Olivier Chomat

Learn More
This paper presents a technique for the analysis and recognition of body motion using local appearance. A set of spatio-temporal lters are determined by principal component analysis of the contents of spatio-temporal neighborhoods from a set of image sequences. A few principal components deene the basis for an orthogonal space for describing the appearance(More)
In this paper we describe an augmented reality tool for collaborative work called the MagicBoard. The MagicBoard is based on a ordinary white board which has been enhanced by a video projector and a steerable camera. A supervisor coordinates the cooperation of several modules including gesture recognition, nger tracking and white board scanning for(More)
This paper addresses the problem of the local scale parameter selection for recognition techniques based on Gaussian derivatives. Patterns are represented in a local appearance subspace or feature space of which each dimension is a receptive elds (a unit composed of Gaussian derivatives). A scale equivariant feature space is obtained using an automatic(More)
This paper addresses the problem of the local scale parameter selection for recognition techniques based on Gaussian derivatives. Patterns are represented in a local subspace or feature space of which each dimension is a scale normalized receptive eld (a unit composed of normalized Gaussian derivativessLin98]). Data are structurally represented in a feature(More)
  • 1