The use of computer vision to classify Xaraés grass according to nutritional status in nitrogen
ABSTRACT This study is based on the principle that vegetation indexes (VIs), derived from the RGB color model obtained from digital images, can be used to characterize spectral signatures and classify Brachiaria brizantha cv. Xaraés according to nitrogen status (N). From colorimetric data obtained f...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Universidade Federal do Ceará
2021-11-01
|
| Series: | Revista Ciência Agronômica |
| Subjects: | |
| Online Access: | http://www.scielo.br/scielo.php?script=sci_arttext&pid=S1806-66902022000100406&tlng=en |
| _version_ | 1818774960912465920 |
|---|---|
| author | Wellington Renato Mancin Lilian Elgalise Techio Pereira Rachel Santos Bueno Carvalho Yeyin Shi Wilson Manuel Castro Silupu Adriano Rogério Bruno Tech |
| author_facet | Wellington Renato Mancin Lilian Elgalise Techio Pereira Rachel Santos Bueno Carvalho Yeyin Shi Wilson Manuel Castro Silupu Adriano Rogério Bruno Tech |
| author_sort | Wellington Renato Mancin |
| collection | DOAJ |
| description | ABSTRACT This study is based on the principle that vegetation indexes (VIs), derived from the RGB color model obtained from digital images, can be used to characterize spectral signatures and classify Brachiaria brizantha cv. Xaraés according to nitrogen status (N). From colorimetric data obtained from leaf blade images acquired in the field, three artificial neural networks were evaluated according to the performance in the classification of N status: Feedforward Backpropagation (FFBP), Cascade Forward Backpropagation (CFBP) and Radial Base function (RBFNN). Four N fertilization rates were applied to generate contrasting N contents in the plants. The youngest completely expanded leaves from 60 tillers were detached at each regrowth cycle of 28 days, thus their images and leaf N content were obtained. Samples were then classified as deficient (>17 g N kg-1 leaf dry matter (DM), moderately deficient (from 17.1 to 20.0 g N kg-1 DM), and sufficient (> 20.1 g N kg-1 DM). The VIs were selected by principal component analysis and the performance of the networks evaluated by the accuracy. The accuracy in classification obtained by the networks were 88%, 86% and 79% for FFBP, CFBP and RBFNN, respectively, indicating that the spectral signatures can be determined from images acquired in the field. So, the proposed method could be used to develop a software that aims to monitor the status of N in real time, providing a fast and inexpensive tool for defining the time and the amount of N fertilizer, according to the pasture demand. |
| first_indexed | 2024-12-18T10:49:27Z |
| format | Article |
| id | doaj.art-3d4290e2a02f427d953d6342399ea858 |
| institution | Directory Open Access Journal |
| issn | 1806-6690 |
| language | English |
| last_indexed | 2024-12-18T10:49:27Z |
| publishDate | 2021-11-01 |
| publisher | Universidade Federal do Ceará |
| record_format | Article |
| series | Revista Ciência Agronômica |
| spelling | doaj.art-3d4290e2a02f427d953d6342399ea8582022-12-21T21:10:28ZengUniversidade Federal do CearáRevista Ciência Agronômica1806-66902021-11-015310.5935/1806-6690.20220006The use of computer vision to classify Xaraés grass according to nutritional status in nitrogenWellington Renato Mancinhttps://orcid.org/0000-0002-4242-1327Lilian Elgalise Techio Pereirahttps://orcid.org/0000-0002-3022-8423Rachel Santos Bueno Carvalhohttps://orcid.org/0000-0003-2628-1915Yeyin Shihttps://orcid.org/0000-0003-3964-2855Wilson Manuel Castro Silupuhttps://orcid.org/0000-0001-7286-1262Adriano Rogério Bruno Techhttps://orcid.org/0000-0002-0555-1480ABSTRACT This study is based on the principle that vegetation indexes (VIs), derived from the RGB color model obtained from digital images, can be used to characterize spectral signatures and classify Brachiaria brizantha cv. Xaraés according to nitrogen status (N). From colorimetric data obtained from leaf blade images acquired in the field, three artificial neural networks were evaluated according to the performance in the classification of N status: Feedforward Backpropagation (FFBP), Cascade Forward Backpropagation (CFBP) and Radial Base function (RBFNN). Four N fertilization rates were applied to generate contrasting N contents in the plants. The youngest completely expanded leaves from 60 tillers were detached at each regrowth cycle of 28 days, thus their images and leaf N content were obtained. Samples were then classified as deficient (>17 g N kg-1 leaf dry matter (DM), moderately deficient (from 17.1 to 20.0 g N kg-1 DM), and sufficient (> 20.1 g N kg-1 DM). The VIs were selected by principal component analysis and the performance of the networks evaluated by the accuracy. The accuracy in classification obtained by the networks were 88%, 86% and 79% for FFBP, CFBP and RBFNN, respectively, indicating that the spectral signatures can be determined from images acquired in the field. So, the proposed method could be used to develop a software that aims to monitor the status of N in real time, providing a fast and inexpensive tool for defining the time and the amount of N fertilizer, according to the pasture demand.http://www.scielo.br/scielo.php?script=sci_arttext&pid=S1806-66902022000100406&tlng=enImage processingRemote sensingHSBSpectral signature |
| spellingShingle | Wellington Renato Mancin Lilian Elgalise Techio Pereira Rachel Santos Bueno Carvalho Yeyin Shi Wilson Manuel Castro Silupu Adriano Rogério Bruno Tech The use of computer vision to classify Xaraés grass according to nutritional status in nitrogen Revista Ciência Agronômica Image processing Remote sensing HSB Spectral signature |
| title | The use of computer vision to classify Xaraés grass according to nutritional status in nitrogen |
| title_full | The use of computer vision to classify Xaraés grass according to nutritional status in nitrogen |
| title_fullStr | The use of computer vision to classify Xaraés grass according to nutritional status in nitrogen |
| title_full_unstemmed | The use of computer vision to classify Xaraés grass according to nutritional status in nitrogen |
| title_short | The use of computer vision to classify Xaraés grass according to nutritional status in nitrogen |
| title_sort | use of computer vision to classify xaraes grass according to nutritional status in nitrogen |
| topic | Image processing Remote sensing HSB Spectral signature |
| url | http://www.scielo.br/scielo.php?script=sci_arttext&pid=S1806-66902022000100406&tlng=en |
| work_keys_str_mv | AT wellingtonrenatomancin theuseofcomputervisiontoclassifyxaraesgrassaccordingtonutritionalstatusinnitrogen AT lilianelgalisetechiopereira theuseofcomputervisiontoclassifyxaraesgrassaccordingtonutritionalstatusinnitrogen AT rachelsantosbuenocarvalho theuseofcomputervisiontoclassifyxaraesgrassaccordingtonutritionalstatusinnitrogen AT yeyinshi theuseofcomputervisiontoclassifyxaraesgrassaccordingtonutritionalstatusinnitrogen AT wilsonmanuelcastrosilupu theuseofcomputervisiontoclassifyxaraesgrassaccordingtonutritionalstatusinnitrogen AT adrianorogeriobrunotech theuseofcomputervisiontoclassifyxaraesgrassaccordingtonutritionalstatusinnitrogen AT wellingtonrenatomancin useofcomputervisiontoclassifyxaraesgrassaccordingtonutritionalstatusinnitrogen AT lilianelgalisetechiopereira useofcomputervisiontoclassifyxaraesgrassaccordingtonutritionalstatusinnitrogen AT rachelsantosbuenocarvalho useofcomputervisiontoclassifyxaraesgrassaccordingtonutritionalstatusinnitrogen AT yeyinshi useofcomputervisiontoclassifyxaraesgrassaccordingtonutritionalstatusinnitrogen AT wilsonmanuelcastrosilupu useofcomputervisiontoclassifyxaraesgrassaccordingtonutritionalstatusinnitrogen AT adrianorogeriobrunotech useofcomputervisiontoclassifyxaraesgrassaccordingtonutritionalstatusinnitrogen |