Method for generating a 3D image comprising at least one merged 3D graphic element corresponding to an object to be detected

Abstract

The invention relates to a method for generating a 3D image comprising at least one fused 3D graphic element corresponding to at least one object to be detected by a security agent or by a detection algorithm using artificial intelligence, comprising in particular the steps of integrating (E4) at least one prepared 3D graphic element into a generated 3D image so that said at least one 3D graphic element appears within the container on the 3D image, processing (E5) the 3D image comprising the at least one integrated 3D graphic element to transform the point mesh of the at least one 3D graphic element into voxels in the 3D image, and post-processing (E6) the processed 3D image to add to the voxels artificial effects related to the material of the at least one 3D graphic element in order to fuse said at least one 3D graphic element into the 3D image. Figure for the abstract: Figure 3

Description

Title of the invention: Method for generating a 3D image comprising at least one merged 3D graphic element corresponding to an object to be detected Technical field

[0001] The present invention relates to the field of security and more particularly concerns a device which can be used for the purposes of training, maintaining the skills and certification of security personnel, particularly airport personnel, or for training artificial intelligence integrated into radioscopic imaging equipment. Prior art

[0002] In the airport world, it is known to use security equipment comprising conveyors coupled with radioscopic imaging equipment making it possible to view the contents of passengers' luggage on two-dimensional images. This type of security system is also used in other places such as, for example, sensitive infrastructures or those intended to accommodate the public, such as stations, prisons, stadiums, performance halls or historic monuments.

[0003] In order to train, maintain the competence of and test the security agents who control the images, it is known to insert objects to be detected, for example weapons or any other prohibited object, into the elements passing through the radioscopic imaging equipment. This method is tedious and time-consuming because it is necessary to insert the objects into the elements to be controlled (luggage, clothing, etc.), train or test the agents, and then recover the objects.

[0004] Another known solution consists of modifying the images generated by the radioscopic imaging equipment before they are viewed by the security officer. This modification consists of scanning the objects to be detected beforehand and then superimposing the images of the scanned objects on the 2D images of the elements to be checked passing through the radioscopic imaging equipment. This method can also prove tedious and time-consuming. In addition, the credibility of the objects integrated into the 2D images can prove to be doubtful, which allows the officers to detect them easily and presents a disadvantage in terms of training.

[0005] In particular to train the detection algorithms integrated into radioscopic imaging equipment or to verify the correct functioning and maintenance of the performance of this equipment, it is also known to use these two solutions.

[0006] The recent arrival of radioscopic imaging equipment allowing visualization the contents of baggage in 3D, allowing better visualization of the baggage and the objects it contains, but also the growing development of artificial intelligence in the field of security, give rise to a need relating to training, maintaining skills, certification and testing of security personnel with this new technology, but also gives rise to a need relating to training, known as "Machine Learning", of artificial intelligence integrated into radioscopic imaging equipment.

[0007] To meet these needs, a first approach consists of inserting prohibited objects into the suitcases and bags to be checked so that they appear in the 3D images. However, as with the 2D method, this process can prove tedious and time-consuming.

[0008] A second solution consists of transforming the 3D images into 2D images, inserting the objects to be detected in 2D by superimposing them in the 2D images before visualization by the agent, as previously. Here again, this process can prove tedious and time-consuming.

[0009] It would therefore be advantageous to propose a simple, reliable and effective solution to at least partially remedy these drawbacks. Statement of the invention

[0010] The aim of the invention is to provide a simple, reliable, effective and rapid solution for training, maintaining the skills of, certifying and testing security agents.

[0011] To this end, the invention firstly aims at a method for generating a 3D image comprising at least one merged 3D graphic element corresponding to at least one object to be detected by a security agent or by a detection algorithm using artificial intelligence, said method comprising the steps of:

[0012] - preparation of at least one 3D graphic element to be detected, said at least one 3D graphic element being characterized by a mesh of points and at least one material,

[0013] - generation of a 3D image in voxels representing at least one container to controlled by the security agent or by the detection algorithm using artificial intelligence,

[0014] - integration of the at least one prepared 3D graphic element into the 3D image generated so that said at least one 3D graphic element appears in the container on the 3D image,

[0015] - 3D image processing comprising at least one integrated 3D graphic element to transform the point mesh of the at least one 3D graphic element into voxels in the 3D image,

[0016] - post-processing of the processed 3D image to add artificial effects to the voxels linked to the material of the at least one 3D graphic element in order to merge said at least one 3D graphic element into the 3D image.

[0017] By the term "voxel" is meant a volume of pixels in three dimensions.

[0018] By the term “point mesh” is meant a vector representation in point meshes.

[0019] The container to be checked may for example be a suitcase, a bag, a parcel, etc.

[0020] The method according to the invention makes it possible to integrate one or more 3D objects into a 3D image by performing a virtual print. In particular, the transformation of the mesh into voxels of each 3D graphic element integrated into the 3D image makes it possible to define the contours and the interior of the said 3D graphic element(s). The integration of virtual 3D objects into a 3D image also makes it possible to avoid the handling of dangerous objects or hazardous materials, thus increasing workplace safety. The integration of virtual 3D objects into a 3D image also makes it possible to integrate objects, for example from their technical specifications, not yet available or whose access is difficult or impossible due to current legislation. The integration of virtual 3D objects into a 3D image also makes it possible to avoid the use of polluting objects.Finally, the method according to the invention can be implemented in parallel with several machines, for example via a communication network, which proves to be simpler and involves less maintenance and costs than with a plurality of real 3D radioscopic imaging equipment used in parallel. In addition, the method according to the invention makes it possible to simulate several different machines in parallel.

[0021] Advantageously, the processing of the 3D image comprising the at least one integrated 3D graphic element comprises a 3D digital scanning of the elements of the 3D image.

[0022] Preferably, the scanning comprises sending a plurality of digital rays onto the elements of the 3D image in order to define for each their contour and their position. Such scanning can for example be carried out by ray tracing or ray walking algorithms. Such scanning, similar to a 3D printing technique, makes it possible to produce in particular the thickness traces of the elements appearing on the 3D image.

[0023] In one embodiment, the generation of the 3D image is carried out from at least one real container, for example via real 3D radioscopic imaging equipment.

[0024] In another embodiment, the generation of the 3D image is carried out virtually, for example from a 3D image generator which will generate a 3D image representing the at least one container, possibly comprising objects.

[0025] In one embodiment, the preparation comprises generating at least one new 3D graphical element.

[0026] In another embodiment, the preparation comprises retrieving at least one existing 3D graphical element, for example in a database.

[0027] Advantageously, the preparation comprises a step of identifying and assigning a material to each part of each 3D graphic element.

[0028] Advantageously, the preparation comprises a step of assigning a density to the material of the at least one 3D graphic element, said density making it possible to determine the nature of the material present in a voxel during the processing of the 3D image.

[0029] Advantageously, the post-processing of the 3D image includes the creation of a volume of raw material (i.e. devoid of artificial effects), the creation of a volume of metallic artificial effects, the creation of a volume of Compton effect and the fusion of these three volumes.

[0030] According to one aspect of the invention, the method comprises a step of associating metadata of the at least one 3D graphic element with an area of ​​the 3D image comprising at least in part the at least one 3D graphic element.

[0031] According to one aspect of the invention, the method comprises a step of selection, by the security agent or by the detection algorithm using artificial intelligence, of an area of ​​the post-processed 3D image.

[0032] According to one aspect of the invention, the method comprises a step of detecting the at least one 3D graphic element when the area of ​​the selected post-processed 3D image corresponds to the area associated with the metadata.

[0033] The invention also relates to a computer program product characterized in that it comprises a set of program code instructions which, when executed by one or more processors, configure the processor(s) to implement a method as presented above.

[0034] The invention also relates to a module for generating a 3D image comprising at least one 3D graphic element corresponding to an object to be detected by a security agent or by a detection algorithm using artificial intelligence, said module being configured to:

[0035] - preparing at least one 3D graphic element to be detected, said at least one element 3D graphic being characterized by a mesh of points and at least one material,

[0036] - generate a 3D image in voxels representing at least one container to be controlled by the security agent or by the detection algorithm using artificial intelligence,

[0037] - integrate at least one prepared 3D graphic element into the generated 3D image in order to that said at least one 3D graphic element appears in the container in the 3D image,

[0038] - process the 3D image comprising at least one integrated 3D graphic element for transform the point mesh of at least one 3D graphic element into voxels in the 3D image,

[0039] - post-process the processed 3D image to add material-related effects in order to finalize its fusion in the 3D image.

[0040] Preferably, the generation module is configured to, during the processing of the 3D image comprising the at least one integrated 3D graphic element, carry out a digital scan of the elements of the 3D image.

[0041] Preferably, the generation module is configured to, during a scan, send a plurality of digital rays onto the elements of the 3D image in order to define for each their contour and their position, for example by “ray tracing” or “ray marching”.

[0042] Advantageously, the generation module is configured to, during preparation, identify and assign a material to each part of each 3D graphic element.

[0043] Advantageously, the generation module is configured to, during preparation, assign a density to the material of the at least one 3D object, said density making it possible to determine the nature of the material present in a voxel during processing of the 3D image.

[0044] In one embodiment, the generation module is configured to generate at least one 3D image from at least one real container, for example via real 3D radioscopic imaging equipment.

[0045] Alternatively or additionally, the generation module is configured to generate at least one 3D image virtually, for example from a 3D image generator.

[0046] Advantageously, the generation module is configured to associate metadata of the at least one 3D graphic element with an area of ​​the 3D image comprising at least in part the at least one 3D graphic element.

[0047] Advantageously, the generation module is configured to detect the at least one 3D graphic element when the area of ​​the selected post-processed 3D image corresponds to the area associated with the metadata.

[0048] In one embodiment, the generation module is configured to, when preparing the at least one 3D object, generate at least one new 3D object.

[0049] Alternatively or additionally, the generation module is configured to, when preparing the at least one 3D object, retrieve at least one existing 3D object.

[0050] Preferably, the generation module is configured to, during post-processing of the 3D image, create a volume of raw material, create a volume of artificial metallic effects, create a volume of Compton effects and merge these three volumes.

[0051] The invention also relates to computer equipment comprising a module of generation as presented above.

[0052] The computer equipment may be user equipment such as, for example, a computer, a tablet, a smartphone, virtual and / or augmented reality equipment, etc.

[0053] The computer equipment can be a server.

[0054] In one embodiment, the computer equipment is configured to allow the selection, by the security agent or by the detection algorithm using artificial intelligence, of an area of ​​the post-processed 3D image.

[0055] The invention also relates to a system comprising server-type computer equipment as presented above and at least one user equipment configured to display a post-processed 3D image received from the server and to allow the selection or pointing by a user of said user equipment of an area of ​​the post-processed 3D image. Brief description of the drawings

[0056] Other characteristics and advantages of the invention will become apparent from reading the description which follows. This is purely illustrative and must be read in conjunction with the appended drawings in which:

[0057] [Fig-1] [Fig.l] schematically illustrates one embodiment of the equipment computer according to the invention.

[0058] [Fig.2] [Fig.2] schematically illustrates an embodiment of the system according to the invention.

[0059] [Fig.3] [Fig.3] schematically illustrates an embodiment of the method according to the invention. Description of the embodiments

[0060] The computer equipment according to the invention can be implemented autonomously or in a communication system in order to allow a security agent or a detection algorithm using artificial intelligence to detect prohibited objects in 3D images.

[0061] [Fig.l] illustrates an embodiment of a computer equipment 1 according to the invention. The computer equipment 1 can operate autonomously by being, for example, of the computer, tablet or smartphone type or any other suitable equipment or by being integrated into a larger system of the communication network type.

[0062] [Fig. 2] illustrates an embodiment of a communication system 2 according to the invention. The system 2 comprises a server-type computer equipment 1 and user equipment 3 of the computer, tablet, smartphone or virtual and / or augmented reality equipment type, connected to said computer equipment 1 via a communication network 4.

[0063] Computer equipment 1

[0064] With reference to [Fig.l], the computer equipment 1 comprises a generation module 10 according to the invention. In the case of a computer-type computer equipment 1, the computer equipment 1 comprises a screen, a keyboard and a mouse to enable the security agent to interact with the 3D image appearing on said screen, in particular by pointing at a suspicious object in said 3D image. In the case of a smartphone or tablet-type computer equipment 1, the computer equipment 1 comprises a touch screen enabling input, pointing and selection to enable the security agent to interact with the 3D image appearing on said touch screen, in particular to attempt to detect a suspicious object in said 3D image.In the case of computer equipment 1 of the virtual reality or augmented reality type, the computer equipment 1 advantageously comprises a hand tracking system, an eye tracking system, neural impulse sensors or a controller allowing pointing and selection to allow the security agent to interact with the 3D image appearing on said touch screen, in particular to attempt to detect a suspicious object in a 3D universe using said 3D image.

[0065] Generation Module 10

[0066] The generation module 10 makes it possible to generate at least one 3D image comprising at least one 3D graphic element corresponding to an object to be detected by a security agent or by a detection algorithm using artificial intelligence. The generation module 10 may at least partly be in the form of an application or a computer program implemented by the computer equipment 1.

[0067] Preparation

[0068] The generation module 10 is configured to prepare at least one 3D graphic element to be detected, said at least one 3D graphic element being characterized by a mesh of points and at least one material.

[0069] The generation module 10 may be configured to, during the preparation of the at least one 3D graphic element, generate at least one new 3D graphic element.

[0070] Alternatively or additionally, the generation module 10 may be configured to, during the preparation of the at least one 3D graphic element, retrieve at least one existing 3D graphic element.

[0071] The generation module 10 is configured to, during preparation, assign a density to the material of the at least one 3D graphic element, said density making it possible to determine the nature of the material present in a voxel during processing of the 3D image.

[0072] More precisely, the assignment of a material and a density makes it possible to calculate a average density per voxel as a function of the density of the materials represented on said voxel (in kg / m3) and to characterize the behavior of a material during scanning.

[0073] On this last point, for example, a solid will generate a full volume, a metal will induce metallic artifacts, a liquid will be generated in the identified volume respecting gravity with insertion of wavelets simulating the effect of the conveyor belt, powder will be generated in the volume respecting gravity and a packing / stacking logic. For a deformable material, a Boolean operation can be performed by prioritizing the other materials present in the same voxel. For a flexible material, for example a garment, a deformation of the mesh can be performed, for example during a shaking phase (described below).

[0074] 3D Image

[0075] The generation module 10 is configured to generate a 3D image in voxels representing at least one container to be checked by the security agent or by the detection algorithm using artificial intelligence.

[0076] The generation module 10 is configured to generate the 3D image from at least one real container, for example via real 3D radioscopic imaging equipment.

[0077] Alternatively or additionally, the generation module 10 may be configured to generate the 3D image virtually, for example from a 3D image generator.

[0078] Added 3D mesh graphic element

[0079] The generation module 10 may be configured to integrate at least one prepared 3D graphic element into the generated 3D image so that said at least one 3D graphic element appears in the container on the 3D image.

[0080] Treatment

[0081] The generation module 10 is configured to process the 3D image comprising the at least one integrated 3D graphic element to transform the point mesh of the at least one 3D graphic element into voxels in the 3D image.

[0082] The generation module 10 is configured to, during the processing of the 3D image comprising the at least one integrated 3D graphic element, carry out a digital scan of the elements of the 3D image.

[0083] The generation module 10 is configured to, during a scan, send a plurality of digital rays onto the elements of the 3D image in order to define for each their contour and their position. Preferably, a “ray tracing” or “ray marching” type method is used.

[0084] The generation module 10 is configured to associate metadata of the at least one 3D graphic element with an area of ​​the 3D image comprising at least in part the at least one 3D graphic element.

[0085] Preferably, the collected metadata are geometric and functional. The geometric data may be linked to a bounding box (known as a "Bounding Box") defined by its center and its size in the baggage reference frame, or may be a volume, a mass, etc. The functional data may be a name, a type of threat to be detected by the agent or the artificial intelligence detection algorithm, a role in a compound threat, a technical specificity (for example an electrical voltage), etc.

[0086] The metadata may also include information from the container that can be interpreted as alarms. The container alarm data may be collected during the container import phase. The metadata is associated with each volume and aggregated when the volumes are merged as described below.

[0087] Post-treatment

[0088] The generation module 10 is configured to post-process the processed 3D image to add material-related effects to merge it into the 3D image.

[0089] The generation module 10 is configured to, during post-processing of the 3D image, create a volume of raw material, create a volume of artificial metallic effects, create a volume of Compton effects and merge these three volumes.

[0090] The generation module 10 is configured to, during post-processing of the 3D image, add artificial effects linked to the material of the container and to the material of each object.

[0091] Use

[0092] The generation module 10 is configured to detect the at least one 3D graphic element when the area of ​​the selected post-processed 3D image corresponds to the area associated with the metadata. To avoid a search step, which would be performed in real time by real 3D radioscopic imaging equipment, the generation module 10 is configured to directly exploit the coordinate, bounding box and volume information already ready and provided in the metadata.

[0093] The generation module 10 or the computer equipment 1 comprises a processor capable of implementing a set of instructions making it possible to carry out these functions.

[0094] Example of implementation

[0095] In a step E1, the generation module 10 prepares one or more 3D graphic elements to be detected. Each 3D graphic element is characterized by its point mesh and its material(s).

[0096] The preparation comprises generating at least one new 3D graphic element or retrieving at least one existing 3D graphic element.

[0097] In the remainder of the example, for reasons of clarity, a single 3D graphic element is prepared and corresponds to a knife with a metal blade and a handle made of another material, for example wood.

[0098] Advantageously, the method may comprise a step of scaling the at least one new 3D graphic element so that all the 3D objects manipulated in the method are at the same reference scale, for example the meter.

[0099] Preferably, the method comprises a retopology step for simplifying the topology of a mesh to make it cleaner and easier to use and manifold.

[0100] Preferably, the preparation comprises a step of identifying and assigning a material to each part of each 3D graphic element. Thus, in the present example, the handle of the knife is associated with the wood material (density of the order of 690 kg / m3 for walnut for example) and the blade of the knife is associated with the steel material (density of the order of 7800 kg / m3). The association of a material with a mesh zone can be carried out in the preparation phase via a graphical interface (for example by pointing or selecting an area) or can be integrated into the computer code, in particular for dynamically generated 3D objects (for example cables or liquids).

[0101] More preferably, the preparation comprises a step of assigning a material density to each material of each 3D graphic element, said density making it possible to determine the nature of the material present in each voxel of the 3D image during the processing of said 3D image. For example, water has a density of 1000 kg / m3.

[0102] In a step E2, the generation module 10 generates a 3D image in voxels representing at least one container to be checked by the security agent or by the detection algorithm based on artificial intelligence, for example a suitcase or a bag. In the remainder of the example, for reasons of clarity, the container is unique and is a suitcase. The generation of the 3D image can be carried out from a real suitcase, for example by passing it through real 3D radioscopic imaging equipment, or virtually, for example from a 3D image generator, in a manner known per se. In the 3D image, the suitcase can include objects placed inside it, such as for example clothes, documents, a camera, shoes, pens, etc. These objects can be actually placed in the suitcase and thus passed through the 3D X-ray imaging equipment or added to the 3D image by a 3D image generator.When the objects are placed in the suitcase by a 3D image generator, the method may include a shaking step to disperse and distribute the objects in the suitcase, in particular when they are simply placed vertically in the suitcase during their in- . integration by the 3D image generator.

[0103] In a step E3, the generation module 10 integrates the prepared knife into the generated 3D image so that said knife appears as being placed inside the suitcase on the 3D image. At this stage, the knife is still a meshed 3D graphic element.

[0104] In a step E4, the generation module 10 performs a processing of the 3D image comprising the 3D representation of the integrated knife in order to transform the mesh of points of the 3D representation of the knife into voxels in the 3D image of the suitcase. In other words, the knife and the suitcase are assembled in the 3D image. This transformation makes it possible in particular to define the contours and the thickness traces of the knife integrated in the 3D image and of the other objects. In this exemplary implementation, the processing of the 3D image comprising the integrated knife comprises a digital scanning of the elements of the 3D image. For example, this scanning may comprise sending a plurality of digital rays onto the elements of the 3D image in order to define for each their contour and their position. A known method of “ray marching” may for example be used.In general, the method according to the invention can be used with a digital scan on at least one axis, for example on three axes (the three dimensions), back and forth in order to define the contours and thicknesses of the objects appearing on the 3D image.

[0105] In a step E5, metadata relating to the knife, for example its nature as an object, its position in the 3D image and its volume in the 3D image, are associated with an area of ​​the processed 3D image. This metadata may have been generated during the preparation phase: for example, dynamic behaviors may have been assigned by “dragging & dropping” onto the objects. For example, a knife may be associated with a sharp-pointed threat type, a battery may be associated with its electrical voltage, etc.

[0106] In a step E6, the generation module 10 performs post-processing of the processed 3D image to add artificial effects related to the material of the at least one 3D graphic element in order to merge said at least one 3D graphic element into the 3D image. The artificial effects, or artifacts, are effects such as those visible on 3D images generated by real 3D radioscopic imaging equipment.

[0107] It will be noted that step E5 could have been carried out before step E4 or after step E6 or in parallel with step E4 or step E6.

[0108] In this preferred example, the post-processing of the 3D image comprises the creation of a raw material volume, the creation of a metallic artificial effects volume, the creation of a Compton effect volume and the merging of these three volumes. The raw material volume, the metallic artificial effects volume and the Compton effect volume correspond to the volume of material represented on the 3D image at the same ladder.

[0109] The raw material volume corresponds to a 3D volume comprising the generated 3D objects to be inserted. In particular, to define the raw material volume, the points of impact of the digital rays on the objects are taken into account to calculate the ratio of material present in each voxel of the processed 3D image and, preferably, the density of each voxel, in particular when said voxel comprises several materials. In the latter case, the density of the voxel is calculated as the sum of the products of the density of each material by the volume occupied by said material in the voxel.

[0110] More precisely, the establishment of the gross volume preferably follows the following algorithm: for each voxel, the traces of materials that compose it are detected, then, depending on the behavior of the material(s) [deformable, powder, liquid, solid, etc.], their density values ​​kg / m3 and the angle of incidence of the digital scanning ray on the material, their participation ratio in the voxel is established and this value is entered in the gross volume.

[0111] The notion of "raw" volume reflects a "perfect" scanning environment without any defects. Defects that may appear in a 3D scan in a real machine context may include an element with non-uniform density, an element with a manufacturing defect or wear or in a degraded state, 3D radioscopic imaging equipment that emits artifacts due to poor calibration or wear, or poor-performing 3D radioscopic imaging equipment.

[0112] The creation of the volume of artificial metallic effects corresponds to making appear on the 3D image, in particular on the knife, deformations such as they appear on the images of real 3D radioscopic imaging equipment made on a real suitcase containing real metallic objects. The creation of the volume of artificial metallic effects includes the analysis of the presence of metal in the processed 3D image, the analysis of the presence of metal in the added 3D graphic elements (knife), the application of artificial effects generated by the suitcase on the knife and the application of artificial effects generated by the knife on the suitcase and its other objects.

[0113] The creation of the Compton effect volume, known per se, involves the creation of a volume comprising artificial effects corresponding to elastic scattering when considering a free electron but inelastic for a bound electron.

[0114] The fusion of these three volumes is carried out by superposition then a fusion is carried out with the suitcase in order to melt the knife into the 3D image of the suitcase as if it were a real element of a suitcase scanned in 3D.

[0115] Post-processing of metallic artifacts is carried out on the entire suitcase and the objects it contains in order to reveal the effects linked to the metallic objects. in their final configuration in the suitcase.

[0116] Then, the post-processed 3D image is made available to a security agent or a detection algorithm using artificial intelligence in a step E7, either directly on the computer equipment 1 in the case for example of a computer or a tablet or a smartphone or virtual or augmented reality equipment or, as illustrated in [Fig.2], via a communication network 4 and a client installed on user equipment (computers, tablet and smartphone 3 in [Fig.2]) remotely in the case where the generation module 10 is implemented on a server.

[0117] The security agent or the detection algorithm using artificial intelligence then selects or points, in a step E8, an area of ​​the post-processed 3D image. If the selected area corresponds to the knife, for example by checking the metadata on the position of the knife in the post-processed 3D image, then the detection of the knife is carried out and confirmed in a step E9. The presentation software to the security agent is content agnostic and uses the metadata file as a map.

[0118] By allowing the total integration of a 3D knife-type object into a 3D image, the invention makes it possible to carry out effective training of security agents and / or also to validate the reliability and performance of a detection algorithm based on artificial intelligence. In particular, numerous 3D images representing different containers containing different objects, prohibited or not, can be generated with the method according to the invention and used in large numbers to train and test security agents. The method and the generation module according to the invention can also be used with real 3D radioscopic imaging equipment to detect threats in real time and thus increase security, particularly at airports.

Claims

Claims

1. Method for generating a 3D image comprising at least one merged 3D graphic element corresponding to at least one object to be detected by a security agent or by a detection algorithm using artificial intelligence, said method comprising the steps of: - preparing (El) at least one 3D graphic element to be detected, said at least one 3D graphic element being characterized by a mesh of points and at least one material, - generating (E2) a 3D image in voxels representing at least one container to be controlled by the security agent or by the detection algorithm using artificial intelligence, - integrating (E3) the at least one prepared 3D graphic element into the generated 3D image so that said at least one 3D graphic element appears in the container on the 3D image,- processing (E4) of the 3D image comprising the at least one integrated 3D graphic element to transform the mesh of points of the at least one 3D graphic element into voxels in the 3D image, - post-processing (E6) of the processed 3D image to add to the voxels artificial effects linked to the material of the at least one 3D graphic element in order to merge said at least one 3D graphic element in the 3D image.,

2. The method of claim 1, wherein processing the 3D image having the at least one integrated 3D graphics element comprises 3D digital scanning of the 3D image elements.

3. Method according to the preceding claim, in which the scanning comprises sending a plurality of digital rays onto the elements of the 3D image in order to define for each their outline and their position.

4. Method according to any one of the preceding claims, in which the step of generating (E2) a 3D image in voxels is carried out from at least one real container, for example via real 3D radioscopic imaging equipment, or virtually, for example from a 3D image generator.

5. Method according to any one of the preceding claims, said method further comprising a step (E5) of associating metadata of the at least one 3D graphic element with an area of ​​the 3D image comprising at least in part the at least one 3D graphic element, a step (E8) of selection, by the security agent or by the algorithm of detection using artificial intelligence, of an area of ​​the post-processed 3D image, and a step (E9) of detecting the at least one 3D graphic element when the area of ​​the selected post-processed 3D image corresponds to the area associated with the metadata.

6. A method according to any preceding claim, wherein the preparation comprises generating at least one new 3D graphical element or retrieving at least one existing 3D graphical element.

7. A method according to any preceding claim, wherein the post-processing of the 3D image comprises creating a raw material volume, creating a metallic artificial effects volume, creating a Compton effect volume and merging these three volumes.

8. A computer program product characterized in that it comprises a set of program code instructions which, when executed by one or more processors, configure the processor(s) to implement a method according to any one of the preceding claims.

9. Module (10) for generating a 3D image comprising at least one 3D graphic element corresponding to an object to be detected by a security agent or by a detection algorithm using artificial intelligence, said module (10) being configured to: - prepare at least one 3D graphic element to be detected, said at least one 3D graphic element being characterized by a mesh of points and at least one material, - generate a 3D image in voxels representing at least one container to be controlled by the security agent or by the detection algorithm using artificial intelligence, - integrate at least one prepared 3D graphic element into the generated 3D image so that said at least one 3D graphic element appears in the container in the 3D image, - process the 3D image comprising the at least one integrated 3D graphic element to transform the mesh of points of the at least one 3D graphic element into voxels in the 3D image,- post-process the processed 3D image to add material-related effects to finalize its fusion into the 3D image.,

10. Computer equipment (1) comprising a generation module (10) according to the preceding claim.

Images