Abstract
Ultraviolet (UV)-reflectance is an essential signal of many plant species, which use wavelength-selective pigments in floral reproductive structures to determine the color of flowers and how they appear to their aerial pollinators, primarily bees. This paper presents a pollinator-inspired remote-sensing system incorporating UV reflectance into a flower detector for strawberry crops. We designed a compact, cost-effective UV-sensitive camera for aerial remote sensing over crop rows. Our camera and a deep-learning algorithm comprise our Nature-Inspired Detector (NID) system. We trained YOLOv5 and Faster R-CNN on our dataset of strawberry images incorporating the UV spectrum (300–400 nm). Our results showed that NID-based YOLO V5 outperformed NID-based Faster R-CNN in training time (0.3 vs. 4.5–5.5 hours) and mean Average Precision—mAP (0.951 vs. 0.934). We also present the field-test of our NID-based YOLOv5 system on a drone platform to validate its ability to detect strawberry flowers.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have