AUTHOR=Rodriguez Iván F. , Chan Jeffrey , Alvarez Rios Manuel , Branson Kristin , Agosto-Rivera José L. , Giray Tugrul , Mégret Rémi TITLE=Automated Video Monitoring of Unmarked and Marked Honey Bees at the Hive Entrance JOURNAL=Frontiers in Computer Science VOLUME=3 YEAR=2022 URL=https://www.frontiersin.org/journals/computer-science/articles/10.3389/fcomp.2021.769338 DOI=10.3389/fcomp.2021.769338 ISSN=2624-9898 ABSTRACT=

We present a novel system for the automatic video monitoring of honey bee foraging activity at the hive entrance. This monitoring system is built upon convolutional neural networks that perform multiple animal pose estimation without the need for marking. This precise detection of honey bee body parts is a key element of the system to provide detection of entrance and exit events at the entrance of the hive including accurate pollen detection. A detailed evaluation of the quality of the detection and a study of the effect of the parameters are presented. The complete system also integrates identification of barcode marked bees, which enables the monitoring at both aggregate and individual levels. The results obtained on multiple days of video recordings show the applicability of the approach for large-scale deployment. This is an important step forward for the understanding of complex behaviors exhibited by honey bees and the automatic assessment of colony health.