Semantic Segmentation of Sorghum Using Hyperspectral Data Identifies Genetic Associations
This study describes the evaluation of a range of approaches to semantic segmentation of hyperspectral images of sorghum plants, classifying each pixel as either nonplant or belonging to one of the three organ types (leaf, stalk, panicle). While many current methods for segmentation focus on separat...
| Principais autores: | , , , , , |
|---|---|
| Formato: | Artigo |
| Idioma: | English |
| Publicado em: |
American Association for the Advancement of Science (AAAS)
2020-01-01
|
| coleção: | Plant Phenomics |
| Acesso em linha: | http://dx.doi.org/10.34133/2020/4216373 |
| _version_ | 1831644334466793472 |
|---|---|
| author | Chenyong Miao Alejandro Pages Zheng Xu Eric Rodene Jinliang Yang James C. Schnable |
| author_facet | Chenyong Miao Alejandro Pages Zheng Xu Eric Rodene Jinliang Yang James C. Schnable |
| author_sort | Chenyong Miao |
| collection | DOAJ |
| description | This study describes the evaluation of a range of approaches to semantic segmentation of hyperspectral images of sorghum plants, classifying each pixel as either nonplant or belonging to one of the three organ types (leaf, stalk, panicle). While many current methods for segmentation focus on separating plant pixels from background, organ-specific segmentation makes it feasible to measure a wider range of plant properties. Manually scored training data for a set of hyperspectral images collected from a sorghum association population was used to train and evaluate a set of supervised classification models. Many algorithms show acceptable accuracy for this classification task. Algorithms trained on sorghum data are able to accurately classify maize leaves and stalks, but fail to accurately classify maize reproductive organs which are not directly equivalent to sorghum panicles. Trait measurements extracted from semantic segmentation of sorghum organs can be used to identify both genes known to be controlling variation in a previously measured phenotypes (e.g., panicle size and plant height) as well as identify signals for genes controlling traits not previously quantified in this population (e.g., stalk/leaf ratio). Organ level semantic segmentation provides opportunities to identify genes controlling variation in a wide range of morphological phenotypes in sorghum, maize, and other related grain crops. |
| first_indexed | 2024-12-19T13:15:53Z |
| format | Article |
| id | doaj.art-a22a90e7e6ca4be2b9c5cae0c69c3b51 |
| institution | Directory Open Access Journal |
| issn | 2643-6515 |
| language | English |
| last_indexed | 2024-12-19T13:15:53Z |
| publishDate | 2020-01-01 |
| publisher | American Association for the Advancement of Science (AAAS) |
| record_format | Article |
| series | Plant Phenomics |
| spelling | doaj.art-a22a90e7e6ca4be2b9c5cae0c69c3b512022-12-21T20:19:49ZengAmerican Association for the Advancement of Science (AAAS)Plant Phenomics2643-65152020-01-01202010.34133/2020/4216373Semantic Segmentation of Sorghum Using Hyperspectral Data Identifies Genetic AssociationsChenyong Miao0Alejandro Pages1Zheng Xu2Eric Rodene3Jinliang Yang4James C. Schnable5Center for Plant Science Innovation, University of Nebraska-Lincoln, Lincoln, NE, USA; Department of Agronomy and Horticulture, University of Nebraska-Lincoln, Lincoln, NE, USA; Quantitative Life Sciences Initiative, University of Nebraska-Lincoln, Lincoln, NE, USAQuantitative Life Sciences Initiative, University of Nebraska-Lincoln, Lincoln, NE, USADepartment of Mathematics and Statistics, Wright State University, Dayton, OH, USACenter for Plant Science Innovation, University of Nebraska-Lincoln, Lincoln, NE, USA; Department of Agronomy and Horticulture, University of Nebraska-Lincoln, Lincoln, NE, USACenter for Plant Science Innovation, University of Nebraska-Lincoln, Lincoln, NE, USA; Department of Agronomy and Horticulture, University of Nebraska-Lincoln, Lincoln, NE, USACenter for Plant Science Innovation, University of Nebraska-Lincoln, Lincoln, NE, USA; Department of Agronomy and Horticulture, University of Nebraska-Lincoln, Lincoln, NE, USA; Quantitative Life Sciences Initiative, University of Nebraska-Lincoln, Lincoln, NE, USAThis study describes the evaluation of a range of approaches to semantic segmentation of hyperspectral images of sorghum plants, classifying each pixel as either nonplant or belonging to one of the three organ types (leaf, stalk, panicle). While many current methods for segmentation focus on separating plant pixels from background, organ-specific segmentation makes it feasible to measure a wider range of plant properties. Manually scored training data for a set of hyperspectral images collected from a sorghum association population was used to train and evaluate a set of supervised classification models. Many algorithms show acceptable accuracy for this classification task. Algorithms trained on sorghum data are able to accurately classify maize leaves and stalks, but fail to accurately classify maize reproductive organs which are not directly equivalent to sorghum panicles. Trait measurements extracted from semantic segmentation of sorghum organs can be used to identify both genes known to be controlling variation in a previously measured phenotypes (e.g., panicle size and plant height) as well as identify signals for genes controlling traits not previously quantified in this population (e.g., stalk/leaf ratio). Organ level semantic segmentation provides opportunities to identify genes controlling variation in a wide range of morphological phenotypes in sorghum, maize, and other related grain crops.http://dx.doi.org/10.34133/2020/4216373 |
| spellingShingle | Chenyong Miao Alejandro Pages Zheng Xu Eric Rodene Jinliang Yang James C. Schnable Semantic Segmentation of Sorghum Using Hyperspectral Data Identifies Genetic Associations Plant Phenomics |
| title | Semantic Segmentation of Sorghum Using Hyperspectral Data Identifies Genetic Associations |
| title_full | Semantic Segmentation of Sorghum Using Hyperspectral Data Identifies Genetic Associations |
| title_fullStr | Semantic Segmentation of Sorghum Using Hyperspectral Data Identifies Genetic Associations |
| title_full_unstemmed | Semantic Segmentation of Sorghum Using Hyperspectral Data Identifies Genetic Associations |
| title_short | Semantic Segmentation of Sorghum Using Hyperspectral Data Identifies Genetic Associations |
| title_sort | semantic segmentation of sorghum using hyperspectral data identifies genetic associations |
| url | http://dx.doi.org/10.34133/2020/4216373 |
| work_keys_str_mv | AT chenyongmiao semanticsegmentationofsorghumusinghyperspectraldataidentifiesgeneticassociations AT alejandropages semanticsegmentationofsorghumusinghyperspectraldataidentifiesgeneticassociations AT zhengxu semanticsegmentationofsorghumusinghyperspectraldataidentifiesgeneticassociations AT ericrodene semanticsegmentationofsorghumusinghyperspectraldataidentifiesgeneticassociations AT jinliangyang semanticsegmentationofsorghumusinghyperspectraldataidentifiesgeneticassociations AT jamescschnable semanticsegmentationofsorghumusinghyperspectraldataidentifiesgeneticassociations |