CN112001232B - Airport passenger flow travel chain accurate sensing device containing individual characteristics - Google Patents
Airport passenger flow travel chain accurate sensing device containing individual characteristics Download PDFInfo
- Publication number
- CN112001232B CN112001232B CN202010659145.8A CN202010659145A CN112001232B CN 112001232 B CN112001232 B CN 112001232B CN 202010659145 A CN202010659145 A CN 202010659145A CN 112001232 B CN112001232 B CN 112001232B
- Authority
- CN
- China
- Prior art keywords
- passenger
- passenger flow
- time
- land
- airport
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012546 transfer Methods 0.000 claims abstract description 124
- 230000008447 perception Effects 0.000 claims abstract description 21
- 238000010276 construction Methods 0.000 claims abstract description 20
- 238000000605 extraction Methods 0.000 claims description 47
- 238000000034 method Methods 0.000 claims description 30
- 238000012937 correction Methods 0.000 claims description 4
- 230000001360 synchronised effect Effects 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 13
- 230000006870 function Effects 0.000 description 8
- 238000001514 detection method Methods 0.000 description 7
- 238000005206 flow analysis Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000004075 alteration Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000011664 signaling Effects 0.000 description 2
- 230000002123 temporal effect Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/178—Human faces, e.g. facial parts, sketches or expressions estimating age from face image; using age information for improving recognition
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Business, Economics & Management (AREA)
- Human Computer Interaction (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Primary Health Care (AREA)
- Traffic Control Systems (AREA)
Abstract
The application provides an airport passenger flow travel chain accurate sensing device with individual characteristics, which comprises: passenger flow position acquisition module and camera module: acquiring passenger positioning data and passenger individual characteristic data; passenger flow streamline construction module: constructing passenger flow lines according to the passenger positioning data; passenger flow classifying module: classifying the passenger positioning data to obtain a passenger flow set; and a time domain module: extracting the time of different passenger flow domains in the passenger flow set reaching different passenger land-side traffic transfer nodes to obtain a plurality of time domains; an individual passenger transit transfer time module: obtaining the time of the individual passengers arriving at the land-side traffic transfer node according to the individual characteristic data of the passengers; trip chain perception module: and matching the time of the individual passengers arriving at the land-side traffic transfer node with the time domains of different traffic modes to obtain an airport passenger flow travel chain containing the individual characteristics of each passenger. Solves the problem that the single passenger flow sensing means in the prior art can not meet the requirements of complete and accurate depiction of airport passenger space-time trajectories.
Description
Technical Field
The application belongs to the technical field of traffic data processing, and particularly relates to an airport passenger flow travel chain accurate sensing device with individual characteristics.
Background
In the study of resident travel chains in the traffic professional field, the complete resident travel chains are obtained mainly through the study of resident travel behaviors and travel mode selection models, and technical support is provided for traffic planning and urban traffic efficiency improvement through the chain analysis. The extraction of a large-scale travel chain in the prior art cannot meet the precision requirement of a small range of an airport. The large-scale travel chain analysis aiming at urban traffic planning and efficiency improvement is not suitable for identifying passenger flow travel chains in a small range on the land side of an airport, and the requirement on the identification precision of the passenger flow travel chains on the land side of the airport is far from being met. For example, based on the identification and extraction of the travel chain of the public transport IC card, the departure, transfer and arrival stations of the passengers can be known through the card swiping records of the passengers, but the track data of the activities of the passengers in the stations cannot be obtained through the IC card data.
Regarding the passenger flow sensing technology means, passenger flow section data of an airport, such as video data, 5G mobile phone data, mobile application data, bluetooth data, dynamic two-dimensional code data and the like, are mainly obtained by using passenger flow sensing equipment, and relevant management and service are carried out on the passenger flow of the airport through the obtained passenger flow data. The current accurate sensing method for the passenger flow of the land side of the airport is still immature. The related research on airport passenger flow perception is mostly focused on statistics and identification of airport passenger flow by using a single perception means, and the related research and method for accurate perception of airport land side passenger flow travel chain are still lacking.
Aiming at a single passenger flow sensing means in the prior art, the passenger flow sensing means can only meet the requirements of passenger flow of a section or passenger flow statistics in a certain range with low precision requirements; the single passenger flow sensing means can not complete and accurate description of airport passengers space-time track, and can not realize accurate sensing of individual travel chains. And moreover, passenger flow data perceived by a single means cannot well support the continuous transportation coordination linkage requirement of various transportation modes, and the airport continuous function cannot be better exerted.
Disclosure of Invention
The application provides an accurate sensing device for an airport passenger flow travel chain with individual characteristics, and aims to solve the problems that a single passenger flow sensing means in the prior art cannot meet the requirements for complete and accurate depiction of space-time trajectories of airport passengers and cannot realize accurate sensing of the individual travel chain.
According to an embodiment of the application, an airport passenger flow travel chain accurate sensing device containing individual characteristics is provided, and the airport passenger flow travel chain accurate sensing device specifically comprises:
passenger flow position acquisition module: the method is used for acquiring passenger positioning data;
and the camera module: acquiring individual characteristic data of the passengers;
passenger flow streamline construction module: the passenger flow line is constructed according to passenger positioning data, and a starting passenger flow node and a stopping passenger flow node of the passenger flow line are respectively a passenger cabin-out node and a passenger land-side traffic transfer node;
Passenger flow classifying module: the passenger positioning data are used for classifying the passengers according to the arrival time and the arrival positions of the passengers to obtain a passenger flow set, and the passenger flow set comprises a plurality of passenger flow areas of the passengers at different positions and different arrival times;
and a time domain module: the method comprises the steps of extracting time for different passenger flow domains in a passenger flow set to reach different passenger land-side traffic transfer nodes respectively, and obtaining a plurality of time domains reaching the different land-side traffic transfer nodes;
an individual passenger transit transfer time module: the method comprises the steps of obtaining the time of an individual passenger arriving at a land-side traffic transfer node according to the individual characteristic data of the passenger;
trip chain perception module: the airport passenger flow travel chain containing individual characteristics of each passenger is obtained by matching the time of the individual passenger arriving at the land-side transportation transfer node with the time domains of different transportation modes and combining passenger flow lines.
Optionally, the passenger flow position acquisition module acquires the passenger flow position data through the passenger 5G mobile phone positioning data or the intelligent wearable device positioning data; and the camera module passengers acquire the individual characteristic data through face recognition camera equipment.
Optionally, the face recognition camera device is arranged at a passenger out-of-cabin node and a passenger land-side traffic transfer node.
Optionally, the passenger flow streamline construction module constructs the passenger flow streamline including the passenger flow node according to the passenger positioning data, and specifically includes the following steps:
determining a passenger flow node of a passenger flow streamline, wherein the passenger flow node further comprises an airport corridor bridge node and a baggage extraction node;
and carrying out data fitting, data interpolation and data deviation correction on the passenger positioning data to obtain passenger flow lines.
Optionally, the time domain module extracts time when different passenger domains in the passenger flow set reach different passenger land-side traffic transfer nodes respectively to obtain a plurality of time domains reaching different land-side traffic transfer nodes, and specifically comprises the following steps:
when different land-side traffic transfer nodes are not overlapped in the vertical space of the passenger flow line, directly extracting the time of different passenger flow domains reaching the different land-side traffic transfer nodes respectively, and obtaining a plurality of time domains reaching the different land-side traffic transfer nodes;
when different land-side traffic transfer nodes overlap on the vertical space of the passenger flow line, accumulating the time for different passenger flow domains to reach the traffic measurable node and the time for different passenger flow domains to reach different land-side traffic transfer nodes from the traffic measurable node to obtain a plurality of time domains reaching different land-side traffic transfer nodes;
The flow measurable node is a fixed position which is not at the overlapping position on the passenger flow line; and predicting the time for different passenger flow domains to reach different land-side traffic transfer nodes from the traffic measurable nodes according to the distance between the traffic measurable nodes and the different land-side traffic transfer nodes.
Optionally, the accurate sensing device of airport passenger flow travel chain further comprises an individual travel chain library module: and the airport passenger flow travel chain is used for classifying the airport passenger flow travel chains containing the individual characteristics of each passenger according to the individual characteristics of the passenger to obtain an individual travel chain library.
Optionally, the passenger individual characteristics include face information, age, and gender.
Optionally, the camera module is disposed at passenger flow nodes, and each passenger flow node is provided with one or more face recognition cameras.
Optionally, the cameras of the plurality of passenger flow nodes are provided with time unifying time service devices, so that the time of each camera is synchronized.
The airport passenger flow travel chain accurate sensing device with individual characteristics comprises a passenger flow position acquisition module: acquiring passenger positioning data; and the camera module: acquiring individual characteristic data of the passengers; passenger flow streamline construction module: constructing a passenger flow line according to the passenger positioning data, wherein an initial passenger flow node and a final passenger flow node of the passenger flow line are respectively a passenger cabin-out node and a passenger land-side traffic transfer node; passenger flow classifying module: classifying the passenger positioning data according to the arrival time and the position of the passengers to obtain a passenger flow set, wherein the passenger flow set comprises a plurality of passenger flow areas of the passengers at different positions and different arrival times; and a time domain module: extracting the time of different passenger flow domains in the passenger flow set reaching different passenger land-side traffic transfer nodes respectively, and obtaining a plurality of time domains reaching different land-side traffic transfer nodes; an individual passenger transit transfer time module: obtaining the time of the individual passengers arriving at the land-side traffic transfer node according to the individual characteristic data of the passengers; trip chain perception module: matching the time of the individual passengers arriving at the land-side traffic transfer node with the time domains of different traffic modes, and combining the passenger flow lines to obtain an airport passenger flow travel chain containing the individual characteristics of each passenger. The accurate sensing device for the airport passenger travel chain with the individual characteristics solves the problems that a single passenger flow sensing means in the prior art cannot meet the requirements of complete and accurate depiction of space-time trajectories of airport passengers and cannot realize accurate sensing of the individual travel chain. Through multi-source passenger flow data such as 5G mobile phone data and video, the accurate perception of the whole travel chain of each continuous transportation mode from the landing to the arrival of airport land side passenger flow is realized, the depiction of individual space-time tracks of airport land side passengers is completed, and technical support means are provided for land side passenger flow analysis, traffic perception, traffic capacity matching and the like.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute a limitation on the application. In the drawings:
FIG. 1 shows a schematic structural diagram of an airport passenger flow travel chain accuracy sensing device with individual features according to an embodiment of the application;
a schematic diagram of the construction of a passenger flow line according to an embodiment of the application is shown in fig. 2;
a schematic diagram of mobile phone data preprocessing according to an embodiment of the present application is shown in fig. 3;
a direct extraction schematic of the time domain according to an embodiment of the application is shown in fig. 4;
an indirect extraction schematic of a time domain according to an embodiment of the application is shown in fig. 5;
a schematic diagram of camera layout according to an embodiment of the application is shown in fig. 6;
an individual travel chain extraction schematic according to an embodiment of the application is shown in fig. 7;
a schematic step diagram of an airport passenger flow travel chain accurate sensing method with individual features according to an embodiment of the application is shown in fig. 8.
Detailed Description
In the process of realizing the application, the inventor finds that the large-range travel chain analysis aiming at urban traffic planning and efficiency improvement is not suitable for identifying the passenger flow travel chain in a small range on the land side of the airport, and the requirement on the identification precision of the passenger flow travel chain on the land side of the airport is far from being met. In order to improve the efficiency of airport land side transfer, it is necessary to know the precise data of the arrival of passengers coming out of the air side to each traffic pattern. In the current airport passenger flow sensing, a method for extracting space-time chains of airport trip individuals is lacking.
The accurate sensing method and device for the airport passenger flow travel chain with the individual characteristics mainly comprise the construction of an airport space passenger flow line and the extraction of the individual travel chain. The airport space passenger flow line construction is used for completing space-time depiction of main passenger flow channels and passenger flow stay key points of an airport through airport passenger flow line construction, and a foundation is established for extraction of subsequent individual continuous travel chains; the individual travel chain is extracted, so that accurate perception of passenger flow is realized through the individual travel chain extraction. The individual travel chain extraction is based on the time domain extracted by the 5G mobile phone data and the accurate matching of the travel time provided by the video detection data.
According to the accurate sensing method and device for the airport passenger flow travel chain containing individual characteristics, through the multi-source passenger flow data such as 5G mobile phone data and video, the accurate sensing of the full travel chain of each continuous transportation mode from the landing to the arrival of the airport land side passenger flow is realized. The method is used for describing individual space-time trajectories of airport land-side passengers, and provides technical support means for land-side passenger flow analysis, traffic perception, traffic capacity matching and the like. It is emphasized that the practice of the present application is a legal use.
In order to make the technical solutions and advantages of the embodiments of the present application more apparent, the following detailed description of exemplary embodiments of the present application is provided in conjunction with the accompanying drawings, and it is apparent that the described embodiments are only some embodiments of the present application and not exhaustive of all embodiments. It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other.
Example 1
The airport passenger flow travel chain accurate sensing method with individual characteristics provided by the embodiment of the application mainly comprises three parts.
The first is to realize the construction of airport passenger flow lines. The method mainly comprises the steps of acquiring land-side passenger flow lines of an airport through 5G mobile phone data acquisition, wherein the passenger flow lines are travel routes passing through land-side key points.
The second is time domain extraction. And obtaining the time information of the positions of the key points of the passenger passing through the airport by utilizing video image recognition, such as feature recognition, face recognition or 5G mobile phone data matching, at the positions of the key points of the passenger passing through the airport, and taking the time information as the basis for accurately sensing the individual travel chains.
Third is the accurate perception of the individual travel chain. Based on the data information, accurate matching of the travel route of the individual travel on the airport land side is achieved, the spatial position matching and the time information matching are included, the complete travel chain information of the individual is obtained, a thematic base based on different individual characteristics is built, and a thematic base support is provided for follow-up accurate passenger flow prediction.
According to the airport passenger flow travel chain accurate sensing method containing individual features, based on the passenger flow streamline construction technology of 5G mobile phone data and the individual feature recognition based on video detection, video intelligent recognition data and 5G mobile phone signaling data are fused and matched, the defect that a single detection means cannot recognize a complete travel chain of passenger flow is overcome, accurate recognition of an airport land side passenger flow travel chain is achieved, and accurate sensing of airport land side passenger flow can be achieved based on the accurate perception.
The embodiment of the application is specifically implemented as follows:
fig. 1 shows a schematic structural diagram of an airport passenger flow travel chain accurate sensing device with individual features according to an embodiment of the application.
As shown in fig. 1, the airport passenger flow travel chain accurate sensing device with individual characteristics comprises a passenger flow position acquisition module 10, a camera module 20, a passenger flow streamline construction module 30, a passenger flow classification module 40, a time domain module 50, an individual passenger transportation transfer time module 60 and a travel chain sensing module 70. The specific structure is as follows:
passenger flow position acquisition module 10: the method is used for acquiring passenger positioning data;
the camera module 20: acquiring individual characteristic data of the passengers;
passenger flow streamline construction module 30: the passenger flow line is constructed according to passenger positioning data, and a starting passenger flow node and a stopping passenger flow node of the passenger flow line are respectively a passenger cabin-out node and a passenger land-side traffic transfer node;
passenger flow classification module 40: the passenger positioning data are used for classifying the passengers according to the arrival time and the arrival positions of the passengers to obtain a passenger flow set, and the passenger flow set comprises a plurality of passenger flow areas of the passengers at different positions and different arrival times;
time domain module 50: the method comprises the steps of extracting time for different passenger flow domains in a passenger flow set to reach different passenger land-side traffic transfer nodes respectively, and obtaining a plurality of time domains reaching the different land-side traffic transfer nodes;
Individual passenger transit transfer time module 60: the method comprises the steps of obtaining the time of an individual passenger arriving at a land-side traffic transfer node according to the individual characteristic data of the passenger;
travel chain perception module 70: the airport passenger flow travel chain containing individual characteristics of each passenger is obtained by matching the time of the individual passenger arriving at the land-side transportation transfer node with the time domains of different transportation modes and combining passenger flow lines.
Specifically, the passenger flow position obtaining module 10 is a 5G mobile phone or an intelligent wearable device, and the passenger flow position obtaining module 10 obtains passenger positioning data through the passenger 5G mobile phone positioning data or the intelligent wearable device positioning data.
Specifically, the camera module 20 is a face recognition camera device, and the camera module 20 obtains individual characteristic data of the passenger through the face recognition camera device. The camera module 20 is disposed at passenger flow nodes, and each passenger flow node is provided with one or more face recognition cameras. The cameras of the passenger flow nodes are provided with a time unified time service device, so that the time of each camera is synchronous.
Specifically, the passenger flow streamline construction module 30 constructs passenger flow streamlines according to passenger positioning data, and specifically includes the following steps:
first, a traffic node of a traffic flow line is determined.
A schematic diagram of the construction of a passenger flow line according to an embodiment of the application is shown in fig. 2.
As shown in fig. 2, airport passenger flows mainly pass through several time nodes from the air side to the land side, including port withstanding, warehouse-out, corridor bridge, terminal building, baggage extraction and subsequent traffic mode waiting areas. The main space nodes are a corridor bridge, a baggage picking-up area and a waiting area in a continuous traffic mode.
Thus, the passenger flow nodes include airport corridor nodes and baggage retrieval nodes in addition to passenger egress nodes and passenger land-side transit transfer nodes.
And then, carrying out data fitting, data interpolation and data deviation correction on airport passenger flow data to obtain a passenger flow line with high precision.
A schematic diagram of mobile phone data preprocessing according to an embodiment of the present application is shown in fig. 3.
As shown in fig. 3, the 5G mobile phone data is used for constructing the passenger flow line, and the characteristics of high layout density of the 5G base station and high position accuracy of the 5G mobile phone data are mainly used for constructing the passenger flow line. Firstly, fitting 5G mobile phone data, removing data with large offset, interpolating and rectifying the data, and finally forming individual trip chain information with higher precision.
And extracting the time for different passenger flow domains in the passenger flow set to reach different passenger land-side traffic transfer nodes respectively, and obtaining a plurality of time domains reaching different land-side traffic transfer nodes.
Before extracting the time domain, a spatial range of time domain extraction needs to be specified. According to the spatial distribution of each successive traffic mode at the airport land side, the time domain extraction mode can be divided into a direct extraction mode and an indirect extraction mode. The direct extraction mode is suitable for the traffic transportation mode waiting areas without overlapping in vertical space, and in this case, the 5G mobile phone data can be directly divided from the precision range of the 5G mobile phone data. The indirect extraction mode is suitable for the condition that the waiting areas of the transportation modes overlap in vertical space.
Specifically, in the time domain module 50, the time for different passenger domains in the passenger flow set to reach different passenger land-side transportation transfer nodes is extracted to obtain a plurality of time domains reaching different land-side transportation transfer nodes, which specifically includes a direct extraction method in step S41 and an indirect extraction method in step S42. The method comprises the following specific steps:
s41: when different land-side traffic transfer nodes are not overlapped in the vertical space of the passenger flow line, the time for different passenger flow domains to reach the different land-side traffic transfer nodes respectively is directly extracted, and a plurality of time domains reaching the different land-side traffic transfer nodes are obtained.
A direct extraction schematic of the time domain according to an embodiment of the application is shown in fig. 4. As shown in fig. 4, the direct extraction mode defines a data acquisition range according to the space structure of each traffic mode waiting area, and the 5G mobile phone data falling into the acquisition range is regarded as the effective data of the traffic mode time domain, and the time that the passenger flows of different passenger flow domains respectively reach the transfer nodes of different traffic modes on the land side is obtained by further processing on the basis of the effective data.
First, the passenger flow classification module 40 classifies passenger flow groups according to temporal features and spatial locations.
After the airport passenger flows out of the cabin, a group of port-shifting passenger flows are formed, and the time of the same group of port-shifting passenger flows reaching different land-side traffic transfer modes has a comparable reference function, so that the same group of port-shifting passenger flows are classified.
The passenger flow fields are defined as passenger flow groups which have the same departure space-time characteristics, namely, the passenger flow groups which leave the cabin at the same position in the same time period, so that the collection of all the passenger flow fields reached by the airport flight forms a passenger flow collection at the land side of the airport. The passenger flow set is denoted by A and the expression is as follows:
A＝A 1 ∪A 2 ∪...∪A n ；
wherein for the passenger basin A i ，i∈[1,n]N is a natural number.
Then, a time domain is extracted from the passenger flow domain.
The time when the passenger flow belonging to the same customer flow basin arrives at different land side traffic transfer modes is classified, and the time when the passenger flow arrives at different land side traffic transfer nodes is called as the time domain. Defining T for time domain j The expression j represents land-side traffic transfer mode; defining a passenger basin A i If the number of passengers is w, the transit time of the w th passenger to the traffic mode j is T Awij 。
Then passenger flow area a i Time domain T of arrival at transfer pattern j within a certain fixed time ij Can be expressed as:
T ij ＝[TA 1ij ，TA 2ij ，TA 3ij ....TA wij ]；
a time domain T consisting of passenger flow domains within a certain period of time, such as 24 hours j The expression is as follows:
s42: when different land-side traffic transfer nodes overlap in the vertical space of the passenger flow line, the time for different passenger flow domains to reach the traffic measurable node and the time for different passenger flow domains to reach different land-side traffic transfer nodes from the traffic measurable node are accumulated, and a plurality of time domains reaching different land-side traffic transfer nodes are obtained.
The time for different passenger flow domains to reach the flow measurable node is obtained by directly extracting the passenger positioning data or the passenger individual characteristic data.
The flow measurable node is a fixed position which is not at the overlapping position on the passenger flow line and is near the overlapping area; and predicting the time for different passenger flow domains to reach different land-side traffic transfer nodes from the traffic measurable nodes according to the distance between the traffic measurable nodes and the different land-side traffic transfer nodes.
Specifically, in the case that there is a spatial overlap in the land-side traffic waiting area, 5G mobile phone data in the range cannot be categorized, so that an end face needs to be found on the traffic flow line, that is, the traffic flow measurable node identifies and collects the 5G mobile phone data, and the traffic flow measurable node is a traffic flow measurable section on the traffic flow line and has uniqueness of a link leading to the traffic waiting area. The indirect extraction mode needs to predict the time of the passenger flow domain reaching different land-side traffic transfer nodes from the traffic measurable nodes according to the distance, speed and other data of the passenger, and finally the complete travel chain time is formed.
An indirect extraction schematic of a time domain according to an embodiment of the application is shown in fig. 5;
as shown in fig. 5, the time TA for different passenger domains to reach the traffic-measurable node wio Reference is made to the direct extraction mode of step S41.
Let us assume basin A i The transit time of the passenger w arriving at the traffic mode j is TA wij Then passenger flow area A i Time domain TA from section O to transfer mode j wij Can be expressed as:
TA wij ＝TA wio +TA woj
the flow measurable section O is a flow measurable node, is fixedly arranged at the position of a trip chain key point near the overlapping area, and is provided with a high-definition video camera;
wherein TA wio The transit time of the passenger w reaching the section O can be directly extracted through 5G mobile phone data.
Wherein TA woj For the predicted transit time of the passenger w arriving at the transfer mode j from the section O, the mainPredictive calculation is performed through data such as distance, speed and the like of the passengers;
time domain TA woj The calculation formula of (2) is as follows:
s is the passing distance from the section O to the traffic mode j; v is the current moving speed measured according to the 5G mobile phone data.
Specifically, in the individual passenger transportation transfer time module 60, the time when the individual passenger arrives at the land-side transportation transfer node is obtained according to the individual characteristic data of the passenger.
Specifically, first, the face recognition cameras need to be arranged in position.
A schematic diagram of camera layout according to an embodiment of the application is shown in fig. 6.
As shown in fig. 6, specifically, a face recognition server is deployed at an airport, and the functions of the airport camera are updated by associating with the established camera, so as to realize intelligent detection. For the situation that cameras are not arranged at key nodes, cameras can be arranged at main nodes of an airport and are associated with a back-end face recognition server. The distribution points of the cameras are required to meet the acquisition of all passenger flows of the section. For areas which cannot be covered by a single camera, a combined camera can be arranged for flow collection.
Travel chain perception module 70: matching the time of the individual passengers arriving at the land-side traffic transfer node with the time domains of different traffic modes, and combining the passenger flow lines to obtain an airport passenger flow travel chain containing the individual characteristics of each passenger.
The trip chain sensing module 70 further performs spatial position matching and time information matching when matching the time domains of different traffic modes, and finally obtains complete trip chain information of the individual.
Optionally, the following steps are further included after the travel chain sensing module 70:
and classifying the airport passenger flow travel chains containing the individual characteristics of each passenger according to the individual characteristics of the passenger to obtain an individual travel chain library. Wherein, the passenger classification comprises classification according to the age of the passenger, the sex of the passenger and the like. Passenger individual characteristics include face information, age, and gender.
Then, the time domain obtained in the time domain module 50 is matched, and individual travel chain extraction is obtained.
Specifically, passenger flow nodes mainly distributed in passenger flow comprise a gallery bridge, a baggage extraction area and different traffic mode transfer areas, cameras with face recognition functions are arranged on the important nodes, unified time service is provided for the cameras, and time synchronization of the cameras is achieved. When passenger flows through each key node, the data of the individual can be recorded through the camera.
An individual travel chain extraction schematic is shown in fig. 7 according to an embodiment of the application.
As shown in fig. 7, the individual characteristics of the passengers are identified by face recognition, and the travel time of the passengers from the bridge to the transfer areas of different traffic modes, i.e. the time of the individual passengers arriving at the land-side transfer node obtained in the individual passenger transfer time module 60, is recorded as t ij Will t ij Matching with the time domain of the traffic mode, namely, the passenger arrives at the continuous transportation traffic mode, namely, the traffic mode is selected, and finally, the complete travel chain information of the passenger is obtained.
And finally, constructing an individual travel chain feature library.
And establishing a trip database based on individual characteristics according to the face recognition and the 5G mobile phone data. And respectively establishing characteristic libraries of individual travel chains according to classification modes such as age groups, gender and the like. And providing data support for subsequent travel prediction and information service for the individual.
The airport passenger flow travel chain accurate sensing device with individual characteristics comprises a passenger flow position acquisition module: acquiring passenger positioning data; and the camera module: acquiring individual characteristic data of the passengers; passenger flow streamline construction module: constructing a passenger flow line according to the passenger positioning data, wherein an initial passenger flow node and a final passenger flow node of the passenger flow line are respectively a passenger cabin-out node and a passenger land-side traffic transfer node; passenger flow classifying module: classifying the passenger positioning data according to the arrival time and the position of the passengers to obtain a passenger flow set, wherein the passenger flow set comprises a plurality of passenger flow areas of the passengers at different positions and different arrival times; and a time domain module: extracting the time of different passenger flow domains in the passenger flow set reaching different passenger land-side traffic transfer nodes respectively, and obtaining a plurality of time domains reaching different land-side traffic transfer nodes; an individual passenger transit transfer time module: obtaining the time of the individual passengers arriving at the land-side traffic transfer node according to the individual characteristic data of the passengers; trip chain perception module: matching the time of the individual passengers arriving at the land-side traffic transfer node with the time domains of different traffic modes, and combining the passenger flow lines to obtain an airport passenger flow travel chain containing the individual characteristics of each passenger. The accurate sensing device for the airport passenger travel chain with the individual characteristics solves the problems that a single passenger flow sensing means in the prior art cannot meet the requirements of complete and accurate depiction of space-time trajectories of airport passengers and cannot realize accurate sensing of the individual travel chain. Through multi-source passenger flow data such as 5G mobile phone data and video, the accurate perception of the whole travel chain of each continuous transportation mode from the landing to the arrival of airport land side passenger flow is realized, the depiction of individual space-time tracks of airport land side passengers is completed, and technical support means are provided for land side passenger flow analysis, traffic perception, traffic capacity matching and the like.
The airport passenger flow travel chain accurate sensing device with individual characteristics mainly comprises three functions.
The first is to realize the construction of airport passenger flow lines. The method mainly comprises the steps of acquiring land-side passenger flow lines of an airport through 5G mobile phone data acquisition, wherein the passenger flow lines are travel routes passing through land-side key points.
The second is time domain extraction. And obtaining the time information of the positions of the key points of the passenger passing through the airport by utilizing video image recognition, such as feature recognition, face recognition or 5G mobile phone data matching, at the positions of the key points of the passenger passing through the airport, and taking the time information as the basis for accurately sensing the individual travel chains.
Third is the accurate perception of the individual travel chain. Based on the data information, accurate matching of the travel route of the individual travel on the airport land side is achieved, the spatial position matching and the time information matching are included, the complete travel chain information of the individual is obtained, a thematic base based on different individual characteristics is built, and a thematic base support is provided for follow-up accurate passenger flow prediction.
According to the airport passenger flow travel chain accurate sensing device containing individual characteristics, based on the passenger flow streamline construction technology of 5G mobile phone data and the individual characteristic identification based on video detection, video intelligent identification data and 5G mobile phone signaling data are fused and matched, the defect that a single detection means cannot identify a complete travel chain of passenger flow is overcome, accurate identification of an airport land side passenger flow travel chain is achieved, and accurate sensing of airport land side passenger flow can be achieved based on the accurate identification.
Example 2
The embodiment provides an accurate sensing method for an airport passenger flow travel chain with individual features, and for details which are not disclosed in the accurate sensing method for the airport passenger flow travel chain with individual features in the embodiment, please refer to the specific implementation of the accurate sensing device for the airport passenger flow travel chain with individual features in other embodiments.
A schematic step diagram of an airport passenger flow travel chain accurate sensing method with individual features according to an embodiment of the application is shown in fig. 8.
As shown in fig. 8, the airport passenger flow travel chain accurate sensing method with individual characteristics in the embodiment specifically includes the following steps:
s10: and obtaining passenger positioning data and passenger individual characteristic data.
The passenger positioning data are acquired through the 5G mobile phone positioning data or the intelligent wearable equipment positioning data of the passenger; the individual characteristic data of the passengers are acquired through face recognition camera equipment.
Specifically, the face recognition camera device is arranged at a passenger cabin-out node and a passenger land-side traffic transfer node.
S20: and constructing a passenger flow line according to the passenger positioning data, wherein an initial passenger flow node and a final passenger flow node of the passenger flow line are respectively a passenger cabin-out node and a passenger land-side traffic transfer node.
The method mainly comprises the steps of acquiring land-side passenger flow lines of an airport based on the collection of 5G mobile phone data, wherein the passenger flow lines are travel routes passing through land-side key points.
Specifically, the method for constructing the passenger flow line according to the passenger positioning data specifically comprises the following steps:
first, a traffic node of a traffic flow line is determined.
A schematic diagram of the construction of a passenger flow line according to an embodiment of the application is shown in fig. 2.
As shown in fig. 2, airport passenger flows mainly pass through several time nodes from the air side to the land side, including port withstanding, warehouse-out, corridor bridge, terminal building, baggage extraction and subsequent traffic mode waiting areas. The main space nodes are a corridor bridge, a baggage picking-up area and a waiting area in a continuous traffic mode.
Thus, the passenger flow nodes include airport corridor nodes and baggage retrieval nodes in addition to passenger egress nodes and passenger land-side transit transfer nodes.
And then, carrying out data fitting, data interpolation and data deviation correction on airport passenger flow data to obtain a passenger flow line with high precision.
A schematic diagram of mobile phone data preprocessing according to an embodiment of the present application is shown in fig. 3.
As shown in fig. 3, the 5G mobile phone data is used for constructing the passenger flow line, and the characteristics of high layout density of the 5G base station and high position accuracy of the 5G mobile phone data are mainly used for constructing the passenger flow line. Firstly, fitting 5G mobile phone data, removing data with large offset, interpolating and rectifying the data, and finally forming individual trip chain information with higher precision.
S30: classifying the passenger positioning data according to the arrival time and the position of the passengers to obtain a passenger flow set, wherein the passenger flow set comprises a plurality of passenger flow areas of the passengers at different positions and different arrival times.
S40: and extracting the time for different passenger flow domains in the passenger flow set to reach different passenger land-side traffic transfer nodes respectively, and obtaining a plurality of time domains reaching different land-side traffic transfer nodes.
Before extracting the time domain, a spatial range of time domain extraction needs to be specified. According to the spatial distribution of each successive traffic mode at the airport land side, the time domain extraction mode can be divided into a direct extraction mode and an indirect extraction mode. The direct extraction mode is suitable for the traffic transportation mode waiting areas without overlapping in vertical space, and in this case, the 5G mobile phone data can be directly divided from the precision range of the 5G mobile phone data. The indirect extraction mode is suitable for the condition that the waiting areas of the transportation modes overlap in vertical space.
Specifically, in step S40, the time for different passenger domains in the passenger set to reach different passenger land-side traffic transfer nodes is extracted to obtain a plurality of time domains reaching different land-side traffic transfer nodes, which specifically includes the direct extraction method in step S41 and the indirect extraction method in step S42. The method comprises the following specific steps:
S41: when different land-side traffic transfer nodes are not overlapped in the vertical space of the passenger flow line, the time for different passenger flow domains to reach the different land-side traffic transfer nodes respectively is directly extracted, and a plurality of time domains reaching the different land-side traffic transfer nodes are obtained.
A direct extraction schematic of the time domain according to an embodiment of the application is shown in fig. 4. As shown in fig. 4, the direct extraction mode defines a data acquisition range according to the space structure of each traffic mode waiting area, and the 5G mobile phone data falling into the acquisition range is regarded as the effective data of the traffic mode time domain, and the time that the passenger flows of different passenger flow domains respectively reach the transfer nodes of different traffic modes on the land side is obtained by further processing on the basis of the effective data.
First, referring to step S30, passenger flow groups are classified according to temporal characteristics and spatial positions.
After the airport passenger flows out of the cabin, a group of port-shifting passenger flows are formed, and the time of the same group of port-shifting passenger flows reaching different land-side traffic transfer modes has a comparable reference function, so that the same group of port-shifting passenger flows are classified.
The passenger flow fields are defined as passenger flow groups which have the same departure space-time characteristics, namely, the passenger flow groups which leave the cabin at the same position in the same time period, so that the collection of all the passenger flow fields reached by the airport flight forms a passenger flow collection at the land side of the airport. The passenger flow set is denoted by A and the expression is as follows:
A＝A 1 ∪A 2 ∪...∪A n ；
Wherein for the passenger basin A i ，i∈[1,n]N is a natural number.
Then, a time domain is extracted from the passenger flow domain.
The time when the passenger flow belonging to the same customer flow basin arrives at different land side traffic transfer modes is classified, and the time when the passenger flow arrives at different land side traffic transfer nodes is called as the time domain. Defining T for time domain j The expression j represents land-side traffic transfer mode; defining a passenger basin A i If the number of passengers is w, the transit time of the w th passenger to the traffic mode j is T Awij 。
Then passenger flow area a i Time domain T of arrival at transfer pattern j within a certain fixed time ij Can be expressed as:
T ij ＝[TA 1ij ，TA 2ij ，TA 3ij ....TA wij ]；
a time domain T consisting of passenger flow domains within a certain period of time, such as 24 hours j The expression is as follows:
s42: when different land-side traffic transfer nodes overlap in the vertical space of the passenger flow line, the time for different passenger flow domains to reach the traffic measurable node and the time for different passenger flow domains to reach different land-side traffic transfer nodes from the traffic measurable node are accumulated, and a plurality of time domains reaching different land-side traffic transfer nodes are obtained.
The flow measurable node is a fixed position which is not at the overlapping position on the passenger flow line and is near the overlapping area; and predicting the time for different passenger flow domains to reach different land-side traffic transfer nodes from the traffic measurable nodes according to the distance between the traffic measurable nodes and the different land-side traffic transfer nodes.
Specifically, in the case that there is a spatial overlap in the land-side traffic waiting area, 5G mobile phone data in the range cannot be categorized, so that an end face needs to be found on the traffic flow line, that is, the traffic flow measurable node identifies and collects the 5G mobile phone data, and the traffic flow measurable node is a traffic flow measurable section on the traffic flow line and has uniqueness of a link leading to the traffic waiting area. The indirect extraction mode needs to predict the time of the passenger flow domain reaching different land-side traffic transfer nodes from the traffic measurable nodes according to the distance, speed and other data of the passenger, and finally the complete travel chain time is formed.
An indirect extraction schematic of a time domain according to an embodiment of the application is shown in fig. 5;
as shown in fig. 5, the time TA for different passenger domains to reach the traffic-measurable node wio Reference is made to the direct extraction mode of step S41.
Let us assume basin A i The transit time of the passenger w arriving at the traffic mode j is TA wij Then passenger flow area A i Time domain TA from section O to transfer mode j wij Can be expressed as:
TA wij ＝TA wio +TA woj
the flow measurable section O is a flow measurable node, is fixedly arranged at the position of a trip chain key point near the overlapping area, and is provided with a high-definition video camera;
wherein TA wio The transit time of the passenger w reaching the section O can be directly extracted through 5G mobile phone data.
Wherein TA woj The predicted transit time of the passenger w reaching the transfer mode j from the section O is mainly calculated by predicting the distance, speed and other data of the passenger;
time domain TA woj The calculation formula of (2) is as follows:
s is the passing distance from the section O to the traffic mode j; v is the current moving speed measured according to the 5G mobile phone data.
After a plurality of time domains reaching different land-side traffic transfer nodes are obtained in step S40, steps S50 and S60 are performed.
S50: and obtaining the time of the individual passengers arriving at the land-side traffic transfer node according to the individual characteristic data of the passengers.
Specifically, first, the face recognition cameras need to be arranged in position.
A schematic diagram of camera layout according to an embodiment of the application is shown in fig. 6.
As shown in fig. 6, specifically, a face recognition server is deployed at an airport, and the functions of the airport camera are updated by associating with the established camera, so as to realize intelligent detection. For the situation that cameras are not arranged at key nodes, cameras can be arranged at main nodes of an airport and are associated with a back-end face recognition server. The distribution points of the cameras are required to meet the acquisition of all passenger flows of the section. For areas which cannot be covered by a single camera, a combined camera can be arranged for flow collection.
S60: matching the time of the individual passengers arriving at the land-side traffic transfer node with the time domains of different traffic modes, and combining the passenger flow lines to obtain an airport passenger flow travel chain containing the individual characteristics of each passenger.
In S60, when the multiple time domains of different traffic modes are matched, spatial position matching and time information matching are further performed, and finally complete trip chain information of the individual is obtained.
Optionally, the following steps are further included after S60:
and classifying the airport passenger flow travel chains containing the individual characteristics of each passenger according to the individual characteristics of the passenger to obtain an individual travel chain library. Wherein, the passenger classification comprises classification according to the age of the passenger, the sex of the passenger and the like. Passenger individual characteristics include face information, age, and gender.
Then, matching is performed based on the time domain in step S40, and individual travel chain extraction is obtained.
Specifically, passenger flow nodes mainly distributed in passenger flow comprise a gallery bridge, a baggage extraction area and different traffic mode transfer areas, cameras with face recognition functions are arranged on the important nodes, unified time service is provided for the cameras, and time synchronization of the cameras is achieved. When passenger flows through each key node, the data of the individual can be recorded through the camera.
An individual travel chain extraction schematic is shown in fig. 7 according to an embodiment of the application.
As shown in fig. 7, the individual characteristics of the passengers are identified by face recognition, and the travel time of the passengers from the bridge to the transfer areas of different traffic means, i.e. the time of the individual passengers arriving at the land-side transfer node obtained in S50, is denoted as t ij Will t ij Matching with the time domain of the traffic mode, namely, the passenger arrives at the continuous transportation traffic mode, namely, the traffic mode is selected, and finally, the complete travel chain information of the passenger is obtained.
And finally, constructing an individual travel chain feature library.
And establishing a trip database based on individual characteristics according to the face recognition and the 5G mobile phone data. And respectively establishing characteristic libraries of individual travel chains according to classification modes such as age groups, gender and the like. And providing data support for subsequent travel prediction and information service for the individual.
By adopting the accurate sensing method of the airport passenger flow travel chain with the individual characteristics, firstly, passenger positioning data and passenger individual characteristic data are obtained; then, constructing a passenger flow line according to the passenger positioning data, wherein an initial passenger flow node and a final passenger flow node of the passenger flow line are respectively a passenger cabin-out node and a passenger land-side traffic transfer node; classifying the passenger positioning data according to the arrival time and the position of the passengers to obtain a passenger flow set, wherein the passenger flow set comprises a plurality of passenger flow areas of the passengers at different positions and different arrival times; extracting the time of different passenger flow domains in the passenger flow set reaching different passenger land-side traffic transfer nodes respectively, and obtaining a plurality of time domains reaching different land-side traffic transfer nodes; obtaining the time of the individual passengers arriving at the land-side traffic transfer node according to the individual characteristic data of the passengers; matching the time of the individual passengers arriving at the land-side traffic transfer node with the time domains of different traffic modes, and combining the passenger flow lines to obtain an airport passenger flow travel chain containing the individual characteristics of each passenger. The accurate sensing method for the airport passenger flow travel chain containing the individual characteristics solves the problems that a single passenger flow sensing means in the prior art cannot meet the requirements of complete and accurate depiction of the space-time track of airport passengers and cannot realize accurate sensing of the individual travel chain. Through multi-source passenger flow data such as 5G mobile phone data and video, the accurate perception of the whole travel chain of each continuous transportation mode from the landing to the arrival of airport land side passenger flow is realized, the depiction of individual space-time tracks of airport land side passengers is completed, and technical support means are provided for land side passenger flow analysis, traffic perception, traffic capacity matching and the like.
While preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the application.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the spirit or scope of the application. Thus, it is intended that the present application also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (10)
1. An airport passenger flow travel chain accurate sensing device containing individual characteristics, which is characterized by comprising the following steps:
passenger flow position acquisition module: the method is used for acquiring passenger positioning data;
and the camera module: acquiring individual characteristic data of the passengers;
passenger flow streamline construction module: the passenger flow line is used for constructing a passenger flow line according to the passenger positioning data, and a starting passenger flow node and a stopping passenger flow node of the passenger flow line are respectively a passenger cabin-out node and a passenger land-side traffic transfer node;
passenger flow classifying module: the passenger positioning data are used for classifying the passengers according to the arrival time and the position of the passengers to obtain a passenger flow set, and the passenger flow set comprises a plurality of passenger flow areas of the passengers with different positions and different arrival times;
And a time domain module: extracting time for different passenger flow domains in the passenger flow set to reach different passenger land-side traffic transfer nodes respectively, and obtaining a plurality of time domains reaching different land-side traffic transfer nodes;
an individual passenger transit transfer time module: the method comprises the steps of obtaining the time of an individual passenger arriving at a land-side traffic transfer node according to the individual characteristic data of the passenger;
trip chain perception module: and the airport passenger flow travel chain containing the individual characteristics of each passenger is obtained by matching the time of the individual passenger arriving at the land-side traffic transfer node with a plurality of time domains of different land-side traffic transfer nodes and combining the passenger flow line.
2. The airport passenger flow chain accurate sensing device of claim 1, wherein the passenger flow position acquisition module acquires passenger positioning data through passenger 5G mobile phone positioning data or intelligent wearable device positioning data.
3. The airport passenger flow chain accurate sensing device of claim 1, wherein the camera module obtains passenger individual characteristic data through face recognition camera equipment.
4. An airport passenger flow travel chain accurate sensing device according to claim 3, wherein the face recognition camera device is arranged at a passenger departure node and a passenger land side traffic transfer node.
5. The airport passenger flow chain accurate sensing device of claim 1, wherein the passenger flow line construction module constructs a passenger flow line comprising passenger flow nodes according to the passenger positioning data, and specifically comprises the following steps:
determining a passenger flow node of a passenger flow line, wherein the passenger flow node further comprises an airport corridor bridge node and a baggage extraction node;
and carrying out data fitting, data interpolation and data deviation correction on the passenger positioning data to obtain passenger flow lines.
6. The airport passenger flow travel chain accurate sensing device according to claim 1, wherein the time domain module extracts the time of arrival of different passenger flow domains at different passenger land-side traffic transfer nodes in the passenger flow set to obtain a plurality of time domains arriving at different land-side traffic transfer nodes, and specifically comprises the following steps:
when different land-side traffic transfer nodes are not overlapped in the vertical space of the passenger flow line, directly extracting the time of different passenger flow domains reaching the different land-side traffic transfer nodes to obtain a plurality of time domains reaching the different land-side traffic transfer nodes;
when different land-side traffic transfer nodes overlap on the vertical space of the passenger flow line, accumulating the time for different passenger flow domains to reach the traffic measurable node and the time for different passenger flow domains to reach different land-side traffic transfer nodes from the traffic measurable node to obtain a plurality of time domains reaching different land-side traffic transfer nodes;
The flow measurable node is a fixed position which is not at the overlapping position on the passenger flow line; and predicting the time of the different passenger flow fields from the traffic measurable node to the different land-side traffic transfer nodes according to the distance between the traffic measurable node and the different land-side traffic transfer nodes.
7. The airport passenger flow travel chain accurate sensing device of claim 1, further comprising an individual travel chain library module: and the airport passenger flow travel chains containing the individual characteristics of each passenger are used for classifying the airport passenger flow travel chains according to the individual characteristics of the passengers to obtain an individual travel chain library.
8. The airport passenger flow chain accurate sensing device of claim 1, wherein the passenger individual characteristics comprise face information, age, and gender.
9. The airport passenger flow chain accurate sensing device of claim 1, wherein the camera module is disposed at the passenger flow nodes, and each passenger flow node is provided with one or more face recognition cameras.
10. The airport passenger flow chain accurate sensing device of claim 9, wherein cameras of the plurality of passenger flow nodes are provided with a time unifying time service device so that time of each camera is synchronized.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010659145.8A CN112001232B (en) | 2020-07-09 | 2020-07-09 | Airport passenger flow travel chain accurate sensing device containing individual characteristics |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010659145.8A CN112001232B (en) | 2020-07-09 | 2020-07-09 | Airport passenger flow travel chain accurate sensing device containing individual characteristics |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112001232A CN112001232A (en) | 2020-11-27 |
| CN112001232B true CN112001232B (en) | 2023-10-13 |
Family
ID=73467397
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010659145.8A Active CN112001232B (en) | 2020-07-09 | 2020-07-09 | Airport passenger flow travel chain accurate sensing device containing individual characteristics |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112001232B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117094062B (en) * | 2023-10-16 | 2024-02-27 | 广东省建筑设计研究院有限公司 | High-efficiency traffic design method, configuration and system for land side of terminal building |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN205283824U (en) * | 2015-11-24 | 2016-06-01 | 如东信息技术服务(上海)有限公司 | Airport stream of people early warning system based on wifi |
| CN105913367A (en) * | 2016-04-07 | 2016-08-31 | 北京晶众智慧交通科技股份有限公司 | Public bus passenger flow volume detection system and method based on face identification and position positioning |
| CN205608812U (en) * | 2016-04-07 | 2016-09-28 | 北京晶众智慧交通科技股份有限公司 | Public transport passenger flow measures detecting system based on face identification and position location |
| WO2016159815A1 (en) * | 2015-03-31 | 2016-10-06 | Юрий Сергеевич СОЛДАТОВ | Method for controlling vehicular traffic and device and system for implementing same |
| WO2016194275A1 (en) * | 2015-05-29 | 2016-12-08 | パナソニックＩｐマネジメント株式会社 | Flow line analysis system, camera device, and flow line analysis method |
| CN107657335A (en) * | 2017-09-06 | 2018-02-02 | 武汉科技大学 | A kind of spatial and temporal distributions Forecasting Methodology of airport traffic |
| CN107833157A (en) * | 2017-11-02 | 2018-03-23 | 广东工业大学 | A kind of hotel's bootstrap technique and system based on cloud platform and recognition of face |
| CN108197760A (en) * | 2018-01-31 | 2018-06-22 | 民航成都电子技术有限责任公司 | A kind of airport traffic above-ground passenger traffic volume Forecasting Methodology |
| CN111126689A (en) * | 2019-12-19 | 2020-05-08 | 广州新科佳都科技有限公司 | Subway station passenger flow line management and control method, device, equipment and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110737788B (en) * | 2019-10-16 | 2022-05-31 | 哈尔滨理工大学 | Rapid three-dimensional model index establishing and retrieving method |
-
2020
- 2020-07-09 CN CN202010659145.8A patent/CN112001232B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016159815A1 (en) * | 2015-03-31 | 2016-10-06 | Юрий Сергеевич СОЛДАТОВ | Method for controlling vehicular traffic and device and system for implementing same |
| WO2016194275A1 (en) * | 2015-05-29 | 2016-12-08 | パナソニックＩｐマネジメント株式会社 | Flow line analysis system, camera device, and flow line analysis method |
| CN205283824U (en) * | 2015-11-24 | 2016-06-01 | 如东信息技术服务(上海)有限公司 | Airport stream of people early warning system based on wifi |
| CN105913367A (en) * | 2016-04-07 | 2016-08-31 | 北京晶众智慧交通科技股份有限公司 | Public bus passenger flow volume detection system and method based on face identification and position positioning |
| CN205608812U (en) * | 2016-04-07 | 2016-09-28 | 北京晶众智慧交通科技股份有限公司 | Public transport passenger flow measures detecting system based on face identification and position location |
| CN107657335A (en) * | 2017-09-06 | 2018-02-02 | 武汉科技大学 | A kind of spatial and temporal distributions Forecasting Methodology of airport traffic |
| CN107833157A (en) * | 2017-11-02 | 2018-03-23 | 广东工业大学 | A kind of hotel's bootstrap technique and system based on cloud platform and recognition of face |
| CN108197760A (en) * | 2018-01-31 | 2018-06-22 | 民航成都电子技术有限责任公司 | A kind of airport traffic above-ground passenger traffic volume Forecasting Methodology |
| CN111126689A (en) * | 2019-12-19 | 2020-05-08 | 广州新科佳都科技有限公司 | Subway station passenger flow line management and control method, device, equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 基于视觉感知的机场旅客主动定位系统;许伟村 等;《民航学报》;第2卷(第4期);第78-81页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112001232A (en) | 2020-11-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108388888B (en) | Vehicle identification method and device and storage medium | |
| CN111310994A (en) | Bus route prediction method and system based on data calibration | |
| WO2023273292A1 (en) | Resident trip chain generation method based on multi-source data fusion, and vehicle-sharing query method | |
| CN114390079B (en) | Smart city public place management method and Internet of things system | |
| CN103593974B (en) | A kind of public transport passenger capacity collection method based on locating information | |
| CN108021858A (en) | Mobile object recognition methods and object flow analysis method | |
| CN109285376A (en) | A kind of bus passenger flow statistical analysis system based on deep learning | |
| CN111311467A (en) | Bus route prediction method and system based on face recognition | |
| CN109102114B (en) | Bus trip getting-off station estimation method based on data fusion | |
| JP7272365B2 (en) | MOBILE TRACKING SYSTEM, MOBILE TRACKING METHOD AND PROGRAM | |
| US20200343982A1 (en) | Apparatus for person identification and motion direction estimation | |
| CN111623791A (en) | Method, apparatus, device and medium for navigating in public area | |
| CN115719475B (en) | Three-stage trackside equipment fault automatic detection method based on deep learning | |
| CN112001232B (en) | Airport passenger flow travel chain accurate sensing device containing individual characteristics | |
| CN112668375A (en) | System and method for analyzing tourist distribution in scenic spot | |
| Hoffmann et al. | Using social media images for building function classification | |
| CN110879990A (en) | Method for predicting queuing waiting time of security check passenger in airport and application thereof | |
| CN111988735B (en) | Airport passenger flow travel chain accurate sensing method containing individual characteristics | |
| CN113780173B (en) | Face recognition system and recognition method | |
| JP2014191711A (en) | Video analysis device, video analysis method, program, and video analysis system | |
| Yeh et al. | An intelligent indoor positioning system based on pedestrian directional signage object detection: a case study of Taipei Main Station | |
| Murayama et al. | Deep pedestrian density estimation for smart city monitoring | |
| CN112906507A (en) | Method for measuring and calculating pedestrian track of commercial street based on digital photo | |
| TWI550566B (en) | Travel road identification system and its method | |
| CN117273285B (en) | Passenger transport data acquisition system based on large passenger flow station of rail transit |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |