SegNeXt-RCMSCA: An improved SegNeXt network for detecting winter wheat lodging from UAS RGB images
Bibliographic record
Abstract
Winter wheat lodging reduces wheat yield and poses a further risk to regional food security, emphasizing the need for timely and accurately monitoring of affected areas. Advances in Unmanned Aerial System (UAS) remote sensing and deep learning techniques provide new tools for detecting winter wheat lodging. In this study, the RGB images of winter wheat were captured by the DJI Phantom 4 Pro V2.0 at flight heights of 60 m (0.8cm/pixel), 90 m (1.8cm/pixel), 120 m (3.1cm/pixel), and 150 m (4.3cm/pixel). A novel SegNeXt-RCMSCA network was proposed by integrating horizontal and vertical pooling with a multi-scale self-calibrated convolution function to enhance global contextual information. The SegNeXt-RCMSCA model achieved an Intersection over Union (IoU) of 86.72 %, F1 score of 92.89 %, Recall of 94.33 %, and Precision of 91.49 %. The model was tested using images with different spatial resolutions, and the results indicated that the 60 m (0.8cm/pixel) achieved the highest detection accuracy. The proposed SegNeXt-RCMSCA demonstrated strong potential for detecting lodging in other crops, offering a robust tool for improving the crop management in precision agriculture. By enabling timely and accurately lodging detection, the model facilitates crop damage assessment, harvest optimization, and informed field management, while supporting large-scale agricultural monitoring and intelligent decision-making in precision farming.
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) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 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".