RapidBenthos: Automated segmentation and multi‐view classification of coral reef communities from photogrammetric reconstruction
Abstract Underwater photogrammetry is routinely used to monitor large areas of complex and heterogeneous ecosystems, such as coral reefs. However, deriving data on benthic components (i.e. sand, rubble, coral and algae) from photogrammetry products has remained challenging due to the highly time‐con...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2025-02-01
|
| Series: | Methods in Ecology and Evolution |
| Subjects: | |
| Online Access: | https://doi.org/10.1111/2041-210X.14477 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832539945633316864 |
|---|---|
| author | Tiny Remmers Nader Boutros Mathew Wyatt Sophie Gordon Maren Toor Chris Roelfsema Katharina Fabricius Alana Grech Marine Lechene Renata Ferrari |
| author_facet | Tiny Remmers Nader Boutros Mathew Wyatt Sophie Gordon Maren Toor Chris Roelfsema Katharina Fabricius Alana Grech Marine Lechene Renata Ferrari |
| author_sort | Tiny Remmers |
| collection | DOAJ |
| description | Abstract Underwater photogrammetry is routinely used to monitor large areas of complex and heterogeneous ecosystems, such as coral reefs. However, deriving data on benthic components (i.e. sand, rubble, coral and algae) from photogrammetry products has remained challenging due to the highly time‐consuming process of manual data extraction. We developed a machine learning approach to quantify benthic community composition in coral reefs from orthomosaics, which requires no manual delineation of benthic components for training or implementation. The current study presents RapidBenthos, an automated workflow that segments and classifies large‐area images. Our pipeline (1) uses a pre‐trained segmentation model, eliminating the need for manually generated fine‐scale segmented training data, and (2) classifies the resulting segments from multiple views using the underlying survey images, allowing for classification to fine taxonomic levels. Within a test photomosaic built from a coral reef area of 40 m−2, the model automatically detected 43 different benthic classes. Validation resulted in an overall classification accuracy of 0.96 and a segmentation accuracy of 0.87, when compared to a manually digitised replica. The RapidBenthos workflow was 195 times faster than manual segmentation and classification. Additional validation of 524 Acropora coral colonies from 11 additional test plots resulted in a segmentation accuracy of 0.92 and classification accuracy of 0.88 to the coarser ‘Acropora’ group. RapidBenthos has the capability to extract an unprecedented level of data from photomosaics of coral reefs or other complex environments, allowing to sustainably scale photogrammetric monitoring technique both in replicate and survey extent, which consequently can lead to new research questions and more informed ecosystem management. |
| format | Article |
| id | doaj-art-0364510b889845a4913d265eeda9dd15 |
| institution | Kabale University |
| issn | 2041-210X |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Wiley |
| record_format | Article |
| series | Methods in Ecology and Evolution |
| spelling | doaj-art-0364510b889845a4913d265eeda9dd152025-02-05T05:43:21ZengWileyMethods in Ecology and Evolution2041-210X2025-02-0116242744110.1111/2041-210X.14477RapidBenthos: Automated segmentation and multi‐view classification of coral reef communities from photogrammetric reconstructionTiny Remmers0Nader Boutros1Mathew Wyatt2Sophie Gordon3Maren Toor4Chris Roelfsema5Katharina Fabricius6Alana Grech7Marine Lechene8Renata Ferrari9College of Science and Engineering James Cook University Townsville Queensland AustraliaAustralian Institute of Marine Science Crawley Western Australia AustraliaAustralian Institute of Marine Science Crawley Western Australia AustraliaAustralian Institute of Marine Science Cape Cleveland Queensland AustraliaAustralian Institute of Marine Science Cape Cleveland Queensland AustraliaSchool of the Environment University of Queensland Brisbane Queensland AustraliaAustralian Institute of Marine Science Cape Cleveland Queensland AustraliaCollege of Science and Engineering James Cook University Townsville Queensland AustraliaCollege of Science and Engineering James Cook University Townsville Queensland AustraliaAustralian Institute of Marine Science Cape Cleveland Queensland AustraliaAbstract Underwater photogrammetry is routinely used to monitor large areas of complex and heterogeneous ecosystems, such as coral reefs. However, deriving data on benthic components (i.e. sand, rubble, coral and algae) from photogrammetry products has remained challenging due to the highly time‐consuming process of manual data extraction. We developed a machine learning approach to quantify benthic community composition in coral reefs from orthomosaics, which requires no manual delineation of benthic components for training or implementation. The current study presents RapidBenthos, an automated workflow that segments and classifies large‐area images. Our pipeline (1) uses a pre‐trained segmentation model, eliminating the need for manually generated fine‐scale segmented training data, and (2) classifies the resulting segments from multiple views using the underlying survey images, allowing for classification to fine taxonomic levels. Within a test photomosaic built from a coral reef area of 40 m−2, the model automatically detected 43 different benthic classes. Validation resulted in an overall classification accuracy of 0.96 and a segmentation accuracy of 0.87, when compared to a manually digitised replica. The RapidBenthos workflow was 195 times faster than manual segmentation and classification. Additional validation of 524 Acropora coral colonies from 11 additional test plots resulted in a segmentation accuracy of 0.92 and classification accuracy of 0.88 to the coarser ‘Acropora’ group. RapidBenthos has the capability to extract an unprecedented level of data from photomosaics of coral reefs or other complex environments, allowing to sustainably scale photogrammetric monitoring technique both in replicate and survey extent, which consequently can lead to new research questions and more informed ecosystem management.https://doi.org/10.1111/2041-210X.14477artificial intelligenceautomatic segmentationbenthic community compositioncoral reefsmachine learningphotogrammetry |
| spellingShingle | Tiny Remmers Nader Boutros Mathew Wyatt Sophie Gordon Maren Toor Chris Roelfsema Katharina Fabricius Alana Grech Marine Lechene Renata Ferrari RapidBenthos: Automated segmentation and multi‐view classification of coral reef communities from photogrammetric reconstruction Methods in Ecology and Evolution artificial intelligence automatic segmentation benthic community composition coral reefs machine learning photogrammetry |
| title | RapidBenthos: Automated segmentation and multi‐view classification of coral reef communities from photogrammetric reconstruction |
| title_full | RapidBenthos: Automated segmentation and multi‐view classification of coral reef communities from photogrammetric reconstruction |
| title_fullStr | RapidBenthos: Automated segmentation and multi‐view classification of coral reef communities from photogrammetric reconstruction |
| title_full_unstemmed | RapidBenthos: Automated segmentation and multi‐view classification of coral reef communities from photogrammetric reconstruction |
| title_short | RapidBenthos: Automated segmentation and multi‐view classification of coral reef communities from photogrammetric reconstruction |
| title_sort | rapidbenthos automated segmentation and multi view classification of coral reef communities from photogrammetric reconstruction |
| topic | artificial intelligence automatic segmentation benthic community composition coral reefs machine learning photogrammetry |
| url | https://doi.org/10.1111/2041-210X.14477 |
| work_keys_str_mv | AT tinyremmers rapidbenthosautomatedsegmentationandmultiviewclassificationofcoralreefcommunitiesfromphotogrammetricreconstruction AT naderboutros rapidbenthosautomatedsegmentationandmultiviewclassificationofcoralreefcommunitiesfromphotogrammetricreconstruction AT mathewwyatt rapidbenthosautomatedsegmentationandmultiviewclassificationofcoralreefcommunitiesfromphotogrammetricreconstruction AT sophiegordon rapidbenthosautomatedsegmentationandmultiviewclassificationofcoralreefcommunitiesfromphotogrammetricreconstruction AT marentoor rapidbenthosautomatedsegmentationandmultiviewclassificationofcoralreefcommunitiesfromphotogrammetricreconstruction AT chrisroelfsema rapidbenthosautomatedsegmentationandmultiviewclassificationofcoralreefcommunitiesfromphotogrammetricreconstruction AT katharinafabricius rapidbenthosautomatedsegmentationandmultiviewclassificationofcoralreefcommunitiesfromphotogrammetricreconstruction AT alanagrech rapidbenthosautomatedsegmentationandmultiviewclassificationofcoralreefcommunitiesfromphotogrammetricreconstruction AT marinelechene rapidbenthosautomatedsegmentationandmultiviewclassificationofcoralreefcommunitiesfromphotogrammetricreconstruction AT renataferrari rapidbenthosautomatedsegmentationandmultiviewclassificationofcoralreefcommunitiesfromphotogrammetricreconstruction |