3D plant morphology phenotyping of sorghum and soybean in near real-field conditions using point cloud analysis

• Published in: Korean Journal of Agricultural Science Vol. 52; no. 2; pp. 183 - 199
• Main Authors: Omia, Emmanuel, Park, Eun-Sung, Semyalo, Dennis, Pahlawan, Muhammad Fahri Reza, Joshi, Rahul, Lee, Hongseok, Kabenge, Isa, Ahn, Chi-Kook, Cho, Byoung-Kwan
• Format: Journal Article
• Language: English
• Published: 농업과학연구소 01.06.2025
• Subjects: 농학
• ISSN: 2466-2402; 2466-2410
• DOI: 10.7744/kjoas.520211

Modern plant phenomics leverages advanced digital technologies to derive qualitative and quantitative traits that define plant phenotypes, offering crucial insights for breeders and farmers in precision agriculture. However, real-field conditions, with their complexity and lack of flexibility, pose significant challenges for machine vision algorithm initially developed in controlled laboratory settings. The objective of this study was to explore the potential of human aided 3D point cloud analysis for phenotyping crop under near real-field conditions using a custom-built desktop application, with sorghum and soybean plants as the case study. Light detection and ranging (LiDAR) data acquisition was performed using a Leica BLK360 imaging laser scanner (Leica Geosystems AG, USA). Coordinate difference measurements were employed in extracting various phenotypic traits from plant point clouds. The sphere outlier removal (SOR) was fundamental in macro-noise reduction, while color-based scatter plot matrix were used for micro-noise isolation. The correlation between point cloud-derived traits and manually measured values was strong, with root mean square error (RMSE) of 17.84 mm for sorghum plant height, 16.28 mm for soybean plant height, 11.65 mm for sorghum panicle height, and 0.967 mm for sorghum stem diameter, and corresponding R-squared values between 0.7334 and 0.9492. However, measuring more complex traits like crown diameter, which are influenced by overlap and occlusion, was less accurate, with an RMSE of 102.4 mm and an R-squared value of 0.3702. While 3D phenotyping in near real-field environment reliably captures linear plant structures, complex morphological traits require improved occlusionhandling algorithms. Future work should prioritize high resolution sensors to capture finer details. Likewise, automated workflows are poised to improve not only throughput but the reliability and reproducibility of the 3D phenotyping approach. KCI Citation Count: 0