New open dataset OSSDD released for Sentinel-1 ship detection

Researchers have introduced OSSDD, a new open dataset designed for training neural networks to detect ships in Synthetic Aperture Radar (SAR) images. This dataset, built upon the OpenSARShip 1.0 dataset, provides 15,197 Sentinel-1 amplitude patches with detailed annotations for over 55,000 ships. OSSDD includes binary ship masks, axis-aligned bounding boxes, and rotated bounding boxes, aiming to serve as a benchmark for future SAR ship detection experiments. The dataset is accessible on Hugging Face. AI

IMPACT Provides a new benchmark dataset to advance research in SAR ship detection using neural networks.

RANK_REASON The item describes a new open dataset for a specific computer vision task, including details about its contents and experimental results. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• DEtection TRansformer
• Faster R-CNN
• FCOS
• Hugging Face
• OpenSARShip 1.0
• OSSDD
• Sentinel-1
• Sylvia Hochstuhl

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →