Enhanced yolo based detection models for precise crop monitoring

Abstract

Precision agriculture has become a critical innovation in modern newlinefarming, offering solutions that enhance crop yield and sustainability by newlineemploying advanced technologies. By integrating machine learning and deep newlinelearning methods, farmers can make real-time decisions that directly impact newlineproductivity. Turmeric farming faces many challenges like plant diseases, newlinepests and weeds which significantly affect the yield of crop. Traditional newlinemanual methods are inefficient and need more human cost. The application of newlinedeep learning models, particularly You Only Look Once (YOLO) algorithms newlineknown for its high speed and accuracy, offers a promising approach for newlineaddressing these challenges. By processing entire images in the single pass, newlineYOLO enables rapid identification of diseases, pest and weeds that allows newlinefarmers to take immediate corrective actions. newlineThis research aims to propose YOLO based detection algorithms to newlineincrease turmeric yield through real time analysis of dataset which are newlinecollected from fields. The main objective is to develop accurate systems that newlinedetect diseases, pests and weeds in turmeric crops to minimize the damage. newlineHigh quality datasets are essential for effective deep learning models. Larger newlinedatasets can significantly enhance object detection accuracy and overall newlineperformance. newline