FGSD: A Dataset for Fine-Grained Ship Detection in High Resolution Satellite Images

TL;DR

The paper introduces FGSD, a comprehensive high-resolution satellite image dataset for fine-grained ship detection, including detailed annotations, orientation data, and additional contextual information to advance research in maritime surveillance.

Contribution

It presents FGSD, a new dataset with precise ship classification, orientation annotations, and dock class, filling gaps in existing datasets for ship detection research.

Findings

FGSD is the most comprehensive ship detection dataset to date.

Provides detailed annotations including orientation and dock class.

Baseline results demonstrate the dataset's utility for future research.

Abstract

Ship detection using high-resolution remote sensing images is an important task, which contribute to sea surface regulation. The complex background and special visual angle make ship detection relies in high quality datasets to a certain extent. However, there is few works on giving both precise classification and accurate location of ships in existing ship detection datasets. To further promote the research of ship detection, we introduced a new fine-grained ship detection datasets, which is named as FGSD. The dataset collects high-resolution remote sensing images that containing ship samples from multiple large ports around the world. Ship samples were fine categorized and annotated with both horizontal and rotating bounding boxes. To further detailed the information of the dataset, we put forward a new representation method of ships' orientation. For future research, the dock as a new class was annotated in the dataset. Besides, rich information of images were provided in FGSD, including the source port, resolution and corresponding GoogleEarth' s resolution level of each image. As far as we know, FGSD is the most comprehensive ship detection dataset currently and it'll be available soon. Some baselines for FGSD are also provided in this paper.