# Orinoquia Camera Traps (Colombia)

## Facts

- Provider: Juliana Velez et al.
- License: CDLA-Permissive-1.0 (https://lila.science/datasets/orinoquia-camera-traps/)
- Format: JPEG (in sampled files)
- Stored at: Azure Blob Storage, https://lilawildlife.blob.core.windows.net/lila-wildlife/orinoquia-camera-traps
- Access: public, readable without an account
- Category: Environmental Science
- Source: https://lila.science/datasets/orinoquia-camera-traps/
- Page: https://scigantic.com/archive/67c33539-d0e4-5cd8-b508-013357335952
- Keywords: Environmental Science, camera traps, JPEG, Azure Blob Storage

## About

104,782 images from a 50-camera array deployed January to July 2020 in the El Rey Zamuro and Las Unamas private reserves, Meta department, Orinoquia region of Colombia. Cameras were placed by stratified random design across forest core strata, 1 km apart on wildlife trails without bait, and images were reviewed by experts on Wildlife Insights. LILA states 51 classes, mostly mammals such as collared peccary, black agouti, spotted paca, white-lipped peccary, lowland tapir and giant anteater, with about 20% empty; human images were removed. The data were used to compare Wildlife Insights, MegaDetector and MLWIC2. Labels are in COCO Camera Traps JSON (open with json, pandas or pycocotools). Layout (measured 2026-11-13): unzipped JPEG images under public/ in one folder per camera (A01/, M00/ and so on), plus a 77.3 GB image zip and a 2 MB metadata zip. Individual images are present unzipped, so the read-only mount serves them directly. Released by LILA BC under the Community Data License Agreement (permissive variant), CDLA-Permissive-1.0; cite Velez et al., Methods in Ecology and Evolution 2023.

## Load the data

```python
import adlfs
fs = adlfs.AzureBlobFileSystem(account_name='lilawildlife', anon=True)
fs.ls('lila-wildlife/orinoquia-camera-traps/')[: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: `public/A01/01090079.JPG`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/67c33539-d0e4-5cd8-b508-013357335952
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/67c33539-d0e4-5cd8-b508-013357335952
- Over MCP: `get_schema_card` with id `67c33539-d0e4-5cd8-b508-013357335952` at https://api.scigantic.com/mcp

## Related topics

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