ShipSG: Ship Segmentation and Georeferencing Dataset

The ShipSG dataset [1] is the first public dataset of its kind for ship segmentation and georeferencing. The dataset has been made available for the development and evaluation of instance segmentation and georeferencing methods using computer vision and deep learning, thus advancing the research field of ship recognition for maritime situational awareness. ShipSG consists of 3505 images of a port location using two different cameras with static and oblique view. In total, 11625 ship masks grouped in seven ship classes were manually annotated. Moreover, each image contains one geographic annotation of one of the ship masks (latitude and longitude) present in the image.
 

ShipSG dataset samples with annotated ship masks
Figure 1: ShipSG dataset samples with annotated ship masks

ShipSG can be accessed through the contact person named below. A further description of the dataset and our methodologies for ship segmentation and georeferencing can be found in [1].
Please refer to [1] for the citation of the dataset.
 

Citation:
[1] Carrillo-Perez, B.; Barnes, S.; Stephan, M. Ship Segmentation and Georeferencing from Static Oblique View Images. Sensors 2022, 22, 2713. https://doi.org/10.3390/s22072713