# MIT Sea Grant River Herring (FishEye underwater video)

## Facts

- Provider: MIT Sea Grant (Robert Vincent, Zhongqi Chen)
- License: CDLA-Permissive-1.0 (https://lila.science/datasets/mit-sea-grant-river-herring/)
- Format: JSON, PNG (in sampled files)
- Stored at: Azure Blob Storage, https://lilawildlife.blob.core.windows.net/lila-wildlife/mit-river-herring
- Access: public, readable without an account
- Category: Environmental Science
- Source: https://lila.science/datasets/mit-sea-grant-river-herring/
- Page: https://scigantic.com/archive/e2541c4e-854e-589d-b22b-1c07c1cb5c2a
- Keywords: Environmental Science, JSON, PNG, Azure Blob Storage

## About

Underwater video frames from the MIT Sea Grant FishEye project, which builds computer vision tools to detect, track and count migrating river herring (alewife and blueback herring) in Massachusetts rivers between March and June. Cameras ran on the Coonamessett River (2024), Ipswich River (2015 to 2018) and Santuit River (2024). LILA states 1,434 clips with about 262k frames, about 91k bounding boxes on about 60k frames (the rest reviewed as empty); about 80% of boxes are river herring, with trout, bass, perch, eel, sunfish, lamprey and unknown fish, in day (about 65%) and night conditions. Annotations are COCO JSON (pycocotools). Layout (measured 2026-11-13): unzipped PNG frame folders per river and clip (Coonamessett/, Ipswich/, Santuit/), per-river CSVs, mit_sea_grant_river_herring.json (68 MB) and a 41.5 GB zip of the same images. The loose frames read directly from the read-only mount. Use for fish counting, anadromous fish passage monitoring and tracking. Released by LILA BC under the Community Data License Agreement (permissive variant), CDLA-Permissive-1.0.

## Load the data

```python
import adlfs
fs = adlfs.AzureBlobFileSystem(account_name='lilawildlife', anon=True)
fs.ls('lila-wildlife/mit-river-herring/')[:10]
```

Lists the files with anonymous access. Runs on any machine, with no cloud account.

## Data structure

File types in sampled files: JSON, PNG

Example file: `Coonamessett/1086961/annotations/instances_default.json`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/e2541c4e-854e-589d-b22b-1c07c1cb5c2a
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/e2541c4e-854e-589d-b22b-1c07c1cb5c2a
- Over MCP: `get_schema_card` with id `e2541c4e-854e-589d-b22b-1c07c1cb5c2a` at https://api.scigantic.com/mcp

## Related topics

- [JSON datasets](https://scigantic.com/topics/json)
- [Environmental Science datasets](https://scigantic.com/topics/environmental-science)
- [PNG datasets](https://scigantic.com/topics/png)
