LodgeNet: an automated framework for precise detection and classification of wheat lodging severity levels in precision farming
Bibliographic record
Abstract
Wheat lodging is a serious problem affecting grain yield, plant health, and grain quality. Addressing the lodging issue in wheat is a desirable task in breeding programs. Precise detection of lodging levels during wheat screening can aid in selecting lines with resistance to lodging. Traditional approaches to phenotype lodging rely on manual data collection from field plots, which are slow and laborious, and can introduce errors and bias. This paper presents a framework called 'LodgeNet,' that facilitates wheat lodging detection. Using Unmanned Aerial Vehicles (UAVs) and Deep Learning (DL), LodgeNet improves traditional methods of detecting lodging with more precision and efficiency. Using a dataset of 2000 multi-spectral images of wheat plots, we have developed a novel image registration technique that aligns the different bands of multi-spectral images. This approach allows the creation of comprehensive RGB images, enhancing the detection and classification of wheat lodging. We have employed advanced image enhancement techniques to improve image quality, highlighting the important features of wheat lodging detection. We combined three color enhancement transformations into two presets for image refinement. The first preset, 'Haze & Gamma Adjustment,' minimize atmospheric haze and adjusts the gamma, while the second, 'Stretching Contrast Limits,' extends the contrast of the RGB image by calculating and applying the upper and lower limits of each band. LodgeNet, which relies on the state-of-the-art YOLOv8 deep learning algorithm, could detect and classify wheat lodging severity levels ranging from no lodging (Class 1) to severe lodging (Class 9). The results show the mean Average Precision (mAP) of 0.952% @0.5 and 0.641% @0.50-0.95 in classifying wheat lodging severity levels. LodgeNet promises an efficient and automated high-throughput solution for real-time crop monitoring of wheat lodging severity levels in the field.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| 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) | 0.000 | 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 teacher head, 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".