Advanced search
1 file | 1.63 MB

Automated spectral feature extraction from hyperspectral images to differentiate weedy rice and barnyard grass from a rice crop

Author
Organization
Abstract
Barnyard grass (Echinochloa crusgalli) and weedy rice (Oryza sativa f. spontanea) are two common and troublesome weed species in rice (Oryza sativa L.) crop. They cause significant yield loss in rice production while it is difficult to differentiate them for site-specific weed management. In this paper, we aimed to develop a classification model with important spectral features to recognize these two weeds and rice based on hyperspectral imaging techniques. There were 287 plant leaf samples in total which were scanned by the hyperspectral imaging systems within the spectral range from 380 nm to 1080 nm. After obtaining hyperspectral images, we first developed an algorithmic pipeline to automatically extract spectral features from line scan hyperspectral images. Then the raw spectral features were subjected to wavelet transformation for noise reduction. Random forests and support vector machine models were developed with the optimal hyperparameters to compare their performances in the test set. Moreover, feature selection was explored through successive projection algorithm (SPA). It is shown that the weighted support vector machine with 6 spectral features selected by SPA can achieve 100%, 100%, and 92% recognition rates for barnyard grass, weedy rice and rice, respectively. Furthermore, the selected 6 wavelengths (415 nm, 561 nm, 687 nm, 705 nm, 735 nm, 1007 nm) have the potential to design a customized optical sensor for these two weeds and rice discrimination in practice.
Keywords
Weed discrimination, Hyperspectral imaging, Support vector machine, Hyperparameter tuning, Feature engineering, ORYZA-SATIVA, DISCRIMINATION, ALGORITHM, MODELS

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 1.63 MB

Citation

Please use this url to cite or link to this publication:

Chicago
Zhang, Yanchao, Junfeng Gao, Haiyan Cen, Yonglian Lu, Xiaoyue Yu, Yong He, and Jan Pieters. 2019. “Automated Spectral Feature Extraction from Hyperspectral Images to Differentiate Weedy Rice and Barnyard Grass from a Rice Crop.” Computers and Electronics in Agriculture 159: 42–49.
APA
Zhang, Yanchao, Gao, J., Cen, H., Lu, Y., Yu, X., He, Y., & Pieters, J. (2019). Automated spectral feature extraction from hyperspectral images to differentiate weedy rice and barnyard grass from a rice crop. COMPUTERS AND ELECTRONICS IN AGRICULTURE, 159, 42–49.
Vancouver
1.
Zhang Y, Gao J, Cen H, Lu Y, Yu X, He Y, et al. Automated spectral feature extraction from hyperspectral images to differentiate weedy rice and barnyard grass from a rice crop. COMPUTERS AND ELECTRONICS IN AGRICULTURE. 2019;159:42–9.
MLA
Zhang, Yanchao et al. “Automated Spectral Feature Extraction from Hyperspectral Images to Differentiate Weedy Rice and Barnyard Grass from a Rice Crop.” COMPUTERS AND ELECTRONICS IN AGRICULTURE 159 (2019): 42–49. Print.
@article{8606016,
  abstract     = {Barnyard grass (Echinochloa crusgalli) and weedy rice (Oryza sativa f. spontanea) are two common and troublesome weed species in rice (Oryza sativa L.) crop. They cause significant yield loss in rice production while it is difficult to differentiate them for site-specific weed management. In this paper, we aimed to develop a classification model with important spectral features to recognize these two weeds and rice based on hyperspectral imaging techniques. There were 287 plant leaf samples in total which were scanned by the hyperspectral imaging systems within the spectral range from 380 nm to 1080 nm. After obtaining hyperspectral images, we first developed an algorithmic pipeline to automatically extract spectral features from line scan hyperspectral images. Then the raw spectral features were subjected to wavelet transformation for noise reduction. Random forests and support vector machine models were developed with the optimal hyperparameters to compare their performances in the test set. Moreover, feature selection was explored through successive projection algorithm (SPA). It is shown that the weighted support vector machine with 6 spectral features selected by SPA can achieve 100%, 100%, and 92% recognition rates for barnyard grass, weedy rice and rice, respectively. Furthermore, the selected 6 wavelengths (415 nm, 561 nm, 687 nm, 705 nm, 735 nm, 1007 nm) have the potential to design a customized optical sensor for these two weeds and rice discrimination in practice.},
  author       = {Zhang, Yanchao and Gao, Junfeng and Cen, Haiyan and Lu, Yonglian and Yu, Xiaoyue and He, Yong and Pieters, Jan},
  issn         = {0168-1699},
  journal      = {COMPUTERS AND ELECTRONICS IN AGRICULTURE},
  keywords     = {Weed discrimination,Hyperspectral imaging,Support vector machine,Hyperparameter tuning,Feature engineering,ORYZA-SATIVA,DISCRIMINATION,ALGORITHM,MODELS},
  language     = {eng},
  pages        = {42--49},
  title        = {Automated spectral feature extraction from hyperspectral images to differentiate weedy rice and barnyard grass from a rice crop},
  url          = {http://dx.doi.org/10.1016/j.compag.2019.02.018},
  volume       = {159},
  year         = {2019},
}

Altmetric
View in Altmetric
Web of Science
Times cited: