Automated Sunflower Head Detection and Yield Estimation from High-Resolution UAV Imagery Using YOLOv11 for Precision Agriculture

Traditional methods for assessing sunflower yield across large agricultural fields are typically labor-intensive and time-consuming. This study explores the integration of unmanned aerial vehicle (UAV) imagery and the YOLOv11 deep learning model for automated sunflower head detection and yield estimation. Aerial imagery was collected from sunflower fields using UAVs, and a YOLOv11-based detection model was developed to identify sunflower heads efficiently. Model performance was optimized by tuning the Confidence Threshold and Intersection over Union (IoU) parameters. A total of 1290 image tiles derived from 215 UAV images were used for model training and evaluation. The dataset was divided into training and testing subsets with an 80:20 ratio. The optimal configuration, achieved at a Confidence Threshold of 0.50 and an IoU Threshold of 0.40, yielded balanced and accurate results, including a Precision of 0.84, Recall of 0.95, mAP@0.5 of 0.95, and an F1-score of 0.90. The findings demonstrate that parameter adjustment directly influences model detection accuracy and reliability. Overall, this study confirms that combining UAV remote sensing with YOLOv11 offers a robust and scalable approach for automated sunflower yield estimation, significantly reducing manual effort and processing time. Moreover, the proposed framework can be adapted for other high-value crops, contributing to the advancement of intelligent and data-driven agricultural management systems.