A Dual-Channel Pine Wilt Disease Recognition Method with Discrete Wavelet Transform
Bibliographic record
Abstract
Pine wilt disease is a significant global plant epidemic and a management priority for numerous countries worldwide. Pine wood nematodes can parasitize a wide range of pine species, making early detection of infected trees essential for preventing further spread of the disease. Recent advances in deep learning and remote sensing technologies have enabled efficient automated detection of diseased trees. Most existing methods rely on convolutional neural network layers for feature extraction and spatial dimension reduction, which may cause the loss of fine-grained texture details and lead to misdetection of background elements and visually similar objects. To enhance diseased tree recognition accuracy, this paper proposes an object detection model using images captured by unmanned aerial vehicles. The proposed method incorporates discrete wavelet transform (DWT) to reduce spatial resolution while preserving critical information for further analysis, and integrates a cross-modal channel enhancement module within a two-stream feature extraction network. Furthermore, the method incorporates a RoI-based similarity constraint that applies cosine similarity loss and classification supervision to ensure coherent feature representations between processing branches. This approach achieves 89.2% accuracy on the pine wilt disease dataset and outperforms advanced methods on the VisDrone dataset. Several object detection models are compared based on the mean average precision (mAP) metric. Results demonstrate that the DWT-based detection algorithm achieves superior performance in detecting individual small targets and clustered infected pine trees.
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 | 0.001 |
| 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 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".