1/8/2024 0 Comments Vector 2d beeIn the dense environment of a hive, even when confined to a 2D surface, partial occlusions are common. Moreover, the recognition of markers is hampered by visual occlusions of parts of the tag and image blur. For example, marking newly hatched bees requires either opening the hive or introducing marked newborns without letting any hatch inside, both of which disrupt the colony 13, 18. While a wealth of information can be extracted with the use of tags, the burden of manually tagging hundreds or thousands of small insects, without harm or inhibition to their motion, does carry some limitations. This information together with recognition of individual bee behaviors bring insights into the quantitative understanding of a bee colony. Barcoded tags allow for the distinct marking of a sufficiently large number of individuals to track a naturally sized colony and have been exploited to unravel important aspects of bee communication 12, 18 and information spread 14, 19. These factors present substantial difficulties for automated image analysis 9, 10, 11 for which a common solution is to apply physical tags to some 12 or all 13, 14, 15, 16, 17 of the colony members. Both of these challenges are now accessible through advances in machine vision.Ī honey bee colony contains a high density of visually similar members, rapidly moving and occluding on the uneven and changing honeycomb surface, and whose numbers change in time. However, a full quantitative understanding of the colony behavior requires measuring the collective dynamics at single-organism resolution as well as the spatiotemporal patterns of colony resources such as food and brood. 3), which includes examinations of collective behavior 4, 5 also in combination with high-throughput sampling technologies such as gene expression sequencing 6, 7, 8. A longstanding fascination with such behavior has driven substantial previous work (see e.g., ref. The effect of these dynamics is to cooperatively divide and organize the effort necessary to maintain a well-functioning collective in response to external and internal environmental change, thus enabling the colony to grow and reproduce. Functioning as a “super organism” 1, a honey bee colony can contain thousands of individuals whose intricate behavior results from a shared genetic background and sophisticated social signals conveyed through multiple communication channels 2. Our results provide opportunities for the quantitative study of collective bee behavior and for advancing tracking techniques of crowded systems.Īmong the rich phenomenology of organismal behavior, honey bees and other eusocial animals are distinguished by their remarkable, self-organizing, collective dynamics on the scale of an entire society. The trajectories reveal important individual behaviors, including waggle dances and crawling 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. 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 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 adapt a convolutional neural network (CNN) segmentation architecture to automatically identify bee and brood cell positions, body orientations and within-cell states. 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. Yet quantifying such phenomena first requires tracking a significant fraction of the group members in natural conditions, a substantial and ongoing challenge. From cells in tissue, to bird flocks, to human crowds, living systems display a stunning variety of collective behaviors.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |