English

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

Computer Vision and Pattern Recognition 2021-10-28 v1 Artificial Intelligence Robotics Machine Learning

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.

Keywords

Cite

@article{arxiv.2110.14491,
  title  = {Training Lightweight CNNs for Human-Nanodrone Proximity Interaction from Small Datasets using Background Randomization},
  author = {Marco Ferri and Dario Mantegazza and Elia Cereda and Nicky Zimmerman and Luca M. Gambardella and Daniele Palossi and Jérôme Guzzi and Alessandro Giusti},
  journal= {arXiv preprint arXiv:2110.14491},
  year   = {2021}
}
R2 v1 2026-06-24T07:14:11.732Z