Detection of Spatially Oriented Fusarium Head Blight Spikes in Wheat Using UAV-Based Remote Sensing Imaging
Bibliographic record
Abstract
Fusarium head blight (FHB) poses a critical threat to global wheat production, compromising yield and quality through mycotoxin contamination. Traditional methods, such as laboratory assays and visual inspections, are labour-intensive, costly, and impractical for large-scale monitoring. Although remote sensing based on unmanned aerial vehicles (UAVs) offers a promising alternative, existing approaches using axis-aligned bounding boxes (AABBs) struggle with arbitrary orientations, large aspect ratios, and dense wheat spike arrangements, limiting detection accuracy. To address these challenges, we introduce a UAV-based remote sensing framework for detecting oriented FHB-infected wheat spikes under real field conditions. We propose a novel modified hybrid YOLO architecture for detecting oriented bounding boxes (OBBs) that integrates the efficiency of YOLOv10 with YOLOv11’s orientation-aware detection capabilities. To enhance lesion visibility in UAV images, we utilize pixel-level cubic power stretching, which amplifies the contrast of FHB-infected regions while normalizing overexposed backgrounds. Experimental results demonstrate state-of-the-art performance; for example, our Hybrid-YOLO-x achieves 93.8% mAP@0.5, surpassing YOLOv8x and YOLOv11x by 3.1% and 1.3%, respectively. It reduces parameters by 30.4% (vs. YOLOv8x) and 17.7% (vs. YOLOv11x) while lowering GFLOPs by 28.3% (vs. YOLOv8x) and 7.1% (vs. YOLOv11x). The model also achieves 67.7% mAP @ 0.5–0.95, outperforming YOLOv8x by 4.3% and YOLOv11x by 0.6%. Our hybrid model also outperforms other state-of-the-art OBB detectors, such as S2ANet, ROI-Transformer, R2CNN, utilizing 12.8% fewer parameters and 5.4% lower computational cost.
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) | 0.001 | 0.000 |
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".