Strawberry Ripeness Detection: Optimizing Harvesting Efficiency with YOLOv11

Strawberry is one of the popular fruits with numerous nutrients [1]. The recognition and localization of strawberries are fundamental for advancing automated harvesting processes and ensuring accurate yield estimation. [2]. The utilization of highly accurate autonomous systems is indispensable for enhancing quality and efficiency in agricultural production while reducing costs [3]. The high labor costs and declining workforce in strawberry harvesting suggest that harvest robots will be highly efficient in the future. This project employs object detection techniques to determine strawberry ripeness, a critical factor affecting fruit quality and marketability. The aim is to enable harvest robots to perform optimal harvesting at the right time. While automated fruit detection offers significant advantages, complex conditions such as lighting, leaf density, and overlapping strawberries pose challenges. YOLOv11 was used to address these issues, and the harvest robot's AI brain was designed. Comparative analysis with different algorithms identified the most efficient model. The developed AI model can be commercially used by strawberry growers for decision-making and creating fully automated detection systems. This project offers significant advantages, including the ability to achieve accurate and the reliable identification of strawberries, even under real-time operational conditions, thereby minimizing costs associated with manual labor. [4].