bertrand.le_saux(a)onera.fr / http://www.onera.fr/en/staff/bertrand-le-saux
I am a researcher in computer science working at the Onera, in the fields of computer vision, image analysis and statistical learning. Current projects include:
We are designing detectors of object of interest in images obtained from airborne sensors (UAV and planes). These detectors are based on geometric-template matching and random-forest classifiers.
We are also working on developping methods for online learning of zones of interest in aerial and satellite images. We model the user query in several steps through a relevance feedback loop. The training and classification phase relies on non-parametric active learning methods like boosting.
Here are some facts and dates. There you can get my papers.
In the past, I was also interested in the following topics:
I worked on 3D reconstruction in tomographic imaging. We used bayesian inference, data fusion and deconvolution to produce 3D volumic images of non adherent living cells. This work was achieved in the Automation project, with Bernard Chalmond and Jiaping Wang from the Applied Mathematics Lab of the ENS Cachan.
My postdoctoral project was carried out at the University of Bern and CNR di Pisa, as a member of the ERCIM fellowship program. I have designed predictors that can learn how to recognize scenes, like particular landscapes, sport pictures, images with people. Techniques include feature selection, kernel methods, graph matching and bayesian combination of classifiers. This is used to generate automatic annotation of multimedia documents and improve search facilities in digital libraries.
I did my PhD at INRIA/Imedia research group, which is interested on content-based image retrieval. I worked on techniques of supervised and unsupervised classification to find and manage categories of similar images. I have developed an original algorithm for clustering : ARC (Adaptive Robust Competition). Besides my work at INRIA, I was a teaching assistant in University Paris-IX Dauphine and some old material for a java course is still available.
Some shortcuts for my works:
publications and talks
classifiers for image annotation
unsupervised classification for image database
motion estimation in video sequences
Recently, I have been serving on the program committee of these conferences:
Visual 2008
Visual 2007
Pacific-Rim Conference on Multimedia 2007
Here is a howto with links to install unix stuff on mac os x, the updated version for os x tiger, and another one about network setup between linux and mac os x. If you're bored, email me. Or let's go to the beach.