Markerless tracking of an entire insect colony
Katarzyna Bozek, Laetitia Hebert, Yoann Portugal, Greg J. Stephens
Received Date: 22nd April 20
We 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. We adapt a convolutional neural network (CNN) segmentation architecture to automatically identify bee and brood cell positions, body orientations and within-cell states. We achieve high accuracy (~10% body width error in position, ~10° error in orientation, and true positive rate > 90%) and demonstrate months-long monitoring of sociometric colony fluctuations. We combine extracted positions with rich 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 a span of 5 minutes. We use the resulting trajectories to discover a surprising negative correlation between brood and total population fluctuations and to identify important individual behaviors, including waggle dances and those related to comb activities which are difficult to detect in tagged systems. Our results provide new opportunities for the quantitative study of collective bee behavior and for advancing tracking techniques of crowded systems.
Read in full at bioRxiv.
This is an abstract of a preprint hosted on an independent third party site. It has not been peer reviewed but is currently under consideration at Nature Communications.