Lindenthal Camera Traps (RGB-D stereo video)
- Provider
- University of Bonn (Timm Haucke, Volker Steinhage)
- License
- CDLA-Permissive-1.0 (source)
- Stored at
- Azure Blob Storage, https://lilawildlife.blob.core.windows.net/lila-wildlife/lindenthal-camera-traps
- Access
- Free and public. No account with the data provider is needed.
- Category
- Environmental Science
- Source
- https://arxiv.org/abs/2102.05607
About Lindenthal Camera Traps (RGB-D stereo video)
775 video sequences from the Lindenthal wildlife park in Cologne, Germany, recorded for the AMMOD project with an Intel RealSense D435 stereo camera that captures colour or infrared intensity plus depth. Animals include birds by day and deer, goats, sheep, donkeys and foxes mostly at night. Videos are RealSense rosbag files of 15 to 45 seconds at 15 fps; later sequences also store raw left and right IR frames. A subset of 412 images carries 1,038 animal annotations in COCO JSON with instance masks, boxes, class labels and track IDs, with extracted JPEG intensity and OpenEXR depth stills and a Jupyter notebook. Layout (measured 2026-11-13): the folder holds a single archive, lindenthal-camera-traps.zip (213.1 GB); nothing is unzipped, so on the read-only mount copy it to local disk and extract it, then read bags with pyrealsense2 or rosbag and the labels with pycocotools. Use for depth-based wildlife monitoring, RGB-D detection and multi-object tracking. Released by LILA BC under the Community Data License Agreement (permissive variant), CDLA-Permissive-1.0; cite Haucke and Steinhage, arXiv:2102.05607.
How to access Lindenthal Camera Traps (RGB-D stereo video) in Python
import adlfs
fs = adlfs.AzureBlobFileSystem(account_name='lilawildlife', anon=True)
fs.ls('lila-wildlife/lindenthal-camera-traps/')[:10]Lists the files with anonymous access. Runs on any machine, with no cloud account.
Data structure
Files
Example file: lindenthal-camera-traps.zip
Analyze this dataset without downloading it
On Scigantic, Lindenthal Camera Traps (RGB-D stereo video) 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
- Structures Damaged by Wildfire in California 2020-2022: Cal Fire Damage Inspection Images
- Subalpine Coniferous Forest Vegetation Segmentation: 11,336 DJI Mavic 2 Drone Image Chips with Pixel Masks, Wanglang Nature Reserve, China (AgML Mirror)
- Soneva Coral Reef Time-Series Photogrammetry: 23 Co-Registered 3D Surveys of Restoration Plots, Maldives
- Caltech Camera Traps
- SPARTAN Data
- CarbonPlan Climate & Carbon Data
- Forest Typology (ForTy) 2020 v1
- JRC Global Forest Types 2020