Separating the Structural Components of Maize for Field Phenotyping Using Terrestrial LiDAR Data and Deep Convolutional Neural Networks
Separating the Structural Components of Maize for Field Phenotyping Using Terrestrial LiDAR Data and Deep Convolutional Neural Networks
复制标题
使用地面激光雷达数据和深度卷积神经网络分离玉米的结构成分以进行现场表型分析
DOI：
10.1109/tgrs.2019.2953092
复制
发表时间：
2020-04-01
影响因子：
8.2
通讯作者：
Guo, Qinghua
中科院分区：
文献类型：
--
作者：
Jin, Shichao;Su, Yanjun;Guo, Qinghua
分离结构组分对于植物表型分析和精准农业来说很重要，但也具有挑战性。光探测和测距（LiDAR）技术可以通过提供高质量的数据来克服这些困难。然而，在自动分类和分割感兴趣的组件中存在困难。深度学习可以提取复杂的特征，但它主要用于图像。在这里，我们提出了一个基于体素的卷积神经网络（VCNN）的玉米茎叶分类和分割。用地面激光雷达扫描玉米植株的三个不同的生长阶段，体素化的激光雷达数据作为输入。共3000株植物（22 004叶和3000茎）准备通过数据增强训练，和103玉米植物被用来评估在实例和点水平的分类和分割的准确性。将VCNN与传统的聚类方法（$K$ -means和基于密度的空间聚类）、基于几何的分割方法以及最先进的深度学习方法（PointNet和PointNet++）进行了比较。结果表明：1）在实例水平上，分类和分割的平均准确率（F-score）分别为1.00和0.96，2）在点水平上，分类和分割的平均准确率（F-score）分别为0.91和0.89，3）VCNN方法优于传统聚类方法; 4）VCNN的分类效果与PointNet和PointNet++相当，分割效果最好。该方法证明了LiDAR使用深度学习分离作物表型结构成分的能力，这对其他领域也很有用。
Separating structural components is important but also challenging for plant phenotyping and precision agriculture. Light detection and ranging (LiDAR) technology can potentially overcome these difficulties by providing high quality data. However, there are difficulties in automatically classifying and segmenting components of interest. Deep learning can extract complex features, but it is mostly used with images. Here, we propose a voxel-based convolutional neural network (VCNN) for maize stem and leaf classification and segmentation. Maize plants at three different growth stages were scanned with a terrestrial LiDAR and the voxelized LiDAR data were used as inputs. A total of 3000 individual plants (22 004 leaves and 3000 stems) were prepared for training through data augmentation, and 103 maize plants were used to evaluate the accuracy of classification and segmentation at both instance and point levels. The VCNN was compared with traditional clustering methods ( $K$ -means and density-based spatial clustering of applications with noise), a geometry-based segmentation method, and state-of-the-art deep learning methods (PointNet and PointNet++). The results showed that: 1) at the instance level, the mean accuracy of classification and segmentation (F-score) were 1.00 and 0.96, respectively; 2) at the point level, the mean accuracy of classification and segmentation (F-score) were 0.91 and 0.89, respectively; 3) the VCNN method outperformed traditional clustering methods; and 4) the VCNN was on par with PointNet and PointNet++ in classification, and performed the best in segmentation. The proposed method demonstrated LiDAR’s ability to separate structural components for crop phenotyping using deep learning, which can be useful for other fields.