Measuring Canopy Geometric Structure for Crop Yield Estimation Using PCA-Driven Machine Learning Models with Hyperspectral Images
K. Sudharshan, Ahmad al-qerem, P Yakaiah, K M Rayudu, V Revathi, A Shanthipriya
Zarqa University New Horizon College of Engineering Rajalakshmi Engineering College
阅读操作
确认中在文库中上传 PDF 后可生成中文音频讲解。
摘要与影响
The Canopy Geometric Structure for Crop Yield Estimation Using PCA-Driven Machine Learning Models with Hyperspectral Images (CGCPMH) utilizes UAV-mounted hyperspectral imagery for estimating plant biomass and evaluating vegetation. The approach involves a preprocessing pipeline that improves image quality and segmentation through CIELAB color space transformation. Principal Component Analysis (PCA) facilitates data dimensionality reduction, enabling extraction of key spectral features relevant to soil moisture. Precision canopy monitoring is accomplished through voxel-based 3D modeling. This methodology supports decision-making in precision agriculture, providing a framework for sustainable practices in Unmanned Aerial Vehicles (UAVs). The following specifications spike weight and plant height analysis, gain weight analysis, error estimation, RMSE, and MAE calculations.
逐年被引趋势
暂无年度引用数据
关键指标
同类平均 = 1
同领域 · 同年份 · 同类型
Google Scholar 与 OpenAlex 的被引统计范围不同,数值存在差异属正常。
AI 辅助阅读
依据:摘要
可就本文提问;依据不足时会说明。
学术脉络
学科主题
物理Remote Sensing in Agriculture
Smart Agriculture and AI · Remote-Sensing Image Classification
参考文献 14
此处列出前 3 条