NERC Data Catalogue Service
Automated detection of Antarctic benthic organisms in high-resolution in situ imagery to aid biodiversity monitoring: optimal model weights
Model weights for the optimal object detection model, trained on the Weddell Sea Benthic Dataset. Trained 2025-05. Weights should be used with a Deformable-DETR architecture.
This work was funded by the UKRI Future Leaders Fellowship MR/W01002X/1 'The past, present and future of unique cold-water benthic (sea floor) ecosystems in the Southern Ocean' awarded to Rowan Whittle.
Simple
- Date (Creation)
- 2025-06-06
- Date (Revision)
- 2025-06-06
- Date (Publication)
- 2025-06-06
- Date (released)
- 2025-06-06
- Edition
- 1.0
- Unique resource identifier
- https://doi.org/10.5285/b2874f3f-285d-4ae6-9bb4-6bfe3eacbfff
- Codespace
- doi
- Unique resource identifier
- GB/NERC/BAS/PDC/02070
- Codespace
- https://data.bas.ac.uk/
- Other citation details
- Please cite this item as: Trotter, C., Griffiths, H.J., Khan, T.M., & Whittle, R.J. (2025). Automated detection of Antarctic benthic organisms in high-resolution in situ imagery to aid biodiversity monitoring: optimal model weights (Version 1.0) [Data set]. NERC EDS UK Polar Data Centre. https://doi.org/10.5285/b2874f3f-285d-4ae6-9bb4-6bfe3eacbfff
- Credit
- No credit.
- Status
- completed Completed
https://www.bas.ac.uk/team/business-teams/information-services/uk-polar-data-centre/
- Maintenance and update frequency
- asNeeded As needed
- Maintenance note
- completed Completed
- Theme
-
- Benthos
- biodiversity monitoring
- computer vision
- deep learning
- marine ecology
- GEMET - INSPIRE themes, version 1.0
- Access constraints
- otherRestrictions Other restrictions
- Other constraints
- no limitations to public access
- Access constraints
- otherRestrictions Other restrictions
- Other constraints
- no limitations
- Use constraints
- license License
- Other constraints
- Open Government Licence v3.0
- Use constraints
- otherRestrictions Other restrictions
- Other constraints
- Data are supplied under Open Government Licence v3.0
- Use constraints
- otherRestrictions Other restrictions
- Other constraints
- None
- Unique resource identifier
- doi
- Codespace
- doi
- Association Type
- crossReference Cross reference
- Unique resource identifier
- doi
- Codespace
- doi
- Association Type
- crossReference Cross reference
- Unique resource identifier
- doi
- Codespace
- doi
- Association Type
- crossReference Cross reference
- Unique resource identifier
- doi
- Codespace
- doi
- Association Type
- crossReference Cross reference
- Unique resource identifier
- doi
- Codespace
- doi
- Association Type
- crossReference Cross reference
- Unique resource identifier
- url
- Codespace
- url
- Association Type
- dependency dependency
- Unique resource identifier
- url
- Codespace
- url
- Association Type
- largerWorkCitation Larger work citation
- Unique resource identifier
- url
- Codespace
- url
- Association Type
- crossReference Cross reference
- Spatial representation type
- textTable Text, table
- Metadata language
- engEnglish
- Character set
- utf8 UTF8
- Topic category
-
- Environment
- Oceans
))
- Begin date
- 2025-05-28
- End date
- 2025-05-28
- Supplemental Information
- It is recommended that careful attention be paid to the contents of any data, and that the author be contacted with any questions regarding appropriate use. If you find any errors or omissions, please report them to polardatacentre@bas.ac.uk.
Distributor
https://www.bas.ac.uk/team/business-teams/information-services/uk-polar-data-centre/
- Name
- application/zip
- Units of distribution
- bytes
- Transfer size
- 171966464
- OnLine resource
-
Get Data
(
WWW:LINK-1.0-http--link
)
Download data
- Hierarchy level
- dataset Dataset
- Statement
-
Methodology:
Model weights for a Deformable-DETR architecture, trained to detect 25 Antarctic benthic morphotypes using the Weddell Sea Benthic Dataset (see Related URLs). Model version: 1.0.0.
Model weights correspond to the optimal object detection model capable of automated benthic organism detection as described in [in-prep].
For model development code, (see Related URLs).
Data collection:
The model was trained using a single High Performance Computing node with CentOS 7, and one NVIDIA A2 GPU. Training was performed using Python v3.8.20 alongside the following packages:
MMDetection v3.3.0 [1]
Pytorch v2.4.0
Pytorch-cuda v12.1
torchvision v0.19.0
sahi v0.11.22 [2]
albumentations v1.3.1 [3]
- File identifier
- b2874f3f-285d-4ae6-9bb4-6bfe3eacbfff XML
- Metadata language
- engEnglish
- Character set
- utf8 UTF8
- Hierarchy level
- dataset Dataset
- Hierarchy level name
- dataset
- Date stamp
- 2025-06-06
- Metadata standard name
- ISO 19115 Geographic Information - Metadata
- Metadata standard version
- ISO 19115:2003(E)
https://www.bas.ac.uk/team/business-teams/information-services/uk-polar-data-centre/
Overviews
Spatial extent
Provided by
