ONERA's Personal Web Pages

Bertrand Le Saux

I am a researcher in computer vision and statistical learning working in the remote sensing domain at Onera, the French aerospace research centre. My current projects include:

Object detection and recognition

We are designing detectors of object of interest in images obtained from airborne sensors (UAV and planes), using a mix of geometric-template matching and learning-based classifiers (typically random forests). A typical use-case we investigate in the AZUR project is a search-and-rescue mission in an urban environment, which objectives like people and vehicle detection, obstacle avoidance and cartography.

Interactive learning

We are also working on developping methods for interactive and user-friendly design of classifiers and detectors, typically non-parametric methods like boosting and support-vector machines. The main application is online learning of patterns of interest in aerial and satellite images.

For students who are interested by this domains, I currently propose a Ph.D thesis subject : "Interactive co-learning of semantic classes for image and video interpretation" with Marin Ferecatu from CNAM Paris.

***

Older research topics and contexts include :

Tomography

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, Jiaping Wang and Alain Trouvé from the Applied Mathematics Lab of the ENS Cachan.

Image content recognition

My postdoctoral project was carried out at the University of Bern with Horst Bunke and the CNR di Pisa with Giuseppe Amato, 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.

Image and video indexing

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 visually similar images. I have developed an original algorithm for clustering : ARC (Adaptive Robust Competition).

if you're bored, email me. Or let's go to the beach.

Welcome to Onera, the French Aerospace Lab