Boxes on Bees and Pollen (BeeLivingSensor)
- Provider
- BeeLivingSensor project
- License
- CDLA-Permissive-1.0 (source)
- Stored at
- Azure Blob Storage, https://lilawildlife.blob.core.windows.net/lila-wildlife/boxes-on-bees
- Access
- Free and public. No account with the data provider is needed.
- Category
- Environmental Science
- Source
- https://lila.science/datasets/boxes-on-bees-and-pollen
About Boxes on Bees and Pollen (BeeLivingSensor)
About 5,000 images of honey bees at hive entrances annotated with bounding boxes on bees and on the pollen loads they carry, about 50,000 annotations in total, from the BeeLivingSensor project, which tracks bees non-invasively and analyses pollen colour to estimate plant biodiversity around hives. LILA states the zipfile holds 4,993 JPEG images, each with a Pascal VOC XML annotation file of the same name (objects such as bee with xmin, ymin, xmax, ymax); parse them with xml.etree or torchvision VOC tools. Layout (measured 2026-11-13): the folder contains a single archive, boxes-on-bees-2021.zip (2.1 GB); the images are not unzipped in the container, so on the read-only mount copy the zip to local disk and extract it first. Use for pollinator monitoring, bee and pollen object detection, and hive-entrance video analysis. Released by LILA BC under the Community Data License Agreement (permissive variant), CDLA-Permissive-1.0; cite Noninvasive bee tracking in videos: deep learning algorithms and cloud platform design specifications, Dataset, 2021.
How to access Boxes on Bees and Pollen (BeeLivingSensor) in Python
import adlfs
fs = adlfs.AzureBlobFileSystem(account_name='lilawildlife', anon=True)
fs.ls('lila-wildlife/boxes-on-bees/')[:10]Lists the files with anonymous access. Runs on any machine, with no cloud account.
Data structure
Files
Example file: boxes-on-bees-2021.zip
Analyze this dataset without downloading it
On Scigantic, Boxes on Bees and Pollen (BeeLivingSensor) 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
- CanadaFireSat Raw: Sentinel-2, ERA5-Land and MODIS Predictor Archives for High-Resolution Wildfire Forecasting in Canada
- SelvaBox: 83,000 Tropical Tree Crown Bounding Boxes on 4.5 cm Drone Orthomosaics from Brazil, Ecuador and Panama (CanopyRS)
- Mangrove Aboveground and Belowground Biomass and Soil Carbon Stocks in Côte d’Ivoire (Fresco and Sassandra) with Sentinel-1 and Sentinel-2 Bands (data354)
- BIRDeep Audio Annotations: Expert-Labeled Bird Song Recordings from AudioMoth Recorders in Doñana National Park, Spain (EBD-CSIC and Universidad de Córdoba)
- Moorings - Estuarine and coastal water quality monitoring - Near real time
- DEA Fuel Moisture Content (Sentinel-2, Australia)
- NEON Tree Crowns, DeepTreeAttention Edition: 41,738 Species-Labelled Crowns at 38 NEON Sites
- GLOBIO 4 Terrestrial Mean Species Abundance (MSA) Biodiversity Intactness, 2015 and SSP 2050 Scenarios