Data Dimension Reduction for Visual Analytics: A Case Study of Oil-in-Water Detection

Our Harsh and Fragile Ocean: OCEANS ’17 MTS/IEEE Anchorage 2017
Ottar Laurits Osen, Anete Vagale, Hao Wang, Karina B. Hjelmervik, Halvor Schøyen

Many different sensors have been installed on board vessels, a new framework is urgently needed to form a Common Operational Picture (COP), to assist the on-board operations and onshore analysis. In this paper, based on the Visual Analytics framework, we present a spatiotemporal dimension reduction method based on a real world case of oil combat operation. With our prototype, we show that how dimension reduction of spatiotemporal data will improve visualisation and ease analysis.

Keywords
Big data, LiDAR
Hyperlink
https://ieeexplore.ieee.org/document/8232294/

Osen, O., Vagale, A., Wang, H., Hjelmervik, K., Schøyen, H. Data Dimension Reduction for Visual Analytics: A Case Study of Oil-in-Water Detection. In: Our Harsh and Fragile Ocean: OCEANS ’17 MTS/IEEE Anchorage, United States of America, Anchorage, 18-21 September, 2017. Piscataway: IEEE, 2017, pp.1-8. ISBN 978-1-5090-6429-8. e-ISBN 978-0-6929-4690-9.

Publication language
English (en)