Abstract

Compressive spectral imaging systems have promising applications in the field of object classification. However, for soil classification problem, conventional methods addressing this specific task often fail to produce satisfying results due to the tradeoff between the invariance and discrepancy of each soil. In this paper, we explore a liquid crystal tunable filters (LCTF)-based system and propose a three-dimensional convolutional neural network (3D-CNN) for soil classification. We first obtain a set of soil compressive measurements via a low spatial resolution detector, and soil hyperspectral images are reconstructed with improved resolution in spatial as well as spectral domains by a compressive sensing (CS) method. Furthermore, different from previous spectral-based object classification methods restricted to extract features from each type independently, on account of the potential of spectral property on individual solid, our method proposes to apply the principal component analysis(PCA) to achieve a dimensionality reduction in the spectral domain. Then, we explore a differential perception model for flexible feature extraction, and finally introduce a 3D-CNN framework to solve the multi-soil classification problem. Experimental results demonstrate that our algorithm not only is able to accelerate the ability of feature discriminability but also performs against conventional soil classification methods.

© 2019 Optical Society of America under the terms of the OSA Open Access Publishing Agreement

Full Article  |  PDF Article
OSA Recommended Articles
Compressive spectral imaging system based on liquid crystal tunable filter

Xi Wang, Yuhan Zhang, Xu Ma, Tingfa Xu, and Gonzalo R. Arce
Opt. Express 26(19) 25226-25243 (2018)

DeepCubeNet: reconstruction of spectrally compressive sensed hyperspectral images with deep neural networks

Daniel Gedalin, Yaniv Oiknine, and Adrian Stern
Opt. Express 27(24) 35811-35822 (2019)

Classification of morphologically similar algae and cyanobacteria using Mueller matrix imaging and convolutional neural networks

Xianpeng Li, Ran Liao, Jialing Zhou, Priscilla T. Y. Leung, Meng Yan, and Hui Ma
Appl. Opt. 56(23) 6520-6530 (2017)

References

  • View by:
  • |
  • |
  • |

  1. Z. Shi, Q. L. Wang, J. Peng, W. J. Ji, H. J. Liu, X. Li, and R. A. Viscarra Rossel, “Development of a national VNIR soil-spectral library for soil classification and prediction of organic matter concentrations,” Sci. China Earth Sci. 57, 1671–1680 (2014).
    [Crossref]
  2. J. Tian and W. D. Philpot, “Soil directional (biconical) reflectance in the principal plane with varied illumination angle under dry and saturated conditions,” Opt. Express 26, 23883 (2018).
    [Crossref] [PubMed]
  3. J. Li, W. Huang, X. Tian, C. Wang, S. Fan, and C. Zhao, “Fast detection and visualization of early decay in citrus using Vis-NIR hyperspectral imaging,” Comput. Electron. Agric. 127, 582–592 (2016).
    [Crossref]
  4. B. Zhang, J. Li, S. Fan, W. Huang, C. Zhao, C. Liu, and D. Huang, “Hyperspectral imaging combined with multivariate analysis and band math for detection of common defects on peaches (Prunus persica),” Comput. Electron. Agric. 114, 14–24 (2015).
    [Crossref]
  5. Z. Lee, S. Shang, G. Lin, J. Chen, and D. Doxaran, “On the modeling of hyperspectral remote-sensing reflectance of high-sediment-load waters in the visible to shortwave-infrared domain,” Appl. Opt. 55, 1738 (2016).
    [Crossref] [PubMed]
  6. D. R. Thompson, J. W. Boardman, M. L. Eastwood, and R. O. Green, “A large airborne survey of Earth’s visible-infrared spectral dimensionality,” Opt. Express 25, 9186 (2017).
    [Crossref] [PubMed]
  7. D. L. Donoho, “Compressed sensing,” IEEE Transactions on Inf. Theory 52(4), 1289–1306 (2006).
    [Crossref]
  8. W. Feng, H. Rueda, C. Fu, G. R. Arce, W. He, and Q. Chen, “3D compressive spectral integral imaging,” Opt. Express 24, 24859 (2016).
    [Crossref] [PubMed]
  9. H. Arguello and G. Arce, “Code Aperture Agile Spectral Imaging (CAASI),” in Imaging Systems Applications, OSA Technical Digest (CD) (Optical Society of America, 2011), paper ITuA4.
    [Crossref]
  10. Y. Wu, I. O. Mirza, G. R. Arce, and D. W. Prather, “Development of a digital-micromirror-device-based multishot snapshot spectral imaging system,” Opt. Lett. 36, 2692 (2011).
    [Crossref] [PubMed]
  11. N. R. Rao, P. K. Garg, and S. K. Ghosh, “Development of an agricultural crops spectral library and classification of crops at cultivar level using hyperspectral data,” Precis. Agric. 8, 173–185 (2007).
    [Crossref]
  12. D. Ramakrishnan and R. Bharti, “Hyperspectral remote sensing and geological applications,” Curr. Sci. 108, 879–891 (2015).
  13. O. E. Adedipe, B. A Dawson-Andoh, J. Slahor, and L. Osborn A, “Classification of red oak (Quercus rubra) and white oak (Quercus alba) wood using a near infrared spectrometer and soft independent modelling of class analogies,” J. Near Infrared Spectrosc. 16, 49–57 (2008).
    [Crossref]
  14. J. Zhao, Q. Chen, J. Cai, and Q. Ouyang, “Automated tea quality classification by hyperspectral imaging,” Appl. Opt. 48, 3557 (2009).
    [Crossref] [PubMed]
  15. C. Yang, J. H. Everitt, and J. M. Bradford, “Yield Estimation from Hyperspectral Imagery Using Spectral Angle Mapper (SAM),” Transactions ASABE 51, 729–737 (2013).
    [Crossref]
  16. F. van der Meer, “The effectiveness of spectral similarity measures for the analysis of hyperspectral imagery,” Int. J. Appl. Earth Obs. Geoinformation 8, 3–17 (2006).
    [Crossref]
  17. K. Huang, S. Li, X. Kang, and L. Fang, “Spectral-Spatial Hyperspectral Image Classification Based on KNN,” Sens. Imaging 17, 1–13 (2016).
    [Crossref]
  18. V. M. Dolas and P. U. Joshi, “A Novel Approach for Classification of Soil and Crop Prediction,” Int. J. Comput. Sci. Mob. Comput. 7, 20–24 (2018).
  19. G. Mountrakis, J. Im, and C. Ogole, “Support vector machines in remote sensing: A review,” ISPRS J. Photogramm. Remote. Sens. 66, 247–259 (2011).
    [Crossref]
  20. M. Pal and G. M. Foody, “Feature selection for classification of hyperspectral data by SVM,” IEEE Transactions on Geosci. Remote. Sens. 48, 2297–2307 (2010).
    [Crossref]
  21. E. C. Brevik, C. Calzolari, B. A. Miller, P. Pereira, C. Kabala, A. Baumgarten, and A. Jordán, “Soil mapping, classification, and pedologic modeling: History and future directions,” Geoderma 264, 256–274 (2016).
    [Crossref]
  22. Y. Ogen, N. Goldshleger, and E. Ben-Dor, “3D spectral analysis in the VNIR-SWIR spectral region as a tool for soil classification,” Geoderma 302, 100–110 (2017).
    [Crossref]
  23. M. Steffens and H. Buddenbaum, “Laboratory imaging spectroscopy of a stagnic Luvisol profile - High resolution soil characterisation, classification and mapping of elemental concentrations,” Geoderma 195-196122–132 (2013).
    [Crossref]
  24. A. D. Vibhute, K. V. Kale, R. K. Dhumal, and S. C. Mehrotra, “Soil type classification and mapping using hyperspectral remote sensing data,” in International Conference on Man and Machine Interfacing, (IEEE, 2016), pp.1–4.
  25. S. Jia, H. Li, Y. Wang, R. Tong, and Q. Li, “Hyperspectral imaging analysis for the classification of soil types and the determination of soil total nitrogen,” Sensors 17, 1–14 (2017).
    [Crossref]
  26. A. Krizhevsk, I. Sutskever, and G. E. Hinton, “ImageNet Classification with Deep Convolutional Neural Networks,” in Neural Information Processing Systems, (Academic, 2012), pp.1097–1105.
  27. C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich, “Going Deeper with Convolutions,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, (IEEE, 2015), pp.1–9.
  28. K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, (IEEE, 2016), pp.770–778.
  29. W. Hu, Y. Huang, L. Wei, F. Zhang, and H. Li, “Deep Convolutional Neural Networks for Hyperspectral Image Classification,” J. Sensors 2015, 258619(2015).
    [Crossref]
  30. J. Yue, W. Zhao, S. Mao, and H. Liu, “Spectral-spatial classification of hyperspectral images using deep convolutional neural networks,” Remote. Sens. Lett. 6(6), 468–477 (2015).
    [Crossref]
  31. K. Makantasis, K. Karantzalos, A. Doulamis, and N. Doulamis, “Deep supervised learning for hyperspectral data classification through convolutional neural networks,” in IEEE International Geoscience and Remote Sensing Symposium, (IEEE, 2015), pp.4959–4962.
  32. H. Liang and Q. Li, “Hyperspectral imagery classification using sparse representations of convolutional neural network features,” Remote. Sens. 8, 99 (2016).
    [Crossref]
  33. Y. Chen, H. Jiang, C. Li, X. Jia, and P. Ghamisi, “Deep Feature Extraction and Classification of Hyperspectral Images Based on Convolutional Neural Networks,” IEEE Transactions on Geosci. Remote. Sens. 54, 6232–6251 (2016).
    [Crossref]
  34. Y. Li, H. Zhang, and Q. Shen, “Spectral-spatial classification of hyperspectral imagery with 3D convolutional neural network,” Remote. Sens. 9, 67 (2017).
    [Crossref]
  35. X. Wang, Y. Zhang, X. Ma, T. Xu, and G. R. Arce, “Compressive spectral imaging system based on liquid crystal tunable filter,” Opt. Express 26, 25226 (2018).
    [Crossref] [PubMed]
  36. S. Ji, W. Xu, M. Yang, and K. Yu, “3D Convolutional neural networks for human action recognition,” IEEE Transactions on Pattern Analysis Mach. Intell. 35, 221–231 (2013).
    [Crossref]
  37. A. A. Gowen, C. P. O. Donnell, M. Taghizadeh, P. J. Cullenb, J. M. Frias, and G. Downey, “Hyperspectral imaging combined with principal component analysis for bruise damage detection on white mushrooms (Agaricus bisporus),” J. Chemom. 22, 259–267 (2008).
    [Crossref]
  38. D. J. Hand and R. J. Till, “A Simple Generalisation of the Area Under the ROC Curve for Multiple Class Classification Problems,” Mach. Learn. 45, 171–186 (2001).
    [Crossref]

2018 (3)

2017 (4)

Y. Ogen, N. Goldshleger, and E. Ben-Dor, “3D spectral analysis in the VNIR-SWIR spectral region as a tool for soil classification,” Geoderma 302, 100–110 (2017).
[Crossref]

S. Jia, H. Li, Y. Wang, R. Tong, and Q. Li, “Hyperspectral imaging analysis for the classification of soil types and the determination of soil total nitrogen,” Sensors 17, 1–14 (2017).
[Crossref]

Y. Li, H. Zhang, and Q. Shen, “Spectral-spatial classification of hyperspectral imagery with 3D convolutional neural network,” Remote. Sens. 9, 67 (2017).
[Crossref]

D. R. Thompson, J. W. Boardman, M. L. Eastwood, and R. O. Green, “A large airborne survey of Earth’s visible-infrared spectral dimensionality,” Opt. Express 25, 9186 (2017).
[Crossref] [PubMed]

2016 (7)

W. Feng, H. Rueda, C. Fu, G. R. Arce, W. He, and Q. Chen, “3D compressive spectral integral imaging,” Opt. Express 24, 24859 (2016).
[Crossref] [PubMed]

J. Li, W. Huang, X. Tian, C. Wang, S. Fan, and C. Zhao, “Fast detection and visualization of early decay in citrus using Vis-NIR hyperspectral imaging,” Comput. Electron. Agric. 127, 582–592 (2016).
[Crossref]

Z. Lee, S. Shang, G. Lin, J. Chen, and D. Doxaran, “On the modeling of hyperspectral remote-sensing reflectance of high-sediment-load waters in the visible to shortwave-infrared domain,” Appl. Opt. 55, 1738 (2016).
[Crossref] [PubMed]

K. Huang, S. Li, X. Kang, and L. Fang, “Spectral-Spatial Hyperspectral Image Classification Based on KNN,” Sens. Imaging 17, 1–13 (2016).
[Crossref]

E. C. Brevik, C. Calzolari, B. A. Miller, P. Pereira, C. Kabala, A. Baumgarten, and A. Jordán, “Soil mapping, classification, and pedologic modeling: History and future directions,” Geoderma 264, 256–274 (2016).
[Crossref]

H. Liang and Q. Li, “Hyperspectral imagery classification using sparse representations of convolutional neural network features,” Remote. Sens. 8, 99 (2016).
[Crossref]

Y. Chen, H. Jiang, C. Li, X. Jia, and P. Ghamisi, “Deep Feature Extraction and Classification of Hyperspectral Images Based on Convolutional Neural Networks,” IEEE Transactions on Geosci. Remote. Sens. 54, 6232–6251 (2016).
[Crossref]

2015 (4)

W. Hu, Y. Huang, L. Wei, F. Zhang, and H. Li, “Deep Convolutional Neural Networks for Hyperspectral Image Classification,” J. Sensors 2015, 258619(2015).
[Crossref]

J. Yue, W. Zhao, S. Mao, and H. Liu, “Spectral-spatial classification of hyperspectral images using deep convolutional neural networks,” Remote. Sens. Lett. 6(6), 468–477 (2015).
[Crossref]

D. Ramakrishnan and R. Bharti, “Hyperspectral remote sensing and geological applications,” Curr. Sci. 108, 879–891 (2015).

B. Zhang, J. Li, S. Fan, W. Huang, C. Zhao, C. Liu, and D. Huang, “Hyperspectral imaging combined with multivariate analysis and band math for detection of common defects on peaches (Prunus persica),” Comput. Electron. Agric. 114, 14–24 (2015).
[Crossref]

2014 (1)

Z. Shi, Q. L. Wang, J. Peng, W. J. Ji, H. J. Liu, X. Li, and R. A. Viscarra Rossel, “Development of a national VNIR soil-spectral library for soil classification and prediction of organic matter concentrations,” Sci. China Earth Sci. 57, 1671–1680 (2014).
[Crossref]

2013 (3)

C. Yang, J. H. Everitt, and J. M. Bradford, “Yield Estimation from Hyperspectral Imagery Using Spectral Angle Mapper (SAM),” Transactions ASABE 51, 729–737 (2013).
[Crossref]

M. Steffens and H. Buddenbaum, “Laboratory imaging spectroscopy of a stagnic Luvisol profile - High resolution soil characterisation, classification and mapping of elemental concentrations,” Geoderma 195-196122–132 (2013).
[Crossref]

S. Ji, W. Xu, M. Yang, and K. Yu, “3D Convolutional neural networks for human action recognition,” IEEE Transactions on Pattern Analysis Mach. Intell. 35, 221–231 (2013).
[Crossref]

2011 (2)

G. Mountrakis, J. Im, and C. Ogole, “Support vector machines in remote sensing: A review,” ISPRS J. Photogramm. Remote. Sens. 66, 247–259 (2011).
[Crossref]

Y. Wu, I. O. Mirza, G. R. Arce, and D. W. Prather, “Development of a digital-micromirror-device-based multishot snapshot spectral imaging system,” Opt. Lett. 36, 2692 (2011).
[Crossref] [PubMed]

2010 (1)

M. Pal and G. M. Foody, “Feature selection for classification of hyperspectral data by SVM,” IEEE Transactions on Geosci. Remote. Sens. 48, 2297–2307 (2010).
[Crossref]

2009 (1)

2008 (2)

O. E. Adedipe, B. A Dawson-Andoh, J. Slahor, and L. Osborn A, “Classification of red oak (Quercus rubra) and white oak (Quercus alba) wood using a near infrared spectrometer and soft independent modelling of class analogies,” J. Near Infrared Spectrosc. 16, 49–57 (2008).
[Crossref]

A. A. Gowen, C. P. O. Donnell, M. Taghizadeh, P. J. Cullenb, J. M. Frias, and G. Downey, “Hyperspectral imaging combined with principal component analysis for bruise damage detection on white mushrooms (Agaricus bisporus),” J. Chemom. 22, 259–267 (2008).
[Crossref]

2007 (1)

N. R. Rao, P. K. Garg, and S. K. Ghosh, “Development of an agricultural crops spectral library and classification of crops at cultivar level using hyperspectral data,” Precis. Agric. 8, 173–185 (2007).
[Crossref]

2006 (2)

D. L. Donoho, “Compressed sensing,” IEEE Transactions on Inf. Theory 52(4), 1289–1306 (2006).
[Crossref]

F. van der Meer, “The effectiveness of spectral similarity measures for the analysis of hyperspectral imagery,” Int. J. Appl. Earth Obs. Geoinformation 8, 3–17 (2006).
[Crossref]

2001 (1)

D. J. Hand and R. J. Till, “A Simple Generalisation of the Area Under the ROC Curve for Multiple Class Classification Problems,” Mach. Learn. 45, 171–186 (2001).
[Crossref]

Adedipe, O. E.

Anguelov, D.

C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich, “Going Deeper with Convolutions,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, (IEEE, 2015), pp.1–9.

Arce, G.

H. Arguello and G. Arce, “Code Aperture Agile Spectral Imaging (CAASI),” in Imaging Systems Applications, OSA Technical Digest (CD) (Optical Society of America, 2011), paper ITuA4.
[Crossref]

Arce, G. R.

Arguello, H.

H. Arguello and G. Arce, “Code Aperture Agile Spectral Imaging (CAASI),” in Imaging Systems Applications, OSA Technical Digest (CD) (Optical Society of America, 2011), paper ITuA4.
[Crossref]

Baumgarten, A.

E. C. Brevik, C. Calzolari, B. A. Miller, P. Pereira, C. Kabala, A. Baumgarten, and A. Jordán, “Soil mapping, classification, and pedologic modeling: History and future directions,” Geoderma 264, 256–274 (2016).
[Crossref]

Ben-Dor, E.

Y. Ogen, N. Goldshleger, and E. Ben-Dor, “3D spectral analysis in the VNIR-SWIR spectral region as a tool for soil classification,” Geoderma 302, 100–110 (2017).
[Crossref]

Bharti, R.

D. Ramakrishnan and R. Bharti, “Hyperspectral remote sensing and geological applications,” Curr. Sci. 108, 879–891 (2015).

Boardman, J. W.

Bradford, J. M.

C. Yang, J. H. Everitt, and J. M. Bradford, “Yield Estimation from Hyperspectral Imagery Using Spectral Angle Mapper (SAM),” Transactions ASABE 51, 729–737 (2013).
[Crossref]

Brevik, E. C.

E. C. Brevik, C. Calzolari, B. A. Miller, P. Pereira, C. Kabala, A. Baumgarten, and A. Jordán, “Soil mapping, classification, and pedologic modeling: History and future directions,” Geoderma 264, 256–274 (2016).
[Crossref]

Buddenbaum, H.

M. Steffens and H. Buddenbaum, “Laboratory imaging spectroscopy of a stagnic Luvisol profile - High resolution soil characterisation, classification and mapping of elemental concentrations,” Geoderma 195-196122–132 (2013).
[Crossref]

Cai, J.

Calzolari, C.

E. C. Brevik, C. Calzolari, B. A. Miller, P. Pereira, C. Kabala, A. Baumgarten, and A. Jordán, “Soil mapping, classification, and pedologic modeling: History and future directions,” Geoderma 264, 256–274 (2016).
[Crossref]

Chen, J.

Chen, Q.

Chen, Y.

Y. Chen, H. Jiang, C. Li, X. Jia, and P. Ghamisi, “Deep Feature Extraction and Classification of Hyperspectral Images Based on Convolutional Neural Networks,” IEEE Transactions on Geosci. Remote. Sens. 54, 6232–6251 (2016).
[Crossref]

Cullenb, P. J.

A. A. Gowen, C. P. O. Donnell, M. Taghizadeh, P. J. Cullenb, J. M. Frias, and G. Downey, “Hyperspectral imaging combined with principal component analysis for bruise damage detection on white mushrooms (Agaricus bisporus),” J. Chemom. 22, 259–267 (2008).
[Crossref]

Dawson-Andoh, B. A

Dhumal, R. K.

A. D. Vibhute, K. V. Kale, R. K. Dhumal, and S. C. Mehrotra, “Soil type classification and mapping using hyperspectral remote sensing data,” in International Conference on Man and Machine Interfacing, (IEEE, 2016), pp.1–4.

Dolas, V. M.

V. M. Dolas and P. U. Joshi, “A Novel Approach for Classification of Soil and Crop Prediction,” Int. J. Comput. Sci. Mob. Comput. 7, 20–24 (2018).

Donnell, C. P. O.

A. A. Gowen, C. P. O. Donnell, M. Taghizadeh, P. J. Cullenb, J. M. Frias, and G. Downey, “Hyperspectral imaging combined with principal component analysis for bruise damage detection on white mushrooms (Agaricus bisporus),” J. Chemom. 22, 259–267 (2008).
[Crossref]

Donoho, D. L.

D. L. Donoho, “Compressed sensing,” IEEE Transactions on Inf. Theory 52(4), 1289–1306 (2006).
[Crossref]

Doulamis, A.

K. Makantasis, K. Karantzalos, A. Doulamis, and N. Doulamis, “Deep supervised learning for hyperspectral data classification through convolutional neural networks,” in IEEE International Geoscience and Remote Sensing Symposium, (IEEE, 2015), pp.4959–4962.

Doulamis, N.

K. Makantasis, K. Karantzalos, A. Doulamis, and N. Doulamis, “Deep supervised learning for hyperspectral data classification through convolutional neural networks,” in IEEE International Geoscience and Remote Sensing Symposium, (IEEE, 2015), pp.4959–4962.

Downey, G.

A. A. Gowen, C. P. O. Donnell, M. Taghizadeh, P. J. Cullenb, J. M. Frias, and G. Downey, “Hyperspectral imaging combined with principal component analysis for bruise damage detection on white mushrooms (Agaricus bisporus),” J. Chemom. 22, 259–267 (2008).
[Crossref]

Doxaran, D.

Eastwood, M. L.

Erhan, D.

C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich, “Going Deeper with Convolutions,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, (IEEE, 2015), pp.1–9.

Everitt, J. H.

C. Yang, J. H. Everitt, and J. M. Bradford, “Yield Estimation from Hyperspectral Imagery Using Spectral Angle Mapper (SAM),” Transactions ASABE 51, 729–737 (2013).
[Crossref]

Fan, S.

J. Li, W. Huang, X. Tian, C. Wang, S. Fan, and C. Zhao, “Fast detection and visualization of early decay in citrus using Vis-NIR hyperspectral imaging,” Comput. Electron. Agric. 127, 582–592 (2016).
[Crossref]

B. Zhang, J. Li, S. Fan, W. Huang, C. Zhao, C. Liu, and D. Huang, “Hyperspectral imaging combined with multivariate analysis and band math for detection of common defects on peaches (Prunus persica),” Comput. Electron. Agric. 114, 14–24 (2015).
[Crossref]

Fang, L.

K. Huang, S. Li, X. Kang, and L. Fang, “Spectral-Spatial Hyperspectral Image Classification Based on KNN,” Sens. Imaging 17, 1–13 (2016).
[Crossref]

Feng, W.

Foody, G. M.

M. Pal and G. M. Foody, “Feature selection for classification of hyperspectral data by SVM,” IEEE Transactions on Geosci. Remote. Sens. 48, 2297–2307 (2010).
[Crossref]

Frias, J. M.

A. A. Gowen, C. P. O. Donnell, M. Taghizadeh, P. J. Cullenb, J. M. Frias, and G. Downey, “Hyperspectral imaging combined with principal component analysis for bruise damage detection on white mushrooms (Agaricus bisporus),” J. Chemom. 22, 259–267 (2008).
[Crossref]

Fu, C.

Garg, P. K.

N. R. Rao, P. K. Garg, and S. K. Ghosh, “Development of an agricultural crops spectral library and classification of crops at cultivar level using hyperspectral data,” Precis. Agric. 8, 173–185 (2007).
[Crossref]

Ghamisi, P.

Y. Chen, H. Jiang, C. Li, X. Jia, and P. Ghamisi, “Deep Feature Extraction and Classification of Hyperspectral Images Based on Convolutional Neural Networks,” IEEE Transactions on Geosci. Remote. Sens. 54, 6232–6251 (2016).
[Crossref]

Ghosh, S. K.

N. R. Rao, P. K. Garg, and S. K. Ghosh, “Development of an agricultural crops spectral library and classification of crops at cultivar level using hyperspectral data,” Precis. Agric. 8, 173–185 (2007).
[Crossref]

Goldshleger, N.

Y. Ogen, N. Goldshleger, and E. Ben-Dor, “3D spectral analysis in the VNIR-SWIR spectral region as a tool for soil classification,” Geoderma 302, 100–110 (2017).
[Crossref]

Gowen, A. A.

A. A. Gowen, C. P. O. Donnell, M. Taghizadeh, P. J. Cullenb, J. M. Frias, and G. Downey, “Hyperspectral imaging combined with principal component analysis for bruise damage detection on white mushrooms (Agaricus bisporus),” J. Chemom. 22, 259–267 (2008).
[Crossref]

Green, R. O.

Hand, D. J.

D. J. Hand and R. J. Till, “A Simple Generalisation of the Area Under the ROC Curve for Multiple Class Classification Problems,” Mach. Learn. 45, 171–186 (2001).
[Crossref]

He, K.

K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, (IEEE, 2016), pp.770–778.

He, W.

Hinton, G. E.

A. Krizhevsk, I. Sutskever, and G. E. Hinton, “ImageNet Classification with Deep Convolutional Neural Networks,” in Neural Information Processing Systems, (Academic, 2012), pp.1097–1105.

Hu, W.

W. Hu, Y. Huang, L. Wei, F. Zhang, and H. Li, “Deep Convolutional Neural Networks for Hyperspectral Image Classification,” J. Sensors 2015, 258619(2015).
[Crossref]

Huang, D.

B. Zhang, J. Li, S. Fan, W. Huang, C. Zhao, C. Liu, and D. Huang, “Hyperspectral imaging combined with multivariate analysis and band math for detection of common defects on peaches (Prunus persica),” Comput. Electron. Agric. 114, 14–24 (2015).
[Crossref]

Huang, K.

K. Huang, S. Li, X. Kang, and L. Fang, “Spectral-Spatial Hyperspectral Image Classification Based on KNN,” Sens. Imaging 17, 1–13 (2016).
[Crossref]

Huang, W.

J. Li, W. Huang, X. Tian, C. Wang, S. Fan, and C. Zhao, “Fast detection and visualization of early decay in citrus using Vis-NIR hyperspectral imaging,” Comput. Electron. Agric. 127, 582–592 (2016).
[Crossref]

B. Zhang, J. Li, S. Fan, W. Huang, C. Zhao, C. Liu, and D. Huang, “Hyperspectral imaging combined with multivariate analysis and band math for detection of common defects on peaches (Prunus persica),” Comput. Electron. Agric. 114, 14–24 (2015).
[Crossref]

Huang, Y.

W. Hu, Y. Huang, L. Wei, F. Zhang, and H. Li, “Deep Convolutional Neural Networks for Hyperspectral Image Classification,” J. Sensors 2015, 258619(2015).
[Crossref]

Im, J.

G. Mountrakis, J. Im, and C. Ogole, “Support vector machines in remote sensing: A review,” ISPRS J. Photogramm. Remote. Sens. 66, 247–259 (2011).
[Crossref]

Ji, S.

S. Ji, W. Xu, M. Yang, and K. Yu, “3D Convolutional neural networks for human action recognition,” IEEE Transactions on Pattern Analysis Mach. Intell. 35, 221–231 (2013).
[Crossref]

Ji, W. J.

Z. Shi, Q. L. Wang, J. Peng, W. J. Ji, H. J. Liu, X. Li, and R. A. Viscarra Rossel, “Development of a national VNIR soil-spectral library for soil classification and prediction of organic matter concentrations,” Sci. China Earth Sci. 57, 1671–1680 (2014).
[Crossref]

Jia, S.

S. Jia, H. Li, Y. Wang, R. Tong, and Q. Li, “Hyperspectral imaging analysis for the classification of soil types and the determination of soil total nitrogen,” Sensors 17, 1–14 (2017).
[Crossref]

Jia, X.

Y. Chen, H. Jiang, C. Li, X. Jia, and P. Ghamisi, “Deep Feature Extraction and Classification of Hyperspectral Images Based on Convolutional Neural Networks,” IEEE Transactions on Geosci. Remote. Sens. 54, 6232–6251 (2016).
[Crossref]

Jia, Y.

C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich, “Going Deeper with Convolutions,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, (IEEE, 2015), pp.1–9.

Jiang, H.

Y. Chen, H. Jiang, C. Li, X. Jia, and P. Ghamisi, “Deep Feature Extraction and Classification of Hyperspectral Images Based on Convolutional Neural Networks,” IEEE Transactions on Geosci. Remote. Sens. 54, 6232–6251 (2016).
[Crossref]

Jordán, A.

E. C. Brevik, C. Calzolari, B. A. Miller, P. Pereira, C. Kabala, A. Baumgarten, and A. Jordán, “Soil mapping, classification, and pedologic modeling: History and future directions,” Geoderma 264, 256–274 (2016).
[Crossref]

Joshi, P. U.

V. M. Dolas and P. U. Joshi, “A Novel Approach for Classification of Soil and Crop Prediction,” Int. J. Comput. Sci. Mob. Comput. 7, 20–24 (2018).

Kabala, C.

E. C. Brevik, C. Calzolari, B. A. Miller, P. Pereira, C. Kabala, A. Baumgarten, and A. Jordán, “Soil mapping, classification, and pedologic modeling: History and future directions,” Geoderma 264, 256–274 (2016).
[Crossref]

Kale, K. V.

A. D. Vibhute, K. V. Kale, R. K. Dhumal, and S. C. Mehrotra, “Soil type classification and mapping using hyperspectral remote sensing data,” in International Conference on Man and Machine Interfacing, (IEEE, 2016), pp.1–4.

Kang, X.

K. Huang, S. Li, X. Kang, and L. Fang, “Spectral-Spatial Hyperspectral Image Classification Based on KNN,” Sens. Imaging 17, 1–13 (2016).
[Crossref]

Karantzalos, K.

K. Makantasis, K. Karantzalos, A. Doulamis, and N. Doulamis, “Deep supervised learning for hyperspectral data classification through convolutional neural networks,” in IEEE International Geoscience and Remote Sensing Symposium, (IEEE, 2015), pp.4959–4962.

Krizhevsk, A.

A. Krizhevsk, I. Sutskever, and G. E. Hinton, “ImageNet Classification with Deep Convolutional Neural Networks,” in Neural Information Processing Systems, (Academic, 2012), pp.1097–1105.

Lee, Z.

Li, C.

Y. Chen, H. Jiang, C. Li, X. Jia, and P. Ghamisi, “Deep Feature Extraction and Classification of Hyperspectral Images Based on Convolutional Neural Networks,” IEEE Transactions on Geosci. Remote. Sens. 54, 6232–6251 (2016).
[Crossref]

Li, H.

S. Jia, H. Li, Y. Wang, R. Tong, and Q. Li, “Hyperspectral imaging analysis for the classification of soil types and the determination of soil total nitrogen,” Sensors 17, 1–14 (2017).
[Crossref]

W. Hu, Y. Huang, L. Wei, F. Zhang, and H. Li, “Deep Convolutional Neural Networks for Hyperspectral Image Classification,” J. Sensors 2015, 258619(2015).
[Crossref]

Li, J.

J. Li, W. Huang, X. Tian, C. Wang, S. Fan, and C. Zhao, “Fast detection and visualization of early decay in citrus using Vis-NIR hyperspectral imaging,” Comput. Electron. Agric. 127, 582–592 (2016).
[Crossref]

B. Zhang, J. Li, S. Fan, W. Huang, C. Zhao, C. Liu, and D. Huang, “Hyperspectral imaging combined with multivariate analysis and band math for detection of common defects on peaches (Prunus persica),” Comput. Electron. Agric. 114, 14–24 (2015).
[Crossref]

Li, Q.

S. Jia, H. Li, Y. Wang, R. Tong, and Q. Li, “Hyperspectral imaging analysis for the classification of soil types and the determination of soil total nitrogen,” Sensors 17, 1–14 (2017).
[Crossref]

H. Liang and Q. Li, “Hyperspectral imagery classification using sparse representations of convolutional neural network features,” Remote. Sens. 8, 99 (2016).
[Crossref]

Li, S.

K. Huang, S. Li, X. Kang, and L. Fang, “Spectral-Spatial Hyperspectral Image Classification Based on KNN,” Sens. Imaging 17, 1–13 (2016).
[Crossref]

Li, X.

Z. Shi, Q. L. Wang, J. Peng, W. J. Ji, H. J. Liu, X. Li, and R. A. Viscarra Rossel, “Development of a national VNIR soil-spectral library for soil classification and prediction of organic matter concentrations,” Sci. China Earth Sci. 57, 1671–1680 (2014).
[Crossref]

Li, Y.

Y. Li, H. Zhang, and Q. Shen, “Spectral-spatial classification of hyperspectral imagery with 3D convolutional neural network,” Remote. Sens. 9, 67 (2017).
[Crossref]

Liang, H.

H. Liang and Q. Li, “Hyperspectral imagery classification using sparse representations of convolutional neural network features,” Remote. Sens. 8, 99 (2016).
[Crossref]

Lin, G.

Liu, C.

B. Zhang, J. Li, S. Fan, W. Huang, C. Zhao, C. Liu, and D. Huang, “Hyperspectral imaging combined with multivariate analysis and band math for detection of common defects on peaches (Prunus persica),” Comput. Electron. Agric. 114, 14–24 (2015).
[Crossref]

Liu, H.

J. Yue, W. Zhao, S. Mao, and H. Liu, “Spectral-spatial classification of hyperspectral images using deep convolutional neural networks,” Remote. Sens. Lett. 6(6), 468–477 (2015).
[Crossref]

Liu, H. J.

Z. Shi, Q. L. Wang, J. Peng, W. J. Ji, H. J. Liu, X. Li, and R. A. Viscarra Rossel, “Development of a national VNIR soil-spectral library for soil classification and prediction of organic matter concentrations,” Sci. China Earth Sci. 57, 1671–1680 (2014).
[Crossref]

Liu, W.

C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich, “Going Deeper with Convolutions,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, (IEEE, 2015), pp.1–9.

Ma, X.

Makantasis, K.

K. Makantasis, K. Karantzalos, A. Doulamis, and N. Doulamis, “Deep supervised learning for hyperspectral data classification through convolutional neural networks,” in IEEE International Geoscience and Remote Sensing Symposium, (IEEE, 2015), pp.4959–4962.

Mao, S.

J. Yue, W. Zhao, S. Mao, and H. Liu, “Spectral-spatial classification of hyperspectral images using deep convolutional neural networks,” Remote. Sens. Lett. 6(6), 468–477 (2015).
[Crossref]

Mehrotra, S. C.

A. D. Vibhute, K. V. Kale, R. K. Dhumal, and S. C. Mehrotra, “Soil type classification and mapping using hyperspectral remote sensing data,” in International Conference on Man and Machine Interfacing, (IEEE, 2016), pp.1–4.

Miller, B. A.

E. C. Brevik, C. Calzolari, B. A. Miller, P. Pereira, C. Kabala, A. Baumgarten, and A. Jordán, “Soil mapping, classification, and pedologic modeling: History and future directions,” Geoderma 264, 256–274 (2016).
[Crossref]

Mirza, I. O.

Mountrakis, G.

G. Mountrakis, J. Im, and C. Ogole, “Support vector machines in remote sensing: A review,” ISPRS J. Photogramm. Remote. Sens. 66, 247–259 (2011).
[Crossref]

Ogen, Y.

Y. Ogen, N. Goldshleger, and E. Ben-Dor, “3D spectral analysis in the VNIR-SWIR spectral region as a tool for soil classification,” Geoderma 302, 100–110 (2017).
[Crossref]

Ogole, C.

G. Mountrakis, J. Im, and C. Ogole, “Support vector machines in remote sensing: A review,” ISPRS J. Photogramm. Remote. Sens. 66, 247–259 (2011).
[Crossref]

Osborn A, L.

Ouyang, Q.

Pal, M.

M. Pal and G. M. Foody, “Feature selection for classification of hyperspectral data by SVM,” IEEE Transactions on Geosci. Remote. Sens. 48, 2297–2307 (2010).
[Crossref]

Peng, J.

Z. Shi, Q. L. Wang, J. Peng, W. J. Ji, H. J. Liu, X. Li, and R. A. Viscarra Rossel, “Development of a national VNIR soil-spectral library for soil classification and prediction of organic matter concentrations,” Sci. China Earth Sci. 57, 1671–1680 (2014).
[Crossref]

Pereira, P.

E. C. Brevik, C. Calzolari, B. A. Miller, P. Pereira, C. Kabala, A. Baumgarten, and A. Jordán, “Soil mapping, classification, and pedologic modeling: History and future directions,” Geoderma 264, 256–274 (2016).
[Crossref]

Philpot, W. D.

Prather, D. W.

Rabinovich, A.

C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich, “Going Deeper with Convolutions,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, (IEEE, 2015), pp.1–9.

Ramakrishnan, D.

D. Ramakrishnan and R. Bharti, “Hyperspectral remote sensing and geological applications,” Curr. Sci. 108, 879–891 (2015).

Rao, N. R.

N. R. Rao, P. K. Garg, and S. K. Ghosh, “Development of an agricultural crops spectral library and classification of crops at cultivar level using hyperspectral data,” Precis. Agric. 8, 173–185 (2007).
[Crossref]

Reed, S.

C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich, “Going Deeper with Convolutions,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, (IEEE, 2015), pp.1–9.

Ren, S.

K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, (IEEE, 2016), pp.770–778.

Rueda, H.

Sermanet, P.

C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich, “Going Deeper with Convolutions,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, (IEEE, 2015), pp.1–9.

Shang, S.

Shen, Q.

Y. Li, H. Zhang, and Q. Shen, “Spectral-spatial classification of hyperspectral imagery with 3D convolutional neural network,” Remote. Sens. 9, 67 (2017).
[Crossref]

Shi, Z.

Z. Shi, Q. L. Wang, J. Peng, W. J. Ji, H. J. Liu, X. Li, and R. A. Viscarra Rossel, “Development of a national VNIR soil-spectral library for soil classification and prediction of organic matter concentrations,” Sci. China Earth Sci. 57, 1671–1680 (2014).
[Crossref]

Slahor, J.

Steffens, M.

M. Steffens and H. Buddenbaum, “Laboratory imaging spectroscopy of a stagnic Luvisol profile - High resolution soil characterisation, classification and mapping of elemental concentrations,” Geoderma 195-196122–132 (2013).
[Crossref]

Sun, J.

K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, (IEEE, 2016), pp.770–778.

Sutskever, I.

A. Krizhevsk, I. Sutskever, and G. E. Hinton, “ImageNet Classification with Deep Convolutional Neural Networks,” in Neural Information Processing Systems, (Academic, 2012), pp.1097–1105.

Szegedy, C.

C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich, “Going Deeper with Convolutions,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, (IEEE, 2015), pp.1–9.

Taghizadeh, M.

A. A. Gowen, C. P. O. Donnell, M. Taghizadeh, P. J. Cullenb, J. M. Frias, and G. Downey, “Hyperspectral imaging combined with principal component analysis for bruise damage detection on white mushrooms (Agaricus bisporus),” J. Chemom. 22, 259–267 (2008).
[Crossref]

Thompson, D. R.

Tian, J.

Tian, X.

J. Li, W. Huang, X. Tian, C. Wang, S. Fan, and C. Zhao, “Fast detection and visualization of early decay in citrus using Vis-NIR hyperspectral imaging,” Comput. Electron. Agric. 127, 582–592 (2016).
[Crossref]

Till, R. J.

D. J. Hand and R. J. Till, “A Simple Generalisation of the Area Under the ROC Curve for Multiple Class Classification Problems,” Mach. Learn. 45, 171–186 (2001).
[Crossref]

Tong, R.

S. Jia, H. Li, Y. Wang, R. Tong, and Q. Li, “Hyperspectral imaging analysis for the classification of soil types and the determination of soil total nitrogen,” Sensors 17, 1–14 (2017).
[Crossref]

van der Meer, F.

F. van der Meer, “The effectiveness of spectral similarity measures for the analysis of hyperspectral imagery,” Int. J. Appl. Earth Obs. Geoinformation 8, 3–17 (2006).
[Crossref]

Vanhoucke, V.

C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich, “Going Deeper with Convolutions,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, (IEEE, 2015), pp.1–9.

Vibhute, A. D.

A. D. Vibhute, K. V. Kale, R. K. Dhumal, and S. C. Mehrotra, “Soil type classification and mapping using hyperspectral remote sensing data,” in International Conference on Man and Machine Interfacing, (IEEE, 2016), pp.1–4.

Viscarra Rossel, R. A.

Z. Shi, Q. L. Wang, J. Peng, W. J. Ji, H. J. Liu, X. Li, and R. A. Viscarra Rossel, “Development of a national VNIR soil-spectral library for soil classification and prediction of organic matter concentrations,” Sci. China Earth Sci. 57, 1671–1680 (2014).
[Crossref]

Wang, C.

J. Li, W. Huang, X. Tian, C. Wang, S. Fan, and C. Zhao, “Fast detection and visualization of early decay in citrus using Vis-NIR hyperspectral imaging,” Comput. Electron. Agric. 127, 582–592 (2016).
[Crossref]

Wang, Q. L.

Z. Shi, Q. L. Wang, J. Peng, W. J. Ji, H. J. Liu, X. Li, and R. A. Viscarra Rossel, “Development of a national VNIR soil-spectral library for soil classification and prediction of organic matter concentrations,” Sci. China Earth Sci. 57, 1671–1680 (2014).
[Crossref]

Wang, X.

Wang, Y.

S. Jia, H. Li, Y. Wang, R. Tong, and Q. Li, “Hyperspectral imaging analysis for the classification of soil types and the determination of soil total nitrogen,” Sensors 17, 1–14 (2017).
[Crossref]

Wei, L.

W. Hu, Y. Huang, L. Wei, F. Zhang, and H. Li, “Deep Convolutional Neural Networks for Hyperspectral Image Classification,” J. Sensors 2015, 258619(2015).
[Crossref]

Wu, Y.

Xu, T.

Xu, W.

S. Ji, W. Xu, M. Yang, and K. Yu, “3D Convolutional neural networks for human action recognition,” IEEE Transactions on Pattern Analysis Mach. Intell. 35, 221–231 (2013).
[Crossref]

Yang, C.

C. Yang, J. H. Everitt, and J. M. Bradford, “Yield Estimation from Hyperspectral Imagery Using Spectral Angle Mapper (SAM),” Transactions ASABE 51, 729–737 (2013).
[Crossref]

Yang, M.

S. Ji, W. Xu, M. Yang, and K. Yu, “3D Convolutional neural networks for human action recognition,” IEEE Transactions on Pattern Analysis Mach. Intell. 35, 221–231 (2013).
[Crossref]

Yu, K.

S. Ji, W. Xu, M. Yang, and K. Yu, “3D Convolutional neural networks for human action recognition,” IEEE Transactions on Pattern Analysis Mach. Intell. 35, 221–231 (2013).
[Crossref]

Yue, J.

J. Yue, W. Zhao, S. Mao, and H. Liu, “Spectral-spatial classification of hyperspectral images using deep convolutional neural networks,” Remote. Sens. Lett. 6(6), 468–477 (2015).
[Crossref]

Zhang, B.

B. Zhang, J. Li, S. Fan, W. Huang, C. Zhao, C. Liu, and D. Huang, “Hyperspectral imaging combined with multivariate analysis and band math for detection of common defects on peaches (Prunus persica),” Comput. Electron. Agric. 114, 14–24 (2015).
[Crossref]

Zhang, F.

W. Hu, Y. Huang, L. Wei, F. Zhang, and H. Li, “Deep Convolutional Neural Networks for Hyperspectral Image Classification,” J. Sensors 2015, 258619(2015).
[Crossref]

Zhang, H.

Y. Li, H. Zhang, and Q. Shen, “Spectral-spatial classification of hyperspectral imagery with 3D convolutional neural network,” Remote. Sens. 9, 67 (2017).
[Crossref]

Zhang, X.

K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, (IEEE, 2016), pp.770–778.

Zhang, Y.

Zhao, C.

J. Li, W. Huang, X. Tian, C. Wang, S. Fan, and C. Zhao, “Fast detection and visualization of early decay in citrus using Vis-NIR hyperspectral imaging,” Comput. Electron. Agric. 127, 582–592 (2016).
[Crossref]

B. Zhang, J. Li, S. Fan, W. Huang, C. Zhao, C. Liu, and D. Huang, “Hyperspectral imaging combined with multivariate analysis and band math for detection of common defects on peaches (Prunus persica),” Comput. Electron. Agric. 114, 14–24 (2015).
[Crossref]

Zhao, J.

Zhao, W.

J. Yue, W. Zhao, S. Mao, and H. Liu, “Spectral-spatial classification of hyperspectral images using deep convolutional neural networks,” Remote. Sens. Lett. 6(6), 468–477 (2015).
[Crossref]

Appl. Opt. (2)

Comput. Electron. Agric. (2)

J. Li, W. Huang, X. Tian, C. Wang, S. Fan, and C. Zhao, “Fast detection and visualization of early decay in citrus using Vis-NIR hyperspectral imaging,” Comput. Electron. Agric. 127, 582–592 (2016).
[Crossref]

B. Zhang, J. Li, S. Fan, W. Huang, C. Zhao, C. Liu, and D. Huang, “Hyperspectral imaging combined with multivariate analysis and band math for detection of common defects on peaches (Prunus persica),” Comput. Electron. Agric. 114, 14–24 (2015).
[Crossref]

Curr. Sci. (1)

D. Ramakrishnan and R. Bharti, “Hyperspectral remote sensing and geological applications,” Curr. Sci. 108, 879–891 (2015).

Geoderma (3)

E. C. Brevik, C. Calzolari, B. A. Miller, P. Pereira, C. Kabala, A. Baumgarten, and A. Jordán, “Soil mapping, classification, and pedologic modeling: History and future directions,” Geoderma 264, 256–274 (2016).
[Crossref]

Y. Ogen, N. Goldshleger, and E. Ben-Dor, “3D spectral analysis in the VNIR-SWIR spectral region as a tool for soil classification,” Geoderma 302, 100–110 (2017).
[Crossref]

M. Steffens and H. Buddenbaum, “Laboratory imaging spectroscopy of a stagnic Luvisol profile - High resolution soil characterisation, classification and mapping of elemental concentrations,” Geoderma 195-196122–132 (2013).
[Crossref]

IEEE Transactions on Geosci. Remote. Sens. (2)

M. Pal and G. M. Foody, “Feature selection for classification of hyperspectral data by SVM,” IEEE Transactions on Geosci. Remote. Sens. 48, 2297–2307 (2010).
[Crossref]

Y. Chen, H. Jiang, C. Li, X. Jia, and P. Ghamisi, “Deep Feature Extraction and Classification of Hyperspectral Images Based on Convolutional Neural Networks,” IEEE Transactions on Geosci. Remote. Sens. 54, 6232–6251 (2016).
[Crossref]

IEEE Transactions on Inf. Theory (1)

D. L. Donoho, “Compressed sensing,” IEEE Transactions on Inf. Theory 52(4), 1289–1306 (2006).
[Crossref]

IEEE Transactions on Pattern Analysis Mach. Intell. (1)

S. Ji, W. Xu, M. Yang, and K. Yu, “3D Convolutional neural networks for human action recognition,” IEEE Transactions on Pattern Analysis Mach. Intell. 35, 221–231 (2013).
[Crossref]

Int. J. Appl. Earth Obs. Geoinformation (1)

F. van der Meer, “The effectiveness of spectral similarity measures for the analysis of hyperspectral imagery,” Int. J. Appl. Earth Obs. Geoinformation 8, 3–17 (2006).
[Crossref]

Int. J. Comput. Sci. Mob. Comput. (1)

V. M. Dolas and P. U. Joshi, “A Novel Approach for Classification of Soil and Crop Prediction,” Int. J. Comput. Sci. Mob. Comput. 7, 20–24 (2018).

ISPRS J. Photogramm. Remote. Sens. (1)

G. Mountrakis, J. Im, and C. Ogole, “Support vector machines in remote sensing: A review,” ISPRS J. Photogramm. Remote. Sens. 66, 247–259 (2011).
[Crossref]

J. Chemom. (1)

A. A. Gowen, C. P. O. Donnell, M. Taghizadeh, P. J. Cullenb, J. M. Frias, and G. Downey, “Hyperspectral imaging combined with principal component analysis for bruise damage detection on white mushrooms (Agaricus bisporus),” J. Chemom. 22, 259–267 (2008).
[Crossref]

J. Near Infrared Spectrosc. (1)

J. Sensors (1)

W. Hu, Y. Huang, L. Wei, F. Zhang, and H. Li, “Deep Convolutional Neural Networks for Hyperspectral Image Classification,” J. Sensors 2015, 258619(2015).
[Crossref]

Mach. Learn. (1)

D. J. Hand and R. J. Till, “A Simple Generalisation of the Area Under the ROC Curve for Multiple Class Classification Problems,” Mach. Learn. 45, 171–186 (2001).
[Crossref]

Opt. Express (4)

Opt. Lett. (1)

Precis. Agric. (1)

N. R. Rao, P. K. Garg, and S. K. Ghosh, “Development of an agricultural crops spectral library and classification of crops at cultivar level using hyperspectral data,” Precis. Agric. 8, 173–185 (2007).
[Crossref]

Remote. Sens. (2)

Y. Li, H. Zhang, and Q. Shen, “Spectral-spatial classification of hyperspectral imagery with 3D convolutional neural network,” Remote. Sens. 9, 67 (2017).
[Crossref]

H. Liang and Q. Li, “Hyperspectral imagery classification using sparse representations of convolutional neural network features,” Remote. Sens. 8, 99 (2016).
[Crossref]

Remote. Sens. Lett. (1)

J. Yue, W. Zhao, S. Mao, and H. Liu, “Spectral-spatial classification of hyperspectral images using deep convolutional neural networks,” Remote. Sens. Lett. 6(6), 468–477 (2015).
[Crossref]

Sci. China Earth Sci. (1)

Z. Shi, Q. L. Wang, J. Peng, W. J. Ji, H. J. Liu, X. Li, and R. A. Viscarra Rossel, “Development of a national VNIR soil-spectral library for soil classification and prediction of organic matter concentrations,” Sci. China Earth Sci. 57, 1671–1680 (2014).
[Crossref]

Sens. Imaging (1)

K. Huang, S. Li, X. Kang, and L. Fang, “Spectral-Spatial Hyperspectral Image Classification Based on KNN,” Sens. Imaging 17, 1–13 (2016).
[Crossref]

Sensors (1)

S. Jia, H. Li, Y. Wang, R. Tong, and Q. Li, “Hyperspectral imaging analysis for the classification of soil types and the determination of soil total nitrogen,” Sensors 17, 1–14 (2017).
[Crossref]

Transactions ASABE (1)

C. Yang, J. H. Everitt, and J. M. Bradford, “Yield Estimation from Hyperspectral Imagery Using Spectral Angle Mapper (SAM),” Transactions ASABE 51, 729–737 (2013).
[Crossref]

Other (6)

H. Arguello and G. Arce, “Code Aperture Agile Spectral Imaging (CAASI),” in Imaging Systems Applications, OSA Technical Digest (CD) (Optical Society of America, 2011), paper ITuA4.
[Crossref]

A. Krizhevsk, I. Sutskever, and G. E. Hinton, “ImageNet Classification with Deep Convolutional Neural Networks,” in Neural Information Processing Systems, (Academic, 2012), pp.1097–1105.

C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich, “Going Deeper with Convolutions,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, (IEEE, 2015), pp.1–9.

K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, (IEEE, 2016), pp.770–778.

A. D. Vibhute, K. V. Kale, R. K. Dhumal, and S. C. Mehrotra, “Soil type classification and mapping using hyperspectral remote sensing data,” in International Conference on Man and Machine Interfacing, (IEEE, 2016), pp.1–4.

K. Makantasis, K. Karantzalos, A. Doulamis, and N. Doulamis, “Deep supervised learning for hyperspectral data classification through convolutional neural networks,” in IEEE International Geoscience and Remote Sensing Symposium, (IEEE, 2015), pp.4959–4962.

Cited By

OSA participates in Crossref's Cited-By Linking service. Citing articles from OSA journals and other participating publishers are listed here.

Alert me when this article is cited.


Figures (14)

Fig. 1
Fig. 1 The schematic diagram of compressive spectral imaging system for soil classification.
Fig. 2
Fig. 2 1D-CNN framework.
Fig. 3
Fig. 3 2D-CNN framework.
Fig. 4
Fig. 4 3D-CNN framework.
Fig. 5
Fig. 5 The flow chart of five CNN-based algorithms:(a)1D-CNN;(b)2D-CNN;(c)3D-CNN;(d)3D-CNN-SD and (e)3D-CNN-SD-PCA.
Fig. 6
Fig. 6 The imaging system in laboratory.
Fig. 7
Fig. 7 The reconstructed hyperspectral images of the five soil types at the wavelength 698.63nm.
Fig. 8
Fig. 8 The average spectra of the five soil types in the range of 500-710 nm.
Fig. 9
Fig. 9 The classification maps obtained by different CNN-based algorithms.
Fig. 10
Fig. 10 The test dataset evaluation metrics as a function of the number of parameters:(a)OA,(b)AUC and (c)Log loss.
Fig. 11
Fig. 11 The spectral difference curve between a single pixel with (a)all soil types,(b) Chernozem, (c) Red earths, (d) Paddy soil,(e) Humid-thermo ferralitic and (f) Purplish soil.
Fig. 12
Fig. 12 The spectral principal component difference curve between a single pixel with five soil types in the 3D-CNN-SD-PCA algorithm.
Fig. 13
Fig. 13 (Top) the reconstructed spectral images, (middle) the reference maps, and (bottom) the classification maps generated by 3D-CNN-SD-PCA algorithm.
Fig. 14
Fig. 14 Classification performance comparison between the 3D-CNN-SD-PCA algorithm with other conventional methods: SAM: the reference spectrum is each soil type mean spectral vector; SVM: the kernal is radial basis function(RBF), multi-class method is one to one, the penalty parameter and the kernel function parameter are obtained by grid search; DT: the Gini index is used to split measure in selecting the splitting attribute; KNN: the distance metric is euclidean distance, the number of neighbors is determined by cross-validation.

Tables (2)

Tables Icon

Table 1 The training time and testing time of nine CNN-based algorithms.

Tables Icon

Table 2 The training time and testing time for different machine learning classification methods.

Equations (12)

Equations on this page are rendered with MathJax. Learn more.

g = Φ f ,
Φ = Φ x y Φ λ ,
Φ x y = [ Φ x y 1 0 M k × δ 2 0 M k × δ 2 0 M k × δ 2 Φ x y 2 0 M k × δ 2 0 M k × δ 2 0 M k × δ 2 Φ x y M x × M y ] ,
γ = N x N y N λ M k M λ M x M y = δ 2 N λ M k M λ .
f = Ψ θ ,
g = Φ Ψ θ + ω ,
θ ^ = arg  min θ θ 1 subject to g Φ Ψ θ 2 ε ,
Y j d = b j + l = 1 L r = 0 R 1 ω j l r X l d + r ,
Y j d = max  ( X j d , 0 ) ,
Y j h w = b j + l = 1 L p = 0 P 1 q = 0 Q 1 ω j l p q X l ( h + p ) ( w + q ) ,
Y j h w d = b j + l = 1 L p = 0 P 1 q = 0 Q 1 r = 0 R 1 ω j l p q r X l ( h + p ) ( w + q ) ( d + r ) ,
F F k = 1 5 × F F ,

Metrics