Skip to main content
Go to the home page of the European Commission (opens in new window)
English en
CORDIS - EU research results
CORDIS
Content archived on 2024-05-14

3d statistical and physics-based deformable models for image sequence analysis

Objective



Moving deformable structures are now key phenomena in a growing number applications (bio-medical imagery, human motion analysis, fluid mecanics, crash tests, etc). Extracting, interpreting and visualizing qualitative and/or quantitative information on moving deformable structures (from image sequences) requires a deep understanding of the complex interactions between motion, distortion, and imaging process.
The objective of this research (which will be pursued in candidacy for french PhD degree) is to develop a comprehensive model-based framework for: - the representation of 3D+t (spatio-temporal) deformable structures - the segmentation of these structures in image sequences - the tracking of 3D deformable structures over long image sequences - the interpretation of deformable motion, within an application in medical imagery (Magnetic Resonance Imagery).
To this end, statistical and physics-based models will be considered, with a special emphasis on statistical approaches. Statistical model identification techniques, bayesian model-based image segmentation, recursive temporal filtering and statistical-based interpretation methods will be investigated.
This project will be conducted at Louis-Pasteur University of Strasbour (Ecole Nationale Superieure de Physique de Strasbourg) in collaboration with IPB ("Institut de Physique Biologique", URA CNRS 1173), Strasbourg Hospital (extraction of moving organs from MRI images).

Fields of science (EuroSciVoc)

Programme(s)

Topic(s)

Call for proposal

Data not available

Funding Scheme

RGI - Research grants (individual fellowships)

Coordinator

UNIVERSITE LOUIS PASTEUR, STRASBOURG 1
EU contribution
No data
Address
Pole API - Boulevard Sebastien Brant
67400 ILLKIRCH GRAFFENSTADEN
France
Total cost
No data

Participants (1)