Deep Learning Techniques for Dragonfly Action Recognition

Martina Monaci, Niccolò Pancino, Niccolò Pancino, Paolo Andreini, Simone Bonechi, Pietro Bongini, Pietro Bongini, Alberto Rossi, Alberto Rossi, Giorgio Ciano, Giorgio Ciano, Giorgia Giacomini, Franco Scarselli, Monica Bianchini

2020

Abstract

Anisoptera are a suborder of insects belonging to the order of Odonata, commonly identified with the generic term dragonflies. They are characterized by a long and thin abdomen, two large eyes, and two pairs of transparent wings. Their ability to move the four wings independently allows dragonflies to fly forwards, backwards, to stop suddenly and to hover in mid–air, as well as to achieve high flight performance, with speed up to 50 km per hour. Thanks to these particular skills, many studies have been conducted on dragonflies, also using machine learning techniques. Some analyze the muscular movements of the flight to simulate dragonflies as accurately as possible, while others try to reproduce the neuronal mechanisms of hunting dragonflies. The lack of a consistent database and the difficulties in creating valid tools for such complex tasks have significantly limited the progress in the study of dragonflies. We provide two valuable results in this context: first, a dataset of carefully selected, pre–processed and labeled images, extracted from videos, has been released; then some deep neural network models, namely CNNs and LSTMs, have been trained to accurately distinguish the different phases of dragonfly flight, with very promising results.

Paper Citation

in Harvard Style

Monaci M., Pancino N., Andreini P., Bonechi S., Bongini P., Rossi A., Ciano G., Giacomini G., Scarselli F. and Bianchini M. (2020). Deep Learning Techniques for Dragonfly Action Recognition. In Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-397-1, pages 562-569. DOI: 10.5220/0009150105620569

in Bibtex Style

@conference{icpram20,
author={Martina Monaci and Niccolò Pancino and Paolo Andreini and Simone Bonechi and Pietro Bongini and Alberto Rossi and Giorgio Ciano and Giorgia Giacomini and Franco Scarselli and Monica Bianchini},
title={Deep Learning Techniques for Dragonfly Action Recognition},
booktitle={Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2020},
pages={562-569},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0009150105620569},
isbn={978-989-758-397-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Deep Learning Techniques for Dragonfly Action Recognition
SN - 978-989-758-397-1
AU - Monaci M.
AU - Pancino N.
AU - Andreini P.
AU - Bonechi S.
AU - Bongini P.
AU - Rossi A.
AU - Ciano G.
AU - Giacomini G.
AU - Scarselli F.
AU - Bianchini M.
PY - 2020
SP - 562
EP - 569
DO - 10.5220/0009150105620569