Integrating a UAV-Derived DEM in Object-Based Image Analysis Increases Habitat Classification Accuracy on Coral Reefs
AuthorsNieuwenhuis, Brian O.
van der Meij, Sancia E.T.
KAUST DepartmentBiological and Environmental Science and Engineering (BESE) Division
Marine Science Program
Red Sea Research Center (RSRC)
KAUST Grant NumberBAS11090-01-01
Permanent link to this recordhttp://hdl.handle.net/10754/682328
MetadataShow full item record
AbstractVery shallow coral reefs (<5 m deep) are naturally exposed to strong sea surface temperature variations, UV radiation and other stressors exacerbated by climate change, raising great concern over their future. As such, accurate and ecologically informative coral reef maps are fundamental for their management and conservation. Since traditional mapping and monitoring methods fall short in very shallow habitats, shallow reefs are increasingly mapped with Unmanned Aerial Vehicles (UAVs). UAV imagery is commonly processed with Structure-from-Motion (SfM) to create orthomosaics and Digital Elevation Models (DEMs) spanning several hundred metres. Techniques to convert these SfM products into ecologically relevant habitat maps are still relatively underdeveloped. Here, we demonstrate that incorporating geomorphometric variables (derived from the DEM) in addition to spectral information (derived from the orthomosaic) can greatly enhance the accuracy of automatic habitat classification. Therefore, we mapped three very shallow reef areas off KAUST on the Saudi Arabian Red Sea coast with an RTK-ready UAV. Imagery was processed with SfM and classified through object-based image analysis (OBIA). Within our OBIA workflow, we observed overall accuracy increases of up to 11% when training a Random Forest classifier on both spectral and geomorphometric variables as opposed to traditional methods that only use spectral information. Our work highlights the potential of incorporating a UAV’s DEM in OBIA for benthic habitat mapping, a promising but still scarcely exploited asset. View Full-Text
CitationNieuwenhuis, B. O., Marchese, F., Casartelli, M., Sabino, A., Van der Meij, S. E. T., & Benzoni, F. (2022). Integrating a UAV-Derived DEM in Object-Based Image Analysis Increases Habitat Classification Accuracy on Coral Reefs. Remote Sensing, 14(19), 5017. https://doi.org/10.3390/rs14195017
SponsorsThis research was funded by KAUST and baseline research funds to F.B. (BAS11090-01-01). This research was partially supported by the Groningen University Fund with an Outstanding Master Student grant, awarded to B.O.N. (2021AU050). We would like to thank members of the Habitat and Benthic Biodiversity lab for their assistance in the field, notably Laura Macrina, Aymere Assayie, Federica Barreca, Francesca Giovenzana, and Silvia Vicario. We also extend our thanks to Colleen Campbell and Ioana Andreea Ciocanaru for lending us the UAV Ground Control Points. Finally, we would like to thank the reviewers for providing knowledgeable comments on an earlier version of this manuscript.
RelationsIs Supplemented By:
Nieuwenhuis, B. O., Marchese, F., Casartelli, M., Sabino, A., Van Der Meij, S., & Benzoni, F. (2022). Data from: Integrating a UAV-derived DEM in object-based image analysis increases habitat classification accuracy on coral reefs (Version 11) [Data set]. Dryad. https://doi.org/10.5061/DRYAD.6M905QG2P. DOI: 10.5061/dryad.6m905qg2p Handle: 10754/686871
Except where otherwise noted, this item's license is described as Archived with thanks to Remote Sensing under a Creative Commons license, details at: https://creativecommons.org/licenses/by/4.0/