Computer vision

Keywords: shape estimation, point clouds.

Abstract: computer vision field is mainly motivated by linear or quasi-linear approaches of image processing, for example for shape estimation from image sequences. But it also need to introduce original point cloud or mesh processing to extract geometric properties.

I was a permanent member of the ALCoV team, ISIT, Université d'Auvergne. ALCoV's scientific project was bringing new tools for surgical gesture training and decision making using computer vision and augmented reality. I am interested methods to enrich the per-operative tools (computer-vision based approaches), by integrating data from pre-operative images.

I was during two months (July-September 2009): visitor at Department of Computer Science, Queen Mary, University of London, joining the Lourdes Agapito's team. We worked on distortion shape estimation from point clouds describing a manifold.

  • P. Schroeder, R. Roux, J.-M. Favreau, A. Bartoli Industrial Phase-Shifting Profilometry in Motion. In 18th Scandinavian Conference on Image Analysis, SCIA 2013. Springer. (2013). bibtex
  • J.-M. Favreau, J. Fayad, L. Agapito Distortion estimation for point clouds and application to motion analysis. In 3DPVT'10 Intl Symp. on 3D Data Processing, Visualization and Transmission. Paris, France (05/2010). bibtex