle queue.

4. The intelligent guidance system for vehicles passing through toll lanes according to claim 3 is characterized in that: The travel time prediction subunit includes: A following distance determination terminal is used to determine the following distance of each current queued vehicle in each toll lane relative to each queue of vehicles to be passed; A following time prediction terminal is used to use the ratio of the following distance of each current queue vehicle in each toll lane relative to each queue of vehicles to be passed and the predicted following speed of the corresponding current queue vehicle relative to the corresponding queue of vehicles to be passed as the predicted passing time of each current queue vehicle in each toll lane relative to each queue of vehicles to be passed; The total travel time prediction terminal is used to take the sum of the predicted travel time of each current queue vehicle in each toll lane relative to the corresponding queues of all vehicles to be passed, the predicted charging processing time of the corresponding current queue vehicle type relative to the current charging method, and the predicted charging processing time of all corresponding previous queue vehicle types relative to the current charging method as the required travel time of each toll lane relative to the current queue vehicle information.

5. The intelligent vehicle guidance system for toll lanes according to claim 1, characterized in that: Traffic guidance scheme generation module, including: A submodule for obtaining information of a pre-queuing vehicle, for obtaining information of vehicles in a pre-queuing vehicle at a toll station based on lane monitoring of each toll lane in the toll station; The traffic guidance scheme generating submodule is used to obtain the current traffic guidance scheme of the toll station based on the required travel time of each toll lane in the toll station relative to the current queue vehicle information and the prepared queue vehicle information.

6. The intelligent vehicle guidance system for toll lanes according to claim 5, characterized in that: The traffic guidance scheme generation submodule includes: A model acquisition unit, used to acquire a guidance scheme generation model; The scheme generating unit is used to input the required passing time of each toll lane in the toll station relative to the current queue vehicle information and the prepared queue vehicle information into the guidance scheme generating model to obtain the current passing guidance scheme of the toll station.

7. The intelligent vehicle guidance system for toll lanes according to claim 1, characterized in that: Also includes: The guide light strip control module is used to control the light strips on the toll side of each toll lane in the toll station to display according to the current traffic guidance plan.

Images