Back to Search Start Over

Training Lightweight CNNs for Human-Nanodrone Proximity Interaction from Small Datasets using Background Randomization

Authors :
Ferri, Marco
Mantegazza, Dario
Cereda, Elia
Zimmerman, Nicky
Gambardella, Luca M.
Palossi, Daniele
Guzzi, Jérôme
Giusti, Alessandro
Publication Year :
2021

Abstract

We consider the task of visually estimating the pose of a human from images acquired by a nearby nano-drone; in this context, we propose a data augmentation approach based on synthetic background substitution to learn a lightweight CNN model from a small real-world training set. Experimental results on data from two different labs proves that the approach improves generalization to unseen environments.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2110.14491
Document Type :
Working Paper