HIGH-RESOLUTION RADAR SCANNING SYSTEM FOR NON-INVASIVE TARGET ANALYSIS

Abstract

A radar scanning system (100) for non-invasive analysis of targets (10) includes a plurality of transceiver radars (111) arranged in an irregular geometric configuration. The system (100) performs sequential acquisitions to generate a high-resolution radar representation (20). A reconstruction processor, coupled to an artificial intelligence module (140), processes the acquired data to detect, classify, and analyze objects within the target. The system (100) dynamically adapts to the characteristics of the target (10) and can compensate for relative motion between the system (100) and the target. This invention finds applications in various fields requiring detailed and non-invasive analysis of internal structures. Figure to be published with the abstract: Figure 1

Description

Title of the invention: HIGH RESOLUTION RADAR SCANNING SYSTEM FOR NON-INVASIVE TARGET ANALYSIS Technical field

[0001] The present invention relates to the field of radar imaging systems, and more particularly to scanning systems for the non-invasive analysis of targets using networks of transmitter-receiver radars with irregular geometric configuration. Prior art

[0002] Conventional radar imaging systems typically use regular configurations of transmitter-receiver radars, which limits their spatial resolution and their ability to analyze targets accurately.

[0003] These systems often struggle to adapt to moving targets, thus compromising the quality of the acquired data.

[0004] Furthermore, the interpretation of radar data frequently relies on manual methods or rigid algorithms, which makes it difficult to automatically and accurately classify detected objects.

[0005] Furthermore, these systems generally lack the flexibility to adapt to the different characteristics of the targets analyzed, which can lead to suboptimal results in certain situations.

[0006] Finally, current techniques do not always allow a sufficiently detailed non-invasive analysis of complex internal structures, thus limiting their applicability in certain critical areas.

[0007] Thus, there is a need for an innovative radar imaging system capable of overcoming these limitations. Summary of the invention

[0008] The invention aims to resolve, at least partially, this need.

[0009] A first aspect of the invention relates to a scanning system for the non-invasive analysis of targets.

[0010] In practice, the system comprises, - at least one radar sensor which comprises a plurality of transmitter-receiver radars which are arranged in a two-dimensional configuration to generate a radar representation of at least one target, wherein, - each transmitter-receiver radar has an identical predetermined two-dimensional footprint and is designed to, during sequential acquisitions, emit electromagnetic signals via its transmitter and at least a first antenna, and receiving corresponding reflected electromagnetic signals via its receiver and at least one second antenna, the electromagnetic signals having a frequency between 3 GHz and THz, - for a matrix of MxN transmitter-receiver radars, the system is designed to perform K sequential acquisitions, each acquisition corresponding to at least one measurement performed by all or part of the matrix of transmitter-receiver radars and contributing to a distinct segment, Ci, of the radar representation, for a different relative position between the radar sensor and the target, the sequential acquisitions being obtained by moving the radar sensor relative to the target or vice versa, according to a predetermined or adaptive direction of movement, D, thus allowing a progressive and piecewise construction of the radar representation, - the transmitter-receiver radars are arranged in an irregularly geometric array with a progressive offset between them, in at least one of the two dimensions of their two-dimensional footprint, this offset being less than the footprint of an individual transmitter-receiver radar in at least the corresponding dimension, this arrangement being designed in such a way that the acquisition of the distinct segments, Ci, of the radar representation is carried out progressively over time, and - the arrangement of the transmitter-receiver radars and the number K of sequential acquisitions are designed to obtain a predetermined spatial resolution in the radar representation which is substantially improved compared to the resolution corresponding to the offset between the transmitter-receiver radars, this improvement being a function of the total number K of acquisitions and the number of transmitter-receiver radars in at least one dimension of the two-dimensional configuration.

[0011] In a first embodiment of the first aspect of the invention, the progressive offset between the transceiver radars is either constant with an identical offset value between each pair of adjacent transceiver radars, or variable with different offset values between the pairs of adjacent transceiver radars, or a combination of constant and variable offsets between different pairs of adjacent transceiver radars.

[0012] In a second embodiment of the first aspect of the invention, the irregular geometry array with progressive shift of the transceiver radars is designed according to a geometric pattern selected from: a linear shift, a staggered pattern, a spiral pattern, a fractal arrangement, a pseudorandom arrangement, or a distorted grid pattern.

[0013] In a third embodiment of the first aspect of the invention, the system comprises at least one optical system which is optically coupled to the radar sensor, the optical system comprising at least one optical element for shaping the electromagnetic signals transmitted and received by one or more of the transmitter-receiver radars.

[0014] In a fourth embodiment of the first aspect of the invention, the system further comprises at least one radar representation reconstruction processor which is operatively coupled to the radar sensor and which is designed to reconstruct the radar representation from all or part of the K measurement sequences generated during all or part of the sequential acquisitions.

[0015] In a first example of the fourth embodiment of the first aspect of the invention, the radar representation reconstruction processor comprises or is coupled to an artificial intelligence module included in the system, the artificial intelligence module being designed to, - receive the radar representation or all or part of the sequential acquisitions, called model input data, - determine, from the model input data, the contours of objects detected in the target, - extract, from the model input data, specific characteristics of the detected objects, - classify the detected objects by associating them with predetermined classes of objects, on the basis of the extracted characteristics.

[0016] In a first variant of the first example of the fourth embodiment of the first aspect of the invention, the artificial intelligence module is further designed to, - generate metadata associated with each detected object, comprising at least its classification and its position in the radar representation, and - integrate the generated metadata into the radar representation.

[0017] In a second variant of the second example of the fourth embodiment of the first aspect of the invention, the system further comprises, - at least one network communication interface, and - at least one online learning module coupled to the artificial intelligence module, the online learning module being designed to, — establish a connection with at least one remote server via the network communication interface, — receive from the remote server update data comprising, — new classification models, — new classes of objects to be detected, and / or — adjusted parameters for feature extraction, — integrate the received update data into the artificial intelligence module, — dynamically adapt the detection and classification algorithms of the artificial intelligence module according to the received update data, — enable the artificial intelligence module to identify and classify new detected objects in accordance with the update data, and — transmit information on classification performance following the update to the remote server, so as to enable an iterative process of improving the artificial intelligence module.

[0018] In a second example of the fourth embodiment of the first aspect of the invention, the radar representation reconstruction processor is designed to reconstruct the radar representation by performing the following steps, - preprocessing the acquired data, including extracting phase and amplitude information from the K measurement sequences and compensating for the progressive shift between the radars, - iteratively generating distinct segments, Ci, of the radar representation for each acquisition, taking into account the irregular geometry of the radar array and using the results of the preprocessing, - progressively merging the distinct segments, Ci, of the radar representation, integrating the relative position information between the radar sensor and the target for each acquisition, and using the results of the previous steps to refine the merging, and - generating a final radar representation by iterative synthesis,combining the information processed at each stage.

[0019] In a variant of the second example of the fourth embodiment of the first aspect of the invention, the radar representation reconstruction processor is further designed to perform the following additional steps, - application of resolution improvement techniques exploiting the spatial diversity created by the progressive shift of the radars, based on the results of the fusion, - adaptive post-processing of the fused radar representation, including the integration of metadata generated by the artificial intelligence module if present, and using information from previous steps to optimize processing, and - integration of the results of these additional steps into the generation of the final radar representation, so as to allow an iterative improvement of the quality and precision of the reconstruction.

[0020] A second aspect of the invention relates to a use of a system according to the first aspect of the invention for the non-invasive analysis of heterogeneous targets.

[0021] In practice, this use includes the following steps, - positioning of the system relative to a heterogeneous target, - acquisition of K measurement sequences, - reconstruction of a radar representation of the heterogeneous target, - analysis of the radar representation to detect localized variations in dielectric properties within the target, - classification of detected variations using the artificial intelligence module, and - generation of a two-dimensional or three-dimensional map of the target integrating the classified variations and their associated characteristics.

[0022] In a first embodiment of the second aspect of the invention, the heterogeneous target is in relative motion with respect to the system during the acquisition of the K measurement sequences, and further comprising the steps of, - compensating for the relative motion in the reconstruction of the radar representation, and - temporal analysis of detected variations to identify dynamic changes within the target.

[0023] In a second embodiment of the second aspect of the invention, the artificial intelligence module is dynamically adapted during the analysis via the online learning module so as to allow, - the identification and classification of new categories of variations not previously recorded, - continuous improvement of the classification accuracy of detected variations, and - real-time adaptation of acquisition and reconstruction parameters according to the specific characteristics of the analyzed target. Brief description of the drawings

[0024] Other characteristics and advantages of the invention will be better understood on reading the description which follows and with reference to the appended drawings, given for illustrative purposes and in no way limiting.

[0025] [Fig-1] [Fig.l] represents a schematic view of the system according to the invention.

[0026] [Fig.2] [Fig.2] represents a perspective view of an implementation of the system according to the invention.

[0027] [Fig.3] [Fig.3] represents a top view of an example radar transmitter according to the invention.

[0028] [Fig.4] [Fig.4] represents a schematic view of the radar transmitter of [Fig.3] coupled with an optical element.

[0029] [Fig.5] [Fig.5] represents an example of a network with irregular geometry according to the invention.

[0030] [Fig.6] [Fig.6] shows two views of a scanning system according to the invention: the Part (S) shows a side view of the system, while Part (T) illustrates a top view of the same system.

[0031] [Fig.7] [Fig.7] represents an example of a reconstruction process of a radar representation according to the invention, for a configuration according to [Fig.6].

[0032] [Fig.8] [Fig.8] represents an example of radar representation according to the invention.

[0033] The figures do not necessarily respect the scales, in particular in thickness, and this, for illustration purposes.

[0034] Furthermore, some drawings are presented in color and / or transparency, because their representation in black and white is impossible. In particular, colors are necessary in these drawings to discern details that would be lost if they were presented in black and white. Description of the embodiments

[0035] Preliminary remarks

[0036] In order not to obscure the description and distract the reader from understanding the teachings of the invention, our explanations will not go beyond what is considered necessary for understanding and appreciating the underlying concepts of the invention. Indeed, the embodiments illustrated in the description are, for the most part, composed of elements known to those skilled in the art.

[0037] Objective of the invention

[0038] One of the main objectives of the invention is to enable precise and detailed non-invasive analysis of targets using an innovative radar system, capable of overcoming the limitations of conventional systems in terms of spatial resolution and adaptability.

[0039] For this, the inventors propose a radar scanning system comprising an irregular geometric configuration of transmitter-receiver radars, coupled with an advanced reconstruction processor and an artificial intelligence module.

[0040] This arrangement makes it possible to significantly improve the spatial resolution of the radar representation while offering increased flexibility in the acquisition and processing of data.

[0041] In particular, the system aims to dynamically adapt to the specific characteristics of each target, including those in motion, while ensuring automatic and precise classification of the detected objects.

[0042] This approach aims to expand the scope of application of radar technology to new areas requiring in-depth non-invasive analysis of complex internal structures, even under variable and demanding operating conditions.

[0043] General structure of the invention

[0044] As illustrated in [Fig.l], the scanning system 100 for the non-invasive analysis of targets 10 comprises at least one radar sensor 110.

[0045] The term “radar sensor” thus designates an essential component of the scanning system 100 for the non-invasive analysis of targets 10. By way of example, in the invention, the term “radar sensor” can designate: a set of miniaturized radars arranged on a flat surface for the inspection of structures, a network of sensors integrated into a portable device for the analysis of composite materials, or even a radar scanning system mounted on a drone for terrain mapping.

[0046] More specifically, as illustrated in [Fig.l], the radar sensor 110 comprises a plurality of transmitter-receiver radars 111.

[0047] The term "transceiver radar" means an individual element of the radar sensor 110 capable of transmitting electromagnetic signals and receiving their reflections. For example, in the invention, the term "transceiver radar" may include: a compact radar module integrating a transmitting antenna and a receiving antenna for analyzing layers of materials, a miniaturized electronic circuit capable of generating and processing high-frequency signals for detecting defects in structures, or a specialized radar component designed to operate in the millimeter wave band for high-resolution imaging.

[0048] In the invention, the transmitter-receiver radars 111 are arranged in a two-dimensional configuration.

[0049] By way of example, in the invention, the term "two-dimensional" may designate: a rectangular matrix of radar sensors for the inspection of solar panels, a hexagonal grid arrangement of transmitter-receiver radars 111 for the analysis of aeronautical structures, or a planar spiral configuration of radar modules for soil mapping.

[0050] By virtue of this arrangement, the two-dimensional configuration generates a radar representation 20 of at least one target, as illustrated in [Fig.8].

[0051] The term “radar representation” means an image or map generated by the system 100 from the signals transmitted and received by the transmitter-receiver radars 111. By way of example, in the invention, the term “radar representation” may include: a grayscale image showing the density of objects detected in a structure, a thermal map representing the variations in dielectric properties in a composite material, or a 3D visualization reconstructed from multiple 2D scans of an archaeological site.

[0052] The term “target” refers to the object or area analyzed non-invasively by the system 100. For example, in the invention, the term “target” may designate: an architectural structure to be inspected to detect hidden defects such as cracks or voids, soil to be analyzed to locate buried objects such as pipes or archaeological remains, or biological tissue to be examined non-invasively to detect abnormalities such as tumors.

[0053] In this configuration, each transmitter-receiver radar 111 has an identical predetermined two-dimensional footprint.

[0054] “Footprint” means the total size occupied by the radar transmitter-receiver 111, including its pins and the electronic clearance area (“courtyard” in English) necessary for the correct soldering of the components on the printed circuit.

[0055] Additionally, as illustrated in [Fig.3] and [Fig.4], each transceiver radar 111 is configured to transmit electromagnetic signals via its transmitter and at least one first antenna 1111 during sequential acquisitions.

[0056] In parallel, each transceiver radar 111 is also designed to receive corresponding reflected electromagnetic signals via its receiver and at least one second antenna 1112.

[0057] The term “reflected electromagnetic signals” means the electromagnetic waves which, after having been emitted by the transmitter-receiver radar 111, are returned by the target 10 and picked up by the radar receiver. These signals contain essential information on the properties and structure of the target 10 analyzed. By way of example, in the invention, the term “reflected electromagnetic signals” may include: millimeter waves reflected by the different layers of a composite material, making it possible to analyze its internal structure without damage; high-frequency signals returned by defects or cracks in an architectural structure, thus revealing anomalies invisible to the naked eye; or radar echoes coming from different depths of a soil, providing information on the composition and stratification of the terrain for geological or archaeological applications.A target's ability to reflect these signals is measured by its reflectivity.

[0058] In the context of the terahertz radars used in this invention, reflectivity can be influenced by phenomena specific to these high frequencies, such as increased sensitivity to small particles and variations in the refractive index of air.

[0059] In the invention, the electromagnetic signals have a frequency between 3 GHz and 30 THz. This frequency range, particularly in the terahertz part (0.06 to 10 THz), allows the system 100 to be used in various fields, in particular for the detection of hidden materials, imaging through clothing for security, or even the study of small-scale phenomena.

[0060] In terms of structure, the system 100 is designed for a matrix of MxN transmitter-receiver radars 111.

[0061] In one example, each radar in this array transmits a Linear Frequency Modulated Continuous Wave (L-FMCW) signal in the specified range. The reflected signal is then picked up by the radar receiver. In addition to the L-FMCW signal, the system 100 may also use other types of radar signals. Stepped Frequency Continuous Wave (SFCW) allows transmission in frequency steps, providing increased flexibility in range resolution. Continuous Wave (CW) transmits a fixed-frequency continuous signal, particularly useful for the precise measurement of radial velocities. These different transmission modalities expand the analysis capabilities of the system 100, allowing it to be adapted to various measurement conditions and requirements.

[0062] In its operation, the system 100 performs K sequential acquisitions, where K is an integer. During each acquisition, the system 100 generates a beat frequency by comparing the transmitted signal and the received signal. This beat frequency contains information on the distance and speed of the analyzed object.

[0063] Thus, each acquisition corresponds to at least one measurement made by all or part of the matrix of transmitter-receiver radars 111. The power of the received signal is measured and used to calculate the reflectivity of the target. This reflectivity is generally converted into decibels (dB) to compress the wide range of possible values.

[0064] The term "measurement" refers to the action of acquiring and recording the electromagnetic signals reflected by the target 10, carried out by all or part of the array of transmitter-receiver radars 111 during each sequential acquisition. By way of example, in the invention, the term "measurement" may refer to: recording the amplitude and phase of the reflected signals at a given time to create an accurate image of the internal structure of an object, capturing the Doppler effect to analyze subtle movements within a target such as the vibrations of a bridge, or acquiring polarization data to differentiate the types of materials in a complex structure such as a multi-layered building.

[0065] For efficient representation, as illustrated in [Fig.8], the measured reflectivity values can be encoded in one byte, giving a range of 0 to 255. This encoding allows a wide range of reflectivity values to be represented in a compact manner, thus facilitating data storage and transmission.

[0066] For improved representation, the measured reflectivity values may be encoded in at least ten bits, giving a range from 0 to at least 1023. This extended encoding allows for a finer and more detailed representation of reflectivity variations, particularly useful for analyzing complex targets or studying subtle phenomena. For example, in the invention, this increased precision encoding may be used to: detect finer variations in the density of materials during inspection of critical structures, or characterize the properties of new composite materials. This approach, although slightly more demanding in terms of data storage and processing, offers increased possibilities for applications requiring finer discrimination of the properties of the targets analyzed.

[0067] However, depending on the needs and available resources, other encoding options may be considered that are not limited to a number of bits that is a multiple of eight. Indeed, it is possible to choose an encoding on an arbitrary number of bits depending on the specific requirements of the application. For example, an encoding on eleven bits would offer a range of 0 to 2047, allowing even finer discrimination of reflectivity values. Similarly, an encoding on thirteen bits would extend the range to 0-8191, providing exceptional granularity for applications requiring extreme precision. These unconventional encoding choices may be particularly relevant in contexts where each additional bit adds significant value to the analysis, while maintaining an optimal balance between data precision and storage and processing constraints.

[0068] It should be noted that each acquisition contributes to a distinct segment Ci of the radar representation 20, as illustrated in [Fig.7].

[0069] The term “distinct segment” means a specific and unique part of the radar representation 20, obtained during a particular sequential acquisition. All the distinct segments Ci, once combined, form the complete radar representation 20. By way of example, in the invention, the term “distinct segment” may include: a vertical slice of a 2D radar image obtained during a linear scan of a wall to detect structural defects, an angular sector of a circular radar representation 20 resulting from a rotary scan for the 360-degree inspection of a pillar, or a specific area of a dielectric properties map corresponding to a given position of the radar sensor 110 during the analysis of a soil for the detection of buried objects.

[0070] In practice, each acquisition is carried out for a different relative position between the radar sensor 110 and the target.

[0071] The term “relative position” refers to the spatial relationship between the radar sensor 110 and the target 10 at the time of each acquisition. This position changes for each measurement, making it possible to obtain varied perspectives of the target 10 and to improve the resolution of the final representation. By way of example, in the invention, the term “relative position” may designate: the distance and angle between a portable radar sensor 110 and a wall to be analyzed for the detection of hidden electrical cables, the height and orientation of a drone equipped with radars flying over an agricultural area for assess soil moisture, or the position along a guide rail of a radar scanning system inspecting a ship's hull for cracks or corrosion.

[0072] Concretely, the sequential acquisitions are obtained by moving the radar sensor 110 relative to the target 10 or vice versa.

[0073] In this process, the movement follows a predetermined or adaptive direction of movement D.

[0074] The term “predetermined or adaptive direction of movement D” means the path followed by the radar sensor 110 relative to the target 10 (or vice versa) during the sequential acquisitions. This direction can be fixed in advance or adapt according to the needs of the analysis. By way of example, in the invention, the term “predetermined or adaptive direction of movement” can designate: a predefined linear path for scanning a flat surface such as a wall, a spiral scanning pattern adapting to the shape of a complex object such as a sculpture, or a trajectory optimized in real time to maximize the coverage of an area of interest such as an archaeological site.

[0075] Consequently, this process allows a progressive and piecewise construction of the radar representation 20.

[0076] As regards their arrangement, the transmitter-receiver radars 111 are arranged in an array with irregular geometry.

[0077] The term “irregular geometry array” means the non-uniform arrangement of the transmitter-receiver radars 111. For example, in the invention, the term “irregular geometry array” may designate: a staggered configuration of the radar sensors to improve spatial coverage, a spiral arrangement of the transmitters-receivers to optimize the detection of circular defects, or a pseudo-random arrangement of the radar modules to reduce interference and improve image quality.

[0078] More specifically, as illustrated in [Fig.5], the network has a progressive offset between the transmitting-receiving radars 111. This progressive offset exists in at least one of the two dimensions of their two-dimensional footprint.

[0079] The term "progressive shift" refers to the non-uniform spacing between the transceiver radars 111 in the irregular geometry array. This shift is less than the size of an individual transceiver radar 111 in at least the corresponding dimension. By way of example, in the invention, the term "progressive shift" may include: an increasing spacing between the sensors from the center to the edges of the array to improve sensitivity to the edges of the analyzed area, a variable shift according to a specific mathematical function to optimize the resolution in certain directions, or an asymmetric arrangement of the radars to adapt the field of view to the shape of the target.

[0080] It is important to emphasize that the offset is less than the footprint of an individual radar transmitter-receiver 111 in at least the corresponding dimension.

[0081] "Lower" means a dimensional characteristic of the offset between the transceiver radars 111 in the irregular geometry array. This term indicates that the offset value is smaller than the footprint of an individual transceiver radar 111 in at least one corresponding dimension. This configuration provides improved spatial resolution and finer coverage of the analyzed area.For example, in the context of the invention, the term "lesser" may refer to: a horizontal offset between two adjacent radars that is smaller than the footprint of a single radar, thus allowing partial overlap of the fields of view; a vertical spacing between the rows of radars that is less than the footprint of an individual radar, ensuring continuity in the vertical coverage; or a diagonal offset in a staggered configuration that remains below the footprint of a transmitting-receiving radar 111, thus optimizing the spatial distribution of the sensors.

[0082] As a concrete example, as illustrated in [Fig. 5], if the transmitter-receiver radars 111 used have a dimension of 5 mm x 5 mm, but their total footprint is 7 mm x 7 mm due to the pins and the electronic clearance area ("courtyard", in English), the offset will be less than 7 mm. This represents the minimum possible distance between two adjacent radars, while ensuring an optimal arrangement for improving spatial resolution.

[0083] Thanks to this configuration, the arrangement of the transmitter-receiver radars 111 is designed to progressively acquire the distinct segments Ci of the radar representation 20 over time.

[0084] In addition, the arrangement of the transmitter-receiver radars 111 and the number K of sequential acquisitions are designed to obtain a predetermined spatial resolution in the radar representation 20.

[0085] “Spatial resolution” means the precision with which the system 100 can distinguish details in the radar representation 20. The spatial resolution is substantially improved compared to the resolution corresponding to the offset between the transmitting-receiving radars 111. By way of example, in the invention, the term “spatial resolution” can include: the ability to distinguish two closely spaced objects in a 2D radar image of a complex structure, the precision of locating a microscopic defect in an analyzed composite material, or the fineness of the observable details in a dielectric properties map of a laminated floor.

[0086] As a result, the spatial resolution is substantially improved compared to the resolution corresponding to the offset between the transmitting-receiving radars 111.

[0087] It should be noted that the improvement in spatial resolution is a function of the total number K of acquisitions.

[0088] Finally, the improvement in spatial resolution is also a function of the number of transmitter-receiver radars 111 in at least one dimension of the two-dimensional configuration.

[0089] Characteristics of the progressive shift in the network of transmitter-receiver radars

[0090] The system 100 according to the invention has specific characteristics concerning the progressive shift between the transmitter-receiver radars 111.

[0091] Indeed, the progressive shift can take different forms.

[0092] First, the progressive offset between the transceiver radars 111 may be constant. In this case, an identical offset value exists between each pair of adjacent transceiver radars 111.

[0093] Second, and alternatively, the progressive offset may be variable. In this configuration, different offset values exist between pairs of adjacent transmitter-receiver radars 111.

[0094] Finally, a third possibility combines the two previous approaches. More precisely, the progressive offset can be a combination of constant and variable offsets between different pairs of adjacent transmitter-receiver radars 111.

[0095] It is important to note that these different configurations of the progressive offset provide flexibility in the arrangement of the transmitting-receiving radars 111 within the system 100. Consequently, this flexibility can influence the spatial resolution of the radar representation 20.

[0096] Geometric configurations of the irregular geometry network of transmitter-receiver radars

[0097] The system 100 according to the invention has specific characteristics concerning the irregular geometry network with progressive shift of the transmitter-receiver radars 111.

[0098] In this context, the irregular geometry network is designed according to a specific geometric pattern.

[0099] More specifically, the geometric pattern of the irregular geometry network can take several forms which include a linear offset, a staggered pattern, a spiral pattern, a fractal arrangement, a pseudo-random arrangement, or a distorted grid pattern.

[0100] First, as illustrated in [Fig.5] and [Fig.6], linear shifting represents a configuration where the transmitter-receiver radars 111 are shifted in a progressive and linear manner.

[0101] Next, the staggered pattern arranges the transmitter-receiver radars 111 in alternation, creating a pattern similar to that of the squares on a chessboard.

[0102] Furthermore, the spiral pattern organizes the transceiver radars 111 in a spiral shape. In the case of spiral or circular configurations, the offset may take the form of an angle rather than a linear distance.

[0103] In addition, the fractal arrangement uses patterns that repeat at different scales.

[0104] Furthermore, the pseudo-random arrangement places the transmitter-receiver radars 111 in a seemingly random manner, but actually following a defined algorithm.

[0105] Finally, the distorted grid pattern represents a configuration where a regular grid of transceiver radars 111 is distorted in a controlled manner.

[0106] In conclusion, these different geometric patterns offer a variety of options for optimizing the arrangement of the transmitter-receiver radars 111 in the system 100.

[0107] Optical system and shaping of electromagnetic signals

[0108] As illustrated in [Fig.2], the system 100 according to the invention comprises at least one optical system 120.

[0109] More specifically, the optical system 120 is optically coupled to the radar sensor 110.

[0110] In its configuration, as illustrated in [Fig.4], the optical system 120 comprises at least one optical element 121 for shaping the electromagnetic signals.

[0111] Concretely, the optical element 121 of the optical system 120 ensures the shaping of the electromagnetic signals emitted and received by one or more of the transmitter-receiver radars 111.

[0112] The term “optical element” means a component of the optical system 120 designed to manipulate and control the electromagnetic signals transmitted and received by the radar transmitters 111 of the radar sensor 110. The optical element 121 plays a key role in optimizing the performance of the radar sensor 110 by modifying the characteristics of the electromagnetic signals. For example, in the context of the invention, the term “optical element” may refer to: a dielectric lens shaped to focus the radar signals on a specific area of the target 10, a diffraction grating capable of separating the different frequencies of the signals for precise spectral analysis, an adjustable polarizer for controlling the polarization of the electromagnetic waves to improve the detection of certain types of materials, or a variable surface mirror for dynamically orienting the radar beam and increasing the coverage area of the system 100.

[0113] Thanks to this functionality, this shaping of the electromagnetic signals by the optical element 121 makes it possible to optimize the performance of the radar sensor 110.

[0114] The term “shaping of the electromagnetic signals” refers to the process by which the optical element 121 modifies the physical properties of the electromagnetic waves emitted and received by the radar sensor 110. This shaping aims to optimize the performance of the system 100 by adapting the characteristics of the signals to the specific needs of non-invasive analysis. For example, in the context of the invention, the term “shaping of the electromagnetic signals” may include: focusing the radar beam to increase the spatial resolution in a region of interest of the target 10, modifying the wavefront to compensate for distortions induced by the propagation medium, modulating the phase of the signals to improve the detection of moving targets 10, or adapting the temporal shape of the radar pulses to optimize penetration into different types of materials while maintaining high resolution.

[0115] It is important to note that the optical coupling between the optical system 120 and the radar sensor 110 ensures efficient integration of these two components. This coupling allows the optical system 120 to interact directly with the electromagnetic signals processed by the radar sensor 110.

[0116] Overall, the addition of the optical system 120 to the scanning system 100 for non-invasive analysis of targets 10 provides additional signal processing capabilities.

[0117] Therefore, these capabilities improve the accuracy and quality of the radar representation 20 generated by the system 100.

[0118] Radar representation reconstruction processor

[0119] The system 100 according to the invention further comprises at least one radar representation reconstruction processor 130.

[0120] More specifically, the radar representation reconstruction processor 130 is operatively coupled to the radar sensor 110.

[0121] In its design, as illustrated in [Fig.7], the radar representation reconstruction processor 130 is designed to reconstruct the radar representation 20.

[0122] Concretely, the reconstruction of the radar representation 20 is carried out from all or part of the K measurement sequences.

[0123] It is important to note that the K measurement sequences are generated during all or part of the sequential acquisitions. In practice, these sequential acquisitions are carried out by the radar sensor 110, as described previously.

[0124] Thanks to this configuration, the functional coupling between the radar representation reconstruction processor 130 and the radar sensor 110 allows efficient interaction between these two components. Consequently, this coupling ensures optimal processing of the data collected by the radar sensor 110.

[0125] Furthermore, the ability of the radar representation reconstruction processor 130 to use all or part of the K measurement sequences provides flexibility in the reconstruction process. This key feature makes it possible to optimize the quality of the reconstructed radar representation 20 according to the specific needs of the application.

[0126] Artificial intelligence module: functionalities and advanced processing of radar data

[0127] In a first particular implementation of the radar representation reconstruction processor 130, the latter includes or is coupled to an artificial intelligence module 140 included in the system 100.

[0128] The term “artificial intelligence module” means an advanced software component integrated into the radar representation reconstruction processor 130. This module uses machine learning techniques to analyze and interpret the radar data autonomously. For example, in the context of the invention, the term “artificial intelligence module” may refer to: a convolutional neural network for analyzing radar images, a clustering algorithm for grouping similar objects in the radar representation 20, or a rule-based expert system for identifying specific characteristics in the radar data.

[0129] More specifically, the artificial intelligence module 140 is designed to perform several specific operations.

[0130] First, the artificial intelligence module 140 receives the radar representation 20 or all or part of the sequential acquisitions.

[0131] It is important to note that this data is referred to as model input data. Subsequently, the artificial intelligence module 140 uses this model input data for its subsequent analyses.

[0132] Then, from the model input data, the artificial intelligence module 140 determines the contours of objects detected in the target.

[0133] This step is important, because this determination of the contours makes it possible to delimit the different objects present in the radar representation 20 or in the sequential acquisitions.

[0134] “Contour determination” means the process by which the artificial intelligence module 140 identifies and delimits the boundaries of objects present in the radar representation 20 or the sequential acquisitions. This step serves to isolate and analyze individually the detected objects. For example, in the context of the invention, the term “contour determination” may include: the application of edge detection algorithms to identify the boundaries of buried objects, the use of image segmentation techniques to separate different structures in a complex radar representation 20, or the use of methods adaptive thresholding to distinguish objects from background noise in radar data.

[0135] In a second step, the artificial intelligence module 140 then extracts specific characteristics of the detected objects.

[0136] It should be emphasized that this extraction is also done from the model input data. The extracted features provide detailed information about each detected object.

[0137] “Extracted features” means the specific and relevant information that the artificial intelligence module 140 identifies and isolates from the objects detected in the radar representation 20. These features serve as a basis for the subsequent analysis and classification of the objects. For example, in the context of the invention, the term “extracted features” may include: the size and geometric shape of a detected object, the estimated dielectric properties of an identified structure, or the texture and apparent density of an area of interest in the radar representation 20.

[0138] Finally, the artificial intelligence module 140 classifies the detected objects.

[0139] More specifically, this classification associates the objects with predetermined classes of objects. To do this, the artificial intelligence module 140 performs this classification on the basis of the characteristics extracted previously.

[0140] In summary, all of these operations allow the artificial intelligence module 140 to analyze the radar representation 20 in depth and to extract structured information on the detected objects.

[0141] Furthermore, in a first variant of the first particular implementation of the radar representation reconstruction processor 130, the artificial intelligence module 140 is designed to perform additional operations.

[0142] In this context, the artificial intelligence module 140 generates metadata associated with each detected object.

[0143] More specifically, the metadata includes at least the classification and the position of the object in the radar representation 20. The artificial intelligence module 140 thus creates a set of structured information for each identified object.

[0144] “Metadata” means the additional information generated by the artificial intelligence module 140 to enrich the radar representation 20. This metadata provides additional details on the detected objects, thus facilitating their interpretation and subsequent analysis. By way of example, in the context of the invention, the term “metadata” may include: the classification assigned to a detected object (for example, “metal pipe” or “cavity”), the precise coordinates of the object in the space of the radar representation 20, or information on the reliability of the detection and classification for each identified object.

[0145] Once this step is completed, after the generation of the metadata, the artificial intelligence module 140 integrates this metadata into the radar representation 20.

[0146] It is important to emphasize that this integration makes it possible to enrich the radar representation 20 with detailed information on each detected object.

[0147] Consequently, the generation and integration of metadata improves the quality and accuracy of the analysis of the radar representation 20. These operations allow for a more in-depth interpretation of the data collected by the scanning system 100 for the non-invasive analysis of targets 10.

[0148] Online learning module and dynamic update of the scanning system

[0149] From another perspective, in a second variant of the first particular implementation of the radar representation reconstruction processor 130, the system 100 comprises at least one network communication interface 150 and at least one online learning module 160.

[0150] More specifically, the network communication interface 150 is coupled to the radar representation reconstruction processor 130, the online learning module 160 and the artificial intelligence module 140.

[0151] In parallel, the online learning module 160 is coupled to the artificial intelligence module 140.

[0152] The term “network communication interface” means a hardware and software component allowing the system 100 to connect and exchange data with external resources, in particular remote servers. This interface facilitates the updating and continuous improvement of the system 100. For example, in the context of the invention, the term “network communication interface” may designate: an integrated Wi-Fi module for wireless connection to a local network, an Ethernet interface for a high-speed wired connection, or a cellular modem for mobile connectivity in a field situation.

[0153] The term “online learning module” means a specialized software component that allows the system 100 to continuously improve its analysis capabilities by integrating new data and knowledge over time. This module works in close collaboration with the artificial intelligence module 140. For example, in the context of the invention, the term “online learning module” may include: an incremental learning algorithm capable of adjusting the classification models without requiring complete retraining, a system 100 for updating the knowledge bases to integrate new types of objects to be detected, or a mechanism for adapting the feature extraction parameters based on user feedback.

[0154] In this context, the online learning module 160 is designed to perform several operations.

[0155] First, the online learning module 160 establishes a connection with at least one remote server 200 via the network communication interface 150 and at least one communication network 300.

[0156] The term “remote server” means a computing infrastructure external to the system 100, accessible via the network communication interface 150, which provides computing, storage and update resources to improve the performance of the system 100. By way of example, in the context of the invention, the term “remote server” may designate: a cloud data center hosting advanced machine learning models, an update server centralizing software improvements for all deployed scanning systems, or a collaborative platform allowing the sharing of experiences and data between different users of the system 100.

[0157] Then, the online learning module 160 receives update data from the remote server 200.

[0158] “Update data” means all the information transmitted by the remote server 200 to the online learning module 160 to improve the performance of the system 100. This data makes it possible to update and enrich the analysis capabilities of the artificial intelligence module 140. For example, in the context of the invention, the term “update data” may include: new training sets to refine existing classification models, corrections of errors identified in the radar signal processing algorithms, or updates to the radar signature database to include new types of materials or objects.

[0159] In a first example of the update data, it includes new classification models.

[0160] “Classification models” means the mathematical and algorithmic structures used by the artificial intelligence module 140 to categorize the objects detected in the radar representation 20. These models are updated and improved using the data received from the remote server 200. By way of example, in the context of the invention, the term “classification models” may designate: a deep neural network trained to recognize different types of structural defects, a set of decision rules to identify the specific characteristics of certain materials, or a probabilistic model to estimate the nature of buried objects based on their radar signature.

[0161] In a second example of the update data, it includes new classes of objects to be detected.

[0162] “New classes of objects to be detected” means the categories of elements or structures that the system 100 was not initially configured to identify, but which it can now recognize thanks to the updates. The addition of these new classes expands the analysis capabilities of the system 100. For example, in the context of the invention, the term “new classes of objects to be detected” may include: new types of composite materials used in construction, specific configurations of recently identified structural defects, or even particular archaeological objects for prospecting applications.

[0163] In a third example of the update data, it includes adjusted parameters for feature extraction.

[0164] “Adjusted parameters for feature extraction” means the optimized variables and configurations that allow the artificial intelligence module 140 to identify and isolate relevant information in the radar data. These parameters are refined to improve the accuracy and efficiency of the analysis. For example, in the context of the invention, the term “adjusted parameters for feature extraction” may include: detection thresholds adapted for different types of soils or structures, optimized filters to reduce noise in radar signals specific to certain environments, or adjusted segmentation parameters to better isolate objects in complex radar representations.

[0165] Once this update data is received, the online learning module 160 integrates it into the artificial intelligence module 140.

[0166] Subsequently, the online learning module 160 dynamically adapts the detection and classification algorithms of the artificial intelligence module 140 based on the received update data.

[0167] The term “dynamically adapts the detection and classification algorithms” means the process by which the online learning module 160 modifies and optimizes in real time the procedures used by the artificial intelligence module 140 to identify and categorize the objects in the radar representation 20. This adaptation is done according to the update data received and the observed performances. For example, in the context of the invention, the term “dynamically adapts the detection and classification algorithms” can designate: the automatic adjustment of the detection thresholds according to the environmental conditions specific to each scan, the modification of the radar signal processing parameters to adapt to different types of materials encountered, or the real-time integration of new classification rules based on feedback from other users of the system 100.

[0168] “Detection and classification algorithms” means the mathematical and logical procedures used by the artificial intelligence module 140 to identify and categorize objects in the radar representation 20. These algorithms rely on the extracted characteristics to associate each object with a predefined class. For example, in the context of the invention, the term “detection and classification algorithms” may refer to: a Bayesian classifier to distinguish different types of materials in a structure, a random forest algorithm to identify the nature of buried objects, or a support vector machine (SVM) system to categorize anomalies detected in a non-destructive inspection.

[0169] Thanks to this adaptation, the online learning module 160 allows the artificial intelligence module 140 to identify and classify new detected objects according to the update data.

[0170] Finally, the online learning module 160 transmits to the remote server 200 information on the classification performance following the update. This step is important, because this transmission allows an iterative process of improving the artificial intelligence module 140.

[0171] “Classification performance information” means the quantitative and qualitative data generated by the system 100 to evaluate the effectiveness and accuracy of the detection and classification algorithms. This information is transmitted to the remote server 200 to enable continuous improvement of the system 100. For example, in the context of the invention, the term “classification performance information” may include: confusion matrices detailing the true positive and false positive rates for each class of detected objects, confidence measures associated with each classification performed, or specific error reports identifying instances where the system 100 encountered particular difficulties in analyzing the radar data.

[0172] In conclusion, the addition of these components and functionalities to the system 100 allows for continuous updating and improvement of the capabilities of detecting and classifying objects by the artificial intelligence module 140.

[0173] Radar representation reconstruction process and improvement techniques

[0174] In a second particular implementation of the radar representation reconstruction processor 130, as illustrated in [Fig.7], it is designed to reconstruct the radar representation 20 by performing several steps.

[0175] The term “reconstruct” refers to the complex process by which the radar representation reconstruction processor 130 generates a complete and detailed image from the raw data acquired by the radar sensor 110. This reconstruction involves several data processing steps to produce a faithful representation of the analyzed target 10. For example, in the context of the invention, the term “reconstruct” can refer to: the assembly of multiple image segments radar into a coherent view of an underground structure, creating a three-dimensional map of an archaeological site from multiple radar scans, or generating a high-resolution representation of a buried object by combining data acquired from different angles.

[0176] First of all, the first step consists of a pre-processing of the acquired data.

[0177] More specifically, the preprocessing includes the extraction of phase and amplitude information from the K measurement sequences.

[0178] “Phase and amplitude information” means the fundamental characteristics of the electromagnetic signals received by the radar sensor 110, which are extracted during the preprocessing of the data. This information is essential for determining the distance, size and nature of the detected objects. For example, in the context of the invention, the term “phase and amplitude information” may include: phase variations allowing the depth of a buried object to be precisely calculated, amplitude changes indicating the density or composition of a detected structure, or phase and amplitude patterns characteristic of certain materials or geometric shapes.

[0179] In addition, the preprocessing also includes compensation for the progressive offset between the radars.

[0180] “Inter-radar progressive offset compensation” means the correction process applied to the raw data to account for the irregular arrangement of the transceiver radars 111 in the sensor. This compensation is necessary to obtain a consistent and accurate representation of the target. For example, in the context of the invention, the term “inter-radar progressive offset compensation” may include: mathematically adjusting the signal arrival times to correctly align the data from each radar, correcting geometric distortions induced by the staggered configuration of the transceivers, or applying spatial filters adapted to the specific geometry of the radar array.

[0181] Then, the second step is the iterative generation of distinct segments Ci of the radar representation 20 for each acquisition.

[0182] “Iterative generation” means the sequential and repetitive process by which the radar representation reconstruction processor 130 creates distinct segments Ci of the radar image for each acquisition. This method takes into account the irregular geometry of the radar array and uses the results of the data preprocessing to progressively construct the complete representation. For example, in the context of the invention, the term “iterative generation” may refer to: the successive creation of radar image slices corresponding to each position of the sensor during a linear scan of a structure, the gradual accumulation of information from depth to construct a 3D representation of an underground site, or the sequential production of partial views of a complex object, each corresponding to a different observation angle of the radar network.

[0183] In a third step, the third stage is the progressive merging of the distinct segments Ci of the radar representation 20.

[0184] “Progressive fusion” means the iterative process by which the distinct segments Ci of the radar representation 20 are combined to form a complete and coherent image. This fusion takes into account the relative position information between the sensor and the target 10 for each acquisition. By way of example, in the context of the invention, the term “progressive fusion” can designate: the assembly of 2D radar image slices to create a 3D representation of a complex structure, the combination of data acquired at different frequencies to improve resolution and penetration, or the integration of multiple scans of an area to reduce noise and improve the overall quality of the image.

[0185] Concretely, this fusion integrates the relative position information between the radar sensor 110 and the target 10 for each acquisition. The fusion uses the results of the previous steps to refine the fusion process.

[0186] Finally, the fourth and final step is the generation of a final radar representation 20 by iterative synthesis.

[0187] More specifically, this synthesis combines the information processed at each previous step to produce the final radar representation 20.

[0188] In summary, these steps allow the radar representation reconstruction processor 130 to generate a complete and accurate radar representation 20 from the data acquired by the radar sensor 110.

[0189] Furthermore, in a variant of the second particular implementation of the radar representation reconstruction processor 130, the latter is designed to perform additional steps in addition to those described previously.

[0190] First, the first additional step is the application of resolution enhancement techniques.

[0191] “Resolution enhancement techniques” means advanced signal processing methods used to increase the accuracy and level of detail of the reconstructed radar image. These techniques exploit the spatial diversity created by the radars’ progressive shift and build on the results of previously performed fusion. For example, in the context of the invention, the term “resolution enhancement techniques” may include: the application of super-resolution algorithms to distinguish close objects beyond the theoretical diffraction limit, the use of synthetic aperture techniques to improve the azimuthal resolution of the radar image, or the use of methods adaptive deconvolution to refine the contours of objects detected in complex environments.

[0192] Then, the second additional step is an adaptive post-processing of the merged radar representation 20.

[0193] “Adaptive post-processing” means all the operations performed on the merged radar representation 20 to optimize its quality and interpretability. This post-processing adapts to the specific characteristics of the acquired data and can integrate additional information provided by other modules of the system 100. For example, in the context of the invention, the term “adaptive post-processing” can designate: the application of noise reduction filters adapted to the type of target analyzed, the integration of metadata generated by the artificial intelligence module 140 to enrich the interpretation of the image, or the dynamic adjustment of the contrast and brightness parameters to highlight specific characteristics of the radar representation 20 according to the needs of the analysis.

[0194] More specifically, this post-processing includes the integration of metadata generated by the artificial intelligence module 140, if this module is present. In addition, the post-processing uses the information from the previous steps to optimize the processing.

[0195] Finally, the third additional step consists of integrating the results of the two previous steps into the generation of the final radar representation 20.

[0196] It is important to emphasize that this integration allows an iterative improvement of the quality and precision of the reconstruction.

[0197] In conclusion, these additional steps performed by the radar representation reconstruction processor 130 make it possible to refine and optimize the final radar representation 20.

[0198] Thus, the iterative improvement process ensures increased quality and accuracy of the reconstruction.

[0199] Process for non-invasive analysis of heterogeneous targets and variants of use of the system

[0200] The invention also covers a use of the system 100 for the non-invasive analysis of heterogeneous targets 10 which comprises several steps.

[0201] “Heterogeneous targets” means the complex objects or structures analyzed by the system 100, characterized by a non-uniform composition and variable dielectric properties. These targets 10 have internal variations that require in-depth and non-invasive analysis to be correctly identified and characterized. For example, in the context of the invention, the term “heterogeneous targets” may designate: a geological structure comprising different layers of soil and rock with distinct electromagnetic properties, a a historic building whose walls contain various building materials and potentially hidden elements, or a biological organism with tissues of varying densities and compositions. In addition, the 100 system is particularly suitable for analyzing materials such as textiles or wood, which may have significant internal variations.

[0202] In practice, these steps allow for in-depth, non-invasive analysis of heterogeneous targets.

[0203] “Positioning” means the initial and fundamental step of the analysis process, which consists of placing the system 100 in an optimal configuration relative to the heterogeneous target 10. This positioning is essential to ensure the accuracy and reliability of the data acquired during the subsequent stages of the analysis. For example, in the context of the invention, the term “positioning” may include: adjusting the distance and angle between the radar sensor 110 and the surface of a structure to be analyzed to maximize signal penetration, setting up an automated scanning system to systematically cover an area of interest on an archaeological site, or configuring an array of fixed sensors around a moving target to ensure continuous and uniform coverage during data acquisition.

[0204] Then, the second step involves the acquisition of K measurement sequences. More precisely, these measurement sequences provide the raw data necessary for the analysis.

[0205] In a third step, the third stage is the reconstruction of a radar representation 20 of the heterogeneous target 10. It should be emphasized that this reconstruction uses the data acquired during the previous step.

[0206] Subsequently, the fourth step consists of the analysis of the radar representation 20. More specifically, this analysis aims to detect localized variations in dielectric properties within the target. This step is particularly important for the detection of localized anomalies, such as hard points, in materials such as textiles or wood.

[0207] “Localized anomalies” means areas within a heterogeneous target 10 having dielectric properties that are significantly different from their immediate surroundings. These localized anomalies, which include hard spots, are particularly important in non-invasive analysis because they can indicate the presence of defects, structures of interest or foreign elements within the target 10. For example, in the context of the invention, the term “localized anomalies” can refer to: a metallic inclusion in a wooden structure that may indicate the presence of a nail or screw, an area of increased density in a textile material suggesting a manufacturing defect or a repair. The detection and characterization Precise analyses of these localized anomalies allow for in-depth, non-destructive analysis of the composition and internal structure of heterogeneous targets.

[0208] Then, the fifth step involves the classification of the detected variations. To do this, this classification uses the artificial intelligence module 140 of the system 100. In the case of the detection of localized anomalies, including hard points, the artificial intelligence module 140 is specifically trained to recognize these variations in different types of materials.

[0209] Finally, the sixth and final step is the generation of a two-dimensional or three-dimensional map of the target. It is important to understand that this map incorporates the classified variations and their associated characteristics. For detected localized anomalies, including hard spots, this map includes their precise position and their specific dielectric characteristics.

[0210] In summary, all of these steps allow a complete and detailed analysis of heterogeneous targets in a non-invasive manner.

[0211] It is important to note that the system 100 also offers the possibility of generating contrast images without going through the classification step. In this case, the use of the system 100 stops after the fourth step, producing a radar representation 20 which highlights the variations in dielectric properties within the target 10, without categorizing them. This option allows for rapid and flexible analysis, particularly useful for preliminary examinations or in situations where detailed classification is not necessary.

[0212] In the specific context of detecting localized anomalies, including hard points, in materials such as textiles or wood, the artificial intelligence module 140 is designed to identify localized variations in dielectric properties corresponding to these anomalies. It uses machine learning models, which may be specific to a type of material or cover several types, to classify these variations. The module then generates metadata for each detected localized anomaly, including its position and its dielectric characteristics, which are integrated into the reconstructed radar representation to facilitate their identification and analysis.

[0213] Furthermore, in a first variant of the use of the system 100, this has additional characteristics when the heterogeneous target 10 is in relative motion with respect to the system 100 during the acquisition of the K measurement sequences.

[0214] In this context, this use comprises two additional steps.

[0215] First, the first additional step consists of the compensation of the relative movement in the reconstruction of the radar representation 20. It is important note that this compensation makes it possible to adjust the radar representation 20 taking into account the movement of the target 10 relative to the system 100.

[0216] Second, the second additional step involves the temporal analysis of the detected variations. More specifically, this temporal analysis aims to identify dynamic changes within the target. Accordingly, the identification of these dynamic changes provides additional information on the behavior of the heterogeneous target 10 in motion.

[0217] In summary, these additional steps make it possible to adapt the non-invasive analysis to moving targets 10, thus providing greater flexibility in using the system 100. In addition, the motion compensation and the temporal analysis enrich the analysis capabilities of the system 100 by taking into account the dynamics of the target.

[0218] From another perspective, in a second variant of the use of the system 100, this presents specific characteristics concerning the dynamic adaptation of the artificial intelligence module 140.

[0219] More specifically, the artificial intelligence module 140 dynamically adapts during analysis via the online learning module 160.

[0220] First of all, the dynamic adaptation of the artificial intelligence module 140 allows the identification and classification of new categories of variations not previously recorded.

[0221] It is important to understand that this ability to identify and classify new categories expands the analysis possibilities of the system 100.

[0222] Then, the dynamic adaptation also allows the continuous improvement of the classification accuracy of the detected variations. As a result, this continuous improvement in accuracy ensures increasing performance of the system 100 over time.

[0223] Finally, dynamic adaptation allows real-time adaptation of the acquisition and reconstruction parameters according to the specific characteristics of the target 10 analyzed.

[0224] It is important to emphasize that this real-time adaptation optimizes the performance of the system 100 for each specific target.

[0225] In conclusion, these dynamic adaptation capabilities of the artificial intelligence module 140 reinforce the flexibility and efficiency of the system 100 in the non-invasive analysis of heterogeneous targets 10.

[0226] Conclusion

[0227] We have described and illustrated the invention. However, the invention is not limited to the embodiments we have presented. Indeed, numerous combinations of the variants, alternatives, embodiments and implementations, can be envisaged without requiring substantial modifications to the invention. Thus, an expert in the field can deduce other variants, alternatives, embodiments and implementations, upon reading the description and the appended figures and depending on the economic, ergonomic and dimensional constraints to be respected.

[0228] In particular, when an expression uses the term "at least one", this means that the element or characteristic in question may be present in a single occurrence or in several occurrences, thus comprising one, two, three or more elements or characteristics, without a specified upper limit.

[0229] On the other hand, when an item is "designed" to perform a particular function, this means that this item is created specifically for the purpose of performing this particular function.

[0230] However, depending on the needs and available resources, it may be possible to consider using an existing element, which will be modified or adapted to fulfill this particular function, without requiring substantial modifications to the invention.

[0231] The invention may be the subject of numerous variants and applications other than those described above. In particular, unless otherwise indicated, the different structural and functional characteristics of each particular implementation described above should not be considered as combined and / or closely and / or inextricably linked to each other, but, on the contrary, as simple juxtapositions. Furthermore, the structural and / or functional characteristics of the different embodiments described above may be the subject in whole or in part of any different juxtaposition or any different combination.

Claims

Claims

1. A scanning system (100) for non-invasive analysis of targets (10), comprising, - at least one radar sensor (110) which comprises a plurality of transceiver radars (111) which are arranged in a two-dimensional configuration to generate a radar representation (20) of at least one target (10), wherein, - each transceiver radar (111) has an identical predetermined two-dimensional footprint and is designed to, during sequential acquisitions, transmit electromagnetic signals via its transmitter and at least one first antenna (1111), and receive corresponding reflected electromagnetic signals via its receiver and at least one second antenna (1112), the electromagnetic signals having a frequency between 3 GHz and 30 THz, - for an array of MxN transceiver radars (111), the system (100) is designed to perform K sequential acquisitions,each acquisition corresponding to at least one measurement made by all or part of the matrix of transmitter-receiver radars (111) and contributing to a distinct segment, Ci, of the radar representation (20), for a different relative position between the radar sensor (110) and the target (10), the sequential acquisitions being obtained by moving the radar sensor (110) relative to the target (10) or vice versa, according to a predetermined or adaptive direction of movement, D, thus allowing a progressive and piecewise construction of the radar representation (20), - the transmitter-receiver radars (111) are arranged in an array of irregular geometry with a progressive offset, de, between them, in at least one of the two dimensions of their two-dimensional footprint, this offset being less than the footprint of an individual transmitter-receiver radar (111) in at least the corresponding dimension,this arrangement being designed so that the acquisition of the distinct segments, Ci, of the radar representation (20) is carried out progressively over time, and - the arrangement of the transmitter-receiver radars (111) and the number K of sequential acquisitions are designed to obtain a resolution, predetermined spatial resolution in the radar representation (20) which is substantially improved compared to the resolution corresponding to the offset between the transmitting-receiving radars (111), this improvement being a function of the total number K of acquisitions and the number of transmitting-receiving radars (111) in at least one dimension of the two-dimensional configuration.

2. The system (100) of claim 1, wherein the offset, of, progressive between the transceiver radars (111) is either constant with an identical offset value between each pair of adjacent transceiver radars (111), or variable with different offset values between the pairs of adjacent transceiver radars (111), or a combination of constant and variable offsets between different pairs of adjacent transceiver radars (111).

3. The system (100) of any one of claims 1 to 2, wherein the irregularly-geometry array with progressive offset of the transceiver radars (111) is designed in a geometric pattern selected from: a linear offset, a staggered pattern, a spiral pattern, a fractal arrangement, a pseudo-random arrangement, or a distorted grid pattern.

4. System (100) according to any one of claims 1 to 3, comprising at least one optical system (120) which is optically coupled to the radar sensor (110), the optical system (120) comprising at least one optical element (121) for shaping the electromagnetic signals transmitted and received by one or more of the transmitter-receiver radars (111).

5. System (100) according to any one of claims 1 to 4, further comprising, - at least one radar representation reconstruction processor (130) which is operatively coupled to the radar sensor (110) and which is adapted to reconstruct the radar representation (20) from all or part of the K measurement sequences generated during all or part of the sequential acquisitions.

6. The system (100) of claim 5, wherein the radar image reconstruction processor (130) comprises or is coupled to an artificial intelligence module (140) included in the system (100), the artificial intelligence module (140) being configured to, - receiving the radar representation (20) or all or part of the sequential acquisitions, called model input data, - determining, from the model input data, the contours of objects detected in the target (10), - extracting, from the model input data, specific characteristics of the detected objects, - classifying the detected objects by associating them with predetermined classes of objects, on the basis of the extracted characteristics.

7. System (100) according to claim 6, wherein the artificial intelligence module (140) is further designed to, - generate metadata associated with each detected object, comprising at least its classification and its position in the radar representation (20), and - integrate the generated metadata into the radar representation (20).

8. System (100) according to any one of claims 6 to 7, further comprising, - at least one network communication interface (150), and - at least one online learning module (160) coupled to the artificial intelligence module (140), the online learning module (160) being adapted to, — establish a connection with at least one remote server (200) via the network communication interface (150), — receive from the remote server (200) update data comprising, — new classification models, — new classes of objects to be detected, and / or — adjusted parameters for feature extraction, — integrate the received update data into the artificial intelligence module (140), — dynamically adapt the detection and classification algorithms of the artificial intelligence module (140) according to the received update data,— enabling the artificial intelligence module (140) to identify and classify new detected objects in accordance with the update data, and — transmitting to the remote server (200) information on the classification performance following the update, so as to, to enable an iterative process of improving the artificial intelligence module (140).

9. System (100) according to any one of claims 5 to 8, wherein the radar representation reconstruction processor (130) is adapted to reconstruct the radar representation (20) by performing the following steps, - preprocessing the acquired data, comprising extracting phase and amplitude information from the K measurement sequences and compensating for the progressive shift, of, between the radars, - iteratively generating distinct segments, Ci, of the radar representation (20) for each acquisition, taking into account the irregular geometry of the radar array and using the results of the preprocessing, - progressively merging the distinct segments, Ci, of the radar representation (20), integrating the relative position information between the radar sensor (110) and the target (10) for each acquisition, and using the results of the previous steps to refine the merging,and - generation of a final radar representation (20) by iterative synthesis, combining the information processed at each stage.,

10. The system (100) of claim 9, wherein the radar representation reconstruction processor (130) is further configured to perform the following additional steps: - applying resolution enhancement techniques exploiting the spatial diversity created by the progressive shift of the radars, based on the results of the fusion, - adaptive post-processing of the merged radar representation (20), including the integration of metadata generated by the artificial intelligence module (140) if present, and using the information from the previous steps to optimize the processing, and - integrating the results of these additional steps into the generation of the final radar representation (20), so as to allow an iterative improvement of the quality and accuracy of the reconstruction.

11. Use of a system (100) according to any one of claims 1 to 10 for the non-invasive analysis of heterogeneous targets (10), comprising the following steps, - positioning the system (100) relative to a heterogeneous target, - acquisition of K measurement sequences, - reconstruction of a radar representation (20) of the heterogeneous target (10), - analysis of the radar representation (20) to detect localized variations of dielectric properties within the target (10), - classification of the detected variations using the artificial intelligence module (140), and - generation of a two-dimensional or three-dimensional map of the target (10) integrating the classified variations and their associated characteristics.

12. Use according to claim 11, in which the heterogeneous target (10) is in relative motion with respect to the system (100) during the acquisition of the K measurement sequences, and further comprising the steps of, - compensating for the relative motion in the reconstruction of the radar representation (20), and - temporal analysis of the detected variations to identify dynamic changes within the target.

13. Use according to any one of claims 11 to 12, in which the artificial intelligence module (140) is dynamically adapted during the analysis via the online learning module (160) so as to allow, - the identification and classification of new categories of variations not previously recorded, - the continuous improvement of the classification accuracy of the detected variations, and - the real-time adaptation of the acquisition and reconstruction parameters according to the specific characteristics of the target (10) analyzed.

Images