Technological Advancements in Greenhouse Production: YOLO-Based Plant Recognition Under Greenhouse Conditions
| dc.contributor.author | BOULARABI Houda Rahil | |
| dc.date.accessioned | 2025-05-05T14:18:38Z | |
| dc.date.available | 2025-05-05T14:18:38Z | |
| dc.date.issued | 2024-07-04 | |
| dc.description.abstract | This study explores the application of the YOLO deep learning-based object detection framework to identify three critical agricultural crops—tomatoes, peppers, and eggplants—under greenhouse conditions. The project entailed growing these crops, gathering specific data for each, building a ground truth dataset, and training a YOLO v8 model on the Kaggle platform. The model achieved a mAP50 of 0.70 and a mAP50-90 with a recall of 0.56. The research aims to automate and enhance the crop detection process in agricultural environments using YOLO v8's accurate, real-time monitoring capabilities. By incorporating deep learning techniques, this work contributes to advancing precision agriculture practices, optimizing resource management, and improving yield prediction and management for tomato, pepper, and eggplant cultivation. Additionally, this study addresses specific challenges related to plant recognition under varying conditions and proposes innovative solutions to overcome these obstacles. Ultimately, the results support the development of sustainable agricultural systems, increasing farm resilience to climate change and environmental stress. | |
| dc.identifier.uri | http://dspace.ensa.dz/handle/123456789/3861 | |
| dc.language.iso | en | |
| dc.subject | Deep learning | |
| dc.subject | Object detection | |
| dc.subject | YOLO v8 | |
| dc.subject | Real-time monitoring | |
| dc.subject | Precision agriculture | |
| dc.subject | Plant recognition | |
| dc.subject | Sustainable agriculture | |
| dc.subject | Greenhouse production | |
| dc.title | Technological Advancements in Greenhouse Production: YOLO-Based Plant Recognition Under Greenhouse Conditions | |
| dc.type | Thesis |