TCI Team

Head : Hadj BATATIA

The research activity of the TCI team focuses on Images, as spatial, temporal, and/or spectral representation of physical phenomena. The team is interested in models and methods for image processing and interpretation in three different domains: medical imaging, remote sensing, and the French sign language (LSF). The Image (the team’s main research topic) is addressed by formulating image processing problems such as:

  • reconstruction, restoration, super-resolution
  • segmentation, classification
  • registration, change detection, motion analysis, fusion

Throughout these problems, members for the team are interested in a set of shared challenges inherent to the image formation process and to the underlying physical phenomena, particularly:

  • data quality and variability: 1) noise, aretfacts, missing data; 2) inter-region, inter-patient, inter-scene variability
  • multiple constraints: 1) spatial, temporal, spectral; 2) regularity, singularity, sparsity
  • dimensionality curse: very large number of parameters, insufficient datasets
  • multi-modality: 1) coherence and complementarity; 2) incompatibility in spatial, temporal and spectral scales

To handle these challenges, the team develops methodological tools for modeling and computing, particularly:

  • modeling: statistics, geometry, graphs, PDE, Bayesian methods
  • computing: optimization, sampling, parallel computing, regularization

The specific aspect of the TCI research lies in the unified approach adopted throughout the three domains. Precisely, a consistent scientific approach is considered for medical imaging, remote sensing and LSF, where models and methods are developed based on the underlying physical phenomena. Consequently, the team aims at developing shared methodological tools for the three domains. This specific aspect is illustrated through the following current research topics:

  • Bayesian methods and stochastic simulation methods, variational approaches and convex optimization for medical image processing and remote sensing
  • Parallel iterative methods for dynamic medical image filtering with strongly non-linear EDP models for convection-diffusion
  • Information geometry for preconditioning optimization problems applied to parameter estimation and medical image segmentation
  • Optical and radar (satellite, embedded sensors) image processing for automated guidance of groups of vehicles (cars, drones…)
  • Elaboration of domain specific sign-lexicon and gesture recognition for LSF

Medical imaging

In medical imaging, the team is interested in anatomic (CT, MRI, HFUS, OCT, Confocal microscopy) and functional (PET, fMRI, MrsI, EEG) images. Two application domains are the most frequently addressed: oncology and brain activity. For oncology, the team currently studies subjects such as tissue heterogeneity for tumor characterization, organs and tumors segmentation and evolution, therapeutic assessment and follow-up, tumor response and relapse prediction, and physiological motion compensation. For brain activity, the team conducts research projects on epilepsy and prediction of awakening in traumatized comatose. The team is particularly interested in dynamic images (3D + t) and multi-modal functional images.

Remote sensing

In remote sensing, the team is interested in multi-modality for change detection, unmixing, and guidance of groups of vehicles. Image modalities currently under study include radar (SAR, GPR), hyperspectral, optics and infrared.

French sign language

The French sign language makes a large research field that covers different and complementary domains, such as illustrated in the following figure :

In this domain, TCI is interested in the analysis and interpretation of communication gestures and attitudes made by persons observed with a vision system. The aim is to detect and track body components (hands, face, chest), to reconstruct the persons’ 3D posture, to analyze expressions, to finally make the linguistic interpretation of this information by recovering the semantics. To account for the variability of the human body and the complexity of the sign language, prior knowledge and constraints are incorporated throughout the process. Accordingly, the team’s research activity concentrates on dynamic models for gestures and face expression, and models of the sign language; while exploiting these models in interpretation methods. The team works also on designing and analyzing sign lexicons for specific domains, such as mathematics.

skills

medical imaging
teledetection
French Sign Language
multimodal fusion
statistical modelling and processing of images
intensive parallel computing
automated group guidance of vehicles
gesture recognition

personnel of the team TCI

Permanent members
Non-permanent members

publications of the team TCI

Articles dans des revues internationales
Articles dans des revues nationales
Rédaction de numéros spéciaux de revues
Conférences et workshops internationaux avec actes édités et comité de lecture
Conférences sans actes publiés
Rédaction d’ouvrages de synthèse Contributions à des ouvrages de synthèse
Thèses et habilitations
Rapports

contrats of the team TCI

AcronymeTitlePeriodScientific
leaders
Partners
CIP
[Contract completed]
Environnement pour le Calcul Intensif Pair à Pair2008-2011Spiteri, PierreLAAS(Laboratoire) – Université de Franche Comté(EPCSCP) – Université de Picardie(EPCSCP) – Euromed Textile(Association)
SignCom
[Contract completed]
Communication à base de signes entre agents réels et virtuels2007-2012Dalle, PatriceINRIA(EPST) – France Télécom(Société Anonyme) – Université de Bretagne Sud(EPCSCP)
AcronymeTitlePeriodScientific
leaders
Partners
DICTA-SIGN
[Contract completed]
Collaborative project, DICTA-SIGN, Sign Language Recognition, Generation and Modelling with application in Deaf Communication2009-2012Collet, ChristopheCNRS (EPCST) – UPS/Université Toulouse III(EPCSCP) – University of Surrey(EPCSCP) – Websourd(SCIC Société Coopérative d’Intérêt Collectif) – Athena Research and Innovation Center in Information Communication & Knowledge Technologies(Institution étrangère) – Universitaet Hambourg(Institution étrangère) – University of East Anglia(Institution étrangère)

[Contract completed]
UP2UML2005-2007Batatia, HadjFraunhofer-Gesellschaft zur Forderung der Angewandten Forschung E.V(Organisme étranger – Public)
KP-LAB
[Contract completed]
Developing Knowledge Practices2005-2010Batatia, HadjCEE/COMMISSION EUROPEENNE(Administration)
Tuesday 16 October 2018, 10h00
Cardiac Motion Estimation In Ultrasound Images using a Sparse Representation and Dictionary Learning
Nora Leïla OUZIR – Team MINDS – IRIT INP-ENSEEIHT, Salle des thèses
#these
Wednesday 25 April 2018, 14h00
Calcul haute performance pour la simulation d’interactions fluide-structure
Vincent PARTIMBENE – Team TCI – IRIT INP-ENSEEIHT, Salle des thèses
#these
Friday 8 December 2017, 10h00
Modélisation et traitement statistique d’images de microscopie confocale : application en dermatologie
Abdelghafour HALIMI – Team TCI – IRIT INP-ENSEEIHT, Salle des thèses
#these
Wednesday 15 November 2017, 14h00
Segmentation interactive multiclasse d’images par classification de superpixels et optimisation dans un graphe de facteurs
Bérengère MATHIEU – Team TCI – IRIT UT3 Paul Sabatier, IRIT, Salle des Thèses
#these
Tuesday 17 October 2017, 10h00
Modeling spatial and temporal variabilities in hyperspectral image unmixing
Pierre-Antoine THOUVENIN – Team SC – IRIT INP-ENSEEIHT, Salle des thèses
#these
Thursday 2 March 2017, 10h00
Bayesian M/EEG Source Localization with possible Joint Skull Conductivity Estimation
Facundo COSTA – Team TCI – IRIT INP-ENSEEIHT, Salle des thèses
#these
Friday 16 December 2016, 14h00
Optimisation de la navigation robotique
Sawssen JALEL – Team TCI – IRIT ENSEEIHT, Salle F501
#these
Friday 21 October 2016, 10h00
Reconstruction of enhanced ultrasound images from compressed measurements
Zhouye CHEN – Team TCI – IRIT UT3 Paul Sabatier, IRIT, Auditorium J. Herbrand
#these
Thursday 20 October 2016, 10h00
Inverse problems in ultrasound imaging – Applications in image deconvolution, segmentation and super-resolution
Ningning ZHAO – Team SC, Team TCI – IRIT INP-ENSEEIHT, Salle des thèses
#these
Friday 14 October 2016, 10h00
Advanced beamforming techniques in ultrasound imaging and the associated inverse problems
Teodora SZASZ – Team TCI – IRIT UT3 Paul Sabatier, IRIT, Auditorium J. Herbrand
#these
Tuesday 30 June 2015 – Friday 3 July 2015
Les Journées nationales du DEVeloppement logiciel 2015 de l’Enseignement Supérieur et de la Recherche
IPB – ENSEIRB-MATMECA, Bordeaux
#congres Know more
Friday 16 February 2018, 14h00 – 16h00
Patch-based regularization in multiband imaging inverse problems
José BIOUCAS – University of Lisboa (Portugal) TéSA, 7 Boulevard de la Gare, Toulouse
#seminaire
Tuesday 28 March 2017, 10h00
Approches bayésiennes, variationnelles et hybrides pour le traitement d’images médicales
Lotfi CHAARI – Team TCI – IRIT INP-ENSEEIHT, Salle des thèses
#hdr
Friday 25 November 2016, 10h00
Quelques problèmes inverses en imagerie ultrasonore
Adrian BASARAB – Team TCI – IRIT UT3 Paul Sabatier, IRIT, Auditorium J. Herbrand
#hdr
Tuesday 12 May 2015, 10h00
Modélisation statistique, problèmes variationnels et inférence bayésienne en traitement d’images médicales
Hadj BATATIA – Team TCI – IRIT INP-ENSEEIHT, Salle des theses
#hdr
Monday 8 April 2019
ado2019 : Journée thématique sur les autorités de données
Meteo-France, Toulouse
#journee
Monday 4 December 2017
Journée sur l’appel COGITER – InfraMED 2017 – COGITER – INFRAMED 2017 – COGITER – INFRAMED 2017
UT3 Paul Sabatier, IRIT, Auditorium J. Herbrand
#journee