Training Lightweight CNNs for Human-Nanodrone Proximity Interaction from Small Datasets using Background Randomization
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...
Gespeichert in:
Hauptverfasser: | , , , , , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | 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. |
---|---|
DOI: | 10.48550/arxiv.2110.14491 |