This repository contains the source code and content for the "Computer Vision Across the Marine Sciences" Jupyter Book, a comprehensive educational resource designed to bridge the gap between marine science and computer vision. The book serves as the foundation for the University of Washington course OCEAN 462-C and is publicly available at oceancv.org.
The book teaches how to apply computer vision techniques to marine science challenges through:
- Interactive Tutorials: Hands-on Python notebooks covering data preparation, model training, and evaluation
- Case Studies: Real-world applications in marine biology, fisheries, and oceanography
- Integration with Modern Tools: Examples using YOLO, PyTorch, TensorFlow, and Hugging Face
Topics covered include:
- Introduction to marine imagery and AI fundamentals
- Image annotation, augmentation, and preprocessing
- Classification, object detection, segmentation, and tracking
- Model deployment with Streamlit
- Dataset discovery and selection
- Model sharing and documentation
Visit oceancv.org to access the interactive web version of the book.
To build and explore the book locally:
-
Clone this repository:
git clone https://github.com/atticus-carter/cv.git cd cv -
Create a conda environment:
conda env create -f environment.yml conda activate cv
-
Build the book:
jupyter-book build . -
View the book:
# Open _build/html/index.html in your browser
We welcome contributions! Please see our contributing guidelines for more information on how to report issues, submit feature requests, or contribute code.
- Ada Carter & Katie Bigham - Primary Authors
- Sasha Seroy - Supervisor
- Mikelle Nuwer - Supervisor
This project is licensed under the MIT License - see the LICENSE file for details.
This book was developed with the support of the National Science Foundation under Grant No. OCE-2307504. Any opinions, findings, and conclusions expressed in this material are those of the authors and do not necessarily reflect the views of the National Science Foundation.