Completing 3D Point Clouds of Thin Corn Leaves for Phenotyping Using 3D Gridding Convolutional Neural Networks

被引：2

作者：

Zhang, Ying ^{[1
,2
]}

Su, Wei ^{[1
,2
]}

Tao, Wancheng ^{[1
,2
]}

Li, Ziqian ^{[1
,2
]}

Huang, Xianda ^{[1
,2
]}

Zhang, Ziyue ^{[1
,2
]}

Xiong, Caisen ^{[1
,2
]}

机构：

[1] China Agr Univ, Coll Land Sci & Technol, Beijing 100083, Peoples R China

[2] Minist Agr, Key Lab Remote Sensing Agrihazards, Beijing 100083, Peoples R China

来源：

REMOTE SENSING | 2023年 / 15卷 / 22期

基金：

中国国家自然科学基金;

关键词：

completion; point cloud; 3D gridding convolutional neural networks; multi-scale fusion; offset-attention; deep learning; thin corn leaves; SHAPE;

D O I：

10.3390/rs15225289

中图分类号：

X [环境科学、安全科学];

学科分类号：

08 ; 0830 ;

摘要：

Estimating the complete 3D points of crop plants from incomplete points is vital for phenotyping and smart agriculture management. Compared with the completion of regular man-made objects such as airplanes, chairs, and desks, the completion of corn plant points is more difficult for thin, curled, and irregular corn leaves. This study focuses on MSGRNet+OA, which is based on GRNet, to complete a 3D point cloud of thin corn plants. The developed MSGRNet+OA was accompanied by gridding, multi-scale 3DCNN, gridding reverse, cubic feature sampling, and offset-attention. In this paper, we propose the introduction of a 3D grid as an intermediate representation to regularize the unorganized point cloud, use multi-scale predictive fusion to utilize global information at different scales, and model the geometric features by adding offset-attention to compute the point position offsets. These techniques enable the network to exhibit good adaptability and robustness in dealing with irregular and varying point cloud structures. The accuracy assessment results show that the accuracy of completion using MSGRNet+OA is superlative, with a CD (x10-4) of 1.258 and an F-Score@1% of 0.843. MSGRNet+OA is the most effective when compared with other networks (PCN, shape inversion, the original GRNet, SeedFormer, and PMP-Net++), and it improves the accuracy of the CD (x10-4)/F-Score@1% with -15.882/0.404, -15.96/0.450, -0.181/0.018, -1.852/0.274, and -1.471/0.203, respectively. These results reveal that the developed MSGRNet+OA can be used to complete a 3D point cloud of thin corn leaves for phenotyping.

引用

页数：24