Descripción
Dataset of species records extracted from video footage recorded by remotely operated vehicles (ROVs) in the marine protected area Kosterhavets nationalpark on the Swedish west-coast. The original movies were collected during 1997-2023. This data set is based on videos of 70 transects across slopes and rock walls in the National Park at depths between 7-105 m. Species records were extracted from the movies using Yolov8 model, while depth information was extracted with the easyOCR python package from the ROV video overlays. Original videos are archived and accessible at Tjärnö Marine Laboratory’s (Univerisity of Gothenburg). The analysis was performed using the Swedish platform for subsea image analysis (www.subsim.se). We acknowledge the support of the technical officers and ROV pilots at Tjärnö Marine Laboratory, in particular Tomas Lundälv, Roger Johannesson, and Joel White.
Registros
Los datos en este recurso de registros biológicos han sido publicados como Archivo Darwin Core(DwC-A), el cual es un formato estándar para compartir datos de biodiversidad como un conjunto de una o más tablas de datos. La tabla de datos del core contiene 72.369 registros.
Este IPT archiva los datos y, por lo tanto, sirve como repositorio de datos. Los datos y los metadatos del recurso están disponibles para su descarga en la sección descargas. La tabla versiones enumera otras versiones del recurso que se han puesto a disposición del público y permite seguir los cambios realizados en el recurso a lo largo del tiempo.
Versiones
La siguiente tabla muestra sólo las versiones publicadas del recurso que son de acceso público.
¿Cómo referenciar?
Los usuarios deben citar este trabajo de la siguiente manera:
Nilsson C (2024). Koster historical biodiversity assessment. Version 1.4. Wildlife.ai. Occurrence dataset. https://ipt.gbif.org.nz/resource?r=koster_historical_assessment&v=1.4
Derechos
Los usuarios deben respetar los siguientes derechos de uso:
El publicador y propietario de los derechos de este trabajo es Wildlife.ai. Esta obra está bajo una licencia Creative Commons de Atribución/Reconocimiento (CC-BY 4.0).
Registro GBIF
Este recurso ha sido registrado en GBIF con el siguiente UUID: 51d0bd32-e215-45ea-a04d-47a474336125. Wildlife.ai publica este recurso y está registrado en GBIF como un publicador de datos avalado por GBIF New Zealand.
Palabras clave
Occurrence; Machine Observations; YOLOv8; Benthic Invertebrates; Koster; Hard Substrate; Marine Biology; Marine Biodiversity; Marine Ecology; Subtidal Zone; Observation; Machine Observations; YOLOv8; Benthic Invertebrates; Koster; Hard Substrate; Marine Biology; Marine Biodiversity; Marine Ecology; Subtidal Zone
Contactos
- Proveedor De Los Metadatos ●
- Originador ●
- Punto De Contacto ●
- Investigador Principal
- Researcher
- Anders Zornsgatan 34B
- 0730682795
https://orcid.org/0009-0005-6356-2152
- Punto De Contacto
- Research Engineer
- Laboratorievägen 10
- +46 31-786 96 03
- Programador
- Researcher
- Programador
- Data Scientist
- Västra Hamngatan 8
- Propietario
- Researcher
- Medicinaregatan 7B
- +4676-618 38 27
Cobertura geográfica
Data collected from the area west of the island of Yttre Vattenholmen. For additional information, feel free to contact authors.
| Coordenadas límite | Latitud Mínima Longitud Mínima [58,9, 11,1], Latitud Máxima Longitud Máxima [58,9, 11,1] |
|---|
Cobertura temporal
| Fecha Inicial / Fecha Final | 1997-08-27 / 2023-10-09 |
|---|
Datos del proyecto
Biodiversity assessment of distribution size and relative abundance of 17 unique benthic invertebrate taxa. Assessment made by applying a YOLOv8 model trained on image data from ROV footage of the study site to 70 ROV transects from 1997-2023.
| Título | Depth Learning - Using Deep-Learning Object Detection Software to Investigate Spatiotemporal Vertical Ecological Trends on a Submarine Canyon Wall in Northern Skagerrak |
|---|---|
| Descripción del área de estudio | Rock walls and slopes from 7-105m in the area west of the island of Yttre Vattenholmen. |
Personas asociadas al proyecto:
Métodos de muestreo
Sampling was performed by ROV from Tjärnö Marine Laboratory. Transects were taken for various purposes and are non-standardized. Thus, time spent at each depth and distance to substrate may vary. Transects are defined as consecutive filming of the study site until departure and may have depths removed if the ROV was not filming the habitat of interest for this study (hard substrate) at these depths. Additionally, inconsistency may exist between substrate depths and ROV depths where the ROV was not filming perpendicular to the seafloor. For further information, contact Joel White or Christian Nilsson.
| Área de Estudio | Archived ROV footage from the area west of Yttre Vattenholmen was utilized. All footage available with sufficient depth information was utilized. Footage was collected for various purposes, therefore sampling frequency & temporal resolution varies. |
|---|---|
| Control de Calidad | Average maxcount per depth (organismQuantity) was added to provide insight regarding false positives. If individualCount for an observation is significantly higher than organismQuantity a false positive may be possible. For further information, contact Christian Nilsson. |
Descripción de la metodología paso a paso:
- ROV depth for each image frame of videos was extracted from the video overlay using the EasyOCR python package. Depth was connected to YOLOv8 model observations through frame number in R, after which maximum and mean individual count was summarized from each transect for each taxon.
Referencias bibliográficas
- Koster historical invertebrate model - SUBSIM 17tx. (model used to generate annotations) https://doi.org/10.5281/zenodo.13589902
Metadatos adicionales
| Identificadores alternativos | 51d0bd32-e215-45ea-a04d-47a474336125 |
|---|---|
| https://ipt.gbif.org.nz/resource?r=koster_historical_assessment |