Super-Resolution YOLO Object Detection for Maritime Surveillance with Real-Time FPGA Processing Onboard Spacecraft

Accurate vessel detection and timely information extraction from optical remote sensing imagery are essential for a wide range of maritime surveillance operations, both civilian and defense-related. These include vessel tracking, unauthorized fishing, illegal migration monitoring, and search and rescue missions. Although artificial intelligence (AI) is a key component for achieving reliable and accurate detection in satellite imagery, traditional AI-based remote sensing methodologies rely on ground-based image processing. This dependence leads to significant delays between data acquisition and the generation of actionable insights, which may hinder rapid decision-making during critical maritime situations such as sea disasters. To address this challenge, we propose a novel hardware design based on the Microchip PolarFire System-on-Chip for low-power, real-time vessel detection onboard spacecraft. Our design integrates the FPGA-based CoreVectorBlox engine to accelerate the inference process of SR-YOLOv5s—an enhanced object detection framework built upon YOLOv5s. This detector incorporates a single image super-resolution backbone that allows the extraction of fine details and features of small targets of interest, thus improving detection performance. Experimental results demonstrate that SR-YOLOv5s consistently outperforms the baseline YOLOv5s framework in vessel detection. The model provides high accuracy in detecting very small targets (area ≤7×7 pixels), achieving a mAP50 of 0.4658 compared to 0.2832—an absolute improvement of 18.26 percentage points. When deployed on the PolarFire FPGA, the end-to-end pipeline sustains real-time operation with an inference latency of 55 ms per frame and an average dynamic power consumption below 1.2 W. These results confirm the suitability of our approach for power-constrained onboard processing and demonstrate its effectiveness as a solution for low-latency alert generation in maritime surveillance through edge-based analysis of Earth observation imagery.