WO2021159866A1

WO2021159866A1 - Bus route prediction method and system based on facial recognition

Info

Publication number: WO2021159866A1
Application number: PCT/CN2020/139840
Authority: WO
Inventors: 苏松剑; 苏松志; 蔡国榕; 陈延行; 杨子扬; 梁军
Original assignee: 罗普特科技集团股份有限公司
Priority date: 2020-02-11
Filing date: 2020-12-28
Publication date: 2021-08-19
Also published as: CN111311467A

Abstract

Provided are a bus route prediction method and system based on facial recognition. The method comprises: by means of facial recognition, acquiring passengers, who get on a bus and get off the bus, from an acquired video stream, and determining stations at which the passengers get on the bus and stations at which the passengers get off the bus; by means of facial recognition, determining whether the passengers who get on one bus are passengers who got off another bus, and if so, determining transfer stations of the passengers; associating the stations at which the passengers get on the bus, the stations at which the passengers get off the bus, and the transfer stations of the passengers to acquire bus routes of the passengers; and predicting the requirements for bus routes on the basis of the acquired bus routes of all passengers. The method, which performs, on the basis of facial recognition technology, face capture and recognition matching on passengers who get on a bus and get off the bus to predict complete bus routes for public travel, and scientifically and rationally plans urban bus routes by using information of the complete bus routes, so that the operation efficiency of urban buses is higher.

Description

A method and system for bus route prediction based on face recognition

Related application

This application claims the priority of the Chinese patent application with the application number 202010086988.3 filed on February 11, 2020, and the entire content of the application is incorporated herein by reference.

Technical field

The present disclosure relates to the field of intelligent transportation technology, and in particular to a method and system for predicting a bus route based on face recognition.

Background technique

Urban traffic is becoming increasingly congested. Buses are the most important means of public transportation. The planned bus routes are directly related to the operational efficiency of buses, which are reflected in the road congestion and carriage congestion of different bus routes, the travel time of people, and the transfer of people. The number of multiplications and so on.

In order to plan urban public transportation routes scientifically and rationally, it is necessary to grasp the travel rules of citizens, and to make statistics of citizens' travel demands at different time periods to achieve more accurate planning and forecasting.

At present, the main data that can be collected in bus operation are: On-board GPS information: it can be used to track vehicle trajectory, arrival time, driving speed, and route congestion; credit card record: it can be used to estimate the number of people on the bus at each stop.

From the existing data collected, it is possible to predict the number of people getting on each bus at each station on each bus route at each time point, but it is impossible to know the information of people getting off at each station, and it is impossible to estimate the end of the citizen’s trip. Because the citizen’s trip information is not available Complete, so it is impossible to scientifically and rationally plan urban bus routes based on existing data.

It can be seen that in the prior art, since it is impossible to identify the information of the disembarking passengers, and even the transfer information of the passengers, it is difficult to formulate a more accurate bus dispatching plan.

Public content

The present disclosure proposes the following technical solutions in view of the above-mentioned defects in the prior art.

A bus route prediction method based on face recognition, the method includes:

In the vehicle interior prediction step, the passengers getting on and off the vehicle are obtained through face recognition from the obtained video stream, and the boarding station and the getting off station of the passenger are determined;

In the inter-vehicle prediction step, it is determined through face recognition whether a passenger on a bus is a passenger on another bus, and if so, the transfer station of the passenger is determined;

Associating step, associating the boarding station, getting off station, and transfer station of the passenger to obtain the riding route of the passenger;

The prediction step is to predict the demand of the bus route based on the obtained bus routes of all passengers.

Furthermore, the step of predicting the interior of the vehicle is performed by a vehicle-mounted processing terminal, which is used to perform the following operations: real-time analysis of the video stream of the passenger door surveillance camera, face capture, and extraction of the person of the passenger in the vehicle Facial features; real-time analysis of the video stream of the passenger door surveillance camera, facial capture and extraction of the facial features of the passengers who disembarked; recognition and matching of the facial features of the passengers who boarded and alighted, and identified the passenger’s boarding in the current vehicle Bus station and getting off station; and upload the facial feature information of passengers who get on and off the bus to the bus operation server through the network in real time.

Furthermore, the operation of recognizing the boarding site and the getting off site of the passengers in the current vehicle is the facial features of the passengers who got off the vehicle, and the similarity with the facial features of each passenger on the vehicle is calculated, and the similarity is the largest And the face feature pairs larger than the first threshold are used as the recognition matching result to determine the boarding station and the getting off station of the passengers in the current vehicle.

Furthermore, the inter-vehicle prediction step is performed by a bus operation server, and the bus operation server is used to perform the following operations: receiving passengers who board and get off at each stop of each bus Face features, store the facial features in the database; calculate the similarity between the facial features of the passengers on each bus and the facial features of other buses, and take the largest similarity and greater than the second Threshold face feature pairs are used as recognition and matching results to determine the passenger's transfer station;

The bus operation server is also used for associating the passenger's boarding station, getting off station and transfer station to obtain the passenger's boarding route.

Furthermore, in the step of predicting between vehicles, it is defined that the distance between the boarding station and the alighting station is less than a first distance threshold and the facial features of the passengers who boarded the vehicle are performed with the facial features of the passengers who got off the vehicle within the first time threshold. Match recognition.

The present disclosure also proposes a bus route prediction system based on face recognition. The system includes on-board equipment and a background bus operation server. The on-board equipment includes a vehicle-mounted processing terminal, a passenger boarding door monitoring camera, and a passenger boarding door monitoring camera. , The vehicle-mounted processing terminal is connected to the passenger boarding gate monitoring camera and the unloading gate monitoring camera, and the vehicle-mounted processing terminal is connected to the bus operation server through a wireless network;

The in-vehicle processing terminal obtains passengers getting on and off the bus through face recognition from the obtained video stream, and determines the boarding station and the getting off station of the passenger;

The background bus operation server is used to determine whether a passenger getting on a bus is a passenger getting off another bus through face recognition. The bus station, the drop off station, and the transfer station are associated to obtain the passenger's boarding route;

The background bus operation server predicts the demand of the bus route based on the obtained bus routes of all passengers.

Furthermore, the vehicle-mounted processing terminal is used to perform the following operations to determine the passenger's boarding and disembarking locations: real-time analysis of the video stream of the boarding door surveillance camera, capturing the faces of the passengers, and extracting the faces of the boarding passengers Features; real-time analysis of the video stream of the passenger door monitoring camera, facial capture and extraction of the facial features of the passengers who got off the bus; recognition and matching of the facial features of the passengers getting on and off, and identifying the passengers in the current vehicle. Stations and drop-off stations; and upload the facial feature information of passengers who get on and off the bus to the bus operation server via the network in real time.

Furthermore, the bus operation server is configured to perform the following operations to determine the transfer station of the passenger: receive the facial features of the passengers boarding and getting off at each station of each bus, and transfer the The facial features are stored in the database; the facial features of the passengers on each bus are calculated similarly to the facial features of other buses, and the face feature pair with the largest similarity and greater than the second threshold is selected. As a result of identification and matching, to determine the passenger's transfer station;

Furthermore, when the transfer station of the passenger is determined, it is defined that the distance between the boarding station and the getting off station is less than the first distance threshold and the facial features of the passengers boarding and the faces of the passengers getting off the bus within the first time threshold are defined. Features are matched and identified.

The technical effect of the present disclosure is that: a method for predicting a bus route based on face recognition of the present disclosure, the method includes: obtaining passengers getting on and off the bus through face recognition from the obtained video stream, and determining the boarding station of the passengers And get off site; through face recognition, determine whether a passenger on a bus is a passenger on another bus, and if so, determine the passenger’s transfer station; compare the passenger’s boarding station, get off The bus station and the transfer station are associated to obtain the passenger's bus route; based on the obtained bus routes of all passengers, the demand for the bus route is predicted. This method is based on face recognition technology to capture and identify the faces of passengers getting on and off the bus, and predict the complete travel route of citizens. Use the complete travel route information to scientifically and rationally plan urban public transportation routes, so that urban public transportation The operation efficiency is higher.

Description of the drawings

By reading the detailed description of the non-limiting embodiments with reference to the following drawings, other features, purposes, and advantages of the present application will become more apparent.

Fig. 1 is a flowchart of a method for predicting a bus route based on face recognition according to an embodiment of the present disclosure.

Fig. 2 is a structural diagram of a bus route prediction system based on face recognition according to an embodiment of the present disclosure.

Detailed ways

The application will be further described in detail below with reference to the drawings and embodiments. It can be understood that the specific embodiments described here are only used to explain the relevant disclosure, but not to limit the disclosure. In addition, it should be noted that, for ease of description, only the parts related to the relevant disclosure are shown in the drawings.

It should be noted that the embodiments in the application and the features in the embodiments can be combined with each other if there is no conflict. Hereinafter, the present application will be described in detail with reference to the drawings and in conjunction with the embodiments.

Fig. 1 shows a method for predicting a bus route based on face recognition of the present disclosure, and the method includes:

In the vehicle interior prediction step S101, the passengers getting on and off the vehicle are acquired through face recognition from the acquired video stream, and the boarding station and the getting off station of the passengers are determined.

In the inter-vehicle prediction step S102, it is determined by face recognition whether a passenger getting on one bus is a passenger getting off another bus, and if so, the transfer station of the passenger is determined.

Associating step S103, associating the passenger's boarding station, getting off station and transfer station to obtain the passenger's boarding route.

In the prediction step S104, the demand of the bus route is predicted based on the obtained bus routes of all passengers.

The method of the present disclosure is implemented based on a bus route prediction system based on face recognition. The system includes on-board equipment and a background bus operation server. The processing terminal is connected to the surveillance camera through the vehicle-mounted Ethernet network, and the vehicle-mounted processing terminal is connected to the mobile signal base station through wireless signals to access the Internet, so as to realize the information communication between the vehicle-mounted equipment and the bus operation server. The vehicle-mounted processing terminal includes NVIDIA Jetson Nano high-performance embedded computing module, GPS module, Ethernet module, and communication module. The surveillance cameras at the entrance and exit doors transmit the video stream to the on-board processing terminal through Ethernet communication for real-time video analysis and processing. The JetsonNano embedded module can process face capture, face feature extraction, and face recognition comparison of 2 video streams in real time. The vehicle-mounted processing terminal includes a 4G communication module or a 5G communication module. Therefore, the vehicle-mounted processing terminal may be called a vehicle-mounted 4G processing terminal or a vehicle-mounted 5G processing terminal. Of course, the vehicle-mounted processing terminal may also include communication modules such as WIFI and Bluetooth.

In one embodiment, the vehicle interior prediction step S101 is performed by a vehicle-mounted processing terminal, and the vehicle-mounted processing terminal is configured to perform the following operations: real-time analysis of the video stream of the passenger door surveillance camera, capture of the face, and extract the vehicle Passenger's facial features; real-time analysis of the video stream of the door monitoring camera for disembarking passengers, taking face captures and extracting the facial features of the disembarking passengers; identifying and matching the facial features of the passengers boarding and disembarking, and identifying the current vehicle Passengers’ boarding and disembarking sites; and real-time upload of the facial feature information of passengers who boarded and alighted to the bus operation server via the network. The upper and lower passenger door monitoring cameras are used to collect the video of passengers getting on and off the car and send them to the on-board processing terminal through the Ethernet network. The on-board terminal analyzes the video streams of the upper and lower passenger door monitoring cameras in real time, and captures the faces of the passengers and extracts the getting on and off the car. The facial features of the passengers, and then the recognition and matching of the facial features of the passengers boarding and getting off are realized, and the boarding station and the getting off station of the passengers in the current vehicle are recognized, which is to realize the determination of the passenger boarding station and the station’s The position is obtained through the GPS module, of course, it can also be obtained through other positioning modules, such as the Beidou navigation module. The vehicle-mounted terminal uploads the facial feature information of the passengers who get on and off the bus to the bus operation server via the network in real time. The purpose of uploading to the bus operation server is to further determine whether the passenger has made a transfer and determine the transfer Site.

In one embodiment, the operation of recognizing the boarding and disembarking sites of passengers in the current vehicle is for the facial features of the passengers who got off the vehicle, calculating the similarity with the facial features of each passenger who boarded the vehicle, and taking the similarity The face feature pair with the largest degree and greater than the first threshold is used as the recognition matching result to determine the boarding station and the getting off station of the passengers in the current vehicle. That is, when a passenger gets on the bus, the boarding station is obtained through the GPS module, and its facial features are saved. When the passenger gets off the bus, the facial features are compared with the saved facial features of all passengers in the car to find In order to ensure the accuracy of recognition, the facial feature with the greatest similarity needs to be greater than the first threshold (for example, 85%, 90%, etc.) before it is considered as the corresponding alighting passenger. The drop-off site is saved corresponding to the corresponding boarding site and facial features, and the drop-off site is transmitted to the bus operation server together with the corresponding boarding site and facial features. Through the vehicle interior prediction step S101, the exact identification of the passenger boarding station is realized, and a solid foundation is laid for accurately identifying each passenger's riding route, which is an important disclosure point of the present disclosure.

In one embodiment, the inter-vehicle prediction step S102 is performed by a bus operation server, and the bus operation server is configured to perform the following operations: receiving the boarding and getting off information of each bus at each stop The facial features of the passengers are stored in the database; the facial features of the passengers on each bus and the facial features of other buses are calculated for similarity, and the similarity is the largest and Face feature pairs greater than the second threshold are used as recognition matching results to determine the passenger's transfer station. The second threshold may be equal to the first threshold, and the method for calculating the facial feature similarity in step S102 is the same as that in step S101 for predicting between the vehicles. In order to accurately identify the transfer station, in the inter-vehicle prediction step S102, the distance between the boarding station and the getting off station is limited to be less than a first distance threshold (for example, 0-1000m) and the facial features of the passengers boarding and the first time The facial features of passengers who get off the bus within a threshold (for example, 15-30 minutes) are matched and recognized, so that it is determined that the passenger has undergone a transfer is more accurate, which is another important disclosure point of this application.

In one embodiment, the bus operation server is further used to associate the boarding station, getting off station, and transfer station of the passenger to obtain the passenger's boarding route, and then, based on the obtained boarding station of all passengers The route predicts the demand of the bus route. Through the local feature matching in the buses and the global matching of transfers between buses, it is possible to predict every bus stop that citizens will pass through in their complete route. After mastering the regularity of citizens' travel and riding route demand, bus operation can improve bus carrying capacity, shorten citizens' travel time, and reduce road congestion by rationally planning bus routes and departure schedules, thereby realizing intelligent transportation.

FIG. 2 shows a bus route prediction system based on face recognition of the present disclosure. The system includes a vehicle-mounted device 201 and a background bus operation server 202. The vehicle-mounted device 201 includes a vehicle-mounted processing terminal 203 and a passenger gate monitoring system. The camera 204, the disembarkation door monitoring camera 205, the in-vehicle processing terminal 203 is connected to the in-vehicle door monitoring camera 204 and the disembarking door monitoring camera 205 via an Ethernet network, and the in-vehicle processing terminal 203 communicates with the bus operation server 202 via a wireless network Phase connection.

The in-vehicle processing terminal 203 obtains passengers getting on and off the bus through face recognition from the obtained video stream, and determines the boarding station and the getting off station of the passenger. The vehicle-mounted processing terminal 203 includes a NVIDIA Jetson Nano high-performance embedded computing module, a GPS module, an Ethernet module, and a communication module. The surveillance cameras at the entrance and exit doors transmit the video stream to the vehicle-mounted processing terminal 203 through Ethernet communication for real-time video analysis and processing. The Jetson Nano embedded module can process face capture, face feature extraction, and face recognition comparison of 2 video streams in real time. The vehicle-mounted processing terminal 203 includes a 4G communication module or a 5G communication module. Therefore, the vehicle-mounted processing terminal 203 may be referred to as a vehicle-mounted 4G processing terminal or a vehicle-mounted 5G processing terminal. Of course, the vehicle-mounted processing terminal 203 may also include communication modules such as WIFI and Bluetooth.

The background bus operation server 202 is used to determine whether a passenger getting on a bus is a passenger getting off another bus through face recognition. The boarding station, the getting off station, and the transfer station are associated to obtain the passenger's boarding route; the background bus operation server 202 predicts the demand for the bus route based on the obtained boarding routes of all passengers.

In one embodiment, the vehicle-mounted processing terminal 203 is used to perform the following operations to determine the passenger's boarding site and disembarking site: real-time analysis of the video stream of the boarding door surveillance camera 204, taking facial capture and extracting the boarding site Passenger's facial features; real-time analysis of the video stream of the passenger door monitoring camera 205, facial capture and extraction of the facial features of the passengers who disembarked; recognition and matching of the facial features of the passengers who boarded and alighted to identify the current vehicle The getting-in and getting-off stations of passengers in the middle; and uploading the facial feature information of the passengers captured and getting off the bus to the bus operation server 202 via the network in real time. The upper and lower passenger door monitoring cameras 204, 205 are used to collect the video of passengers getting on and off the vehicle, and send them to the vehicle processing terminal 203 through the Ethernet network. The vehicle terminal analyzes the video streams of the upper and lower passenger door monitoring cameras 204, 205 in real time to perform Face capture and extract the facial features of passengers getting on and off the car, and then realize the recognition and matching of the facial features of the passengers getting on and off, and identifying the getting on and off stations of the passengers in the current vehicle, which realizes the identification of passengers The station of getting on and off the vehicle, the position of the station is obtained through the GPS module, of course, it can also be obtained through other positioning modules, such as the Beidou navigation module. The vehicle-mounted terminal uploads the facial feature information of the passengers who get on and off the bus to the bus operation server 202 via the network in real time. The purpose of uploading to the bus operation server 202 is to further determine whether the passenger has transferred and determine whether the transfer is made. Take the site.

In one embodiment, the operation of recognizing the boarding and disembarking sites of passengers in the current vehicle is for the facial features of the passengers who got off the vehicle, calculating the similarity with the facial features of each passenger who boarded the vehicle, and taking the similarity The face feature pair with the largest degree and greater than the first threshold is used as the recognition matching result to determine the boarding station and the getting off station of the passengers in the current vehicle. That is, when a passenger gets on the bus, the boarding station is obtained through the GPS module, and its facial features are saved. When the passenger gets off the bus, the facial features are compared with the saved facial features of all passengers in the car to find In order to ensure the accuracy of recognition, the facial feature with the greatest similarity needs to be greater than the first threshold (for example, 85%, 90%, etc.) before it is considered as the corresponding alighting passenger. The drop-off site is saved corresponding to the corresponding boarding site and facial features, and the drop-off site is transmitted to the bus operation server 202 together with the corresponding boarding site and facial features, and accurate recognition is achieved through the matching of internal features of the vehicle. The stations where passengers get on and off have laid a solid foundation for accurately identifying each passenger's riding route, which is an important disclosure point of this disclosure.

In one embodiment, the bus operation server 202 is configured to perform the following operations to determine the transfer station of the passenger: receive the facial features of passengers boarding and getting off at each station of each bus, Store the facial features in the database; calculate the similarity between the facial features of the passengers on each bus and the facial features of other buses, and take the person with the largest similarity and greater than the second threshold The face feature pair is used as the recognition and matching result to determine the transfer station of the passenger; the second threshold may be equal to the first threshold, and the facial feature similarity calculation method in the bus operation server 202 is the same as that of the person in the on-board processing terminal 203 The facial feature similarity method is the same. In order to accurately identify the transfer station, in the calculation in the bus operation server 202, the distance between the boarding station and the getting off station is limited to be less than the first distance threshold (for example, 0-1000m) and the facial features of the passengers boarding and the first time The facial features of passengers who get off the bus within a threshold (for example, 15-30 minutes) are matched and recognized, so that it is determined that the passenger has undergone a transfer is more accurate, which is another important disclosure point of this application.

The bus operation server 202 is also used to associate the boarding station, getting off station, and transfer station of the passenger to obtain the passenger's bus route, and then predict the bus route based on the obtained bus routes of all passengers. need. Through the local feature matching in the buses and the global matching of transfers between buses, it is possible to predict every bus stop that citizens will pass through in their complete route. After mastering the regularity of citizens' travel and riding route demand, bus operation can improve bus carrying capacity, shorten citizens' travel time, and reduce road congestion by rationally planning bus routes and departure schedules, thereby realizing intelligent transportation.

For the convenience of description, when describing the above device, the functions are divided into various units and described separately. Of course, when implementing this application, the functions of each unit can be implemented in the same or multiple software and/or hardware.

From the description of the foregoing implementation manners, it can be known that those skilled in the art can clearly understand that this application can be implemented by means of software plus a necessary general hardware platform. Based on this understanding, the technical solution of this application essentially or the part that contributes to the existing technology can be embodied in the form of a software product, and the computer software product can be stored in a storage medium, such as ROM/RAM, magnetic disk , CD-ROM, etc., including several instructions to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute the devices described in the various embodiments or some parts of the embodiments of the present application.

Finally, it should be noted that the above embodiments only illustrate rather than limit the technical solutions of the present disclosure. Although the present disclosure has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that the present disclosure can still be modified or modified. Equivalent replacements, any modifications or partial replacements that do not depart from the spirit and scope of the present disclosure, shall be covered by the scope of the claims of the present disclosure.

Claims

A bus route prediction method based on face recognition, characterized in that the method includes:

In the vehicle interior prediction step, the passengers getting on and off the vehicle are obtained through face recognition from the obtained video stream, and the boarding station and the getting off station of the passenger are determined;

In the inter-vehicle prediction step, it is determined through face recognition whether a passenger on a bus is a passenger on another bus, and if so, the transfer station of the passenger is determined;

Associating step, associating the boarding station, getting off station, and transfer station of the passenger to obtain the riding route of the passenger;

The prediction step is to predict the demand of the bus route based on the obtained bus routes of all passengers.
The method according to claim 1, characterized in that the step of predicting the interior of the vehicle is performed by a vehicle-mounted processing terminal, and the vehicle-mounted processing terminal is configured to perform the following operations: real-time analysis of the video stream of the door-to-door surveillance camera, and Face capture and extract the facial features of the passengers on the bus; real-time analysis of the video stream of the passenger door surveillance camera, take facial capture and extract the facial features of the passengers who get off the bus; recognize the facial features of the passengers on and off the bus Matching, identifying the boarding and disembarking sites of passengers in the current vehicle; and uploading the facial feature information of the passengers who boarded and alighted to the bus operation server via the network in real time.
The method according to claim 2, wherein the operation of recognizing the boarding and disembarking sites of the passengers in the current vehicle is the facial features of the passengers getting off the vehicle and calculating the facial features of each passenger who boarded the vehicle. For the similarity of features, take the face feature pair with the largest similarity and greater than the first threshold as the recognition matching result to determine the boarding station and the getting off station of the passengers in the current vehicle.
The method according to claim 1, wherein the step of predicting between vehicles is performed by a bus operation server, and the bus operation server is configured to perform the following operations: receiving information from each bus for each stop The facial features of passengers boarding and getting off the bus are stored in the database; the facial features of passengers boarding on each bus are calculated similarly to the facial features of other buses getting off the bus , Taking the face feature pair with the greatest similarity and greater than the second threshold as the recognition matching result to determine the passenger's transfer station;

The bus operation server is also used for associating the passenger's boarding station, getting off station and transfer station to obtain the passenger's boarding route.
The method according to claim 4, characterized in that, in the step of predicting between vehicles, it is defined that the distance between boarding and disembarking stations is less than a first distance threshold and the facial features of passengers boarding are within the first time threshold. The facial features of passengers getting off the bus are matched and recognized.
A bus route prediction system based on face recognition, characterized in that the system includes on-board equipment and a background bus operation server, and the on-board equipment includes a vehicle-mounted processing terminal, a passenger boarding door monitoring camera, and a passenger boarding door monitoring camera, The in-vehicle processing terminal is connected to the passenger boarding door monitoring camera and the unloading door monitoring camera, and the vehicle-mounted processing terminal is connected to a bus operation server through a wireless network;

The in-vehicle processing terminal obtains passengers getting on and off the bus through face recognition from the obtained video stream, and determines the boarding station and the getting off station of the passenger;

The background bus operation server is used to determine whether a passenger getting on a bus is a passenger getting off another bus through face recognition. The bus station, the drop off station, and the transfer station are associated to obtain the passenger's boarding route;

The background bus operation server predicts the demand of the bus route based on the obtained bus routes of all passengers.
The system according to claim 6, wherein the vehicle-mounted processing terminal is configured to perform the following operations to determine the passenger's boarding and disembarking sites: real-time analysis of the video stream of the boarding door surveillance camera to perform facial analysis. Capture and extract the facial features of the passengers on the bus; analyze the video stream of the surveillance camera of the exit door in real time, capture the faces and extract the facial features of the passengers who get off the bus; identify and match the facial features of the passengers on and off the bus , To identify the boarding and disembarking sites of passengers in the current vehicle; and upload the facial feature information of the passengers who boarded and alighted to the bus operation server via the network in real time.
The system according to claim 7, wherein the operation of recognizing the boarding and disembarking sites of the passengers in the current vehicle is the facial features of the passengers getting off the vehicle and calculating the facial features of each passenger who boarded the vehicle. For the similarity of features, take the face feature pair with the largest similarity and greater than the first threshold as the recognition matching result to determine the boarding station and the getting off station of the passengers in the current vehicle.
The system according to claim 6, wherein the bus operation server is configured to perform the following operations to determine the transfer station of the passenger: receiving the boarding and disembarking information of each bus at each station The facial features of the passengers are stored in the database; the facial features of the passengers on each bus and the facial features of other buses are calculated for similarity, and the similarity is the largest and Face feature pairs greater than the second threshold are used as a recognition matching result to determine the passenger's transfer station;

The bus operation server is also used for associating the passenger's boarding station, getting off station and transfer station to obtain the passenger's boarding route.
The system according to claim 9, wherein when the transfer station of the passenger is determined, the distance between the boarding station and the getting off station is limited to be less than a first distance threshold, and the facial features of the passengers boarding are compared with the first time. The facial features of passengers who got off the bus within the threshold are matched and recognized.