Abstract Hyperspectral imaging is an emerging technology that has gained significant attention in the medical field due to its ability provide precise and accurate of biological tissues. The current methods hyperspectral imaging, such as filter-wheel, snapshot, line-scanning, push-broom cameras have limitations low spatial spectral resolution, slow acquisition time. New developments on light sh...

Three line stereo scanners working in push-broom mode are of high interest for future remote sensing camera developments. This contribution deals with some basic considerations concerning the geometric, spectral, and radiometric design of such a camera. These considerations are applied to the design of the Wide-Angle Optoelectronic Stereo Scanner WAOSS for the Russian mission Mars-96 (Bild&Ton,...

The study of sign languages provides a wide field of applications for computer vision systems, but the analysis of such gestures often leads to complex 3D reconstructions or to ambiguities. In this paper, we describe the architecture of an image analysis system that performs sign language analysis by using a prediction/verification approach. The system integrates a model of the sign language’s ...

The recognition of people orientation in single images is still an open issue in several real cases, when the image resolution is poor, body parts cannot be distinguished and localized or motion cannot be exploited. However, the estimation of a person orientation, even an approximated one, could be very useful to improve people tracking and re-identification systems, or to provide a coarse alig...

The implementation of a Structure-from-Motion (SfM) pipeline from a synthetically generated scene as well as the investigation of the faithfulness of diverse reconstructions is the subject of this project. A series of different SfM reconstructions are implemented and their camera pose estimations are being contrasted with their respective ground truth locations. Finally, injection of ground tru...

We demonstrate how the problem of speaker diarization can be solved using both gesture and speaker parametric models. The novelty of our solution is that we approach the speaker diarization problem as a speaker recognition problem after learning speaker models from speech samples corresponding to gestures (the occurrence of gestures indicates the presence of speech and the location of gestures ...