Cargando…
Drone vs. Bird Detection: Deep Learning Algorithms and Results from a Grand Challenge
Adopting effective techniques to automatically detect and identify small drones is a very compelling need for a number of different stakeholders in both the public and private sectors. This work presents three different original approaches that competed in a grand challenge on the “Drone vs. Bird” d...
Autores principales: | , , , , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8072977/ https://www.ncbi.nlm.nih.gov/pubmed/33923829 http://dx.doi.org/10.3390/s21082824 |
_version_ | 1783684027847278592 |
---|---|
author | Coluccia, Angelo Fascista, Alessio Schumann, Arne Sommer, Lars Dimou, Anastasios Zarpalas, Dimitrios Méndez, Miguel de la Iglesia, David González, Iago Mercier, Jean-Philippe Gagné, Guillaume Mitra, Arka Rajashekar, Shobha |
author_facet | Coluccia, Angelo Fascista, Alessio Schumann, Arne Sommer, Lars Dimou, Anastasios Zarpalas, Dimitrios Méndez, Miguel de la Iglesia, David González, Iago Mercier, Jean-Philippe Gagné, Guillaume Mitra, Arka Rajashekar, Shobha |
author_sort | Coluccia, Angelo |
collection | PubMed |
description | Adopting effective techniques to automatically detect and identify small drones is a very compelling need for a number of different stakeholders in both the public and private sectors. This work presents three different original approaches that competed in a grand challenge on the “Drone vs. Bird” detection problem. The goal is to detect one or more drones appearing at some time point in video sequences where birds and other distractor objects may be also present, together with motion in background or foreground. Algorithms should raise an alarm and provide a position estimate only when a drone is present, while not issuing alarms on birds, nor being confused by the rest of the scene. In particular, three original approaches based on different deep learning strategies are proposed and compared on a real-world dataset provided by a consortium of universities and research centers, under the 2020 edition of the Drone vs. Bird Detection Challenge. Results show that there is a range in difficulty among different test sequences, depending on the size and the shape visibility of the drone in the sequence, while sequences recorded by a moving camera and very distant drones are the most challenging ones. The performance comparison reveals that the different approaches perform somewhat complementary, in terms of correct detection rate, false alarm rate, and average precision. |
format | Online Article Text |
id | pubmed-8072977 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-80729772021-04-27 Drone vs. Bird Detection: Deep Learning Algorithms and Results from a Grand Challenge Coluccia, Angelo Fascista, Alessio Schumann, Arne Sommer, Lars Dimou, Anastasios Zarpalas, Dimitrios Méndez, Miguel de la Iglesia, David González, Iago Mercier, Jean-Philippe Gagné, Guillaume Mitra, Arka Rajashekar, Shobha Sensors (Basel) Article Adopting effective techniques to automatically detect and identify small drones is a very compelling need for a number of different stakeholders in both the public and private sectors. This work presents three different original approaches that competed in a grand challenge on the “Drone vs. Bird” detection problem. The goal is to detect one or more drones appearing at some time point in video sequences where birds and other distractor objects may be also present, together with motion in background or foreground. Algorithms should raise an alarm and provide a position estimate only when a drone is present, while not issuing alarms on birds, nor being confused by the rest of the scene. In particular, three original approaches based on different deep learning strategies are proposed and compared on a real-world dataset provided by a consortium of universities and research centers, under the 2020 edition of the Drone vs. Bird Detection Challenge. Results show that there is a range in difficulty among different test sequences, depending on the size and the shape visibility of the drone in the sequence, while sequences recorded by a moving camera and very distant drones are the most challenging ones. The performance comparison reveals that the different approaches perform somewhat complementary, in terms of correct detection rate, false alarm rate, and average precision. MDPI 2021-04-16 /pmc/articles/PMC8072977/ /pubmed/33923829 http://dx.doi.org/10.3390/s21082824 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Coluccia, Angelo Fascista, Alessio Schumann, Arne Sommer, Lars Dimou, Anastasios Zarpalas, Dimitrios Méndez, Miguel de la Iglesia, David González, Iago Mercier, Jean-Philippe Gagné, Guillaume Mitra, Arka Rajashekar, Shobha Drone vs. Bird Detection: Deep Learning Algorithms and Results from a Grand Challenge |
title | Drone vs. Bird Detection: Deep Learning Algorithms and Results from a Grand Challenge |
title_full | Drone vs. Bird Detection: Deep Learning Algorithms and Results from a Grand Challenge |
title_fullStr | Drone vs. Bird Detection: Deep Learning Algorithms and Results from a Grand Challenge |
title_full_unstemmed | Drone vs. Bird Detection: Deep Learning Algorithms and Results from a Grand Challenge |
title_short | Drone vs. Bird Detection: Deep Learning Algorithms and Results from a Grand Challenge |
title_sort | drone vs. bird detection: deep learning algorithms and results from a grand challenge |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8072977/ https://www.ncbi.nlm.nih.gov/pubmed/33923829 http://dx.doi.org/10.3390/s21082824 |
work_keys_str_mv | AT colucciaangelo dronevsbirddetectiondeeplearningalgorithmsandresultsfromagrandchallenge AT fascistaalessio dronevsbirddetectiondeeplearningalgorithmsandresultsfromagrandchallenge AT schumannarne dronevsbirddetectiondeeplearningalgorithmsandresultsfromagrandchallenge AT sommerlars dronevsbirddetectiondeeplearningalgorithmsandresultsfromagrandchallenge AT dimouanastasios dronevsbirddetectiondeeplearningalgorithmsandresultsfromagrandchallenge AT zarpalasdimitrios dronevsbirddetectiondeeplearningalgorithmsandresultsfromagrandchallenge AT mendezmiguel dronevsbirddetectiondeeplearningalgorithmsandresultsfromagrandchallenge AT delaiglesiadavid dronevsbirddetectiondeeplearningalgorithmsandresultsfromagrandchallenge AT gonzaleziago dronevsbirddetectiondeeplearningalgorithmsandresultsfromagrandchallenge AT mercierjeanphilippe dronevsbirddetectiondeeplearningalgorithmsandresultsfromagrandchallenge AT gagneguillaume dronevsbirddetectiondeeplearningalgorithmsandresultsfromagrandchallenge AT mitraarka dronevsbirddetectiondeeplearningalgorithmsandresultsfromagrandchallenge AT rajashekarshobha dronevsbirddetectiondeeplearningalgorithmsandresultsfromagrandchallenge |