Brad Dwyer

Brackish Underwater

Object Detection

Brackish Underwater Computer Vision Project

Drop an image or


12444 images
Explore Dataset

Example image from the dataset

Dataset Information

This dataset contains 14,674 images (12,444 of which contain objects of interest with bounding box annotations) of fish, crabs, and other marine animals. It was collected with a camera mounted 9 meters below the surface on the Limfjords bridge in northern Denmark by Aalborg University.


Roboflow has extracted and processed the frames from the source videos and converted the annotations for use with many popular computer vision models. We have maintained the same 80/10/10 train/valid/test split as the original dataset.

The class balance in the annotations is as follows: Class Balance

Most of the identified objects are congregated towards the bottom of the frames.

Annotation Heatmap

More Information

For more information, see the Detection of Marine Animals in a New Underwater Dataset with Varying Visibility paper.

If you find the dataset useful, the authors request that you please cite their paper:

    title={Detection of Marine Animals in a New Underwater Dataset with Varying Visibility},
    author={Pedersen, Malte and Haurum, Joakim Bruslund and Gade, Rikke and Moeslund, Thomas B. and Madsen, Niels},
    booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
    month = {June},
    year = {2019}

Trained Model API

This project has a trained model available that you can try in your browser and use to get predictions via our Hosted Inference API and other deployment methods.

Connect Your Model With Program Logic

Find utilities and guides to help you start using the Brackish Underwater project in your project.


Brad Dwyer

Last Updated

2 years ago

Project Type

Object Detection




Views: 2460

Views in previous 30 days: 162

Downloads: 376

Downloads in previous 30 days: 24


CC BY 4.0