Airport hub taxi transfer area passenger retention early warning system

By setting up video analysis subsystem, prediction subsystem and early warning subsystem in the airport hub, real-time monitoring and early warning of taxi transfer areas and taxi storage lots is solved, and the lack of passenger flow attribute identification and early warning capabilities in the existing technology is solved. The problem of this has achieved prediction and early warning of the capacity matching between taxi transfer areas and taxi storage tracts, avoiding passengers being stranded.

CN118982087APending Publication Date: 2024-11-19BEIJING GAOCHENG TECH DEV CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202410817039.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-06-24
Publication Date
2024-11-19

AI Technical Summary

Technical Problem

The passenger flow monitoring system of the existing airport hub taxi transfer area lacks ability to identify and deal with the transfer passenger flow attributes, and the monitoring of capacity and passenger flow data is separated from the application, so it is impossible to effectively predict and early warning of the saturation of taxi storage tracts. and passenger stranded incidents.

Method used

A passenger stranding warning system for airport hub taxi transfer areas including video analysis subsystem, prediction subsystem and early warning subsystem was designed. Passenger flow and traffic data were extracted through video analysis algorithm, and RNN model was used to carry out capacity in future time periods. Forecast, and set warning thresholds based on the prediction results, and automatically push warning information to the hub operating personnel.

Benefits of technology

Real-time monitoring and early warning of taxi transfer areas and taxi storage tracts in the airport hub, timely feedback on abnormal conditions, support pre-prevention and capacity scheduling, and avoid passengers being stranded.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118982087A_ABST
    Figure CN118982087A_ABST
Patent Text Reader

Abstract

The invention, which relates to the technical field of data analysis, discloses an airport hub taxi transfer area passenger retention early warning system comprising a video analysis subsystem module, a prediction subsystem module and an early warning subsystem module. The video analysis subsystem module extracts passenger flow number and traffic flow data of a hub transfer area and a vehicle storage yard, and transmits the extracted data to the prediction subsystem module; the prediction subsystem module receives the passenger flow number and traffic flow data transmitted by the video analysis subsystem module, predicts the passenger flow capacity condition of the airport in a future time period by using a prediction algorithm, and generates prediction results including taxi storage yard saturation prediction and passenger retention event prediction; and the early warning subsystem module is used for setting an early warning threshold value according to the prediction result generated by the prediction subsystem module, judging whether a taxi storage yard saturation event and a passenger retention event occur or not, and sending an early warning and pushing the early warning to hub operation personnel.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and more specifically, to a passenger stranded warning system in an airport hub taxi transfer area. Background Art

[0002] The "National Comprehensive Three-dimensional Transportation Network Planning Outline" puts forward the requirements for the integrated construction of comprehensive transportation hubs. As the combination of transportation architecture and urban design, comprehensive transportation hubs have been included in the scope of urban design and have become an important part of urban development strategies. Comprehensive transportation hubs such as airports mean that they will undertake the intersection and transfer of multiple modes of transportation. Therefore, such areas will also undertake a large number of passenger distribution tasks.

[0003] Currently, there are many methods for monitoring hub passenger flow. It is a relatively mature technology to use video, mobile phone positioning or other integrated data to accurately monitor the quantitative distribution of passenger flow. However, the current technical applications still have the following two deficiencies: first, the ability to identify and respond to the attributes of transfer passenger flow is insufficient; second, the current system separates the monitoring and application of capacity and passenger flow data. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a passenger stranded warning system in an airport hub taxi transfer area to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: an airport hub taxi transfer area passenger detention warning system, comprising a video analysis subsystem module, a prediction subsystem module, and an early warning subsystem module;

[0006] Video analysis subsystem module: Use existing monitoring equipment and newly added camera points to conduct video monitoring of the airport hub transfer area and parking lot, and connect the monitoring video stream to the video analysis subsystem module. Use the video analysis algorithm to process and analyze the monitoring screen, extract the passenger flow and vehicle flow data of the hub transfer area and parking lot, and transmit the extracted data to the prediction subsystem module;

[0007] Prediction subsystem module: receives the passenger flow and vehicle flow data transmitted by the video analysis subsystem module, uses the prediction algorithm to predict the passenger flow capacity of the airport in the future time period, and generates prediction results, including the saturation prediction of the taxi parking lot and the prediction of passenger detention events;

[0008] Early warning subsystem module: According to the prediction results generated by the prediction subsystem module, the early warning threshold is set to determine whether the taxi parking lot is saturated and passengers are stranded, and an early warning is issued and pushed to the hub operation personnel.

[0009] In a preferred embodiment, in the video analysis subsystem module, the existing monitoring equipment and the newly added camera points are used to conduct video monitoring of the airport hub transfer area and the parking lot, and the monitoring video stream is connected to the video analysis subsystem module, and the monitoring screen is processed and analyzed by the video analysis algorithm to extract the passenger flow and vehicle flow data of the hub transfer area and the parking lot, and the extracted data is transmitted to the prediction subsystem module. The specific steps are as follows:

[0010] Step A1: Arrange monitoring equipment and add new camera locations: Select monitoring equipment and camera locations according to the actual situation of the hub, and arrange and debug them. For areas with blind spots, add new camera locations to ensure comprehensive video coverage.

[0011] Step A2, video stream access and processing: the video stream is accessed to the video analysis subsystem module, and the accessed video stream is processed to monitor the entrance and exit of the taxi transfer queue area and the taxi parking lot in real time, and computer vision technology is used to perform face recognition and target detection, and to extract the real-time flow of passengers entering and leaving the taxi transfer area, as well as the real-time flow of taxis entering and leaving the taxi parking lot;

[0012] Step A3, data transmission: The extracted capacity flow and passenger flow information is transmitted to the prediction subsystem module through the network protocol. In order to ensure the real-time and accuracy of the data, the data transmission is optimized and encrypted.

[0013] In a preferred embodiment, in the video stream access and processing of step A2, computer vision technology is used to perform face recognition and target detection, and the real-time flow of passengers entering and leaving the taxi transfer area and the real-time flow of taxis entering and leaving the taxi parking lot are extracted, further comprising the following steps:

[0014] Step A201, target detection and tracking: using a target detection algorithm to detect faces and vehicles in the video, and tracking the detected faces and vehicles to obtain their motion trajectories;

[0015] Step A202, actual capacity and passenger flow data: Install vehicle sensors at the entrance and exit of the queue area and the parking lot to detect the entry and exit of vehicles to count the actual vehicle flow, expressed as P actual ; A card swiping system is set up at the hub entrance to record the time of passengers entering and leaving to count the actual number of passengers, expressed as V actual ;

[0016] Step A203, face recognition: for the detected faces, a face recognition model based on deep learning is used to identify passengers and distinguish their entry and exit from the queue area;

[0017] Step A204, video analysis: For the entrance and exit of the queuing area and the parking lot, count the number of people entering and leaving per unit time based on the tracked faces and vehicle trajectories to obtain the real-time passenger flow number P video 、Traffic flow V video ;

[0018] Step A205: Set a correction coefficient based on the actual passenger capacity flow at the hub monitoring location, and perform correction processing on the video analysis results. The specific calculation formula is as follows:

[0019]

[0020] Among them, k p represents the passenger flow correction coefficient, k v represents the traffic flow correction coefficient, P video is the passenger flow obtained by video analysis, P actual is the actual number of passengers, V video is the traffic volume obtained by video analysis, V actual is the actual traffic volume;

[0021] The correction coefficient is applied to the passenger flow and vehicle flow obtained by video analysis to perform correction processing to obtain the corrected real-time passenger flow and vehicle flow, and the corrected real-time passenger flow capacity analysis results are stored in the real-time capacity and passenger flow database. The specific calculation formula is as follows:

[0022] P adjusted =k p ×P video

[0023] V adjusted =k v ×V video

[0024] Among them, P adjusted represents the corrected real-time passenger flow number, V adjusted represents the corrected real-time traffic flow, k p represents the passenger flow correction coefficient, k v represents the traffic flow correction coefficient, P video is the passenger flow obtained by video analysis, V video It is the traffic volume obtained by video analysis.

[0025] In a preferred embodiment, the prediction subsystem module receives the passenger flow and vehicle flow data transmitted by the video analysis subsystem module, and uses the prediction algorithm to predict the passenger flow capacity of the airport in the future time period, and generates prediction results, including the taxi parking lot saturation prediction and the passenger detention event prediction. The specific steps are as follows:

[0026] Step B1, data preparation: receiving the passenger flow and vehicle flow data transmitted by the video analysis subsystem module, and extracting feature information including the weather of the day, whether it is a working day, and the operation status of the hub rail transit;

[0027] Step B2, RNN model construction: construct an RNN model, which includes an input layer, a hidden layer and an output layer. The input layer receives the number of passengers, vehicle flow data and feature information, and obtains the output of the hidden layer through weighted processing and nonlinear activation. The output layer generates the prediction results of the number of passengers and vehicle flow in the future time period.

[0028] Step B3, training model: input the passenger flow, vehicle flow data and feature information into the RNN neural network model for training, and generate the prediction results of the airport passenger flow and vehicle flow in the future time period, expressed as The specific calculation formula is as follows:

[0029]

[0030] in, It indicates the passenger flow forecast result in the future time period. represents the traffic flow prediction result in the future time period, h t represents the output of the hidden layer, g represents the activation function, b y is the bias vector of the hidden layer, W hy is the weight matrix, t represents the time step;

[0031] Step B4: Based on the forecast results of the number of airport passengers and vehicle volume in the future time period, the saturation of the taxi parking lot and the passenger detention event are predicted.

[0032] In a preferred embodiment, the warning subsystem module sets a warning threshold according to the prediction results generated by the prediction subsystem module, determines whether a taxi parking lot is saturated and a passenger is stranded, and sends a warning to the hub operation personnel. The warning push includes relevant information and recommended measures for events such as taxi parking lot saturation and passenger stranding, and automatically matches the hub's disposal plan for the hub operation personnel to complete the disposal of the hub passenger flow gathering event. The specific steps are as follows:

[0033] Step C1, receiving prediction results: obtaining prediction results of taxi parking lot saturation and passenger detention events from the prediction subsystem module, including the predicted number of parking lot vehicles, the number of passenger arrivals, and the predicted values ​​of passenger detention events;

[0034] Step C2, determine the warning triggering conditions: according to the prediction results, set the saturation warning and detention warning triggering conditions. When the number of vehicles in the parking lot reaches the saturation threshold and the predicted number of arriving passengers exceeds the detention limit, the warning condition is triggered;

[0035] Step C3, generating warning information: generating saturation warning information and detention warning information according to the triggering conditions, wherein the saturation warning information includes: timestamp, parking lot status, predicted value, comparison result with saturation threshold, and recommended action; the detention warning information includes: timestamp, predicted number of passenger detention events, comparison result with detention threshold, prediction result analysis, and recommended action;

[0036] Step C4: Send warning push: The generated warning information is automatically sent to the hub operation personnel via email, SMS, or App push to ensure timely communication of the information.

[0037] In a preferred embodiment, in the step C2, the warning triggering conditions are determined, and the saturation warning and detention warning triggering conditions are set. When the number of vehicles in the parking lot reaches the saturation threshold and the predicted number of arriving passengers exceeds the detention limit, the warning condition is triggered. The specific steps include:

[0038] The saturation warning: regularly count the number of vehicles in the taxi parking lot, set the saturation warning threshold to 0.8, and use the predicted value of the parking lot saturation as an indicator for determining saturation. When the parking lot saturation index S>0.8, a saturation warning reminder is triggered;

[0039] The detention warning: based on the predicted taxi arrival capacity and taxi arrival passenger flow, and combined with the current number of vehicles in the parking lot, it is predicted whether there will be an imbalance in passenger flow and capacity matching in the next two hours and the number of capacity gaps that exist. The detention warning threshold is set to 50. When the predicted value of the passenger detention event D>50, the detention warning reminder is triggered.

[0040] The beneficial effects of the present invention are as follows: through integrated monitoring of the taxi transfer flow and the number of vehicles in the taxi parking lot at the airport hub, the real-time taxi transfer flow and the capacity matching of the taxi parking lot in the airport hub are grasped globally, and timely early warning feedback is given to abnormal conditions. Through the prediction subsystem module, the taxi transfer flow and the matching of capacity within the next two hours are predicted, which supports relevant personnel to effectively carry out pre-emptive prevention, deploy capacity scheduling work in advance, quickly relieve the large number of passenger flows that are about to arrive at the airport, and fundamentally avoid the detention and gathering of passengers. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 is a system flow chart of the present invention;

[0042] Figure 2It is a structural block diagram of the present invention. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0044] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0045] In the description of the present application, the term "for example" is used to mean "used as an example, illustration or description". Any embodiment described as "for example" in the present application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid unnecessary details to obscure the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0046] Example 1

[0047] This embodiment provides Figure 1 and Figure 2 The passenger stranded warning system in the taxi transfer area of ​​the airport hub shown in the figure specifically includes a video analysis subsystem module, a prediction subsystem module, and an early warning subsystem module;

[0048] Video analysis subsystem module: Use existing monitoring equipment and newly added camera points to conduct video monitoring of the airport hub transfer area and parking lot, and connect the monitoring video stream to the video analysis subsystem module. Use the video analysis algorithm to process and analyze the monitoring screen, extract the passenger flow and vehicle flow data of the hub transfer area and parking lot, and transmit the extracted data to the prediction subsystem module;

[0049] Prediction subsystem module: receives the passenger flow and vehicle flow data transmitted by the video analysis subsystem module, uses the prediction algorithm to predict the passenger flow capacity of the airport in the future time period, and generates prediction results, including the saturation prediction of the taxi parking lot and the prediction of passenger detention events;

[0050] Early warning subsystem module: According to the prediction results generated by the prediction subsystem module, the early warning threshold is set to determine whether the taxi parking lot is saturated and passengers are stranded, and an early warning is issued and pushed to the hub operation personnel.

[0051] In this embodiment, the video analysis subsystem module specifically needs to be explained. In the video analysis subsystem module, the existing monitoring equipment and the newly added camera points are used to conduct video monitoring of the airport hub transfer area and the parking lot, and the monitoring video stream is connected to the video analysis subsystem module. The monitoring screen is processed and analyzed by the video analysis algorithm, and the passenger flow and vehicle flow data of the hub transfer area and the parking lot are extracted, and the extracted data is transmitted to the prediction subsystem module. The specific steps are as follows:

[0052] Step A1, deploy monitoring equipment: According to the actual situation of the hub, select monitoring equipment and camera locations, and deploy and debug them. For areas with blind spots, add camera locations to ensure comprehensive video coverage, further including the following steps:

[0053] Step A101: plan the layout of video surveillance according to the survey results of the hub structure, distribution of pedestrian and vehicle flows, and determine the number and area of ​​surveillance equipment;

[0054] Step A102: Arrange the camera points reasonably according to the planned monitoring area, connect the monitoring equipment to the network, and connect it to the monitoring center to ensure that the monitoring images can be viewed and managed in real time;

[0055] Step A2, video stream access and processing: For situations where there is existing video surveillance equipment coverage and the monitoring angle and video quality are relatively good, the existing video surveillance equipment is directly reused, and the real-time video stream is accessed to the video analysis subsystem module; for situations where video surveillance is not covered and the video surveillance angle is not good, a new camera point is added, the video stream is accessed to the video analysis subsystem module, and the accessed video stream is processed to monitor the entrance and exit of the taxi transfer queue area and the entrance and exit of the taxi parking lot in real time, use computer vision technology to perform face recognition and target detection, extract the real-time flow of passengers entering and leaving the taxi transfer area, and the real-time taxi flow entering and leaving the taxi parking lot, further comprising the following steps:

[0056] Step A201, target detection and tracking: using a target detection algorithm to detect faces and vehicles in the video, and tracking the detected faces and vehicles to obtain their motion trajectories;

[0057] Step A202, actual capacity and passenger flow data: Install vehicle sensors at the entrance and exit of the queue area and the parking lot to detect the entry and exit of vehicles to count the actual vehicle flow, expressed as P actual ; A card swiping system is set up at the hub entrance to record the time of passengers entering and leaving to count the actual number of passengers, expressed as V actual ;

[0058] Step A203, face recognition: for the detected faces, a face recognition model based on deep learning is used to identify passengers and distinguish their entry and exit from the queue area;

[0059] Step A204, video analysis: For the entrance and exit of the queuing area and the parking lot, count the number of people entering and leaving per unit time based on the tracked faces and vehicle trajectories to obtain the real-time passenger flow number P video 、Traffic flow V video ;

[0060] Step A205: Set a correction coefficient based on the actual passenger capacity flow at the hub monitoring location, and perform correction processing on the video analysis results. The specific calculation formula is as follows:

[0061]

[0062] Among them, k p represents the passenger flow correction coefficient, k v represents the traffic flow correction coefficient, P video is the passenger flow obtained by video analysis, P actual is the actual number of passengers, V video is the traffic volume obtained by video analysis, V actual is the actual traffic volume;

[0063] The correction coefficient is applied to the passenger flow and vehicle flow obtained by video analysis to perform correction processing to obtain the corrected real-time passenger flow and vehicle flow, and the corrected real-time passenger flow capacity analysis results are stored in the real-time capacity and passenger flow database. The specific calculation formula is as follows:

[0064] P adjusted =k p ×P video

[0065] V adjusted =k v ×V video

[0066] Among them, P adjusted represents the corrected real-time passenger flow number, V adjusted represents the corrected real-time traffic flow, k p represents the passenger flow correction coefficient, k v represents the traffic flow correction coefficient, P video is the passenger flow obtained by video analysis, V video is the traffic volume obtained by video analysis;

[0067] Step A3, data transmission: The extracted capacity flow and passenger flow information is transmitted to the prediction subsystem module through the network protocol. In order to ensure the real-time and accuracy of the data, the data transmission is optimized and encrypted.

[0068] In this embodiment, the prediction subsystem module specifically needs to be explained. The prediction subsystem module receives the passenger flow and vehicle flow data transmitted by the video analysis subsystem module, and uses the prediction algorithm to predict the passenger flow capacity of the airport in the future time period, and generates prediction results, including the taxi parking lot saturation prediction and the passenger detention event prediction. The specific steps are as follows:

[0069] Step B1, data preparation: receiving the passenger flow and vehicle flow data transmitted by the video analysis subsystem module, and extracting characteristic information including the weather of the day, whether it is a working day, and the operation status of the hub rail transit; the characteristic information is represented as: x t =[p t ,v t ,w t ,d t ,r t ], where x t represents a vector containing the number of passengers, vehicle flow data and feature information at the current moment, p t represents the number of passengers at the current moment, v t represents the current traffic flow, w t Indicates the weather of the day, d t Indicates whether it is a working day, r t It indicates whether there is rail transit operation at the hub, and t represents the time step;

[0070] Step B2, RNN model construction: construct an RNN model, which includes an input layer, a hidden layer and an output layer. The input layer receives the number of passengers, vehicle flow data and feature information, and obtains the output of the hidden layer through weighted processing and nonlinear activation. The output layer generates the prediction results of the number of passengers and vehicle flow in the future time period.

[0071] Step B3, training model: input the passenger flow, vehicle flow data and feature information into the RNN neural network model for training, and generate the prediction results of the airport passenger flow and vehicle flow in the future time period, expressed as in It indicates the passenger flow forecast result in the future time period. It represents the traffic flow prediction result in the future time period; the prediction result formula of the number of airport passengers in the future time period is as follows:

[0072]

[0073] in, It indicates the passenger flow forecast result in the future time period. represents the traffic flow prediction result in the future time period, h t represents the output of the hidden layer, g represents the activation function, b y is the bias vector of the hidden layer, W hy is the weight matrix, t represents the time step;

[0074] Step B4: based on the prediction results of the number of airport passengers and vehicle flow in the future time period, the saturation of the taxi parking lot and the passenger detention event are predicted;

[0075] The taxi parking lot saturation prediction is based on the traffic flow prediction results in the future time period obtained by the RNN neural network model, and is compared with the parking lot capacity to calculate the predicted value of the parking lot saturation. By consulting with the airport management department, the specific data of the airport parking lot capacity is obtained, including the number of available parking spaces, the size of the parking spaces, and the arrangement of the parking spaces. The parking lot capacity refers to the maximum number of vehicles that the airport can accommodate. The specific calculation formula is as follows:

[0076]

[0077] Among them, S is the predicted value of parking lot saturation, is the number of taxis arriving in the future time period, C is the capacity of the parking lot, and t represents the time step;

[0078] The passenger detention event prediction is to calculate the predicted value of the passenger detention event based on the passenger flow prediction results in the future time period obtained from the RNN neural network model and the processing capacity of the hub. Assuming that the number of passengers that the hub can handle per hour is M, the predicted passenger flow number is The predicted value of the passenger detention event is:

[0079]

[0080] in, Indicates taking The larger value of 0 ensures that the predicted value of the detention event will not be negative, which represents the gap between the actual number of passengers arriving at the time point (t+i) and the hub's processing capacity. When this gap is less than or equal to 0, that is, the actual number of passengers arriving does not exceed the hub's processing capacity, the gap is taken as 0; otherwise, the gap between the actual number of passengers arriving and the hub's processing capacity is taken. It represents the number of passengers who actually arrive at the time point (t+i), D represents the predicted value of the passenger detention event, t represents the time step, n represents the number of predicted time periods, and the summation symbol in the formula represents the summation of each time point. The obtained value represents the gap between the actual number of passengers who arrive and the hub processing capacity at that time point. When the gap is less than or equal to 0, it is set to 0. The final predicted value is the sum of the gaps at all time points.

[0081] In this embodiment, it should be specifically explained that the RNN neural network model is represented as: t =f(W hh h t-1 +W xh x t +b h ); the prediction result is expressed as: y t =g(W hy h t +b y ), where h t represents the hidden layer state, x t Represents feature information and data input, y t represents the prediction result output, f and g represent the activation function, (W hh ,W xh ,W hy ) is the weight matrix, b h and b y is the bias vector;

[0082] During the model training process, the mean square error is used as the loss function to measure the difference between the predicted value and the actual value. The model is optimized according to the training data through the back propagation algorithm to make the predicted result close to the actual value. The trained model is used to input new time series data and feature information to obtain the passenger flow prediction results in the future time period.

[0083] In this embodiment, the early warning subsystem module specifically needs to be explained. The early warning subsystem module sets an early warning threshold according to the prediction results generated by the prediction subsystem module, determines whether there are taxi parking lot saturation and passenger stranding events, and sends an early warning to the hub operation personnel. The early warning push includes relevant information and recommended measures for events such as taxi parking lot saturation and passenger stranding, and automatically matches the hub's disposal plan for the hub operation personnel to complete the disposal of the hub passenger flow gathering event. The specific steps are as follows:

[0084] Step C1, receiving prediction results: obtaining prediction results of taxi parking lot saturation and passenger detention events from the prediction subsystem module, including the predicted number of parking lot vehicles, the number of passenger arrivals, and the predicted values ​​of passenger detention events;

[0085] Step C2, determine the warning triggering conditions: according to the prediction results, set the saturation warning and detention warning triggering conditions. When the number of vehicles in the parking lot reaches the saturation threshold and the predicted number of arriving passengers exceeds the detention limit, the warning condition is triggered;

[0086] The saturation warning: regularly count the number of vehicles in the taxi parking lot, and set the saturation warning threshold to 0.8. The predicted value of the parking lot saturation is used as the indicator for determining saturation. When the parking lot saturation index S>0.8, the saturation warning reminder is triggered, and it is predicted that the parking lot will begin to be congested;

[0087] The detention warning: based on the predicted taxi arrival capacity and taxi arrival passenger flow, and combined with the current number of vehicles in the parking lot, it is predicted whether there will be an imbalance in passenger flow and capacity matching in the next two hours and the number of capacity gaps that exist. The detention warning threshold is set to 50. When the predicted value of the passenger detention event D>50, the detention warning reminder is triggered. The taxi arrival capacity refers to the service capacity that the airport taxi can provide, that is, the number of taxis that can be handled per hour; the taxi arrival passenger flow refers to the number of airport taxi passengers, that is, the number of passengers who arrive at the airport and need to take a taxi per hour;

[0088] Step C3, generating warning information: generating saturation warning information and detention warning information according to the triggering conditions, wherein the saturation warning information includes: the timestamp of the warning triggering, the parking lot status of "saturation" and "congestion", the predicted value and the comparison result with the saturation threshold, and the recommended actions to alleviate the parking lot saturation by increasing the taxi capacity and guiding passengers to choose other modes of transportation;

[0089] Detention warning information: the timestamp of the warning trigger, the predicted number of passenger detention events, the comparison results with the detention threshold, and the prediction result analysis, which analyzes the imbalance between passenger flow and capacity matching in the next two hours, explains the reasons for the detention, and recommends actions to alleviate passenger detention by increasing taxi services and optimizing capacity scheduling;

[0090] Step C4: Send warning push: The generated warning information is automatically sent to the hub operation personnel via email, SMS, or App push to ensure timely communication of the information.

[0091] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0092] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0093] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0094] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0095] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0096] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0097] 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. The passenger stranded warning system in the airport hub taxi transfer area is characterized by: It includes video analysis subsystem module, prediction subsystem module, and early warning subsystem module; Video analysis subsystem module: Use existing monitoring equipment and newly added camera points to conduct video monitoring of the airport hub transfer area and parking lot, and connect the monitoring video stream to the video analysis subsystem module. Use the video analysis algorithm to process and analyze the monitoring screen, extract the passenger flow and vehicle flow data of the hub transfer area and parking lot, and transmit the extracted data to the prediction subsystem module; Prediction subsystem module: receives the passenger flow and vehicle flow data transmitted by the video analysis subsystem module, uses the prediction algorithm to predict the passenger flow capacity of the airport in the future time period, and generates prediction results, including the saturation prediction of the taxi parking lot and the prediction of passenger detention events; Early warning subsystem module: According to the prediction results generated by the prediction subsystem module, the early warning threshold is set to determine whether the taxi parking lot is saturated and passengers are stranded, and an early warning is issued and pushed to the hub operation personnel.

2. The passenger stranding warning system in the airport hub taxi transfer area according to claim 1 is characterized by: In the video analysis subsystem module, the existing monitoring equipment and the newly added camera points are used to conduct video monitoring of the airport hub transfer area and the parking lot, and the monitoring video stream is connected to the video analysis subsystem module. The monitoring screen is processed and analyzed by the video analysis algorithm, and the passenger flow and vehicle flow data of the hub transfer area and the parking lot are extracted, and the extracted data is transmitted to the prediction subsystem module. The specific steps are as follows: Step A1: Arrange monitoring equipment: Select monitoring equipment and camera locations according to the actual situation of the hub, and arrange and debug them. For areas with blind spots, add camera locations to ensure comprehensive video coverage. Step A2, video stream access and processing: the video stream is accessed to the video analysis subsystem module, and the accessed video stream is processed, face recognition and target detection are performed using computer vision technology, and the real-time flow of passengers entering and leaving the taxi transfer area and the real-time flow of taxis entering and leaving the taxi parking lot are extracted; Step A3, data transmission: The extracted capacity flow and passenger flow information is transmitted to the prediction subsystem module through the network protocol, and the data transmission is optimized and encrypted.

3. The passenger stranding warning system in the airport hub taxi transfer area according to claim 2 is characterized by: The step A2 uses computer vision technology to perform face recognition and target detection, extracts the real-time flow of passengers entering and leaving the taxi transfer area, and the real-time flow of taxis entering and leaving the taxi parking lot, and further includes the following steps: Step A201, target detection and tracking: using a target detection algorithm to detect faces and vehicles in the video, and tracking the detected faces and vehicles to obtain their motion trajectories; Step A202, actual capacity and passenger flow data: Install vehicle sensors at the entrance and exit of the queue area and the parking lot to detect the entry and exit of vehicles to count the actual vehicle flow, expressed as P actual ; A card swiping system is set up at the hub entrance to record the time of passengers entering and leaving to count the actual number of passengers, expressed as V actual ; Step A203, face recognition: for the detected faces, a face recognition model based on deep learning is used to identify passengers and distinguish their entry and exit of the queuing area; Step A204, video analysis: For the entrance and exit of the queuing area and the parking lot, count the number of people entering and leaving per unit time based on the tracked faces and vehicle trajectories to obtain the real-time passenger flow number P video 、Traffic flow V video ; Step A205: Set a correction coefficient based on the actual passenger capacity flow at the hub monitoring location, and perform correction processing on the video analysis results. The specific calculation formula is as follows: Among them, k p represents the passenger flow correction coefficient, k v represents the traffic flow correction coefficient, P video is the passenger flow obtained by video analysis, P actual is the actual number of passengers, V video is the traffic volume obtained by video analysis, V actual It is the actual traffic volume.

4. The passenger stranding warning system in the airport hub taxi transfer area according to claim 3 is characterized by: The step of correcting the video analysis result in step A205 includes: applying the correction coefficient to the passenger flow number and vehicle flow obtained by the video analysis to perform correction processing to obtain the corrected real-time passenger flow number and vehicle flow, and storing the corrected real-time passenger flow capacity analysis result in the real-time capacity and passenger flow database. The specific calculation formula is as follows: P adjusted =k p ×P video V adjusted =k v ×V video Among them, P adjusted represents the corrected real-time passenger flow number, V adjusted represents the corrected real-time traffic flow, k p represents the passenger flow correction coefficient, k v represents the traffic flow correction coefficient, P video is the passenger flow obtained by video analysis, V video It is the traffic volume obtained by video analysis.

5. The passenger stranding warning system in the airport hub taxi transfer area according to claim 4 is characterized by: The prediction subsystem module receives the passenger flow and vehicle flow data transmitted by the video analysis subsystem module, and uses the prediction algorithm to predict the passenger flow capacity of the airport in the future time period, and generates prediction results, including the taxi parking lot saturation prediction and the passenger detention event prediction. The specific steps are as follows: Step B1, data preparation: receiving the passenger flow and vehicle flow data transmitted by the video analysis subsystem module, and extracting feature information including the weather of the day, whether it is a working day, and the operation status of the hub rail transit; Step B2, RNN model construction: construct an RNN model, which includes an input layer, a hidden layer and an output layer. The input layer receives the number of passengers, vehicle flow data and feature information, and obtains the output of the hidden layer through weighted processing and nonlinear activation. The output layer generates the prediction results of the number of passengers and vehicle flow in the future time period. Step B3, training model: input the passenger flow, vehicle flow data and feature information into the RNN neural network model for training, and generate the prediction results of the airport passenger flow and vehicle flow in the future time period, expressed as The specific calculation formula is as follows: in, It indicates the passenger flow forecast result in the future time period. represents the traffic flow prediction result in the future time period, h t represents the output of the hidden layer, g represents the activation function, b y is the bias vector of the hidden layer, W hy is the weight matrix, t represents the time step; Step B4: Based on the forecast results of the number of airport passengers and vehicle volume in the future time period, the saturation of the taxi parking lot and the passenger detention event are predicted.

6. The passenger stranding warning system in the airport hub taxi transfer area according to claim 5 is characterized by: The taxi parking lot saturation prediction is based on the traffic flow prediction results in the future time period obtained by the RNN neural network model, and compared with the parking lot capacity to calculate the predicted value of the parking lot saturation. The specific calculation formula is as follows: Among them, S is the predicted value of parking lot saturation, is the number of taxis arriving in the future time period, C is the capacity of the parking lot, and t represents the time step.

7. The passenger stranding warning system in the airport hub taxi transfer area according to claim 5 is characterized by: The passenger detention event prediction is to calculate the predicted value of the passenger detention event based on the passenger flow prediction results in the future time period obtained by the RNN neural network model. Assuming that the number of passengers that the hub can handle per hour is M, the predicted passenger flow number is The predicted value of the passenger detention event is: in, Indicates taking and 0, whichever is greater. represents the number of passengers who actually arrived at the time point (t+i), D represents the predicted value of the passenger detention event, t represents the time step, and n represents the number of predicted time periods.

8. The passenger stranding warning system in the airport hub taxi transfer area according to claim 7 is characterized by: The warning subsystem module sets a warning threshold according to the prediction results generated by the prediction subsystem module, determines whether a taxi parking lot is saturated and a passenger is stranded, and issues a warning to the hub operator. The specific steps are as follows: Step C1, receiving prediction results: obtaining prediction results of taxi parking lot saturation and passenger detention events from the prediction subsystem module, including the predicted number of parking lot vehicles, the number of passenger arrivals, and the predicted values ​​of passenger detention events; Step C2, determine the warning triggering conditions: according to the prediction results, set the saturation warning and detention warning triggering conditions. When the number of vehicles in the parking lot reaches the saturation threshold and the predicted number of arriving passengers exceeds the detention limit, the warning condition is triggered; Step C3, generating warning information: generating saturation warning and detention warning information according to the triggering conditions, and automatically sending the generated warning information to the hub operation personnel.

Citation Information

Cited By

  • Multi-source data fusion type passenger station intelligent management and control method and system based on AI drive

    CN121544079A