Advance inspection target tracking method and tracking system

Abstract

The present disclosure provides an advance inspection target tracking method and tracking system. The tracking method comprises: performing zone-based detection on targets to obtain a plurality of pieces of initial detection data for a plurality of zones, wherein the targets comprise luggage to be detected and / or a person to be detected; using zone processing units of the plurality of zones to respectively process the corresponding plurality of pieces of initial detection data to obtain first processed data for the plurality of zones; sending the first processed data for the plurality of zones to a central server; using the central server to process the first processed data for the plurality of zones to obtain second processed data for the plurality of zones; and performing tracking detection on the targets within the plurality of zones on the basis of the second processed data for the plurality of zones.

Description

Preliminary machine inspection target tracking method and tracking system

[0001] This application claims priority to Chinese Patent Application No. 202411896675.9, filed on December 20, 2024, the contents of which are incorporated herein by reference. Technical Field

[0002] This disclosure relates to the field of article security inspection technology, and more specifically, to a method and system for tracking targets during early machine inspection. Background Technology

[0003] There are two main methods for tracking and monitoring target baggage during the initial machine inspection. The first method is to manually check the surveillance video for target baggage marked with customs. If the manual method determines that target baggage has been found, the on-site customs officers will be notified to handle it. The second method is to install electronic fence locks on the target baggage, so that on-site customs officers can handle the target baggage within the supervised area.

[0004] However, current preliminary inspection systems do not track pedestrians or luggage throughout the entire process, lacking real-time tracking, accurate location, and abnormal behavior identification after pedestrians have collected their checked baggage. The first method, using video surveillance, requires staff to visually inspect and judge the footage, significantly increasing manpower requirements and increasing the risk of misjudgment. The second method, using electronic fence locks, has relatively high installation and maintenance costs, requiring complex electronic equipment and technology. Covering large areas requires even higher investment, and interference from surrounding electronic devices can affect the fence's accuracy. There are also risks of electronic lock damage or breaches, which prevents continued tracking of the target person, increasing the risk of missed interceptions. Furthermore, both methods rely on manual review of surveillance video to review past events, making it difficult to link target baggage with the surveillance viewpoint in real time. This hinders pre-emptive warnings and rapid post-incident location, negatively impacting customs processing efficiency. Summary of the Invention

[0005] In view of this, embodiments of the present disclosure provide a method and system for early machine detection target tracking.

[0006] One aspect of this disclosure provides a method for early machine-detected target tracking, comprising:

[0007] The target is partitioned for detection, resulting in multiple initial detection data for multiple partitions. The target includes luggage to be detected and / or people to be detected.

[0008] The partition processing units of the multiple partitions are used to process the corresponding initial detection data to obtain the first processed data of the multiple partitions;

[0009] The first processed data from the multiple partitions is sent to the central server;

[0010] The central server is used to process the first processing data of the multiple partitions to obtain the second processing data of the multiple partitions; and the targets within the multiple partitions are tracked and detected based on the second processing data of the multiple partitions.

[0011] According to embodiments of this disclosure, the plurality of zones include a baggage identification area, a baggage claim and lobby area, a concealed area, and an exit area;

[0012] The initial detection data obtained by performing partition detection on the target to obtain multiple partitions include:

[0013] In the baggage identification area, the baggage to be inspected is inspected to obtain the first inspection data of the baggage identification area;

[0014] In the baggage claim and lobby area, the baggage to be inspected and the person to be inspected are inspected to obtain second inspection data for the baggage claim and lobby area; and

[0015] In the concealed area and the exit area, the luggage to be inspected and the person to be inspected are inspected to obtain the third inspection data of the concealed area and the exit area.

[0016] According to embodiments of this disclosure, the partition processing unit for the plurality of partitions includes a first processing unit, a second processing unit, and a third processing unit;

[0017] The step of using the partition processing units of the multiple partitions to process the corresponding initial detection data to obtain the first processed data of the multiple partitions includes:

[0018] The first processing unit processes the first detection data to obtain the first processed data for the baggage identification area;

[0019] The second processing unit processes the second detection data to obtain the first processed data for baggage claim and the lobby area; and

[0020] The third processing unit processes the third detection data to obtain the first processed data of the concealed area and the exit area.

[0021] According to embodiments of this disclosure, processing the first detection data using the first processing unit to obtain the first processed data for the baggage identification area includes:

[0022] The first processing unit is used to identify and process the first detection data in order to determine the target luggage that needs to be focused on;

[0023] Add a baggage tag to the target baggage, the baggage tag including a first tracking address;

[0024] Based on the first tracking address, the target luggage is tracked and detected to obtain its coordinates and video frames; and

[0025] The luggage coordinates and video frames of the target luggage are encoded together with the first tracking address to obtain the first processed data of the luggage identification area.

[0026] According to embodiments of this disclosure, processing the first processing data of the plurality of partitions using the central server to obtain the second processing data of the plurality of partitions includes: processing the first processing data of the baggage identification area to obtain the second processing data of the baggage identification area.

[0027] The step of processing the first processing data of the baggage identification area to obtain the second processing data of the baggage identification area includes:

[0028] Extract the luggage coordinates, the first tracking address, and video frame data from the first processed data of the luggage identification area;

[0029] An image of the target luggage is obtained from the video frame data based on the luggage coordinates; and

[0030] The image of the target luggage is analyzed and extracted to obtain the first feature of the target luggage.

[0031] According to embodiments of this disclosure, processing the first processing data of the baggage identification area to obtain the second processing data of the baggage identification area further includes: saving the first feature of the target baggage to the baggage global cache of the central server; and

[0032] Based on the current state of the target baggage, update the first feature of the target baggage in the baggage global cache.

[0033] According to embodiments of this disclosure, the step of processing the second detection data using the second processing unit to obtain the first processed data for baggage claim and the lobby area includes:

[0034] Obtain the second location coordinates of all the luggage to be inspected, and add a second tracking address to the luggage to be inspected;

[0035] Obtain the third location coordinates of the person to be detected near the luggage to be detected, and add a third tracking address to the person to be detected; and

[0036] The data containing the second location coordinates, the second tracking address, and the video frame of the baggage to be detected, and the data containing the third location coordinates, the third tracking address, and the video frame of the person to be detected are encoded to obtain the first processing data for baggage retrieval and the lobby area.

[0037] According to embodiments of this disclosure, processing the first processing data of the multiple partitions using the central server to obtain the second processing data of the multiple partitions includes: processing the first processing data of the baggage claim and lobby areas to obtain the second processing data of the baggage claim and lobby areas.

[0038] The process of processing the first processing data of the baggage claim and lobby area to obtain the second processing data of the baggage claim and lobby area includes:

[0039] Based on the baggage claim and the first processing data of the lobby area, data containing the second location coordinates, the second tracking address and the video frame of the baggage to be detected and data containing the third location coordinates, the third tracking address and the video frame of the person to be detected are extracted;

[0040] Based on the second position coordinates, an image of the luggage to be detected is obtained from a video frame containing the luggage to be detected, and feature extraction is performed on the image of the luggage to be detected to obtain the second feature of the luggage to be detected;

[0041] The image of the person to be detected is obtained from the video frame containing the person to be detected based on the third position coordinates, and the third feature of the person to be detected is obtained by feature extraction from the image of the person to be detected.

[0042] The second feature of the baggage to be detected is compared with the first feature of the target baggage in the baggage global cache to determine whether the baggage to be detected is the target baggage; and

[0043] The characteristics of the target person associated with the target luggage are obtained by calculating and verifying the target person associated with the target luggage using consecutive frames.

[0044] According to embodiments of this disclosure, the step of using continuous frames to calculate and verify the target person associated with the target luggage includes: using continuous frames to calculate and verify the person whose coordinates overlap with the target luggage within a unit time period.

[0045] According to embodiments of this disclosure, the method further includes: forming a pairing group between the target luggage and the associated target person, and saving the characteristics of the pairing group to a global cache of the pairing group on the central server.

[0046] According to embodiments of this disclosure, the method further includes: simultaneously tracking and detecting the target baggage and the target person based on the second tracking address and the third tracking address, and updating the features of the optimal viewpoint of the target baggage and the target person to the global cache of the pairing group.

[0047] According to embodiments of this disclosure, the method further includes: during the tracking of the target baggage, sending the latest image and location of the target baggage to a display terminal.

[0048] According to embodiments of this disclosure, the method further includes: when an abnormal situation occurs in the pairing group, sending an alarm message to the display terminal, the abnormal situation including the loss of the target luggage; and / or,

[0049] The method further includes sending an alarm message to the display terminal when the baggage tag is damaged.

[0050] According to embodiments of this disclosure, processing the first processing data of the plurality of partitions using the central server to obtain the second processing data of the plurality of partitions includes: processing the first processing data of the hidden area and the exit area to obtain the second processing data of the hidden area and the exit area.

[0051] The process of processing the first processing data of the concealed area and the exit area to obtain the second processing data of the concealed area and the exit area includes:

[0052] Based on the global cache of the pairing group on the central server, the target luggage and the target person are determined;

[0053] The system detects whether the target luggage and / or the target person has entered the concealed area or the exit area. If so, it sends an alert message to the display terminal.

[0054] According to an embodiment of this disclosure, the method includes: detecting whether the target luggage has entered the concealed area;

[0055] If the target luggage enters the concealed area, an abnormality alert message is sent to the display terminal.

[0056] According to embodiments of this disclosure, the method further includes: detecting whether the target baggage and the target person have entered the exit area;

[0057] If either the target luggage or the target person enters the exit area, an alarm message is sent to the display terminal.

[0058] Another aspect of this disclosure provides an early-stage machine-detected target tracking system, comprising:

[0059] Multiple partitioned cameras are used to perform partitioned detection of targets and obtain multiple initial detection data for multiple partitions. The targets include luggage to be detected and people to be detected.

[0060] Multiple partition processing units are used to process the corresponding initial detection data respectively to obtain first processed data for the multiple partitions, and then send the first processed data of the multiple partitions to the central server; and

[0061] A central server is configured to process the first processing data of the plurality of partitions to obtain the second processing data of the plurality of partitions, and to track and detect targets within the plurality of partitions based on the second processing data of the plurality of partitions.

[0062] According to embodiments of this disclosure, the plurality of zoned cameras include baggage identification cameras and baggage tracking cameras, wherein the baggage identification cameras are located in the baggage identification area, and the baggage tracking cameras are located in the baggage claim and hall area and the exit area.

[0063] According to embodiments of this disclosure, the plurality of partition processing units include a first processing unit, a second processing unit, and a third processing unit.

[0064] The first processing unit is used to process the first detection data detected by the baggage tag camera in the baggage tag area to obtain the first processed data of the baggage tag area;

[0065] The second processing unit is used to process the second detection data detected by the baggage tracking camera in the baggage claim and hall area to obtain the first processed data of the baggage claim and hall area; and

[0066] The third processing unit is used to process the third detection data detected by the baggage tracking camera in the concealed area and the exit area to obtain the first processed data of the concealed area and the exit area.

[0067] According to embodiments of this disclosure, the central server includes a first feature extraction module, a second feature extraction module, a comparison module, and an association module, wherein...

[0068] The first feature extraction module is used to extract the first feature of the target luggage;

[0069] The second feature extraction module is used to extract the second feature of the luggage to be detected and the third feature of the person to be detected;

[0070] The comparison module is used to compare the second feature of the baggage to be detected with the first feature of the target baggage in order to determine whether the baggage to be detected is the target baggage;

[0071] The association module is used to associate the target luggage with the target person.

[0072] According to embodiments of this disclosure, the central server further includes:

[0073] A pairing group generation module, configured to generate a pairing group between the target luggage and the target person based on the results of the comparison module and the association module; and

[0074] A pairing group global cache module is used to store and update records of the characteristics of the target luggage and the characteristics of the target person.

[0075] According to an embodiment of this disclosure, the central server further includes a baggage global cache module, which is used to store and update records of the first characteristics of the target baggage.

[0076] According to embodiments of this disclosure, the tracking system further includes a display terminal, which is used to receive images and locations of the target luggage, images and locations of the target person, abnormal alert messages, and alarm information. Attached Figure Description

[0077] The above and other objects, features, and advantages of this disclosure will become clearer from the following description of embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0078] Figure 1 is a schematic diagram of a scenario of a preliminary machine inspection target tracking system according to an embodiment of the present disclosure;

[0079] Figure 2 is a flowchart of a preliminary machine inspection target tracking method according to an embodiment of the present disclosure;

[0080] Figure 3 is a flowchart of multiple partition detection according to an embodiment of the present disclosure;

[0081] Figure 4 is a flowchart of the processing of partition processing unit data for multiple partitions according to an embodiment of the present disclosure;

[0082] Figure 5 is a flowchart of the first processing unit processing the first detection data according to an embodiment of the present disclosure;

[0083] Figure 6 is a flowchart of the processing of first processing data of the baggage identification area by the central server according to an embodiment of the present disclosure;

[0084] Figure 7 is a flowchart of the second processing unit processing the second detection data according to an embodiment of the present disclosure;

[0085] Figure 8 is a flowchart of the processing of baggage claim and first processing data of the lobby area by the central server according to an embodiment of the present disclosure;

[0086] Figure 9 is a flowchart of the processing of first processed data of the hidden area and the exit area by the central server according to an embodiment of the present disclosure;

[0087] Figure 10 is a structural block diagram of an early-stage machine-detected target tracking system according to an embodiment of the present disclosure; and

[0088] Figure 11 is a structural block diagram of a central server according to an embodiment of the present disclosure.

[0089] It should be noted that, for clarity, the dimensions of the overall / partial structure or the overall / partial region in the drawings used to describe the embodiments of this disclosure may be enlarged or reduced, i.e., these drawings are not drawn to actual scale. Detailed Implementation

[0090] The embodiments of the present disclosure will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the disclosure. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of the present disclosure for ease of explanation. However, it will be apparent that one or more embodiments may be practiced without these specific details. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concepts of the present disclosure.

[0091] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0092] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0093] Baggage inspection is a crucial step in airport and customs operations. Checked baggage first undergoes preliminary screening by X-ray imaging, which identifies and marks problematic baggage. As this baggage passes through the detection gates, the tags are read to intercept or allow it to proceed. To further enhance monitoring, problematic baggage or individuals associated with it are marked as it leaves the baggage carousel. When the target baggage or person is detected at the exit, an alarm system is triggered, allowing staff to intercept and inspect the baggage.

[0094] However, in related technologies, the initial detection of target baggage and individuals relies too heavily on subjective human judgment, leading to a high risk of missed detection during peak periods. Furthermore, these technologies lack end-to-end tracking of target baggage or individuals; if a pedestrian removes the tag after collecting their baggage but before exiting customs, problematic baggage may be missed, increasing the risk of missed detection. Additionally, problematic baggage may be transferred or abandoned en route, easily resulting in missed detection or the inability to locate one or more individuals associated with it. This may prevent real-time tracking and status updates of associated target baggage and individuals, hindering pre-emptive warnings and rapid post-incident location, thus impairing the efficiency of security checks.

[0095] Based on this, embodiments of this disclosure provide a method and system for early-stage machine inspection target tracking. The early-stage machine inspection target tracking method includes: performing target partitioning detection to obtain multiple initial detection data for multiple partitions, where targets include luggage to be inspected and / or people to be inspected; processing the corresponding multiple initial detection data using partitioning processing units for each of the multiple partitions to obtain first processed data for the multiple partitions; sending the first processed data for the multiple partitions to a central server; processing the first processed data for the multiple partitions using the central server to obtain second processed data for the multiple partitions; and tracking and detecting targets within the multiple partitions based on the second processed data for the multiple partitions. By refining the early-stage machine inspection scenario and adopting a cloud-edge collaborative deployment approach, single-view target detection and tracking are placed on the edge camera side, improving detection real-time performance. The central server performs differentiated calculation and analysis based on the camera's detection results, effectively reducing central computing power consumption and solving the computing power bottleneck problem during peak traffic periods.

[0096] The following explanation will use arriving baggage at an airport as an example. It should be noted that the preliminary inspection target tracking method and tracking system disclosed herein can be used in locations such as ports, airports, and train stations. However, these locations should not be used to limit the scope of this disclosure. Within these locations, any movement and time period that occurs between the time a pedestrian collects their baggage and the time before special baggage inspection (e.g., customs clearance) is considered within the scope of this disclosure.

[0097] Figure 1 is a schematic diagram of a scenario of a pre-inspection target tracking system according to an embodiment of the present disclosure, and Figure 2 is a flowchart of a pre-inspection target tracking method according to an embodiment of the present disclosure.

[0098] For example, referring to FIG1, the pre-inspection target tracking system provided in the embodiments of this disclosure can perform zone detection on the target, obtaining multiple initial detection data for multiple zones. For example, the target may include baggage 140 to be inspected and person 170 to be inspected. The multiple zones include baggage identification zone N1, baggage claim and lobby area N2, and concealed area and exit area N3. Baggage 140 to be inspected can be sent from baggage identification zone N1 through security conveyor belt 130 to baggage carousel 200 in baggage claim and lobby area N2. Person 170 to be inspected can retrieve baggage 140 to be inspected in baggage claim and lobby area N2 and carry baggage 140 to move between baggage claim and lobby area N2 or concealed area and exit area N3. The concealed area and exit area N3 includes concealed area 180 and exit area 190.

[0099] For example, the concealed area 180 can be an area not monitored by the baggage tracking camera 160; for instance, the concealed area 180 may include a restroom. Multiple baggage tracking cameras 160 may be installed in the baggage claim and lobby area N2 and the exit area 190 for tracking and monitoring. For example, multiple baggage tracking cameras 160 located in different areas can perform cross-view tracking of the baggage to be detected 140 and the person to be detected 170, such as cross-view tracking of the target baggage and the target person associated with the target baggage.

[0100] For example, the baggage identification area N1 can be located at the entrance of the area to be inspected, and the baggage to be inspected 140 will first enter the baggage identification area N1. In the baggage identification area N1, the baggage to be inspected 140 can be security-checked using the baggage identification camera 120 to obtain initial detection data in the baggage identification area N1. The first processing unit M1 can process the initial detection data in the baggage identification area N1 to obtain first processed data for the baggage identification area N1. For example, the first processing unit M1 can filter out target baggage from multiple bags to be inspected 140. The target baggage can be a suspicious item, such as a suspicious baggage. The first processing unit M1 can also be used to encode data such as the coordinates and video frames of the target baggage to obtain the first processed data.

[0101] For example, the first processing unit M1 can process the initial detection data collected by one or more baggage identification cameras 120.

[0102] For example, the first processing unit M1 may include a processor or processing module embedded in one or more baggage tagging cameras 120 in the baggage tagging area S1. That is, the first processing unit M1 and the baggage tagging camera 120 may be integrated together, for example, the first processing unit M1 and the baggage tagging camera 120 may be integrated together to form a smart camera with data processing capabilities. Alternatively, the first processing unit M1 may be a separate processor or processing module capable of communicating with the baggage tagging camera 120 and a central server.

[0103] After baggage 140 undergoes initial inspection in baggage identification area N1, it can be transferred to baggage claim and hall area N2, for example, via baggage conveyor belt 130 to baggage carousel 200 in baggage claim and hall area N2. The person to be inspected 170 can retrieve baggage 140 in baggage claim and hall area N2, for example, from baggage carousel 200. The person to be inspected 170 can carry baggage 140 to different areas of baggage claim and hall area N2 and / or concealed area and exit area N3 until the person to be inspected 170 and / or baggage 140 reach exit area 190, where exit security inspection is completed, thus ending the security check process.

[0104] For example, the preliminary machine inspection target tracking system may further include a second processing unit M2 and a third processing unit M3. The second processing unit M2 can be used to process the initial detection data detected by the baggage tracking cameras 160 in the baggage claim area and the hall area N2 to obtain the first processed data of the baggage claim area and the hall area N2. The third processing unit M3 can be used to process the initial detection data detected by the baggage tracking cameras 160 in the concealed area and the exit area N3 to obtain the first processed data of the concealed area and the exit area N3.

[0105] For example, the second processing unit M2 may include a processor or processing module embedded in one or more baggage tracking cameras 160 in the baggage claim and hall area N2. That is, the second processing unit M2 and the baggage tracking camera 160 may be integrated together, for example, the second processing unit M2 and the baggage tracking camera 160 may be integrated together to form a smart camera with data processing capabilities. Alternatively, the second processing unit M2 may be a separate processor or processing module capable of communicating with the baggage tracking cameras 160 in the baggage claim and hall area N2 and the central server 110.

[0106] For example, the third processing unit M3 may include a processor or processing module embedded in one or more baggage tracking cameras 160 located in the concealed area and exit area N3. Alternatively, the third processing unit M3 may be a separate processor or processing module capable of communicating with the baggage tracking cameras 160 in the concealed area and exit area N3 and the central server 110.

[0107] For example, the pre-inspection target tracking system may include a central server 110. The central server 110 may be a cloud server used for processing security inspection information. For instance, the central server 110 may process images of luggage and / or people to be inspected, extracting features from the luggage and people. The central server 110 may also be used to send information to security personnel, such as sending images and location information of the target luggage, or sending alarm information.

[0108] For example, the first processing unit M1 can transmit the first processed data of the baggage identification area N1 to the central server 110. The central server 110 processes the first processed data of the baggage identification area N1 to obtain the second processed data of the baggage identification area N1. The central server 110 can also feed back the second processed data of the baggage identification area N1 to the first processing unit M1 to facilitate further tracking and detection of the baggage to be detected in the baggage identification area N1.

[0109] For example, the second processing unit M2 can transmit the first processing data of baggage claim and hall area N2 to the central server 110. The central server 110 processes the first processing data of baggage claim and hall area N2 to obtain the second processing data of baggage claim and hall area N2.

[0110] For example, the third processing unit M3 can transmit the first processed data of the concealed area and the exit area N3 to the central server 110. The central server 110 then processes the first processed data of the concealed area and the exit area N3 to obtain the second processed data of the concealed area and the exit area N3.

[0111] By refining the early-stage machine inspection scenario, the first processing unit M1, the second processing unit M2, and the third processing unit M3 located on the camera side and the central server 110 located on the center side adopt a cloud-edge collaborative deployment method. Single-view target detection and tracking are placed on the edge camera side, which improves the real-time performance of detection. The central server performs differentiated calculation and analysis based on the camera's detection results (i.e., the detection results after processing by the first processing unit M1, the second processing unit M2, and the third processing unit M3), which can effectively reduce the central computing power consumption and solve the computing power bottleneck problem during peak traffic periods.

[0112] For example, cameras located in different areas can interact with the same central server 110 through a partitioned processing unit. For instance, the central server 110 can extract and analyze the first processed data of the baggage identification area N1 obtained by the first processing unit M1, thereby determining the target baggage in the baggage identification area N1 and the first characteristics of the target baggage. The central server 110 can also extract and analyze the first processed data of the baggage collection and hall area N2 obtained by the second processing unit M2 and the first processed data of the concealed area and exit area N3 obtained by the third processing unit M3, to obtain the second characteristics of the baggage to be detected 140 and the third characteristics of the person to be detected 170 located in the baggage collection and hall area N2 and / or the concealed area and exit area N3. The central server 110 can also associate the baggage to be detected 140 and the person to be detected 170, for example, by analyzing the coordinate overlap relationship between the baggage to be detected 140 and the person to be detected 170.

[0113] For example, the central server 110 can also compare the second feature of the baggage to be detected 140 extracted from the baggage claim and lobby area N2 and / or the hidden area and exit area N3 with the first feature of the target baggage previously extracted from the baggage identification area N1, thereby identifying the target baggage located in the baggage claim and lobby area N2 and / or the hidden area and exit area N3, and identifying the target person located in the baggage claim and lobby area N2 and / or the hidden area and exit area N3 based on the association between the baggage to be detected 140 and the person to be detected 170 in the baggage claim and lobby area N2 and / or the hidden area and exit area N3. The central server 110 can also be used to perform cross-view tracking and detection of the target baggage and the associated target person.

[0114] This method avoids relying too heavily on subjective human judgment in the discovery of target luggage and individuals, thus reducing the risk of missed detections and effectively lowering installation and maintenance costs. Furthermore, by linking target luggage and individuals for tracking, it solves the problem of not being able to track the individual after the luggage is lost.

[0115] For example, referring to Figures 1 and 2, the early detection target tracking method provided by the embodiments of this disclosure may include the following steps S1-S5.

[0116] In step S1, the target is partitioned for detection, resulting in multiple initial detection data for multiple partitions. The target includes luggage to be detected and / or people to be detected.

[0117] In step S2, the partition processing units of multiple partitions are used to process the corresponding initial detection data to obtain the first processed data of multiple partitions.

[0118] In step S3, the first processing data from multiple partitions is sent to the central server.

[0119] In step S4, the central server processes the first processing data of multiple partitions to obtain the second processing data of multiple partitions.

[0120] In step S5, targets within multiple partitions are tracked and detected based on the second processing data from multiple partitions.

[0121] By refining the early-stage machine inspection scenario, the first processing unit M1, the second processing unit M2, and the third processing unit M3 located on the camera side and the central server 110 located on the center side adopt a cloud-edge collaborative deployment method. Single-view target detection and tracking are placed on the edge camera side, which improves the real-time performance of detection. The central server performs differentiated calculation and analysis based on the camera's detection results (i.e., the detection results after processing by the first processing unit M1, the second processing unit M2, and the third processing unit M3), which effectively reduces the central computing power consumption and solves the computing power bottleneck problem during peak traffic periods.

[0122] Figure 3 is a flowchart of multiple partition detection according to an embodiment of the present disclosure.

[0123] For example, in an embodiment of this disclosure, referring to Figures 1 and 3, step S1, which involves partitioning the target to obtain multiple initial detection data for multiple partitions, may specifically include the following steps S11-S13.

[0124] In step S11, the baggage identification camera 120 is used to perform single-view detection on the baggage to be detected in baggage identification area N1, and the first detection data of baggage identification area N1 is obtained.

[0125] In step S12, in baggage claim and hall area N2, baggage tracking camera 160 is used to perform cross-view detection of baggage 140 to be detected and person 170 to be detected, and obtain second detection data of baggage claim and hall area N2.

[0126] In step S13, baggage tracking camera 160 is used to perform cross-view detection of baggage 140 and person 170 in the concealed area and exit area N3 to obtain third detection data of concealed area and exit area N3.

[0127] Figure 4 is a data processing flowchart of a partition processing unit for multiple partitions according to an embodiment of the present disclosure.

[0128] For example, in an embodiment of this disclosure, referring to FIG4, step S2, which uses a partition processing unit of multiple partitions to process the corresponding multiple initial detection data to obtain the first processed data of multiple partitions, may specifically include the following steps S21-S23.

[0129] In step S21, the first detection data is processed by the first processing unit M1 to obtain the first processed data of the baggage identification area N1.

[0130] In step S22, the second detection data is processed by the second processing unit M2 to obtain the first processed data of baggage claim and hall area N2.

[0131] In step S23, the third detection data is processed by the third processing unit M3 to obtain the first processed data of the concealed area and the exit area N3.

[0132] Figure 5 is a flowchart of the first processing unit processing the first detection data according to an embodiment of the present disclosure.

[0133] For example, in an embodiment of this disclosure, referring to FIG5, the first processing unit M1 is used to process the first detection data in step S21 to obtain the first processed data of the baggage identification area N1, which may specifically include the following steps S211-S214.

[0134] In step S211, the first processing unit M1 performs identification processing on the first detection data to determine the target baggage that needs attention. For example, the target baggage that needs attention can be selected from multiple bags to be detected.

[0135] In step S212, a baggage tag is added to the target baggage, and the baggage tag includes the first tracking address.

[0136] In step S213, the target baggage is tracked and detected based on the first tracking address to obtain the baggage coordinates and video frames.

[0137] In step S214, the luggage coordinates and video frames of the target luggage are encoded together with the first tracking address to obtain the first processed data of the luggage identification area.

[0138] For example, step S4, which uses the central server to process the first processing data of multiple partitions to obtain the second processing data of multiple partitions, may specifically include the following step S41.

[0139] In step S41, the first processing data of the baggage identification area is processed to obtain the second processing data of the baggage identification area.

[0140] Figure 6 is a flowchart of the processing of first processing data of the baggage identification area by the central server according to an embodiment of the present disclosure.

[0141] For example, in an embodiment of this disclosure, referring to FIG6, the processing of the first processing data of the baggage identification area in step S41 to obtain the second processing data of the baggage identification area may specifically include the following steps S411-S413.

[0142] In step S411, the baggage coordinates, first tracking address, and video frame data are extracted from the first processing data of baggage identification area N1.

[0143] In step S412, the image of the target luggage is obtained from the video frame data based on the luggage coordinates.

[0144] In step S413, the image of the target luggage is analyzed and extracted to obtain the first feature of the target luggage.

[0145] The detection data from the baggage tagging area is processed by a first processing unit located at the camera side to obtain the first processed data for the baggage tagging area. This first processed data is then transmitted to the central server for further calculations. This method reduces the computational power consumption of the central server and solves the computational bottleneck problem during peak passenger flow periods. Moreover, the first processing unit located at the camera side offers greater timeliness in data processing, which helps improve the real-time performance of detection.

[0146] In some embodiments, the process of processing the first processing data of the baggage identification area to obtain the second processing data of the baggage identification area in step S41 may further include the following steps S414-S415.

[0147] In step S414, the first characteristic of the target baggage is saved to the baggage global cache on the central server.

[0148] By saving the first feature of the target baggage to the baggage global cache on the central server, the first feature of the target baggage can be used for comparison during subsequent detection. The target baggage can be screened out from the many bags to be detected in baggage claim and hall area N2 and / or hidden area and exit area N3. There is no need to perform perspective detection again. The target baggage can be screened out by only obtaining the external image of the baggage to be detected by the camera, which helps to improve detection efficiency.

[0149] In step S415, the first feature of the target baggage in the global baggage cache is updated based on the current state of the target baggage.

[0150] This method can improve the accuracy and efficiency of detection, helping staff to better understand the current status of target luggage and individuals, thereby improving security check efficiency and reducing the risk of missed detections.

[0151] According to embodiments of this disclosure, the preliminary machine inspection target tracking method may further include: pushing an alert message to a display terminal, for example, the alert message may include the discovery of target luggage; and displaying an image of the target luggage and a monitoring screen of the current viewpoint on the display terminal. For example, the display terminal may be a mobile display terminal carried by staff.

[0152] This method helps staff to understand the information of the target luggage in a timely manner, enabling them to conduct relevant inspections and processing more promptly and accurately, thus improving the efficiency of security checks.

[0153] For example, in the baggage identification area N1, different types of image detection devices can be used to inspect the baggage to be inspected. For instance, a perspective image detection device can be used to obtain a perspective image of the baggage to be inspected, and a baggage identification camera can be used to obtain an external image of the baggage to be inspected, thereby enabling better screening of target baggage and tracking and detection of target baggage.

[0154] Figure 7 is a flowchart of the second processing unit processing the second detection data according to an embodiment of the present disclosure.

[0155] For example, in an embodiment of this disclosure, referring to FIG7, the second processing unit M2 is used to process the second detection data in step S22 to obtain the first processed data of baggage claim and hall area N2, which may specifically include the following steps S221-S223.

[0156] In step S221, the second location coordinates of all baggage to be inspected are obtained, and a second tracking address is added to the baggage. For example, after all baggage to be inspected is inspected by the baggage tracking camera 160 in the baggage claim and hall area N2, the second server M2 can process the initial inspection data of all baggage to be inspected to obtain the second location coordinates of all baggage to be inspected and add a second tracking address to the baggage.

[0157] In step S222, the third location coordinates of the person to be detected near the baggage to be detected are obtained, and a third tracking address is added to the person to be detected. For example, the baggage tracking camera 160 in baggage claim and hall area N2 can also detect the person to be detected near each baggage to be detected, and the second server M2 can obtain the third location coordinates of the person to be detected near the baggage to be detected and add a third tracking address to the person to be detected.

[0158] In step S223, the data containing the second location coordinates, the second tracking address and the video frame of the baggage to be detected and the data containing the third location coordinates, the third tracking address and the person to be detected are encoded to obtain the first processing data for baggage retrieval and the hall area.

[0159] This method can improve the real-time performance of baggage claim and lobby area inspection, while also reducing the computing power consumption of the central server.

[0160] For example, step S4, which uses the central server to process the first processing data of multiple partitions to obtain the second processing data of multiple partitions, may also include step S42.

[0161] In step S42, the first processing data of baggage claim and hall area N2 is processed to obtain the second processing data of baggage claim and hall area N2.

[0162] Figure 8 is a flowchart of the processing of baggage claim and first processing data of the lobby area by the central server according to an embodiment of the present disclosure.

[0163] For example, in an embodiment of this disclosure, referring to FIG8, the processing of the first processing data of baggage claim and hall area N2 in step S42 to obtain the second processing data of baggage claim and hall area N2 may specifically include the following steps S421-S425.

[0164] In step S421, based on the baggage claim and the first processing data of the hall area N2, data containing the second location coordinates, the second tracking address and the video frame of the baggage to be detected and data containing the third location coordinates, the third tracking address and the video frame of the person to be detected are extracted.

[0165] In step S422, an image of the baggage to be detected is obtained from a video frame containing the baggage to be detected based on the second position coordinates, and feature extraction is performed on the image of the baggage to be detected to obtain the second feature of the baggage to be detected.

[0166] In step S423, the image of the person to be detected is obtained from the video frame containing the person to be detected based on the third position coordinates, and feature extraction is performed on the image of the person to be detected to obtain the third feature of the person to be detected.

[0167] In some embodiments, the central server can also filter out some video frames based on the second tracking address and / or the third tracking address, thereby obtaining images of the luggage to be detected and the person to be detected more quickly, which helps to improve the processing efficiency of the central server.

[0168] In step S424, the second feature of the baggage to be detected is compared with the first feature of the target baggage in the baggage global cache to determine whether the baggage to be detected is the target baggage.

[0169] For example, the second feature of the baggage to be detected, obtained in the baggage claim and hall area N2, can be compared with the first feature of the target baggage, obtained in the baggage identification area N1. If the overlap between the first and second features is higher than a preset threshold, the baggage to be detected can be considered the target baggage. Subsequently, tracking and monitoring of the target baggage can be strengthened in the baggage claim and hall area N2, as well as in the concealed area and exit area N3, thereby better understanding the real-time information of the target baggage.

[0170] In step S425, consecutive frames are used to calculate and verify the target person associated with the target baggage in order to obtain the characteristics of the target person associated with the target baggage.

[0171] For example, using consecutive frames to calculate and verify the target person associated with the target baggage may include: using consecutive frames to calculate and verify people whose coordinates overlap with the target baggage within a unit of time. For example, the unit of time can be less than or equal to 10 seconds. That is, the person to be detected who is in the same location as the target baggage within 10 seconds can be considered as the target person associated with the target baggage.

[0172] By using consecutive video frames, one or more individuals whose coordinates overlap with the target luggage can be identified, and these individuals are considered as the target person associated with the luggage. Then, based on the third feature of the individuals extracted in step S423, the characteristics of the target person are determined.

[0173] According to embodiments of this disclosure, the characteristics of the target person may include at least one of a body image and a face image.

[0174] In some embodiments, the baggage tracking camera can obtain a clear image of the target person's face, and the target person's features can be extracted using the facial image.

[0175] In some embodiments, baggage tracking cameras may not be able to obtain a clear image of the target person's face, for example, if the camera is positioned high in the airport terminal and the obtained facial image is not clear enough. In such cases, the target person's features can be extracted based on the target person's body image.

[0176] In some embodiments, features of the target person's facial and body images can be extracted simultaneously, which can improve the reliability of tracking and monitoring.

[0177] According to embodiments of this disclosure, the preliminary machine inspection target tracking method may further include: forming a pairing group of target luggage and associated target person, and saving the characteristics of the pairing group to the pairing group global cache of the central server.

[0178] Pairing target luggage with target person makes it easy to track them from different perspectives. Even if the target luggage and target person are separated, the real-time status of both can be monitored simultaneously, solving the problem of not being able to track the target person separately after the target luggage is lost.

[0179] According to embodiments of this disclosure, the preliminary machine inspection target tracking method may further include: simultaneously tracking and detecting target baggage and target person based on a second tracking address and a third tracking address, and updating the features of the target baggage and target person from the optimal perspective to the global cache of the pairing group.

[0180] This method allows for timely monitoring of the latest status of target luggage and the target person. Even if the target luggage and / or the target person have changed their appearance (e.g., the target person changes their clothes, shoes, or hats, or the target luggage changes its color or is repackaged), the target luggage and the target person can still be accurately identified, thereby reducing the risk of missed detection.

[0181] For example, step S4, which uses the central server to process the first processing data of multiple partitions to obtain the second processing data of multiple partitions, may also include step S43.

[0182] In step S43, the first processing data of the concealed area and the exit area N3 are processed to obtain the second processing data of the concealed area and the exit area N3.

[0183] Figure 9 is a flowchart of the processing of first processing data of the hidden area and the exit area by the central server according to an embodiment of the present disclosure.

[0184] For example, in an embodiment of this disclosure, referring to FIG9, the processing of the first processing data of the concealed area and the exit area N3 in step S43 to obtain the second processing data of the concealed area and the exit area N3 may specifically include the following steps S431-S432.

[0185] In step S431, the target baggage and target person are determined based on the global cache of the pairing groups on the central server. For example, the target baggage and target person located in or about to enter the hidden area and exit area N3 can be determined based on the global cache of the pairing groups of target baggage and target person previously obtained in baggage claim and hall area N2, combined with the processing results of the detection data of the hidden area and exit area N3 by the third server M3.

[0186] In step S432, it is detected whether the target luggage and / or the target person has entered the concealed area or the exit area. If so, an alert message is sent to the display terminal.

[0187] According to embodiments of this disclosure, the preliminary machine inspection target tracking method may further include: during the tracking of target baggage, sending the latest image and location of the target baggage to a display terminal.

[0188] According to embodiments of this disclosure, the preliminary machine detection target tracking method may further include: during the tracking of the target person, sending the latest image and location of the target person to a display terminal.

[0189] By linking information from cameras, partition processing units, central servers, and display terminals, staff can obtain the latest images and locations of target luggage and target persons in a timely manner, enabling them to quickly reach the location of the target luggage and target persons for inspection and processing.

[0190] According to embodiments of this disclosure, the preliminary machine inspection target tracking method may further include: issuing an alarm message to a display terminal when an abnormality occurs in the target baggage and target person pairing group. For example, the abnormality may include the loss of the target baggage.

[0191] According to embodiments of this disclosure, the preliminary machine inspection target tracking method may further include: sending an alarm message to a display terminal when the baggage tag is tampered with. For example, it can be determined whether the baggage tag has been tampered with by recognizing the target person's actions (detecting actions by the target person that tamper with the tag).

[0192] This method allows for the correlation and tracking of target luggage and target individuals. When the physical identification of the target luggage is found to be damaged, an alarm message will be issued in real time, while the associated target individuals will continue to be tracked, which can reduce the chance of missed detection.

[0193] In embodiments of this disclosure, the preliminary machine inspection target tracking method may further include promptly sending a reminder or alarm message to a display terminal when the target luggage and / or target person enters or is about to enter a special area, so that staff can notice the relevant situation and take timely action. For example, the special area may include a concealed area and an exit area.

[0194] According to embodiments of this disclosure, the preliminary machine inspection target tracking method may further include the following steps S4321-S4322.

[0195] In step S4321, it is detected whether the target luggage has entered the concealed area.

[0196] In step S4322, if the target luggage enters the concealed area, an abnormality alert message is sent to the display terminal.

[0197] For example, if a target baggage reappears in the hall area after being concealed in a concealed area, the system will issue an alarm message for the target baggage that entered the concealed area within a specified time and has not reappeared, alerting customs officers and continuing to track the target person associated with the target baggage.

[0198] According to embodiments of this disclosure, the preliminary machine inspection target tracking method may further include the following steps S4323-S4324.

[0199] In step S4323, it is detected whether the target baggage and the target person have entered the exit area.

[0200] In step S4324, if either the target baggage or the target person enters the exit area, an alarm message is sent to the display terminal.

[0201] When the target baggage and / or the target person arrives at the exit area, the system will push a message to the display terminal that the target baggage and / or the target person has arrived at the exit. This can help staff to understand the information of the target baggage and the target person in a timely manner, which is conducive to improving the efficiency of security checks and reducing the probability of missed checks.

[0202] This method enables intelligent detection and tracking of target baggage and passengers, pushes suspicious information in real time, and provides early warnings before the baggage reaches the exit, allowing customs officers to prepare in advance, improving customs processing efficiency, and reducing missed inspections.

[0203] Figure 10 is a structural block diagram of a preliminary machine inspection target tracking system according to an embodiment of the present disclosure.

[0204] Another aspect of this disclosure provides an early detection target tracking system 1000. Exemplarily, referring to Figures 1 and 10, the early detection target tracking system 1000 may include: multiple partition cameras, multiple partition processing units, and a central server.

[0205] For example, the multiple zone cameras include, for instance, a baggage tagging camera 120 located in the baggage claim and hall area N1, a baggage tracking camera 1601 located in the baggage claim and hall area N2, and a baggage tracking camera 1602 located in the concealed area and exit area N3. The multiple zone cameras can be used to perform zoned detection of targets, obtaining multiple initial detection data for multiple zones, where the targets include baggage to be detected and people to be detected. For example, the baggage tagging camera 120 located in the baggage tagging area N1 can be used to detect baggage to be detected in the baggage tagging area N1. As another example, the baggage tracking camera 1601 located in the baggage claim and hall area N2 can detect both baggage to be detected and people to be detected in the baggage claim and hall area N2. As yet another example, the baggage tracking camera 1602 located in the concealed area and exit area N3 can detect both baggage to be detected and people to be detected in the concealed area and exit area N3.

[0206] For example, the multiple partition processing units include, for instance, a first processing unit M1, a second processing unit M2, and a third processing unit M3. The multiple partition processing units can be used to process corresponding initial detection data respectively, obtain first processed data for multiple partitions, and send the first processed data for multiple partitions to the central server.

[0207] For example, the partition processing unit can be integrated with the corresponding partition camera design.

[0208] For example, the partition processing unit can be designed independently of the corresponding partition camera.

[0209] For example, the first processing unit M1 is used to process the first detection data detected by the baggage tagging camera 120 in the baggage tagging area N1 to obtain the first processed data of the baggage tagging area. For example, the first processing unit M1 can process the initial detection data detected by the baggage tagging camera 120 in the baggage tagging area N1, such as filtering out target baggage, marking the address of the target baggage, and encoding the video frames and coordinate addresses of the target baggage into data packets.

[0210] For example, the second processing unit M2 can be used to process the second detection data detected by the baggage tracking camera 160 in the baggage claim area and the lobby area N2 to obtain the first processed data of the baggage claim area and the lobby area N2. For example, the second processing unit M2 can be used to detect all baggage to be detected in the baggage claim area and the lobby area N2, as well as people to be detected near the baggage to be detected. It can also add tracking addresses to the baggage to be detected and the people to be detected respectively to facilitate continuous tracking and detection. The second processing unit M2 can also package and encode the address coordinates and video frames of the detected baggage to be detected and the people to be detected into a data packet and send it to the central server 110.

[0211] For example, the third processing unit M3 can be used to process the third detection data detected by the baggage tracking camera 160 in the concealed area and the exit area N3 to obtain the first processed data of the concealed area and the exit area N3.

[0212] For example, the central server 110 can process first processing data from multiple partitions to obtain second processing data from multiple partitions, and track and detect targets within multiple partitions based on the second processing data from multiple partitions. For instance, the central server 110 can obtain the first characteristics of target luggage in baggage identification area N1 based on the first processing data of baggage identification area N1 processed by the first processing unit M1. As another example, the central server 110 can also obtain the second characteristics of luggage to be detected and the third characteristics of the person to be detected in baggage collection and hall area N2 based on the first processing data of baggage claim and hall area N2 processed by the second processing unit M2, and filter out target luggage and target person in baggage claim and hall area N2 through comparison.

[0213] This design addresses the issue of excessive reliance on human judgment in the initial machine inspection of target luggage and individuals, particularly the high risk of missed detection during peak hours. Compared to electronic fence locks, it effectively reduces installation and maintenance costs and solves the problem of tracking lost luggage and individuals independently. Furthermore, by refining the initial machine inspection scenario and adopting a cloud-edge collaborative deployment approach, single-view target detection and tracking are placed at the edge cameras, improving real-time detection performance. The central server performs differentiated calculations and analysis based on the camera detection results, effectively reducing central computing power consumption and resolving the computing bottleneck during peak hours.

[0214] For example, the central server 110 can also associate and match target luggage and target people, and then combine the partition processing units of each area and cameras to continuously track and detect the target luggage and target people, such as continuous monitoring of target luggage and target people from different perspectives.

[0215] By linking and tracking target luggage with target individuals, the problem of not being able to track target individuals separately after target luggage is lost can be solved.

[0216] For example, continuing to refer to Figure 10, the preliminary machine inspection target tracking system 1000 may further include a display terminal 500. The display terminal 500 can be used to receive various information such as images and locations of target luggage, images and locations of target persons, abnormal alert messages, and alarm information. For example, the display terminal can display the screens that require attention in each zone, and can also receive alert messages from each zone.

[0217] This design helps staff to understand the information of the target luggage and the target person in a timely manner, enabling them to conduct relevant inspections and processing more promptly and accurately, thus improving the efficiency of security checks.

[0218] Figure 11 is a structural block diagram of a central server according to an embodiment of the present disclosure.

[0219] According to an embodiment of this disclosure, referring to FIG11, the central server 110 may include a first feature extraction module 1101, a second feature extraction module 1102, a comparison module 1103, and an association module 1104.

[0220] For example, the first feature extraction module 1101 can be used to extract a first feature of the target baggage. For instance, it can extract the first feature of the target baggage detected in the baggage identification area N1.

[0221] For example, the second feature extraction module 1102 can be used to extract the second feature of the baggage to be inspected and the third feature of the person to be inspected. For example, it can extract the second feature of the baggage to be inspected and the third feature of the person to be inspected in the baggage claim and hall area N2 and / or the concealed area and exit area N3.

[0222] For example, the comparison module 1103 can be used to compare the second feature of the baggage to be detected with the first feature of the target baggage to determine whether the baggage to be detected is the target baggage.

[0223] For example, the association module 1104 can be used to associate target luggage with target person.

[0224] The first feature extraction module extracts features from target baggage in baggage identification area N1, reducing computational load and improving real-time detection. The second feature extraction module performs target locking and feature extraction on baggage and people to be detected in baggage claim area N2 and / or hidden areas and exit area N3, ensuring accuracy and timeliness of detection. By refining the initial machine inspection scenario, the central server processes information according to the refined scenario, which helps reduce the central computing power consumption and solves the computing power bottleneck problem during peak traffic periods.

[0225] According to an embodiment of this disclosure, continuing to refer to FIG11, the central server 110 may further include: a pairing group generation module 1105 and a pairing group global cache module 1106.

[0226] For example, the pairing group generation module 1105 can be used to generate a pairing group of target luggage and target person based on the results of the comparison module 1103 and the association module 1104.

[0227] For example, the pairing group global cache module 1106 can be used to store and update the characteristics of the target luggage and the characteristics of the target person.

[0228] This design allows target luggage and target person to be paired together, enabling convenient cross-view tracking of both. Even if the target luggage and target person are separated, their real-time status can be monitored simultaneously, solving the problem of not being able to track the target person separately after the target luggage is lost.

[0229] According to an embodiment of this disclosure, continuing to refer to FIG11, the central server 110 may further include: a baggage global cache module 1107. The baggage global cache module 1107 can be used to store and update the first characteristics of the target baggage.

[0230] This design allows for clearer and more accurate identification of the target baggage, which helps improve the accuracy of tracking and detection and reduce the chance of missed detection.

[0231] In some embodiments, the pre-inspection target tracking system 1000 may further include a baggage tag assigning device located in the baggage tagging area, which can be used to add a baggage tag to the target baggage, the baggage tag including a first tracking address.

[0232] This design facilitates subsequent tracking and monitoring of the target luggage, helps to quickly locate the target luggage and associated target individuals, and improves tracking and monitoring efficiency.

[0233] According to embodiments of this disclosure, the baggage tracking camera 160 can be installed in multiple areas such as baggage claim area, hall area, and exit area to continuously track and update the images and locations of target baggage and target person from multiple perspectives, thereby facilitating timely processing by staff and improving security check efficiency.

[0234] For example, the target person is all pedestrians whose coordinates overlap with the target baggage within a unit of time. For example, the unit of time is less than or equal to 10 seconds. For example, a target baggage can be associated with one or more target people.

[0235] By setting up multiple tracking cameras in various areas such as baggage claim, the hall area, and the exit area, cross-view tracking of target baggage and target person can be achieved, which can solve the problem of not being able to track the target person alone after the target baggage is lost.

[0236] The above-described one or more embodiments of this disclosure have the following beneficial effects:

[0237] (1) It solves the problem that the discovery of target luggage and target person in the early inspection of related equipment relies too much on human subjective judgment, especially the high risk of missed inspection during peak traffic periods. At the same time, compared with electronic fence locks, it effectively reduces installation and maintenance costs and solves the problem that the target person cannot be tracked separately after the target luggage is lost.

[0238] (2) By refining the early-stage machine inspection scenario and adopting a cloud-edge collaborative deployment approach, single-view target detection and tracking are placed on the edge camera side, improving the real-time performance of detection. The central server performs differentiated calculation and analysis based on the camera's detection results, effectively reducing the central computing power consumption and solving the computing power bottleneck problem during peak traffic periods.

[0239] (3) The system will track the target baggage and the target person together. When the physical identification of the target baggage is found to be damaged, an alarm message will be issued in real time, and the target person associated with the baggage will continue to be tracked. When the target baggage is covered in the concealed area and reappears in the hall area, the system will issue an alarm message for the target baggage that has entered the concealed area within a specified time and has not reappeared, reminding customs officers to pay attention, and will continue to track the target person associated with the target baggage. When the target baggage and the target person that have been lost or destroyed arrive at the exit area, the system will push a message that the target person has arrived at the exit.

[0240] (4) Intelligent detection and tracking of target baggage and passengers, real-time push of suspicious information, and early warning before reaching the exit, so that customs officers can prepare in advance, improve customs processing efficiency, and reduce missed inspections.

[0241] Those skilled in the art will understand that the embodiments described above are exemplary and can be improved upon. The structures described in the various embodiments can be freely combined without causing any conflict in structure or principle.

[0242] After a detailed description of the preferred embodiments of this disclosure, those skilled in the art will clearly understand that various changes and modifications can be made without departing from the scope and spirit of the appended claims, and that this disclosure is not limited to the implementation of the exemplary embodiments described in the specification.

Claims

1. An early inspection target tracking method, comprising: partitioning detection of a target to obtain a plurality of initial detection data of a plurality of partitions, the target comprising luggage to be detected and / or a person to be detected; processing, by a partition processing unit of each of the plurality of partitions, the corresponding initial detection data to obtain first processing data of the plurality of partitions; sending the first processing data of the plurality of partitions to a central server; processing, by the central server, the first processing data of the plurality of partitions to obtain second processing data of the plurality of partitions; and tracking detection of the target in the plurality of partitions according to the second processing data of the plurality of partitions. The plurality of partitions comprises a luggage identification area, a luggage extraction and lobby area, a concealed area, and an exit area.

2. The method of claim 1, wherein, The partitioning detection of the target to obtain a plurality of initial detection data of a plurality of partitions comprises: detecting the luggage to be detected in the luggage identification area to obtain first detection data of the luggage identification area; detecting the luggage to be detected and the person to be detected in the luggage extraction and lobby area to obtain second detection data of the luggage extraction and lobby area; and detecting the luggage to be detected and the person to be detected in the concealed area and the exit area to obtain third detection data of the concealed area and the exit area. The partition processing unit of the plurality of partitions comprises a first processing unit, a second processing unit, and a third processing unit.

3. The method of claim 2, wherein, The processing, by the partition processing unit of each of the plurality of partitions, the corresponding initial detection data to obtain first processing data of the plurality of partitions comprises: processing, by the first processing unit, the first detection data to obtain first processing data of the luggage identification area; processing, by the second processing unit, the second detection data to obtain first processing data of the luggage extraction and lobby area; and processing, by the third processing unit, the third detection data to obtain first processing data of the concealed area and the exit area. The processing, by the first processing unit, the first detection data to obtain first processing data of the luggage identification area comprises:

4. The method of claim 3, wherein, identifying processing, by the first processing unit, the first detection data to determine target luggage that needs to be focused on; adding a luggage mark to the target luggage, the luggage mark comprising a first tracking address; tracking detection of the target luggage based on the first tracking address to obtain luggage coordinates and video frames of the target luggage; and encoding the luggage coordinates and video frames of the target luggage together with the first tracking address to obtain first processing data of the luggage identification area. The processing, by the central server, the first processing data of the plurality of partitions to obtain second processing of the plurality of partitions data comprises processing the first processing data of the luggage identification area to obtain second processing data of the luggage identification area, 5. The method of claim 4, wherein, wherein the processing the first processing data of the luggage identification area to obtain second processing data of the luggage identification comprises: ​ extracting the luggage coordinates, the first tracking address and video frame data in the first processing data of the luggage identification area; obtaining the image of the target luggage from the video frame data according to the luggage coordinates; and analyzing and extracting the image of the target luggage to obtain the first feature of the target luggage.

6. The method of claim 5, wherein, the processing of the first processing data of the luggage identification area to obtain the second processing data of the luggage identification area further comprises: saving the first feature of the target luggage to the luggage global cache of the central server; and updating the first feature of the target luggage in the luggage global cache according to the current state of the target luggage.

7. The method of claim 3, wherein, the processing of the second detection data by the second processing unit to obtain the first processing data of the luggage extraction and lobby area comprises: obtaining the second position coordinates of all the to-be-detected luggage, and adding the second tracking address to the to-be-detected luggage; obtaining the third position coordinates of the to-be-detected person near the to-be-detected luggage, and adding the third tracking address to the to-be-detected person; and encoding the data containing the second position coordinates, the second tracking address and the video frame of the to-be-detected luggage and the data containing the third position coordinates, the third tracking address and the video frame of the to-be-detected person to obtain the first processing data of the luggage extraction and lobby area.

8. The method of claim 7, wherein, the processing of the first processing data of the multiple partitions by the central server to obtain the second processing data of the multiple partitions comprises: processing the first processing data of the luggage extraction and lobby area to obtain the second processing data of the luggage extraction and lobby area, wherein the processing of the first processing data of the luggage extraction and lobby area to obtain the second processing data of the same comprises: extracting the data containing the second position coordinates, the second tracking address and the video frame of the to- be-detected luggage and the data containing the third position coordinates, the third tracking address and the video frames of the to-be-detected person based on the first processing data of the luggage extraction and lobby area; obtaining the image of the to-be-detected luggage from the video frame containing the to-be-detected luggage according to the second position coordinates, and performing feature extraction on the image of the to-be-detected luggage to obtain the second feature of the to-be-detected luggage; obtaining the image of the to-be-detected person from the video frame containing the to-be-detected person according to the third position coordinates, and performing feature extraction on the image of the to-be-detected person to obtain the third feature of the to-be-detected person; comparing the second feature of the to-be-detected luggage with the first feature of the target luggage in the luggage global cache to determine whether the to-be-detected luggage is a target luggage; and calculating and reviewing the target person associated with the target luggage by using continuous frames to obtain the features of the target person associated with the target luggage.

9. The method of claim 8, wherein, the calculation and review of the target person associated with the target luggage by using continuous frames comprises: calculating and reviewing the person having coordinate overlap with the target luggage within a unit time by using continuous frames.

10. The method of claim 9, wherein, The method further includes: forming a pairing group between the target luggage and the associated target person, and saving the characteristics of the pairing group to the pairing group global cache of the central server.

11. The method of claim 10, wherein, The method further includes: simultaneously tracking and detecting the target luggage and the target person based on the second tracking address and the third tracking address, and updating the features of the optimal viewpoint of the target luggage and the target person to the global cache of the pairing group.

12. The method of claim 11, wherein, The method further includes sending the latest image and location of the target baggage to a display terminal during the tracking process.

13. The method of claim 12, wherein, The method further includes: sending an alarm message to the display terminal when an abnormal situation occurs in the pairing group, the abnormal situation including the loss of the target luggage; and / or, The method further includes sending an alarm message to the display terminal when the baggage tag is damaged.

14. The method of claim 10, wherein, The step of processing the first processing data of the multiple partitions using the central server to obtain the second processing data of the multiple partitions includes: processing the first processing data of the concealed area and the exit area to obtain the second processing data of the concealed area and the exit area. The process of processing the first processing data of the concealed area and the exit area to obtain the second processing data of the concealed area and the exit area includes: Based on the global cache of the pairing group on the central server, the target luggage and the target person are determined; The system detects whether the target luggage and / or the target person has entered the concealed area or the exit area. If so, it sends an alert message to the display terminal.

15. The method of claim 14, wherein, The method includes: detecting whether the target luggage has entered the concealed area; If the target luggage enters the concealed area, an abnormality alert message is sent to the display terminal.

16. The method of claim 14 or 15, wherein, The method further includes: detecting whether the target luggage and the target person have entered the exit area; If either the target luggage or the target person enters the exit area, an alarm message is sent to the display terminal.

17. A pre-detection target tracking system, comprising: Multiple partitioned cameras are used to perform partitioned detection of targets and obtain multiple initial detection data for multiple partitions. The targets include luggage to be detected and people to be detected. Multiple partition processing units are configured to process the corresponding multiple initial detection data respectively to obtain the first processed data of the multiple partitions, and send the first processed data of the multiple partitions to the central server; and A central server is configured to process the first processing data of the plurality of partitions to obtain the second processing data of the plurality of partitions, and to track and detect targets within the plurality of partitions based on the second processing data of the plurality of partitions.

18. The system of claim 17, wherein, The plurality of zoned cameras include baggage identification cameras and baggage tracking cameras. The baggage identification cameras are located in the baggage identification area, and the baggage tracking cameras are located in the baggage claim and hall area and the exit area.

19. The system of claim 17, wherein, The plurality of partition processing units include a first processing unit, a second processing unit, and a third processing unit. The first processing unit is used to process the first detection data detected by the baggage tag camera in the baggage tag area to obtain the first processed data of the baggage tag area; The second processing unit is used to process the second detection data detected by the baggage tracking camera in the baggage claim and hall areas to obtain the first processed data of the baggage claim and hall areas; and The third processing unit is used to process the third detection data detected by the baggage tracking camera in the concealed area and the exit area to obtain the first processed data of the concealed area and the exit area.

20. The system of claim 17, wherein, The central server includes a first feature extraction module, a second feature extraction module, a comparison module, and an association module, wherein... The first feature extraction module is used to extract the first feature of the target luggage; The second feature extraction module is used to extract the second feature of the luggage to be detected and the third feature of the person to be detected; The comparison module is used to compare the second feature of the baggage to be detected with the first feature of the target baggage in order to determine whether the baggage to be detected is the target baggage; The association module is used to associate the target luggage with the target person.

21. The system of claim 20, wherein, The central server also includes: A pairing group generation module, configured to generate a pairing group between the target luggage and the target person based on the results of the comparison module and the association module; and A pairing group global cache module is used to store and update records of the characteristics of the target luggage and the characteristics of the target person.

22. The system of claim 20, wherein, The central server also includes a baggage global cache module, which is used to store and update the first characteristics of the target baggage.

23. The system of any of claims 17-22, wherein, The tracking system also includes a display terminal, which is used to receive images and locations of the target luggage, images and locations of the target person, abnormal alert messages, and alarm information.

Images