Subtidal seagrass detector: development of a deep learning seagrass detection and classification model for seagrass presence and density in diverse habitats from underwater photoquadrats
This paper presents the development and evaluation of a Subtidal Seagrass Detector (the Detector). Deep learning models were used to detect most forms of seagrass occurring in a diversity of habitats across the northeast Australian seascape from underwater images and classify them based on how much...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-07-01
|
| Series: | Frontiers in Marine Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmars.2023.1197695/full |
| _version_ | 1827899087037399040 |
|---|---|
| author | Lucas A. Langlois Catherine J. Collier Len J. McKenzie |
| author_facet | Lucas A. Langlois Catherine J. Collier Len J. McKenzie |
| author_sort | Lucas A. Langlois |
| collection | DOAJ |
| description | This paper presents the development and evaluation of a Subtidal Seagrass Detector (the Detector). Deep learning models were used to detect most forms of seagrass occurring in a diversity of habitats across the northeast Australian seascape from underwater images and classify them based on how much the cover of seagrass was present. Images were collected by scientists and trained contributors undertaking routine monitoring using drop-cameras mounted over a 50 x 50 cm quadrat. The Detector is composed of three separate models able to perform the specific tasks of: detecting the presence of seagrass (Model #1); classify the seagrass present into three broad cover classes (low, medium, high) (Model #2); and classify the substrate or image complexity (simple of complex) (Model #3). We were able to successfully train the three models to achieve high level accuracies with 97%, 80.7% and 97.9%, respectively. With the ability to further refine and train these models with newly acquired images from different locations and from different sources (e.g. Automated Underwater Vehicles), we are confident that our ability to detect seagrass will improve over time. With this Detector we will be able rapidly assess a large number of images collected by a diversity of contributors, and the data will provide invaluable insights about the extent and condition of subtidal seagrass, particularly in data-poor areas. |
| first_indexed | 2024-03-12T23:12:16Z |
| format | Article |
| id | doaj.art-3306ad8bb42c40b5a70899cfc60be95f |
| institution | Directory Open Access Journal |
| issn | 2296-7745 |
| language | English |
| last_indexed | 2024-03-12T23:12:16Z |
| publishDate | 2023-07-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Marine Science |
| spelling | doaj.art-3306ad8bb42c40b5a70899cfc60be95f2023-07-17T19:34:19ZengFrontiers Media S.A.Frontiers in Marine Science2296-77452023-07-011010.3389/fmars.2023.11976951197695Subtidal seagrass detector: development of a deep learning seagrass detection and classification model for seagrass presence and density in diverse habitats from underwater photoquadratsLucas A. LangloisCatherine J. CollierLen J. McKenzieThis paper presents the development and evaluation of a Subtidal Seagrass Detector (the Detector). Deep learning models were used to detect most forms of seagrass occurring in a diversity of habitats across the northeast Australian seascape from underwater images and classify them based on how much the cover of seagrass was present. Images were collected by scientists and trained contributors undertaking routine monitoring using drop-cameras mounted over a 50 x 50 cm quadrat. The Detector is composed of three separate models able to perform the specific tasks of: detecting the presence of seagrass (Model #1); classify the seagrass present into three broad cover classes (low, medium, high) (Model #2); and classify the substrate or image complexity (simple of complex) (Model #3). We were able to successfully train the three models to achieve high level accuracies with 97%, 80.7% and 97.9%, respectively. With the ability to further refine and train these models with newly acquired images from different locations and from different sources (e.g. Automated Underwater Vehicles), we are confident that our ability to detect seagrass will improve over time. With this Detector we will be able rapidly assess a large number of images collected by a diversity of contributors, and the data will provide invaluable insights about the extent and condition of subtidal seagrass, particularly in data-poor areas.https://www.frontiersin.org/articles/10.3389/fmars.2023.1197695/fullseagrassGreat Barrier Reefdeep learningimage classificationunderwater |
| spellingShingle | Lucas A. Langlois Catherine J. Collier Len J. McKenzie Subtidal seagrass detector: development of a deep learning seagrass detection and classification model for seagrass presence and density in diverse habitats from underwater photoquadrats Frontiers in Marine Science seagrass Great Barrier Reef deep learning image classification underwater |
| title | Subtidal seagrass detector: development of a deep learning seagrass detection and classification model for seagrass presence and density in diverse habitats from underwater photoquadrats |
| title_full | Subtidal seagrass detector: development of a deep learning seagrass detection and classification model for seagrass presence and density in diverse habitats from underwater photoquadrats |
| title_fullStr | Subtidal seagrass detector: development of a deep learning seagrass detection and classification model for seagrass presence and density in diverse habitats from underwater photoquadrats |
| title_full_unstemmed | Subtidal seagrass detector: development of a deep learning seagrass detection and classification model for seagrass presence and density in diverse habitats from underwater photoquadrats |
| title_short | Subtidal seagrass detector: development of a deep learning seagrass detection and classification model for seagrass presence and density in diverse habitats from underwater photoquadrats |
| title_sort | subtidal seagrass detector development of a deep learning seagrass detection and classification model for seagrass presence and density in diverse habitats from underwater photoquadrats |
| topic | seagrass Great Barrier Reef deep learning image classification underwater |
| url | https://www.frontiersin.org/articles/10.3389/fmars.2023.1197695/full |
| work_keys_str_mv | AT lucasalanglois subtidalseagrassdetectordevelopmentofadeeplearningseagrassdetectionandclassificationmodelforseagrasspresenceanddensityindiversehabitatsfromunderwaterphotoquadrats AT catherinejcollier subtidalseagrassdetectordevelopmentofadeeplearningseagrassdetectionandclassificationmodelforseagrasspresenceanddensityindiversehabitatsfromunderwaterphotoquadrats AT lenjmckenzie subtidalseagrassdetectordevelopmentofadeeplearningseagrassdetectionandclassificationmodelforseagrasspresenceanddensityindiversehabitatsfromunderwaterphotoquadrats |