Predicting seafloor visual classes from multimodal remote sensed priors using location-guided self-supervised Learning

Liang, Cailei; Cappelletto, Jose; Bodenmann, Adrian; Turnock, Stephen; Thornton, Blair; Huvenne, Veerle A. I. ORCID: https://orcid.org/0000-0001-7135-6360; Wardell, Catherine. 2025 Predicting seafloor visual classes from multimodal remote sensed priors using location-guided self-supervised Learning. In: 2024 IEEE/OES Autonomous Underwater Vehicles Symposium (AUV), Boston, MA, USA, 18 - 20 September 2024. IEEE, 1-6.

Full text not available from this repository.

Abstract/Summary

Remote sensed mapping data and seafloor in-situ imagery are often gathered to infer benthic habitat distributions. However, leveraging multimodal data is challenging because of inherent inconsistencies between measurement modes (e.g., resolution, positional offsets, shape discrepancies). We investigate the impact of using location metadata in multimodal, self-supervised feature learning on habitat classification. Experiments were carried out on a multimodal dataset gathered using and Autonomous Underwater Vehicle (AUV) at the Darwin Mounds Marine Protected Area (MPA). Introducing location metadata improved F1 classification performance of a Bayesian classifier by an average of 27.7% over all conditions tested in this work, with a larger improvement of 32.9% achieved when multiple remote sensing data modes are combined for the analysis.

Item Type:	Publication - Conference Item (Paper)
Digital Object Identifier (DOI):	10.1109/AUV61864.2024.11030795
ISBN:	979-8-3315-4223-8
Additional Keywords:	multimodal feature learning, seafloor habitat classification, self-supervised learning, inference
NORA Subject Terms:	Marine Sciences
Date made live:	28 Jul 2025 13:05 +0 (UTC)
URI:	https://nora.nerc.ac.uk/id/eprint/539953

Actions (login required)

View Item

Document Downloads

More statistics for this item...