Long titles ] Panicle-3 D : Efficient phenotyping tool for precise semantic segmentation of 2 rice panicle point cloud

16 The automated measurement of crop phenotypic parameters is of great significance to 17 the quantitative study of crop growth. The segmentation and classification of crop point 18 cloud help to realize the automation of crop phenotypic parameter measurement. At 19 present, crop spike-shaped point cloud segmentation has problems such as fewer samples, 20 uneven distribution of point clouds, occlusion of stem and spike, disorderly arrangement 21 of point clouds, and lack of targeted network models. The traditional clustering method 22 can realize the segmentation of the plant organ point cloud with relatively independent 23 spatial location, but the accuracy is not acceptable. This paper first builds a desktop-level 24 point cloud scanning apparatus based on a structured-light projection module to facilitate 25 the point cloud acquisition process. Then, the rice ear point cloud was collected, and the 26 rice ear point cloud data set was made. In addition, data argumentation is used to improve 27