Enhanced Wheat Head Detection in Images Using Fourier Domain Adaptation and Random Guided Filter
Bibliographic record
Abstract
Wheat head detection is essential in estimating the important characteristics of wheat. However, detecting wheat heads in images from different domains has been challenging due to variations in domain features and environmental conditions. This research aims to improve the robustness of wheat head detection in wheat images. A combination of Fourier domain adaptation (FDA), adaptive alpha beta gamma correction (AABG) and random guided filter (RGF) preprocessing methods was applied in this study. The authors utilized FDA to reduce variations between different domains by transforming an image into the Fourier domain, aligning its distribution with a randomly selected image of another domain. AABG adjusts image properties based on local statistics of the image patches, and RGF, a technique for edge-aware image filtering, was used as augmentation. An EfficientDet model was trained on the publicly available wheat dataset and the results were analyzed and compared to a baseline model. The FDA + RGF approach achieved an improved mean average precision (mAP) of 0.6534 compared to the baseline mAP of 0.6292. Our study can contribute to advancing wheat head detection techniques in agriculture, addressing factors like variations in wheat head appearance by focusing on improving domain variation through data dependent approaches.
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".