Automated Phenotypic Analysis of Mature Soybean Using Multi-View Stereo 3D Reconstruction and Point Cloud Segmentation
Phenotypic analysis of mature soybeans is a critical aspect of soybean breeding. However, manually obtaining phenotypic parameters not only is time-consuming and labor intensive but also lacks objectivity. Therefore, there is an urgent need for a rapid, accurate, and efficient method to collect the...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Agriculture |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0472/15/2/175 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589500785623040 |
|---|---|
| author | Daohan Cui Pengfei Liu Yunong Liu Zhenqing Zhao Jiang Feng |
| author_facet | Daohan Cui Pengfei Liu Yunong Liu Zhenqing Zhao Jiang Feng |
| author_sort | Daohan Cui |
| collection | DOAJ |
| description | Phenotypic analysis of mature soybeans is a critical aspect of soybean breeding. However, manually obtaining phenotypic parameters not only is time-consuming and labor intensive but also lacks objectivity. Therefore, there is an urgent need for a rapid, accurate, and efficient method to collect the phenotypic parameters of soybeans. This study develops a novel pipeline for acquiring the phenotypic traits of mature soybeans based on three-dimensional (3D) point clouds. First, soybean point clouds are obtained using a multi-view stereo 3D reconstruction method, followed by preprocessing to construct a dataset. Second, a deep learning-based network, PVSegNet (Point Voxel Segmentation Network), is proposed specifically for segmenting soybean pods and stems. This network enhances feature extraction capabilities through the integration of point cloud and voxel convolution, as well as an orientation-encoding (OE) module. Finally, phenotypic parameters such as stem diameter, pod length, and pod width are extracted and validated against manual measurements. Experimental results demonstrate that the average Intersection over Union (IoU) for semantic segmentation is 92.10%, with a precision of 96.38%, recall of 95.41%, and F1-score of 95.87%. For instance segmentation, the network achieves an average precision (AP@50) of 83.47% and an average recall (AR@50) of 87.07%. These results indicate the feasibility of the network for the instance segmentation of pods and stems. In the extraction of plant parameters, the predicted values of pod width, pod length, and stem diameter obtained through the phenotypic extraction method exhibit coefficients of determination (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula>) of 0.9489, 0.9182, and 0.9209, respectively, with manual measurements. This demonstrates that our method can significantly improve efficiency and accuracy, contributing to the application of automated 3D point cloud analysis technology in soybean breeding. |
| format | Article |
| id | doaj-art-cfff33eb50ed492a900b8ed7a31cd5a0 |
| institution | Kabale University |
| issn | 2077-0472 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agriculture |
| spelling | doaj-art-cfff33eb50ed492a900b8ed7a31cd5a02025-01-24T13:16:00ZengMDPI AGAgriculture2077-04722025-01-0115217510.3390/agriculture15020175Automated Phenotypic Analysis of Mature Soybean Using Multi-View Stereo 3D Reconstruction and Point Cloud SegmentationDaohan Cui0Pengfei Liu1Yunong Liu2Zhenqing Zhao3Jiang Feng4College of Electrical and Information, Northeast Agricultural University, Harbin 150030, ChinaCollege of Electrical and Information, Northeast Agricultural University, Harbin 150030, ChinaCollege of Electrical and Information, Northeast Agricultural University, Harbin 150030, ChinaCollege of Electrical and Information, Northeast Agricultural University, Harbin 150030, ChinaCollege of Electrical and Information, Northeast Agricultural University, Harbin 150030, ChinaPhenotypic analysis of mature soybeans is a critical aspect of soybean breeding. However, manually obtaining phenotypic parameters not only is time-consuming and labor intensive but also lacks objectivity. Therefore, there is an urgent need for a rapid, accurate, and efficient method to collect the phenotypic parameters of soybeans. This study develops a novel pipeline for acquiring the phenotypic traits of mature soybeans based on three-dimensional (3D) point clouds. First, soybean point clouds are obtained using a multi-view stereo 3D reconstruction method, followed by preprocessing to construct a dataset. Second, a deep learning-based network, PVSegNet (Point Voxel Segmentation Network), is proposed specifically for segmenting soybean pods and stems. This network enhances feature extraction capabilities through the integration of point cloud and voxel convolution, as well as an orientation-encoding (OE) module. Finally, phenotypic parameters such as stem diameter, pod length, and pod width are extracted and validated against manual measurements. Experimental results demonstrate that the average Intersection over Union (IoU) for semantic segmentation is 92.10%, with a precision of 96.38%, recall of 95.41%, and F1-score of 95.87%. For instance segmentation, the network achieves an average precision (AP@50) of 83.47% and an average recall (AR@50) of 87.07%. These results indicate the feasibility of the network for the instance segmentation of pods and stems. In the extraction of plant parameters, the predicted values of pod width, pod length, and stem diameter obtained through the phenotypic extraction method exhibit coefficients of determination (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula>) of 0.9489, 0.9182, and 0.9209, respectively, with manual measurements. This demonstrates that our method can significantly improve efficiency and accuracy, contributing to the application of automated 3D point cloud analysis technology in soybean breeding.https://www.mdpi.com/2077-0472/15/2/175deep learningplant phenotypingpoint cloud segmentationsoybean |
| spellingShingle | Daohan Cui Pengfei Liu Yunong Liu Zhenqing Zhao Jiang Feng Automated Phenotypic Analysis of Mature Soybean Using Multi-View Stereo 3D Reconstruction and Point Cloud Segmentation Agriculture deep learning plant phenotyping point cloud segmentation soybean |
| title | Automated Phenotypic Analysis of Mature Soybean Using Multi-View Stereo 3D Reconstruction and Point Cloud Segmentation |
| title_full | Automated Phenotypic Analysis of Mature Soybean Using Multi-View Stereo 3D Reconstruction and Point Cloud Segmentation |
| title_fullStr | Automated Phenotypic Analysis of Mature Soybean Using Multi-View Stereo 3D Reconstruction and Point Cloud Segmentation |
| title_full_unstemmed | Automated Phenotypic Analysis of Mature Soybean Using Multi-View Stereo 3D Reconstruction and Point Cloud Segmentation |
| title_short | Automated Phenotypic Analysis of Mature Soybean Using Multi-View Stereo 3D Reconstruction and Point Cloud Segmentation |
| title_sort | automated phenotypic analysis of mature soybean using multi view stereo 3d reconstruction and point cloud segmentation |
| topic | deep learning plant phenotyping point cloud segmentation soybean |
| url | https://www.mdpi.com/2077-0472/15/2/175 |
| work_keys_str_mv | AT daohancui automatedphenotypicanalysisofmaturesoybeanusingmultiviewstereo3dreconstructionandpointcloudsegmentation AT pengfeiliu automatedphenotypicanalysisofmaturesoybeanusingmultiviewstereo3dreconstructionandpointcloudsegmentation AT yunongliu automatedphenotypicanalysisofmaturesoybeanusingmultiviewstereo3dreconstructionandpointcloudsegmentation AT zhenqingzhao automatedphenotypicanalysisofmaturesoybeanusingmultiviewstereo3dreconstructionandpointcloudsegmentation AT jiangfeng automatedphenotypicanalysisofmaturesoybeanusingmultiviewstereo3dreconstructionandpointcloudsegmentation |