Haitham Mahmoud, Ibnu F. Kurniawan, Adel Aneiba, A. Taufiq Asyhari
A figure of 33,000 search and rescue (SAR) incidents were responded to by the UK’s HM Coastguard in 2020, and over 1322 rescue missions were conducted by SAR helicopters during that year. Combined with Unmanned Aerial Vehicles (UAVs), artificial intelligence, and computer vision, SAR operations can be revolutionized through enabling rescuers to expand ground coverage with improved detection accuracy whilst reducing costs and personal injury risks. However, detecting small objects is one of the significant challenges associated with using computer vision on UAVs. Several approaches have been proposed for improving small object detection, including data augmentation techniques like replication and variation of image sizes, but their suitability for SAR application characteristics remains questionable. To address these issues, this paper evaluates four float detection algorithms against the baseline and augmented datasets to improve float detection for maritime SAR. Results demonstrated that YOLOv8 and YOLOv5 outperformed the others in which F1 scores ranged from 82.9 to 95.3%, with an enhancement range of 0.1–29.2%. These models were both of low complexity and capable of real-time response. © The Author(s) 2024.
School of Computing and Digital Technology, Birmingham City University, Birmingham, B4 7XG, United Kingdom; Data Science Department, Monash University, Indonesia, Banten, Tangerang, 15345, Indonesia; Centre for Computational Science and Mathematical Modelling, Coventry University, Coventry, CV1 2TL, United Kingdom; Department of Data Science, Universitas Negeri Surabaya, Surabaya, 60231, Indonesia
