3D Fine-scale terrain variables from underwater photogrammetry: a new approach to benthic microhabitat modeling in a circalittoral rocky shelf

• Published in: Remote Sensing
• Main Authors: Prado Ortega, Elena, Rodríguez Basalo, Augusto, Cobo García, Adolfo, Ríos López, María Pilar, Sánchez Delgado, Francisco
• Other Authors: Universidad de Cantabria
• Format: Article in Journal/Newspaper
• Language: English
• Published: MDPI 2020
• Subjects: Circalittoral rocky shelf; Underwater 3D photogrammetry; Structure-from-motion; Avilés Canyon System; Benthic habitat modeling; Deep-learning; YOLO; Annotation of underwater images; Gam; North Atlantic
• Online Access: http://hdl.handle.net/10902/19148; https://doi.org/10.3390/rs12152466

The relationship between 3D terrain complexity and fine-scale localization and distribution of species is poorly understood. Here we present a very fine-scale 3D reconstruction model of three zones of circalittoral rocky shelf in the Bay of Biscay. Detailed terrain variables are extracted from 3D models using a structure-from-motion (SfM) approach applied to ROTV images. Significant terrain variables that explain species location were selected using general additive models (GAMs) and micro-distribution of the species were predicted. Two models combining BPI, curvature and rugosity can explain 55% and 77% of the Ophiuroidea and Crinoidea distribution, respectively. The third model contributes to explaining the terrain variables that induce the localization of Dendrophyllia cornigera. GAM univariate models detect the terrain variables for each structural species in this third zone (Artemisina transiens, D. cornigera and Phakellia ventilabrum). To avoid the time-consuming task of manual annotation of presence, a deep-learning algorithm (YOLO v4) is proposed. This approach achieves very high reliability and low uncertainty in automatic object detection, identification and location. These new advances applied to underwater imagery (SfM and deep-learning) can resolve the very-high resolution information needed for predictive microhabitat modeling in a very complex zone. This research was partially funded in the scope of the European Commission LIFE+ “Nature and Biodiversity” call and included in the LIFE IP INTEMARES project (LIFE15 IPE/ES/000,012). Moreover, it was partially funded by the Spanish Science and Technology Ministry and included in the ECOMARG (Scientific and technical assistance for the declaration, management and protection of MPAs in Spain) Project (REN2002-00,916/MAR). Deep-learning advances presented here are part of Deep-RAMP (Deep learning to improve the management of marine protected area network in the North Atlantic region) project funded in the frame of the Pleamar Program of the Biodiversity ...