Biological Physics Theory Unit, OIST Graduate University, Okinawa, Japan.
University of Cologne, Center for Molecular Medicine Cologne (CMMC), Faculty of Medicine and University Hospital Cologne, Cologne, Germany.
Nat Commun. 2021 Mar 19;12(1):1733. doi: 10.1038/s41467-021-21769-1.
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. 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. These fluctuations include ~24 h cycles in the counted detections, negative correlation between bee and brood, and nightly enhancement of bees inside comb cells. We combine detected positions 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. Our results provide opportunities for the quantitative study of collective bee behavior and for advancing tracking techniques of crowded systems.
从组织中的细胞、鸟群到人群，生命系统表现出令人惊叹的各种集体行为。然而，要对这些现象进行量化，首先需要在自然条件下追踪群体中相当一部分成员，这是一个重大且持续的挑战。我们提出了一种全面的、基于计算的方法，使用高分辨率视频在自然蜂巢背景下对整个蜜蜂（Apis mellifera）群体进行追踪。我们改编了卷积神经网络 (CNN) 分割架构，以自动识别蜜蜂和蜂卵细胞的位置、身体方向和细胞内状态。我们实现了高精度（位置误差约为 10%的身体宽度，方向误差约为 10°，真阳性率 > 90%），并演示了长达数月的社会计量群体波动监测。这些波动包括计数检测中的约 24 小时周期、蜜蜂和蜂卵之间的负相关以及夜间蜂箱内蜜蜂数量的增加。我们将检测到的位置与以生物体为中心的图像的视觉特征相结合，以随时间跟踪个体并通过具有挑战性的遮挡事件进行跟踪，从五个观察蜂箱在 5 分钟的时间跨度内恢复了约 79%的蜜蜂轨迹。这些轨迹揭示了重要的个体行为，包括摇摆舞和在蜂巢内爬行。我们的结果为定量研究集体蜜蜂行为提供了机会，并为跟踪拥挤系统的技术提供了进展。
