Martial Sanfourche

Learn More
We present a robust method for vehicle categorization in aerial images. This approach relies on a multiple-classifier system that merges the answers of classifiers applied at various camera angle incidences. The single classifiers are built by matching 3D-templates to the vehicle silhouettes with a local projection model that is compatible with the(More)
We address DSM reconstruction from calibrated limited-angle aerial side-looking image sequences. We use a regularised approach which combines a multi-view pixel-wise similarity criterion and a L1-norm regularisation term. Although it gives quite good results, it has two main drawbacks: occlusions are not dealt with and the reconstruction improvement brought(More)
This paper focuses on applications of fuzzy segmentation in region indexing and image retrieval. First, our algorithm of fuzzy segmentation is shortly explained. Some features characterizing a fuzzy region are then defined, and a distance between fuzzy regions is proposed. This distance can be used to rank regions on color and/or shape features or to(More)
The navigation of a miniature aerial vehicle (MAV) in GPS-denied environments requires a robust embedded visual localization method. In this paper, we describe a simple but efficient stereo visual odometry algorithm, called eVO, running onboard our quadricopter MAV at video-rate. The proposed eVO algorithm relies on a keyframe scheme which allows to(More)
This paper outlines an autonomous flight system developed onboard the ONERA ReSSAC unmanned helicopter for an air-to-ground target tracking mission in an unkown urban environment. The system consists of the following three components: i) an image processor which detects the target and estimates ground motion around the detected target position, ii) an(More)
We propose solutions to provide unmanned aerial vehicles (UAV) with features to understand the scene below and help the operational planning. First, using a visual mapping of the environnement, interactive learning of specific targets of interest is performed on the ground control station to build semantic maps useful for planning. Then, the learned target(More)
This paper outlines a UAV onboard vision-based system for simultaneous navigation and tracking of a moving ground target in a GPS-denied environment. The system consists of i) an image processor which detects the target and estimates the apparent motion of the groud surface, ii) a navigation filter which localizes both the own-ship UAV and the target by(More)