Detection of Plant Diseases in an Industrial Greenhouse: Development, Validation & Exploitation
Bibliographic record
Abstract
The effective detection of plant diseases is crucial for the optimal management of agricultural systems. In this paper, we present our contributions in the context of detecting plant diseases in an industrial greenhouse [1], focusing specifically on tomatoes. Our main objectives are to develop and validate a detection system using the YOLOv8 model and to explore its potential for practical application in a real-world setting. To facilitate our research, we introduce a novel dataset comprising images of tomato leaves affected by various diseases. This dataset serves as a valuable resource for training and evaluating our detection model. We employ the YOLOv8 architecture, a state-of-the-art object detection framework, and experiment with different parameters to assess its performance in accurately detecting diseased areas on tomato leaves. Through extensive experimentation, we compare the performance of the YOLOv8 model using various parameters, such as different training strategies, data augmentation techniques, and hyperparameter configurations. The results provide insights into the optimal settings for achieving high detection accuracy and robustness. Furthermore, we demonstrate the practical utility of our developed model by conducting a real-life implementation within an industrial green-house. This exemplifies the integration of our detection system into an operational environment, showcasing its potential to assist greenhouse operators in early disease detection, monitoring, and decision-making processes. Our preliminary findings demonstrate promising disease detection capabilities on tomato leaves inside greenhouses, achieving an mAP50 score of 0.8 using our best model. Although there is room for improvement, these initial results indicate significant potential.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".