Snapshot Safari South Africa and Kenya Reserves (Karoo, Kgalagadi, Enonkishu, Camdeboo, Mountain Zebra, Kruger)
- Provider
- Snapshot Safari (University of Minnesota)
- License
- CDLA-Permissive-1.0 (source)
- Format
- JPEG (in sampled files)
- Stored at
- Azure Blob Storage, https://lilawildlife.blob.core.windows.net/lila-wildlife/snapshot-safari
- Access
- Free and public. No account with the data provider is needed.
- Category
- Environmental Science
- Source
- https://lila.science/datasets/snapshot-karoo
About this dataset
Six per-reserve camera trap releases from the Snapshot Safari network, which applies one protocol across African protected areas. LILA states: Snapshot Karoo 38,074 images (38 categories, about 83% empty); Kgalagadi 10,222 images (31 categories); Enonkishu, Kenya, 28,544 images (39 categories); Camdeboo 30,227 images (43 categories); Mountain Zebra 73,034 images (54 categories, home of the largest Cape mountain zebra population); Kruger 10,072 images (46 categories). Common labels include gemsbok, kudu, springbok, impala, elephant and zebra; human images were removed. Annotations are COCO Camera Traps JSON plus CSV, reliable at sequence level (pandas, pycocotools). Layout (measured 2026-11-13): one folder per reserve (CDB, ENO, KAR, KGA, KRU, MTZ); in KAR, for example, unzipped images sit under KAR_public/KAR_S1/ next to a 43.3 GB KAR_S1.lila.zip and the JSON, CSV and species list. The unzipped folders read directly from the read-only mount. Released by LILA BC under the Community Data License Agreement (permissive variant), CDLA-Permissive-1.0.
How to access this dataset in Python
import adlfs
fs = adlfs.AzureBlobFileSystem(account_name='lilawildlife', anon=True)
fs.ls('lila-wildlife/snapshot-safari/')[:10]Lists the files with anonymous access. Runs on any machine, with no cloud account.
Data structure
File types in sampled files: JPEG
Files
Example file: CDB/CDB_public/CDB_S1/A05/A05_R1/CDB_S1_A05_R1_IMAG0007.JPG
Analyze this dataset without downloading it
On Scigantic, Snapshot Safari South Africa and Kenya Reserves (Karoo, Kgalagadi, Enonkishu, Camdeboo, Mountain Zebra, Kruger) 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
- The Wilds bioacoustic monitors: passive acoustic recordings, Ohio, summer 2025
- Japanese Vegetation Map (1/25,000)
- NASA Low-Cost Sensor AQ Project
- Missouri Camera Traps
- NOAA Arctic Seals 2019 (Kotzebue aerial RGB and thermal)
- Africa Soil Information Service (AfSIS) Soil Chemistry
- USFS Forest Activity Tracking System (FACTS)
- Archival Tag Depth and Temperature Records from Pacific Cod, Kodiak and Eastern Bering Sea, 2001-2005