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