Rapeseed Leaf Estimation Methods at Field Scale by Using Terrestrial LiDAR Point Cloud

Exploring the key technologies of agricultural robots is an inevitable trend in development smart agriculture. It significant to continuously transplant and develop novel algorithms models update that use light detection ranging (LiDAR) as a remote sensing method. This paper implements method for extracting estimating rapeseed leaves through based on LiDAR point cloud, taking leaf area (LA) measurement example. Firstly, three-dimensional (3D) cloud obtained with terrestrial laser scanner (TLS) were used extract crop phenotypic information. We then imported within study into custom hybrid filter, from which was segmented. Finally, new LA estimation model, Delaunay triangulation (DT) algorithm proposed, namely, LA-DT. In this study, canopy analyzer, LAI-2200C, measure farmland. The measured values employed standard compare calculated results using LA-DT, differences between two methods 3%. addition, 100 individual crops extracted, output LA-DT model subjected linear regression analysis. R² equation 0.93. outputs LAI-2200C these experiments passed paired samples t-test correlation (p < 0.01). All comparison verification showed has excellent performance parameters under complex environments. These help coping working environment special objects robots. great significance expanding interpretation 3D