Towards Automatic Honey Bee Flower-Patch Assays with Paint Marking Re-Identification
This work addresses the need for lightweight, automated monitoring of honey bee behavior in field studies, though it is incremental in applying existing methods to a new domain-specific dataset.
The paper tackled the problem of automating honey bee behavioral assays by using paint markings for re-identification, achieving almost perfect recognition in a closed setting with a dataset of 4392 images and 27 identities.
In this paper, we show that paint markings are a feasible approach to automatize the analysis of behavioral assays involving honey bees in the field where marking has to be as lightweight as possible. We contribute a novel dataset for bees re-identification with paint-markings with 4392 images and 27 identities. Contrastive learning with a ResNet backbone and triplet loss led to identity representation features with almost perfect recognition in closed setting where identities are known in advance. Diverse experiments evaluate the capability to generalize to separate IDs, and show the impact of using different body parts for identification, such as using the unmarked abdomen only. In addition, we show the potential to fully automate the visit detection and provide preliminary results of compute time for future real-time deployment in the field on an edge device.