# Trail Camera Images of New Zealand Animals

## Facts

- Provider: New Zealand trail camera projects (contact Joris Tinnemans)
- License: CDLA-Permissive-1.0 (https://lila.science/datasets/nz-trailcams)
- Format: JPEG (in sampled files)
- Stored at: Azure Blob Storage, https://lilawildlife.blob.core.windows.net/lila-wildlife/nz-trailcams
- Access: public, readable without an account
- Category: Environmental Science
- Source: https://lila.science/datasets/nz-trailcams
- Page: https://scigantic.com/archive/dd01ec07-5481-56c0-a54c-c2d46afe4f0a
- Keywords: Environmental Science, JPEG, Azure Blob Storage

## About

About 2.5 million trail camera images from many projects across New Zealand, run by various organisations in diverse habitats with a range of camera brands. Most images were labeled by project staff and verified by volunteers. LILA states labels for 110 categories, primarily species; the most common are mouse (49% of images), possum (6.7%) and rat (5.5%), relevant to invasive predator control and Predator Free 2050 work, alongside native birds such as yellow-eyed penguin. Labels are in COCO Camera Traps JSON (open with json, pandas or pycocotools); species also appear in folder names and location identifiers in the EXIF ImageDescription tag. Layout (measured 2026-11-13): 57 unzipped project folders by three-letter code (e.g. AIV/, KCR/, WLG/), each with per-species subfolders (AIV/cat/, AIV/sealion/) of JPEG files, plus a 144 MB COCO metadata zip and a category list. Images are loose files, not zip archives, so they can be read directly on the read-only mount. Use for invasive species detection (stoat, rat, possum, cat) and species classification. 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/nz-trailcams/')[:10]
```

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

## Data structure

File types in sampled files: JPEG

Example file: `ACC/banded_rail/0067A52A-FB22-4CB4-B54A-1894E7F2B1A5.JPG`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/dd01ec07-5481-56c0-a54c-c2d46afe4f0a
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/dd01ec07-5481-56c0-a54c-c2d46afe4f0a
- Over MCP: `get_schema_card` with id `dd01ec07-5481-56c0-a54c-c2d46afe4f0a` at https://api.scigantic.com/mcp

## Related topics

- [Environmental Science datasets](https://scigantic.com/topics/environmental-science)
- [JPEG datasets](https://scigantic.com/topics/jpeg)
