Hierarchical deep learning framework for automated marine vegetation and fauna analysis using ROV video data
The integration of deep learning with Remotely Operated Vehicles (ROVs) has advanced scalable, detailed marine biodiversity monitoring. This study presents the Esefjorden Marine Vegetation Segmentation Dataset (EMVSD) and FjordVision, a framework designed for automated analysis of marine vegetation...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-03-01
|
| Series: | Ecological Informatics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1574954124005089 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832595374951366656 |
|---|---|
| author | Bjørn Christian Weinbach Rajendra Akerkar Marianne Nilsen Reza Arghandeh |
| author_facet | Bjørn Christian Weinbach Rajendra Akerkar Marianne Nilsen Reza Arghandeh |
| author_sort | Bjørn Christian Weinbach |
| collection | DOAJ |
| description | The integration of deep learning with Remotely Operated Vehicles (ROVs) has advanced scalable, detailed marine biodiversity monitoring. This study presents the Esefjorden Marine Vegetation Segmentation Dataset (EMVSD) and FjordVision, a framework designed for automated analysis of marine vegetation and fauna in natural habitats. FjordVision combines state-of-the-art object detection, iterative dataset refinement, and a taxonomy-aware hierarchical reclassification framework that enhances accuracy across four taxonomic levels: binary, class, genus, and species. Although YOLOv8 was initially employed for instance segmentation, results showed Mask R-CNN to be more effective across hierarchical levels. FjordVision’s hierarchical classification supports marine biodiversity assessments, offering critical insights for conservation applications in fjord ecosystems. |
| format | Article |
| id | doaj-art-107b645ab566453ea521148d331b2bf3 |
| institution | Kabale University |
| issn | 1574-9541 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Ecological Informatics |
| spelling | doaj-art-107b645ab566453ea521148d331b2bf32025-01-19T06:24:41ZengElsevierEcological Informatics1574-95412025-03-0185102966Hierarchical deep learning framework for automated marine vegetation and fauna analysis using ROV video dataBjørn Christian Weinbach0Rajendra Akerkar1Marianne Nilsen2Reza Arghandeh3Western Norway Research Institute, Røyrgata 4, Sogndal, 6856, Vestland, Norway; Corresponding author.Western Norway Research Institute, Røyrgata 4, Sogndal, 6856, Vestland, NorwayWestern Norway University of Applied Sciences, Røyrgata 6, Sogndal, 6856, NorwayWestern Norway University of Applied Sciences, Inndalsveien 28, Bergen, 5063, NorwayThe integration of deep learning with Remotely Operated Vehicles (ROVs) has advanced scalable, detailed marine biodiversity monitoring. This study presents the Esefjorden Marine Vegetation Segmentation Dataset (EMVSD) and FjordVision, a framework designed for automated analysis of marine vegetation and fauna in natural habitats. FjordVision combines state-of-the-art object detection, iterative dataset refinement, and a taxonomy-aware hierarchical reclassification framework that enhances accuracy across four taxonomic levels: binary, class, genus, and species. Although YOLOv8 was initially employed for instance segmentation, results showed Mask R-CNN to be more effective across hierarchical levels. FjordVision’s hierarchical classification supports marine biodiversity assessments, offering critical insights for conservation applications in fjord ecosystems.http://www.sciencedirect.com/science/article/pii/S1574954124005089Esefjorden Marine Vegetation Segmentation Dataset (EMVSD)Hierarchical Deep Learning FrameworkEsefjordenNorwayMarine biodiversityUnderwater imagery |
| spellingShingle | Bjørn Christian Weinbach Rajendra Akerkar Marianne Nilsen Reza Arghandeh Hierarchical deep learning framework for automated marine vegetation and fauna analysis using ROV video data Ecological Informatics Esefjorden Marine Vegetation Segmentation Dataset (EMVSD) Hierarchical Deep Learning Framework Esefjorden Norway Marine biodiversity Underwater imagery |
| title | Hierarchical deep learning framework for automated marine vegetation and fauna analysis using ROV video data |
| title_full | Hierarchical deep learning framework for automated marine vegetation and fauna analysis using ROV video data |
| title_fullStr | Hierarchical deep learning framework for automated marine vegetation and fauna analysis using ROV video data |
| title_full_unstemmed | Hierarchical deep learning framework for automated marine vegetation and fauna analysis using ROV video data |
| title_short | Hierarchical deep learning framework for automated marine vegetation and fauna analysis using ROV video data |
| title_sort | hierarchical deep learning framework for automated marine vegetation and fauna analysis using rov video data |
| topic | Esefjorden Marine Vegetation Segmentation Dataset (EMVSD) Hierarchical Deep Learning Framework Esefjorden Norway Marine biodiversity Underwater imagery |
| url | http://www.sciencedirect.com/science/article/pii/S1574954124005089 |
| work_keys_str_mv | AT bjørnchristianweinbach hierarchicaldeeplearningframeworkforautomatedmarinevegetationandfaunaanalysisusingrovvideodata AT rajendraakerkar hierarchicaldeeplearningframeworkforautomatedmarinevegetationandfaunaanalysisusingrovvideodata AT mariannenilsen hierarchicaldeeplearningframeworkforautomatedmarinevegetationandfaunaanalysisusingrovvideodata AT rezaarghandeh hierarchicaldeeplearningframeworkforautomatedmarinevegetationandfaunaanalysisusingrovvideodata |