The paper investigates how raw or minimally processed satellite imagery affects onboard AI object detection for space missions. By systematically degrading Very High Resolution Maxar images in terms of Signal‑to‑Noise Ratio, Modulation Transfer Function, and Ground Sampling Distance, the authors evaluate three lightweight detectors—YOLOv5s, YOLOX‑S, and NanoDet—on the resulting data. Results show that image quality impacts detection performance in a degradation‑specific way, with GSD consistently shifting performance, while MTF and SNR effects vary by model and resolution; severe blur‑plus‑noise combinations cause the greatest losses.
By Adrien Dorise, Marjorie Bellizzi, St\'ephane May
arXiv:2608.29852v1 Announce Type: new
Abstract: Automated maritime surveillance from satellite and aerial imagery requires large, precisely annotated datasets, which remain scarce for the instance-se...
By Amir Abbes, Ines Harrabi, Lucas Justin Yirepoa Kinda, Rim Trabelsi, Adnane Cabani, Fatma Abdelkefi
The paper introduces a pipeline that localizes frames from historical PTZ maritime video onto a reference panorama and uses context-aware sampling to build compact, scene‑specific training sets for ship detection. By enriching frames with weather and solar metadata and applying diversity sampling, the method reduces 40,718 candidate frames to just 220 for annotation, achieving a 99.5% reduction. Fine‑tuned YOLOv26‑m on this curated subset attains high detection performance (AP50 ≈ 94.8% and AP50‑95 ≈ 75.1%).
Vessel perception from space is crucial for a wide range of maritime applications, from traffic monitoring to environmental protection. However, most existing datasets predominantly focus on general o...
The paper introduces a pipeline that localizes frames from historical PTZ maritime video onto a reference panorama and then selects a context‑aware, diverse subset for ship detection training. By combining SuperPoint‑LightGlue localization, weather and solar‑state metadata, and diversity sampling, the method reduces 40,718 candidate frames to just 220 images for annotation. Fine‑tuned YOLOv26 on this compact set achieves high detection performance (AP50 ≈ 94.8%) while cutting annotation effort by 99.5%.
By Ignat Romanov, Andreas Hadjipieris, Neofytos Dimitriou
arXiv:2609.25500v1 Announce Type: new
Abstract: Training data quantity and quality greatly affect object detection model performance, regardless of model architecture. When using object detection mod...
By Lonny Lundsten, Kevin Barnard, Dave Caress