CN112001232A - Airport passenger flow travel chain accurate sensing device with individual characteristics - Google Patents
Airport passenger flow travel chain accurate sensing device with individual characteristics Download PDFInfo
- Publication number
- CN112001232A CN112001232A CN202010659145.8A CN202010659145A CN112001232A CN 112001232 A CN112001232 A CN 112001232A CN 202010659145 A CN202010659145 A CN 202010659145A CN 112001232 A CN112001232 A CN 112001232A
- Authority
- CN
- China
- Prior art keywords
- passenger
- passenger flow
- time
- flow
- individual
- 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.)
- Granted
Links
- 238000012546 transfer Methods 0.000 claims abstract description 132
- 230000008447 perception Effects 0.000 claims abstract description 47
- 238000000605 extraction Methods 0.000 claims description 50
- 238000010276 construction Methods 0.000 claims description 11
- 230000001360 synchronised effect Effects 0.000 claims description 5
- 238000012937 correction Methods 0.000 claims description 4
- 239000000284 extract Substances 0.000 claims description 2
- 238000000034 method Methods 0.000 description 27
- 238000010586 diagram Methods 0.000 description 17
- 230000006870 function Effects 0.000 description 8
- 238000001514 detection method Methods 0.000 description 7
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 238000005206 flow analysis Methods 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000000052 comparative effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000010006 flight Effects 0.000 description 2
- 230000011664 signaling Effects 0.000 description 2
- 230000002123 temporal effect Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Images
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)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Primary Health Care (AREA)
- Traffic Control Systems (AREA)
Abstract
The application provides accurate perception device of airport passenger flow trip chain who contains individuality characteristics includes: passenger flow position acquisition module and camera module: acquiring passenger positioning data and passenger individual characteristic data; a passenger flow streamline building module: constructing a passenger flow streamline according to passenger positioning data; a passenger flow classification module: classifying the passenger positioning data to obtain a passenger flow set; 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; the individual passenger traffic transfer time module: obtaining the time of the individual passenger reaching the land side traffic transfer node according to the individual characteristic data of the passenger; trip chain perception module: and matching the time of the individual passenger arriving at the land side traffic transfer node with the time domains of different traffic modes to obtain an airport passenger flow trip chain containing the individual characteristics of each passenger. The problem of prior art single passenger flow perception means can not satisfy complete, accurate portrayal requirement of airport passenger's space-time orbit is solved.
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 research of the resident trip chain in the traffic professional field, the complete trip chain of the resident is obtained mainly through the research of the resident trip behavior and the trip mode selection model, and the technical support is provided for the traffic planning and the improvement of the urban traffic efficiency through the analysis of the chains. The extraction of a large-range trip chain in the prior art cannot meet the small-range precision requirement of an airport. The large-range travel chain analysis aiming at urban traffic planning and efficiency improvement is not suitable for identifying the small-range passenger flow travel chain 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 less met. For example, based on travel chain identification and extraction of a bus IC card, a departure, transfer, and arrival station of a traveler can be known through a card swiping record of the traveler, but trajectory data of the traveler moving in the station cannot be acquired through the IC card data.
Regarding the passenger flow perception technical means, the passenger flow perception device is mainly utilized to obtain airport passenger flow section data, such as video data, 5G mobile phone data, mobile application data, Bluetooth data, dynamic two-dimensional code data and the like, and relevant management and service are carried out on airport passenger flow through the obtained passenger flow data. At present, an accurate airport land-side passenger flow perception method is not mature. Most of relevant researches for airport passenger flow perception focus on counting and identifying airport passenger flow by using a single perception means, and relevant researches and methods for accurate perception of airport land-side passenger flow travel chains are lacked.
Aiming at a single passenger flow perception means in the prior art, the passenger flow perception method can only meet the requirements of section passenger flow or passenger flow statistics in a certain range with low precision requirements; the single passenger flow perception means cannot meet the requirements of complete and accurate depiction of airport passengers' space-time trajectories, and cannot realize accurate perception of individual trip chains. Moreover, the passenger flow data sensed by a single means cannot well support the continuous transportation coordination linkage needs of various transportation modes, and the airport continuous function cannot be well played.
Disclosure of Invention
The invention provides an airport passenger flow travel chain accurate sensing device with individual characteristics, and aims to solve the problems that a single passenger flow sensing means in the prior art cannot meet requirements for complete and accurate space-time trajectories of airport passengers and cannot realize accurate sensing of individual travel chains.
According to the embodiment of the application, an airport passenger flow travel chain accurate sensing device with individual characteristics is provided, which specifically comprises:
passenger flow position acquisition module: the system is used for acquiring passenger positioning data;
a camera module: acquiring passenger individual characteristic data;
a passenger flow streamline building module: the system comprises a passenger flow line, a passenger exit node and a passenger land side traffic transfer node, wherein the passenger flow line is constructed according to passenger positioning data, and an initial passenger flow node and a final passenger flow node of the passenger flow line are respectively a passenger exit node and a passenger land side traffic transfer node;
a passenger flow classification module: the passenger positioning data are classified according to the arrival time and the arrival position of the passenger to obtain a passenger flow set, and the passenger flow set comprises a plurality of passenger flow areas of the passenger at different positions and different arrival times;
a time domain module: the system is used for extracting the time when different passenger flow domains in the passenger flow set respectively reach different passenger land side traffic transfer nodes to obtain a plurality of time domains reaching the different land side traffic transfer nodes;
the individual passenger traffic transfer time module: the system is used for obtaining the time of the individual passenger reaching the land side traffic transfer node according to the individual characteristic data of the passenger;
trip chain perception module: the method is used for matching the time of the individual passengers arriving at the land side traffic transfer node with the time domains of different traffic modes, and obtaining the airport passenger flow travel chain containing the individual characteristics of each passenger by combining the passenger flow streamline.
Optionally, the passenger flow position acquisition module acquires the passenger flow position through passenger positioning data through 5G mobile phone positioning data or intelligent wearable device positioning data of the passenger; the image pickup module is used for enabling passengers to acquire individual characteristic data through face recognition image pickup equipment.
Optionally, the face recognition camera device is arranged at a passenger exit node and a passenger land side traffic transfer node.
Optionally, the passenger flow streamline building module builds a passenger flow streamline including the passenger flow node according to the passenger positioning data, and specifically includes the following steps:
determining passenger flow nodes of a passenger flow streamline, wherein the passenger flow nodes further comprise airport corridor bridge nodes and luggage extraction nodes;
and carrying out data fitting, data interpolation and data correction on the passenger positioning data to obtain a passenger flow streamline.
Optionally, the time domain module extracts the time when different passenger flow domains in the passenger flow set respectively reach different passenger land side traffic transfer nodes to obtain a plurality of time domains reaching the different land side traffic transfer nodes, and specifically includes the following steps:
when different land side traffic transfer nodes are not overlapped in the vertical space of the passenger flow streamline, directly extracting the time when different passenger flow domains respectively reach different land side traffic transfer nodes to obtain a plurality of time domains reaching different land side traffic transfer nodes;
when different land side traffic transfer nodes are overlapped on a vertical space of a passenger flow streamline, accumulating the time of different passenger flow domains reaching the flow measurable node and the time of different passenger flow domains reaching different land side traffic transfer nodes from the flow measurable node to obtain a plurality of time domains reaching different land side traffic transfer nodes;
wherein, the flow measurable node is a fixed position on the passenger flow streamline, which is not at the overlapping position; and predicting the time of different passenger flow areas from the flow measurable nodes to different land side traffic transfer nodes according to the distance between the flow measurable nodes and the different land side traffic transfer nodes.
Optionally, the accurate sensing device of airport passenger flow trip chain still includes individual trip chain library module: the system is used for classifying the airport passenger flow trip chain containing each passenger individual characteristic according to the passenger individual characteristic to obtain an individual trip chain library.
Optionally, the passenger individual characteristics include face information, age, and gender.
Optionally, the camera module is disposed at the passenger flow nodes, and each passenger flow node is disposed with one or more face recognition cameras.
Optionally, the cameras of the multiple passenger flow nodes are provided with a time unification timer, so that the time of each camera is synchronized.
Adopt the accurate perception device of airport passenger flow trip chain that contains individual character of this application, include, passenger flow position acquisition module: acquiring passenger positioning data; a camera module: acquiring passenger individual characteristic data; a passenger flow streamline building module: constructing a passenger flow streamline according to passenger positioning data, wherein an initial passenger flow node and a final passenger flow node of the passenger flow streamline are a passenger departure node and a passenger land side traffic transfer node respectively; a passenger flow classification module: classifying the passenger positioning data according to the arrival time and the arrival position of the passenger to obtain a passenger flow set, wherein the passenger flow set comprises a plurality of passenger flow areas of the passenger at different positions and different arrival times; a time domain module: extracting the time when different passenger flow domains in the passenger flow set respectively reach different passenger land side traffic transfer nodes to obtain a plurality of time domains reaching the different land side traffic transfer nodes; the individual passenger traffic transfer time module: obtaining the time of the individual passenger reaching the land side traffic transfer node according to the individual characteristic data of the passenger; trip chain perception module: and matching the time of the individual passenger arriving at the land side traffic transfer node with the time domains of different traffic modes, and combining the passenger flow streamline to obtain an airport passenger flow travel chain containing the individual characteristics of each passenger. The accurate perception device of airport passenger flow trip chain that contains individual character of this application has solved single passenger flow perception means among the prior art and can not satisfy complete, accurate portrayal requirement and can't realize the accurate perception of individual trip chain to airport passenger space-time orbit. By means of multisource passenger flow data such as 5G mobile phone data and videos, accurate sensing of a full travel chain of continuous transportation modes from landing to landing of airport land side passenger flow is achieved, depiction of space-time trajectories of airport land side passenger individuals is completed, and technical support means are provided for land side passenger flow analysis, freight capacity sensing, transport 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 application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
fig. 1 is a schematic structural diagram illustrating an airport passenger flow chain precision perception device with individual features according to an embodiment of the application;
FIG. 2 is a schematic diagram illustrating the construction of a passenger flow streamline according to an embodiment of the present application;
fig. 3 is a schematic diagram illustrating data preprocessing of a mobile phone according to an embodiment of the present application;
a direct extraction schematic of a time domain according to an embodiment of the application is shown in fig. 4;
an indirect extraction schematic diagram of a time domain according to an embodiment of the application is shown in fig. 5;
a schematic diagram of a camera layout according to an embodiment of the present application is shown in fig. 6;
an individual trip chain extraction schematic diagram according to an embodiment of the application is shown in fig. 7;
fig. 8 is a schematic step diagram illustrating an airport passenger flow chain accurate perception method with individual features according to an embodiment of the present application.
Detailed Description
In the process of realizing the method, the inventor finds that the wide-range travel chain analysis which aims at urban traffic planning and efficiency improvement is not suitable for identifying the small-range passenger flow travel chain 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 not met. In order to improve the efficiency of airport land-side transfer, accurate data of arrival of passengers coming out from the air side to each transportation mode needs to be known. At present, a method for extracting a space-time chain of an individual when the airport goes out is lacked in airport passenger flow perception.
The method and the device for accurately sensing the airport passenger flow travel chain with the individual characteristics mainly comprise the construction of an airport space passenger flow streamline and the extraction of the individual travel chain. The airport space passenger flow streamline construction completes the space-time depiction of main passenger flow channels and passenger flow staying key points of an airport through the construction of the airport passenger flow streamline, and establishes a basis for the extraction of subsequent individual continuous travel chains; the extraction of the individual trip chain realizes accurate perception of passenger flow through the extraction of the individual trip chain. The individual trip chain extraction is based on the time domain of the 5G mobile phone data extraction and on the precise matching of the travel time provided by the video detection data.
According to the airport passenger flow travel chain accurate sensing method and device with the individual characteristics, the full travel chain accurate sensing of all continuous transport modes of airport land-side passenger flow from landing to landing on the land side is achieved through multisource passenger flow data such as 5G mobile phone data and videos. The method completes the depiction of the space-time trajectory of the airport land-side passenger individuals and provides a technical support means for the analysis of land-side passenger flow, the perception of transportation capacity, the matching of transportation capacity and the like.
In order to make the technical solutions and advantages of the embodiments of the present application more apparent, the following further detailed description of the exemplary embodiments of the present application with reference to the accompanying drawings makes it clear that the described embodiments are only a part of the embodiments of the present application, and are not exhaustive of all embodiments. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
Example 1
The airport passenger flow travel chain accurate perception method with individual characteristics mainly comprises three parts.
The first is to realize the construction of airport passenger flow streamline. The method mainly comprises the step of acquiring a passenger flow line on the land side of the airport through the acquisition of 5G mobile phone data, wherein the passenger flow line is a travel route passing through a key point on the land side.
The second is time domain extraction. When arriving at the position of a passenger flow passing through a key point on the land side in an airport, the time information of the passenger passing through the key point position is obtained by means of video image recognition, such as feature recognition, face recognition or 5G mobile phone data matching, and the time information is used as the basis for accurate perception of a subsequent individual trip chain.
And thirdly, accurate perception of individual trip chains. Based on the data information, accurate matching of individual trip routes on the land side of the airport is achieved, including spatial position matching and time information matching, complete trip chain information of the individuals is obtained, a special topic library based on different individual characteristics is constructed, and special topic library support is provided for subsequent accurate passenger flow prediction.
The airport passenger flow travel chain accurate perception method with the individual characteristics, based on 5G mobile phone data passenger flow streamline construction technology and video detection-based individual characteristic recognition, fusion and matching are conducted on video intelligent recognition data and 5G mobile phone signaling data, the defect that a complete travel link of passenger flow cannot be recognized by a single detection means is overcome, accurate recognition of airport land side passenger flow travel chains is achieved, and accurate perception of airport land side passenger flow can be achieved on the basis.
The embodiment of the application is implemented as follows:
fig. 1 shows a schematic structural diagram of an airport passenger flow chain precision perception device with individual characteristics according to an embodiment of the application.
As shown in fig. 1, the airport passenger flow travel chain accurate sensing device with individual characteristics includes a passenger flow position obtaining module 10, a camera module 20, a passenger flow streamline constructing module 30, a passenger flow classifying module 40, a time domain module 50, an individual passenger traffic transfer time module 60, and a travel chain sensing module 70. The concrete structure is as follows:
the passenger flow position acquisition module 10: the system is used for acquiring passenger positioning data;
the camera module 20: acquiring passenger individual characteristic data;
the passenger flow streamline building module 30: the system comprises a passenger flow line, a passenger exit node and a passenger land side traffic transfer node, wherein the passenger flow line is constructed according to passenger positioning data, and an initial passenger flow node and a final passenger flow node of the passenger flow line are respectively a passenger exit node and a passenger land side traffic transfer node;
the passenger flow classification module 40: the passenger positioning data are classified according to the arrival time and the arrival position of the passenger to obtain a passenger flow set, and the passenger flow set comprises a plurality of passenger flow areas of the passenger at different positions and different arrival times;
time domain module 50: the system is used for extracting the time when different passenger flow domains in the passenger flow set respectively reach different passenger land side traffic transfer nodes to obtain a plurality of time domains reaching the different land side traffic transfer nodes;
individual passenger traffic transfer time module 60: the system is used for obtaining the time of the individual passenger reaching the land side traffic transfer node according to the individual characteristic data of the passenger;
travel chain perception module 70: the method is used for matching the time of the individual passengers arriving at the land side traffic transfer node with the time domains of different traffic modes, and obtaining the airport passenger flow travel chain containing the individual characteristics of each passenger by combining the passenger flow streamline.
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 passenger positioning data of the 5G mobile phone or the intelligent wearable device.
Specifically, the camera module 20 is a face recognition camera device, and the camera module 20 acquires the passenger individual feature data through the face recognition camera device. The camera module 20 is disposed at the 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 time unified time service devices, so that the time of each camera is synchronized.
Specifically, the passenger flow streamline building module 30 builds the passenger flow streamline according to the passenger positioning data, and specifically includes the following steps:
first, a passenger flow node of a passenger flow streamline is determined.
A schematic diagram of the construction of a passenger flow streamline according to an embodiment of the application is shown in fig. 2.
As shown in fig. 2, airport passenger flow mainly passes through several time nodes from the air side to the land side, including arrival at a port, departure from a warehouse, a gallery bridge, an entry station, baggage pickup, and a continuous traffic pattern waiting area. The main space nodes are the gallery bridge, the luggage extraction area and the waiting area of the continuous traffic mode.
Therefore, the passenger flow nodes comprise an airport corridor bridge node and a baggage extraction node besides the passenger exit node and the passenger land side traffic transfer node.
And then, carrying out data fitting, data interpolation and data correction on airport passenger flow data to obtain a high-precision passenger flow streamline.
Fig. 3 is a schematic diagram illustrating data preprocessing of a mobile phone according to an embodiment of the present application.
As shown in fig. 3, the 5G mobile phone data is used to construct the passenger flow stream line, and the characteristics of high distribution density of the 5G base stations and high position accuracy of the 5G mobile phone data are mainly used to construct the passenger flow stream line. Firstly, fitting 5G mobile phone data, eliminating data with large offset, interpolating and correcting the data, and finally forming individual trip chain information with high precision.
And extracting the time when different passenger flow domains in the passenger flow set respectively reach different passenger land side traffic transfer nodes to obtain a plurality of time domains reaching the different land side traffic transfer nodes.
Before extracting the time domain, the spatial range of the time domain extraction needs to be defined. According to the spatial distribution of each continuous traffic mode on the land side of the airport, 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 situation that waiting areas of various transportation modes are not overlapped in a vertical space, and under the situation, the waiting areas can be directly divided from the precision range of 5G mobile phone data. The indirect extraction mode is suitable for the condition that waiting areas of all traffic transportation modes are overlapped in a vertical space.
Specifically, in the time domain module 50, the time when different passenger flow domains in the passenger flow set respectively reach different passenger land-side traffic transfer nodes is extracted to obtain a plurality of time domains reaching the different land-side traffic transfer nodes, and the time domain module specifically includes the direct extraction manner in step S41 and the indirect extraction manner 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 streamline, the time when different passenger flow domains respectively reach different land side traffic transfer nodes is directly extracted, and a plurality of time domains reaching 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 method defines a data acquisition range according to the spatial structure of each traffic mode waiting area, regards 5G mobile phone data falling into the data acquisition range as valid data of the traffic mode time domain, and further processes the valid data to obtain the time when the passenger flows of different passenger flow domains respectively reach transfer nodes of different traffic modes on the land side.
First, the passenger flow classification module 40 classifies the passenger flow group according to the temporal characteristics and the spatial position.
After the airport passenger flow leaves the cabin, a transfer port passenger flow is formed, and the time when the same transfer port passenger flow arrives at different land side traffic transfer modes has the function of comparative reference, so that the same transfer port passenger flow is classified into one class.
The passenger flow domains are defined as passenger flow groups which have the same arrival time-space characteristics, namely, the passenger flow groups which are out of the cabin at the same position in the same time period, so that the set of all the passenger flow domains where airport flights arrive forms a passenger flow set at the land side of the airport. The set of passenger flows is denoted by A and the expression is as follows:
A＝A1∪A2∪...∪An；
wherein, for the passenger flow area Ai，i∈[1,n]And n is a natural number.
Then, a time domain is extracted from the passenger flow domain.
And classifying the time when the passenger flow belonging to the same passenger flow domain reaches different land side traffic transfer modes, wherein the time is called the time domain reaching different land side traffic transfer nodes. Defining T for time domainjJ represents a land side traffic transfer mode; defining a watershed AiW, the transit time for the w-th passenger to arrive at the traffic mode j is TAwij。
Then the passenger flow area AiReach the time domain T of the transfer mode j within a certain fixed timeijCan be expressed as:
Tij＝[TA1ij，TA2ij，TA3ij....TAwij]；
time zone T consisting of passenger flow zones for a certain period of time, e.g. 24 hoursjIs represented as follows:
s42: when different land side traffic transfer nodes are overlapped on the vertical space of the passenger flow streamline, the time of different passenger flow domains reaching the flow measurable node and the time of different passenger flow domains reaching different land side traffic transfer nodes from the flow measurable node are accumulated to obtain a plurality of time domains reaching different land side traffic transfer nodes.
And the time of different passenger flow domains reaching the flow measurable node is directly extracted through the passenger positioning data or the passenger individual characteristic data.
Wherein, the flow measurable node is a fixed position which is not at the overlapping position on the passenger flow streamline and is near the overlapping area; and predicting the time of different passenger flow areas from the flow measurable nodes to different land side traffic transfer nodes according to the distance between the flow measurable nodes and the different land side traffic transfer nodes.
Specifically, for the condition that the space of the land side traffic mode waiting area is overlapped, 5G mobile phone data in the range cannot be classified, so that an end face needs to be found on a passenger flow line, namely, a flow measurable node identifies and collects the 5G mobile phone data, the flow measurable node is a flow measurable section on the passenger flow line, and the traffic mode waiting area has uniqueness of a link leading to the traffic mode waiting area. The indirect extraction mode needs to predict the time of the passenger flow domain from the flow measurable node to different land side traffic transfer nodes according to data such as passenger distance, speed and the like, and finally complete travel chain time is formed.
An indirect extraction schematic diagram of a time domain according to an embodiment of the application is shown in fig. 5;
as shown in FIG. 5, the time TA of the arrival of different passenger flow domains at the traffic measurable nodewioRefer to the direct extraction mode of step S41.
Suppose a watershed AiThe transit time of the passenger w arriving at the traffic mode j is TAwijThen the passenger flow area AiTime domain TA from cross section O to transfer mode jwijCan be expressed as:
TAwij＝TAwio+TAwoj
the flow measurable section O is a flow measurable node and is fixedly arranged at the position of a trip chain key point near the overlapping area, and a high-definition video camera is arranged;
wherein, TAwioThe transit time of the passenger w reaching the section O can be directly extracted through 5G mobile phone data.
Wherein, TAwojThe predicted transit time of the passenger w from the section O to the transfer mode j is mainly predicted and calculated according to data such as the passing distance and the passing speed of the passenger;
time domain TAwojThe calculation formula of (2) is as follows:
wherein S is the passing distance from the section O to the traffic mode j; and V is the current moving speed measured according to the 5G mobile phone data.
Specifically, in the individual passenger traffic transfer time module 60, the time when the individual passenger arrives at the land-side traffic transfer node is obtained according to the individual characteristic data of the passenger.
Specifically, firstly, the face recognition cameras need to be arranged in positions.
A schematic diagram of a camera layout according to an embodiment of the present application is shown in fig. 6.
As shown in fig. 6, specifically, a face recognition server is deployed in an airport, and functions of the airport camera are upgraded by associating with a built camera, so as to implement intelligent detection. For the condition that the cameras are not arranged on the key nodes, the cameras can be arranged on the main nodes of the airport and are associated with the back-end face recognition server. The arrangement points of the cameras need to meet the requirement of collecting all passenger flow of the cross section. And for the area which can not be covered by a single camera, a combined camera can be arranged for carrying out flow collection.
Travel chain perception module 70: and matching the time of the individual passenger arriving at the land side traffic transfer node with the time domains of different traffic modes, and combining the passenger flow streamline to obtain an airport passenger flow travel chain containing the individual characteristics of each passenger.
In the trip chain sensing module 70, when matching the multiple time domains of different transportation modes, spatial position matching and time information matching are further performed, and finally, complete trip chain information of an individual is obtained.
Optionally, the following steps are further included after the trip chain perceiving module 70:
and classifying the airport passenger flow trip chain containing each passenger individual characteristic according to the passenger individual characteristic to obtain an individual trip chain library. The passenger classification includes classification according to the age, sex, and the like of the passenger. The passenger individual characteristics comprise face information, age and gender.
Then, the time domains obtained in the time domain module 50 are matched to obtain the individual trip chain extraction.
Specifically, passenger flow nodes mainly distributed by passenger flows comprise a gallery bridge, a luggage extraction area and different transportation mode transfer areas, cameras with a face recognition function are arranged in the important nodes, unified time service is provided for the cameras, and time of the cameras is synchronized. When the passenger flow passes through each key node, the data of the individual can be recorded through the camera.
An individual trip chain extraction schematic according to an embodiment of the application is shown in fig. 7.
As shown in fig. 7, the individual characteristics of the passengers are identified through face recognition, and the travel time of the passengers from the gallery bridge to the different transportation mode transfer areas, that is, the time of the individual passengers arriving at the land-side transportation transfer node obtained in the individual passenger transportation transfer time module 60 is recorded as tijWill tijAnd matching with the time domain of the transportation mode, namely, selecting the transportation mode when the passenger arrives at the continuous transportation mode, and finally obtaining the complete travel chain information of the passenger.
And finally, constructing an individual trip 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 a feature library of the individual trip chain according to classification modes such as age group, gender and the like. And data support is provided for the subsequent trip prediction and information service aiming at the individual.
Adopt the accurate perception device of airport passenger flow trip chain that contains individual character of this application, include, passenger flow position acquisition module: acquiring passenger positioning data; a camera module: acquiring passenger individual characteristic data; a passenger flow streamline building module: constructing a passenger flow streamline according to passenger positioning data, wherein an initial passenger flow node and a final passenger flow node of the passenger flow streamline are a passenger departure node and a passenger land side traffic transfer node respectively; a passenger flow classification module: classifying the passenger positioning data according to the arrival time and the arrival position of the passenger to obtain a passenger flow set, wherein the passenger flow set comprises a plurality of passenger flow areas of the passenger at different positions and different arrival times; a time domain module: extracting the time when different passenger flow domains in the passenger flow set respectively reach different passenger land side traffic transfer nodes to obtain a plurality of time domains reaching the different land side traffic transfer nodes; the individual passenger traffic transfer time module: obtaining the time of the individual passenger reaching the land side traffic transfer node according to the individual characteristic data of the passenger; trip chain perception module: and matching the time of the individual passenger arriving at the land side traffic transfer node with the time domains of different traffic modes, and combining the passenger flow streamline to obtain an airport passenger flow travel chain containing the individual characteristics of each passenger. The accurate perception device of airport passenger flow trip chain that contains individual character of this application has solved single passenger flow perception means among the prior art and can not satisfy complete, accurate portrayal requirement and can't realize the accurate perception of individual trip chain to airport passenger space-time orbit. By means of multisource passenger flow data such as 5G mobile phone data and videos, accurate sensing of a full travel chain of continuous transportation modes from landing to landing of airport land side passenger flow is achieved, depiction of space-time trajectories of airport land side passenger individuals is completed, and technical support means are provided for land side passenger flow analysis, freight capacity sensing, transport capacity matching and the like.
The airport passenger flow travel chain accurate sensing device with the individual characteristics mainly comprises three functions.
The first is to realize the construction of airport passenger flow streamline. The method mainly comprises the step of acquiring a passenger flow line on the land side of the airport through the acquisition of 5G mobile phone data, wherein the passenger flow line is a travel route passing through a key point on the land side.
The second is time domain extraction. When arriving at the position of a passenger flow passing through a key point on the land side in an airport, the time information of the passenger passing through the key point position is obtained by means of video image recognition, such as feature recognition, face recognition or 5G mobile phone data matching, and the time information is used as the basis for accurate perception of a subsequent individual trip chain.
And thirdly, accurate perception of individual trip chains. Based on the data information, accurate matching of individual trip routes on the land side of the airport is achieved, including spatial position matching and time information matching, complete trip chain information of the individuals is obtained, a special topic library based on different individual characteristics is constructed, and special topic library support is provided for subsequent accurate passenger flow prediction.
The airport passenger flow travel chain accurate sensing device with the individual characteristics comprises a passenger flow streamline construction technology based on 5G mobile phone data and 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 complete travel link of passenger flow cannot be identified by a single detection means 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 on the basis.
Example 2
For details not disclosed in the method for accurately perceiving airport passenger flow travel chain with individual characteristics of this embodiment, please refer to specific implementation of an airport passenger flow travel chain accurate perceiving device with individual characteristics in other embodiments.
Fig. 8 is a schematic step diagram illustrating an airport passenger flow chain accurate perception method with individual features according to an embodiment of the present application.
As shown in fig. 8, the method for accurately sensing the passenger flow travel chain of the airport with individual characteristics in this embodiment specifically includes the following steps:
s10: and acquiring passenger positioning data and passenger individual characteristic data.
The passenger positioning data is obtained through 5G mobile phone positioning data or intelligent wearable device positioning data of passengers; the passenger individual characteristic data is acquired through face recognition camera equipment.
Specifically, the face recognition camera device is arranged on a passenger cabin exit node and a passenger land side traffic transfer node.
S20: and constructing a passenger flow streamline according to the passenger positioning data, wherein an initial passenger flow node and a final passenger flow node of the passenger flow streamline are a passenger out-of-cabin node and a passenger land-side traffic transfer node respectively.
The method mainly comprises the steps of acquiring a land-side passenger flow line of the airport based on the acquisition of 5G mobile phone data, wherein the passenger flow line is a travel route passing through a land-side key point.
Specifically, the method for constructing the passenger flow streamline according to the passenger positioning data specifically comprises the following steps:
first, a passenger flow node of a passenger flow streamline is determined.
A schematic diagram of the construction of a passenger flow streamline according to an embodiment of the application is shown in fig. 2.
As shown in fig. 2, airport passenger flow mainly passes through several time nodes from the air side to the land side, including arrival at a port, departure from a warehouse, a gallery bridge, an entry station, baggage pickup, and a continuous traffic pattern waiting area. The main space nodes are the gallery bridge, the luggage extraction area and the waiting area of the continuous traffic mode.
Therefore, the passenger flow nodes comprise an airport corridor bridge node and a baggage extraction node besides the passenger exit node and the passenger land side traffic transfer node.
And then, carrying out data fitting, data interpolation and data correction on airport passenger flow data to obtain a high-precision passenger flow streamline.
Fig. 3 is a schematic diagram illustrating data preprocessing of a mobile phone according to an embodiment of the present application.
As shown in fig. 3, the 5G mobile phone data is used to construct the passenger flow stream line, and the characteristics of high distribution density of the 5G base stations and high position accuracy of the 5G mobile phone data are mainly used to construct the passenger flow stream line. Firstly, fitting 5G mobile phone data, eliminating data with large offset, interpolating and correcting the data, and finally forming individual trip chain information with high precision.
S30: and classifying the passenger positioning data according to the arrival time and the arrival position of the passenger to obtain a passenger flow set, wherein the passenger flow set comprises a plurality of passenger flow areas of the passenger at different positions and different arrival times.
S40: and extracting the time when different passenger flow domains in the passenger flow set respectively reach different passenger land side traffic transfer nodes to obtain a plurality of time domains reaching the different land side traffic transfer nodes.
Before extracting the time domain, the spatial range of the time domain extraction needs to be defined. According to the spatial distribution of each continuous traffic mode on the land side of the airport, 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 situation that waiting areas of various transportation modes are not overlapped in a vertical space, and under the situation, the waiting areas can be directly divided from the precision range of 5G mobile phone data. The indirect extraction mode is suitable for the condition that waiting areas of all traffic transportation modes are overlapped in a vertical space.
Specifically, in step S40, the time when different passenger flow domains in the passenger flow set respectively 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 manner in step S41 and the indirect extraction manner 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 streamline, the time when different passenger flow domains respectively reach different land side traffic transfer nodes is directly extracted, and a plurality of time domains reaching 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 method defines a data acquisition range according to the spatial structure of each traffic mode waiting area, regards 5G mobile phone data falling into the data acquisition range as valid data of the traffic mode time domain, and further processes the valid data to obtain the time when the passenger flows of different passenger flow domains respectively reach transfer nodes of different traffic modes on the land side.
First, referring to step S30, the passenger flow group is classified according to the temporal characteristics and the spatial position.
After the airport passenger flow leaves the cabin, a transfer port passenger flow is formed, and the time when the same transfer port passenger flow arrives at different land side traffic transfer modes has the function of comparative reference, so that the same transfer port passenger flow is classified into one class.
The passenger flow domains are defined as passenger flow groups which have the same arrival time-space characteristics, namely, the passenger flow groups which are out of the cabin at the same position in the same time period, so that the set of all the passenger flow domains where airport flights arrive forms a passenger flow set at the land side of the airport. The set of passenger flows is denoted by A and the expression is as follows:
A＝A1∪A2∪...∪An；
wherein, for the passenger flow area Ai，i∈[1,n]And n is a natural number.
Then, a time domain is extracted from the passenger flow domain.
And classifying the time when the passenger flow belonging to the same passenger flow domain reaches different land side traffic transfer modes, wherein the time is called the time domain reaching different land side traffic transfer nodes. Defining T for time domainjJ represents a land side traffic transfer mode; defining a watershed AiW, the transit time for the w-th passenger to arrive at the traffic mode j is TAwij。
Then the passenger flow area AiReach the time domain T of the transfer mode j within a certain fixed timeijCan be expressed as:
Tij＝[TA1ij，TA2ij，TA3ij....TAwij]；
time zone T consisting of passenger flow zones for a certain period of time, e.g. 24 hoursjIs represented as follows:
s42: when different land side traffic transfer nodes are overlapped on the vertical space of the passenger flow streamline, the time of different passenger flow domains reaching the flow measurable node and the time of different passenger flow domains reaching different land side traffic transfer nodes from the flow measurable node are accumulated to obtain a plurality of time domains reaching different land side traffic transfer nodes.
Wherein, the flow measurable node is a fixed position which is not at the overlapping position on the passenger flow streamline and is near the overlapping area; and predicting the time of different passenger flow areas from the flow measurable nodes to different land side traffic transfer nodes according to the distance between the flow measurable nodes and the different land side traffic transfer nodes.
Specifically, for the condition that the space of the land side traffic mode waiting area is overlapped, 5G mobile phone data in the range cannot be classified, so that an end face needs to be found on a passenger flow line, namely, a flow measurable node identifies and collects the 5G mobile phone data, the flow measurable node is a flow measurable section on the passenger flow line, and the traffic mode waiting area has uniqueness of a link leading to the traffic mode waiting area. The indirect extraction mode needs to predict the time of the passenger flow domain from the flow measurable node to different land side traffic transfer nodes according to data such as passenger distance, speed and the like, and finally complete travel chain time is formed.
An indirect extraction schematic diagram of a time domain according to an embodiment of the application is shown in fig. 5;
as shown in FIG. 5, the time TA of the arrival of different passenger flow domains at the traffic measurable nodewioRefer to the direct extraction mode of step S41.
Suppose a watershed AiThe transit time of the passenger w arriving at the traffic mode j is TAwijThen the passenger flow area AiTime domain TA from cross section O to transfer mode jwijCan be expressed as:
TAwij＝TAwio+TAwoj
the flow measurable section O is a flow measurable node and is fixedly arranged at the position of a trip chain key point near the overlapping area, and a high-definition video camera is arranged;
wherein, TAwioThe transit time of the passenger w reaching the section O can be directly extracted through 5G mobile phone data.
Wherein, TAwojThe predicted transit time of the passenger w from the section O to the transfer mode j is mainly predicted and calculated according to data such as the passing distance and the passing speed of the passenger;
time domain TAwojThe calculation formula of (2) is as follows:
wherein S is the passing distance from the section O to the traffic mode j; and V is the current moving speed measured according to the 5G mobile phone data.
After obtaining a plurality of time domains to reach different land-side traffic transfer nodes in step S40, steps S50 and S60 are performed.
S50: and obtaining the time of the individual passenger reaching the land side traffic transfer node according to the individual characteristic data of the passenger.
Specifically, firstly, the face recognition cameras need to be arranged in positions.
A schematic diagram of a camera layout according to an embodiment of the present application is shown in fig. 6.
As shown in fig. 6, specifically, a face recognition server is deployed in an airport, and functions of the airport camera are upgraded by associating with a built camera, so as to implement intelligent detection. For the condition that the cameras are not arranged on the key nodes, the cameras can be arranged on the main nodes of the airport and are associated with the back-end face recognition server. The arrangement points of the cameras need to meet the requirement of collecting all passenger flow of the cross section. And for the area which can not be covered by a single camera, a combined camera can be arranged for carrying out flow collection.
S60: and matching the time of the individual passenger arriving at the land side traffic transfer node with the time domains of different traffic modes, and combining the passenger flow streamline to obtain an airport passenger flow travel chain containing the individual characteristics of each passenger.
In S60, when matching the multiple time domains of different transportation modes, spatial location matching and time information matching are performed, so as to finally obtain complete individual trip chain information.
Optionally, the following step is further included after S60:
and classifying the airport passenger flow trip chain containing each passenger individual characteristic according to the passenger individual characteristic to obtain an individual trip chain library. The passenger classification includes classification according to the age, sex, and the like of the passenger. The passenger individual characteristics comprise face information, age and gender.
Then, matching is performed based on the time domain in step S40, resulting in an individual trip chain extraction.
Specifically, passenger flow nodes mainly distributed by passenger flows comprise a gallery bridge, a luggage extraction area and different transportation mode transfer areas, cameras with a face recognition function are arranged in the important nodes, unified time service is provided for the cameras, and time of the cameras is synchronized. When the passenger flow passes through each key node, the data of the individual can be recorded through the camera.
An individual trip chain extraction schematic according to an embodiment of the application is shown in fig. 7.
As shown in fig. 7, the individual characteristics of the traveler are recognized by face recognition, and the travel time of the traveler from the gallery bridge to the different transportation mode transfer area, that is, the time when the individual traveler arrives at the land-side transportation transfer node obtained in S50 is denoted as tijWill tijAnd matching with the time domain of the transportation mode, namely, selecting the transportation mode when the passenger arrives at the continuous transportation mode, and finally obtaining the complete travel chain information of the passenger.
And finally, constructing an individual trip 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 a feature library of the individual trip chain according to classification modes such as age group, gender and the like. And data support is provided for the subsequent trip prediction and information service aiming at the individual.
By adopting the airport passenger flow travel chain accurate perception method containing the individual characteristics, firstly, passenger positioning data and passenger individual characteristic data are obtained; then, constructing a passenger flow streamline according to the passenger positioning data, wherein an initial passenger flow node and a final passenger flow node of the passenger flow streamline are a passenger out-of-cabin node and a passenger land-side traffic transfer node respectively; classifying the passenger positioning data according to the arrival time and the arrival position of the passenger to obtain a passenger flow set, wherein the passenger flow set comprises a plurality of passenger flow areas of the passenger at different positions and different arrival times; extracting the time when different passenger flow domains in the passenger flow set respectively reach different passenger land side traffic transfer nodes to obtain a plurality of time domains reaching the different land side traffic transfer nodes; obtaining the time of the individual passenger reaching the land side traffic transfer node according to the individual characteristic data of the passenger; and matching the time of the individual passenger arriving at the land side traffic transfer node with the time domains of different traffic modes, and combining the passenger flow streamline to obtain an airport passenger flow travel chain containing the individual characteristics of each passenger. The airport passenger flow travel chain accurate perception method with the individual characteristics solves the problems that in the prior art, a single passenger flow perception means cannot meet requirements for complete and accurate space-time trajectories of airport passengers and cannot realize accurate perception of individual travel chains. By means of multisource passenger flow data such as 5G mobile phone data and videos, accurate sensing of a full travel chain of continuous transportation modes from landing to landing of airport land side passenger flow is achieved, depiction of space-time trajectories of airport land side passenger individuals is completed, and technical support means are provided for land side passenger flow analysis, freight capacity sensing, transport capacity matching and the like.
While the 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. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all alterations and modifications as fall within the scope of the application.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.
Claims (10)
1. The utility model provides an airport passenger flow trip chain accurate perception device that contains individual character which characterized in that specifically includes:
passenger flow position acquisition module: the system is used for acquiring passenger positioning data;
a camera module: acquiring passenger individual characteristic data;
a passenger flow streamline building module: the system comprises a passenger flow line, a passenger exit node and a passenger land side traffic transfer node, wherein the passenger flow line is established according to the passenger positioning data, and an initial passenger flow node and a final passenger flow node of the passenger flow line are respectively a passenger exit node and a passenger land side traffic transfer node;
a passenger flow classification module: the passenger positioning data are classified according to the arrival time and the arrival position of the passenger to obtain a passenger flow set, and the passenger flow set comprises a plurality of passenger flow areas of passengers at different positions and different arrival times;
a time domain module: the time domain acquisition module is used for extracting the time when different passenger flow domains in the passenger flow set respectively reach different passenger land side traffic transfer nodes to obtain a plurality of time domains reaching the different land side traffic transfer nodes;
the individual passenger traffic transfer time module: the system is used for obtaining the time of the individual passenger reaching the land side traffic transfer node according to the individual characteristic data of the passenger;
trip chain perception module: and the time for the individual passengers to arrive at the land side traffic transfer node is matched with the time domains of different traffic modes, and an airport passenger flow travel chain containing the individual characteristics of each passenger is obtained by combining the passenger flow streamline.
2. The airport passenger flow travel chain accurate sensing device of claim 1, wherein the passenger flow position obtaining module obtains passenger positioning data through 5G mobile phone positioning data or intelligent wearable device positioning data of passengers.
3. The airport passenger flow travel chain accurate sensing device of claim 1, wherein the camera module obtains passenger individual feature data through a face recognition camera device.
4. The airport passenger flow travel chain accurate sensing device of claim 3, wherein the face recognition camera device is disposed at a passenger exit node and a passenger land side traffic transfer node.
5. The airport passenger flow travel chain accurate sensing device of claim 1, wherein the passenger flow streamline construction module constructs a passenger flow streamline including passenger flow nodes according to the passenger positioning data, and specifically comprises the following steps:
determining passenger flow nodes of a passenger flow streamline, wherein the passenger flow nodes further comprise airport corridor bridge nodes and luggage extraction nodes;
and performing data fitting, data interpolation and data correction on the passenger positioning data to obtain a passenger flow streamline.
6. The accurate airport passenger flow travel chain sensing device of claim 1, wherein the time domain module extracts 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 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 streamline, the time of different passenger flow domains reaching different land side traffic transfer nodes is directly extracted to obtain a plurality of time domains reaching different land side traffic transfer nodes;
when different land side traffic transfer nodes are overlapped on a vertical space of a passenger flow streamline, accumulating the time of different passenger flow domains reaching the flow measurable node and the time of different passenger flow domains reaching different land side traffic transfer nodes from the flow measurable node to obtain a plurality of time domains reaching different land side traffic transfer nodes;
wherein the flow measurable nodes are fixed positions on the passenger flow streamline, which are not at the overlapping positions; and predicting the time of the different passenger flow areas from the flow measurable nodes to the different land side traffic transfer nodes according to the distance between the flow measurable nodes and the different land side traffic transfer nodes.
7. The accurate airport passenger flow travel chain sensing device of claim 1, further comprising an individual travel chain library module: and the system is used for classifying the airport passenger flow trip chain containing each passenger individual characteristic according to the passenger individual characteristic to obtain an individual trip chain library.
8. The airport passenger flow chain precision perception device of claim 1, wherein the passenger individual characteristics include 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 disposed with one or more face recognition cameras.
10. The accurate airport passenger flow chain sensing device of claim 9, wherein the cameras of the plurality of passenger flow nodes are provided with time unification timers, so that the 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 true CN112001232A (en) | 2020-11-27 |
| CN112001232B 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) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117094062A (en) * | 2023-10-16 | 2023-11-21 | 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 (10)
| 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 |
| CN110737788A (en) * | 2019-10-16 | 2020-01-31 | 哈尔滨理工大学 | Rapid three-dimensional model index establishing and retrieving method |
| 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 |
-
2020
- 2020-07-09 CN CN202010659145.8A patent/CN112001232B/en active Active
Patent Citations (10)
| 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 |
| CN110737788A (en) * | 2019-10-16 | 2020-01-31 | 哈尔滨理工大学 | Rapid three-dimensional model index establishing and retrieving method |
| 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 |
|---|
| 许伟村 等: "基于视觉感知的机场旅客主动定位***", 《民航学报》, vol. 2, no. 4, pages 78 - 81 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117094062A (en) * | 2023-10-16 | 2023-11-21 | 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 |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112001232B (en) | 2023-10-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109285376B (en) | Bus passenger flow statistical analysis system based on deep learning | |
| CN111310994B (en) | Bus route prediction method and system based on data calibration | |
| CN111145545B (en) | Road traffic behavior unmanned aerial vehicle monitoring system and method based on deep learning | |
| KR102652023B1 (en) | Method and apparatus for real time traffic information provision | |
| CN103593974B (en) | A kind of public transport passenger capacity collection method based on locating information | |
| CN109886096B (en) | Wisdom tourism supervision and safe emergency management linkage command system | |
| CN110660222B (en) | Intelligent environment-friendly electronic snapshot system for black-smoke road vehicle | |
| CN104318324B (en) | Shuttle Bus website and route planning method based on taxi GPS records | |
| CN103366154B (en) | Reconfigurable clear path detection system | |
| CN105933650A (en) | Video monitoring system and method | |
| CN111311467A (en) | Bus route prediction method and system based on face recognition | |
| CN110276950A (en) | A kind of urban transportation Trip chain reconstructing method based on bayonet video data | |
| CN109644360A (en) | A method of differentiating that pedestrian flows to using WI-FI probe | |
| CN112601187B (en) | Bus frequent passenger prediction method and system based on mobile phone signaling | |
| CN107145819A (en) | A kind of bus crowding determines method and apparatus | |
| CN111623791A (en) | Method, apparatus, device and medium for navigating in public area | |
| CN112668375A (en) | System and method for analyzing tourist distribution in scenic spot | |
| CN107330840A (en) | Urban Public Transit Passenger Flow Survey method and its investigating system based on platform video analysis | |
| CN110879990A (en) | Method for predicting queuing waiting time of security check passenger in airport and application thereof | |
| CN112001232A (en) | Airport passenger flow travel chain accurate sensing device with individual characteristics | |
| CN111988735B (en) | Airport passenger flow travel chain accurate sensing method containing individual characteristics | |
| CN116310894B (en) | Unmanned aerial vehicle remote sensing-based intelligent recognition method for small-sample and small-target Tibetan antelope | |
| CN111931968B (en) | Method for optimizing public bicycle station layout by using mobile phone GPS data | |
| CN111898434B (en) | Video detection and analysis system | |
| CN114550094A (en) | Method and system for flow statistics and manned judgment of tricycle |
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 |