BeeWhere: Segmenting Bumble Bee Colonies to Quantify Behavioral Effects

2026-10-02

AI Summary

This study addresses the challenge of scalable, precise quantification of individual and collective behaviors in densely clustered social bees. We propose an AI-assisted analytical workflow integrating ArUco markers with deep learning-based instance segmentation. Methodologically, a YOLO instance segmentation model combined with ArUco detection enables high-precision tracking, while spatial metrics are extracted from body contours to effectively overcome the performance bottlenecks of conventional tagging under severe occlusion. The proposed approach significantly improves individual detection rates in heavily occluded environments and successfully captures pesticide-induced alterations in colony spatial organization. By delivering a reliable, automated analytical paradigm, this work provides a valuable methodological framework for research in ecotoxicology and collective animal behavior.

Abstract

Social bees are important pollinators that support biodiversity and crop pollination globally and serve as important model systems for collective behavior, but scalable measurement of individual- and colony-level behavior remains difficult in dense, occluded nest environments. Existing monitoring workflows use fiducial tags (e.g., ArUco) to preserve individual identity, yet tag-based tracking can fail when markers are obscured and provide limited information about body extent, spatial context, and untagged individuals. We present BeeWhere, an AI-assisted annotation and analysis workflow that combines ArUco detections with deep-learnt instance segmentations to quantify bumble bee behavior from high-resolution colony images and videos. Using bumble bee (Bombus impatiens) microcolonies as a test case, we annotate 483 frames containing 8,443 bee instances. We additionally annotate pollen balls, nest structures, and chamber boundaries, and train YOLO instance segmentation models for downstream behavioral analysis. Instance segmentations enable quantification of important behavioral metrics based on body contours, including nearest-neighbor distance, proximity to nest structures, spatial occupancy within the nest, and detection counts over time. We apply the BeeWhere models to tag-based tracking in an exploratory validation study assessing the behavioral impacts of neonicotinoid pesticide exposure. BeeWhere increased detection rates compared to tag-based tracking, particularly when bees were partially obscured or under challenging imaging conditions, and also captured treatment-associated changes in bee spatial organization not captured using tag-based tracking alone. These results suggest that instance segmentation can complement fiducial-marker tracking by recovering behaviorally meaningful signals under challenging colony conditions.

Problem

• instance segmentation
• bumble bee behavior
• colony monitoring
• occlusion
• fiducial tracking

Innovation

• Instance Segmentation
• Behavioral Quantification
• ArUco Detection
• YOLO
• Social Bees