See as a Bee: UV Sensor for Aerial Strawberry Crop Monitoring
Bibliographic record
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. RÉSUMÉLa réflectance ultraviolette (UV) est un signal essentiel de nombreuses espèces végétales qui utilisent des pigments sélectifs en longueur d'onde dans les structures reproductives florales pour déterminer la couleur des fleurs et leur apparence pour leurs pollinisateurs aériens, principalement les abeilles.Cet article présente un système de télédétection inspiré des pollinisateurs incorporant la réflectance UV dans un détecteur de fleurs pour les cultures de fraises.Nous avons conçu une caméra sensible aux UV compacte et économique pour la télédétection aérienne sur les rangées de cultures.Notre caméra et un algorithme d'apprentissage profond constituent notre système de détection inspiré de la nature (NID).Nous avons entraîné YOLOv5 et Faster R-CNN sur notre ensemble de données d'images de fraises incorporant le specter UV (300-400 nm).Nos résultats ont montré que YOLOv5 pour notre NID surpassait Faster R-CNN en temps d'entraînement (0,3 contre 4,5-5,5 heures) et mAP (0,951 contre 0,934).Nous présentons également une validation sur le terrain de notre système YOLOv5 avec notre NID sur une plateforme aérienne pour valider sa capacité à détecter les fleurs de fraisier.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".