Intelligent pre-checking self-service luggage check-in terminal system and method based on visual image technology

Abstract

The invention relates to an intelligent pre-checking self-service luggage consignment terminal system based on a visual image technology, and relates to the field of image processing, and the terminal system comprises a size detection module which is used for employing a depth visual camera to detect whether the shape and the size of a target luggage meet a consignment standard or not; and the intelligent identification module is used for collecting a current scanning picture obtained by scanning the target luggage by the X-ray scanner, and intelligently identifying whether each object in the current scanning picture belongs to a forbidden object type or not. The invention further relates to an intelligent pre-checking self-service luggage check-in method based on the visual image technology. According to the invention, the intelligent identification model with a customized structure can be adopted to intelligently identify whether prohibited articles exist on each piece of luggage, and the intelligent identification of the prohibited articles is organically combined with the detection of the appearance, size, type and weight of the luggage, so that the passenger can complete the detection of all detection parameters of the luggage only at one place.

Description

Technical Field

[0001] The present invention relates to the field of image processing, and in particular to an intelligent pre-inspection self-service baggage check-in terminal system and method based on visual image technology. Background Art

[0002] In the process of passengers handling self-service baggage check-in at the airport check-in, it is necessary to detect the baggage carried by passengers to obtain baggage-related information and determine whether the baggage meets the check-in requirements. For example, various detection technologies such as the appearance, size, type, and weight of the baggage are required. For each piece of baggage carried by each passenger, targeted detection and judgment are carried out on whether the appearance, size, type, and weight respectively meet the standards. Only when all detection indicators meet the standards, is it allowed to release each piece of baggage carried by each passenger, and the corresponding baggage is allowed to be transmitted to the conveyor belt to be sent to the baggage handling system leading to the airport freight vehicle.

[0003] Exemplarily, the Chinese utility model patent publication text CN205486359U proposes a multi-functional self-service baggage check-in intelligent terminal, including a box body, a main chassis embedded in the front side of the box body, and a display device, a baggage label scanning device, a baggage conveying device, and a baggage specification detection device connected to the main chassis in sequence. The box body of the multi-functional self-service baggage check-in intelligent terminal is a traditional manual counter; the display device includes a support arm installed on one side of the box body and a display installed on the support arm; the display can rotate around the support arm as the center. The terminal realizes the organic combination of the manual counter and self-service check-in. When the self-service baggage check-in terminal operates, the manual counter can provide services such as receiving consultations and handling boarding passes for passengers. The counter staff only needs to rotate the display device to a suitable position to assist passengers in handling self-service check-in, thus facilitating passengers to handle check-in matters, saving time, and enhancing the passenger experience, and more fully realizing the maximization of benefits.

[0004] Exemplarily, the Chinese invention patent publication text CN112164186A proposes a check-in and baggage check-in method for an online terminal building ATIS intelligent terminal. The method uses an online terminal building ATIS intelligent terminal, a passenger client, a city terminal building check-in service provider client, a handheld terminal client, a monitor, a standby intelligent terminal, and a baggage storage and check-in self-service station. The passenger scans the check-in QR code to reserve the check-in service, and the online terminal building ATIS intelligent terminal judges the source of the baggage check-in QR code scanned by the passenger and sends the passenger information to the city terminal building check-in service provider client. The city terminal building service provider performs online seat selection and check-in, reducing the waiting time of passengers, reducing the pressure and risk of channel congestion caused by centralization, and effectively improving the travel efficiency of passengers; the baggage storage and check-in self-service station provides services for passengers to check in their baggage, improving the travel efficiency and experience of passengers.

[0005] At present, the self-service baggage check-in equipment is responsible for interacting with the airport departure system and the baggage transfer system. While completing the passenger baggage check-in service, it prompts the dangerous goods in the checked baggage of the passenger at the equipment end. If the passenger is not clear about the requirements for prohibited dangerous goods or forgets whether they are carrying dangerous goods, after completing the checked baggage business process, they need to move to the baggage opening room to unpack and inspect the baggage that has not passed the security check and remove the dangerous goods. It can be seen that the self-service baggage check-in equipment in the prior art can only detect the appearance, size, type and weight of the baggage, but has no detection and prompt function for prohibited items. Such a separate detection mode and the detection difficulty of prohibited items will increase the passenger's business handling links and reduce the speed and efficiency of the passenger boarding business process. Summary of the Invention

[0006] In order to solve the technical problems in the prior art, the present invention provides an intelligent pre-inspection self-service baggage check-in terminal system and method based on visual image technology, which can perform intelligent identification processing on whether there are prohibited items in each piece of baggage carried by each passenger based on various basic data screened specifically by an intelligent recognition model with a customized structure. On this basis, the intelligent identification processing of the prohibited items in the baggage is organically combined with the detection of the appearance, size, type and weight of the baggage, so as to ensure that the passenger can complete the detection of all the detection parameters of the baggage at only one place, thereby improving the speed and efficiency of the passenger boarding business process.

[0007] According to one aspect of the present invention, there is provided an intelligent pre-inspection self-service baggage check-in terminal system based on visual image technology, the terminal system comprising:

[0008] A document scanning module, configured to scan the identity document of the current passenger to obtain the identity information of the current passenger when the current passenger handles the baggage check-in, and print a passenger boarding pass and a baggage tag corresponding to the obtained identity information;

[0009] A barcode recognition module, connected to the document scanning module, configured to perform barcode recognition on the baggage tag of the target baggage of the current passenger located in the baggage detection area by using a high-definition industrial camera to obtain the baggage barcode corresponding to the target baggage;

[0010] A size detection module, connected to the barcode recognition module, configured to detect the shape and size of the target baggage by using a depth vision camera, and issue a first detection signal when the shape and size of the target baggage both meet the check-in standards, otherwise, issue a second detection signal;

[0011] An intelligent recognition module, connected to the size detection module, is configured to collect the current scanned image obtained by the X-ray scanner scanning the target luggage, analyze the respective image regions occupied by each object in the current scanned image, and perform the following intelligent recognition operations on each object as an object to be recognized: using a convolutional neural network after multiple learning processes, based on the respective cyan component values, respective magenta component values, respective yellow component values, and respective black component values corresponding to each pixel point in the image region corresponding to the object to be recognized, the respective vertical coordinate values and respective horizontal coordinate values corresponding to each pixel point in the image region corresponding to the object to be recognized, the respective pixel value gradients corresponding to multiple edge pixel points in the image region corresponding to the object to be recognized, the number of pixel rows and pixel columns of the current scanned image, and the signal-to-noise ratio of the current scanned image, to intelligently recognize the object type corresponding to the object to be recognized; the intelligent recognition module is further configured to, when there is more than one prohibited item type among the respective object types corresponding to each object in the current scanned image, send out a first recognition signal, otherwise, send out a second recognition signal.

[0012] According to another aspect of the present invention, there is provided an intelligent pre-inspection self-service luggage consignment method based on visual image technology, the method comprising:

[0013] When the current passenger handles luggage consignment, scan the identity document of the current passenger to obtain the identity information of the current passenger, and print a passenger boarding pass and a luggage tag corresponding to the obtained identity information;

[0014] Use a high-definition industrial camera to perform barcode recognition on the luggage tag of the target luggage of the current passenger located in the luggage detection area to obtain the luggage barcode corresponding to the target luggage;

[0015] Use a depth vision camera to detect the shape and size of the target luggage, and when both the shape and size of the target luggage meet the consignment standards, send out a first detection signal, otherwise, send out a second detection signal;

[0016] Collect the current scan image obtained by the X-ray scanner when scanning the target luggage, analyze the respective image areas occupied by each object in the current scan image, and perform the following intelligent recognition operations on each object as the object to be recognized: Use a convolutional neural network after multiple trainings to respectively correspond to each cyan component value, each magenta component value, each yellow component value, and each black component value corresponding to each pixel point in the image area corresponding to the object to be recognized, each vertical coordinate value and each horizontal coordinate value corresponding to each pixel point in the image area corresponding to the object to be recognized, multiple pixel value gradients corresponding to multiple edge pixel points in the image area corresponding to the object to be recognized, the number of pixel rows and pixel columns of the current scan image, and the signal-to-noise ratio of the current scan image to intelligently recognize the object type corresponding to the object to be recognized;

[0017] When there is one or more prohibited item types among the respective object types corresponding to each object in the current scan image, send a first recognition signal; otherwise, send a second recognition signal;

[0018] When receiving the second detection signal or the first recognition signal, return the target luggage to the luggage detection area, and when receiving the first detection signal or the second recognition signal, transfer the target luggage to the conveyor belt to be sent to the luggage transportation system leading to the airport freight vehicle;

[0019] Among them, when there is one or more prohibited item types among the respective object types corresponding to each object in the current scan image, sending a first recognition signal; otherwise, sending a second recognition signal includes: The prohibited item types include lighters, oversized cosmetics, and power banks.

[0020] Thus, the present invention at least has the following four key inventive points:

[0021] Inventive point one: For the intelligent pre-inspection self-service luggage check-in terminal system at the airport, supplement the intelligent recognition module to complete the intelligent recognition of whether each piece of luggage of the current passenger as the target luggage carries prohibited items, and when it is intelligently recognized that the target luggage carries prohibited items or the shape or size of the target luggage does not meet the check-in standard, return the target luggage to the luggage detection area; otherwise, transfer the target luggage to the conveyor belt to be sent to the luggage sorting system, so as to detect the appearance and size of the luggage and check for prohibited items and give prompts when handling the self-service luggage check-in business, thereby helping the airport management side obtain more comprehensive luggage information data, improving the airport operation safety level, and at the same time reducing the subsequent business handling links of passengers and improving the efficiency of the business process before passengers board the plane;

[0022] Inventive Point 2: An intelligent recognition model with a customized structure is adopted to complete the intelligent recognition of the types of prohibited items. The customization of the structure of the intelligent recognition model is mainly manifested in that the intelligent recognition model is a convolutional neural network after multiple learnings, and the number of learnings undergone by the convolutional neural network is positively correlated with the scanning resolution of the X-ray scanner, so as to construct intelligent recognition models with different structures for different X-ray scanners, ensuring the stability and reliability of the intelligent recognition of prohibited items;

[0023] Inventive Point 3: A sufficient and comprehensive set of basic data is introduced to perform the intelligent recognition of the types of prohibited items. The set of basic data includes the respective cyan component values, magenta component values, yellow component values, and black component values corresponding to each pixel point in the image area corresponding to the object to be recognized in the current scanned image, the respective vertical coordinate values and horizontal coordinate values corresponding to each pixel point in the image area corresponding to the object to be recognized, the multiple pixel value gradients corresponding to multiple edge pixel points in the image area corresponding to the object to be recognized, the number of pixel rows and pixel columns of the current scanned image, and the signal-to-noise ratio of the current scanned image, thereby further ensuring the stability and reliability of the intelligent recognition of prohibited items;

[0024] Inventive Point 4: In each learning operation performed on the convolutional neural network, the object type of the recognized object in the historical scanned image obtained by the historical scan of the X-ray scanner is used as the single output content of the convolutional neural network, and the respective cyan component values, magenta component values, yellow component values, and black component values corresponding to each pixel point in the image area occupied by the recognized object in the historical scanned image, the respective vertical coordinate values and horizontal coordinate values corresponding to each pixel point in the image area occupied by the recognized object in the historical scanned image, the multiple pixel value gradients corresponding to multiple edge pixel points in the image area occupied by the recognized object in the historical scanned image, the number of pixel rows and pixel columns of the historical scanned image, and the signal-to-noise ratio of the historical scanned image are used as the item-by-item output content of the convolutional neural network, and the current learning operation performed on the convolutional neural network is completed, thereby ensuring the learning effect of each learning operation of the convolutional neural network. Description of the Drawings

[0025] The embodiments of the present invention will be described below with reference to the drawings, where:

[0026] Figure 1 It is a schematic external view of the hardware structure based on an intelligent pre-inspection self-service baggage check-in terminal system and method according to the present invention.

[0027] Figure 2It is a technical flowchart of an intelligent pre-inspection self-service baggage check-in terminal system and method based on visual image technology according to the present invention.

[0028] Figure 3 It is an internal structure diagram of an intelligent pre-inspection self-service baggage check-in terminal system based on visual image technology shown in the first embodiment according to the present invention.

[0029] Figure 4 It is an internal structure diagram of an intelligent pre-inspection self-service baggage check-in terminal system based on visual image technology shown in the second embodiment according to the present invention.

[0030] Figure 5 It is an internal structure diagram of an intelligent pre-inspection self-service baggage check-in terminal system based on visual image technology shown in the third embodiment according to the present invention.

[0031] Figure 6 It is an internal structure diagram of an intelligent pre-inspection self-service baggage check-in terminal system based on visual image technology shown in the fourth embodiment according to the present invention.

[0032] Figure 7 It is an internal structure diagram of an intelligent pre-inspection self-service baggage check-in terminal system based on visual image technology shown in the fifth embodiment according to the present invention.

[0033] Figure 8 It is a step flowchart of an intelligent pre-inspection self-service baggage check-in method based on visual image technology shown in the sixth embodiment according to the present invention. Detailed implementation manners

[0034] Figure 1 It is an external shape schematic diagram of the hardware structure on which an intelligent pre-inspection self-service baggage check-in terminal system and method based on visual image technology according to the present invention are based.

[0035] As Figure 2 shown, a technical flowchart of an intelligent pre-inspection self-service baggage check-in terminal system and method based on visual image technology shown according to the present invention is given.

[0036] In Figure 2 , the specific technical process of the present invention is as follows:

[0037] Technical process A: Design a customized intelligent recognition model to complete the intelligent recognition of whether each piece of baggage of the current passenger, when regarded as the target baggage, contains prohibited items in the target baggage;

[0038] Specifically, the customization of the structure of the intelligent recognition model is mainly manifested in the following aspects:

[0039] First: The intelligent recognition model is a convolutional neural network after multiple learnings;

[0040] Second: The number of learning times experienced by the convolutional neural network is positively correlated with the scanning resolution of the X-ray scanner;

[0041] Third: In each learning action performed on the convolutional neural network, the object type of the identified object in the historical scan image obtained from the historical scans of the X-ray scanner is used as the single output content of the convolutional neural network. The cyan component values, magenta component values, yellow component values, and black component values corresponding to each pixel point in the image area occupied by the identified object in the historical scan image, the vertical coordinate values and horizontal coordinate values corresponding to each pixel point in the image area occupied by the identified object in the historical scan image, the multiple pixel value gradients corresponding to multiple edge pixel points in the image area occupied by the identified object in the historical scan image, the number of pixel rows and pixel columns of the historical scan image, and the signal-to-noise ratio of the historical scan image are used as the item-by-item output content of the convolutional neural network, and this learning action performed on the convolutional neural network is completed;

[0042] The design of the above customized structures constructs intelligent recognition models with different structures for different X-ray scanners, thus ensuring the stability and reliability of the intelligent recognition of prohibited items;

[0043] Technical process B: Introduce a sufficient and comprehensive set of basic data to complete the intelligent recognition of whether prohibited items are carried in each piece of luggage of the current passenger when the luggage is used as the target luggage;

[0044] Specifically, the set of basic data includes the cyan component values, magenta component values, yellow component values, and black component values corresponding to each pixel point in the image area corresponding to the object to be recognized in the current scan image of the luggage, the vertical coordinate values and horizontal coordinate values corresponding to each pixel point in the image area corresponding to the object to be recognized, the multiple pixel value gradients corresponding to multiple edge pixel points in the image area corresponding to the object to be recognized, the number of pixel rows and pixel columns of the current scan image, and the signal-to-noise ratio of the current scan image;

[0045] The full and comprehensive introduction of the above set of basic data further ensures the stability and reliability of the intelligent recognition of prohibited items;

[0046] Technical process C: Use the intelligent recognition model designed with the customized structure of technical process A based on the set of basic data specifically screened by technical process B to intelligently recognize whether prohibited items are carried in each piece of luggage of the current passenger when the luggage is used as the target luggage;

[0047] Technical Process D: Incorporate the intelligent recognition module that executes Technical Process C into the existing intelligent pre-check self-service baggage check-in terminal system at the airport to help the airport management obtain more comprehensive baggage information data;

[0048] Specifically, in the intelligent pre-check self-service baggage check-in terminal system after incorporating the intelligent recognition module, when it is detected that the target baggage contains prohibited items or the shape or size of the target baggage does not meet the check-in standard, the target baggage is returned to the baggage detection area; otherwise, the target baggage is transported to the conveyor belt to be sent to the baggage sorting system, so as to check for and prompt prohibited items while detecting the appearance and size of the baggage when handling self-service baggage check-in business;

[0049] In this way, the comprehensive parameters of the target baggage are detected in one place, improving the safety of airport operation. At the same time, the subsequent business handling links of passengers are reduced, improving the efficiency of the business process before passengers board the plane;

[0050] The key points of the present invention lie in: the organic combination of the intelligent recognition module with the existing intelligent pre-check self-service baggage check-in terminal system at the airport, the design of multiple customized structures of the intelligent recognition model, and the full and comprehensive introduction of multiple basic data for intelligent recognition of prohibited items.

[0051] Next, a specific description will be given of an intelligent pre-check self-service baggage check-in terminal system and method based on visual image technology according to the present invention by way of embodiments.

[0052] First Embodiment

[0053] Figure 3 FIG. is the internal structure diagram of an intelligent pre-check self-service baggage check-in terminal system based on visual image technology shown according to the first embodiment of the present invention.

[0054] As Figure 3 shown, the intelligent pre-check self-service baggage check-in terminal system based on visual image technology includes the following components:

[0055] A document scanning module, which is used to scan the identity document of the current passenger when handling baggage check-in to obtain the identity information of the current passenger, and print a passenger boarding pass and a baggage tag corresponding to the obtained identity information;

[0056] Exemplarily, when handling baggage check-in for the current passenger, scanning the identity document of the current passenger to obtain the identity information of the current passenger, accessing the network database to collect the passenger boarding pass and baggage tag corresponding to the obtained identity information, and printing the passenger boarding pass and baggage tag corresponding to the obtained identity information includes: scanning the identity document of the current passenger to obtain the identity information of the current passenger, accessing the network database to collect the passenger boarding pass and baggage tag corresponding to the obtained identity information, and printing the passenger boarding pass and baggage tag corresponding to the obtained identity information;

[0057] A barcode recognition module, connected to the document scanning module, is configured to perform barcode recognition on the luggage strip of the target luggage of the current passenger located in the luggage detection area by using a high-definition industrial camera, so as to obtain the luggage barcode corresponding to the target luggage;

[0058] Specifically, performing barcode recognition on the luggage strip of the target luggage of the current passenger located in the luggage detection area by using a high-definition industrial camera to obtain the luggage barcode corresponding to the target luggage includes: the high-definition industrial camera is internally provided with a high-definition imaging mechanism, an image processing mechanism, a barcode output mechanism, and a parallel data bus;

[0059] A size detection module, connected to the barcode recognition module, is configured to detect the shape and size of the target luggage by using a depth vision camera, and issue a first detection signal when both the shape and size of the target luggage meet the consignment standard, otherwise, issue a second detection signal;

[0060] Exemplarily, detecting the shape and size of the target luggage by using a depth vision camera, and issuing a first detection signal when both the shape and size of the target luggage meet the consignment standard, otherwise, issuing a second detection signal includes: the depth vision camera is internally provided with a depth sensor and a vision sensor, and the depth sensor and the vision sensor are integrated together to form a sensing component of the depth vision camera;

[0061] And exemplarily, detecting the shape and size of the target luggage by using a depth vision camera, and issuing a first detection signal when both the shape and size of the target luggage meet the consignment standard, otherwise, issuing a second detection signal further includes: the depth vision camera is further internally provided with an image detection component for intelligently detecting the shape and size of the target luggage based on the collected visual data. Since the intelligent detection of the shape and size of the objects in the imaging area belongs to the conventional technology in the field of artificial intelligence, it will not be elaborated here;

[0062] An intelligent recognition module, connected to the size detection module, is configured to collect the current scanned image obtained by the X-ray scanner scanning the target luggage, analyze the respective image regions occupied by each object in the current scanned image, and perform the following intelligent recognition operations on each object as the object to be recognized: Using a convolutional neural network after multiple learning processes, based on the respective cyan component values, respective magenta component values, respective yellow component values, and respective black component values corresponding to each pixel point in the image region corresponding to the object to be recognized, the respective vertical coordinate values and respective horizontal coordinate values corresponding to each pixel point in the image region corresponding to the object to be recognized, the respective pixel value gradients corresponding to multiple edge pixel points in the image region corresponding to the object to be recognized, the number of pixel rows and pixel columns of the current scanned image, and the signal-to-noise ratio of the current scanned image, intelligently recognize the object type corresponding to the object to be recognized;

[0063] Exemplarily, using a programmable logic device, a convolutional neural network after multiple learning processes is used to intelligently recognize the object type corresponding to the object to be recognized based on the respective cyan component values, respective magenta component values, respective yellow component values, and respective black component values corresponding to each pixel point in the image region corresponding to the object to be recognized, the respective vertical coordinate values and respective horizontal coordinate values corresponding to each pixel point in the image region corresponding to the object to be recognized, the respective pixel value gradients corresponding to multiple edge pixel points in the image region corresponding to the object to be recognized, the number of pixel rows and pixel columns of the current scanned image, and the signal-to-noise ratio of the current scanned image;

[0064] Wherein, the intelligent recognition module is further configured to issue a first recognition signal when there is more than one type of prohibited item among the respective object types corresponding to each object in the current scanned image, otherwise, issue a second recognition signal;

[0065] Wherein, using a convolutional neural network after multiple learning processes to intelligently recognize the object type corresponding to the object to be recognized based on the respective cyan component values, respective magenta component values, respective yellow component values, and respective black component values corresponding to each pixel point in the image region corresponding to the object to be recognized, the respective vertical coordinate values and respective horizontal coordinate values corresponding to each pixel point in the image region corresponding to the object to be recognized, the respective pixel value gradients corresponding to multiple edge pixel points in the image region corresponding to the object to be recognized, the number of pixel rows and pixel columns of the current scanned image, and the signal-to-noise ratio of the current scanned image includes: The number of learning processes passed by the convolutional neural network is positively correlated with the scanning resolution of the X-ray scanner;

[0066] Exemplarily, the number of learning times experienced by the convolutional neural network is positively correlated with the scanning resolution of the X-ray scanner, which includes: the higher the scanning resolution of the X-ray scanner, the more learning times the convolutional neural network experiences;

[0067] Among them, using the convolutional neural network after multiple learning processes, based on the respective cyan component values, magenta component values, yellow component values, and black component values corresponding to each pixel point in the image area corresponding to the object to be recognized, the respective vertical coordinate values and horizontal coordinate values corresponding to each pixel point in the image area corresponding to the object to be recognized, the multiple pixel value gradients corresponding to multiple edge pixel points in the image area corresponding to the object to be recognized, the number of pixel rows and pixel columns in the current scanning screen, and the signal-to-noise ratio of the current scanning screen to intelligently identify the object type corresponding to the object to be recognized further includes: in each learning action performed on the convolutional neural network, taking the object type of the recognized object in the historical scanning screen obtained by the historical scanning of the X-ray scanner as the single output content of the convolutional neural network, and taking the respective cyan component values, magenta component values, yellow component values, and black component values corresponding to each pixel point in the image area occupied by the recognized object in the historical scanning screen, the respective vertical coordinate values and horizontal coordinate values corresponding to each pixel point in the image area occupied by the recognized object in the historical scanning screen, the multiple pixel value gradients corresponding to multiple edge pixel points in the image area occupied by the recognized object in the historical scanning screen, the number of pixel rows and pixel columns in the historical scanning screen, and the signal-to-noise ratio of the historical scanning screen as the item-by-item output content of the convolutional neural network, and completing the current learning action performed on the convolutional neural network;

[0068] Specifically, among the single cyan component value, single magenta component value, single yellow component value, and single black component value corresponding to each pixel point, the value range of any color component value is between 0 and 255;

[0069] And specifically, each pixel point has a corresponding single cyan component value, i.e., single C component value, single magenta component value, i.e., single M component value, single yellow component value, i.e., single Y component value, and single black component value, i.e., single K component value in the CMYK color space;

[0070] Among them, using a depth vision camera to detect the shape and size of the target luggage, and when both the shape and size of the target luggage meet the consignment standard, sending a first detection signal, otherwise, sending a second detection signal includes: using a depth vision camera to detect the shape of the target luggage based on a deep learning mode;

[0071] And among them, a depth vision camera is used to detect the shape and size of the target luggage, and when the shape and size of the target luggage both meet the consignment standard, a first detection signal is sent, otherwise, a second detection signal is sent. It further includes: using the depth vision camera to detect the size of the target luggage based on the collected depth information of the target luggage.

[0072] Second Embodiment

[0073] Figure 4 It is an internal structure diagram of an intelligent pre-inspection self-service luggage consignment terminal system based on visual image technology shown in the second embodiment of the present invention.

[0074] As Figure 4 shown, compared with Figure 3 , the intelligent pre-inspection self-service luggage consignment terminal system based on visual image technology further includes:

[0075] A luggage conveying module, which is respectively connected to the size detection module and the intelligent recognition module, and is used to return the target luggage to the luggage detection area when receiving the second detection signal or the first recognition signal;

[0076] Exemplarily, a luggage conveying module, which is respectively connected to the size detection module and the intelligent recognition module, and is used to return the target luggage to the luggage detection area when receiving the second detection signal or the first recognition signal includes: the luggage conveying module is internally provided with a signal receiving component, a signal analysis component, a conveying execution component and a luggage return component;

[0077] Among them, the luggage conveying module is also used to transfer the target luggage to the conveying belt when receiving the first detection signal or the second recognition signal to send it to the luggage sorting system;

[0078] Among them, the intelligent recognition module is also used to send a first recognition signal when there is more than one type of prohibited item among the types of each object corresponding to each object in the current scanned picture, otherwise, a second recognition signal is sent. It includes: the types of prohibited items include lighters, over-sized cosmetics and power banks.

[0079] Third Embodiment

[0080] Figure 5 It is an internal structure diagram of an intelligent pre-inspection self-service luggage consignment terminal system based on visual image technology shown in the third embodiment of the present invention.

[0081] As Figure 5 shown, compared with Figure 3 , the intelligent pre-inspection self-service luggage consignment terminal system based on visual image technology further includes:

[0082] The on-site warning module, which is respectively connected to the size detection module and the intelligent recognition module, is configured to perform on-site broadcast of warning information corresponding to the identification of prohibited items when receiving the second detection signal or the first recognition signal;

[0083] Specifically, the on-site warning module, which is respectively connected to the size detection module and the intelligent recognition module, is configured to perform on-site broadcast of warning information corresponding to the identification of prohibited items when receiving the second detection signal or the first recognition signal, including: the on-site warning module is an acoustic alarm module or an optical alarm module.

[0084] The fourth embodiment

[0085] Figure 6 It is an internal structure diagram of the intelligent pre-inspection self-service baggage check-in terminal system based on visual image technology shown in the fourth embodiment of the present invention.

[0086] As Figure 6 shown, compared with Figure 3 , the intelligent pre-inspection self-service baggage check-in terminal system based on visual image technology further includes:

[0087] The interaction operation module is configured to display a passenger interaction operation interface and provide an interaction operation interface for information interaction of the current passenger;

[0088] Exemplarily, the interaction operation module is configured to display a passenger interaction operation interface and provide an interaction operation interface for information interaction of the current passenger, including: the interaction operation module is implemented by using a touch screen.

[0089] The fifth embodiment

[0090] Figure 7 It is an internal structure diagram of the intelligent pre-inspection self-service baggage check-in terminal system based on visual image technology shown in the fifth embodiment of the present invention.

[0091] As Figure 7 shown, compared with Figure 3 , the intelligent pre-inspection self-service baggage check-in terminal system based on visual image technology further includes:

[0092] The model storage module, which is connected to the intelligent recognition module, is configured to receive various model parameters of the convolutional neural network, that is, the intelligent recognition model, after multiple learning processes, and complete the model storage of the intelligent recognition model by storing the various model parameters of the intelligent recognition model;

[0093] Specifically, a FLASH flash memory or an MMC storage chip can be selected to implement the model storage module, which is connected to the intelligent recognition module, used to receive various model parameters of the convolutional neural network, i.e., the intelligent recognition model, after multiple learning processes, and complete the model storage of the intelligent recognition model by storing the various model parameters of the intelligent recognition model.

[0094] Next, further descriptions will be continued for each embodiment of the present invention.

[0095] Optionally, in each of the above embodiments, in the intelligent pre-inspection self-service baggage check-in terminal system based on visual image technology:

[0096] Using the convolutional neural network after multiple learning processes to intelligently identify the object type corresponding to the object to be identified based on the cyan component values, magenta component values, yellow component values, and black component values respectively corresponding to each pixel point in the image area corresponding to the object to be identified, the vertical coordinate values and horizontal coordinate values respectively corresponding to each pixel point in the image area corresponding to the object to be identified, the pixel value gradients respectively corresponding to multiple edge pixel points in the image area corresponding to the object to be identified, the number of pixel rows and pixel columns of the current scanned image, and the signal-to-noise ratio of the current scanned image further includes: parallelly inputting the cyan component values, magenta component values, yellow component values, and black component values respectively corresponding to each pixel point in the image area corresponding to the object to be identified, the vertical coordinate values and horizontal coordinate values respectively corresponding to each pixel point in the image area corresponding to the object to be identified, the pixel value gradients respectively corresponding to multiple edge pixel points in the image area corresponding to the object to be identified, the number of pixel rows and pixel columns of the current scanned image, and the signal-to-noise ratio of the current scanned image into the convolutional neural network after multiple learning processes;

[0097] Exemplarily, parallelly inputting each cyan component value, each magenta component value, each yellow component value, and each black component value corresponding to each pixel point in the image region corresponding to the object to be recognized, each vertical coordinate value and each horizontal coordinate value corresponding to each pixel point in the image region corresponding to the object to be recognized, multiple pixel value gradients corresponding to multiple edge pixel points in the image region corresponding to the object to be recognized, the number of pixel rows and the number of pixel columns of the current scanned image, and the signal-to-noise ratio of the current scanned image into the convolutional neural network after multiple learning processes includes: Selecting to use the MATLAB toolbox to implement the test and simulation of the data processing process of parallelly inputting each cyan component value, each magenta component value, each yellow component value, and each black component value corresponding to each pixel point in the image region corresponding to the object to be recognized, each vertical coordinate value and each horizontal coordinate value corresponding to each pixel point in the image region corresponding to the object to be recognized, multiple pixel value gradients corresponding to multiple edge pixel points in the image region corresponding to the object to be recognized, the number of pixel rows and the number of pixel columns of the current scanned image, and the signal-to-noise ratio of the current scanned image into the convolutional neural network after multiple learning processes;

[0098] Using the convolutional neural network after multiple learning processes to intelligently identify the object type corresponding to the object to be recognized based on each cyan component value, each magenta component value, each yellow component value, and each black component value corresponding to each pixel point in the image region corresponding to the object to be recognized, each vertical coordinate value and each horizontal coordinate value corresponding to each pixel point in the image region corresponding to the object to be recognized, multiple pixel value gradients corresponding to multiple edge pixel points in the image region corresponding to the object to be recognized, the number of pixel rows and the number of pixel columns of the current scanned image, and the signal-to-noise ratio of the current scanned image further includes: Running the convolutional neural network after multiple learning processes to obtain the object type corresponding to the object to be recognized output by the convolutional neural network after multiple learning processes.

[0099] And in each of the above embodiments, optionally, in the intelligent pre-inspection self-service baggage check-in terminal system based on visual image technology:

[0100] The number of learning times of the convolutional neural network is positively correlated with the scanning resolution of the X-ray scanner, including: Using an information conversion function to represent the information conversion relationship between the number of learning times of the convolutional neural network and the scanning resolution of the X-ray scanner;

[0101] Among them, the information conversion relationship representing the positive correlation between the number of learning times experienced by the convolutional neural network and the scanning resolution of the X-ray scanner using an information conversion function includes: in the information conversion function, the scanning resolution of the X-ray scanner is the input information of the information conversion function;

[0102] Among them, the information conversion relationship representing the positive correlation between the number of learning times experienced by the convolutional neural network and the scanning resolution of the X-ray scanner using an information conversion function further includes: in the information conversion function, the number of learning times experienced by the convolutional neural network corresponding to the scanning resolution of the X-ray scanner is the output information of the information conversion function.

[0103] Sixth Embodiment

[0104] Figure 8 It is a step flowchart of an intelligent pre-inspection self-service baggage check-in method based on visual image technology shown in the sixth embodiment of the present invention.

[0105] As Figure 8 shown, the intelligent pre-inspection self-service baggage check-in method based on visual image technology includes the following steps:

[0106] When the current passenger checks in baggage, scan the identity document of the current passenger to obtain the identity information of the current passenger, and print the passenger boarding pass and baggage tag corresponding to the obtained identity information;

[0107] Exemplarily, when the current passenger checks in baggage, scanning the identity document of the current passenger to obtain the identity information of the current passenger, and printing the passenger boarding pass and baggage tag corresponding to the obtained identity information includes: scanning the identity document of the current passenger to obtain the identity information of the current passenger, accessing the network database to collect the passenger boarding pass and baggage tag corresponding to the obtained identity information, and printing the passenger boarding pass and baggage tag corresponding to the obtained identity information;

[0108] Use a high-definition industrial camera to perform barcode recognition on the baggage tag of the target baggage of the current passenger located in the baggage detection area to obtain the baggage barcode corresponding to the target baggage;

[0109] Specifically, using a high-definition industrial camera to perform barcode recognition on the baggage tag of the target baggage of the current passenger located in the baggage detection area to obtain the baggage barcode corresponding to the target baggage includes: the high-definition industrial camera is built-in with a high-definition camera mechanism, an image processing mechanism, a barcode output mechanism, and a parallel data bus;

[0110] Use a depth vision camera to detect the shape and size of the target baggage, and when the shape and size of the target baggage both meet the check-in standard, send a first detection signal, otherwise, send a second detection signal;

[0111] Exemplarily, a depth vision camera is used to detect the shape and size of the target luggage, and when the shape and size of the target luggage both meet the consignment standard, a first detection signal is sent; otherwise, a second detection signal is sent, including: the depth vision camera is internally provided with a depth sensor and a vision sensor, and the depth sensor and the vision sensor are integrated together to form the sensing component of the depth vision camera;

[0112] And exemplarily, using a depth vision camera to detect the shape and size of the target luggage, and when the shape and size of the target luggage both meet the consignment standard, a first detection signal is sent; otherwise, a second detection signal is sent, further including: the depth vision camera is also internally provided with an image detection component for intelligently detecting the shape and size of the target luggage based on various visual data collected. Since the intelligent detection of the shape and size of objects in the imaging area belongs to the conventional technology in the field of artificial intelligence, it will not be elaborated here;

[0113] Collect the current scan image obtained by the X-ray scanner scanning the target luggage, analyze the respective image areas occupied by each object in the current scan image, and perform the following intelligent recognition operations on each object as the object to be recognized: use the convolutional neural network after multiple learnings to respectively correspond to each cyan component value, each magenta component value, each yellow component value, and each black component value corresponding to each pixel point in the image area corresponding to the object to be recognized, each vertical coordinate value and each horizontal coordinate value corresponding to each pixel point in the image area corresponding to the object to be recognized, multiple pixel value gradients respectively corresponding to multiple edge pixel points in the image area corresponding to the object to be recognized, the number of pixel rows, the number of pixel columns of the current scan image, and the signal-to-noise ratio of the current scan image to intelligently recognize the object type corresponding to the object to be recognized;

[0114] Exemplarily, a programmable logic device is used to use the convolutional neural network after multiple learnings to respectively correspond to each cyan component value, each magenta component value, each yellow component value, and each black component value corresponding to each pixel point in the image area corresponding to the object to be recognized, each vertical coordinate value and each horizontal coordinate value corresponding to each pixel point in the image area corresponding to the object to be recognized, multiple pixel value gradients respectively corresponding to multiple edge pixel points in the image area corresponding to the object to be recognized, the number of pixel rows, the number of pixel columns of the current scan image, and the signal-to-noise ratio of the current scan image to intelligently recognize the object type corresponding to the object to be recognized;

[0115] When there is more than one type of prohibited item among the types of each item corresponding to each item in the current scanned image, a first recognition signal is sent; otherwise, a second recognition signal is sent.

[0116] When the second detection signal or the first recognition signal is received, the target luggage is sent back to the luggage detection area, and when the first detection signal or the second recognition signal is received, the target luggage is transported to the conveyor belt to be sent to the luggage transportation system leading to the airport freight vehicle.

[0117] Among them, when there is more than one type of prohibited item among the types of each item corresponding to each item in the current scanned image, a first recognition signal is sent; otherwise, a second recognition signal is sent, including: the types of prohibited items include lighters, firearms, blasting materials, power banks or knives.

[0118] Among them, using a convolutional neural network after multiple learning processes, based on each cyan component value, each magenta component value, each yellow component value, each black component value corresponding to each pixel point in the image area corresponding to the item to be recognized, each vertical coordinate value and each horizontal coordinate value corresponding to each pixel point in the image area corresponding to the item to be recognized, multiple pixel value gradients corresponding to multiple edge pixel points in the image area corresponding to the item to be recognized, the number of pixel rows and pixel columns of the current scanned image, and the signal-to-noise ratio of the current scanned image to intelligently recognize the type of item corresponding to the item to be recognized, including: the number of learning processes of the convolutional neural network is positively correlated with the scanning resolution of the X-ray scanner.

[0119] Exemplarily, the number of learning processes of the convolutional neural network being positively correlated with the scanning resolution of the X-ray scanner includes: the higher the scanning resolution of the X-ray scanner, the more learning processes the convolutional neural network has gone through.

[0120] Among them, using a convolutional neural network after multiple learning processes to intelligently identify the object type corresponding to the object to be recognized based on the cyan component values, magenta component values, yellow component values, and black component values corresponding to each pixel point in the image area corresponding to the object to be recognized, the vertical coordinate values and horizontal coordinate values corresponding to each pixel point in the image area corresponding to the object to be recognized, the pixel value gradients corresponding to multiple edge pixel points in the image area corresponding to the object to be recognized, the number of pixel rows and pixel columns in the current scanned image, and the signal-to-noise ratio of the current scanned image further includes: in each learning action performed on the convolutional neural network, using the object type of the object already recognized in the historical scanned image obtained by the X-ray scanner as the single output content of the convolutional neural network, and using the cyan component values, magenta component values, yellow component values, and black component values corresponding to each pixel point in the image area occupied by the already recognized object in the historical scanned image, the vertical coordinate values and horizontal coordinate values corresponding to each pixel point in the image area occupied by the already recognized object in the historical scanned image, the pixel value gradients corresponding to multiple edge pixel points in the image area occupied by the already recognized object in the historical scanned image, the number of pixel rows and pixel columns in the historical scanned image, and the signal-to-noise ratio of the historical scanned image as the item-by-item output content of the convolutional neural network, and completing the current learning action performed on the convolutional neural network;

[0121] Specifically, among the single cyan component value, single magenta component value, single yellow component value, and single black component value corresponding to each pixel point, the value range of any color component value is between 0 and 255;

[0122] And specifically, each pixel point has a corresponding single cyan component value, i.e., single C component value, single magenta component value, i.e., single M component value, single yellow component value, i.e., single Y component value, and single black component value, i.e., single K component value in the CMYK color space;

[0123] Among them, using a depth vision camera to detect the shape and size of the target luggage, and when both the shape and size of the target luggage meet the consignment standards, sending a first detection signal, otherwise, sending a second detection signal includes: using a depth vision camera to detect the shape of the target luggage based on a deep learning mode;

[0124] And among them, a depth vision camera is used to detect the shape and size of the target luggage, and when both the shape and size of the target luggage meet the consignment standard, a first detection signal is sent, otherwise, a second detection signal is sent. It also includes: using the depth vision camera to detect the size of the target luggage based on the collected depth information of the target luggage.

[0125] In addition, in an intelligent pre-inspection self-service luggage consignment terminal system and method based on visual image technology according to the present invention:

[0126] Parallelly inputting the respective cyan component values, respective magenta component values, respective yellow component values, and respective black component values corresponding to each pixel point in the image area corresponding to the object to be recognized, the respective vertical coordinate values and respective horizontal coordinate values corresponding to each pixel point in the image area corresponding to the object to be recognized, the respective pixel value gradients corresponding to multiple edge pixel points in the image area corresponding to the object to be recognized, the number of pixel rows and pixel columns in the current scanned image, and the signal-to-noise ratio of the current scanned image into the convolutional neural network after multiple learnings includes: performing octal numerical conversion on the respective cyan component values, respective magenta component values, respective yellow component values, and respective black component values corresponding to each pixel point in the image area corresponding to the object to be recognized, the respective vertical coordinate values and respective horizontal coordinate values corresponding to each pixel point in the image area corresponding to the object to be recognized, the respective pixel value gradients corresponding to multiple edge pixel points in the image area corresponding to the object to be recognized, the number of pixel rows and pixel columns in the current scanned image, and the signal-to-noise ratio of the current scanned image respectively, and then parallelly inputting them into the convolutional neural network after multiple learnings;

[0127] Exemplarily, after respectively performing octal numerical conversion on each cyan component value, each magenta component value, each yellow component value, each black component value corresponding to each pixel point in the image region corresponding to the object to be recognized, each vertical coordinate value and each horizontal coordinate value corresponding to each pixel point in the image region corresponding to the object to be recognized, multiple pixel value gradients respectively corresponding to multiple edge pixel points in the image region corresponding to the object to be recognized, the number of pixel rows and pixel columns of the current scanned image, and the signal-to-noise ratio of the current scanned image, and then inputting them in parallel to the convolutional neural network after multiple trainings, it includes: first, using a numerical conversion module to respectively perform octal numerical conversion on each cyan component value, each magenta component value, each yellow component value, each black component value corresponding to each pixel point in the image region corresponding to the object to be recognized, each vertical coordinate value and each horizontal coordinate value corresponding to each pixel point in the image region corresponding to the object to be recognized, multiple pixel value gradients respectively corresponding to multiple edge pixel points in the image region corresponding to the object to be recognized, the number of pixel rows and pixel columns of the current scanned image, and the signal-to-noise ratio of the current scanned image;

[0128] And exemplarily, after respectively performing octal numerical conversion on each cyan component value, each magenta component value, each yellow component value, each black component value corresponding to each pixel point in the image region corresponding to the object to be recognized, each vertical coordinate value and each horizontal coordinate value corresponding to each pixel point in the image region corresponding to the object to be recognized, multiple pixel value gradients respectively corresponding to multiple edge pixel points in the image region corresponding to the object to be recognized, the number of pixel rows and pixel columns of the current scanned image, and the signal-to-noise ratio of the current scanned image, and then inputting them in parallel to the convolutional neural network after multiple trainings, it further includes: then using a parallel control module to input in parallel to the convolutional neural network after multiple trainings each cyan component value, each magenta component value, each yellow component value, each black component value corresponding to each pixel point in the image region corresponding to the object to be recognized, each vertical coordinate value and each horizontal coordinate value corresponding to each pixel point in the image region corresponding to the object to be recognized, multiple pixel value gradients respectively corresponding to multiple edge pixel points in the image region corresponding to the object to be recognized, the number of pixel rows and pixel columns of the current scanned image, and the signal-to-noise ratio of the current scanned image that have respectively undergone octal numerical conversion;

[0129] And among them, running the convolutional neural network after multiple learnings to obtain the object type corresponding to the object to be recognized output by the convolutional neural network after multiple learnings includes: the object type corresponding to the object to be recognized output by the convolutional neural network after multiple learnings is in the form of an octal numerical representation.

[0130] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, method, article or device including said element.

[0131] Each embodiment in this specification is described in a related manner. For the same and similar parts among the embodiments, reference can be made to each other. The key point of each embodiment is to illustrate the differences from other embodiments. In particular, for the device / electronic device / computer-readable storage medium / computer program product embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0132] The above is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.

Claims

1. An intelligent pre-inspection self-service baggage check-in terminal system based on visual image technology, characterized in that: The terminal system comprises: The document scanning module is used to scan the identity document of the current passenger to obtain the identity information of the current passenger when the current passenger checks in the luggage, and print the passenger boarding pass and luggage tag corresponding to the obtained identity information; A barcode recognition module, connected to the document scanning module, is used to use a high-definition industrial camera to perform barcode recognition on the luggage bar of the current passenger's target luggage located in the luggage detection area to obtain a luggage barcode corresponding to the target luggage; a size detection module, connected to the barcode recognition module, for detecting the shape and size of the target luggage using a depth vision camera, and issuing a first detection signal when the shape and size of the target luggage meet the consignment standard, otherwise, issuing a second detection signal; an intelligent recognition module, connected to the size detection module, for collecting a current scanned image obtained by an X-ray scanner scanning the target baggage, analyzing the image regions respectively occupied by the objects in the current scanned image, and performing the following intelligent recognition operation on each object as an object to be recognized: using a convolutional neural network after multiple learnings to intelligently recognize the object type corresponding to the object to be recognized based on the respective cyan component values, the respective magenta component values, the respective yellow component values, and the respective black component values ​​respectively corresponding to the respective pixel points in the image region corresponding to the object to be recognized, the respective vertical coordinate values ​​and the respective horizontal coordinate values ​​respectively corresponding to the respective pixel points in the image region corresponding to the object to be recognized, the respective pixel value gradients respectively corresponding to the plurality of edge pixel points in the image region corresponding to the object to be recognized, the number of pixel rows and the number of pixel columns in the current scanned image, and the signal-to-noise ratio of the current scanned image; the intelligent recognition module is further configured to, when there is more than one prohibited article type in the respective object types respectively corresponding to the respective objects in the current scanned image, send a first recognition signal, otherwise, send a second recognition signal.

2. The intelligent pre-inspection self-service baggage check-in terminal system based on visual image technology as claimed in claim 1, characterized in that: Using a convolutional neural network that has undergone multiple learnings to intelligently identify the object type corresponding to the object to be identified based on each cyan component value, each magenta component value, each yellow component value and each black component value corresponding to each pixel point in the image area corresponding to the object to be identified, each vertical coordinate value and each horizontal coordinate value corresponding to each pixel point in the image area corresponding to the object to be identified, multiple pixel value gradients corresponding to multiple edge pixels in the image area corresponding to the object to be identified, the number of pixel rows and the number of pixel columns in the current scanning screen, and the signal-to-noise ratio of the current scanning screen, the convolutional neural network includes: the number of learning times of the convolutional neural network is positively correlated with the scanning resolution of the X-ray scanner; Wherein, using a convolutional neural network that has undergone multiple learnings to intelligently identify the object type corresponding to the object to be identified based on each cyan component value, each magenta component value, each yellow component value and each black component value corresponding to each pixel point in the image area corresponding to the object to be identified, each vertical coordinate value and each horizontal coordinate value corresponding to each pixel point in the image area corresponding to the object to be identified, multiple pixel value gradients corresponding to multiple edge pixels in the image area corresponding to the object to be identified, the number of pixel rows and the number of pixel columns in the current scanning screen and the signal-to-noise ratio of the current scanning screen also includes: in each learning action performed on the convolutional neural network, the number of identified objects in the historical scanning screen obtained by the historical scanning of the X-ray scanner is The object type is used as the single output content of the convolutional neural network, and the cyan component values, magenta component values, yellow component values ​​and black component values ​​corresponding to each pixel point of the image area occupied by the identified object in the historical scanning picture, the vertical coordinate values ​​and horizontal coordinate values ​​corresponding to each pixel point of the image area occupied by the identified object in the historical scanning picture, the multiple pixel value gradients corresponding to multiple edge pixels in the image area occupied by the identified object in the historical scanning picture, the number of pixel rows, the number of pixel columns and the signal-to-noise ratio of the historical scanning picture are used as the output content of the convolutional neural network one by one to complete the current learning action performed on the convolutional neural network.

3. The intelligent pre-inspection self-service baggage check-in terminal system based on visual image technology as claimed in claim 2, characterized in that: in, Using a deep vision camera to detect the shape and size of the target luggage, and when the shape and size of the target luggage meet the consignment standard, issuing a first detection signal, otherwise, issuing a second detection signal includes: using a deep vision camera to detect the shape of the target luggage based on a deep learning model; Among them, using a depth vision camera to detect the shape and size of the target luggage, and when the shape and size of the target luggage meet the consignment standards, issuing a first detection signal, otherwise, issuing a second detection signal also includes: using a depth vision camera to detect the size of the target luggage based on the collected depth information of the target luggage.

4. The intelligent pre-inspection self-service baggage check-in terminal system based on visual image technology as claimed in claim 3, characterized in that: The terminal system further includes: a baggage conveying module, connected to the size detection module and the intelligent identification module respectively, and configured to return the target baggage to a baggage detection area upon receiving the second detection signal or the first identification signal; The baggage conveying module is further configured to transfer the target baggage to a conveyor belt conveyor to a baggage sorting system upon receiving the first detection signal or the second identification signal; Among them, the intelligent recognition module is also used to issue a first recognition signal when there is more than one type of prohibited item in the object types corresponding to each object in the current scanning screen, otherwise, the second recognition signal is issued, including: the prohibited item types include lighters, oversized cosmetics and power banks.

5. The intelligent pre-inspection self-service baggage check-in terminal system based on visual image technology as claimed in claim 3, characterized in that: The terminal system further includes: The on-site warning module is connected to the size detection module and the intelligent identification module respectively, and is used to perform on-site broadcasting of warning information corresponding to prohibited item identification when the second detection signal or the first identification signal is received.

6. The intelligent pre-inspection self-service baggage check-in terminal system based on visual image technology as claimed in claim 3, characterized in that: The terminal system further includes: The interactive operation module is used to display the passenger interactive operation interface and provide an interactive operation interface for the current passenger to interact with information.

7. The intelligent pre-inspection self-service baggage check-in terminal system based on visual image technology as claimed in claim 3, characterized in that: The terminal system further includes: The model storage module is connected to the intelligent recognition module and is used to receive various model parameters of the convolutional neural network, i.e., the intelligent recognition model, after multiple learnings, and complete the model storage of the intelligent recognition model by storing the various model parameters of the intelligent recognition model.

8. The intelligent pre-inspection self-service baggage check-in terminal system based on visual image technology according to any one of claims 3 to 7, characterized in that: Using a convolutional neural network that has undergone multiple learnings to intelligently identify the object type corresponding to the object to be identified based on each cyan component value, each magenta component value, each yellow component value and each black component value corresponding to each pixel point of the image area corresponding to the object to be identified, each vertical coordinate value and each horizontal coordinate value corresponding to each pixel point of the image area corresponding to the object to be identified, multiple pixel value gradients corresponding to multiple edge pixels in the image area corresponding to the object to be identified, the number of pixel rows and the number of pixel columns of the current scanning picture, and the signal-to-noise ratio of the current scanning picture, further comprising: inputting each cyan component value, each magenta component value, each yellow component value and each black component value corresponding to each pixel point of the image area corresponding to the object to be identified, each vertical coordinate value and each horizontal coordinate value corresponding to each pixel point of the image area corresponding to the object to be identified, multiple pixel value gradients corresponding to multiple edge pixels in the image area corresponding to the object to be identified, the number of pixel rows and the number of pixel columns of the current scanning picture, and the signal-to-noise ratio of the current scanning picture into the convolutional neural network that has undergone multiple learnings in parallel; Using a convolutional neural network that has undergone multiple learnings to intelligently identify the object type corresponding to the object to be identified based on each cyan component value, each magenta component value, each yellow component value and each black component value corresponding to each pixel point in the image area corresponding to the object to be identified, each vertical coordinate value and each horizontal coordinate value corresponding to each pixel point in the image area corresponding to the object to be identified, multiple pixel value gradients corresponding to multiple edge pixels in the image area corresponding to the object to be identified, the number of pixel rows, the number of pixel columns and the signal-to-noise ratio of the current scanning image, also includes: running the convolutional neural network that has undergone multiple learnings to obtain the object type corresponding to the object to be identified output by the convolutional neural network that has undergone multiple learnings.

9. The intelligent pre-inspection self-service baggage check-in terminal system based on visual image technology according to any one of claims 3 to 7, characterized in that: The number of learning times of the convolutional neural network and the scanning resolution of the X-ray scanner are positively correlated, including: using an information conversion function to represent the information conversion relationship of the number of learning times of the convolutional neural network and the scanning resolution of the X-ray scanner being positively correlated; The information conversion relationship of using an information conversion function to represent the positive correlation between the number of learning times of the convolutional neural network and the scanning resolution of the X-ray scanner includes: in the information conversion function, the scanning resolution of the X-ray scanner is the input information of the information conversion function; Among them, the information conversion relationship that uses an information conversion function to represent the positive correlation between the number of learning times of the convolutional neural network and the scanning resolution of the X-ray scanner also includes: in the information conversion function, the number of learning times of the convolutional neural network corresponding to the scanning resolution of the X-ray scanner is the output information of the information conversion function.

10. An intelligent pre-inspection self-service baggage check-in method based on visual image technology, characterized in that: The method comprises: When the current passenger checks in the baggage, the current passenger's ID card is scanned to obtain the current passenger's identity information, and the passenger boarding pass and baggage tag corresponding to the obtained identity information are printed; Use a high-definition industrial camera to perform barcode recognition on the baggage tag of the current passenger's target baggage located in the baggage inspection area to obtain the baggage barcode corresponding to the target baggage; Using a depth vision camera to detect the shape and size of the target luggage, and when the shape and size of the target luggage meet the consignment standard, a first detection signal is issued, otherwise, a second detection signal is issued; The current scanned image obtained by the X-ray scanner scanning the target baggage is collected, and each image area occupied by each object in the current scanned image is analyzed, and each object is used as an object to be identified to perform the following intelligent identification operation: a convolutional neural network that has undergone multiple learnings is used to intelligently identify the object type corresponding to the object to be identified based on each cyan component value, each magenta component value, each yellow component value and each black component value corresponding to each pixel point in the image area corresponding to the object to be identified, each vertical coordinate value and each horizontal coordinate value corresponding to each pixel point in the image area corresponding to the object to be identified, multiple pixel value gradients corresponding to multiple edge pixels in the image area corresponding to the object to be identified, the number of pixel rows and the number of pixel columns in the current scanned image, and the signal-to-noise ratio of the current scanned image; When there is more than one prohibited article type in each of the object types corresponding to each object in the current scanning image, a first identification signal is issued; otherwise, a second identification signal is issued; When the second detection signal or the first identification signal is received, the target baggage is returned to the baggage detection area; and when the first detection signal or the second identification signal is received, the target baggage is transferred to the conveyor belt conveyor to be sent to the transportation system leading to the airport freight vehicle; Among them, when there is more than one prohibited item type in the object types corresponding to the objects in the current scanning screen, a first identification signal is issued, otherwise, a second identification signal is issued, including: the prohibited item types include lighters, firearms, blasting equipment, power banks or knives.

Images