Yolo Object Detection Models Can Locate And Classify Broad Groups Of Flower-visiting Arthropods In Images

This article discusses the development of image recognition AI algorithms for flower-visiting arthropods, which has the potential to revolutionize the way we monitor pollinators. Three deep learning light-weight models, YOLOv5nano, YOLOv5small, and YOLOv7tiny, were tested for object recognition and classification in real time on eight groups of flower-visiting arthropods. All three models had high accuracy, ranging from 93 to 97%. The model could accurately distinguish flies in the family Syrphidae from the Hymenoptera that they are known to mimic, showing the capability of existing YOLO models to contribute to pollination monitoring.