Improved Detection of Urtica Dioica Weeds in Agricultural Fields Using YOLOv5 with Enhanced Non-Maximum Suppression
Bibliographic record
Abstract
This study presents an enhanced deep learning approach for detecting Urtica weed plants using the YOLOv5 object detection model integrated with an Enhanced Non-Maximum Suppression (ENMS) algorithm. The proposed ENMS+YOLOv5 model addresses key challenges in dense vegetation, particularly overlapping instances and fine-grained morphological variations. A comprehensive evaluation was conducted using a dataset of Urtica weed plants across four growth stages—early, young, mature, and flowering—under varying environmental conditions. Performance metrics including True Positive Rate (TPR), False Negative Rate (FNR), Accuracy, and Intersection over Union (IoU) were used to benchmark the proposed model against baseline detectors such as DetectNet, AlexNet, SSD, and NMS+DLN. The ENMS+YOLOv5 model achieved an overall classification accuracy of 90.77%, the highest IoU of 91.21%, and the lowest FNR of 3.42%, demonstrating superior localization and detection performance. Visual analyses further confirmed the model’s robustness to occlusion, scale variation, and lighting conditions. These results suggest that the proposed method is highly effective for automated Urtica weed detection and holds significant potential for precision agriculture applications.
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) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| 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".