# MusselGooseneckSeg: Drone Imagery Segmentation of Mussels and Gooseneck Barnacles in the Rocky Intertidal (Hakai Institute)

## Facts

- Provider: Hakai Institute
- License: CC-BY-4.0 (https://huggingface.co/datasets/HakaiInstitute/mussel-gooseneck-seg-rgb-1024-1024)
- Size: 19 files
- Stored at: Hugging Face, https://huggingface.co/datasets/HakaiInstitute/mussel-gooseneck-seg-rgb-1024-1024
- Access: public, readable without an account
- DOI: https://doi.org/10.57967/hf/7792
- Category: Environmental Science
- Source: https://huggingface.co/datasets/HakaiInstitute/mussel-gooseneck-seg-rgb-1024-1024
- Page: https://scigantic.com/archive/c6d0351d-10be-560d-bac7-eec3b6d8740e
- Keywords: Environmental Science, image segmentation, Hugging Face

## About

A three-class semantic segmentation dataset of rocky intertidal habitat from high resolution drone (UAV) RGB imagery collected by the Hakai Institute. Every pixel is labeled mussel, gooseneck barnacle or background, by manual heads-up digitizing with manual verification. There are 909 image and label pairs as non-overlapping 1024 by 1024 pixel TIFF tiles, packed as WebDataset tar shards with train, validation and test splits (about 3.8 GB) and a metadata.json; load with the datasets library (keys image.tif and label.tif) or stream the shards. Suited to training and benchmarking models that map intertidal invertebrate cover, a companion to the single-class MusselSeg dataset. Released by the Hakai Institute under CC BY 4.0; cite the dataset, DOI 10.57967/hf/7792.

## Load the data

```python
from huggingface_hub import hf_hub_download
path = hf_hub_download(repo_id="HakaiInstitute/mussel-gooseneck-seg-rgb-1024-1024", filename="test-000000.tar", repo_type="dataset")
print(path)
```

## Data structure

Example file: `test-000000.tar`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/c6d0351d-10be-560d-bac7-eec3b6d8740e
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/c6d0351d-10be-560d-bac7-eec3b6d8740e
- Over MCP: `get_schema_card` with id `c6d0351d-10be-560d-bac7-eec3b6d8740e` at https://api.scigantic.com/mcp

## Related topics

- [Image segmentation datasets](https://scigantic.com/topics/image-segmentation)
- [Environmental Science datasets](https://scigantic.com/topics/environmental-science)
