Team VISTAS

Members
Overall Objectives
Scientific Foundations
Application Domains
Software
New Results
Contracts and Grants with Industry
Other Grants and Activities
Dissemination
Bibliography

Section: Other Grants and Activities

National initiatives

CNRS-INRIA MINCyT : Reduced dynamical modeling

Participants : Patrick Heas, Etienne Mémin.

duration 36 months.

This bilateral collaboration project between Argentina and France is a three years project that gathers the ESPCI (E. Weifreid) the ENS-LMD (M. Farge) and the University of Buenos Aires (G. Artana). It concerns the study of estimation techniques of low order dynamical from image sequences with the aim of providing recursive and adaptable techniques to go toward the possibility of flow control through visual servoing.

AIP INRA / ARC INRIA : DynaMIT project

Participant : Charles Kervrann.

no. xxx, duration 12 months.

This project, labeled within the arc Inria program and contracted in January 2007, was supported by INRA in 2009. The Vistas team is the prime contractor of the project dynamit which associates the following other groups: mia (Mathématiques et Informatique Appliquées) Unit from Inra Jouy-en-Josas, Curie Institute (“Compartimentation et Dynamique Cellulaires” Laboratory, umr cnrs -144 located in Paris). In this project, we develop new methods dedicated to the analysis of nd microscopy data and to the modeling of molecular and macromolecular mechanisms at the cell level (confocal spinning-disk microscopy, Fluorescence Recovery After Photobleaching microscopy, Fluorescence Lifetime Microscopy Imaging). Our main objective is then to provide computational methods and mathematical models to automatically extract, organize and model dynamic information observed in temporal series of images in multi-dimensional (nd ) microscopy. The central problem addressed by this project concerns the roles played by different molecular motors in Rab dynamics and a rich set of data (mostly image sequences in video-microscopy) will support the analysis. The biologist partners use very powerful and novel molecular (RNA interference), mechanical (micro-patterning) and optical (FRAP, photoablation) tools to normalize and perturb the cell activity.

ANR Icos-HD : Scalable Indexing and Compression for High Definition TV

Participants : Patrick Pérez, Hervé Jégou.

duration 36 months.

The partners of this projects are Temics and Texmex Inria project-teams; Labri (Bordeaux), L2S (Nice), OrangeLabs (Rennes). The objective of the project is to develop new solutions of scalable description for High Definition video content to facilitate their editing, their access via heterogeneous infrastructures (terminals, networks). The introduction of HDTV requires adaptations at different levels of the production and delivery chain. The access to the content for editing or delivery requires associating local or global spatio-temporal descriptors to the content. These descriptors must allow the collection of information related to actions, events or activities taking place in the video document and which can happen at different spatial and temporal resolutions. In this project, we aim at devising scalable descriptors that take motion explicitly into account, either on a time-localized basis (spatio-temporal interest points in particular), or on a longer-term basis (partial tracks on points or objects).

QUAERO

Participants : Ivan Laptev, Patrick Pérez.

no. Inria 3184, duration 60 months

Quaero is a European collaborative research and development program with the goal of developing multimedia and multi-lingual indexing and management tools for professional and public applications. The program has been approved by European Commission on 11 March 2008. The program is planed for five years and is supported by the French government through OSEO with a total budget of 200 millions Euro. Quaero consortium involves 24 academic and industrial partners leaded by Thomson. Vista participates in the Work Package 9 on Video Processing (WP9) of QUAERO Core Technology Cluster Project (CTC). Within WP9 Vista leads three tasks: Motion Recognition (Task 9.2), Object Tracking (Task 9.3) and Event Recognition (Task 9.4).

Other involvements


previous
next

Logo Inria