SciSpace

Automatic sugarcane yield estimation using unmanned aerial vehicles (UAVs) is a promising approach for the sugar industry. UAVs equipped with sensors and cameras can capture aerial imagery of sugarcane fields, allowing for the assessment of crop development and yield prediction. Several studies have demonstrated the effectiveness of using UAVs and image analysis techniques for sugarcane yield estimation. Speranza et al. developed a predictive model based on vegetation indices extracted from drone and satellite images, showing reliable results for forecasting productivity months before harvest time [1]. Khuimphukhieo et al. investigated the use of UAVs with RGB cameras to assess sugarcane yield and found significant correlations between canopy features and yield parameters [2]. Barbosa Júnior et al. merged multispectral images and machine learning algorithms to develop a non-invasive, predictive framework for mapping canopy reflectance to sugar quality indicators [3]. These studies highlight the potential of UAV-based imagery and machine learning techniques for accurate and efficient sugarcane yield estimation in the sugar industry.