FlightScope: An Experimental Comparative Review of Aircraft Detection Algorithms in Satellite Imagery

Object detection in remotely sensed satellite pictures is fundamental in many fields such as biophysical and environmental monitoring. While deep learning algorithms are constantly evolving, they have been mostly implemented and tested on popular ground-taken photos. This paper critically evaluates...

Full description

Saved in:
Bibliographic Details
Main Authors: Safouane El Ghazouali, Arnaud Gucciardi, Francesca Venturini, Nicola Venturi, Michael Rueegsegger, Umberto Michelucci
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/16/24/4715
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846102843239432192
author Safouane El Ghazouali
Arnaud Gucciardi
Francesca Venturini
Nicola Venturi
Michael Rueegsegger
Umberto Michelucci
author_facet Safouane El Ghazouali
Arnaud Gucciardi
Francesca Venturini
Nicola Venturi
Michael Rueegsegger
Umberto Michelucci
author_sort Safouane El Ghazouali
collection DOAJ
description Object detection in remotely sensed satellite pictures is fundamental in many fields such as biophysical and environmental monitoring. While deep learning algorithms are constantly evolving, they have been mostly implemented and tested on popular ground-taken photos. This paper critically evaluates and compares a suite of advanced object detection algorithms customized for the task of identifying aircraft within satellite imagery. The goal is to enable researchers to choose efficiently from algorithms that are trainable and usable in real time on a deep learning infrastructure with moderate requirements. Using the large HRPlanesV2 dataset, together with rigorous validation with the GDIT dataset, this research encompasses an array of methodologies including YOLO versions 5, 8, and 10, Faster RCNN, CenterNet, RetinaNet, RTMDet, DETR, and grounding DINO, all trained from scratch. This exhaustive training and validation study reveals YOLOv5 as the pre-eminent model for the specific case of identifying airplanes from remote sensing data, showcasing high precision and adaptability across diverse imaging conditions. This research highlights the nuanced performance landscapes of these algorithms, with YOLOv5 emerging as a robust solution for aerial object detection, underlining its importance through superior mean average precision, recall, and intersection over union scores. The findings described here underscore the fundamental role of algorithm selection aligned with the specific demands of satellite imagery analysis and extend a comprehensive framework to evaluate model efficacy. This aims to foster exploration and innovation in the realm of remote sensing object detection, paving the way for improved satellite imagery applications.
format Article
id doaj-art-3bff3e49985541df95a849fcc8532e48
institution Kabale University
issn 2072-4292
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-3bff3e49985541df95a849fcc8532e482024-12-27T14:50:58ZengMDPI AGRemote Sensing2072-42922024-12-011624471510.3390/rs16244715FlightScope: An Experimental Comparative Review of Aircraft Detection Algorithms in Satellite ImagerySafouane El Ghazouali0Arnaud Gucciardi1Francesca Venturini2Nicola Venturi3Michael Rueegsegger4Umberto Michelucci5TOELT LLC, Research and Development, 8600 Dübendorf, SwitzerlandTOELT LLC, Research and Development, 8600 Dübendorf, SwitzerlandTOELT LLC, Research and Development, 8600 Dübendorf, SwitzerlandCompetence Center for Artificial Intelligence and Simulation, Armasuisse S+T, Feuerwerkerstrasse 39, 3602 Thun, SwitzerlandCompetence Center for Artificial Intelligence and Simulation, Armasuisse S+T, Feuerwerkerstrasse 39, 3602 Thun, SwitzerlandTOELT LLC, Research and Development, 8600 Dübendorf, SwitzerlandObject detection in remotely sensed satellite pictures is fundamental in many fields such as biophysical and environmental monitoring. While deep learning algorithms are constantly evolving, they have been mostly implemented and tested on popular ground-taken photos. This paper critically evaluates and compares a suite of advanced object detection algorithms customized for the task of identifying aircraft within satellite imagery. The goal is to enable researchers to choose efficiently from algorithms that are trainable and usable in real time on a deep learning infrastructure with moderate requirements. Using the large HRPlanesV2 dataset, together with rigorous validation with the GDIT dataset, this research encompasses an array of methodologies including YOLO versions 5, 8, and 10, Faster RCNN, CenterNet, RetinaNet, RTMDet, DETR, and grounding DINO, all trained from scratch. This exhaustive training and validation study reveals YOLOv5 as the pre-eminent model for the specific case of identifying airplanes from remote sensing data, showcasing high precision and adaptability across diverse imaging conditions. This research highlights the nuanced performance landscapes of these algorithms, with YOLOv5 emerging as a robust solution for aerial object detection, underlining its importance through superior mean average precision, recall, and intersection over union scores. The findings described here underscore the fundamental role of algorithm selection aligned with the specific demands of satellite imagery analysis and extend a comprehensive framework to evaluate model efficacy. This aims to foster exploration and innovation in the realm of remote sensing object detection, paving the way for improved satellite imagery applications.https://www.mdpi.com/2072-4292/16/24/4715object detectionsurveyremote sensingsatellite imageaircraftlocalization
spellingShingle Safouane El Ghazouali
Arnaud Gucciardi
Francesca Venturini
Nicola Venturi
Michael Rueegsegger
Umberto Michelucci
FlightScope: An Experimental Comparative Review of Aircraft Detection Algorithms in Satellite Imagery
Remote Sensing
object detection
survey
remote sensing
satellite image
aircraft
localization
title FlightScope: An Experimental Comparative Review of Aircraft Detection Algorithms in Satellite Imagery
title_full FlightScope: An Experimental Comparative Review of Aircraft Detection Algorithms in Satellite Imagery
title_fullStr FlightScope: An Experimental Comparative Review of Aircraft Detection Algorithms in Satellite Imagery
title_full_unstemmed FlightScope: An Experimental Comparative Review of Aircraft Detection Algorithms in Satellite Imagery
title_short FlightScope: An Experimental Comparative Review of Aircraft Detection Algorithms in Satellite Imagery
title_sort flightscope an experimental comparative review of aircraft detection algorithms in satellite imagery
topic object detection
survey
remote sensing
satellite image
aircraft
localization
url https://www.mdpi.com/2072-4292/16/24/4715
work_keys_str_mv AT safouaneelghazouali flightscopeanexperimentalcomparativereviewofaircraftdetectionalgorithmsinsatelliteimagery
AT arnaudgucciardi flightscopeanexperimentalcomparativereviewofaircraftdetectionalgorithmsinsatelliteimagery
AT francescaventurini flightscopeanexperimentalcomparativereviewofaircraftdetectionalgorithmsinsatelliteimagery
AT nicolaventuri flightscopeanexperimentalcomparativereviewofaircraftdetectionalgorithmsinsatelliteimagery
AT michaelrueegsegger flightscopeanexperimentalcomparativereviewofaircraftdetectionalgorithmsinsatelliteimagery
AT umbertomichelucci flightscopeanexperimentalcomparativereviewofaircraftdetectionalgorithmsinsatelliteimagery