Estimating Plant Nitrogen Concentration of Rice through Fusing Vegetation Indices and Color Moments Derived from UAV-RGB Images
Estimating plant nitrogen concentration (PNC) has been conducted using vegetation indices (VIs) from UAV-based imagery, but color features have been rarely considered as additional variables. In this study, the VIs and color moments (color feature) were calculated from UAV-based RGB images, then par...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-04-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/9/1620 |
| _version_ | 1827694483267911680 |
|---|---|
| author | Haixiao Ge Haitao Xiang Fei Ma Zhenwang Li Zhengchao Qiu Zhengzheng Tan Changwen Du |
| author_facet | Haixiao Ge Haitao Xiang Fei Ma Zhenwang Li Zhengchao Qiu Zhengzheng Tan Changwen Du |
| author_sort | Haixiao Ge |
| collection | DOAJ |
| description | Estimating plant nitrogen concentration (PNC) has been conducted using vegetation indices (VIs) from UAV-based imagery, but color features have been rarely considered as additional variables. In this study, the VIs and color moments (color feature) were calculated from UAV-based RGB images, then partial least square regression (PLSR) and random forest regression (RF) models were established to estimate PNC through fusing VIs and color moments. The results demonstrated that the fusion of VIs and color moments as inputs yielded higher accuracies of PNC estimation compared to VIs or color moments as input; the RF models based on the combination of VIs and color moments (R<sup>2</sup> ranging from 0.69 to 0.91 and NRMSE ranging from 0.07 to 0.13) showed similar performances to the PLSR models (R<sup>2</sup> ranging from 0.68 to 0.87 and NRMSE ranging from 0.10 to 0.29); Among the top five important variables in the RF models, there was at least one variable which belonged to the color moments in different datasets, indicating the significant contribution of color moments in improving PNC estimation accuracy. This revealed the great potential of combination of RGB-VIs and color moments for the estimation of rice PNC. |
| first_indexed | 2024-03-10T12:06:37Z |
| format | Article |
| id | doaj.art-4e1005816690413baa457db03b446df4 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T12:06:37Z |
| publishDate | 2021-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-4e1005816690413baa457db03b446df42023-11-21T16:33:04ZengMDPI AGRemote Sensing2072-42922021-04-01139162010.3390/rs13091620Estimating Plant Nitrogen Concentration of Rice through Fusing Vegetation Indices and Color Moments Derived from UAV-RGB ImagesHaixiao Ge0Haitao Xiang1Fei Ma2Zhenwang Li3Zhengchao Qiu4Zhengzheng Tan5Changwen Du6The State Key Laboratory of Soil and Sustainable Agriculture, Institute of Soil Science Chinese Academy of Sciences, Nanjing 210008, ChinaThe State Key Laboratory of Soil and Sustainable Agriculture, Institute of Soil Science Chinese Academy of Sciences, Nanjing 210008, ChinaThe State Key Laboratory of Soil and Sustainable Agriculture, Institute of Soil Science Chinese Academy of Sciences, Nanjing 210008, ChinaThe State Key Laboratory of Soil and Sustainable Agriculture, Institute of Soil Science Chinese Academy of Sciences, Nanjing 210008, ChinaThe State Key Laboratory of Soil and Sustainable Agriculture, Institute of Soil Science Chinese Academy of Sciences, Nanjing 210008, ChinaYuan Longping High-Tech Agriculture Co., Ltd., Changsha 410001, ChinaThe State Key Laboratory of Soil and Sustainable Agriculture, Institute of Soil Science Chinese Academy of Sciences, Nanjing 210008, ChinaEstimating plant nitrogen concentration (PNC) has been conducted using vegetation indices (VIs) from UAV-based imagery, but color features have been rarely considered as additional variables. In this study, the VIs and color moments (color feature) were calculated from UAV-based RGB images, then partial least square regression (PLSR) and random forest regression (RF) models were established to estimate PNC through fusing VIs and color moments. The results demonstrated that the fusion of VIs and color moments as inputs yielded higher accuracies of PNC estimation compared to VIs or color moments as input; the RF models based on the combination of VIs and color moments (R<sup>2</sup> ranging from 0.69 to 0.91 and NRMSE ranging from 0.07 to 0.13) showed similar performances to the PLSR models (R<sup>2</sup> ranging from 0.68 to 0.87 and NRMSE ranging from 0.10 to 0.29); Among the top five important variables in the RF models, there was at least one variable which belonged to the color moments in different datasets, indicating the significant contribution of color moments in improving PNC estimation accuracy. This revealed the great potential of combination of RGB-VIs and color moments for the estimation of rice PNC.https://www.mdpi.com/2072-4292/13/9/1620UAVplant nitrogen concentrationRGB-VIscolor momentsPLSRRF |
| spellingShingle | Haixiao Ge Haitao Xiang Fei Ma Zhenwang Li Zhengchao Qiu Zhengzheng Tan Changwen Du Estimating Plant Nitrogen Concentration of Rice through Fusing Vegetation Indices and Color Moments Derived from UAV-RGB Images Remote Sensing UAV plant nitrogen concentration RGB-VIs color moments PLSR RF |
| title | Estimating Plant Nitrogen Concentration of Rice through Fusing Vegetation Indices and Color Moments Derived from UAV-RGB Images |
| title_full | Estimating Plant Nitrogen Concentration of Rice through Fusing Vegetation Indices and Color Moments Derived from UAV-RGB Images |
| title_fullStr | Estimating Plant Nitrogen Concentration of Rice through Fusing Vegetation Indices and Color Moments Derived from UAV-RGB Images |
| title_full_unstemmed | Estimating Plant Nitrogen Concentration of Rice through Fusing Vegetation Indices and Color Moments Derived from UAV-RGB Images |
| title_short | Estimating Plant Nitrogen Concentration of Rice through Fusing Vegetation Indices and Color Moments Derived from UAV-RGB Images |
| title_sort | estimating plant nitrogen concentration of rice through fusing vegetation indices and color moments derived from uav rgb images |
| topic | UAV plant nitrogen concentration RGB-VIs color moments PLSR RF |
| url | https://www.mdpi.com/2072-4292/13/9/1620 |
| work_keys_str_mv | AT haixiaoge estimatingplantnitrogenconcentrationofricethroughfusingvegetationindicesandcolormomentsderivedfromuavrgbimages AT haitaoxiang estimatingplantnitrogenconcentrationofricethroughfusingvegetationindicesandcolormomentsderivedfromuavrgbimages AT feima estimatingplantnitrogenconcentrationofricethroughfusingvegetationindicesandcolormomentsderivedfromuavrgbimages AT zhenwangli estimatingplantnitrogenconcentrationofricethroughfusingvegetationindicesandcolormomentsderivedfromuavrgbimages AT zhengchaoqiu estimatingplantnitrogenconcentrationofricethroughfusingvegetationindicesandcolormomentsderivedfromuavrgbimages AT zhengzhengtan estimatingplantnitrogenconcentrationofricethroughfusingvegetationindicesandcolormomentsderivedfromuavrgbimages AT changwendu estimatingplantnitrogenconcentrationofricethroughfusingvegetationindicesandcolormomentsderivedfromuavrgbimages |