Three-Dimensional Phenotyping Pipeline of Potted Plants Based on Neural Radiation Fields and Path Segmentation

Precise acquisition of potted plant traits has great theoretical significance and practical value for variety selection and guiding scientific cultivation practices. Although phenotypic analysis using two dimensional(2D) digital images is simple and efficient, leaf occlusion reduces the available ph...

Full description

Saved in:
Bibliographic Details
Main Authors: Xinghui Zhu, Zhongrui Huang, Bin Li
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Plants
Subjects:
Online Access:https://www.mdpi.com/2223-7747/13/23/3368
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850060191895126016
author Xinghui Zhu
Zhongrui Huang
Bin Li
author_facet Xinghui Zhu
Zhongrui Huang
Bin Li
author_sort Xinghui Zhu
collection DOAJ
description Precise acquisition of potted plant traits has great theoretical significance and practical value for variety selection and guiding scientific cultivation practices. Although phenotypic analysis using two dimensional(2D) digital images is simple and efficient, leaf occlusion reduces the available phenotype information. To address the current challenge of acquiring sufficient non-destructive information from living potted plants, we proposed a three dimensional (3D) phenotyping pipeline that combines neural radiation field reconstruction with path analysis. An indoor collection system was constructed to obtain multi-view image sequences of potted plants. The structure from motion and neural radiance fields (SFM-NeRF) algorithm was then utilized to reconstruct 3D point clouds, which were subsequently denoised and calibrated. Geometric-feature-based path analysis was employed to separate stems from leaves, and density clustering methods were applied to segment the canopy leaves. Phenotypic parameters of potted plant organs were extracted, including height, stem thickness, leaf length, leaf width, and leaf area, and they were manually measured to obtain the true values. The results showed that the coefficient of determination (R<sup>2</sup>) values, indicating the correlation between the model traits and the true traits, ranged from 0.89 to 0.98, indicating a strong correlation. The reconstruction quality was good. Additionally, 22 potted plants were selected for exploratory experiments. The results indicated that the method was capable of reconstructing plants of various varieties, and the experiments identified key conditions essential for successful reconstruction. In summary, this study developed a low-cost and robust 3D phenotyping pipeline for the phenotype analysis of potted plants. This proposed pipeline not only meets daily production requirements but also advances the field of phenotype calculation for potted plants.
format Article
id doaj-art-13ea63e2a839441d92658c60bb3d45be
institution DOAJ
issn 2223-7747
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Plants
spelling doaj-art-13ea63e2a839441d92658c60bb3d45be2025-08-20T02:50:40ZengMDPI AGPlants2223-77472024-11-011323336810.3390/plants13233368Three-Dimensional Phenotyping Pipeline of Potted Plants Based on Neural Radiation Fields and Path SegmentationXinghui Zhu0Zhongrui Huang1Bin Li2College of Information and Intelligence, Hunan Agricultural University, Changsha 410128, ChinaHunan Engineering Technology Research Center of Agricultural Rural Informatization, Changsha 410128, ChinaHunan Engineering Technology Research Center of Agricultural Rural Informatization, Changsha 410128, ChinaPrecise acquisition of potted plant traits has great theoretical significance and practical value for variety selection and guiding scientific cultivation practices. Although phenotypic analysis using two dimensional(2D) digital images is simple and efficient, leaf occlusion reduces the available phenotype information. To address the current challenge of acquiring sufficient non-destructive information from living potted plants, we proposed a three dimensional (3D) phenotyping pipeline that combines neural radiation field reconstruction with path analysis. An indoor collection system was constructed to obtain multi-view image sequences of potted plants. The structure from motion and neural radiance fields (SFM-NeRF) algorithm was then utilized to reconstruct 3D point clouds, which were subsequently denoised and calibrated. Geometric-feature-based path analysis was employed to separate stems from leaves, and density clustering methods were applied to segment the canopy leaves. Phenotypic parameters of potted plant organs were extracted, including height, stem thickness, leaf length, leaf width, and leaf area, and they were manually measured to obtain the true values. The results showed that the coefficient of determination (R<sup>2</sup>) values, indicating the correlation between the model traits and the true traits, ranged from 0.89 to 0.98, indicating a strong correlation. The reconstruction quality was good. Additionally, 22 potted plants were selected for exploratory experiments. The results indicated that the method was capable of reconstructing plants of various varieties, and the experiments identified key conditions essential for successful reconstruction. In summary, this study developed a low-cost and robust 3D phenotyping pipeline for the phenotype analysis of potted plants. This proposed pipeline not only meets daily production requirements but also advances the field of phenotype calculation for potted plants.https://www.mdpi.com/2223-7747/13/23/33683D reconstructionstem and leaf segmentationneural radiance fieldsstructure from motionpotted plant analysisplant digitization
spellingShingle Xinghui Zhu
Zhongrui Huang
Bin Li
Three-Dimensional Phenotyping Pipeline of Potted Plants Based on Neural Radiation Fields and Path Segmentation
Plants
3D reconstruction
stem and leaf segmentation
neural radiance fields
structure from motion
potted plant analysis
plant digitization
title Three-Dimensional Phenotyping Pipeline of Potted Plants Based on Neural Radiation Fields and Path Segmentation
title_full Three-Dimensional Phenotyping Pipeline of Potted Plants Based on Neural Radiation Fields and Path Segmentation
title_fullStr Three-Dimensional Phenotyping Pipeline of Potted Plants Based on Neural Radiation Fields and Path Segmentation
title_full_unstemmed Three-Dimensional Phenotyping Pipeline of Potted Plants Based on Neural Radiation Fields and Path Segmentation
title_short Three-Dimensional Phenotyping Pipeline of Potted Plants Based on Neural Radiation Fields and Path Segmentation
title_sort three dimensional phenotyping pipeline of potted plants based on neural radiation fields and path segmentation
topic 3D reconstruction
stem and leaf segmentation
neural radiance fields
structure from motion
potted plant analysis
plant digitization
url https://www.mdpi.com/2223-7747/13/23/3368
work_keys_str_mv AT xinghuizhu threedimensionalphenotypingpipelineofpottedplantsbasedonneuralradiationfieldsandpathsegmentation
AT zhongruihuang threedimensionalphenotypingpipelineofpottedplantsbasedonneuralradiationfieldsandpathsegmentation
AT binli threedimensionalphenotypingpipelineofpottedplantsbasedonneuralradiationfieldsandpathsegmentation