Fusion of Low-Density LiDAR Data with RGB Images for Plant 3D Modeling

Plant architecture is defined as the three-dimensional modeling of the plant's morphology for extracting relevant phenological traits. Most applications rely on expensive high-density LiDAR devices for enabling high-throughput mapping. In this paper, we explore the use of low-cost LiDAR equipment by using a sensor fusion approach. The proposed method is based on the fusion of LiDAR-acquired low resolution 3D point cloud data with high resolution 2D imagery. We use an extrinsic calibration method that requires oversampling to enhance the data fusion from both sensors. As a result, we increased the resolution of the output 3D model of the plant.