Chlorophyll content for millet leaf using hyperspectral imaging and an attention-convolutional neural network
ABSTRACT: Chlorophyll is a major factor affecting photosynthesis; and consequently, crop growth and yield. In this study, we devised a chlorophyll-content detection model for millet leaves in different stages of growth based on hyperspectral data. The hyperspectral images of millet leaves were obtai...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Universidade Federal de Santa Maria
2020-04-01
|
| Series: | Ciência Rural |
| Subjects: | |
| Online Access: | http://www.scielo.br/scielo.php?script=sci_arttext&pid=S0103-84782020000300205&tlng=en |
| _version_ | 1818951142101483520 |
|---|---|
| author | Wang Xiaoyan Li Zhiwei Wang Wenjun Wang Jiawei |
| author_facet | Wang Xiaoyan Li Zhiwei Wang Wenjun Wang Jiawei |
| author_sort | Wang Xiaoyan |
| collection | DOAJ |
| description | ABSTRACT: Chlorophyll is a major factor affecting photosynthesis; and consequently, crop growth and yield. In this study, we devised a chlorophyll-content detection model for millet leaves in different stages of growth based on hyperspectral data. The hyperspectral images of millet leaves were obtained under a wavelength range of 380-1000 nm using a hyperspectral imager. Threshold segmentation was performed with near-infrared (NIR) reflectance and normalized difference vegetation index (NDVI) to intelligently acquire the regions of interest (ROI). Furthermore, raw spectral data were preprocessed using multivariate scatter correction (MSC). A correlation coefficient-successive projections algorithm (CC-SPA) was used to extract the characteristic wavelengths, and the characteristic parameters were extracted based on the spectral and image information. A partial least squares regression (PLSR) prediction model was established based on the single characteristic parameter and multi-characteristic parameter fusion. The determination coefficient (Rv 2) and the root-mean-square error (RMSEv) of the validation set for the multi-characteristic parameter fusion model were reported to be 0.813 and 1.766, respectively, which are higher than those obtained by the single characteristic parameter model. Based on the multi-characteristic parameter fusion, an attention-convolutional neural network (attention-CNN) (Rv 2 = 0.839, RMSEv = 1.451, RPD = 2.355) was established, which is more effective than the PLSR (Rv 2 = 0.813, RMSEv = 1.766, RPD = 2.167) and least squares support vector machine (LS-SVM) models (Rv 2 = 0.806, RMSEv = 1.576, RPD = 2.061). These results indicated that the combination of hyperspectral imaging and attention-CNN is beneficial to the application of nutrient element monitoring of crops. |
| first_indexed | 2024-12-20T09:29:47Z |
| format | Article |
| id | doaj.art-9175d3fb65a14b2cbb602c46d34dcfcd |
| institution | Directory Open Access Journal |
| issn | 1678-4596 |
| language | English |
| last_indexed | 2024-12-20T09:29:47Z |
| publishDate | 2020-04-01 |
| publisher | Universidade Federal de Santa Maria |
| record_format | Article |
| series | Ciência Rural |
| spelling | doaj.art-9175d3fb65a14b2cbb602c46d34dcfcd2022-12-21T19:45:06ZengUniversidade Federal de Santa MariaCiência Rural1678-45962020-04-0150310.1590/0103-8478cr20190731Chlorophyll content for millet leaf using hyperspectral imaging and an attention-convolutional neural networkWang Xiaoyanhttps://orcid.org/0000-0002-4411-1429Li Zhiweihttps://orcid.org/0000-0001-6803-2349Wang WenjunWang JiaweiABSTRACT: Chlorophyll is a major factor affecting photosynthesis; and consequently, crop growth and yield. In this study, we devised a chlorophyll-content detection model for millet leaves in different stages of growth based on hyperspectral data. The hyperspectral images of millet leaves were obtained under a wavelength range of 380-1000 nm using a hyperspectral imager. Threshold segmentation was performed with near-infrared (NIR) reflectance and normalized difference vegetation index (NDVI) to intelligently acquire the regions of interest (ROI). Furthermore, raw spectral data were preprocessed using multivariate scatter correction (MSC). A correlation coefficient-successive projections algorithm (CC-SPA) was used to extract the characteristic wavelengths, and the characteristic parameters were extracted based on the spectral and image information. A partial least squares regression (PLSR) prediction model was established based on the single characteristic parameter and multi-characteristic parameter fusion. The determination coefficient (Rv 2) and the root-mean-square error (RMSEv) of the validation set for the multi-characteristic parameter fusion model were reported to be 0.813 and 1.766, respectively, which are higher than those obtained by the single characteristic parameter model. Based on the multi-characteristic parameter fusion, an attention-convolutional neural network (attention-CNN) (Rv 2 = 0.839, RMSEv = 1.451, RPD = 2.355) was established, which is more effective than the PLSR (Rv 2 = 0.813, RMSEv = 1.766, RPD = 2.167) and least squares support vector machine (LS-SVM) models (Rv 2 = 0.806, RMSEv = 1.576, RPD = 2.061). These results indicated that the combination of hyperspectral imaging and attention-CNN is beneficial to the application of nutrient element monitoring of crops.http://www.scielo.br/scielo.php?script=sci_arttext&pid=S0103-84782020000300205&tlng=enchlorophyll contentmulti-characteristic parameters fusionattention-CNNhyperspectral imaging technology. |
| spellingShingle | Wang Xiaoyan Li Zhiwei Wang Wenjun Wang Jiawei Chlorophyll content for millet leaf using hyperspectral imaging and an attention-convolutional neural network Ciência Rural chlorophyll content multi-characteristic parameters fusion attention-CNN hyperspectral imaging technology. |
| title | Chlorophyll content for millet leaf using hyperspectral imaging and an attention-convolutional neural network |
| title_full | Chlorophyll content for millet leaf using hyperspectral imaging and an attention-convolutional neural network |
| title_fullStr | Chlorophyll content for millet leaf using hyperspectral imaging and an attention-convolutional neural network |
| title_full_unstemmed | Chlorophyll content for millet leaf using hyperspectral imaging and an attention-convolutional neural network |
| title_short | Chlorophyll content for millet leaf using hyperspectral imaging and an attention-convolutional neural network |
| title_sort | chlorophyll content for millet leaf using hyperspectral imaging and an attention convolutional neural network |
| topic | chlorophyll content multi-characteristic parameters fusion attention-CNN hyperspectral imaging technology. |
| url | http://www.scielo.br/scielo.php?script=sci_arttext&pid=S0103-84782020000300205&tlng=en |
| work_keys_str_mv | AT wangxiaoyan chlorophyllcontentformilletleafusinghyperspectralimagingandanattentionconvolutionalneuralnetwork AT lizhiwei chlorophyllcontentformilletleafusinghyperspectralimagingandanattentionconvolutionalneuralnetwork AT wangwenjun chlorophyllcontentformilletleafusinghyperspectralimagingandanattentionconvolutionalneuralnetwork AT wangjiawei chlorophyllcontentformilletleafusinghyperspectralimagingandanattentionconvolutionalneuralnetwork |