Weed Detection and Localization in Soybean Crops Using YOLOv4 Deep Learning Model
Bibliographic record
Abstract
In precision agriculture, detection of weed is vital to control or remove it, as the weeds will impact the crop's yield.Also accurately distinguishing weeds and crop and their localization is important, to reduce the herbicides and pesticides usage.Deep learning techniques are effective for classification and detection of these.You Only Look Once v4 (YOLOv4) deep learning architecture is very widely used for object detection and localization of objects in an image.In this work, YOLOv4 is used for detection and localization of weeds in soybean fields.The experiments are done on publicly available soybean and weed dataset containing soybean, grass, broadleaf and soil images, each group having 1000 images.YOLOv4 architecture yielded an accuracy of 98.42%, recall of 93.13% and mAP of 81.24%, better than the performance of R-CNN and SSD networks.Additionally, different pre-trained networks viz., Darknet19, Mobilenetv2, VGG19, Resnet18, Inceptionv3 and Densenet201 are also investigated for classification of weed/crop which yielded an accuracy of 98.75%, 98.9%, 99.25%, 99.25%, 99.42%, 99.58% and 99.67% respectively.For preprocessing of images CLAHE algorithm is used.From different models investigated, it is observed that YOLOv4 is efficient for both classification and detection along with localization.
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 | 0.000 |
| Open science | 0.001 | 0.000 |
| 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".