Deep Learning-Based Plant Organ Segmentation and Phenotyping of Sorghum Plants Using LiDAR Point Cloud

Abstract

Increasing food demands, global climatic variations, and population growth have spurred the growth of crop yield driven by plant phenotyping in the age of big data. High-throughput phenotyping of sorghum at each plant and organ level is vital in molecular plant breeding to increase crop yield. LiDAR (light detection and ranging) sensor provides 3D point clouds of plants with the advantages of high precision, high resolution, and rapid measurement. However, need to develop robust algorithms for extracting the phenotypic traits of sorghum plants using LiDAR 3D point cloud. This study utilized four 3D point cloud-based deep learning models named PointNet, PointNet++, PointCNN, and dynamic graph CNN (DGCNN) for the specific objective of the segmentation of sorghum plants. Subsequently, phenotypic traits were extracted using the segmentation results. Study plants sample were grown under controlled conditions at various developmental stages. The extracted phenotypic traits outcome has been validated through the manually measured phenotypic traits of the sorghum plant. PointNet++ outperformed the other three deep learning models and provided the best segmentation result with a mean accuracy of 91.5%. The correlations of the six phenotypic traits, such as plant height, plant crown diameter, plant compactness, stem diameter, panicle length, and panicle width were calculated from the segmentation results of the PointNet++ model and the measured coefficient of determination (R2) were 0.97, 0.96, 0.94, 0.90, 0.95, and 0.88, respectively. The obtained results showed that LiDAR 3D point cloud have good potential to measure the sorghum plant phenotype traits rapidly and accurately using deep learning techniques.

Plant phenotyping relevance

LiDAR点群と深層学習による器官分割・形質抽出を開発し、手測定で妥当性検証しており、植物フェノタイピング手法が研究の中心です。

Code and data availability

The supplied blocks describe a labeled sorghum LiDAR point cloud dataset (800 samples from 500 plants) and deep learning segmentation/phenotyping pipeline, but contain no public deposit, availability statement, URL, or code release for the dataset, models, or analysis. The only URL present is the license notice.

No evidence-backed public reproduction asset is currently recorded.