REAL-TIME IMAGE-BASED MONITORING OF CHILLI PLANT MATURATION USING OBJECT DETECTION TECHNIQUES

Abstract

Chilli crop monitoring plays a vital role in maximizing harvest, ensuring quality, and determining market willingness. Traditional manual approaches to judging crop maturity are labor-intensive and prone to error because of human involvement. Advancements in AI-driven technologies have allowed for efficient and accurate crop monitoring. This study proposed a Deep learning image-based monitoring framework for using advanced object detection techniques (YOLOV11 model) due to its superior performance in speed and accuracy in real- time object detection. The proposed system is designed to help farmers make informed yield decisions, thereby minimizing post-harvest losses and enhancing profitability, achieving a validation accuracy of 98.4%. Results show the robustness and practicality of the model for precision agriculture applications.

Key words: Chilli crops monitoring, Object detection, Deep learning, Yolo, Real-time object detection