Research activities

Research projects :

  • APASH (Assistance au Pilotage pour l’Autonomie et la Sécurité des personnes Handicapées) [2012 -]

This project is supported by the Images & Réseaux cluster. It involves three laboratories, namely IRISA/Inria, IETR and LGCGM. Two industrial partners take part into this project: AdvanSEE and Ergovie. It aims at designing a driving assistance for electrical wheelchair towards the autonomy and security of disabled people. The idea is to propose a robotic vision based system dedicated to assisted navigation of electrical wheelchair in an unknown environment. In particular, navigating along a corridor, going through doors in a secure way without risking collision because of hazardous wheelchair motions remains a relevant issue. The idea is here to provide an embedded and flexible system able to ensure the immediate compatibility of the proposed system with existing electrical wheelchairs. This study is conducted in conjunction with the scope of the Inria Large-scale initiative action named Personally Assisted Living.

  • PERSEE (PERceptual Scheme for 2D&3D vidE(E)o Coding) [2009-2013]

This project is a fundamental research project coordinated by IRCCyN-­Nantes. It
associates 3 other laboratories : INRIA-Rennes, IETR-Rennes and LTCI-TelecomParisTech. It was financed by ANR.The result of the project is the definition of methods and algorithmic tools for efficient compression of 2D and 3D video (multi-­‐‑view and multi-­‐‑view plus depth). For example, we can give the definition of new 2D and 3D visual attention models, the improved visual quality of synthesized views (3D video), the development of efficient 2D coding methods.
Some of these tools have been integrated into a complete software architecture of video
coding, and have been proposed for the standardization (context : HEVC designed first for
the 2D video coding, and then expanded to include the 3D video coding). Two contributions
have been adopted by the standard 3DV-­‐‑HEVC.

  •  RUBI3 (Rendu Urbain Basé Image Immersif et Interactif) [2010-2012]

L‘objectif du projet RUBI3 était de concevoir et développer un système de navigation complexe dans des environnements 3D de grande taille tels que les villes. Le système doit offrir un seul mode de navigation (uniquement des modèles 3D, pas de modèles mixtes 2D/3D) pour des visions globales et immersives, permettre une navigation libre (le placement de la caméra ne sera pas contraint), ne nécessiter que des appareils à faible coût (ainsi que des données SIG) pour reconstruire la géométrie 3D des rues, bâtiments, magasins, etc. D’où la possibilité d’un déploiement à grande échelle (villes), se baser sur des méthodes de rendu et modélisation basés image pour atteindre les objectifs fixés.

Le consortium regroupait 4 partenaires : l’équipe Image de l’IETR, le projet Bunraku de l’IRISA/INRIA et deux entreprises : Viametris et Archividéo.

Phd co-supervision:

Laisser un commentaire

Votre adresse de messagerie ne sera pas publiée. Les champs obligatoires sont indiqués avec *