Michael Benjamin Rüegsegger

Dr. Michael Benjamin Rüegsegger


Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 December 2024 in Remote Sensing
Verified
Journal Article
Open access
PDF file
SGSafouane El Ghazouali
Safouane El Ghazouali
AGArnaud Gucciardi
Arnaud Gucciardi
Francesca VenturiniFrancesca Venturini
Francesca Venturini
NVNicola Venturi
Nicola Venturi
MRMichael Benjamin Rüegsegger
Michael Benjamin Rüegsegger
Umberto MichelucciUmberto Michelucci
Umberto Michelucci
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.