Method and system for tracking a target object in a test object

Abstract

The present disclosure provides a method and system for tracking a target object in a subject. The method includes identifying the target object in a perspective image, determining first position information of the target object in a three-dimensional model of the subject, constructing a three-dimensional profile image of the subject using a mobile viewing device, determining second position information of the mobile viewing device relative to the three-dimensional profile image, obtaining three-dimensional coordinates of the target object relative to the mobile viewing device based on the first position information and the second position information, and associating the three-dimensional coordinates to the mobile viewing device, and guiding a user of the mobile viewing device to approach the target object by real-time viewing of a relative position of the mobile viewing device to the target object through the mobile viewing device. The system includes a processor and a mobile viewing device, and the processor includes an identification module.

Description

Technical Field

[0001] At least one embodiment of this disclosure relates to a method for tracking a target object in an object under test, and in particular, to a method and system for tracking a target object in an object under test. Background Technology

[0002] Transparent imaging is an indispensable tool in the field of security inspection, while digital radiography (DR) and computed tomography (CT) are both advantageous technologies for distinguishing materials.

[0003] In particular, during security inspections of large equipment such as containers and cargo trucks, if X-ray inspection equipment detects prohibited items such as explosives, drugs, firearms, or controlled knives inside the container or truck, the prohibited items need to be specifically inspected and determined. Current inspection methods generally only use X-ray imaging to determine the presence of suspected prohibited items; a definitive determination still requires human confirmation after the prohibited items are found within the inspected item.

[0004] Currently, there is no effective method for pinpointing the exact location of contraband within the inspected items. Generally, only perspective imaging can determine the approximate location of the contraband from one or more viewpoints, followed by manual searching. However, due to the large capacity of containers and cargo trucks, which may contain numerous items, current inspection methods cannot provide real-time updates on the relative positions of inspectors and contraband during manual tracking, nor can they effectively guide inspectors. Summary of the Invention

[0005] In view of at least one of the above-mentioned or other technical problems of the prior art, embodiments of the present disclosure provide a method and system for tracking a target object in an object under test, so as to quickly and accurately locate the target object.

[0006] According to one aspect of this disclosure, a method for tracking a target object in an object under test is provided, comprising: identifying the target object in a perspective image and determining first position information of a three-dimensional model of the target object in the object under test; constructing a three-dimensional shape image of the object under test using a mobile viewing device and determining second position information of the mobile viewing device relative to the three-dimensional shape image; obtaining three-dimensional coordinates of the target object relative to the mobile viewing device based on the first position information and the second position information; and associating the three-dimensional coordinates with the mobile viewing device, and viewing the relative position of the mobile viewing device to the target object in real time through the mobile viewing device to guide the user of the mobile viewing device to approach the target object.

[0007] In some embodiments of this disclosure, the method further includes acquiring first information and a perspective image of the object to be tested.

[0008] In some embodiments of this disclosure, constructing a three-dimensional shape image of the object under test using a mobile viewing device includes: identifying the first information; and constructing a three-dimensional shape image of the object under test corresponding to the first information.

[0009] In some embodiments of this disclosure, acquiring the radiographic image of the object under test includes scanning the object under test with X-rays and acquiring the radiographic image.

[0010] In some embodiments of this disclosure, obtaining a perspective image of the object under test includes scanning the object under test with X-ray computed tomography to obtain the three-dimensional perspective image.

[0011] In some embodiments of this disclosure, the step of identifying a target object in a perspective image and determining the first position information of the target object in the three-dimensional model of the object under test includes: identifying and marking the target object in the perspective image to obtain a marked target from one viewpoint; adding new marked targets by increasing the viewpoint to obtain at least one marked target from another viewpoint; and determining the first position information of the target object within the three-dimensional model of the space defined by the object under test based on the viewpoint and the marked target.

[0012] In some embodiments of this disclosure, identifying the target object in the perspective image and determining the first position information of the target object in the three-dimensional model of the object under test includes: identifying and marking the target object in the perspective image to obtain marked targets from at least two viewpoints; and determining the first position information of the target object within the three-dimensional model of the space defined by the object under test based on the viewpoints and the marked targets.

[0013] In some embodiments of this disclosure, constructing a three-dimensional shape image of the object under test includes: acquiring features of multiple outer surfaces of the object under test using a mobile viewing device; and constructing a three-dimensional shape image of the object under test based on the features of the multiple outer surfaces.

[0014] In some embodiments of this disclosure, obtaining the three-dimensional coordinates of the target object relative to the mobile viewing device based on the first position information and the second position information includes: constructing a three-dimensional coordinate system of the three-dimensional shape image with a point on the object to be measured as the origin; generating a first coordinate point of the first position information in the three-dimensional coordinate system; generating a second coordinate point of the second position information in the three-dimensional coordinate system; and obtaining the three-dimensional coordinates of the first coordinate point relative to the second coordinate point in the three-dimensional coordinate system.

[0015] In some embodiments of this disclosure, associating the three-dimensional coordinates with a mobile viewing device and using the mobile viewing device to view the relative position of the mobile viewing device to the target object in real time, so as to guide the user of the mobile viewing device to approach the target object, includes: associating the three-dimensional coordinates with the mobile viewing device; setting the viewing angle of the mobile viewing device as an initial tracking position, setting the direction from the initial tracking position to the target object as a first tracking direction; and moving the mobile viewing device along the first tracking direction, such that the distance between the tracking position of the mobile viewing device after movement and the target object decreases, and stopping movement when the distance decreases to a preset value.

[0016] In some embodiments of this disclosure, associating the three-dimensional coordinates with a mobile viewing device and viewing the relative position of the mobile viewing device to the target object in real time through the mobile viewing device to guide the user of the mobile viewing device to approach the target object further includes: when the mobile viewing device moves along a second tracking direction different from the first tracking direction, and the distance between the tracking position of the mobile viewing device after movement and the target object increases, adjusting the movement direction of the mobile viewing device to the first tracking direction and moving along the first tracking direction, so that the distance between the tracking position of the mobile viewing device after movement and the target object decreases.

[0017] In another aspect of this disclosure, a system for tracking a target object in an object under test is provided, comprising: a processor including: a recognition module configured to recognize and mark the target object in a perspective image to determine first position information of the target object in a three-dimensional model of the object under test; and a mobile viewing device configured to acquire a three-dimensional shape image of the object under test; wherein the mobile viewing device is further configured to determine second position information of the mobile viewing device relative to the three-dimensional shape image; acquire three-dimensional coordinates of the target object relative to the mobile viewing device based on the first and second position information; associate the three-dimensional coordinates with the mobile viewing device; and view the relative position of the mobile viewing device to the target object in real time through the mobile viewing device to guide the user of the mobile viewing device to approach the target object.

[0018] In some embodiments of this disclosure, the system further includes a scanning device adapted to scan the object under test to obtain a perspective image of the object under test.

[0019] In some embodiments of this disclosure, the scanning apparatus includes an X-ray scanning imaging device adapted to acquire a perspective image of the object under test from at least one viewpoint.

[0020] In some embodiments of this disclosure, the scanning apparatus includes an X-ray tomography device adapted to acquire a three-dimensional perspective image of the object under test.

[0021] In some embodiments of this disclosure, the system further includes a data acquisition device adapted to acquire first information about the object under test.

[0022] In some embodiments of this disclosure, the mobile viewing device further includes a verification module configured to verify first information about the object under test.

[0023] In some embodiments of this disclosure, the processor further includes a retrieval module configured to retrieve first location information of a target object in a test object corresponding to the first information from a database; the test object includes a container or a vehicle; the first information of the test object includes a container number or a vehicle license plate number.

[0024] In some embodiments of this disclosure, the recognition module is further configured to: identify a target object in the object under test in the perspective image, and mark the target object to obtain a marked target from one perspective; add new marked targets by adding perspectives and supplementing the markings to obtain marked targets from at least two perspectives; and determine the first position information of the target object within a three-dimensional model of the space defined by the object under test based on the perspective and the marked target.

[0025] In some embodiments of this disclosure, the recognition module is further configured to: identify a target object in the object under test in the perspective image, and mark the target object to obtain a marked target from at least two perspectives; and determine, based on the perspectives and the marked target, the first position information of the target object within a three-dimensional model of the space defined by the object under test.

[0026] In some embodiments of this disclosure, the mobile viewing device includes a lidar module configured to acquire features of multiple outer surfaces of the object under test and construct a three-dimensional shape image of the object under test based on the features of the multiple outer surfaces.

[0027] In some embodiments of this disclosure, the mobile viewing device is further configured to: construct a three-dimensional coordinate system of the three-dimensional shape image with a point on the object to be measured as the origin; generate a first coordinate point of the first position information in the three-dimensional coordinate system; generate a second coordinate point of the second position information in the three-dimensional coordinate system; and obtain the three-dimensional coordinates of the first coordinate point relative to the second coordinate point in the three-dimensional coordinate system.

[0028] In some embodiments of this disclosure, the mobile viewing device is configured to: stop moving when it moves along a second tracking direction different from the first tracking direction and the distance between the tracking position of the mobile viewing device after movement and the target object increases; and adjust the moving direction of the mobile viewing device to the first tracking direction, move along the first tracking direction such that the distance between the tracking position of the mobile viewing device after movement and the target object decreases, and stop moving when the distance decreases to a preset value.

[0029] The method and system for tracking a target object in an object under test according to the above embodiments of this disclosure identify the target object in a perspective image to determine the position information of the target object's three-dimensional model in the object under test. The perspective image and the three-dimensional shape image of the object under test are correlated to register the position of the target object in three-dimensional space. Furthermore, based on the registered information, the position of the target object in three-dimensional space is associated with a mobile viewing device, allowing the user to understand the relative position of the mobile viewing device and the target object and guiding the user closer to the target object, thereby improving the convenience and accuracy of the user's target object tracking. Attached Figure Description

[0030] The foregoing contents, as well as other objects, features, and advantages of this disclosure, will become clearer from the following description of embodiments with reference to the accompanying drawings, in which:

[0031] Figure 1The flowchart illustrates a method for tracking a target object in an object under test according to an illustrative embodiment of the present disclosure.

[0032] Figure 2 A flowchart illustrating a method for tracking a target object in a test object according to another illustrative embodiment of the present disclosure is shown.

[0033] Figure 3 Schematic illustration Figure 2 A flowchart of one implementation method of step S200;

[0034] Figure 4 Schematic illustration Figure 2 A flowchart of another implementation method of step S200;

[0035] Figure 5 Schematic illustration Figure 2 A flowchart of one implementation method of step S300;

[0036] Figure 6 The illustration shows a partial display effect of a three-dimensional shape image according to an embodiment of the present disclosure;

[0037] Figure 7 The diagram illustrates a block diagram of a system for tracking a target object in an object under test, according to an illustrative embodiment of the present disclosure.

[0038] Figure 8 Schematic illustration Figure 7 A block diagram of a system according to an illustrative embodiment is shown.

[0039] Figure 9 Schematic illustration Figure 7 A block diagram of another illustrative embodiment of the system is shown;

[0040] Figure 10 The illustration shows a schematic diagram of the structure of a scanning device according to an illustrative embodiment of the present disclosure;

[0041] Figure 11 The schematic diagram illustrates the structure of a scanning device according to another illustrative embodiment of the present disclosure; and

[0042] Figure 12 The diagram illustrates a schematic embodiment of a three-dimensional shape image acquisition device. Detailed Implementation

[0043] 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 merely illustrative and 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.

[0044] 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.

[0045] 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.

[0046] When using expressions such as "at least one of A, B, and C", they should generally be interpreted in accordance with the meaning that is commonly understood by a person skilled in the art (e.g., "a system having at least one of A, B, and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B, and C, etc.).

[0047] According to a general inventive concept of this disclosure, a method for tracking a target object in a test object is provided.

[0048] Figure 1 The flowchart illustrates a method for tracking a target object in a test object according to an illustrative embodiment of the present disclosure.

[0049] refer to Figure 1As shown, according to an illustrative embodiment of this disclosure, a method for tracking a target object in an object under test is provided, including identifying the target object in a perspective image and determining the first position information of the target object's three-dimensional model in the object under test; constructing a three-dimensional shape image of the object under test using a mobile viewing device 2 and determining the second position information of the mobile viewing device relative to the three-dimensional shape image; obtaining the three-dimensional coordinates of the target object relative to the mobile viewing device 2 based on the first and second position information; associating the three-dimensional coordinates with the mobile viewing device 2, and viewing the relative position of the mobile viewing device to the target object in real time through the mobile viewing device 2, so as to guide the user of the mobile viewing device 2 to approach the target object.

[0050] In some embodiments of this disclosure, the target object can be displayed on the mobile viewing device 2 while the user is viewing the relative position of the mobile viewing device 2 to the target object in real time.

[0051] In one specific embodiment, the target object may be concretely displayed in the mobile viewing device 2. For example, the target object may be displayed in a visual form as a point in a three-dimensional coordinate system or as a region based on the outline of the target object in the display component (e.g., a display screen) of the mobile viewing device 2. More specifically, a point on the target object may be used as a point displayed in the three-dimensional coordinate system of the mobile viewing device 2. For example, the geometric center of the target object, a point on the outline of the target object, and / or a point inside the target object.

[0052] In another specific embodiment, the target object may be displayed on the mobile viewing device 2 in the form of distance, orientation, and / or other parameters relative to the mobile viewing device 2. For example, the target object may be displayed at the shortest distance located on one side of the viewing angle and on the side extending in the direction of the viewing angle.

[0053] In some embodiments of this disclosure, the perspective images obtained include perspective images of objects under test such as containers (including ISO air freight containers) and cargo trucks.

[0054] In other embodiments of this disclosure, the tracking method further includes acquiring first information and a perspective image of the object to be measured.

[0055] Figure 2 A flowchart illustrating a method for tracking a target object in a test object according to another illustrative embodiment of the present disclosure is shown.

[0056] refer to Figure 2 As shown, in some specific embodiments, the tracking method includes steps S100 to S600.

[0057] In step S100, the acquisition device 3 acquires the first information of the object to be tested (such as a container or a cargo truck), the scanning device 4 acquires a perspective image of the object to be tested, and the first information and the perspective image of the object to be tested corresponding to the first information are associated (e.g., a data mapping relationship is established) and stored in a database for later retrieval. The first information is characterized as information used to identify the object to be tested, including but not limited to at least one of the following: the container's identification number, the cargo truck's license plate number, and an information code corresponding to the object to be tested.

[0058] In step S200, the processor 1 identifies the target object in the perspective image to determine the first position information of the target object's three-dimensional model within the object to be tested. This first position information is then associated with the perspective image and stored in a database for later retrieval. The three-dimensional model within the object to be tested includes, but is not limited to, a first three-dimensional model constructed using the length, width, and height of the inner wall of the accommodating space defined by the object to be tested as the X-axis, Y-axis, and Z-axis, respectively. The first position information includes, but is not limited to, coordinate points within the first three-dimensional model established based on the object to be tested. The target object includes, but is not limited to, explosives, flammable materials, drugs, firearms, and prohibited items such as controlled knives. It should be noted that in step S200, if no target object (prohibited item) is identified in the perspective image of the object to be tested, the object can be released directly without further steps.

[0059] In step S300, the mobile viewing device 2 is used to identify the second information, construct a three-dimensional shape image of the object under test, and determine the second position information of the mobile viewing device 2 relative to the three-dimensional shape image. The second information is characterized as information used to identify the object under test, including but not limited to at least one of the following: container number, truck license plate number, and information code corresponding to the object under test. The second position information includes but is not limited to coordinate points within a second three-dimensional model established based on the three-dimensional shape image.

[0060] In step S400, the first location information and / or perspective image containing the first location information are retrieved from the database based on the second information, corresponding to the first information that matches the second information.

[0061] In step S500, the three-dimensional coordinates of the target object relative to the mobile viewing device are obtained. Since the position of the accommodating space defined by the object under test relative to the external shape of the object under test is relatively unique, the position of the first three-dimensional model (including first position information) constructed based on the accommodating space of the object under test relative to the three-dimensional shape image of the object under test is also relatively unique. Furthermore, the three-dimensional shape image is constructed through the mobile viewing device 2, and the relative position of the mobile viewing device 2 and the three-dimensional shape image is known; the mobile viewing device 2 can be used as another point in the three-dimensional coordinate system. Therefore, the corresponding first position information and the three-dimensional shape image can be associated (including but not limited to data association or image association established using at least one of pointer and label information) to represent the coordinates of the target object in the second three-dimensional model. In other words, the relative position between two points in the three-dimensional coordinate system (the target object and the mobile viewing device 2) is known, and the relative position of the mobile viewing device 2 to the target object can be viewed in real time through the mobile viewing device 2, guiding the user of the mobile viewing device 2 to approach the target object. The three-dimensional coordinates of the target object relative to the mobile viewing device include directly related or indirectly related three-dimensional coordinates. The directly related three-dimensional coordinates are represented as the three-dimensional coordinates of the target object relative to the mobile viewing device; the indirectly related three-dimensional coordinates are represented as the first three-dimensional coordinates of the target object relative to a third point other than the target object and the mobile viewing device, and the second three-dimensional coordinates of the third point relative to the mobile viewing device. Based on the first and second three-dimensional coordinates, the three-dimensional coordinates of the target object relative to the mobile viewing device can be calculated. The third point includes, but is not limited to, a point on the object under test, which can be used as the origin of the three-dimensional coordinate system for establishing the second three-dimensional model.

[0062] In step S600, the three-dimensional coordinates are associated with the mobile viewing device 2 (including but not limited to displaying the three-dimensional coordinates on the mobile viewing device 2 and constructing image information of the three-dimensional coordinate system to express the three-dimensional coordinates in the three-dimensional coordinate system).

[0063] In one specific embodiment, a vehicle is scanned using an X-ray imaging device to obtain a perspective image of the vehicle. If a contraband is detected in the vehicle, and only one viewpoint is currently available for marking, additional viewpoints can be added to manually supplement the marking, ensuring that the contraband is marked from at least two viewpoints. Finally, based on the viewpoints and marking targets, the first position information of the target object's three-dimensional model within the object under test is confirmed. Here, for example, if the target object has marking targets from two viewpoints, the first position information of the geometric center of the target object's three-dimensional model within the object under test can be determined based on the viewpoint (i.e., the incident direction of the X-rays). In the following text, unless otherwise specified, the first position information of the target object includes the first position information of the target object's geometric center.

[0064] In this implementation, a perspective image of the object to be inspected is acquired during the security check, and initial information is associated with the perspective image. Subsequently, the target object in the perspective image is identified. If the acquired perspective image shows the presence of a target object (contraband), a three-dimensional shape image of the object to be inspected is further acquired. If the acquired perspective image does not show a target object (contraband), the security check of the object to be inspected is completed. This eliminates the need to construct a three-dimensional shape image for each object to be inspected, effectively reducing the amount of data processing.

[0065] In one specific embodiment, it includes, but is not limited to, using a point in the object to be measured (such as the midpoint of a side wall of a container, or at least one of the front or rear license plates of a freight truck) as the origin to obtain the three-dimensional coordinates of the target object relative to the origin.

[0066] In this implementation, since the relative position of the origin and the object under test is fixed, establishing a three-dimensional coordinate system based on the origin facilitates the calibration of other coordinate points within the three-dimensional coordinate system (including but not limited to the target object and / or the mobile viewing device). Furthermore, since the aforementioned three-dimensional shape image is established using the mobile viewing device 2, which can also be considered a point in the three-dimensional coordinate system, the relative position between the mobile viewing device 2 and, for example, the aforementioned origin can be determined, thereby allowing the acquisition of the relative position (three-dimensional coordinates) of the target object relative to the mobile viewing device 2.

[0067] According to one illustrative embodiment of this disclosure, obtaining a perspective image of the object under test includes, but is not limited to, obtaining a perspective image by scanning the object under test with X-rays.

[0068] Figure 3 Schematic illustration Figure 2 A flowchart of one implementation method of step S200.

[0069] refer to Figure 3 As shown, in one implementation of step S200, the following sub-steps S210 to S240 are included.

[0070] In step S210, the recognition module of processor 1 identifies the target object in the perspective image and marks the target object. It should be noted that the specific method for identifying the target object is not a key point of this disclosure; any image marking method known in the art may be applied, and will not be elaborated further.

[0071] In step S220, processor 1 determines whether the target object has markers with two or more viewpoints.

[0072] If two or more marked targets are obtained, then in step S230, the position information of the target object within the three-dimensional model of the space defined by the object to be measured is determined according to the viewpoint and the marked target.

[0073] If only one viewpoint is obtained as the marked target, then in step S240, by changing the viewpoint, new marked targets are added to supplement the marks, so as to obtain at least one marked target from another viewpoint, and then the process returns to sub-step S220.

[0074] In such implementations, if the perspective image is acquired from a single viewpoint, it only defines a plane in space. Therefore, it is necessary to acquire other perspective images from another viewpoint, and then manually mark the target object in the perspective image acquired from that viewpoint, thereby determining the target object's position information in the 3D model. If the perspective image is acquired from two different viewpoints (such as two mutually orthogonal viewpoints), a 3D model can be formed in space.

[0075] According to another illustrative embodiment of this disclosure, obtaining a perspective image of the object under test includes, but is not limited to, obtaining a perspective image of the object under test by X-ray computed tomography.

[0076] Figure 4 Schematic illustration Figure 2 A flowchart of another implementation method of step S200.

[0077] The X-ray computed tomography (CT) scan used in this implementation differs from the aforementioned method in that it eliminates the need to acquire multiple perspective images from multiple viewpoints and obtain the marked target from multiple viewpoints. (Reference) Figure 4 As shown, in another implementation of step S200, the following sub-steps S250 to S260 are specifically included.

[0078] In step S250, a three-dimensional tomographic image is reconstructed based on multiple tomographic scan images (perspective images) of the object to be tested, and a marker is obtained by marking the three-dimensional tomographic image.

[0079] In step S260, the first position information of the target object in the three-dimensional tomographic image is determined based on the first three-dimensional model established by the three-dimensional tomographic image.

[0080] In this implementation, X-ray computed tomography itself has three-dimensional imaging capabilities, so the first position information of the target object can be obtained without determining the number of viewing angles.

[0081] Figure 5 Schematic illustration Figure 2 A flowchart of one implementation method of step S300.

[0082] In one implementation of step S300, the following sub-steps S310 to S330 are included.

[0083] In step S310, second information is identified for the object under test for which the first information was collected in step S100 using the acquisition device 3. The second information can be similar to the first information, such as a container number. As described below, the second information of the object under test can be collected using a verification module.

[0084] In step S320, features of multiple outer surfaces of the object under test can be acquired by moving the viewing device 2.

[0085] In step S330, a three-dimensional shape image of the object under test is constructed based on the features of the plurality of outer surfaces.

[0086] In step S340, second position information of the mobile viewing device relative to the three-dimensional shape image is determined.

[0087] According to an illustrative embodiment of this disclosure, steps S320 and S330 include using the lidar module of the mobile viewing device 2 to collect the original point cloud data of the outer surface of the object under test, then performing registration, stitching, noise reduction and simplification on the original point cloud data to obtain the entity point cloud data of the object under test, and then using the entity point cloud data to perform modeling (including but not limited to at least one of geometry creation, plane creation and texture mapping) to generate a three-dimensional shape image of the object under test.

[0088] According to an illustrative embodiment of the present disclosure, step S340 includes selecting a point on the object to be tested as the origin, establishing a second three-dimensional model based on the origin and the three-dimensional shape image of the object to be tested, and representing the mobile viewing device 2 as a point in the second three-dimensional model in a three-dimensional coordinate system established based on the second three-dimensional model.

[0089] According to another illustrative embodiment of this disclosure, constructing a three-dimensional shape image of the object under test includes acquiring features of multiple outer surfaces of opposite sides and top of the object under test using a three-dimensional shape image acquisition device 5. Based on common features in two adjacent shape images, the multiple shape images are stitched together to form a three-dimensional shape image of the object under test.

[0090] In one specific embodiment, a capturing device 52, such as a camera, is mounted on a gantry 51. When a vehicle passes through the gantry 51, three capturing devices 52 are used to capture images of the vehicle's exterior shape, including at least the opposite sides and top. The types of vehicles may include, but are not limited to, large trucks, light trucks, SUVs, and sedans.

[0091] In this implementation, the 3D shape image acquisition device 5 is independent of the mobile viewing device 2 and can be positioned side-by-side with the object to be inspected, so that a 3D shape image can be acquired simultaneously with the inspection. This eliminates the need for the user to actively construct the 3D shape image, effectively reducing the user's workload.

[0092] Figure 6 The illustration shows a partial display effect of a three-dimensional shape image according to an embodiment of the present disclosure.

[0093] According to embodiments of this disclosure, when a vehicle passes over a gantry 51, multiple imaging devices 52 capture images of the vehicle's exterior and send the captured images to a vehicle exterior panoramic stitching device 53. The vehicle exterior panoramic stitching device 53 stitches the multiple exterior images together based on common features found in adjacent exterior images captured by the same imaging device 52, thereby stitching the multiple exterior images into a panoramic image of the vehicle. The panoramic image may include the vehicle's front surface, rear surface, and left surface. Figure 6 As shown in (a), right surface ( Figure 6 As shown in (b), the upper surface ( Figure 6 (c) shown) and the lower surface.

[0094] According to an illustrative embodiment of this disclosure, due to the containment space defined by the object under test... ( The relative position of a container (such as a freight truck container) to the object being measured (the freight truck) is unique. Therefore, the position of the 3D model built based on the container space relative to the object being measured is also unique. The 3D model and the 3D shape image of the object being measured are associated, and a 3D coordinate system is constructed with a point on the object being measured (such as the midpoint of the front license plate of the freight truck) as the origin. The position information (such as coordinate points) of the target object in the 3D model is mapped onto the 3D coordinate system to obtain the 3D coordinates of the target object in the 3D coordinate system.

[0095] In this implementation, the perspective image, the 3D shape image, and the positional information of the object under test and the target object are only related in terms of data. This reduces the amount of data that needs to be processed and simplifies the operation.

[0096] According to another illustrative embodiment of this disclosure, since a three-dimensional model can be obtained from a perspective image, and a three-dimensional shape image of the object under test can be obtained, the perspective image and the three-dimensional shape image can be stitched together to obtain a stitched image. The steps for obtaining the stitched image include: obtaining multiple first identification features of the object under test based on the perspective image; obtaining multiple second identification features of the object under test based on the three-dimensional shape image; obtaining the stitched image based on the first and second identification features; constructing a three-dimensional coordinate system of the stitched image with a point on the object under test as the origin; and obtaining the three-dimensional coordinates of the target object within the three-dimensional coordinate system.

[0097] According to one illustrative embodiment of this disclosure, the first identification feature includes features of the edge portion of a perspective image, and the second identification feature includes features of the edge portion of a three-dimensional shape image.

[0098] In one specific embodiment of this disclosure, five feature points on the edge contour of the vehicle are obtained based on a perspective image as five first recognition features, and five feature points on the edge contour features of the vehicle are obtained based on a three-dimensional image as five second recognition features. The five first recognition features and the five second recognition features are aligned to obtain multiple stitched images, and the stitched image with the highest alignment accuracy between the first recognition features and the second recognition features is selected.

[0099] In this implementation, the perspective image and the three-dimensional shape image are stitched together to form a composite image. The composite image is represented in three-dimensional space, with both the target object and the mobile viewing device 2 visualized in a three-dimensional coordinate system (for example, the mobile viewing device 2 uses the user's viewpoint as a coordinate point in a second coordinate system, and displays the relative positions of the target object and the mobile viewing device in the three-dimensional coordinate system). This concretely demonstrates the distance between the mobile viewing device 2 and the target object, making the user's tracking process more intuitive.

[0100] According to an illustrative embodiment of this disclosure, associating three-dimensional coordinates with a mobile viewing device 2 and using the mobile viewing device 2 to detect the relative position of the mobile viewing device 2 to a target object in real time to guide the user of the mobile viewing device 2 closer to the target object includes: associating three-dimensional coordinates with the mobile viewing device 2; setting the viewing angle of the mobile viewing device 2 as the initial tracking position and the direction from the initial tracking position to the target object as the first tracking direction; moving the mobile viewing device 2 along the first tracking direction, thereby reducing the distance between the tracking position of the mobile viewing device 2 and the target object, and stopping the movement when the distance is reduced to a preset value. Here, the preset value can be set to half of the minimum distance in a certain direction of the object to be measured, such as half of the length in the width direction of a container. Typically, when the distance between the mobile viewing device and the target object is the preset value, the mobile viewing device has already accurately located the target object and cannot or does not need to move further.

[0101] In one specific embodiment, associating three-dimensional coordinates with the mobile viewing device 2 includes displaying the three-dimensional coordinate system in the form of video and / or images on the mobile viewing device 2. The mobile viewing device 2 is further configured to operate on the displayed three-dimensional coordinate system, the operation being characterized by being able to zoom in, zoom out, or rotate a partial or all area of ​​the three-dimensional coordinate system (including rotating in three-dimensional space about a coordinate point in the three-dimensional coordinate system and / or rotating about an axis of the three-dimensional coordinate system).

[0102] According to an illustrative embodiment of this disclosure, associating three-dimensional coordinates with a mobile viewing device 2 and real-time detecting the relative position of the mobile viewing device 2 to the target object to guide the user of the mobile viewing device 2 closer to the target object further includes: when the mobile viewing device 2 moves along a second tracking direction different from the first tracking direction, and the distance between the tracking position of the mobile viewing device 2 after movement and the target object increases, stopping the movement, adjusting the movement direction of the mobile viewing device 2 to the first tracking direction, and moving along the first tracking direction to reduce the distance between the tracking position of the mobile viewing device 2 after movement and the target object. Here, when the distance between the tracking position of the mobile viewing device 2 after movement and the target object increases, the mobile viewing device 2 may vibrate, sound a bell, or display a text warning to prompt the user to adjust the movement direction of the mobile viewing device 2.

[0103] In this implementation, in the method for tracking a target object in the test object according to the embodiments of this disclosure, the mobile viewing device 2 can display the three-dimensional coordinates of the target object. The user can determine the initial tracking position of the mobile viewing device 2 and the tracking direction of the target object based on these three-dimensional coordinates. Then, the user can hold the mobile viewing device 2 and move it towards the target object. As the mobile viewing device 2 moves along the first tracking direction, the distance between the tracking position of the mobile viewing device 2 and the target object decreases, stopping when the distance reaches a preset value. Afterward, the specific location of the target object can be confirmed by conventional manual inspection, and it can be determined whether it is a contraband. In this way, the user can hold the mobile viewing device 2 and move it while the relative three-dimensional coordinates of the target object are displayed in real time on the mobile viewing device 2, which can essentially determine the specific location of the target object in the test object, thereby achieving accurate tracking and positioning of the target object, greatly shortening the time for manual tracking, improving image readability, and making it more convenient, faster, and more accurate to find suspects.

[0104] According to another general inventive concept of this disclosure, a system for tracking a target object in a test object is also provided.

[0105] Figure 7 The diagram illustrates a block diagram of a system for tracking a target object in an object under test, according to an illustrative embodiment of the present disclosure.

[0106] refer to Figure 7As shown, a system for tracking a target object within a test object includes a processor 1 and a mobile viewing device 2. The processor 1 includes a recognition module configured to identify and mark the target object in a perspective image to determine first position information of the target object. The mobile viewing device 2 is configured to acquire a three-dimensional shape image of the test object, determine second position information of the mobile viewing device 2 relative to the three-dimensional shape image, acquire the three-dimensional coordinates of the target object relative to the mobile viewing device 2 based on the first and second position information, and associate the three-dimensional coordinates with the mobile viewing device 2. The system also allows real-time detection of the relative position of the mobile viewing device 2 to the target object to guide the user of the mobile viewing device 2 closer to the target object.

[0107] Continue to refer to Figure 7 As shown, the mobile viewing device 2 includes a LiDAR module. The LiDAR module is configured to acquire raw point cloud data of the outer surface of the object under test, then perform registration, stitching, noise reduction, and simplification processing on the raw point cloud data to obtain solid point cloud data of the object under test. The solid point cloud data is then used to create a model (including but not limited to at least one of geometry creation, plane creation, and texture mapping) to generate a 3D shape image of the object under test. More specifically, the LiDAR module includes, but is not limited to, a LiDAR scanner.

[0108] In some embodiments of this disclosure, the acquired perspective images include perspective images of objects under test such as containers (including ISO air freight containers) and cargo trucks. The acquired perspective images can be two-dimensional perspective images obtained through X-ray scanning or three-dimensional perspective images obtained through CT scanning. A single two-dimensional perspective image obtained from an X-ray scan at one viewpoint is insufficient to determine the target object; therefore, it is necessary to perform X-ray scans at multiple viewpoints to obtain corresponding two-dimensional perspective images at each viewpoint, and then determine the target object based on multiple two-dimensional perspective images. Here, "multiple" generally refers to at least two.

[0109] In this implementation, in a system for tracking a target object within an object under test according to embodiments of the present disclosure, the mobile viewing device 2 can display the relative position of the target object and the mobile viewing device 2. This allows the user to hold the mobile viewing device 2 and track the target object on a three-dimensional image, improving image readability and facilitating faster and more accurate identification of suspects.

[0110] In one illustrative embodiment of this disclosure, the system for tracking a target object within a test object may optionally include a scanning device 4 configured to acquire a perspective image of the test object, such as a container (including ISO air freight containers) or a cargo truck. Alternatively, after acquiring the perspective image of the test object, the perspective image of the test object may be stored in a database, and the perspective image of the test object stored in the database may be directly retrieved during the current use.

[0111] Figure 8 Schematic illustration Figure 7 A block diagram of a system according to an illustrative embodiment is shown.

[0112] refer to Figure 8 As shown, the system for tracking a target object in the test object also includes a scanning device 4 suitable for scanning the test object to obtain a perspective image of the test object.

[0113] In one illustrative embodiment of this disclosure, the scanning device 4 includes an X-ray scanning imaging device suitable for acquiring perspective images of the object under test from at least two viewpoints.

[0114] In some embodiments, the mobile viewing device 2 may include a handheld terminal device, such as, but not limited to, smartphones, tablets, laptops, and desktop computers, or may be various unmanned electronic devices, including but not limited to drones and robots.

[0115] In one specific embodiment, the mobile viewing device 2 is a smartphone. The user can view their current tracking location on the smartphone screen and use this location as the initial tracking location. The user can swipe up, down, left, or right on the screen and manually select the desired location to confirm the tracking position. The user can also zoom in and out using two fingers to swipe relative to each other or in opposite directions on the screen, making it easier to view details. More specifically, the mobile viewing device 2 can be a smart terminal with a LiDAR scanner, such as an iPhone or iPad with LiDAR.

[0116] Continue to refer to Figure 8 As shown, the system for tracking a target object in the test object also includes an acquisition device 3 suitable for acquiring first information about the test object. More specifically, the acquisition device 3 can be a camera, such as a visible light camera.

[0117] In one specific embodiment, the camera identifies the vehicle's front license plate number and / or rear license plate number (first information).

[0118] In another specific embodiment, the camera identifies the container number (first information) on the ISO air container.

[0119] In yet another specific embodiment, the camera identifies the container number (first information) on the vehicle-mounted ISO aviation container.

[0120] Continue to refer to Figure 8 As shown, the system for tracking target objects in the test object also includes a verification module.

[0121] In one illustrative embodiment of this disclosure, the verification module and the identification module are communicatively connected and configured to verify the first information of the object under test. More specifically, the verification module may be a camera integrated into the mobile viewing device 2 and an image recognition component (including image recognition software) communicatively connected to the camera, configured to acquire image information of at least a portion of the object under test (including the portion containing the second information, such as a license plate), identify the acquired image information to identify the second information, and match and verify it with the first information stored in the database.

[0122] In this implementation, the acquisition device 3 is suitable for acquiring the first information of the object to be tested, and the verification module is suitable for acquiring the second information of the object to be tested, and comparing the second information with the first information to verify the first information.

[0123] Continue to refer to Figure 8 As shown, the system for tracking target objects within the test object also includes a retrieval module (not shown) in processor 1. The retrieval module is configured to retrieve, from a database, first location information and / or a perspective image containing the first location information of the test object, corresponding to the first information. The test object may include a container or a vehicle, and the first information of the test object may include a container number or a vehicle license plate number. More specifically, the retrieval module may be a functional module that retrieves data from a database or a cloud platform storing relevant information about the test object (including a 3D model and location information within the 3D model) via pipeline communication.

[0124] In this implementation, after the verification module verifies the first information, it retrieves the first location information corresponding to the first information and / or the perspective image containing the first location information stored in the database.

[0125] Figure 10 The illustration shows a schematic diagram of the structure of a scanning device according to an illustrative embodiment of the present disclosure.

[0126] refer to Figure 10 As shown, the scanning device 4 includes a first radiation source 40 that emits X-rays towards the object under test, such as a container, from a certain angle. Two sets of detector arrays (not shown in the figure) mounted on the gantry 54 receive the X-rays passing through the object under test, thereby obtaining a perspective image of the object under test from a certain angle (e.g., ...). Figure 10(The height direction mentioned above). In order to obtain a perspective image of the object under test from another viewpoint through the first radiation source 40, the object under test can be reoriented (e.g., the object under test can be set to pass through the radiation position of the first radiation source 40 again along the length direction, not shown in the figure), or the angle of the rays emitted by the first radiation source 40 can be adjusted, or another set of first radiation sources 40 can be set to obtain a perspective image from another viewpoint.

[0127] In some embodiments, the recognition module is configured to: identify a target object in the object to be tested in a perspective image, mark the target object to obtain marked targets from two or more viewpoints; and determine the position information of the target object in the perspective image based on the viewpoints and the marked targets.

[0128] In some embodiments, the recognition module is configured to: identify a target object in the object under test in a perspective image and mark the target object to obtain a marked target from one viewpoint; add new marked targets by increasing the viewpoint and supplementing the marking to obtain marked targets from two or more viewpoints; and determine the first position information of the target object in the three-dimensional model of the object under test based on the viewpoint and the marked target.

[0129] In some embodiments, the recognition module is configured to: identify a target object in a test object in a perspective image and mark the target object to obtain a marked target; and determine the first position information of the target object in the perspective image based on the viewpoint and the marked target.

[0130] In another illustrative embodiment of this disclosure, the scanning device 4 includes an X-ray tomography device suitable for acquiring a three-dimensional perspective image of the object to be measured.

[0131] In some embodiments, the scanning device 4 is an X-ray imaging device based on CT scanning. CT scanning is a scanning method that uses computer technology to reconstruct three-dimensional tomographic images of a tested object from a tomographic scan image. This scanning method uses rays from a single axis to penetrate the tested object. Based on the different absorption and transmittance of rays by different parts of the tested object, the computer performs three-dimensional reconstruction imaging based on the transmitted rays received by the detector. Thus, the CT scanning-based fluoroscopic image acquisition device can acquire three-dimensional fluoroscopic images using only one set of X-ray source and detector.

[0132] Figure 11 The schematic diagram illustrates the structure of a scanning device according to another illustrative embodiment of the present disclosure.

[0133] refer to Figure 11As shown, the scanning device 4 includes a second radiation source 41 suitable for emitting X-rays, a corrector 42, a front collimator 43, a circular rotating frame 44, a detector array 45 and a rear collimator 46 mounted on the circular rotating frame 44, a conveyor 47 suitable for transporting container vehicles, a drive device 48 suitable for driving the circular rotating frame 44 to rotate, and a braking device 49 suitable for braking the conveyor 47, etc.

[0134] In one specific embodiment, the annular rotating frame 44 is a large rotating ring. The second radiation source 41 and the detector array 45 are both fixed on the annular rotating frame 44. The annular rotating frame 44 rotates to scan and obtain a three-dimensional perspective image of the container.

[0135] In one illustrative embodiment of this disclosure, the recognition module is further configured to identify a target object in the test object in a perspective image and mark the target object to obtain marked targets from at least two viewpoints. Based on the viewpoints and marked targets, the position information of the target object within a three-dimensional model of the space defined by the test object is determined.

[0136] In one illustrative embodiment of this disclosure, the recognition module is further configured to identify target objects in the test object in a perspective image and mark the target objects. Marked targets are obtained from one viewpoint; by changing the viewpoint, new marked targets are added to supplement the existing markings, resulting in marked targets from at least two viewpoints. Based on the viewpoints and marked targets, the positional information of the target object within the three-dimensional model of the space defined by the test object is determined.

[0137] In some embodiments, the verification module includes, but is not limited to, a camera integrated into the mobile viewing device 2 and an image recognition component (including image recognition software) that is communicatively connected to the camera.

[0138] Figure 9 Schematic illustration Figure 7 A block diagram of another illustrative embodiment of the system is shown.

[0139] refer to Figure 9 As shown in an illustrative embodiment of this disclosure, the system based on target object tracking in the object under test further includes a three-dimensional shape image acquisition device 5. The three-dimensional shape image acquisition device 5 is configured to acquire a three-dimensional shape image of the object under test to construct a three-dimensional coordinate system.

[0140] Continue to refer to Figure 9 As shown, the system for tracking target objects in the test object also includes a stitching module, which is configured to construct a stitched image based on perspective images and three-dimensional shape images, and to construct a three-dimensional coordinate system of the stitched image in the stitched image.

[0141] In some embodiments of this disclosure, the stitching module is further configured to acquire multiple first identification features of the object under test based on a perspective image and multiple second identification features of the object under test based on a three-dimensional shape image. A stitched image is then acquired based on the first and second identification features.

[0142] In some embodiments of this disclosure, the first identification feature includes features of the edge portion of the perspective image, and the second identification feature includes features of the edge portion of the three-dimensional shape image.

[0143] Figure 12 The diagram illustrates a schematic embodiment of a three-dimensional shape image acquisition device.

[0144] Reference Figure 12 As shown in an illustrative embodiment of this disclosure, the three-dimensional shape image acquisition device includes: a gantry 51, at least three imaging devices 52, and a vehicle exterior panoramic stitching device 53. The gantry 51 includes at least two side pillars 511 and / or at least one crossbeam 512, with both ends of the crossbeam 512 connected to the side pillars 511 respectively. The at least three imaging devices 52 are respectively disposed on two opposite side pillars 511 and on the crossbeam 512. As the container vehicle drives past the gantry 51, the imaging devices 52 capture multiple shape images of the vehicle at a preset frame rate. The vehicle exterior panoramic stitching device 53 is communicatively connected to the imaging devices 52 and is used to stitch multiple shape images into sub-images based on common features in two adjacent shape images captured by each imaging device 52, and then stitch the multiple sub-images into a three-dimensional image of the vehicle under test.

[0145] As an embodiment of this disclosure, if the mobile viewing device 2 does not move along the first tracking direction, but moves along the second tracking direction (the second tracking direction can be any direction other than the first tracking direction, for example, the opposite direction to the first tracking direction), the mobile viewing device 2 can prompt the user to change the moving direction. Specifically, if the mobile viewing device 2 moves along the second tracking direction, which is different from the first tracking direction, the distance between the tracking position of the mobile viewing device 2 after the movement and the target object increases, then the movement stops; further, the moving direction of the mobile viewing device 2 is adjusted to the modified first tracking direction, and the device moves along the modified first tracking direction, so that the distance between the tracking position of the mobile viewing device 2 after the movement and the target object decreases, and the movement stops when the distance decreases to a preset value.

[0146] In some embodiments, the position of the target object in the three-dimensional coordinate system is fixed, while the position of the mobile viewing device changes according to the user's position. Based on the position change of the mobile viewing device, the user's coordinates can be updated in real time, and the three-dimensional coordinates relative to the first coordinate point (target object) can be re-acquired based on the updated second coordinate point to correct the position of the user and the target object.

[0147] Those skilled in the art will understand that the features described in the various embodiments and / or claims of this disclosure can be combined or combined in various ways, even if such combinations or combinations are not explicitly described in this disclosure. In particular, the features described in the various embodiments and / or claims of this disclosure can be combined or combined in various ways without departing from the spirit and teachings of this disclosure. All such combinations and / or combinations fall within the scope of this disclosure.

[0148] The embodiments of this disclosure have been described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of this disclosure. Although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be used advantageously in combination. The scope of this disclosure is defined by the appended claims and their equivalents. Various substitutions and modifications can be made by those skilled in the art without departing from the scope of this disclosure, and all such substitutions and modifications should fall within the scope of this disclosure.

Claims

1. A method for tracking a target object in an object to be tested, comprising: The target object in the perspective image is identified, and the first position information of the target object in the three-dimensional model of the object under test is determined; A three-dimensional shape image of the object under test is constructed using a mobile viewing device, and a second position information of the mobile viewing device relative to the three-dimensional shape image is determined. Based on the first location information and the second location information, obtain the three-dimensional coordinates of the target object relative to the mobile viewing device; as well as The three-dimensional coordinates are associated with a mobile viewing device, which allows the user to view the relative position of the mobile viewing device to the target object in real time, thereby guiding the user of the mobile viewing device to approach the target object.

2. The method according to claim 1 further includes acquiring first information and a perspective image of the object to be tested.

3. The method of claim 2, wherein, The process of constructing a three-dimensional shape image of the object under test using a mobile viewing device includes: Identify the first information; and Construct a three-dimensional shape image of the object under test corresponding to the first information.

4. The method of claim 2 or 3, wherein, The process of obtaining the perspective image of the object under test includes scanning the object under test with X-rays and obtaining the perspective image.

5. The method of claim 2 or 3, wherein, Acquiring a perspective image of the object under test includes scanning the object under test with X-ray computed tomography to obtain the three-dimensional perspective image.

6. The method of claim 4, wherein, The process of identifying the target object in the perspective image and determining the first position information of the target object in the three-dimensional model of the object under test includes: The target object in the object under test is identified and marked in the perspective image to obtain the marked target from a single viewpoint; By adding a new viewpoint and supplementing the markers, new marker targets are added, resulting in at least one marker target from another viewpoint; and Based on the perspective and the marked target, the first position information of the target object within the three-dimensional model of the space defined by the object under test is determined.

7. The method of claim 4, wherein, The process of identifying the target object in the perspective image and determining the first position information of the target object in the three-dimensional model of the object under test includes: Identify and mark target objects in the object under test in the perspective image, obtaining marked targets from at least two viewpoints; and Based on the perspective and the marked target, the first position information of the target object within the three-dimensional model of the space defined by the object under test is determined.

8. The method of any one of claims 1 to 3, wherein, The construction of the three-dimensional shape image of the object under test includes: The features of multiple outer surfaces of the object under test are acquired using a mobile viewing device; and A three-dimensional shape image of the object under test is constructed based on the features of the multiple outer surfaces.

9. The method of any one of claims 1 to 3, wherein, The step of obtaining the three-dimensional coordinates of the target object relative to the mobile viewing device based on the first location information and the second location information includes: A three-dimensional coordinate system for the three-dimensional shape image is constructed using a point on the object under test as the origin; Generate the first coordinate point of the first position information in the three-dimensional coordinate system; Generate the second coordinate point of the second position information in the three-dimensional coordinate system; and Obtain the three-dimensional coordinates of the first coordinate point relative to the second coordinate point in the three-dimensional coordinate system.

10. The method of any one of claims 1 to 3, wherein, The step of associating the three-dimensional coordinates with a mobile viewing device, and using the mobile viewing device to view the relative position of the mobile viewing device to the target object in real time, so as to guide the user of the mobile viewing device to move closer to the target object, includes: The three-dimensional coordinates are associated with the mobile viewing device; Set the viewing angle of the mobile viewing device as the initial tracking position, and set the direction from the initial tracking position to the target object as the first tracking direction; and The mobile viewing device moves along the first tracking direction, thereby reducing the distance between the tracking position of the mobile viewing device and the target object, and stops moving when the distance is reduced to a preset value.

11. The method of claim 10, wherein, The step of associating the three-dimensional coordinates with the mobile viewing device and using the mobile viewing device to view the relative position of the mobile viewing device to the target object in real time, so as to guide the user of the mobile viewing device to approach the target object, further includes: when the mobile viewing device moves along a second tracking direction different from the first tracking direction, and the distance between the tracking position of the mobile viewing device after the movement and the target object increases, adjusting the movement direction of the mobile viewing device to the first tracking direction and moving along the first tracking direction, so that the distance between the tracking position of the mobile viewing device after the movement and the target object decreases.

12. A system for tracking a target object in an object to be tested, comprising: Processor, including: The recognition module is configured to identify and mark a target object in the test object in a perspective image to determine the first position information of the target object's three-dimensional model in the test object; and A mobile viewing device is configured to acquire a three-dimensional shape image of the object under test; The mobile viewing device is further configured to determine second position information of the mobile viewing device relative to the three-dimensional shape image; obtain the three-dimensional coordinates of the target object relative to the mobile viewing device based on the first and second position information; associate the three-dimensional coordinates with the mobile viewing device; and view the relative position of the mobile viewing device to the target object in real time through the mobile viewing device to guide the user of the mobile viewing device to approach the target object.

13. The system of claim 12 further includes a scanning device adapted to scan the object under test to obtain a perspective image of the object under test.

14. The system according to claim 13, wherein, The scanning device includes an X-ray scanning imaging device, suitable for acquiring a perspective image of the object under test from at least one angle.

15. The system according to claim 13, wherein, The scanning device includes an X-ray tomography scanner, which is suitable for acquiring three-dimensional perspective images of the object under test.

16. The system according to any one of claims 12 to 15 further includes a data acquisition device adapted to acquire first information of the object under test.

17. The system according to claim 16, wherein, The mobile viewing device also includes a verification module configured to verify first information about the object under test.

18. The system according to claim 17, wherein, The processor further includes a retrieval module configured to retrieve the first location information of the target object in the test object corresponding to the first information from the database; The object to be tested includes a container or a vehicle; the first information of the object to be tested includes the container number or the vehicle license plate number.

19. The system according to any one of claims 12 to 14, wherein, The identification module is further configured to: Identify the target object in the object under test in the perspective image, and mark the target object to obtain a marked target from a single perspective; By adding viewpoints and supplementing the markers, new marker targets are added, resulting in marker targets from at least two viewpoints. as well as Based on the perspective and the marked target, the first position information of the target object within the three-dimensional model of the space defined by the object under test is determined.

20. The system according to any one of claims 12 to 14, wherein, The identification module is further configured to: Identify the target object in the object under test in the perspective image, and mark the target object to obtain the marked target from at least two viewpoints; and Based on the perspective and the marked target, the first position information of the target object within the three-dimensional model of the space defined by the object under test is determined.

21. The system according to any one of claims 12 to 15, wherein, The mobile viewing device includes a lidar module configured to acquire features of multiple outer surfaces of the object under test and construct a three-dimensional shape image of the object under test based on the features of the multiple outer surfaces.

22. The system according to any one of claims 12 to 15, wherein, The mobile viewing device is further configured to: A three-dimensional coordinate system for the three-dimensional shape image is constructed using a point on the object under test as the origin; Generate the first coordinate point of the first position information in the three-dimensional coordinate system; Generate the second coordinate point of the second position information in the three-dimensional coordinate system; as well as Obtain the three-dimensional coordinates of the first coordinate point relative to the second coordinate point in the three-dimensional coordinate system.

23. The system according to any one of claims 12 to 15, wherein, The mobile viewing device is configured to: When the device moves along a second tracking direction different from the first tracking direction, and the distance between the tracking position of the moving viewing device and the target object increases, the movement stops. as well as The moving direction of the mobile viewing device is adjusted to the first tracking direction, and the device moves along the first tracking direction to reduce the distance between the tracking position of the mobile viewing device and the target object. The movement stops when the distance is reduced to a preset value.

Images