Deep Learning for Non-Invasive Diagnosis of Nutrient Deficiencies in Sugar Beet Using RGB Images
In order to enable timely actions to prevent major losses of crops caused by lack of nutrients and, hence, increase the potential yield throughout the growing season while at the same time prevent excess fertilization with detrimental environmental consequences, early, non-invasive, and on-site dete...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-10-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/20/5893 |
| _version_ | 1797550630356647936 |
|---|---|
| author | Jinhui Yi Lukas Krusenbaum Paula Unger Hubert Hüging Sabine J. Seidel Gabriel Schaaf Juergen Gall |
| author_facet | Jinhui Yi Lukas Krusenbaum Paula Unger Hubert Hüging Sabine J. Seidel Gabriel Schaaf Juergen Gall |
| author_sort | Jinhui Yi |
| collection | DOAJ |
| description | In order to enable timely actions to prevent major losses of crops caused by lack of nutrients and, hence, increase the potential yield throughout the growing season while at the same time prevent excess fertilization with detrimental environmental consequences, early, non-invasive, and on-site detection of nutrient deficiency is required. Current non-invasive methods for assessing the nutrient status of crops deal in most cases with nitrogen (N) deficiency only and optical sensors to diagnose N deficiency, such as chlorophyll meters or canopy reflectance sensors, do not monitor N, but instead measure changes in leaf spectral properties that may or may not be caused by N deficiency. In this work, we study how well nutrient deficiency symptoms can be recognized in RGB images of sugar beets. To this end, we collected the Deep Nutrient Deficiency for Sugar Beet (DND-SB) dataset, which contains 5648 images of sugar beets growing on a long-term fertilizer experiment with nutrient deficiency plots comprising N, phosphorous (P), and potassium (K) deficiency, as well as the omission of liming (Ca), full fertilization, and no fertilization at all. We use the dataset to analyse the performance of five convolutional neural networks for recognizing nutrient deficiency symptoms and discuss their limitations. |
| first_indexed | 2024-03-10T15:32:03Z |
| format | Article |
| id | doaj.art-f374130224584a9b8b8c0aff16fb1f06 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T15:32:03Z |
| publishDate | 2020-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-f374130224584a9b8b8c0aff16fb1f062023-11-20T17:33:28ZengMDPI AGSensors1424-82202020-10-012020589310.3390/s20205893Deep Learning for Non-Invasive Diagnosis of Nutrient Deficiencies in Sugar Beet Using RGB ImagesJinhui Yi0Lukas Krusenbaum1Paula Unger2Hubert Hüging3Sabine J. Seidel4Gabriel Schaaf5Juergen Gall6Computer Vision Group, Institute of Computer Science III, University of Bonn, Endenicher Allee 19a, 53115 Bonn, GermanyPlant Nutrition Group, Institute of Crop Science and Resource Conservation, University of Bonn, Karlrobert-Kreiten-Strasse 13, 53115 Bonn, GermanyPlant Nutrition Group, Institute of Crop Science and Resource Conservation, University of Bonn, Karlrobert-Kreiten-Strasse 13, 53115 Bonn, GermanyCrop Science Group, Institute of Crop Science and Resource Conservation, University of Bonn, Katzenburgweg 5, 53115 Bonn, GermanyCrop Science Group, Institute of Crop Science and Resource Conservation, University of Bonn, Katzenburgweg 5, 53115 Bonn, GermanyPlant Nutrition Group, Institute of Crop Science and Resource Conservation, University of Bonn, Karlrobert-Kreiten-Strasse 13, 53115 Bonn, GermanyComputer Vision Group, Institute of Computer Science III, University of Bonn, Endenicher Allee 19a, 53115 Bonn, GermanyIn order to enable timely actions to prevent major losses of crops caused by lack of nutrients and, hence, increase the potential yield throughout the growing season while at the same time prevent excess fertilization with detrimental environmental consequences, early, non-invasive, and on-site detection of nutrient deficiency is required. Current non-invasive methods for assessing the nutrient status of crops deal in most cases with nitrogen (N) deficiency only and optical sensors to diagnose N deficiency, such as chlorophyll meters or canopy reflectance sensors, do not monitor N, but instead measure changes in leaf spectral properties that may or may not be caused by N deficiency. In this work, we study how well nutrient deficiency symptoms can be recognized in RGB images of sugar beets. To this end, we collected the Deep Nutrient Deficiency for Sugar Beet (DND-SB) dataset, which contains 5648 images of sugar beets growing on a long-term fertilizer experiment with nutrient deficiency plots comprising N, phosphorous (P), and potassium (K) deficiency, as well as the omission of liming (Ca), full fertilization, and no fertilization at all. We use the dataset to analyse the performance of five convolutional neural networks for recognizing nutrient deficiency symptoms and discuss their limitations.https://www.mdpi.com/1424-8220/20/20/5893nutrient deficienciessugar beetdeep learningnitrogenphosphorouspotassium |
| spellingShingle | Jinhui Yi Lukas Krusenbaum Paula Unger Hubert Hüging Sabine J. Seidel Gabriel Schaaf Juergen Gall Deep Learning for Non-Invasive Diagnosis of Nutrient Deficiencies in Sugar Beet Using RGB Images Sensors nutrient deficiencies sugar beet deep learning nitrogen phosphorous potassium |
| title | Deep Learning for Non-Invasive Diagnosis of Nutrient Deficiencies in Sugar Beet Using RGB Images |
| title_full | Deep Learning for Non-Invasive Diagnosis of Nutrient Deficiencies in Sugar Beet Using RGB Images |
| title_fullStr | Deep Learning for Non-Invasive Diagnosis of Nutrient Deficiencies in Sugar Beet Using RGB Images |
| title_full_unstemmed | Deep Learning for Non-Invasive Diagnosis of Nutrient Deficiencies in Sugar Beet Using RGB Images |
| title_short | Deep Learning for Non-Invasive Diagnosis of Nutrient Deficiencies in Sugar Beet Using RGB Images |
| title_sort | deep learning for non invasive diagnosis of nutrient deficiencies in sugar beet using rgb images |
| topic | nutrient deficiencies sugar beet deep learning nitrogen phosphorous potassium |
| url | https://www.mdpi.com/1424-8220/20/20/5893 |
| work_keys_str_mv | AT jinhuiyi deeplearningfornoninvasivediagnosisofnutrientdeficienciesinsugarbeetusingrgbimages AT lukaskrusenbaum deeplearningfornoninvasivediagnosisofnutrientdeficienciesinsugarbeetusingrgbimages AT paulaunger deeplearningfornoninvasivediagnosisofnutrientdeficienciesinsugarbeetusingrgbimages AT huberthuging deeplearningfornoninvasivediagnosisofnutrientdeficienciesinsugarbeetusingrgbimages AT sabinejseidel deeplearningfornoninvasivediagnosisofnutrientdeficienciesinsugarbeetusingrgbimages AT gabrielschaaf deeplearningfornoninvasivediagnosisofnutrientdeficienciesinsugarbeetusingrgbimages AT juergengall deeplearningfornoninvasivediagnosisofnutrientdeficienciesinsugarbeetusingrgbimages |