Human detection in UAV-captured imagery for search and rescue operations: a aystematic review of deep learning and image processing methods
CEAS Aeronautical Journal · 29.10.2026
DOI: 10.1007/s13272-026-01033-2 ↗Kurz gefasst
Fachartikel in der Zeitschrift CEAS Aeronautical Journal, online erschienen am 29.10.2026. Verfasst von Thomas Oliver de Aquino und 4 weiteren Autor:innen. Die Arbeit nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Universidade Federal De Itajubá.
Abstract (Originalsprache)
The use of drones in search and rescue operations has become a widely adopted practice because of their availability and ability to capture a large, controlled area in a short amount of time. To increase the efficiency of detecting people using images captured by drones, various image processing techniques and deep learning methods have been utilized. This study aimed to identify and evaluate each of the machine learning methods discussed in recent research and provide insights into their applicability and effectiveness for human detection in diverse aerial scenarios. This study identified a paradigm shift towards end-to-end Convolutional Neural Networks (CNNs). The You Only Look Once (YOLO) architecture has emerged as the prevailing standard, optimally balancing real-time inference speed and detection accuracy, often achieving performances over 90% in precision and recall. While widespread operational deployment remains limited, recent documented successes of lightweight frameworks in active SAR missions demonstrate the life-saving potential of bridging the gap between theoretical deep learning models and practical emergency response.
Förderung
- Universidade Federal De Itajubá
Zitieren
APA
Aquino, T. O. D., Ramos, A. C. R., Mora-Camino, F., Olanrewaju, O. A., & Ramos, A. C. B. (2026). Human detection in UAV-captured imagery for search and rescue operations: a aystematic review of deep learning and image processing methods. CEAS Aeronautical Journal. https://doi.org/10.1007/s13272-026-01033-2
Vancouver
Aquino TOD, Ramos ACR, Mora-Camino F, Olanrewaju OA, Ramos ACB. Human detection in UAV-captured imagery for search and rescue operations: a aystematic review of deep learning and image processing methods. CEAS Aeronautical Journal. 2026. doi:10.1007/s13272-026-01033-2
BibTeX
@article{Aquino2026,
author = {Aquino, Thomas Oliver de and Ramos, Alexandre Carlos Rodrigues and Mora-Camino, Felix and Olanrewaju, Oludolapo Akanni and Ramos, Alexandre Carlos Brandão},
title = {Human detection in UAV-captured imagery for search and rescue operations: a aystematic review of deep learning and image processing methods},
journal = {CEAS Aeronautical Journal},
year = {2026},
doi = {10.1007/s13272-026-01033-2}
}
EUVIMED