The Koster Seafloor Observatory is an open-source, citizen science and machine learning approach to analyse subsea movies.

This Object Detection module contains scripts and resources to train and evaluate Object Detection models.

The tutorials enable users to customise Yolov5 models using Ultralytics. The repository contains both model-specific files (same structure as Ultralytics) as well as specific source files related to Koster pipelines (src folder) and utils (tutorial_utils).

• Python 3.7
• Anaconda
• GIT

Clone this repository using

git clone --recurse-submodules https://github.com/ocean-data-factory-sweden/koster_data_management.git

Navigate to the folder where you have cloned the repository or unzipped the manually downloaded repository.

cd koster_yolov4

Then install the requirements by running.

pip install -r requirements.txt

WIP

If you use this code or its models in your research, please cite:

Anton V, Germishuys J, Bergström P, Lindegarth M, Obst M (2021) An open-source, citizen science and machine learning approach to analyse subsea movies. Biodiversity Data Journal 9: e60548. https://doi.org/10.3897/BDJ.9.e60548

You can find out more about the project at https://www.zooniverse.org/projects/victorav/the-koster-seafloor-observatory.

We are always excited to collaborate and help other marine scientists. Please feel free to contact us with your questions.