3D Classification of Cold-Water Coral Reefs: A Comparison of Classification Techniques for 3D Reconstructions of Cold-Water Coral Reefs and Seabed

Abstract

Cold-water coral (CWC) reefs are complex structural habitats that are considered biodiversity “hotspots” in deep-sea environments and are subject to several climate and anthropogenic threats. As three-dimensional structural habitats, there is a need for robust and accessible technologies to enable more accurate reef assessments. Photogrammetry derived from remotely operated vehicle video data is an effective and non-destructive method that creates high-resolution reconstructions of CWC habitats. Here, three classification workflows [Multiscale Geometrical Classification (MGC), Colour and Geometrical Classification (CGC) and Object-Based Image Classification(OBIA)] are presented and applied to photogrammetric reconstructions of CWC habitats in the Porcupine Bank Canyon, NE Atlantic. In total, six point clouds, orthomosaics, and digital elevation models, generated from structure-from-motion photogrammetry, are used to evaluate each classification workflow. Our results show that 3D Multiscale Geometrical Classification outperforms the Colour and Geometrical Classification method. However, each method has advantages for specific applications pertinent to the wider marine scientific community. Results suggest that advancing from commonly employed 2D image analysis techniques to 3D photogrammetric classification methods is advantageous and provides a more realistic representation of CWC habitat composition.

A blueprint for integrating scientific approaches and international communities to assess basin-wide ocean ecosystem status

“…Acoustic surveys of seabed features, including cliffs and overhangs, carried out using ROVs and AUVs, produce 3D ultra-high-resolution bathymetric maps 32 with ecological communities assessed using visual and targeted sampling. Photogrammetry using structure-from-motion techniques is increasingly applied to create 3D models of deep ecosystems 33,34 and to study species interactions using point pattern analysis 35 .…”

High-resolution 3D mapping of cold-water coral reefs using machine learning

“…The ROV is also mounted with two deep-sea lasers spaced at 10 cm for scaling. Positioning data were acquired with a Sonardyne Ranger 2 ultrashort baseline (USBL) beacon with accuracy of 1.3% of slant range (measurement of relative position from time of return signal from ROV transponder to the USBL in relation to the Turnaround Travel Time (TAT) and underwater sound velocity) similar to (Lim et al, 2020a;Oliveira et al, 2021). The ROV was kept at a height of approximately 2 m above the seabed with a survey speed of <0.2 knots during the video data collection.…”

3D photogrammetry and deep‐learning deliver accurate estimates of epibenthic biomass

“…To date, SfM has been used from tropical reefs (e.g. Fukunaga et al, 2019), to temperate (Spyksma et al, 2022), polar (Piazza et al, 2019) and deep-water environments (De Oliveira et al, 2021) and has been used to assess habitat complexity (Aston et al, 2022;Bayley et al, 2019;Price et al, 2019), growth rates (Olinger et al, 2019;Prado et al, 2021), bioerosion (Morais et al, 2022), habitat provision (Urbina-Barreto et al, 2021) and benthic cover (Raoult et al, 2016). Furthermore, Palma et al (2018) used SfM-derived surface area measurements to estimate biomass of Mediterranean sea fans and Ríos et al (2020) estimated biomass of the deep-sea sponges from SfM-derived sponge perimeter.…”