CN112380277A - Train ticket checking auxiliary system based on face recognition - Google Patents
Train ticket checking auxiliary system based on face recognition Download PDFInfo
- Publication number
- CN112380277A CN112380277A CN202011108537.1A CN202011108537A CN112380277A CN 112380277 A CN112380277 A CN 112380277A CN 202011108537 A CN202011108537 A CN 202011108537A CN 112380277 A CN112380277 A CN 112380277A
- Authority
- CN
- China
- Prior art keywords
- passenger
- face
- information
- model
- face recognition
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/248—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
-
- 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
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/24—Reminder alarms, e.g. anti-loss alarms
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/02—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP]
- H04L67/025—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP] for remote control or remote monitoring of applications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/52—Network services specially adapted for the location of the user terminal
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Signal Processing (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Artificial Intelligence (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Emergency Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Devices For Checking Fares Or Tickets At Control Points (AREA)
Abstract
The invention discloses a train ticket checking auxiliary system based on face recognition, wherein the same face recognition system is arranged behind each seat of a train, ticket purchasing information of passengers and face images recognized by a face recognition machine when the passengers enter a station are correspondingly packed and sent to the face recognition system in a railway system server, the face recognition system is used for correspondingly packing and sending the recognized face information of the passengers and passenger riding information sent by the railway system server, when the face information of the passengers who should be ridden on the corresponding seats is not matched with the passenger obtained on the seats, the face recognition system can automatically send out an alarm to remind the passengers to find the positions of the passengers, a worker can know that the riding information of the passengers has problems by checking the alarm information of the face recognition system, and the passengers can check station passing, arrival time and the number of the train on the face recognition system, And the terminal station of the passenger can automatically send out a prompt when the terminal station is about to arrive.
Description
Technical Field
The invention relates to the field of face recognition, in particular to a train ticket checking auxiliary system based on face recognition.
Background
With the rapid development of railways in China, the system construction of railway systems is also continuously perfected, and a comfortable and safe travel environment is provided for passengers. The good riding environment can bring good riding experience to the client, and the client can trust the national railway service industry. With the increasing position of the service industry in market economy, the railway general company is actively improving the service level of the railway general company, and striving for a safe, convenient and comfortable transportation route for people.
In order to prevent passengers from taking up the positions of other people due to the fact that the passengers get on a staggered train or cannot find the corresponding positions of the passengers, the railway head office dispatches related workers to check tickets in a carriage, persuades the passengers in the staggered positions to the seats of the passengers, reminds the passengers who do not buy the tickets to go to ticket buying places on the train to buy the tickets and reminds the passengers who sit at the station to get out of the train. And the passenger is more on the train, and the ticket checking has increased staff's intensity of labour one by one, and can wake up the passenger who falls asleep when checking the ticket, influences passenger's rest, brings not good experience of taking a bus for the passenger.
With the development of the internet, the face recognition technology and the 5G technology, the technologies are applied to a railway system, so that the working intensity of workers can be reduced, and the comfort of passengers can be improved.
Disclosure of Invention
In order to solve the above problems, the present invention provides a train ticket checking auxiliary system based on face recognition, which integrates the internet technology and the 5G technology, and the face recognition system of the present invention is connected with the server of the railway system in a data exchange manner, so that the ticket purchasing information of passengers and the face images recognized by the face recognition machine during entering are correspondingly packaged and sent to the face recognition system, when the passengers sit at the corresponding positions, the face recognition system performs face recognition on the passengers, if the passengers sit at wrong positions, the face recognition system automatically sends out an alarm to remind the passengers to find their own positions, the working personnel can know that there is a problem in the riding information of the passengers by checking the alarm information of the face recognition system, and the working personnel can see a striking alarm information once entering the carriage, the ticket can be checked without checking the ticket purchasing information of the passengers one by the staff, so that the working intensity of the staff is reduced, and the passengers are not easily disturbed.
In order to achieve the purpose, the train ticket checking auxiliary system based on face recognition provided by the invention is realized as follows:
a train ticket checking auxiliary system based on face recognition comprises a face recognition system, wherein the same face recognition system is installed behind each seat of a train and used for recognizing face information of passengers behind the seats, passenger ticket purchasing information and face images recognized by a face recognition machine when the passengers enter a station are correspondingly packaged and sent to the face recognition system in a railway system server, the face recognition system is used for matching the recognized face information of the passengers with passenger riding information sent by the railway system server, when the passengers on the seats are matched with the face information of the passengers who should be riding on the corresponding seats, the face recognition system judges that the current passenger riding information is correct, if the passengers are in wrong positions, the face recognition system can automatically give an alarm to remind the passengers to find own positions, and workers can know that the riding information of the passengers has problems by checking alarm information of the face recognition system, the passenger can also check the station where the train passes, the arrival time, order food, buy tickets and the like on the face recognition system, and the passenger can automatically send out a prompt when the terminal station of the passenger is about to arrive.
The invention relates to a face recognition system, which comprises a metal frame, an indicator light, a high-definition camera, a control circuit board, a storage, a 5G module and a liquid crystal display screen, wherein the indicator light is arranged at the top of the metal frame and is used as a reminding signal light for whether a passenger checks the seat, the control circuit board, the storage and the 5G module are arranged in the metal frame, the 5G module is used for establishing wireless communication between the face recognition system and a railway system server, the liquid crystal display screen is embedded on the surface of the metal frame, the railway system server correspondingly packages ticket purchasing information of the passenger and a face image recognized by a face recognition machine when the passenger enters the station and sends the information to the control circuit board through the 5G module, the control circuit board transmits the information to the storage for storage, after the passenger sits on the position, the high-definition camera collects the face image of the passenger and sends the collected image information to the, and comparing the recognized result with the face image stored in the memory, wherein the recognized result and the face image are the same, the control circuit board judges that the passenger in the seat has entered the seat in a number-checking mode, and the control circuit board controls the liquid crystal display screen to display information such as next station information, current time information, arrival reminding and the like.
The liquid crystal display screen adopts a touch liquid crystal display screen, a next station display window, a station inquiry window, a ticket ordering window, a station arrival reminding window and a meal ordering window are arranged on the interface of the liquid crystal display screen, passengers can inquire the station which is passed by the passenger for times on the liquid crystal display screen, the ticket can be purchased and the meal can be ordered on the liquid crystal display screen, the passenger clicks the station inquiry window, clicks the ticket purchasing window and clicks the meal ordering window, the control circuit board accesses the railway system server through the 5G module, the station inquiry can be clicked to display the station where the passenger passes by the train and the corresponding time, the ticket purchasing is clicked to display the information of the required ticket purchasing, and clicking the required number of the purchased train and paying to finish ticket purchasing, clicking the order to display the meal information sold by the train, clicking the meal required to be purchased and paying, and sending the meal to the hands of the passengers after the staff receives the order.
The ticket inquiry auxiliary flow scheme of the invention is as follows:
1. a face feature recognition model and a database are established at a railway system server side.
(1) Data set acquisition
A large-scale data set WIDER FACE data set proposed by hong Kong Chinese university is used as a test and training set of a model, and the data set comprises 32203 pictures and faces under different conditions such as scale, posture, occlusion, expression, dressing, illumination and the like.
(2) Establishing a face region detection model
The method comprises the steps of establishing a face region detection model by adopting an SSD target detection algorithm based on deep learning, namely establishing an SSD algorithm model under a TensorFlow frame environment, replacing a backbone network of the SSD algorithm model with ResNet of a deep separable convolution network, modifying configuration files and parameters according to the particularity of face detection in the training process, using WIDER FACE data sets and preprocessing the data sets, packaging the data sets into tfrecrd format files for training the SSD algorithm model, testing model files generated after training is finished, and converting the model files into pb model files.
(3) Establishing a face feature recognition model
The method comprises the steps of building a FaceNet algorithm model under a TensorFlow frame environment, using a triple Loss training method, adding a data enhancement method, using a CASIA-faceVS, CASIA-Webface, Celeba and LFW data set, preprocessing the data set to enable the data set to meet the data format requirements of a FaceNet model training set and a testing set, then using the data set for training and testing the FaceNet algorithm model, performing a comparison test on the data set in model training, finishing the training to obtain 4 different training models, testing on the LFW data set, selecting an optimal model as a face feature recognition model of a system, and converting the optimal model into a pb model file.
(4) Establishing a face key point positioning model
The method comprises the steps of positioning key points of a human face by adopting a SENET algorithm based on deep learning, embedding the SENET algorithm into a ResNet network module to form a complete human face key point positioning model SENET-ResNet, building the SENET-ResNet under a TensorFlow frame environment, preprocessing a 300W-LP data set, packaging the data set into a tfrecrd format file, realizing training for positioning 68 human face key points of the SENET-ResNet algorithm model by programming, testing a model file generated after training and converting the model file into a pb model file.
2. The image collected by the railway system face recognizer is transmitted to a railway system server, when a passenger enters a station, an identity card and face recognition are brushed on the railway system face recognizer, namely riding information is registered on the railway server, and the riding information and the face image of the passenger exist on the railway server.
3. The passenger ticket buying information and the face image identified by the face identification machine when the passenger enters the station are correspondingly packed and sent to the face identification system to be stored in the railway system server, after the face identification system identifies the face image of the passenger, the face image identified by the face identification machine in the face identification system is compared with the stored face image, if the passenger is in a wrong position, the face identification system can automatically give an alarm to remind the passenger to find the position of the passenger, and the working personnel can know that the riding information of the passenger has problems by checking the alarm information of the face identification system.
4. Human-computer interaction
The passenger clicks a station inquiry window, clicks a ticket purchasing window and clicks a meal ordering window, the control circuit board accesses the railway system server through the 5G module, the station inquiry is clicked to display the station through which the train taken by the passenger passes and the corresponding time of the station, the ticket purchasing information is clicked to display the required ticket purchasing information, the required number of purchased trains is clicked and paid to finish ticket purchasing, the meal ordering is clicked to display meal information sold by the train, the meal required to be purchased is clicked and paid, and the worker sends the meal to the passenger after receiving the order.
The face recognition system can automatically update passenger information, namely, the face recognition system automatically clears the stored passenger riding information after a passenger finishes a car trip.
Because the invention adopts the face recognition system structure which integrates the internet technology, the 5G technology and the face recognition technology, the following beneficial effects can be obtained:
1. when the passenger sits and corresponds the position on, face identification system carries out face identification to this passenger, if the passenger sits when wrong position, face identification system can send the warning automatically, in order to remind the passenger to find own position, the staff can know passenger's riding information problem through looking over face identification system's alarm information, staff's an entering carriage can see striking alarm information, the ticket information of buying that need not the staff to investigate the passenger one by one can check the ticket, staff's working strength has been reduced, the passenger is also difficult to be disturbed.
2. The passenger can look over the name of next station through face identification system, can purchase the ticket on face identification system, order meal, inquire the website that the train that takes advantage of passes through, send the website in advance and remind when the train arrives the passenger website of getting off soon, let the passenger experience the convenience that railway science and technology brought.
Drawings
FIG. 1 is an installation structure intention of a train ticket checking auxiliary system based on face recognition;
FIG. 2 is a diagram showing a relationship between a face recognition system and a railway system server of the train ticket checking auxiliary system based on face recognition;
FIG. 3 is a schematic structural diagram of a face recognition system of the train ticket checking auxiliary system based on face recognition;
FIG. 4 is a liquid crystal display interface design diagram of a train ticket checking auxiliary system based on face recognition according to the present invention;
FIG. 5 is a schematic diagram of an auxiliary ticket inquiry process of the train ticket checking auxiliary system based on face recognition;
fig. 6 is a flowchart of the operation of the train ticket checking auxiliary system based on face recognition.
The main elements are indicated by symbols.
| Face recognition system | 1 | |
2 |
| |
3 | High- |
4 |
| |
5 | |
6 |
| |
7 | Liquid |
8 |
| Railway system server | 9 |
Detailed Description
The present invention will be described in further detail with reference to the following examples and drawings.
Referring to fig. 1 to fig. 6, a train ticket checking auxiliary system based on face recognition is shown, which includes a face recognition system 1.
As shown in figure 1, the same face recognition system 1 is installed behind each seat of the train, which is used for recognizing the face information of the passenger behind the seat, so as to determine whether the passenger sits on the corresponding seat, the passenger ticket purchasing information and the face image recognized by the face recognition machine when the passenger enters the station are correspondingly packaged and sent to the face recognition system 1 in the railway system server 9, the face recognition system 1 and the passenger riding information sent by the railway system server 9 are used for matching the recognized face information of the passenger on the seat with the face information of the passenger who should be seated on the corresponding seat, the face recognition system 1 judges that the current passenger riding information is correct, if the passenger sits at a wrong position, the face recognition system 1 can automatically give an alarm to remind the passenger to find the position of the passenger, and the worker can know that the riding information of the passenger has problems by looking up the alarm information of the face recognition system 1, the staff can see striking alarm information as soon as entering the carriage, need not the staff and arrange the ticket buying information of passenger one by one and can check the ticket, reduced staff's working strength, the passenger is also difficult to be disturbed, the passenger can also look over the operation such as bus number through website, arrival time, order a meal, purchase ticket on face identification system 1, can send the warning voluntarily when passenger's terminal station is about to arrive, prevent that the passenger from missing should arrive.
As shown in fig. 2, the face recognition system 1 and the railway system server 9 are accessed through a 5G network, that is, the face recognition system 1 is wirelessly connected to a vehicle server through the 5G module 7, and the vehicle server is connected to a platform server and the railway system server 9, so as to access the railway system server 9, thereby effectively improving the access speed.
As shown in fig. 3, the face recognition system 1 includes a metal frame 2, an indicator lamp 3, a high-definition camera 4, a control circuit board 5, a storage 6, a 5G module 7, and a liquid crystal display 8, wherein the indicator lamp 3 is installed on the top of the metal frame 2 and serves as a warning signal lamp for the passengers to check whether to sit in the seat, when the face information of the passengers in the seat is identified to be matched with the face information of the passengers to be seated in the corresponding seat, the indicator lamp 3 displays a green light to indicate that the passengers are seated correctly, and when the face information of the passengers in the seat is identified to be not matched with the face information of the passengers to be seated in the corresponding seat, the indicator lamp 3 displays a red light to remind the passengers to find their seats, the high-definition camera 4 is embedded on the upper end surface of the metal frame 2 and is used for collecting face images of the passengers, and the indicator lamp 3, the high-definition, The liquid crystal display screens 8 are electrically connected with the control circuit board 5, the storage 6 and the 5G module 7 are installed in the metal frame 2, the 5G module 7 is used for establishing wireless communication between the face recognition system 1 and the railway system server 9, the liquid crystal display screens 8 are embedded on the surface of the metal frame 2, passenger ticket purchasing information and face images recognized by a face recognition machine when a passenger enters a station are correspondingly packed in the railway system server 9 and are sent to the control circuit board 5 through the 5G module 7, the control circuit board 5 sends the information to the storage 6 for storage, after the passenger sits on the station, the high-definition camera 4 collects the face images of the passenger and sends the collected image information to the control circuit board 5 for face recognition processing, and the recognized result is compared with the face images stored in the storage, the control circuit board 5 judges that the passenger on the seat has entered the seat in a checking-in manner, the control circuit board 5 judges that the passenger on the seat has not entered the seat in a checking-in manner, the control circuit board 5 controls the indicator lamp 3 to light the red light to indicate that the passenger has a wrong seat number, and the control circuit board 5 controls the liquid crystal display screen 8 to display information such as next station information, current time information, arrival reminding and the like.
As shown in fig. 4, the liquid crystal display 8 adopts a touch liquid crystal display, which can realize human-computer interaction, a next station display window, a station inquiry window, a ticket ordering window, a station arrival reminding window and a meal ordering window are arranged on the interface of the liquid crystal display 8, passengers can inquire the station passed by the train number on the liquid crystal display 8, can purchase tickets and order meals on the liquid crystal display 8, the passengers click the station inquiry window, click the ticket purchasing window and click the meal ordering window, the control circuit board 5 accesses the railway system server 9 through the 5G module 7, the station inquiry can display the station passed by the train number and the corresponding time of the passenger, click the ticket purchasing information, click the required purchased number and pay to complete ticket purchasing, the passengers can buy the next train ticket when taking the train, and do not need to buy the ticket at the ticket selling place, the train ticket booking system has the advantages that ticket booking time is saved for passengers, meal information sold by the train is clicked and displayed, meals to be bought are clicked and paid, and the workers receive the orders and then send the meals to the hands of the passengers, so that organic integration of the internet technology, the face recognition technology and the 5G technology is achieved, the train is more intelligent, and comfort of the passengers is improved.
As shown in fig. 5, the ticket query auxiliary flow scheme is as follows:
1. and establishing a human face feature recognition model at the railway system server 9.
(1) Data set acquisition
The method comprises the following steps: a large-scale data set WIDER FACE data set proposed by hong Kong Chinese university is used as a test and training set of a model, and the data set comprises 32203 pictures and faces under different conditions such as scale, posture, occlusion, expression, dressing, illumination and the like.
(2) Establishing a face region detection model
The method comprises the steps of establishing a face region detection model by adopting an SSD target detection algorithm based on deep learning, namely establishing an SSD algorithm model under a TensorFlow frame environment, replacing a backbone network of the SSD algorithm model with ResNet of a deep separable convolution network, modifying configuration files and parameters according to the particularity of face detection in the training process, using WIDER FACE data sets and preprocessing the data sets, packaging the data sets into tfrecrd format files for training the SSD algorithm model, testing model files generated after training is finished, and converting the model files into pb model files.
(3) Establishing a face feature recognition model
The FaceNet has the main idea that the face images are mapped to a multi-dimensional space, then the similarity of the faces is represented through the spatial distance, the spatial distance between the face images of the same person is smaller, and the spatial distance between the face images of different persons is larger, so that different face images of the same person and face images of different persons can be distinguished through the spatial mapping of the face images, and face recognition is realized. The method comprises the steps of utilizing a large-scale data set WIDER FACE data set proposed by hong Kong Chinese university as a test and training set of a model, building a FaceNet algorithm model under a TensorFlow frame environment, utilizing a triple Loss training method, adding a data enhancement method, utilizing and preprocessing a CASIA-faceVS, CASIA-Webface, Celeba and LFW data set to enable the data set to meet the data format requirements of the FaceNet model training set and the test set, then utilizing the data enhancement method in the FaceNet algorithm model training and testing, conducting a comparison test on the data set during model training, finishing the training to obtain 4 different training models, and selecting an optimal model as a face feature recognition model of a system through testing on the LFW data set to convert the optimal model into a pb model file.
(4) Establishing a face key point positioning model
The method comprises the steps of positioning key points of a human face by adopting a SENET algorithm based on deep learning, embedding the SENET algorithm into a ResNet network module to form a complete human face key point positioning model SENET-ResNet, building the SENET-ResNet under a TensorFlow frame environment, preprocessing a 300W-LP data set, packaging the data set into a tfrecrd format file, realizing training for positioning 68 human face key points of the SENET-ResNet algorithm model by programming, testing a model file generated after training and converting the model file into a pb model file.
2. Database establishment
The image collected by the railway system face recognizer is transmitted to a railway system server 9, a passenger information table is created in a MySQL database on the railway system server 9, when a passenger enters a station, an identity card is swiped on the railway system face recognizer, the face recognition is equivalent to the riding information is registered on the railway system server, and the riding information and the face image of the passenger exist on the railway system server.
3. In railway system server 9 with passenger ticket buying information and the face image that face identification machine discerned when arriving at a station correspond, get up to pack and send to face identification system 1 in and save, face identification system 1 discerns passenger face image after, carry out face identification in face identification system 1 after with the face image who saves and compare, if the passenger sits wrong position, face identification system 1 can send out the warning automatically, in order to remind the passenger to find own position, the staff can know passenger's riding information problem through looking over face identification system 1's alarm information.
4. Human-computer interaction
The passenger clicks the station inquiry window, clicks the ticket purchasing window and clicks the meal ordering window, the control circuit board 5 accesses the railway system server 9 through the 5G module 7, the station inquiry can be clicked to display the station where the train taken by the passenger passes and the corresponding time of the station, the ticket purchasing information is clicked to display the required ticket purchasing information, the required purchased train number is clicked and the required purchased train number is paid to complete the ticket purchasing, the passenger can conveniently buy the ticket of the next train when taking the train, the ticket purchasing time is saved for the passenger without going to a ticket selling place, the meal selling information of the train is clicked to display, the meal needing to be purchased is clicked and paid, and the worker sends the meal to the passenger after receiving the order, so that the organic integration of the internet technology, the face recognition technology and the 5G technology is realized, the train is more intelligent, and the comfort of the passenger is improved.
The face recognition system 1 can automatically update passenger information, namely after a passenger finishes a journey, the face recognition system 1 automatically clears the stored passenger riding information.
The working principle and the working process of the invention are as follows:
as shown in fig. 6, the passenger ticket purchasing information and the face image recognized by the face recognition machine during the arrival are correspondingly packaged in the railway system server 9 and sent to the control circuit board 5 through the 5G module 7, the control circuit board 5 sends the information to the storage 6 for storage, after the passenger sits on the seat, the high-definition camera 4 collects the face image of the passenger, and sends the collected image information to the control circuit board 5 for face recognition processing, the recognized result is compared with the face image stored in the storage, the two are the same, the control circuit board 5 judges that the passenger in the seat has entered the seat by checking the number, the two are different, the control circuit board 5 judges that the passenger in the seat has not entered the seat by checking the number, the control circuit board 5 controls the indicator lamp 3 to light red to indicate that the passenger has a wrong seat, the passenger can inquire the station passed by the bus on the liquid crystal display 8, the system can purchase tickets and order food on the liquid crystal display screen 8, passengers click a station inquiry window, click a ticket purchasing window and click a food ordering window, the control circuit board 5 accesses the railway system server 9 through the 5G module 7, the station inquiry can display stations through which the trains taken by the passengers pass and the corresponding time of the stations, the information of the required tickets is clicked and displayed, the required purchased train number is clicked and the ticket is paid, the passengers can conveniently buy the tickets of the next train when taking the train without going to a ticket selling place, the time for buying the tickets is saved for the passengers, the food information sold by the train is clicked and displayed by the click food ordering, the foods required to be purchased are clicked and paid, and the passengers can send the foods to the passengers after receiving the orders.
Claims (3)
1. The utility model provides a train ticket checking auxiliary system based on face identification which characterized in that: the train passenger taking system comprises a face recognition system, wherein the same face recognition system is installed behind each seat of a train and used for recognizing face information of a passenger behind the seat, passenger ticket purchasing information and face images recognized by a face recognition machine when the passenger enters a station are correspondingly packed and sent to the face recognition system in a railway system server, the face recognition system is used for recognizing the face information of the passenger and passenger taking information sent by the railway system server, when the passenger on the seat is matched with the face information of the passenger to be taken on the corresponding seat, the face recognition system judges that the current passenger taking information is correct, if the passenger is in a wrong position, the face recognition system can automatically give an alarm to remind the passenger to find the position, a worker can know that the passenger taking information of the passenger has problems by checking alarm information of the face recognition system, and the passenger can also check the position where the train passes the station on the face recognition system, The terminal station of the passenger can automatically send out a prompt when the terminal station of the passenger is about to arrive.
2. The train ticket checking auxiliary system based on the face recognition as claimed in claim 1, wherein: the face recognition system comprises a metal frame, an indicator light, a high-definition camera, a control circuit board, a storage device, a 5G module and a liquid crystal display screen, wherein the liquid crystal display screen adopts a touch liquid crystal display screen, a next station display window, a station inquiry window, a ticket ordering window, a station arrival reminding window and a meal ordering window are arranged on the interface of the liquid crystal display screen, a passenger can inquire stations passed by the train on the liquid crystal display screen for buying tickets and ordering, the passenger clicks the station inquiry window, clicks the ticket buying window and clicks the meal ordering window, the control circuit board accesses a railway system server through the 5G module, clicks the station inquiry to display the stations passed by the train and the corresponding time of the stations passed by the passenger, clicks the ticket buying information to display the required ticket buying information, clicks the required number of purchased trains and pays to finish ticket buying, clicks the meal ordering to display meal information sold by the train, the meal required to be purchased is clicked and paid, and the worker sends the meal to the hands of the passengers after receiving the order.
3. The train ticket checking auxiliary system based on the face recognition as claimed in claim 1, wherein: the ticket inquiry auxiliary flow scheme is as follows:
1. establishing a human face feature recognition model at a railway system server side:
(1) data set acquisition
Adopting a large-scale data set-WIDER FACE data set proposed by hong Kong Chinese university as a test and training set of a model, wherein the data set comprises 32203 pictures and faces under different conditions such as scale, posture, occlusion, expression, dressing, illumination and the like;
(2) establishing a face region detection model
Establishing a face region detection model by adopting an SSD (solid State disk) target detection algorithm based on deep learning, namely establishing an SSD algorithm model under a TensorFlow frame environment, replacing a backbone network of the SSD algorithm model with ResNet of a deep separable convolution network, modifying configuration files and parameters according to the particularity of face detection in the training process, using WIDER FACE data sets and preprocessing the data sets, packaging the data sets into tfrecrd format files for training the SSD algorithm model, testing model files generated after the training is finished and converting the model files into pb model files;
(3) establishing a face feature recognition model
Building a FaceNet algorithm model in a TensorFlow frame environment, using a triple Loss training method, adding a data enhancement method, using a CASIA-faceVS, CASIA-Webface, Celeba and LFW data set, preprocessing the data set to meet the data format requirements of a FaceNet model training set and a testing set, then using the data set for training and testing the FaceNet algorithm model, performing a comparison test on the data set in model training, finishing the training to obtain 4 different training models, testing on the LFW data set, selecting an optimal model as a face feature recognition model of a system, and converting the optimal model into a pb model file;
(4) establishing a face key point positioning model
Positioning key points of a human face by adopting a SENET algorithm based on deep learning, embedding the SENET algorithm into a ResNet network module to form a complete human face key point positioning model SENET-ResNet, building the SENET-ResNet under a TensorFlow frame environment, preprocessing a 300W-LP data set, packaging the data set into a tfrecrd format file, realizing training for positioning the key points of 68 human faces of the SENET-ResNet algorithm model by programming, testing a model file generated after training and converting the model file into a pb model file;
2. database with a plurality of databases
The image collected by the railway system face recognizer is transmitted to a railway system server 9, a passenger information table is created in a MySQL database on the railway system server 9, when a passenger enters a station, an identity card is brushed on the railway system face recognizer, the face recognition is equivalent to the riding information is registered on the railway system server, and the riding information and the face image of the passenger exist on the railway system server;
3. the passenger ticket purchasing information and the face image identified by the face identification machine when the passenger enters the station are correspondingly packed and sent to the face identification system for storage in the railway system server, after the face identification system identifies the face image of the passenger, the face identification system carries out face identification and then compares the face image with the stored face image, if the passenger is in a wrong position, the face identification system automatically gives an alarm to remind the passenger to find the position of the passenger, and a worker can know that the passenger has a problem in riding information by checking the alarm information of the face identification system;
4. human-computer interaction
The passenger clicks a station inquiry window, clicks a ticket purchasing window and clicks a meal ordering window, the control circuit board accesses the railway system server through the 5G module, the station inquiry is clicked to display the station through which the train taken by the passenger passes and the corresponding time of the station, the ticket purchasing information is clicked to display the required ticket purchasing information, the required number of purchased trains is clicked and paid to finish ticket purchasing, the meal ordering is clicked to display meal information sold by the train, the meal required to be purchased is clicked and paid, and the worker sends the meal to the passenger after receiving the order.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011108537.1A CN112380277A (en) | 2020-10-16 | 2020-10-16 | Train ticket checking auxiliary system based on face recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011108537.1A CN112380277A (en) | 2020-10-16 | 2020-10-16 | Train ticket checking auxiliary system based on face recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112380277A true CN112380277A (en) | 2021-02-19 |
Family
ID=74579943
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011108537.1A Pending CN112380277A (en) | 2020-10-16 | 2020-10-16 | Train ticket checking auxiliary system based on face recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112380277A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113158923A (en) * | 2021-04-27 | 2021-07-23 | 华录智达科技股份有限公司 | Bus transfer reminding system based on face recognition |
| CN115862068A (en) * | 2022-12-06 | 2023-03-28 | 北京崇迅科技有限公司 | Computer data information processing method and system based on big data |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170018007A1 (en) * | 2015-07-15 | 2017-01-19 | Edmond Defrank | Integrated mobile device management system |
| CN107415972A (en) * | 2017-07-24 | 2017-12-01 | 徐晨炫 | A kind of train arrival reminds seat |
| CN109625024A (en) * | 2017-10-09 | 2019-04-16 | 陈成 | A kind of train car information service system |
| CN109685919A (en) * | 2019-02-18 | 2019-04-26 | 烟台市安特洛普网络科技有限公司 | Intelligent service terminal in compartment |
| CN110667655A (en) * | 2019-10-31 | 2020-01-10 | 江西理工大学 | Permanent magnetic levitation track traffic control system and method based on 5G communication technology |
| CN110879997A (en) * | 2019-12-11 | 2020-03-13 | 袁慧凤 | Seat AI face recognition system and recognition method |
| CN111126158A (en) * | 2019-11-27 | 2020-05-08 | 中铁程科技有限责任公司 | Automatic ticket checking method, device and system based on face recognition |
| CN210691491U (en) * | 2019-09-12 | 2020-06-05 | 益逻触控系统公司 | Auxiliary system for self-service terminal and self-service terminal |
| CN211541234U (en) * | 2019-12-17 | 2020-09-22 | 中铁建设集团有限公司 | Intelligent robot for serving railway passenger station construction and operation and maintenance full flow |
-
2020
- 2020-10-16 CN CN202011108537.1A patent/CN112380277A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170018007A1 (en) * | 2015-07-15 | 2017-01-19 | Edmond Defrank | Integrated mobile device management system |
| CN107415972A (en) * | 2017-07-24 | 2017-12-01 | 徐晨炫 | A kind of train arrival reminds seat |
| CN109625024A (en) * | 2017-10-09 | 2019-04-16 | 陈成 | A kind of train car information service system |
| CN109685919A (en) * | 2019-02-18 | 2019-04-26 | 烟台市安特洛普网络科技有限公司 | Intelligent service terminal in compartment |
| CN210691491U (en) * | 2019-09-12 | 2020-06-05 | 益逻触控系统公司 | Auxiliary system for self-service terminal and self-service terminal |
| CN110667655A (en) * | 2019-10-31 | 2020-01-10 | 江西理工大学 | Permanent magnetic levitation track traffic control system and method based on 5G communication technology |
| CN111126158A (en) * | 2019-11-27 | 2020-05-08 | 中铁程科技有限责任公司 | Automatic ticket checking method, device and system based on face recognition |
| CN110879997A (en) * | 2019-12-11 | 2020-03-13 | 袁慧凤 | Seat AI face recognition system and recognition method |
| CN211541234U (en) * | 2019-12-17 | 2020-09-22 | 中铁建设集团有限公司 | Intelligent robot for serving railway passenger station construction and operation and maintenance full flow |
Non-Patent Citations (1)
| Title |
|---|
| 文昌卫: "基于深度学习的人脸识别系统的设计和实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113158923A (en) * | 2021-04-27 | 2021-07-23 | 华录智达科技股份有限公司 | Bus transfer reminding system based on face recognition |
| CN113158923B (en) * | 2021-04-27 | 2022-09-06 | 华录智达科技股份有限公司 | Bus transfer reminding system based on face recognition |
| CN115862068A (en) * | 2022-12-06 | 2023-03-28 | 北京崇迅科技有限公司 | Computer data information processing method and system based on big data |
| CN115862068B (en) * | 2022-12-06 | 2023-10-13 | 中软国际科技服务有限公司 | Big data-based computer data information processing method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102098516B1 (en) | Passenger management device and passenger management method | |
| CN112380277A (en) | Train ticket checking auxiliary system based on face recognition | |
| CN109636397A (en) | Transit trip control method, device, computer equipment and storage medium | |
| CN103177297A (en) | Method for carrying out electronic identity recognition by utilizing two-dimensional code | |
| CN108717798A (en) | A kind of intelligent public transportation system based on Internet of Things pattern | |
| CN110208739A (en) | Assist method, apparatus, equipment and the computer readable storage medium of vehicle location | |
| CN106296935A (en) | Quick Response Code subway ticket automatic ticket checker | |
| CN113627438B (en) | Method and system for automatically reimbursing travel expenses based on bill recognition and configuration engine | |
| CN109903555B (en) | Bus passenger getting-off data prediction method and system based on big data | |
| CN111653092A (en) | Bus route is wisdom public transit management monitored control system in coordination | |
| CN110874908A (en) | Verification system | |
| CN109360278A (en) | Taxi pricing method, system and server | |
| CN112258723A (en) | System and method for forecasting queuing length in comprehensive passenger transport hub | |
| CN109471389A (en) | Railway transportation monitoring system based on big data | |
| KR20110038272A (en) | System and method for detecting free ride | |
| JP3502156B2 (en) | Traffic monitoring system | |
| CN109615036B (en) | Fine particle exposure risk assessment method based on bus IC card swiping system | |
| CN205983830U (en) | Intelligence is mutual system for public transit information processing | |
| CN109978744A (en) | Trip information processing method and processing device | |
| CN114118470A (en) | Intelligent management and control method and system for production and operation of full-automatic driving vehicle base | |
| CN108053297A (en) | A kind of public cloud is in the occupation mode of automobile industry | |
| JP2004110508A (en) | Train seat status/congestion status grasping system, method and program, and seat wireless device | |
| CN104092709B (en) | Vehicle-mounted recourse method, vehicle-mounted recourse device, mutual aid method and mutual auxiliary system | |
| CN109117904A (en) | One kind is stolen a ride detection method and terminal | |
| CN116416101A (en) | Cloud station system and interaction method thereof |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210219 |
|
| RJ01 | Rejection of invention patent application after publication |