Three-Dimensional Reconstruction, Phenotypic Traits Extraction, and Yield Estimation of Shiitake Mushrooms Based on Structure from Motion and Multi-View Stereo

Phenotypic traits of fungi and their automated extraction are crucial for evaluating genetic diversity, breeding new varieties, and estimating yield. However, research on the high-throughput, rapid, and non-destructive extraction of fungal phenotypic traits using 3D point clouds remains limited. In...

Full description

Saved in:
Bibliographic Details
Main Authors: Xingmei Xu, Jiayuan Li, Jing Zhou, Puyu Feng, Helong Yu, Yuntao Ma
Format: Article
Language:English
Published: MDPI AG 2025-01-01
Series:Agriculture
Subjects:
Online Access:https://www.mdpi.com/2077-0472/15/3/298
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850200278942351360
author Xingmei Xu
Jiayuan Li
Jing Zhou
Puyu Feng
Helong Yu
Yuntao Ma
author_facet Xingmei Xu
Jiayuan Li
Jing Zhou
Puyu Feng
Helong Yu
Yuntao Ma
author_sort Xingmei Xu
collection DOAJ
description Phenotypic traits of fungi and their automated extraction are crucial for evaluating genetic diversity, breeding new varieties, and estimating yield. However, research on the high-throughput, rapid, and non-destructive extraction of fungal phenotypic traits using 3D point clouds remains limited. In this study, a smart phone is used to capture multi-view images of shiitake mushrooms (<i>Lentinula edodes</i>) from three different heights and angles, employing the YOLOv8x model to segment the primary image regions. The segmented images were reconstructed in 3D using Structure from Motion (SfM) and Multi-View Stereo (MVS). To automatically segment individual mushroom instances, we developed a CP-PointNet++ network integrated with clustering methods, achieving an overall accuracy (OA) of 97.45% in segmentation. The computed phenotype correlated strongly with manual measurements, yielding <i>R</i><sup>2</sup> > 0.8 and <i>nRMSE</i> < 0.09 for the pileus transverse and longitudinal diameters, <i>R</i><sup>2</sup> = 0.53 and <i>RMSE</i> = 3.26 mm for the pileus height, <i>R</i><sup>2</sup> = 0.79 and <i>nRMSE</i> = 0.12 for stipe diameter, and <i>R</i><sup>2</sup> = 0.65 and RMSE = 4.98 mm for the stipe height. Using these parameters, yield estimation was performed using PLSR, SVR, RF, and GRNN machine learning models, with GRNN demonstrating superior performance (<i>R</i><sup>2</sup> = 0.91). This approach was also adaptable for extracting phenotypic traits of other fungi, providing valuable support for fungal breeding initiatives.
format Article
id doaj-art-e4ef88e4ade74cf5b0fb903e4d26140a
institution OA Journals
issn 2077-0472
language English
publishDate 2025-01-01
publisher MDPI AG
record_format Article
series Agriculture
spelling doaj-art-e4ef88e4ade74cf5b0fb903e4d26140a2025-08-20T02:12:23ZengMDPI AGAgriculture2077-04722025-01-0115329810.3390/agriculture15030298Three-Dimensional Reconstruction, Phenotypic Traits Extraction, and Yield Estimation of Shiitake Mushrooms Based on Structure from Motion and Multi-View StereoXingmei Xu0Jiayuan Li1Jing Zhou2Puyu Feng3Helong Yu4Yuntao Ma5College of Information Technology, Jilin Agricultural University, Changchun 130118, ChinaCollege of Information Technology, Jilin Agricultural University, Changchun 130118, ChinaCollege of Information Technology, Jilin Agricultural University, Changchun 130118, ChinaCollege of Land Science and Technology, China Agricultural University, Beijing 100193, ChinaCollege of Information Technology, Jilin Agricultural University, Changchun 130118, ChinaCollege of Information Technology, Jilin Agricultural University, Changchun 130118, ChinaPhenotypic traits of fungi and their automated extraction are crucial for evaluating genetic diversity, breeding new varieties, and estimating yield. However, research on the high-throughput, rapid, and non-destructive extraction of fungal phenotypic traits using 3D point clouds remains limited. In this study, a smart phone is used to capture multi-view images of shiitake mushrooms (<i>Lentinula edodes</i>) from three different heights and angles, employing the YOLOv8x model to segment the primary image regions. The segmented images were reconstructed in 3D using Structure from Motion (SfM) and Multi-View Stereo (MVS). To automatically segment individual mushroom instances, we developed a CP-PointNet++ network integrated with clustering methods, achieving an overall accuracy (OA) of 97.45% in segmentation. The computed phenotype correlated strongly with manual measurements, yielding <i>R</i><sup>2</sup> > 0.8 and <i>nRMSE</i> < 0.09 for the pileus transverse and longitudinal diameters, <i>R</i><sup>2</sup> = 0.53 and <i>RMSE</i> = 3.26 mm for the pileus height, <i>R</i><sup>2</sup> = 0.79 and <i>nRMSE</i> = 0.12 for stipe diameter, and <i>R</i><sup>2</sup> = 0.65 and RMSE = 4.98 mm for the stipe height. Using these parameters, yield estimation was performed using PLSR, SVR, RF, and GRNN machine learning models, with GRNN demonstrating superior performance (<i>R</i><sup>2</sup> = 0.91). This approach was also adaptable for extracting phenotypic traits of other fungi, providing valuable support for fungal breeding initiatives.https://www.mdpi.com/2077-0472/15/3/298shiitake mushroomsstructure from motionpoint clouddeep learningpoint cloud semantic segmentation
spellingShingle Xingmei Xu
Jiayuan Li
Jing Zhou
Puyu Feng
Helong Yu
Yuntao Ma
Three-Dimensional Reconstruction, Phenotypic Traits Extraction, and Yield Estimation of Shiitake Mushrooms Based on Structure from Motion and Multi-View Stereo
Agriculture
shiitake mushrooms
structure from motion
point cloud
deep learning
point cloud semantic segmentation
title Three-Dimensional Reconstruction, Phenotypic Traits Extraction, and Yield Estimation of Shiitake Mushrooms Based on Structure from Motion and Multi-View Stereo
title_full Three-Dimensional Reconstruction, Phenotypic Traits Extraction, and Yield Estimation of Shiitake Mushrooms Based on Structure from Motion and Multi-View Stereo
title_fullStr Three-Dimensional Reconstruction, Phenotypic Traits Extraction, and Yield Estimation of Shiitake Mushrooms Based on Structure from Motion and Multi-View Stereo
title_full_unstemmed Three-Dimensional Reconstruction, Phenotypic Traits Extraction, and Yield Estimation of Shiitake Mushrooms Based on Structure from Motion and Multi-View Stereo
title_short Three-Dimensional Reconstruction, Phenotypic Traits Extraction, and Yield Estimation of Shiitake Mushrooms Based on Structure from Motion and Multi-View Stereo
title_sort three dimensional reconstruction phenotypic traits extraction and yield estimation of shiitake mushrooms based on structure from motion and multi view stereo
topic shiitake mushrooms
structure from motion
point cloud
deep learning
point cloud semantic segmentation
url https://www.mdpi.com/2077-0472/15/3/298
work_keys_str_mv AT xingmeixu threedimensionalreconstructionphenotypictraitsextractionandyieldestimationofshiitakemushroomsbasedonstructurefrommotionandmultiviewstereo
AT jiayuanli threedimensionalreconstructionphenotypictraitsextractionandyieldestimationofshiitakemushroomsbasedonstructurefrommotionandmultiviewstereo
AT jingzhou threedimensionalreconstructionphenotypictraitsextractionandyieldestimationofshiitakemushroomsbasedonstructurefrommotionandmultiviewstereo
AT puyufeng threedimensionalreconstructionphenotypictraitsextractionandyieldestimationofshiitakemushroomsbasedonstructurefrommotionandmultiviewstereo
AT helongyu threedimensionalreconstructionphenotypictraitsextractionandyieldestimationofshiitakemushroomsbasedonstructurefrommotionandmultiviewstereo
AT yuntaoma threedimensionalreconstructionphenotypictraitsextractionandyieldestimationofshiitakemushroomsbasedonstructurefrommotionandmultiviewstereo