Far-station boarding re-checking system and related method

Abstract

The invention discloses a remote airport boarding re-checking system and a related method, and relates to the technical field of software, the remote airport boarding re-checking system comprises a server side and acquisition equipment deployed in a ferry vehicle, and the acquisition equipment and the server side establish remote network connection by using a near earth orbit satellite. The acquisition device performs face scanning and segmentation on a target passenger in the ferry vehicle to obtain a face image of the target passenger; and sending the face image to the server based on the remote network connection. The server extracts a first face feature in the face image; and second face features of all passengers in the security-checked flight are called, whether the target passenger belongs to the security-checked flight is determined by comparing the first face features with the second face features, and a comparison result is output. According to the invention, all passengers in the ferry vehicle can be subjected to remote boarding re-check in batches, queuing waiting is avoided, and the re-check and boarding efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of software technology, and in particular to a remote boarding check-in system and related methods. Background Art

[0002] With the development of information technology, airports' demand for intelligent and information-based passenger services is also growing. Remote boarding review is an important node in the airport boarding process.

[0003] Currently, during the remote boarding review, passengers take a shuttle bus from the terminal to the remote boarding stand for boarding. Ground staff will check the passenger's boarding pass and identity again at the aircraft to ensure that the information on the passenger's boarding pass matches the flight, avoiding incorrect boarding or safety hazards.

[0004] This method of issuing boarding passes and manual verification requires passengers to show their boarding passes at the gate, and passengers are also prone to losing their boarding passes when riding the shuttle bus, which affects travel experience and boarding efficiency. Summary of the invention

[0005] In view of the above problems, the present application provides a remote boarding check-in system and related methods to achieve the purpose of efficient remote boarding check-in. The specific scheme is as follows:

[0006] In a first aspect, the present application provides a remote boarding check-in system, the remote boarding check-in system comprising: a server, and a collection device deployed in a shuttle bus, the collection device and the server establishing a remote network connection using a low-Earth orbit satellite;

[0007] The acquisition device is used to scan and segment the face of the target passenger in the shuttle bus to obtain the face image of the target passenger; and send the face image to the server based on the remote network connection;

[0008] The server is used to extract the first facial feature in the facial image; retrieve the second facial features of all passengers on the checked flight, determine whether the target passenger belongs to the checked flight by comparing the first facial feature with the second facial feature, and output the comparison result.

[0009] In a possible implementation, the acquisition device includes a plurality of cameras, the sum of the top-view angles of the plurality of cameras is greater than the range of the carriage of the shuttle bus, a local area network connection is established between the plurality of cameras in a grid manner, and each camera can communicate with the server based on the remote network connection;

[0010] The multiple cameras determine a master camera and a slave camera based on the local area network connection, the master camera is the camera communicating with the server this time, and the slave camera is other cameras among the multiple cameras except the master camera;

[0011] The slave camera is used to scan and segment the face of the first target passenger within its bird's-eye view to obtain a first face image of the first target passenger; and send the first face image to the master camera;

[0012] The main camera is used to scan and segment the face of the second target passenger within its overhead viewing angle to obtain a second face image of the second target passenger; splice the first face image and the second face image, and send the splicing result to the server based on the remote network connection.

[0013] In a possible implementation, the multiple cameras are cameras integrated with infrared light sources respectively.

[0014] In a possible implementation, the server for extracting the first facial feature in the facial image is specifically configured to:

[0015] The facial image is preprocessed by compression filtering, grayscale conversion and color space conversion in sequence; a facial feature extraction network is retrieved, wherein the facial feature extraction network is obtained by training a convolutional neural network; and the preprocessing result of the facial image is input into the facial feature extraction network to obtain the first facial feature output by the facial feature extraction network.

[0016] In a possible implementation, the server for retrieving the second facial features of all passengers on the checked flight and determining whether the target passenger belongs to the checked flight by comparing the first facial features with the second facial features is specifically used for:

[0017] Retrieve multi-level cache data of the security inspection system, wherein the multi-level cache data contains the first sub-facial features of all passengers of the inspected flight in multiple first time intervals; traverse the multiple first time intervals in order from late to early; for the currently traversed target time interval, extract the first sub-facial feature of the target time interval from the multi-level cache data, and determine whether the target passenger belongs to the passenger of the inspected flight in the target time interval by comparing the first facial feature with the extracted first sub-facial feature; if so, record the inspected flight and the target time interval; if not, return to execute Perform the step of traversing the multiple first time intervals in order from late to early until all the multiple first time intervals are traversed, then retrieve the database of the security inspection system, the database recording the second sub-facial features of all passengers on the inspected flight in the second time interval, the second time interval being earlier than the multiple first time intervals; determine whether the target passenger is a passenger on the inspected flight in the second time interval by comparing the first facial feature with the second sub-facial feature in the database; if so, record the inspected flight and the second time interval; if not, generate an error message.

[0018] In a possible implementation, the remote boarding check-in system further includes: a client;

[0019] The server is further configured to send the comparison result to the client;

[0020] The client is used to display the comparison result.

[0021] A second aspect of the present application provides a remote boarding verification method, which is applied to a server in a remote boarding verification system, wherein the remote boarding verification system further includes a collection device deployed in a shuttle bus, wherein the collection device and the server establish a remote network connection using a low-Earth orbit satellite, and the remote boarding verification method includes:

[0022] Receiving a facial image sent by the acquisition device based on the remote network connection, wherein the facial image is obtained by the acquisition device through facial scanning and segmentation of a target passenger in the shuttle bus;

[0023] Extracting a first facial feature from the facial image;

[0024] The second facial features of all passengers on the checked flight are retrieved, and whether the target passenger belongs to the checked flight is determined by comparing the first facial features with the second facial features, and the comparison result is output.

[0025] In a possible implementation, the extracting the first facial feature from the facial image includes:

[0026] Performing compression filtering, grayscale conversion and color space conversion preprocessing on the face image in sequence;

[0027] Retrieving a facial feature extraction network, wherein the facial feature extraction network is obtained by training a convolutional neural network;

[0028] The preprocessing result of the face image is input into the face feature extraction network to obtain the first face feature output by the face feature extraction network.

[0029] In a possible implementation, retrieving the second facial features of all passengers on the checked flight and determining whether the target passenger belongs to the checked flight by comparing the first facial features with the second facial features includes:

[0030] Retrieving multi-level cache data of the security inspection system, wherein the multi-level cache data includes first sub-facial features of all passengers of the inspected flight in multiple first time intervals;

[0031] Traversing the plurality of first time intervals in order from latest to earliest;

[0032] For the currently traversed target time interval, extract the first sub-facial feature in the target time interval from the multi-level cache data, and determine whether the target passenger is a passenger of the checked flight in the target time interval by comparing the first facial feature with the extracted first sub-facial feature;

[0033] If yes, record the checked flight and the target time interval;

[0034] If not, returning to the step of traversing the multiple first time intervals in order from late to early, until all the multiple first time intervals are traversed, calling the database of the security inspection system, wherein the database records the second sub-face features of all passengers of the inspected flight in the second time interval, and the second time interval is earlier than the multiple first time intervals;

[0035] Determining whether the target passenger is a passenger on the checked flight in the second time interval by comparing the first facial feature with the second sub-facial feature in the database;

[0036] If yes, record the checked flight and the second time interval;

[0037] If it does not belong, an error message is generated.

[0038] In a possible implementation, the remote boarding check-in system further includes a client, and the remote boarding check-in method further includes:

[0039] The comparison result is sent to the client so that the client displays the comparison result.

[0040] By means of the above technical scheme, the present application provides a remote boarding verification system and related methods, wherein the remote boarding verification system includes a server and a collection device deployed in a shuttle bus, wherein the collection device and the server establish a remote network connection using a low-Earth orbit satellite. The collection device performs facial scanning and segmentation on the target passenger in the shuttle bus to obtain a facial image of the target passenger; and sends the facial image to the server based on a remote network connection. The server extracts the first facial feature in the facial image; retrieves the second facial feature of all passengers on the checked flight, determines whether the target passenger belongs to the checked flight by comparing the first facial feature with the second facial feature, and outputs the comparison result. The present application can automatically collect the facial image of the passenger when he / she enters the shuttle bus by deploying the collection device, and the server performs feature extraction and comparative analysis to quickly determine whether the passenger belongs to the checked flight, so that the remote boarding verification can be completed in batches for all passengers in the shuttle bus, avoiding queuing and improving the efficiency of verification and boarding. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0042] Figure 1 A schematic diagram of the architecture of a remote boarding check-in system provided in an embodiment of the present application;

[0043] Figure 2 A schematic diagram of the structure of a server provided in an embodiment of the present application;

[0044] Figure 3 A schematic diagram of the deployment of a camera in a shuttle bus provided in an embodiment of the present application;

[0045] Figure 4 A flowchart of a remote boarding check-in method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0046] The following describes the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. The terms used in the implementation method section of the present application are only used to explain the specific embodiments of the present application, and are not intended to limit the present application.

[0047] The embodiments of the present application are described below in conjunction with the accompanying drawings. Those skilled in the art will appreciate that, with the development of technology and the emergence of new scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0048] The terms "first", "second" etc. in the specification of the application and the above-mentioned drawings are used to distinguish similar objects, and need not be used to describe a specific order or sequential order. It should be understood that the terms used in this way can be interchangeable in appropriate circumstances, and this is only to describe the distinction mode adopted by the objects of the same attributes when describing in the embodiments of the application. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, so that the process, method, system, product or equipment comprising a series of units need not be limited to those units, but may include other units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0049] See also Figure 1 , Figure 1 This is a schematic diagram of the architecture of a remote boarding check-in system provided in an embodiment of the present application. Figure 1 As shown, the remote boarding verification system includes a server 10 and a collection device 20 deployed in a shuttle bus, and the collection device 20 and the server 10 establish a remote network connection using a low-earth orbit satellite. The server 10 may include one or more servers, and the server 10 may provide the remote boarding verification method provided by the embodiment of the present application for one or more shuttle buses.

[0050] See also Figure 2 , Figure 2 A schematic diagram of the structure of a server provided in an embodiment of the present application. Figure 2 As shown, the server 10 includes a bus 101, a processor 102, a communication interface 103 and a memory 104. The processor 102, the memory 104 and the communication interface 103 communicate with each other via the bus 101.

[0051] The bus 101 is a PCI-Express (peripheral component interconnect express) bus or the like. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 2 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0052] The processor 102 may be any one or more of a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0053] The memory 104 may include a volatile memory, such as a random access memory (RAM). The memory 104 may also include a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard drive (HDD), or a solid state drive (SSD).

[0054] The memory 104 may be used to store software codes related to the remote boarding verification method, and the processor 102 may execute the steps of the remote boarding verification method of the chip, and may also schedule other units to implement corresponding functions.

[0055] It should be understood that the above-mentioned server 10 can be a centralized or distributed device, and the above-mentioned processor 102 can be a hardware circuit (such as an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a general-purpose processor, a digital signal processor (DSP), a microprocessor or a microcontroller, etc.), or a combination of these hardware circuits. For example, the processor can be a hardware system with an instruction execution function, such as a CPU, DSP, etc., or a hardware system without an instruction execution function, such as an ASIC, FPGA, etc., or a combination of the above-mentioned hardware systems without an instruction execution function and hardware systems with an instruction execution function.

[0056] like Figure 1 As shown, a remote boarding check system provided by an embodiment of the present application may include a server 10 and a collection device 20 deployed in a shuttle bus. The collection device 20 and the server 10 use a low-Earth orbit satellite to establish a remote network connection. The low-Earth orbit satellite can provide high bandwidth, low latency, is not interfered by ground mobile phone base station signals, and can maintain the advantages of high-speed network transmission when driving at high speeds.

[0057] The acquisition device 20 is used to scan and segment the face of the target passenger in the shuttle bus to obtain the face image of the target passenger; and send the face image to the server 10 based on the remote network connection.

[0058] The server 10 is used to extract the first facial feature in the facial image; retrieve the second facial features of all passengers on the checked flight, determine whether the target passenger belongs to the checked flight by comparing the first facial feature with the second facial feature, and output the comparison result.

[0059] Specifically, in the embodiment of the present application, the acquisition device 20 is pre-deployed in the shuttle bus, and its shooting range can cover the range of the shuttle bus compartment, so as to shoot the objects in the shuttle bus, and perform face scanning and segmentation on the photographed passengers (i.e., target passengers) to obtain the face image of the target passenger. Among them, the target passenger can be one or more passengers, and accordingly, the face image obtained after face scanning and segmentation contains the face areas of all passengers. Further, the acquisition device 20 sends the face image to the server 10 via a remote network connection.

[0060] After obtaining the facial image, the server 10 can obtain the facial features (i.e., the first facial features) in the facial image through feature extraction. At the same time, in combination with the flight data and the departing passenger data, the facial features (i.e., the second facial features) of all passengers on a certain checked flight within a specified time can be retrieved. By comparing the first facial features with the second facial features, it can be determined whether the target passenger belongs to the checked flight, thereby determining whether the target passenger has a problem of incorrect registration.

[0061] In practical applications, the acquisition device 20 can be composed of multiple cameras. In the embodiment of the present application, multiple cameras can be installed at a high position on the shuttle bus to form a bird's-eye view to facilitate face scanning of objects in the shuttle bus. The sum of the bird's-eye view ranges of the multiple cameras is greater than the range of the shuttle bus's compartment. A local area network connection is established between the multiple cameras in a grid manner, and each camera can communicate with the server 10 based on a remote network connection. Preferably, the acquisition device 20 can be composed of six cameras, and the bird's-eye view ranges of the various cameras intersect with each other, ultimately covering the range of the shuttle bus's compartment.

[0062] See also Figure 3 , Figure 3 A schematic diagram of the deployment of a camera in a shuttle bus provided in an embodiment of the present application. Figure 3As shown, the six cameras constituting the acquisition device 20 are respectively deployed at the four top corners of the roof and the middle positions on both sides of the vehicle body, so as to form a LAN communication structure in the form of a grid. In this grid structure, any camera can be directly connected to the other five cameras through the LAN, and data can be shared through the grid, and a task can be completed together through the grid to improve efficiency. Thus, the cameras in the acquisition device 20 are networked in the shuttle bus using a grid method, and the cameras communicate with each other through the grid to share the collected facial images, which can increase the throughput while reducing the probability of repeated face scanning. In addition, in order to ensure that the camera can successfully complete the face scan in a dark environment, each camera can be integrated with an infrared light source.

[0063] Multiple cameras are connected based on a local area network to determine the master camera and the slave camera. The master camera is the camera communicating with the server this time, and the slave camera is the other cameras among the multiple cameras except the master camera.

[0064] The slave camera is used to scan and segment the face of the first target passenger within its bird's-eye view to obtain a first face image of the first target passenger; and send the first face image to the main camera;

[0065] The main camera is used to scan and segment the face of the second target passenger within its overhead viewing angle to obtain a second face image of the second target passenger; stitch the first face image and the second face image, and send the stitching result to the server 10 based on the remote network connection.

[0066] Specifically, in the embodiment of the present application, for ease of understanding, the acquisition device 20 is composed of six cameras as an example. Based on the grid structure, the six cameras can select the main camera that communicates with the server 10 this time based on the local area network connection by a polling algorithm or a selection algorithm, and the other five cameras are slave cameras.

[0067] For any slave camera, at least one target passenger (i.e., the first target passenger) within its overlooking viewing angle can be scanned and segmented. Specifically, by photographing objects within the shuttle bus within its overlooking viewing angle, and determining and segmenting at least one face region based on a face recognition algorithm, a face image (i.e., the first face image) containing at least one face region is obtained, and the first face image is sent to the master camera. In this way, the master camera can obtain the first face images sent by each of the other five cameras.

[0068] For the main camera, the face of at least one target passenger (i.e., the second target passenger) within its overhead viewing angle can also be scanned and segmented. Specifically, by photographing objects within the shuttle bus within its overhead viewing angle, and determining and segmenting at least one face region based on a face recognition algorithm, a face image (i.e., the second face image) containing at least one face region is obtained. Further, the main camera splices the obtained first face image and the second face image, and sends the splicing result to the server 10.

[0069] In addition, to avoid too many passengers in the shuttle bus, which would lead to a decrease in the accuracy of the camera's face scanning, identification areas can be set in the seat area and standing area of ​​the shuttle bus through calibration. Each identification area can only be assigned to one passenger, so a pressure sensor can be set in each identification area. The pressure sensor in each identification area sends the detected pressure signal to the main camera, and the main camera determines the number of passengers in the shuttle bus based on the pressure signal, and determines whether the number of passengers exceeds the scanning capacity of all cameras. This can maximize the efficiency of remote aircraft stand registration review and prevent review errors caused by too many passengers in the shuttle bus.

[0070] In a possible implementation, in order to ensure the efficiency of facial feature extraction by the server 10, the embodiment of the present application provides a remote boarding check-in system, wherein the server 10 for extracting the first facial feature in the facial image is specifically used to:

[0071] The facial image is preprocessed by compression filtering, grayscale conversion and color space conversion in sequence; the facial feature extraction network is retrieved, and the facial feature extraction network is obtained by training the convolutional neural network; the preprocessing result of the facial image is input into the facial feature extraction network to obtain the first facial feature output by the facial feature extraction network.

[0072] Specifically, in the embodiment of the present application, after obtaining the facial image, the server 10 may first pre-process the facial image, including compression filtering, grayscale conversion, and color space conversion. Among them, compressing and filtering the face image can remove other information that affects face processing, such as depth of field information and background information; graying the compressed and filtered results of the face image can convert the original RGB color data into grayscale data, which can remove the interference of color information and highlight the contour and details of the image, thereby improving the accuracy of recognition. Moreover, the computational complexity of the grayscale image is much smaller than that of the color image, which makes the grayscale processing significantly improve the operation efficiency of the algorithm in large-scale face detection tasks. In addition, the brightness change in the grayscale image can reflect the detailed features of the face contour, texture, etc., which are crucial for face detection. Through grayscale processing, these features can be more effectively extracted and the robustness of recognition can be enhanced; the grayscale result of the face image is converted into a color space, which can be converted from the RGB color space to the HSV color space, which can reduce the influence of lighting factors on the face detection results and improve the stability of recognition. Moreover, the skin color information can be more effectively separated through color space conversion, which helps to improve the accuracy and efficiency of face detection based on skin color information.

[0073] Further, the server 10 retrieves a facial feature extraction network, which is obtained by pre-training a convolutional neural network. In order to optimize the feature extraction efficiency of the convolutional neural network, the convolutional neural network can be trained in advance according to the face image segmented by multi-camera scanning. The face image used as a training sample can contain multiple face areas, and the multiple face areas can be arranged in a grid in the face image, and each face area in the face image is the same. The same convolutional neural network feature group is added to each face area to increase the extraction efficiency of the neural network and reduce resource consumption during the extraction process.

[0074] The preprocessing result of the face image is sent to the face feature extraction network, and the first face feature output by the face feature extraction network can be obtained.

[0075] In a possible implementation, the server 10 can compare the cache and database of the security inspection system in turn, so as to improve the efficiency of remote stand registration verification. In this regard, the embodiment of the present application provides a remote stand boarding verification system, in which the server 10 is used to retrieve the second facial features of all passengers on the checked flight, and to determine whether the target passenger belongs to the checked flight by comparing the first facial features with the second facial features, and is specifically used to:

[0076] Retrieve multi-level cache data of the security inspection system, wherein the multi-level cache data contains first sub-facial features of all passengers of the checked flights in multiple first time intervals; traverse multiple first time intervals in order from late to early; for the target time interval currently traversed, extract the first sub-facial features in the target time interval from the multi-level cache data, and determine whether the target passenger belongs to the passenger of the checked flight in the target time interval by comparing the first facial features with the extracted first sub-facial features; if yes, record the checked flight and the target time interval; if not, return to execute the step of traversing multiple first time intervals in order from late to early, until all the multiple first time intervals are traversed, retrieve the database of the security inspection system, wherein the database records the second sub-facial features of all passengers of the checked flight in the second time interval, and the second time interval is earlier than the multiple first time intervals; determine whether the target passenger belongs to the passenger of the checked flight in the second time interval by comparing the first facial features with the second sub-facial features in the database; if yes, record the checked flight and the second time interval; if not, generate an error message.

[0077] Specifically, in the embodiment of the present application, the security inspection system records the facial features of all passengers on the inspected flight at different times, and the facial features can be recorded in the cache and the database respectively. The server 10 first retrieves the multi-level cache data in the cache of the security inspection system, and the multi-level cache data contains the second facial features (i.e., the first sub-facial features) of all passengers on the inspected flight in multiple time intervals (i.e., the first time interval); then, traverses multiple first time intervals in order from late to early, and the first time interval currently traversed is the target time interval, extracts the first sub-facial features under the target time interval from the multi-level cache data, and compares the first sub-facial features with the first facial features, so as to determine whether the target passenger is a passenger in the target time interval of the inspected flight. If yes, the server 10 records the inspected flight and the target time interval, otherwise, if no, the next round of traversal of multiple first time intervals is performed until all traversals are completed, and then retrieves the database of the security inspection system.

[0078] Take the example of multi-level cache data including first-level cache data and second-level cache data. The first-level cache data is the first sub-facial features of all passengers on the day of the security check flight, and the second-level cache data is the first sub-facial features of all passengers on the security check flight within the past week. The server 10 first tries to compare in the first-level cache data. The hardware foundation used by the first-level cache data is better than that of the second-level cache data, so the speed will be faster. If the first facial feature of the target passenger is not hit in the first-level cache data, it will be compared in the second-level cache data. Since both the first-level cache data and the second-level cache data are stored in high-speed memory, the speed is very fast. Only when both the first-level cache data and the second-level cache data do not hit, the server 10 will call the database again.

[0079] The database records the second facial features (i.e., second sub-facial features) of all passengers on the checked flight in the second time interval, and the second time interval is earlier than the plurality of first time intervals. The server 10 compares the first facial features with the second sub-facial features to determine whether the target passenger belongs to the passengers on the checked flight in the second time interval. If so, the server 10 records the checked flight and the second time interval. Otherwise, if not, an error message is generated.

[0080] In a possible implementation, in order to enable ground staff to obtain the remote boarding check result in time, the remote boarding check system provided by the embodiment of the present application also includes a client. The server 10 is also used to send the comparison result to the client; the client is used to display the comparison result.

[0081] Specifically, in the embodiment of the present application, the comparison result of the server 10 can be sent to the client held by the ground staff, so that the client can obtain the checked flight and time interval of the target passenger. The ground staff can determine whether the target passenger has missed the boarding situation according to the flight number and current time of the current flight.

[0082] Through the above description, a remote boarding review system provided in an embodiment of the present application can complete batch face detection in the shuttle bus, optimize the remote boarding review process, and ensure that the review of all passengers in the shuttle bus is completed before the shuttle bus arrives at the aircraft, so that passengers do not need to wait in line after getting off the shuttle bus, thereby improving the review and boarding efficiency.

[0083] The above describes a remote boarding verification system provided by an embodiment of the present application, and the following describes a remote boarding verification method based on the remote boarding verification system. The remote boarding verification method is applied to a server 10 in the remote boarding verification system, and the remote boarding verification system also includes a collection device 20 deployed in a shuttle bus, and the collection device 20 and the server 10 establish a remote network connection using a low-Earth orbit satellite.

[0084] See also Figure 4 , Figure 4 A flowchart of a remote boarding check-in method provided in an embodiment of the present application. Figure 4 As shown, a remote boarding check-in method provided in an embodiment of the present application includes the following steps:

[0085] S101, receiving a facial image sent by a collection device based on a remote network connection, where the facial image is obtained by the collection device through facial scanning and segmentation of a target passenger in a shuttle bus.

[0086] S102: extracting a first facial feature from the facial image.

[0087] S103, retrieve the second facial features of all passengers on the checked flight, determine whether the target passenger belongs to the checked flight by comparing the first facial features with the second facial features, and output the comparison result.

[0088] In a possible implementation, the above step S102 of “extracting the first facial feature from the facial image” may be performed by the following steps:

[0089] The facial image is preprocessed by compression filtering, grayscale conversion and color space conversion in sequence;

[0090] Retrieve the face feature extraction network, which is obtained by training the convolutional neural network;

[0091] The preprocessing result of the face image is input into the face feature extraction network to obtain the first face feature output by the face feature extraction network.

[0092] In a possible implementation, in the above step S103, "retrieve the second facial features of all passengers on the checked flight, and determine whether the target passenger belongs to the checked flight by comparing the first facial features with the second facial features", the following steps may be adopted:

[0093] Retrieving multi-level cache data of the security inspection system, the multi-level cache data including first sub-facial features of all passengers on the inspected flights in multiple first time intervals;

[0094] Traversing multiple first time intervals in order from latest to earliest;

[0095] For the currently traversed target time interval, extract the first sub-facial feature in the target time interval from the multi-level cache data, and determine whether the target passenger is a passenger on a checked flight in the target time interval by comparing the first facial feature with the extracted first sub-facial feature;

[0096] If yes, record the checked flights and target time interval;

[0097] If not, return to the step of traversing the multiple first time intervals in order from late to early, until all the multiple first time intervals are traversed, retrieve the database of the security inspection system, and the database records the second sub-face features of all passengers of the inspected flight in the second time interval, and the second time interval is earlier than the multiple first time intervals;

[0098] Determine whether the target passenger is a passenger on the checked flight in the second time interval by comparing the first facial feature with the second facial feature in the database;

[0099] If yes, record the checked flight and the second time interval;

[0100] If it does not belong, an error message is generated.

[0101] In a possible implementation, the remote boarding check-in system further includes a client, and a remote boarding check-in method provided in an embodiment of the present application further includes the following steps:

[0102] The comparison result is sent to the client so that the client can display the comparison result.

[0103] It should be noted that the implementation method of each step in the embodiment of the present application can refer to the corresponding public part of the above-mentioned remote boarding review system embodiment, which will not be repeated here.

[0104] Through the description of the above implementation mode, the technicians in the field can clearly understand that the present application can be implemented by means of software plus necessary general hardware, and of course, it can also be implemented by special hardware including special integrated circuits, special CPUs, special memories, special components, etc. In general, all functions completed by computer programs can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be various, such as analog circuits, digital circuits or special circuits. However, for the present application, software program implementation is a better implementation mode in more cases. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a readable storage medium, such as a computer floppy disk, a U disk, a mobile hard disk, a ROM, a RAM, a disk or an optical disk, etc., including a number of instructions to enable a computer device (which can be a personal computer, a training device, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0105] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.

[0106] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, a computer, a training device, or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, training device, or data center. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a training device, a data center, etc. that includes one or more available media integrations. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.

Claims

1. A remote boarding check-in system, characterized in that: The remote boarding check-in system includes: a service end, and a collection device deployed in a shuttle bus, wherein the collection device and the service end establish a remote network connection using a low-earth orbit satellite; The acquisition device is used to scan and segment the face of the target passenger in the shuttle bus to obtain the face image of the target passenger; The facial image is sent to the server; The server is used to extract the first facial feature in the facial image; retrieve the second facial features of all passengers on the checked flight, determine whether the target passenger belongs to the checked flight by comparing the first facial feature with the second facial feature, and output the comparison result.

2. The remote boarding check-in system according to claim 1, characterized in that: The acquisition device includes a plurality of cameras, the sum of the top-view angles of the plurality of cameras is larger than the range of the carriage of the shuttle bus, a local area network connection is established between the plurality of cameras in a grid manner, and each camera can communicate with the server based on the remote network connection; The multiple cameras determine a master camera and a slave camera based on the local area network connection, the master camera is the camera communicating with the server this time, and the slave camera is other cameras among the multiple cameras except the master camera; The slave camera is used to scan and segment the face of the first target passenger within its bird's-eye view to obtain a first face image of the first target passenger; and send the first face image to the master camera; The main camera is used to scan and segment the face of the second target passenger within its overhead viewing angle to obtain a second face image of the second target passenger; splice the first face image and the second face image, and send the splicing result to the server based on the remote network connection.

3. The remote boarding check-in system according to claim 2, characterized in that: The multiple cameras are cameras integrated with infrared light sources respectively.

4. The remote boarding check-in system according to claim 1, characterized in that: The server for extracting the first facial feature from the facial image is specifically used for: The facial image is preprocessed by compression filtering, grayscale conversion and color space conversion in sequence; a facial feature extraction network is retrieved, wherein the facial feature extraction network is obtained by training a convolutional neural network; and the preprocessing result of the facial image is input into the facial feature extraction network to obtain the first facial feature output by the facial feature extraction network.

5. The remote boarding check-in system according to claim 1, characterized in that: The server is used to retrieve the second facial features of all passengers on the checked flight, and determine whether the target passenger belongs to the checked flight by comparing the first facial features with the second facial features, specifically used to: Retrieving multi-level cache data of a security inspection system, wherein the multi-level cache data includes first sub-facial features of all passengers of the inspected flight in multiple first time intervals; Traversing the multiple first time intervals in order from late to early; for the currently traversed target time interval, extracting the first sub-facial feature in the target time interval from the multi-level cache data, and determining whether the target passenger is a passenger of the checked flight in the target time interval by comparing the first facial feature with the extracted first sub-facial feature; If yes, record the checked flight and the target time interval; If not, returning to the step of traversing the multiple first time intervals in order from late to early, until all the multiple first time intervals are traversed, retrieving the database of the security inspection system, wherein the database records the second sub-facial features of all passengers of the inspected flight in the second time interval, and the second time interval is earlier than the multiple first time intervals; determining whether the target passenger is a passenger of the inspected flight in the second time interval by comparing the first facial feature with the second sub-facial feature in the database; If yes, record the checked flight and the second time interval; If it does not belong, an error message is generated.

6. The remote boarding check-in system according to claim 1, characterized in that: The remote boarding check-in system further includes: a client; The server is further configured to send the comparison result to the client; The client is used to display the comparison result.

7. A remote boarding check-in method, characterized in that: The remote boarding verification method is applied to the server of the remote boarding verification system, and the remote boarding verification system further includes a collection device deployed in a shuttle bus, and the collection device and the server establish a remote network connection using a low-earth orbit satellite. The remote boarding verification method includes: Receiving a facial image sent by the acquisition device based on the remote network connection, wherein the facial image is obtained by the acquisition device through facial scanning and segmentation of a target passenger in the shuttle bus; Extracting a first facial feature from the facial image; The second facial features of all passengers on the checked flight are retrieved, and whether the target passenger belongs to the checked flight is determined by comparing the first facial features with the second facial features, and the comparison result is output.

8. The remote boarding verification method according to claim 7, characterized in that: The extracting the first facial feature from the facial image includes: Performing compression filtering, grayscale conversion and color space conversion preprocessing on the face image in sequence; Retrieving a facial feature extraction network, wherein the facial feature extraction network is obtained by training a convolutional neural network; The preprocessing result of the face image is input into the face feature extraction network to obtain the first face feature output by the face feature extraction network.

9. The remote boarding verification method according to claim 7, characterized in that: The retrieving the second facial features of all passengers on the checked flight and determining whether the target passenger belongs to the checked flight by comparing the first facial features with the second facial features includes: Retrieving multi-level cache data of a security inspection system, wherein the multi-level cache data includes first sub-facial features of all passengers of the inspected flight in multiple first time intervals; Traversing the plurality of first time intervals in order from latest to earliest; For the currently traversed target time interval, extract the first sub-facial feature in the target time interval from the multi-level cache data, and determine whether the target passenger is a passenger of the checked flight in the target time interval by comparing the first facial feature with the extracted first sub-facial feature; If yes, record the checked flight and the target time interval; If not, returning to the step of traversing the multiple first time intervals in order from late to early, until all the multiple first time intervals are traversed, calling the database of the security inspection system, wherein the database records the second sub-face features of all passengers of the inspected flight in the second time interval, and the second time interval is earlier than the multiple first time intervals; Determining whether the target passenger is a passenger on the checked flight in the second time interval by comparing the first facial feature with the second sub-facial feature in the database; If yes, record the checked flight and the second time interval; If it does not belong, an error message is generated.

10. The remote boarding verification method according to claim 7, characterized in that: The remote boarding check-in system further includes a client, and the remote boarding check-in method further includes: The comparison result is sent to the client so that the client displays the comparison result.

Images