Estimation of Crop Height Distribution for Mature Rice Based on a Moving Surface and 3D Point Cloud Elevation

Estimation of rice plant height distribution plays a significant role in keeping the feed rate combine harvesters stable. This is an effective way to guarantee working stability whole machine, as consequence, improving threshing and cleaning efficiency reducing loss damage rates. However, dense growth leafy bent branches mature make it difficult detect lowest point aggregated growing plants three dimensional (3D) cloud data. Therefore, objective this study was put forward method estimate on basis moving surface 3D elevation. The statistical outlier removal (SOR) algorithm used reduce noise points far away from target body, then fitting elevation applied achieve accurate classification ground crop data for estimation. Experiments showed that, compared with actual value, average square root error (RMSE) estimation results 8.29, absolute percentage (MAPE) 9.28%, accuracy 90%. proposed could accurately beneficial calculating advance, which can provide reference further investigation automatic intelligent harvesting.