Authors:
Martina Monaci
1
;
Niccolò Pancino
2
;
1
;
Paolo Andreini
1
;
Simone Bonechi
1
;
Pietro Bongini
2
;
1
;
Alberto Rossi
2
;
1
;
Giorgio Ciano
2
;
1
;
Giorgia Giacomini
3
;
Franco Scarselli
1
and
Monica Bianchini
1
Affiliations:
1
University of Siena, Department of Information Engineering and Mathematics, via Roma 56, 53100, Siena (SI), Italy
;
2
University of Florence, Department of Information Engineering, via S. Marta 3, 50139, Florence (FI), Italy
;
3
University of Siena, Department of Biochemistry and Molecular Biology, via Aldo Moro 2, 53100, Siena (SI), Italy
Keyword(s):
Dragonfly, Machine Learning, Action Recognition, Deep Learning.
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 caref
ully 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.
(More)