Consulter le flux RSS

Publications

Affichage des publications 1541 à 1550 sur 3838 au total

Machine Learning

Active learning for high-density crowd count regression

Efficient crowd counting is an essential task in crowd monitoring, and significant advances have been made in this field recently by counting-by-regression techniques. We propose in this work a learning-to-count strategy with a generic detection…

Jennifer Vandoni, Emanuel Aldea, Sylvie Le Hégarat-Mascle

2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) -

Electronics

Trade-off between Losses and EMI Issues in Three-Phase SiC Inverters for Aircraft Applications

Power converters will only be effectively used in future aircrafts if they are compact, efficient and reliable. All these aspects can be improved by the use of disruptive technology such as the so-called Wide Bandgap (WBG) semiconductors made of…

Victor dos Santos, Bernardo Cougo, Nicolas Roux, Bruno Sareni, Bertrand Revol, Jean-Pierre Carayon

EMC 2017 (Electromagnetic Compatibility, Signal and Power Integrity) -

Materials

Influence of ns-laser wavelength in laser-induced breakdown spectroscopy for discrimination of painting techniques

The influence of ns-laser wavelength to discriminate ancient painting techniques such as are fresco, casein, animal glue, egg yolk and oil was investigated in this work. This study was carried out with a single shot laser on samples covered by a…

Xueshi Bai, Delphine Syvilay, Nicolas Wilkie-Chancellier, Annick Texier, Loïc Martinez, Stéphane Serfaty, Dominique Martos-Levif, Vincent Detalle

Spectrochimica Acta Part B: Atomic Spectroscopy -

Analytical chemistry

The behaviour of molecular-plasmonic assemblies in solution

he bottom-up approach for making functional nanostructures via self-assembly in solution leads to objects that are usually represented pictorially using idealised models. These models are then validated against experimental observations (microscopy,…

Martinus H. V. Werts

Molecular Plasmonics 2017 -

Signal and Image processing

Evidential multi-class classification from binary classifiers: application to waste sorting quality control from hyperspectral data

Our application deals with waste sorting using an automatic system involving a hyperspectral camera. This latter provides the data for classification of the different kinds of waste allowing the evaluation of mechanical pre-sorting and its…

Marie Lachaize, Sylvie Le Hégarat-Mascle, Emanuel Aldea, Aude Maitrot, Roger Reynaud

The International Conference on Quality Control by Artificial Vision 2017 -