SWG Camera Traps 2018-2020 (Northern and Central Annamites, Vietnam and Laos)

Provider
IUCN SSC Asian Wild Cattle Specialist Group's Saola Working Group
License
CDLA-Permissive-1.0 (source)
Stored at
Azure Blob Storage, https://lilawildlife.blob.core.windows.net/lila-wildlife/swg-camera-traps
Access
Free and public. No account with the data provider is needed.
Category
Environmental Science
Source
https://lila.science/datasets/swg-camera-traps

About SWG Camera Traps 2018-2020 (Northern and Central Annamites, Vietnam and Laos)

Camera trap images from 982 locations in the Annamite mountains of Vietnam and Laos, provided by the Saola Working Group with Asian Arks, WCS Lao, WWF Lao, the ICBF project and Vinh University. LILA states 436,617 sequences totaling 2,039,657 images, labels for 120 categories (most common Eurasian wild pig, large-antlered muntjac and unidentified murid), about 13% empty, and 101,659 bounding boxes on 88,135 images. Human images were removed. Labels are in COCO Camera Traps JSON (open with json, pandas or pycocotools); separate zips hold class labels and bounding boxes with and without species. Layout (measured 2026-11-13): images are unzipped JPEG folders under public/lao/ and public/vietnam/ organised by location and date; the top-level zips (62 MB and two of 7 MB) and archive/ hold only metadata, so the images themselves are not zipped and read directly from the read-only mount. Useful for tropical forest biodiversity, Annamite endemics, saola monitoring and geographic domain shift in species classifiers. Released by LILA BC under the Community Data License Agreement (permissive variant), CDLA-Permissive-1.0; cite SWG (2021), Northern and Central Annamites Camera Traps 2.0.

How to access this dataset in Python

import adlfs
fs = adlfs.AzureBlobFileSystem(account_name='lilawildlife', anon=True)
fs.ls('lila-wildlife/swg-camera-traps/')[:10]

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

Data structure

Files

Example file: archive/swg_camera_traps_1.0.json.zip

Analyze this dataset without downloading it

On Scigantic, SWG Camera Traps 2018-2020 (Northern and Central Annamites, Vietnam and Laos) opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.

This page is also available as Markdown and as JSON.

Related Environmental Science datasets