Early machine inspection luggage identification system and method

Abstract

The present disclosure provides an early machine inspection baggage identification system, comprising: a baggage transport platform configured to transport baggage in a baggage transport direction; the security inspection equipment is configured to detect luggage and generate a target security inspection result; the appearance acquisition equipment at least comprises first appearance acquisition equipment and second appearance acquisition equipment, the first appearance acquisition equipment is arranged at the upstream of the security inspection equipment and is used for acquiring a first appearance image of the luggage, and the second appearance acquisition equipment is arranged at the upstream of the luggage extraction area and is used for acquiring a second appearance image of the luggage; the control device is in communication connection with the security inspection equipment and the appearance acquisition equipment; wherein the control device is configured to perform association matching on the target security check result, the first appearance image and the second appearance image, and form interception prompt information of the luggage based on an association matching result.

Description

Technical Field

[0001] The present disclosure relates to the field of article security inspection, and in particular, to a pre-machine-inspected baggage identification system and method. Background Art

[0002] Baggage inspection is a core link in airports, customs and other important entry and exit sites, and its purpose is to ensure public safety and regulate the circulation management of goods and passengers. Existing baggage inspection systems usually use pre-machine inspection technology to perform perspective scanning and problem identification on checked baggage, and then perform subsequent processing on a small amount of interesting baggage.

[0003] At present, the marking of interesting luggage mainly relies on physical means, which requires supervisors to manually operate the marking after the luggage is identified. Therefore, this method relies on the subjective judgment ability of the supervisor, which is prone to marking errors or missed inspections. Another covert marking method is to identify the interesting luggage through electronic tags. When the marked luggage reaches the electronic tag sensing position, the system will trigger an alarm to notify the supervisor to intercept it. However, electronic tag sensing devices are usually installed in personnel passages, where there is a concentrated flow of people and a high density of luggage, making it difficult for staff to accurately identify specific interesting luggage in a timely manner during actual interception, increasing the risk of congestion. Summary of the invention

[0004] In order to solve the above technical problems, the embodiments of the present disclosure provide a system and method for identifying baggage before machine inspection. By collecting appearance images of the baggage before it enters the security inspection equipment and when the baggage is about to enter the pick-up area, it is possible to achieve dynamic tracking of the baggage throughout the entire process, improve the accuracy of identifying problematic baggage, and avoid misjudgment and missed judgment problems caused by relying on physical markings or electronic tags.

[0005] In view of at least one aspect of the above technical problems, the present disclosure provides a system and method for identifying baggage prior to machine inspection.

[0006] According to a first aspect of the present disclosure, a pre-machine-inspected baggage identification system is provided, comprising: a baggage conveying platform, the baggage conveying platform being configured to convey baggage along a baggage conveying direction; a security inspection device, the security inspection device being configured to inspect the baggage and generate a target security inspection result; an appearance acquisition device, the appearance acquisition device comprising at least a first appearance acquisition device and a second appearance acquisition device, wherein the first appearance acquisition device is arranged upstream of the security inspection device and is used to acquire a first appearance image of the baggage, and the second appearance acquisition device is arranged upstream of a baggage claim area and is used to acquire a second appearance image of the baggage; and a control device, the control device being communicatively connected with the security inspection device and the appearance acquisition device; wherein the control device is configured to perform association matching on the target security inspection result, the first appearance image and the second appearance image, and form interception prompt information of the baggage based on the result of the association matching.

[0007] According to some exemplary embodiments, the appearance acquisition device includes: a camera configured to capture an appearance image of the luggage in a luggage appearance acquisition area; and a photoelectric sensor configured to detect an arrival status of the luggage and trigger the camera to capture.

[0008] According to some exemplary embodiments, the appearance collection device is configured as an appearance collection box, and the appearance collection device also includes: a light source; a supporting structure, wherein the supporting structure is configured to fix the light source, the camera and the photoelectric sensor inside the appearance collection box and / or above the luggage transfer path.

[0009] According to some exemplary embodiments, during the association matching process, the control device is configured to: associate and match the first appearance image with the target security inspection result, generate association information, and store the association information in a time queue; based on the time queue, associate and match the association information with the second appearance image.

[0010] According to some exemplary embodiments, the control device is further configured to: extract a first appearance feature of the first appearance image, generate entrance portrait information by combining the first appearance feature and the target security inspection result, and store the entrance portrait information in a time queue, wherein the time queue is sorted by baggage transfer time; extract a second appearance feature of the second appearance image, and calculate the corresponding entrance time window according to the baggage transfer speed, and obtain the target entrance portrait information matching the entrance time window from the time queue; associate and match the second appearance feature with the target entrance portrait information to generate an association matching result.

[0011] According to some exemplary embodiments, in the process of forming the interception prompt information of the luggage based on the result of the association matching, the control device is configured to: generate the arrival information of the luggage based on the result of the association matching; and generate the interception prompt information in the form of a visual prompt based on the arrival information.

[0012] According to some exemplary embodiments, the arrival information is set as differentiated information for different luggage.

[0013] According to some exemplary embodiments, the appearance acquisition device is configured such that, in response to the arrival of luggage, the photoelectric sensor triggers the camera to continuously take a plurality of photos within a preset time interval.

[0014] According to some exemplary embodiments, the appearance acquisition device further includes an analysis device, which is configured to perform quality analysis on a plurality of photos taken continuously, and select photos of target quality as the first appearance image or the second appearance image.

[0015] According to some exemplary embodiments, the camera includes a plurality of cameras arranged at different positions of the luggage appearance collection area.

[0016] According to some exemplary embodiments, the light source includes a plurality of light sources arranged at different positions of the appearance collection box.

[0017] According to some exemplary embodiments, the baggage conveying platform includes a baggage entrance platform and a baggage exit platform that are arranged opposite to each other, the first appearance collection device is arranged on the baggage entrance platform, and the second appearance collection device is arranged on the baggage exit platform.

[0018] According to some exemplary embodiments, the baggage identification system further includes an execution terminal, which is communicatively connected to the control device and is used to receive and display the interception prompt information.

[0019] According to some exemplary embodiments, the execution terminal is configured to display the location information and appearance image of the corresponding luggage after receiving the interception prompt information.

[0020] According to some exemplary embodiments, the analysis device is further configured to: comprehensively score multiple photos taken continuously based on image clarity, brightness balance and contrast; and use photos whose comprehensive scores exceed a preset threshold as the first appearance image or the second appearance image.

[0021] According to a second aspect of the present disclosure, a method for identifying baggage for pre-machine inspection is provided, comprising: collecting a first appearance image of the baggage by a first appearance acquisition device, wherein the first appearance acquisition device is arranged upstream of a security inspection device along a baggage conveying direction; inspecting the baggage by using the security inspection device and generating a target security inspection result; collecting a second appearance image of the baggage by a second appearance acquisition device, wherein the second appearance acquisition device is arranged upstream of a baggage claiming area along the baggage conveying direction; and associating and matching the target security inspection result, the first appearance image and the second appearance image, and forming interception prompt information of the baggage based on the result of the associative matching.

[0022] According to some exemplary embodiments, the associating and matching the target security inspection result, the first appearance image, and the second appearance image specifically includes: extracting a first appearance feature of the first appearance image, generating entrance portrait information by combining the first appearance feature and the target security inspection result, and placing the entrance portrait information into a time queue sorted by baggage transfer time; extracting a second appearance feature of the second appearance image, calculating a corresponding entrance time window according to the baggage transfer speed, and obtaining target entrance portrait information matching the entrance time window from the time queue; and associating and matching the second appearance feature with the target entrance portrait information to generate an associating and matching result.

[0023] According to the pre-machine inspection baggage identification system of the disclosed embodiment, by setting the first appearance collection device and the second appearance collection device at different positions of the baggage conveying path, the whole process tracking and multi-point feature collection of the baggage are realized, ensuring the accurate positioning and identification of the problematic baggage. Compared with the traditional physical marking or electronic tag method, the system can dynamically track the location of the baggage without relying on physical marking, and there are no consumables generated by marking the baggage; at the same time, by advancing the inspection location of special baggage to the baggage claim area, the execution process of the staff can be optimized, and the congestion during the passenger clearance process can be reduced, thereby improving the intelligence and efficiency of baggage supervision. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 is a structural schematic diagram of a pre-machine-inspected baggage identification system according to some exemplary embodiments of the present disclosure;

[0025] Figure 2 is a hardware block diagram of a pre-machine-inspected baggage identification system according to some exemplary embodiments of the present disclosure;

[0026] Figure 3 yes Figure 2 The hardware processing flow chart of the pre-machine-checked baggage identification system;

[0027] Figure 4is a flowchart of a method for identifying baggage for pre-machine inspection according to an exemplary embodiment of the present disclosure; and

[0028] Figure 5 A block diagram of an electronic device suitable for implementing the above method according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0029] In order to make the objectives, technical solutions and advantages of the present disclosure more clearly understood, the present disclosure is further described in detail below in combination with specific embodiments and with reference to the accompanying drawings.

[0030] However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, the description of the known technology is omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0031] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The term "comprising" used herein indicates the existence of features, steps, operations, but does not exclude the existence or addition of one or more other features.

[0032] In the case of using expressions such as "at least one of A, B, and C, etc.", it should generally be interpreted in accordance with the meaning of the expression generally understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.). In the case of using expressions such as "at least one of A, B, or C, etc.", it should generally be interpreted in accordance with the meaning of the expression generally understood by those skilled in the art (for example, "a system having at least one of A, B, or C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0033] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0034] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0035] Baggage inspection is a key link in ensuring public safety and regulating the flow of goods and passengers at airports, customs and other important entry and exit sites. Existing baggage inspection systems usually use pre-machine inspection technology to screen out a small amount of interesting luggage containing prohibited items or suspected risk items through perspective scanning and problem identification of checked baggage, and conduct subsequent inspection and interception.

[0036] The applicant has found through research that the existing technology still has obvious limitations in the marking and tracking of luggage of interest.

[0037] Specifically, currently, the marking of luggage of interest mainly relies on physical means, such as customs locks, wrapping tape, etc. This method requires supervisors to manually mark the luggage of interest after luggage identification. The effect and accuracy of the marking often rely on the subjective judgment of the supervisor, which is prone to marking errors or missed inspections. In addition, in the subsequent inspection process, physically marked luggage usually needs to be manually observed and tracked by supervisors after the passengers pick up their luggage. This not only increases the law enforcement burden of supervisors, but may also lead to missed inspections of luggage of interest due to unclear markings or high passenger mobility. At the same time, areas where passengers collect their luggage are prone to traffic congestion due to supervisory operations, affecting customs clearance efficiency and user experience.

[0038] Another marking method is to covertly mark the luggage of interest with an electronic tag. When the marked luggage reaches the location of the electronic tag sensing device, the system will trigger an alarm and notify the supervisor to intercept it. However, there are many limitations in the actual application of electronic tags: the sensing device is usually installed in the personnel passage, which is an area with dense traffic and large amount of luggage, which makes it difficult for supervisors to accurately identify specific luggage of interest in a timely manner. In addition, the electronic tag marking method lacks the ability to track the location of the luggage throughout the entire process. Once the tag is lost or falls off or is damaged, it may cause the luggage of interest to be missed, misdetected, or unable to be accurately located.

[0039] Based on this, the embodiments of the present disclosure provide a system and method for identifying baggage for machine inspection in advance, which dynamically tracks the appearance characteristics and security inspection conclusions of the baggage throughout the entire process, locates the position and status of the baggage of interest in real time, and generates accurate interception prompt information before the baggage arrives at the baggage claim area, so as to facilitate the staff to implement efficient interception of the baggage of interest in advance and reduce the risks of missed inspection, false inspection and congestion in the exit area.

[0040] The following explanation will be given by taking the luggage arriving at the customs as an example. It should be noted that the pre-machine inspection luggage identification system disclosed in the present invention can also be used in places such as airports and stations, and the present invention does not limit the specific application scenarios of the pre-machine inspection luggage identification system. In such places, if pedestrians have a certain trajectory displacement and time period after picking up items and before the items are specially inspected, they are all within the scope of the present invention.

[0041] Figure 1 1 is a schematic diagram of the structure of a pre-machine-inspected baggage identification system according to some exemplary embodiments of the present disclosure. Figure 2 is a hardware block diagram of a pre-machine-inspected baggage identification system according to some exemplary embodiments of the present disclosure. Figure 3 yes Figure 2 The hardware processing flow chart of the pre-machine-checked baggage identification system.

[0042] Combined with reference Figure 1 , Figure 2 and Figure 3 According to some exemplary embodiments of the present disclosure, a pre-machine-inspected baggage identification system 100 may include a baggage conveying platform 1, a security inspection device 2, an appearance collection device 3, and a baggage carousel 4.

[0043] In the embodiment of the present disclosure, the baggage conveying platform 1 is used as the basic structure for conveying baggage in the pre-machine inspection baggage identification system 100, and provides a stable conveying path and support structure for the operation of the appearance collection device 3, the security inspection device 2 and other related components. The baggage conveying platform 1 can be set from the initial input point (entrance) of the baggage, through the security inspection device area and the appearance collection area, to the final output point (exit) of the baggage, and connected to the baggage carousel 4 in the baggage claim area.

[0044] The baggage conveying platform 1 can be used for baggage transfer via a conveyor belt assembly. The transmission system of the conveyor belt assembly can adopt a high-precision drive device to maintain a constant speed under various load conditions and avoid speed fluctuations caused by uneven baggage weight, size or distribution.

[0045] In some exemplary embodiments, the support structure of the baggage conveying platform 1 can be made of high-strength materials, such as stainless steel or aluminum alloy, so as to maintain high durability and stability in complex operating environments. Furthermore, in order to improve the stability of the conveying path, the baggage conveying platform 1 can also be provided with a positioning base to facilitate the positioning and installation of the appearance collection device 3 and the security inspection device 2, so that each device can maintain the consistency of relative position in a fixed state.

[0046] In some exemplary embodiments, the overall structure of the baggage conveying platform 1 can be designed as a modular and expandable structure. That is, the transmission path of the baggage conveying platform 1 can be flexibly adjusted in length, width and height according to site requirements, and can support a multi-stage layout while maintaining the overall continuity of the system operation.

[0047] According to an embodiment of the present disclosure, the baggage conveying platform 1 can be designed to include a baggage entrance platform 11, a baggage intermediate conveying path 12 and a baggage exit platform 13, so as to separate the appearance collection area and the security scanning area to meet the baggage collection and detection requirements of multiple areas.

[0048] Continue to combine references Figure 1 , Figure 2 and Figure 3 The security inspection device 2 is arranged in the middle area of ​​the baggage conveying platform 1, and is connected to the baggage entrance platform 11 and the baggage intermediate conveying path 12 respectively. The security inspection device 2 is used to scan and analyze the items inside the baggage and generate security inspection results. Among them, the security inspection results can include ordinary security inspection results and target security inspection results.

[0049] Exemplarily, the security inspection device 2 can use X-ray technology or non-contact imaging technology to generate multi-view imaging data of the luggage through high-frequency perspective scanning, and quickly capture the image information of the items inside the luggage through the built-in detector array to generate a high-resolution perspective image. The perspective image generated by the scan can be analyzed in real time by the security inspection analysis module built into the security inspection device 2. For example, the security inspection analysis module can integrate intelligent recognition algorithms based on machine learning and traditional image processing methods to extract and classify the features of items in the image (such as density, shape, material, etc.). Based on the results of extraction and classification, the security inspection analysis module can identify contraband and high-risk items in the luggage, such as metal weapons, dangerous chemicals or other controlled items, and output target security inspection results related to the characteristics of the items, that is, obtain the luggage of interest.

[0050] In some exemplary embodiments, the security analysis module may be provided with a risk determination module for further analysis and evaluation. For example, the risk determination module may perform a risk level assessment on suspicious items in the luggage based on the data output by the image processing module in combination with a preset risk rule library and determination model.

[0051] In some exemplary embodiments, the security inspection device 2 may adopt a dynamic scanning mode and synchronize in real time with the conveying speed of the baggage conveying platform 1. In order to improve the adaptability and stability of the system, the security inspection device 2 may also be provided with an adjustment mechanism. For example, when the items inside the baggage are stacked or the density is high, the security inspection device 2 may automatically adjust the scanning parameters, such as the radiation energy or the image contrast, to ensure the imaging quality of the high-density area.

[0052] It should be noted that in this disclosure, interesting luggage refers to luggage that is marked as having special handling requirements by security inspection equipment or associated matching results during the luggage inspection process. For example: possible contraband (such as flammable and explosive items, controlled knives, etc.) or suspected high-risk items are detected in the luggage; special supervision is required in specific scenarios (such as luggage carrying a large number of valuables); the luggage has abnormal appearance characteristics, etc.

[0053] Correspondingly, in the present disclosure, the target security inspection result generated by the security inspection device 2 may represent the identification and screening result of the baggage of interest, including specific identification information of the baggage of interest, such as the characteristic information, risk level and processing priority of risk items, so as to achieve focused processing of the baggage of interest in the subsequent process.

[0054] Reference Figure 1 It can be seen that, different from the prior art, the embodiment of the present disclosure realizes the full process tracking of luggage by collecting multiple appearance images of luggage by the appearance collection device 3. The appearance collection device 3 may include a camera 301 and a photoelectric sensor 302. The camera 301 may be configured in the luggage appearance collection area of ​​the luggage entrance platform 11 and the luggage exit platform 13, and is used to capture the appearance image of the luggage. The photoelectric sensor 302 is an auxiliary detection component of the appearance collection device 3, and is used to monitor the arrival status of the luggage in real time and trigger the camera to shoot.

[0055] In some exemplary embodiments, the photoelectric sensor 302 may be set at a specific position on the baggage transfer path, such as the middle position between the baggage entrance platform 11 and the baggage exit platform 13, above or on the side of the conveyor belt. When the baggage passes through the appearance collection area, the photoelectric sensor 302 may sense the edge position of the baggage, and control the start and stop of the camera through a preset logic signal to ensure that the camera 301 only takes pictures when the baggage completely enters the collection area, thereby avoiding the occurrence of false or missed pictures. The photoelectric sensor 302 may also dynamically adjust the shooting frequency of the camera 301 according to the transmission speed of the baggage to ensure the synchronization and continuity of image collection.

[0056] In some exemplary embodiments, the appearance acquisition device 3 may be equipped with multiple cameras, which are arranged at different positions of the luggage appearance acquisition area, such as the top, side, and bottom, to collect complete appearance information of the luggage from multiple angles. The arrangement of multiple cameras enables the appearance acquisition device 3 to obtain all-round image data of the luggage, especially when dealing with complex-shaped or irregular luggage, multi-angle shooting significantly improves the integrity of the image and the accuracy of feature extraction.

[0057] Continue to refer to Figure 1In order to ensure the image acquisition quality under different light conditions, the appearance acquisition device 3 may further include a light source 303 and a supporting structure, and the appearance acquisition device 3 is configured to adopt a box structure of an appearance acquisition box to isolate natural light. Among them, the light source 303 can provide stable and uniform light irradiation, reducing the impact of changes in external ambient light on image quality. The supporting structure can be made of high-strength and durable materials, and is used to fix the light source 303, the camera 301 and the photoelectric sensor 302 at appropriate positions of the appearance acquisition box and / or the baggage transfer path. For example, the light source 303 and the camera 301 can be fixed to the top of the appearance acquisition box by the supporting structure, and the photoelectric sensor 302 can be fixed to the middle position of the appearance acquisition box on the baggage transfer path by the supporting structure.

[0058] In some exemplary embodiments, the light source 303 may be arranged in a multi-point manner, and its position and angle may be adapted to luggage of different sizes and shapes to ensure that the luggage can obtain uniform and sufficient lighting within the collection area.

[0059] Combined with reference Figure 1 and Figure 2 The appearance acquisition device 3 may include a first appearance acquisition device 31 and a second appearance acquisition device 32 .

[0060] Reference Figure 1 In this article, for the convenience of description, the baggage conveying direction x is defined. For example, the baggage conveying direction x corresponds to the transmission path of the baggage conveying platform 1, that is, the running track of the baggage. For example, the baggage conveying direction x starts from the baggage entrance and passes through the first appearance collection device 31; then, the baggage conveying direction x extends along the security inspection device 2; finally, the baggage conveying direction x passes through the second appearance collection device 32 and extends to the baggage carousel 4.

[0061] In some exemplary embodiments, the first appearance collection device 31 is arranged on the baggage entrance platform 11, upstream of the security inspection device 2 along the baggage conveying direction x; the second appearance collection device 32 is arranged on the baggage exit platform 13, upstream of the baggage carousel 4 along the baggage conveying direction x.

[0062] According to an embodiment of the present disclosure, the first appearance acquisition device 31 provided at the baggage entrance platform 11 can be used to acquire a first appearance image of the baggage entering the baggage conveying platform 1, and obtain the size, shape, color and other key feature information of the baggage. The second appearance acquisition device 32 provided at the baggage exit platform 13 can be used to acquire a second appearance image of the baggage when it is about to be conveyed. In other words, the second appearance acquisition device 32 can also capture the appearance changes that may occur to the baggage during the transmission process, such as possible displacement, appearance changes or loss of iconic features, etc., to assist in the final identification and positioning of the baggage.

[0063] It should be noted that in the embodiments of the present disclosure, the first appearance acquisition device 31 and the second appearance acquisition device 32 may have the same structure and implement the same function. For example, the first appearance acquisition device 31 and the second appearance acquisition device 32 may both be equipped with a camera and a photoelectric sensor to take photos of the arrived luggage. For example, the first appearance acquisition device 31 and the second appearance acquisition device 32 may be configured as a box structure and equipped with a camera, a photoelectric sensor, a light source and a supporting structure to reduce ambient light interference while taking photos of the arrived luggage and improve the quality of the captured pictures. The structures of the first appearance acquisition device 31 and the second appearance acquisition device 32 may also be different. For example, the positions of the light sources, cameras and photoelectric sensors of the two may be adjusted to different positions as needed.

[0064] Combined with reference Figure 2 and Figure 3 In response to the arrival of the luggage, the photoelectric sensor 302 can sense the luggage entering the collection area in real time and send a trigger signal to trigger the camera 301 to continuously take multiple photos at a fixed frequency within a preset time interval.

[0065] The multiple photos taken continuously by the camera may have different quality due to the movement state of the luggage, ambient lighting or other factors. In order to solve this problem, the appearance acquisition device 3 can be further equipped with an appearance analysis module to perform quality analysis on the multiple photos taken. The appearance analysis module can score each photo from the dimensions of clarity, contrast, brightness balance, etc. based on a preset quality evaluation algorithm, and use the photo with a comprehensive score exceeding a preset threshold as the first appearance image or the second appearance image.

[0066] Specifically, the quality assessment algorithm of the appearance analysis module can analyze the changes in different ambient light, luggage color and material. For example, when the luggage surface has reflective or complex textures, the appearance analysis module can identify and filter out blurred photos caused by light interference, ensuring that the selected target image has sufficient detail clarity. For example, the appearance analysis module can appropriately increase the weight of clarity in complex scenes, or give priority to images with higher brightness in low light conditions to meet actual operational needs.

[0067] In the embodiment of the present disclosure, the pre-machine-inspected baggage identification system 100 further includes a control device, which is in communication with the security inspection device 2 and the appearance acquisition device 3. The control device is configured to perform correlation matching on the target security inspection result generated by the security inspection device 2, the first appearance image and the second appearance image acquired by the appearance acquisition device 3, and form interception prompt information of the baggage of interest based on the result of the correlation matching.

[0068] Specifically, the control device can extract features of the first appearance image and the second appearance image and perform correlation analysis on the target security inspection results to construct a baggage identification and matching mechanism based on time window binding, thereby achieving full-process dynamic tracking and positioning of the baggage of interest.

[0069] It should be noted that the control device can operate in a centralized or independent mode. For example, the control device can simultaneously control the security inspection analysis module of the security inspection equipment and the appearance analysis module of the appearance collection equipment, thereby realizing a comprehensive analysis of the baggage information. Through centralized control, the control device can schedule the workflow of each module with a unified logic, ensuring that the information collection and processing steps of the baggage in the conveying path are consistent and coherent.

[0070] On the other hand, the control device can operate independently of the security analysis module and the appearance analysis module, providing greater flexibility. In this mode, the control device is mainly responsible for receiving and integrating the output results of each analysis module without directly intervening in its internal analysis process. For example, the security analysis module can operate independently and process the perspective scanning data in real time through the built-in machine learning algorithm and rule base; the appearance analysis module independently completes the screening of appearance images. After receiving these analysis results, the control device comprehensively processes them through technologies such as time window binding and feature matching to generate associated matching results and interception prompt information. Therefore, in this mode, the control device can effectively share the computational burden of each analysis module, while allowing each module to be independently optimized according to different task requirements.

[0071] In the embodiment of the present disclosure, during the process of correlation matching, the control device may be configured to: correlate and match the first appearance image with the target security inspection result, generate correlation information, and store the correlation information in the time queue; and correlate and match the correlation information with the second appearance image based on the time queue. That is, the first appearance image and the target security inspection result, the first appearance image, the target security inspection result, and the second appearance image are sequentially correlated and matched.

[0072] Specifically, refer to Figure 3 , the control device can be used to extract the first appearance feature of the luggage from the first appearance image, including size, shape, color, texture and other characteristic features. The first appearance feature is combined with the target security inspection result generated by the security inspection device 2 to generate the entrance portrait information. That is to say, the entrance portrait information not only contains the relevant data of the appearance feature, but also can record the timestamp of the luggage entering the luggage conveying platform 1 and the risk level and marking status related to the security inspection conclusion. The generated entrance portrait information can be stored in the time queue, where the time queue is sorted according to the transfer time of the luggage.

[0073] In response to the second appearance acquisition device 32 of the luggage being transmitted to the luggage exit platform 13, a second appearance image may be acquired and its second appearance features may be extracted. Similar to the first appearance features, the second appearance features include information such as the size, color and texture of the luggage, but may also include features reflecting the appearance changes that may occur to the luggage during the transportation process, such as damage, loss of iconic features or appearance contamination. Through the time window calculation module in the control device, the entrance time window corresponding to the second appearance image can be calculated according to the conveying speed of the luggage and the length of the conveying path. The entrance time window is used as a matching condition and compared with the entrance portrait information in the time queue to locate the target entrance portrait information that matches the entrance time window.

[0074] After matching the target entrance portrait information, the control device may further associate and match the second appearance feature with the first appearance feature in the target entrance portrait information. For example, based on a feature comparison algorithm, the association between the first appearance feature and the second appearance feature is determined by calculating the similarity between the two. If the similarity exceeds a preset threshold, it is considered that the current luggage matches the target entrance portrait information successfully, and an association matching result is generated. The association matching result may include the appearance images collected twice for the luggage, and the risk warning information for the luggage generated in combination with the target security inspection result.

[0075] According to the embodiments of the present disclosure, by collecting the first appearance image at the baggage entrance platform, collecting the second appearance image at the baggage exit platform and combining the security inspection conclusion generated by the security inspection equipment, the interception link can be advanced to the exit of the baggage conveyor belt to avoid congestion in passenger concentration areas. In addition, through the intelligent analysis of efficient appearance collection equipment and security inspection equipment combined with the control device, it is possible to avoid dependence on traditional physical marking methods, thereby reducing operating costs, reducing the demand for disposable consumables, and avoiding the additional workload caused by the procurement and management of consumables.

[0076] In some exemplary embodiments, in the process of forming interception prompt information of the baggage of interest based on the result of association matching, the control device can also provide accurate prompts and differentiated displays of the baggage of interest through a multi-layer data processing and information generation mechanism. Exemplarily, the control device can only generate arrival information of the baggage of interest based on the result of association matching, and the arrival information includes the real-time position, appearance characteristics and security risk level of the baggage on the conveying path. For ordinary baggage whose detected items meet the standards, arrival information may not be generated. Alternatively, arrival information can be generated for both ordinary baggage and baggage of interest, but different marks can be given to the two. Furthermore, the real-time position information can be dynamically calculated and updated in real time by the control device.

[0077] According to the embodiments of the present disclosure, the logic for generating arrival information relies on the associated matching results. After the entrance image information of the luggage is successfully matched with the exit appearance features, the control device can determine the specific time and location of its arrival at the exit by calculating the transmission progress of the luggage. Furthermore, the priority level of the luggage of interest can be marked in combination with the risk assessment results provided by the security inspection equipment.

[0078] Based on the arrival information, the control device can further generate interception prompt information and push it to the customs officer in the form of visual prompts. Specifically, the graphical interface can present the appearance image of the baggage, the estimated arrival time and interception suggestions. Through this intuitive display method, customs officers can quickly identify the target baggage and take corresponding measures, which significantly improves the interception efficiency and operational convenience.

[0079] Continue to refer to Figure 3 The pre-machine-inspected baggage identification system 100 further includes an execution terminal. The execution terminal is in communication with the control device and is used to receive and display interception prompt information of the baggage of interest to the customs officer, so as to assist the customs officer in efficiently supervising and handling the baggage. The execution terminal is configured to display the location information and appearance image of the baggage of interest after receiving the interception prompt information.

[0080] It should be understood that the types of execution terminals can be diverse, such as handheld terminals, fixed display screens, wearable devices, and multi-device collaborative systems. The types of execution terminals can be selected according to different scenarios and needs. For example, as a portable device, the handheld terminal is suitable for highly flexible operation scenarios. The handheld terminal can be equipped with a touch screen and a mobile communication module, which can receive prompt information in real time when the customs officer is moving, and display the location information and appearance image of the luggage of interest in a visual interface. The customs officer can quickly browse and take corresponding actions through the handheld terminal. In addition, the handheld terminal can also be configured with a vibration or sound reminder function to ensure that the information of high-priority luggage can attract the attention of customs officers in a timely manner and improve interception efficiency.

[0081] According to the embodiments of the present disclosure, when special luggage is about to appear on the carousel, customs officers can learn the exact location and time of the luggage inspection in advance through the received interception prompt information, which can improve the timeliness of the preliminary machine inspection supervision.

[0082] Based on the above-mentioned pre-machine-inspected baggage identification system, the embodiment of the present disclosure also provides a pre-machine-inspected baggage identification method. It should be noted that, in the absence of conflict, the content and features described above can be combined with the various embodiments described below. In order to save space, they will not be repeated in the various embodiments below. For example, the control device generates the arrival information of the baggage based on the result of the association match, and generates the interception prompt information in the form of a visual prompt based on the arrival information. The setting can also be applied to the process of identifying the baggage of interest in the pre-machine-inspected baggage identification method.

[0083] Figure 4 The figure is a flow chart of a method for identifying baggage in advance through machine inspection according to an exemplary embodiment of the present disclosure.

[0084] like Figure 4 As shown, the pre-machine inspection baggage identification method of this embodiment includes operations S410 to S440.

[0085] In operation S410, a first appearance image of luggage is captured by a first appearance capturing device.

[0086] In response to the luggage entering the first appearance acquisition device, the photoelectric sensor in the first appearance acquisition device can be triggered to detect the arrival status of the luggage, and the camera can be controlled to start and continuously take multiple photos of the luggage appearance within a preset time interval. Subsequently, the image analysis algorithm can be used to screen the quality of the multiple photos taken, and the photos with better clarity, brightness balance and contrast are selected as the first appearance image. The selected first appearance image is sent to the control device in real time.

[0087] In operation S420, the luggage is inspected using the security inspection equipment, the luggage of interest is identified, and a target security inspection result is generated.

[0088] After the luggage is scanned by the security inspection equipment, the items inside the luggage can be analyzed based on the preset algorithm and risk assessment model to determine whether there are prohibited items or other high-risk items. If the luggage of interest is detected, the security inspection equipment will generate the target security inspection results, including risk level, item category and other information, and transmit this information to the control device, which is associated with the first appearance image to form the entrance portrait information.

[0089] In operation S430, a second appearance image of the luggage is captured by a second appearance capturing device.

[0090] In response to the luggage entering the second appearance acquisition device, the photoelectric sensor in the second appearance acquisition device can be triggered to start the shooting mechanism. The camera continuously captures multi-angle photos of the luggage at a fixed frequency, and also uses the image analysis algorithm to select the better photos as the second appearance image. The selected second appearance image is sent to the control device for matching with the entrance portrait information.

[0091] In operation S440, the target security inspection result, the first appearance image, and the second appearance image are correlated and matched, and interception prompt information of the baggage of interest is formed based on the result of the correlation matching. The first appearance image and the target security inspection result can be correlated and matched first to generate correlation information, and the correlation information is stored in the time queue. Then, based on the time queue, the correlation information and the second appearance image are correlated and matched. That is, the process of sequential correlation matching is realized.

[0092] Specifically, the process of sequential associative matching may include: extracting a first appearance feature of a first appearance image, generating entrance portrait information by combining the first appearance feature and a target security inspection result, and placing the entrance portrait information into a time queue sorted by baggage transfer time; extracting a second appearance feature of a second appearance image, calculating a corresponding entrance time window according to a baggage transfer speed, and obtaining target entrance portrait information matching the entrance time window from the time queue; and associating and matching the second appearance feature with the target entrance portrait information to generate an associative matching result.

[0093] After successful matching, the uniqueness and status of the baggage can be confirmed, and interception prompt information of the baggage of interest can be generated. The interception prompt information can be transmitted to the customs officer's execution terminal in a visual form, and the customs officer can quickly locate and handle the problematic baggage based on the interception prompt information.

[0094] Figure 5 A block diagram of an electronic device suitable for implementing the above method according to an embodiment of the present disclosure is schematically shown. Figure 5 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0095] like Figure 5 As shown, the electronic device 500 according to an embodiment of the present disclosure includes a processor 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage part 508 to a random access memory (RAM) 503. The processor 501 may include, for example, a general-purpose microprocessor (such as a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (for example, an application-specific integrated circuit (ASIC)), etc. The processor 501 may also include an onboard memory for caching purposes. The processor 501 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0096] In RAM 503, various programs and data required for the operation of electronic device 500 are stored. Processor 501, ROM 502 and RAM 503 are connected to each other via bus 504. Processor 501 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 502 and / or RAM 503. It should be noted that the program can also be stored in one or more memories other than ROM 502 and RAM 503. Processor 501 can also perform various operations of the method flow according to the embodiment of the present disclosure by executing the program stored in the one or more memories.

[0097] According to an embodiment of the present disclosure, the electronic device 500 may further include an input / output (I / O) interface 505, which is also connected to the bus 504. The electronic device 500 may further include one or more of the following components connected to the input / output (I / O) interface 505: an input portion 506 including a keyboard, a mouse, etc.; an output portion 507 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 508 including a hard disk, etc.; and a communication portion 509 including a network interface card such as a LAN card, a modem, etc. The communication portion 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the input / output (I / O) interface 505 as needed. A removable medium 511, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 510 as needed, so that a computer program read therefrom is installed into the storage portion 508 as needed.

[0098] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.

[0099] According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, it may include but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, an apparatus or a device. For example, according to an embodiment of the present disclosure, the computer-readable storage medium may include the ROM 502 and / or RAM 503 described above and / or one or more memories other than ROM 502 and RAM 503.

[0100] The embodiment of the present disclosure also includes a computer program product, which includes a computer program, and the computer program contains program code for executing the method shown in the flowchart. When the computer program product is run in a computer system, the program code is used to enable the computer system to implement the user interaction method provided by the embodiment of the present disclosure.

[0101] The above functions defined in the system / device of the embodiment of the present disclosure are performed when the computer program is executed by the processor 501. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0102] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices, magnetic storage devices, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of signals on a network medium, and downloaded and installed through the communication part 509, and / or installed from the removable medium 511. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0103] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 509, and / or installed from the removable medium 511. When the computer program is executed by the processor 501, the above functions defined in the system of the embodiment of the present disclosure are performed. According to the embodiment of the present disclosure, the system, device, means, module, unit, etc. described above can be implemented by a computer program module.

[0104] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

[0105] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0106] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present disclosure. It should be understood that the above description is only a specific embodiment of the present disclosure and is not intended to limit the present disclosure. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present disclosure should be included in the protection scope of the present disclosure.

Claims

1. A pre-machine inspection baggage identification system, characterized in that: include: a baggage conveying platform, wherein the baggage conveying platform is configured to convey baggage along a baggage conveying direction; A security inspection device, wherein the security inspection device is configured to inspect the luggage and generate a target security inspection result; an appearance collection device, the appearance collection device comprising at least a first appearance collection device and a second appearance collection device, wherein the first appearance collection device is arranged upstream of the security inspection device and is used to collect a first appearance image of the luggage, and the second appearance collection device is arranged upstream of the luggage claim area and is used to collect a second appearance image of the luggage; and A control device, the control device being in communication connection with the security inspection device and the appearance acquisition device; The control device is configured to perform association matching on the target security inspection result, the first appearance image and the second appearance image, and form interception prompt information of the luggage based on the result of the association matching.

2. The system according to claim 1, characterized in that The appearance acquisition device comprises: a camera, wherein the camera is configured to capture an appearance image of the luggage in a luggage appearance collection area; A photoelectric sensor is configured to detect the arrival status of the luggage and trigger the camera to shoot.

3. The system according to claim 2, characterized in that The appearance collection device is configured as an appearance collection box, and the appearance collection device further includes: light source; A supporting structure is configured to fix the light source, the camera and the photoelectric sensor inside the appearance collection box and / or above the baggage transfer path.

4. The system according to any one of claims 1 to 3, characterized in that: During the process of association matching, the control device is configured to: Correlate and match the first appearance image with the target security inspection result to generate correlation information, and store the correlation information in a time queue; Based on the time queue, the association information and the second appearance image are associated and matched.

5. The system according to claim 4, characterized in that The control device is further configured to: extracting a first appearance feature of the first appearance image, combining the first appearance feature and the target security inspection result to generate entrance portrait information, and storing the entrance portrait information in the time queue, wherein the time queue is sorted by baggage transfer time; extracting a second appearance feature of the second appearance image, calculating a corresponding entrance time window according to a conveying speed of the baggage, and acquiring target entrance portrait information matching the entrance time window from the time queue; The second appearance feature is associated and matched with the target entrance portrait information to generate an associated matching result.

6. The system according to any one of claims 1 to 3, characterized in that: In the process of forming the interception prompt information of the baggage based on the result of the association matching, the control device is configured to: Generate baggage arrival information based on the result of association matching; Interception prompt information is generated in the form of a visual prompt based on the arrival information.

7. The system according to claim 6, characterized in that The arrival information is set as differentiated information for different luggage.

8. The system according to claim 2 or 3, characterized in that: The appearance acquisition device is configured such that, in response to the arrival of the luggage, the photoelectric sensor triggers the camera to continuously take a plurality of photos within a preset time interval.

9. The system according to claim 8, characterized in that The appearance acquisition device further includes an analyzing device, which is configured to perform quality analysis on a plurality of photos taken continuously, and select photos of target quality as the first appearance image or the second appearance image.

10. The system according to claim 2 or 3, characterized in that: The camera includes a plurality of cameras arranged at different positions in a baggage appearance collection area.

11. The system according to claim 3, characterized in that The light source includes a plurality of light sources arranged at different positions of the appearance collection box.

12. The system according to any one of claims 1 to 3, 5, 7, 9 and 11, characterized in that: The baggage conveying platform comprises a baggage entrance platform and a baggage exit platform which are arranged opposite to each other. The first appearance collecting device is arranged on the baggage entrance platform, and the second appearance collecting device is arranged on the baggage exit platform.

13. The system according to any one of claims 1 to 3, 5, 7, 9 and 11, characterized in that: The baggage identification system further comprises an execution terminal, which is communicatively connected with the control device and is used for receiving and displaying the interception prompt information.

14. The system according to claim 13, characterized in that The execution terminal is configured to display the location information and appearance image of the corresponding luggage after receiving the interception prompt information.

15. The system according to claim 9, characterized in that The analysis device is further configured to: Comprehensive scoring of multiple photos taken continuously based on image clarity, brightness balance and contrast; The photo with a comprehensive score exceeding a preset threshold is used as the first appearance image or the second appearance image.

16. A method for identifying baggage prior to machine inspection, characterized in that: include: collecting a first appearance image of the luggage by a first appearance collecting device, wherein the first appearance collecting device is arranged upstream of the security inspection device along the luggage conveying direction; Using the security inspection equipment to inspect the luggage and generate a target security inspection result; collecting a second appearance image of the luggage by a second appearance collecting device, wherein the second appearance collecting device is arranged upstream of a luggage claiming area along the luggage conveying direction; and The target security inspection result, the first appearance image and the second appearance image are correlated and matched, and interception prompt information of the luggage is formed based on the result of the correlation and matching.

17. The method according to claim 16, characterized in that The associating and matching the target security inspection result, the first appearance image, and the second appearance image specifically includes: extracting a first appearance feature of the first appearance image, combining the first appearance feature and the target security inspection result to generate entrance portrait information, and placing the entrance portrait information into a time queue sorted by baggage transfer time; extracting a second appearance feature of the second appearance image, calculating a corresponding entrance time window according to a conveying speed of the baggage, and acquiring target entrance portrait information matching the entrance time window from the time queue; and The second appearance feature and the target entrance portrait information are correlated and matched to generate a correlation matching result.

Images