Research library

Markerless tracking of an entire honey bee colony

From cells in tissue, to bird flocks, to human crowds, living systems display a stunning variety of collective behaviors. Yet quantifying such phenomena first requires tracking a significant fraction of the group members in natural conditions — a substantial and ongoing challenge. The authors present a comprehensive, computational method for tracking an entire colony of the honey bee *Apis mellifera* using high-resolution video on a natural honeycomb background. A convolutional neural network (CNN) segmentation architecture is adapted to automatically identify bee and brood cell positions, body orientations, and within-cell states. The method achieves high accuracy (~10% body width error in position, ~10° error in orientation, and true positive rate > 90%) and demonstrates months-long monitoring of sociometric colony fluctuations. These fluctuations include ~24 h cycles in counted detections, negative correlation between bee and brood, and nightly enhancement of bees inside comb cells. Detected positions are combined with visual features of organism-centered images to track individuals over time and through challenging occluding events, recovering ~79% of bee trajectories from five observation hives over 5-min timespans. The trajectories reveal important individual behaviors including waggle dances and crawling inside comb cells.