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

• DOI: 10.3389/fmars.2021.640713
• Publication Date: 2021-03-22T06:49:17Z
• Authors: Larissa Macedo Cr...; Aaron Lim; Luis A. Conti; Andrew J. Wheeler
• Keywords: Benthic Habitat; Structure from Motion

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