Note
This is a Hugging Face dataset. Learn how to load datasets from the Hub in the Hugging Face integration docs.
Dataset Card for OpenSARWake#
OpenSARWake is a benchmark dataset built for ship wake detection. This collection provides 3,973 images containing two polarization modes and 4,096 instances. Most importantly, it encompasses SAR images in the L-, C-, and X-bands, which have not been provided by previous datasets. The images in the dataset have spatial resolutions of 1.25 m to 12.5 m. The image size is 1024× 1024 pixels.

This is a FiftyOne dataset with 2383 samples.
Installation#
If you haven’t already, install FiftyOne:
pip install -U fiftyone
Usage#
import fiftyone as fo
from fiftyone.utils.huggingface import load_from_hub
# Load the dataset
# Note: other available arguments include 'max_samples', etc
dataset = load_from_hub("dgural/OpenSARWake")
# Launch the App
session = fo.launch_app(dataset)
Dataset Details#
Dataset Sources#
Repository: https://github.com/libzzluo/OpenSARWake?tab=readme-ov-file
Dataset Structure#
The dataset includes ground_truth field as well as clip embeddings for visualization
Source Data#
Who are the source data producers?#
Xu, Chengji and Wang, Xiaoqing
Citation [optional]#
@ARTICLE{10507047, author={Xu, Chengji and Wang, Xiaoqing}, journal={IEEE Geoscience and Remote Sensing Letters}, title={OpenSARWake: A Large-Scale SAR Dataset for Ship Wake Recognition with a Feature Refinement Oriented Detector}, year={2024}, doi={10.1109/LGRS.2024.3392681}}