Uniri-Seastate-LL and Uniri-SeaState-R

The UNIRI-SeaState-R and UNIRI-SeaState-LL datasets contains visual-range sea surface images labelled according to eight sea state categories (classes 1–8), corresponding to sea states defined by the Beaufort wind force scale. Both datasets contain cropped 331 x 331 pixel portions of the original 3840 x 2160 frames captured from a camera mounted on the left bridge wing of a large ocean-going ship extracted in the following way: UNIRI-SeaState-R: random position to the left of the ship's hull. UNIRI-SeaState-L: bottom-left part of the frame. These datasets accompany the following publication: Vorkapic, A., Pobar, M., & Ivasic-Kos, M. (2024). A computer vision approach to estimate the localized sea state. Ocean engineering, 309, 118318. DOI: https://doi.org/10.1016/j.oceaneng.2024.118318