← Research

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

Marco Ferri (1), Dario Mantegazza (1), Elia Cereda (1), Nicky Zimmerman (1, 2), Luca M. Gambardella (1), Daniele Palossi (1, 3), J\'er\^ome Guzzi (1), Alessandro Giusti (1) ((1) Dalle Molle Institute for Artificial Intelligence (IDSIA), USI-SUPSI, Lugano, Switzerland, (2) University of Bonn, (3) Integrated Systems Laboratory (IIS), ETH Z\"urich, Switzerland)

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.

PDF ↗

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace