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

• Published in: Frontiers in Marine Science Vol. 8
• Main Authors: de Oliveira, Larissa Macedo Cruz, Lim, Aaron, Conti, Luis A., Wheeler, Andrew J.
• Format: Journal Article
• Language: English
• Published: Lausanne Frontiers Research Foundation 22.03.2021; Frontiers Media S.A
• Subjects: 3D image classification; 3D photogrammetry; Anthropogenic factors; Automation; Biodiversity; Biodiversity hot spots; Canyons; Classification; Cold; cold-water corals; Colour; Coral reefs; Datasets; Deep sea; Deep water; Habitats; Image processing; Marine invertebrates; Methods; object-based classification; Ocean floor; Photogrammetry; remotely operated vehicles; Salinity; Software; structure-from-motion; Water temperature; Ireland
• ISSN: 2296-7745; 2296-7745
• DOI: 10.3389/fmars.2021.640713

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.