Spectrum- and RGB-D-Based Image Fusion for the Prediction of Nitrogen Accumulation in Wheat
The accurate estimation of nitrogen accumulation is of great significance to nitrogen fertilizer management in wheat production. To overcome the shortcomings of spectral technology, which ignores the anisotropy of canopy structure when predicting the nitrogen accumulation in wheat, resulting in low...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-12-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/12/24/4040 |
| _version_ | 1797545087838715904 |
|---|---|
| author | Ke Xu Jingchao Zhang Huaimin Li Weixing Cao Yan Zhu Xiaoping Jiang Jun Ni |
| author_facet | Ke Xu Jingchao Zhang Huaimin Li Weixing Cao Yan Zhu Xiaoping Jiang Jun Ni |
| author_sort | Ke Xu |
| collection | DOAJ |
| description | The accurate estimation of nitrogen accumulation is of great significance to nitrogen fertilizer management in wheat production. To overcome the shortcomings of spectral technology, which ignores the anisotropy of canopy structure when predicting the nitrogen accumulation in wheat, resulting in low accuracy and unstable prediction results, we propose a method for predicting wheat nitrogen accumulation based on the fusion of spectral and canopy structure features. After depth images are repaired using a hole-filling algorithm, RGB images and depth images are fused through IHS transformation, and textural features of the fused images are then extracted in order to express the three-dimensional structural information of the canopy. The fused images contain depth information of the canopy, which breaks through the limitation of extracting canopy structure features from a two-dimensional image. By comparing the experimental results of multiple regression analyses and BP neural networks, we found that the characteristics of the canopy structure effectively compensated for the model prediction of nitrogen accumulation based only on spectral characteristics. Our prediction model displayed better accuracy and stability, with prediction accuracy values (R<sup>2</sup>) based on BP neural network for the leaf layer nitrogen accumulation (LNA) and shoot nitrogen accumulation (SNA) during a full growth period of 0.74 and 0.73, respectively, and corresponding relative root mean square errors (RRMSEs) of 40.13% and 35.73%. |
| first_indexed | 2024-03-10T14:10:32Z |
| format | Article |
| id | doaj.art-3096ff9fa34a4056bac8c0a58f9e622a |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T14:10:32Z |
| publishDate | 2020-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-3096ff9fa34a4056bac8c0a58f9e622a2023-11-21T00:11:16ZengMDPI AGRemote Sensing2072-42922020-12-011224404010.3390/rs12244040Spectrum- and RGB-D-Based Image Fusion for the Prediction of Nitrogen Accumulation in WheatKe Xu0Jingchao Zhang1Huaimin Li2Weixing Cao3Yan Zhu4Xiaoping Jiang5Jun Ni6College of Agriculture, Nanjing Agricultural University, Nanjing 210095, ChinaNanjing Institute of Agricultural Mechanization, Ministry of Agriculture and Rural Affairs, Nanjing 210014, ChinaCollege of Agriculture, Nanjing Agricultural University, Nanjing 210095, ChinaCollege of Agriculture, Nanjing Agricultural University, Nanjing 210095, ChinaCollege of Agriculture, Nanjing Agricultural University, Nanjing 210095, ChinaCollege of Agriculture, Nanjing Agricultural University, Nanjing 210095, ChinaCollege of Agriculture, Nanjing Agricultural University, Nanjing 210095, ChinaThe accurate estimation of nitrogen accumulation is of great significance to nitrogen fertilizer management in wheat production. To overcome the shortcomings of spectral technology, which ignores the anisotropy of canopy structure when predicting the nitrogen accumulation in wheat, resulting in low accuracy and unstable prediction results, we propose a method for predicting wheat nitrogen accumulation based on the fusion of spectral and canopy structure features. After depth images are repaired using a hole-filling algorithm, RGB images and depth images are fused through IHS transformation, and textural features of the fused images are then extracted in order to express the three-dimensional structural information of the canopy. The fused images contain depth information of the canopy, which breaks through the limitation of extracting canopy structure features from a two-dimensional image. By comparing the experimental results of multiple regression analyses and BP neural networks, we found that the characteristics of the canopy structure effectively compensated for the model prediction of nitrogen accumulation based only on spectral characteristics. Our prediction model displayed better accuracy and stability, with prediction accuracy values (R<sup>2</sup>) based on BP neural network for the leaf layer nitrogen accumulation (LNA) and shoot nitrogen accumulation (SNA) during a full growth period of 0.74 and 0.73, respectively, and corresponding relative root mean square errors (RRMSEs) of 40.13% and 35.73%.https://www.mdpi.com/2072-4292/12/24/4040RGB-D imagefused imagespectrumwheat nitrogen accumulation |
| spellingShingle | Ke Xu Jingchao Zhang Huaimin Li Weixing Cao Yan Zhu Xiaoping Jiang Jun Ni Spectrum- and RGB-D-Based Image Fusion for the Prediction of Nitrogen Accumulation in Wheat Remote Sensing RGB-D image fused image spectrum wheat nitrogen accumulation |
| title | Spectrum- and RGB-D-Based Image Fusion for the Prediction of Nitrogen Accumulation in Wheat |
| title_full | Spectrum- and RGB-D-Based Image Fusion for the Prediction of Nitrogen Accumulation in Wheat |
| title_fullStr | Spectrum- and RGB-D-Based Image Fusion for the Prediction of Nitrogen Accumulation in Wheat |
| title_full_unstemmed | Spectrum- and RGB-D-Based Image Fusion for the Prediction of Nitrogen Accumulation in Wheat |
| title_short | Spectrum- and RGB-D-Based Image Fusion for the Prediction of Nitrogen Accumulation in Wheat |
| title_sort | spectrum and rgb d based image fusion for the prediction of nitrogen accumulation in wheat |
| topic | RGB-D image fused image spectrum wheat nitrogen accumulation |
| url | https://www.mdpi.com/2072-4292/12/24/4040 |
| work_keys_str_mv | AT kexu spectrumandrgbdbasedimagefusionforthepredictionofnitrogenaccumulationinwheat AT jingchaozhang spectrumandrgbdbasedimagefusionforthepredictionofnitrogenaccumulationinwheat AT huaiminli spectrumandrgbdbasedimagefusionforthepredictionofnitrogenaccumulationinwheat AT weixingcao spectrumandrgbdbasedimagefusionforthepredictionofnitrogenaccumulationinwheat AT yanzhu spectrumandrgbdbasedimagefusionforthepredictionofnitrogenaccumulationinwheat AT xiaopingjiang spectrumandrgbdbasedimagefusionforthepredictionofnitrogenaccumulationinwheat AT junni spectrumandrgbdbasedimagefusionforthepredictionofnitrogenaccumulationinwheat |