A virtual testbed for maritime search and rescue: Customizing YOLO for small object detection in unreal engine

• Demonstrates the effectiveness of drone technology for maritime search and rescue using a virtual testbed and custom object detection models. • Uses drone simulations with robust detection algorithms to evaluate and validate deployment strategies prior to real-world implementation. • Achieves 94.6 % mAP 50 with the enhanced YOLOv12s model through targeted dataset balancing and architectural improvements. • Identifies enhanced YOLOv12n as the optimal model for drone deployment, achieving 92.3 % mAP 50 at 31.2 FPS on Jetson Nano NX. • Develops a photo-realistic virtual testbed in Unreal Engine 4.2 with Cesium for mission planning and synthetic data generation. Maritime Search and Rescue (SAR) operations face three main issues: they are time-critical, rescue boat access is often difficult, and the vastness of the ocean poses a great challenge to identifying drowning victims. Rescue operations in situations such as a shipwreck or when enthusiasts drown due to rip currents at seashores are largely unsuccessful due to an over-reliance on manual methods. The need for faster, semi-automated methods thus becomes important. This paper aims to introduce drones as agents for rapid detection and rescue in such scenarios. This study introduces a virtual simulation testbed, created in Unreal Engine (UE) 4.2 for maritime SAR scenarios. With the integration of the Cesium plug-in, the simulation platform provides a photo-realistic representation of the Earth’s surface, making it valuable for planning search and rescue (SAR) missions. Beyond simulation, the testbed offers the potential to generate large volumes of custom synthetic data, thereby supporting future research toward safer maritime transportation. This study introduces an object detection framework tailored for maritime SAR scenarios, employing selected models from the YOLOv11 and YOLOv12 series trained on domain-relevant classes. A systematic training approach was followed, combining dataset balancing strategies with targeted architecture modifications. These efforts led to a 38.7% improvement in the mAP 50 metric compared to the baseline YOLOv12s model, with the enhanced YOLOv12s achieving 94.6% mAP 50 . Further evaluation on three edge devices demonstrated the Jetson Nano NX as the most suitable platform for deployment. Among the tested models, the enhanced YOLOv12n emerged as the optimal choice for drone-based applications, delivering 92.3% mAP 50 at 31.2 FPS on the Jetson Nano NX, thereby achieving an effective balance between accuracy and real-time performance.