ENHANCING OIL PALM FRUIT DETECTION: A COMPARATIVE ANALYSIS OF YOLO ALGORITHMS

Abstract

The oil palm industry is pivotal in agricultural research because of its importance. The central focus of this study, however, revolves around elevating cutting-edge intelligent techniques in agriculture, specifically for the improved detection of Fresh Fruit Bunches within oil palm plantations. Moreover, Malaysia’s economic impact on oil palm production is explored, emphasizing its position as a leading producer and exporter of palm oil. The study compares and corroborates the performances among a series of YOLO algorithm models, namely YOLOv3, YOLOv4, YOLOv7, and YOLOv8, by exploiting diverse essential metrics that embrace mean Average Precision, precision, recall, and F1-score. Through the rigorous evaluations of these models, the research contributes to the precision agricultural field, underscoring the superior performance of YOLOv8 in accurately detecting FFBs and facilitating its realization of advanced computer vision techniques for optimal oil palm plantation management and enhanced productivity.