Back to datasets
Dataset assetOpen Source CommunityRemote Sensing Image AnalysisObject Detection
SAR-Ship-Dataset
The dataset was annotated by SAR experts and consists of 102 GF‑3 (Gaofen‑3) satellite images and 108 Sentinel‑1 images, providing a total of 43,819 ship chips sized 256 × 256 pixels with varying scales and backgrounds. It can be used to develop object detectors for multi‑scale and small‑object detection.
Source
github
Created
Apr 29, 2019
Updated
Apr 29, 2019
Signals
278 views
Availability
Linked source ready
Overview
Dataset description and usage context
SAR‑Ship‑Dataset Overview
Dataset Composition
- Source Images: 102 Gaofen‑3 images and 108 Sentinel‑1 images.
- Data Volume: 43,819 ship chips, each 256 pixels (range and azimuth).
- Characteristics: Ships exhibit diverse scales and backgrounds, suitable for developing multi‑scale and small‑object detection models.
Citation Information
- Paper Title: "A SAR Dataset of Ship Detection for Deep Learning under Complex Backgrounds"
- Authors: Wang, Yuanyuan; Wang, Chao; Zhang, Hong; Dong, Yingbo; Wei, Sisi
- Year: 2019
- Journal: Remote Sensing
- Volume: 11
- Issue: 7
- Article Number: 765
- DOI: 10.3390/rs11070765
Need downstream help?
Pair the dataset with AI analysis and content workflows.
Once the source passes your review, move straight into summarization, transformation, report drafting, or presentation generation with the JuheAI toolchain.