Sea Situational Awareness (SeaSAW) Dataset

Parneet Kaur, Arslan Aziz, Darshan Jain, Harshil Patel, Jonathan Hirokawa, Lachlan Townsend, Christoph Reimers, Fiona Hua; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2022, pp. 2579-2587

Abstract


The oceans provide 90% global trade by vessels. Situational awareness from intelligent vessel systems can enable enhanced safety and decision-making for mariners. As the foundation for these intelligent systems, advanced perception technology requires sufficient real-world operational data to leverage recent AI technologies. In this work, we introduce the Sea Situational Awareness (SeaSAW) dataset - a novel dataset that comprises 1.9 million images with 14.6 million objects associated 20.4 million attributes from 12 object classes, making it the largest maritime dataset for object detection, fine-grained classification and tracking. Furthermore, this dataset consists 9 sources in combination with various RGB cameras mounted on different moving vessels operating in different geographic locations globally, having variations in scenario, weather and illumination conditions. This work assembles the data collected across 4 years with rigorous efforts on data selection, annotation, management and analysis to enhance the marine perception technology.

Related Material


[pdf]
[bibtex]
@InProceedings{Kaur_2022_CVPR, author = {Kaur, Parneet and Aziz, Arslan and Jain, Darshan and Patel, Harshil and Hirokawa, Jonathan and Townsend, Lachlan and Reimers, Christoph and Hua, Fiona}, title = {Sea Situational Awareness (SeaSAW) Dataset}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {2579-2587} }