Thales

Sispia

Thomson-csf

Universite Dé Lorraine

Institut D'optique

Universite Paris X

Gérard Berginc

Ion Berechet

Stefan Berechet

Brigitte Loiseaux

Daniel Dolfi

Jean-Luc Reverchon

Mehdi Alouini

Romain Czarny

Michel Pate

Francedillaois Micheron

François Goudail

Jean-Baptiste Bellet

Michel Jouffroy

Arnaud Beniere

Frank Normand

Rodolphe Krawczyk

Géraldine Guida

A method for an object of interest in a degraded 2D digital image of the object is provided. The method includes the following steps: detecting, beforehand, the object of interest in a 2D digital image and assigning it a label; reconstructing a 3D volume of the object thus labeled from a plurality of available 2D digital images of the object of interest; storing, in a database, a record relating to the object thus reconstructed in 3D form and labeled; for each record thus stored, generating a new plurality of 2D digital images according to a plurality of viewing modes from the thus reconstructed 3D volume of each object; training a neural network on a learning set composed of an expanded set of 2D digital images thus generated and corresponding with the label of the object of interest to be recognized; from a degraded 2D digital image of the object of interest to be recognized; using the neural network thus trained to deliver as output the label of the object and a confidence index linked to the recognition of the object of interest.

Object recognition method with increased representativeness

A method for discriminating and identifying, by 3D imaging, an object in a complex scene comprises the following steps: generating a sequence of 2D MIP images of the object, from a 3D voxel volume of the complex scene, this volume visualized by an operator by using an iterative process of MIP type from a projection plane and an intensity threshold determined by the operator on each iteration, automatically extracting, from the sequence of images, coordinates of a reduced volume corresponding to the sequence of images, choosing one of the intensity thresholds used during the iterations, automatically extracting, from the 3D volume of the complex scene, from the coordinates and chosen intensity threshold, a reduced 3D volume containing the object, automatically generating, from the reduced volume, by intensity threshold optimization, an optimized intensity threshold and an optimized voxel volume, a color being associated with each intensity, identifying the object by visualization.

Method for discrimination and identification of objects of a scene by 3-D imaging

A method for 3D reconstruction of an object based on back-scattered and sensed signals, including: generating, from the sensed signals, 3D points to which their back-scattering intensity is respectively assigned, which form a set A of reconstructed data, starting from A, extracting a set B of data, whose points are located within a volume containing the object, as a function of volume characteristics F, starting from B, extracting a set C of data characterizing the external surface of the object, the surface having regions with missing parts, depending on an extraction criterion, based on C, filling in the regions with missing parts by generation of a three-dimensional surface so as to obtain a set D of completed data of the object, without having to use an external database, and identifying the object based on D.

Method for 3D reconstruction of an object in a scene

An optronic porthole comprises a substrate with two faces. It comprises on one of the faces of the substrate or on both faces, a stack of several hetero-structures, each hetero-structure being composed of at least two semi-conducting layers SC1, SC2, the layer SC1 being doped, the layer SC2 itself comprising a two-dimensional electron gas layer formed at the interface with the layer SC1. It furthermore comprises an electrode in contact with all the electron gas layers, a bi-periodic metallic grid buried in the stack, in contact with the electrode. The substrate and the layers are transparent in the 0.4 &#x3bc;m-5 &#x3bc;m band.

Optronic window transparent to IR and reflecting RF

The invention relates to an optronic system for identifying an object including a photosensitive sensor, communication means and a computerized processing means making it possible to reconstruct the object in three dimensions on the basis of the images captured by the sensor and to identify the object on the basis of the reconstruction. The photosensitive sensor is able to record images of the object representing the intensity levels of an electromagnetic radiation reflected by the surface of the object captured from several observation angles around the object and the communication means are able to transmit the said images to the computerized processing means to reconstruct the object in three dimensions by means of a tomography function configured to process the images of the object representing the intensity levels of an electromagnetic radiation reflected by the surface of the object. The invention also relates to a method of computerized processing for object identification by reconstruction of the object in three dimensions. The invention is applied to the field of target detection, to the medical field and also microelectronics, for example.

Optronic system and method dedicated to identification for formulating three-dimensional images

Techniques for identifying images of a scene including illuminating the scene with a beam of 3 or more wavelengths, polarized according to a determined direction; simultaneously acquiring for each wavelength an image X(&#x3bb;) polarized according to said direction and an image X(&#x3bb;) polarized according to a direction perpendicular to said direction, X(&#x3bb;) being spatially distinct from X(&#x3bb;); calculating for each wavelength an intensity image which is a linear combination of X(&#x3bb;) and X(&#x3bb;), providing an intensity spectrum for each pixel; calculating for each wavelength a polarization contrast image on the basis of an intensity ratio calculated as a function of X(&#x3bb;) and of X(&#x3bb;), providing a polarization contrast spectrum for each pixel; and calculating a spectro-polarimetric contrast image of the scene, each pixel of this spectro-polarimetric contrast image calculated based on the intensity spectrum and the contrast spectrum of the pixel considered.

Method for identifying a scene from multiple wavelength polarized images

A method for synthetic reconstruction of objects includes: extracting criteria from a knowledge base; extracting, from sensed signals filtered by the criteria, weak signals; extracting, from the weak signals, weak signals of interest; removing noise from and amplifying the weak signals of interest and obtaining useful weak signals; identifying useful direct information, from useful weak signals filtered by the criteria and supplying optimum criteria; reconstructing, using the useful direct information, information of interest; reconstructing, using the information of interest, useful information and supplying optimum criteria; reconstructing, based on the useful information, three-dimensional information, supplying a recognition state file and supplying the optimum criteria; and updating the criteria with the optimum criteria.

Method for the three-dimensional synthetic reconstruction of objects exposed to an electromagnetic and/or elastic wave

The disclosed jacket comprises a layer that is discreet with respect to the visible and infrared frequencies, having a specified thickness, with a specified dielectric permittivity and emissivity close to 1 for the infrared frequency bands considered; a resistive layer, with an electrical resistivity and thickness that are determined so that the inverse of their product gives a specified resistance; a layer of dielectric material with a specified thickness and a specified dielectric permittivity; and a conductive layer with electrical conductivity determined so that it is considered as a reflective plane for the radar frequencies considered.

Growing community of inventors

Thiais, France

Gérard Berginc