date: 2025-12-04T08:11:14Z
pdf:PDFVersion: 1.7
pdf:docinfo:title: A Novel Semi-Hydroponic Root Observation System Combined with Unsupervised Semantic Segmentation for Root Phenotyping
xmp:CreatorTool: LaTeX with hyperref
access_permission:can_print_degraded: true
subject: Root system analysis remains methodologically challenging in plant research: traditional soil cultivation obstructs comprehensive root observation, whereas hydroponic visualization lacks ecological relevance due to soil environment exclusion?a critical limitation for crops like soybean. This manuscript developed a cost-effective hybrid imaging system integrating transparent acrylic plates, semi-permeable membranes, and natural soil substrates with high-resolution imaging and controlled illumination, enabling non-destructive root monitoring in quasi-natural soil conditions. Complementing this hardware innovation, this manuscript proposed an unsupervised semantic segmentation algorithm that synergizes path planning with an enhanced DBSCAN framework, achieving the precise extraction of primary and lateral root architectures. Experimental validation demonstrated superior performance in soybean root analysis, with segmentation metrics reaching 0.8444 accuracy, 0.9203 recall, 0.8743 F1-score, and 0.7921 mIoU?significantly outperforming existing unsupervised methods (p<0.01). Strong correlations (R2 > 0.94) with WinRHIZO in quantifying root length, projected area, dimensional parameters, and lateral root counts confirmed system reliability. This soil-compatible phenotyping platform establishes new opportunities for root research, with future developments targeting multi-crop adaptability and complex soil condition applications through modular hardware redesign and 3D reconstruction algorithm integration. 
dc:format: application/pdf; version=1.7
pdf:docinfo:creator_tool: LaTeX with hyperref
access_permission:fill_in_form: true
pdf:encrypted: false
dc:title: A Novel Semi-Hydroponic Root Observation System Combined with Unsupervised Semantic Segmentation for Root Phenotyping
modified: 2025-12-04T08:11:14Z
cp:subject: Root system analysis remains methodologically challenging in plant research: traditional soil cultivation obstructs comprehensive root observation, whereas hydroponic visualization lacks ecological relevance due to soil environment exclusion?a critical limitation for crops like soybean. This manuscript developed a cost-effective hybrid imaging system integrating transparent acrylic plates, semi-permeable membranes, and natural soil substrates with high-resolution imaging and controlled illumination, enabling non-destructive root monitoring in quasi-natural soil conditions. Complementing this hardware innovation, this manuscript proposed an unsupervised semantic segmentation algorithm that synergizes path planning with an enhanced DBSCAN framework, achieving the precise extraction of primary and lateral root architectures. Experimental validation demonstrated superior performance in soybean root analysis, with segmentation metrics reaching 0.8444 accuracy, 0.9203 recall, 0.8743 F1-score, and 0.7921 mIoU?significantly outperforming existing unsupervised methods (p<0.01). Strong correlations (R2 > 0.94) with WinRHIZO in quantifying root length, projected area, dimensional parameters, and lateral root counts confirmed system reliability. This soil-compatible phenotyping platform establishes new opportunities for root research, with future developments targeting multi-crop adaptability and complex soil condition applications through modular hardware redesign and 3D reconstruction algorithm integration. 
pdf:docinfo:subject: Root system analysis remains methodologically challenging in plant research: traditional soil cultivation obstructs comprehensive root observation, whereas hydroponic visualization lacks ecological relevance due to soil environment exclusion?a critical limitation for crops like soybean. This manuscript developed a cost-effective hybrid imaging system integrating transparent acrylic plates, semi-permeable membranes, and natural soil substrates with high-resolution imaging and controlled illumination, enabling non-destructive root monitoring in quasi-natural soil conditions. Complementing this hardware innovation, this manuscript proposed an unsupervised semantic segmentation algorithm that synergizes path planning with an enhanced DBSCAN framework, achieving the precise extraction of primary and lateral root architectures. Experimental validation demonstrated superior performance in soybean root analysis, with segmentation metrics reaching 0.8444 accuracy, 0.9203 recall, 0.8743 F1-score, and 0.7921 mIoU?significantly outperforming existing unsupervised methods (p<0.01). Strong correlations (R2 > 0.94) with WinRHIZO in quantifying root length, projected area, dimensional parameters, and lateral root counts confirmed system reliability. This soil-compatible phenotyping platform establishes new opportunities for root research, with future developments targeting multi-crop adaptability and complex soil condition applications through modular hardware redesign and 3D reconstruction algorithm integration. 
pdf:docinfo:creator: Kunhong Li, Siyue Xu, Christoph Menz, Feng Yang, Helder Fraga, Joao A. Santos, Bing Liu and Chenyao Yang
PTEX.Fullbanner: This is pdfTeX, Version 3.141592653-2.6-1.40.25 (TeX Live 2023) kpathsea version 6.3.5
meta:author: Kunhong Li, Siyue Xu, Christoph Menz, Feng Yang, Helder Fraga, Joao A. Santos, Bing Liu and Chenyao Yang
trapped: False
meta:creation-date: 2025-12-04T08:08:07Z
created: 2025-12-04T08:08:07Z
access_permission:extract_for_accessibility: true
Creation-Date: 2025-12-04T08:08:07Z
Author: Kunhong Li, Siyue Xu, Christoph Menz, Feng Yang, Helder Fraga, Joao A. Santos, Bing Liu and Chenyao Yang
producer: pdfTeX-1.40.25; modified using OpenPDF 1.4.2
pdf:docinfo:producer: pdfTeX-1.40.25; modified using OpenPDF 1.4.2
pdf:unmappedUnicodeCharsPerPage: 0
Keywords: machine vision; tea bud detection; small target; model pruning
access_permission:modify_annotations: true
dc:creator: Kunhong Li, Siyue Xu, Christoph Menz, Feng Yang, Helder Fraga, Joao A. Santos, Bing Liu and Chenyao Yang
dcterms:created: 2025-12-04T08:08:07Z
Last-Modified: 2025-12-04T08:11:14Z
dcterms:modified: 2025-12-04T08:11:14Z
title: A Novel Semi-Hydroponic Root Observation System Combined with Unsupervised Semantic Segmentation for Root Phenotyping
Last-Save-Date: 2025-12-04T08:11:14Z
pdf:docinfo:keywords: machine vision; tea bud detection; small target; model pruning
pdf:docinfo:modified: 2025-12-04T08:11:14Z
meta:save-date: 2025-12-04T08:11:14Z
pdf:docinfo:custom:PTEX.Fullbanner: This is pdfTeX, Version 3.141592653-2.6-1.40.25 (TeX Live 2023) kpathsea version 6.3.5
Content-Type: application/pdf
X-Parsed-By: org.apache.tika.parser.DefaultParser
creator: Kunhong Li, Siyue Xu, Christoph Menz, Feng Yang, Helder Fraga, Joao A. Santos, Bing Liu and Chenyao Yang
dc:subject: machine vision; tea bud detection; small target; model pruning
access_permission:assemble_document: true
xmpTPg:NPages: 20
pdf:charsPerPage: 3391
access_permission:extract_content: true
access_permission:can_print: true
pdf:docinfo:trapped: False
meta:keyword: machine vision; tea bud detection; small target; model pruning
access_permission:can_modify: true
pdf:docinfo:created: 2025-12-04T08:08:07Z