Abstract

Optical remote sensing data processing is proposed for the airborne images of high spectral and spatial resolution. Optimization techniques are undertaken to gain information about spatial distribution of the pixels on the hyperspectral images and the texture of the forest stands of different species and ages together with reducing redundancy of the spectral channels used. The category of neighborhood of pixels for particular forest classes and the step up method of selecting optimal spectral channels are employed in the relevant processing procedures. We present examples of pattern recognition for the forests as a result of separating pixels, which characterize the sunlit tops, shaded space and intermediate cases of the Sun illumination conditions on the hyperspectral images.

© 2014 Optical Society of America

Full Article  |  PDF Article
OSA Recommended Articles
Improved technique for retrieval of forest parameters from hyperspectral remote sensing data

Vladimir V. Kozoderov, Egor V. Dmitriev, and Anton A. Sokolov
Opt. Express 23(24) A1342-A1353 (2015)

Testing different classification methods in airborne hyperspectral imagery processing

Vladimir V. Kozoderov and Egor V. Dmitriev
Opt. Express 24(10) A956-A965 (2016)

Hyperspectral remote sensing image retrieval system using spectral and texture features

Jing Zhang, Wenhao Geng, Xi Liang, Jiafeng Li, Li Zhuo, and Qianlan Zhou
Appl. Opt. 56(16) 4785-4796 (2017)

References

  • View by:
  • |
  • |
  • |

  1. S. Z. Li, Markov Random Field Modeling in Computer Vision (Springer-Verlag, 1995).
  2. V. V. Kozoderov and E. V. Dmitriev, “Remote sensing of soils and vegetation: pattern recognition and forest stand structure assessment,” Int. J. Remote Sens. 32(3), 5699–5717 (2011).
    [Crossref]
  3. A. K. Jain, “Advances in mathematical models in image processing,” Proc. IEEE 69(5), 502–528 (1981).
    [Crossref]
  4. N. S. Friedland and A. Rosenfeld, “Compact object recognition using energy-based optimization,” IEEE Trans. Pattern Anal. Mach. Intell. 14(7), 770–777 (1992).
    [Crossref]
  5. B. Tso and R. C. Olsen, “A contextual classification scheme based on MRF model with improved parameter estimation and multiscale fuzzy line process,” Remote Sens. Environ. 97(1), 127–136 (2005).
    [Crossref]
  6. J. Bolton and P. Gader, “Random set framework for context-based classification with hyperspectral imagery,” IEEE Trans. Geosci. Rem. Sens. 47(11), 3810–3821 (2009).
    [Crossref]
  7. V. V. Kozoderov, “Application of optical remote sensing data to study natural and climatic processes,” Climate and Nature 2(3), 3–16 (2012).
  8. F. G. Hall, D. E. Knapp, and K. F. Huemmrich, “Physically based classification and satellite mapping of biophysical characteristic in the southern boreal forest,” J. Geophys. Res. 102(D24), 29567–29580 (1997).
    [Crossref]
  9. T. Hakala, J. Suomalainen, S. Kaasalainen, and Y. Chen, “Full waveform hyperspectral LiDAR for terrestrial laser scanning,” Opt. Express 20(7), 7119–7127 (2012).
    [Crossref] [PubMed]
  10. E. V. Dmitriev and V. V. Kozoderov, “Optimization of spectral bands for hyperspectral remote sensing of forest vegetation,” Proc. SPIE 8887, 888705 (2013).
    [Crossref]
  11. J. Suomalainen, T. Hakala, H. Kaartinen, E. Räikkönen, and S. Kaasalainen, “Demonstration of a virtual active hyperspectral LiDAR in automated point cloud classification,” ISPRS J. Photogramm. Remote Sens. 66(5), 637–641 (2011).
    [Crossref]
  12. M. Dalponte, L. Bruzzone, and D. Gianelle, “Fusion of hyperspectral and LIDAR remote sensing data for classification of complex forest areas,” IEEE Trans. Geosci. Rem. Sens. 113, 1416–1427 (2009).
  13. V. V. Kozoderov and E. V. Dmitriev, “Remote sensing of soils and vegetation: regional aspects,” Int. J. Remote Sens. 29(9), 2733–2748 (2008).
    [Crossref]
  14. V. V. Kozoderov, T. V. Kondranin, E. V. Dmitriev, and V. P. Kamentsev, “Mapping forest and peat fires using hyperspectral airborne remote-sensing data,” Izv., Atmos. Ocean. Phys. 48(9), 941–948 (2012).
    [Crossref]
  15. J. Besag and P. J. Green, “Spatial statistics and Bayesian computation,” J. R. Stat. Soc., B 55(1), 25–37 (1993).
  16. M. Bertero, T. A. Poggio, and V. Torre, “Ill-posed problems in early vision,” Proc. IEEE 76(8), 869–889 (1988).
    [Crossref]
  17. V. V. Kozoderov, E. V. Dmitriev, and V. P. Kamentsev, “A system of airborne remote sensing data processing of high spectral and spatial resolution,” Issledovanie Zemli Iz Kosmosa. 6, 57–64 (2013).
  18. V. V. Kozoderov, T. V. Kondranin, and E. V. Dmitriev, Thematic processing of multispectral and hyperspectral airspace images (MIPT Publication, 2013).
  19. S. Z. Li, “Object recognition from range data prior to segmentation,” Image Vis. Comput. 10(8), 566–576 (1992).
    [Crossref]
  20. R. Kohavi, “A study of cross-validation and bootstrap for accuracy estimation and model selection,” Int. Joint Conf. on Artificial Intell. (IJCAI), 528–535 (1995).
  21. T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning (Springer, 2001).
  22. M. Dalponte, L. Bruzzone, L. Vescovo, and D. Gianelle, “The role of spatial resolution and classifier complexity in the analysis of hyperspectral images of forest areas,” Remote Sens. Environ. 113(11), 2345–2355 (2009).
    [Crossref]
  23. V. V. Kozoderov, T. V. Kondranin, and E. V. Dmitriev, “ An apparatus and programmatic system of hyperspectral airspace imagery processing,” Proc. Int. Symp. Atm. Radiation and Dynamics (ISARD), 41 (2013).

2013 (2)

E. V. Dmitriev and V. V. Kozoderov, “Optimization of spectral bands for hyperspectral remote sensing of forest vegetation,” Proc. SPIE 8887, 888705 (2013).
[Crossref]

V. V. Kozoderov, E. V. Dmitriev, and V. P. Kamentsev, “A system of airborne remote sensing data processing of high spectral and spatial resolution,” Issledovanie Zemli Iz Kosmosa. 6, 57–64 (2013).

2012 (3)

V. V. Kozoderov, T. V. Kondranin, E. V. Dmitriev, and V. P. Kamentsev, “Mapping forest and peat fires using hyperspectral airborne remote-sensing data,” Izv., Atmos. Ocean. Phys. 48(9), 941–948 (2012).
[Crossref]

V. V. Kozoderov, “Application of optical remote sensing data to study natural and climatic processes,” Climate and Nature 2(3), 3–16 (2012).

T. Hakala, J. Suomalainen, S. Kaasalainen, and Y. Chen, “Full waveform hyperspectral LiDAR for terrestrial laser scanning,” Opt. Express 20(7), 7119–7127 (2012).
[Crossref] [PubMed]

2011 (2)

V. V. Kozoderov and E. V. Dmitriev, “Remote sensing of soils and vegetation: pattern recognition and forest stand structure assessment,” Int. J. Remote Sens. 32(3), 5699–5717 (2011).
[Crossref]

J. Suomalainen, T. Hakala, H. Kaartinen, E. Räikkönen, and S. Kaasalainen, “Demonstration of a virtual active hyperspectral LiDAR in automated point cloud classification,” ISPRS J. Photogramm. Remote Sens. 66(5), 637–641 (2011).
[Crossref]

2009 (3)

M. Dalponte, L. Bruzzone, and D. Gianelle, “Fusion of hyperspectral and LIDAR remote sensing data for classification of complex forest areas,” IEEE Trans. Geosci. Rem. Sens. 113, 1416–1427 (2009).

J. Bolton and P. Gader, “Random set framework for context-based classification with hyperspectral imagery,” IEEE Trans. Geosci. Rem. Sens. 47(11), 3810–3821 (2009).
[Crossref]

M. Dalponte, L. Bruzzone, L. Vescovo, and D. Gianelle, “The role of spatial resolution and classifier complexity in the analysis of hyperspectral images of forest areas,” Remote Sens. Environ. 113(11), 2345–2355 (2009).
[Crossref]

2008 (1)

V. V. Kozoderov and E. V. Dmitriev, “Remote sensing of soils and vegetation: regional aspects,” Int. J. Remote Sens. 29(9), 2733–2748 (2008).
[Crossref]

2005 (1)

B. Tso and R. C. Olsen, “A contextual classification scheme based on MRF model with improved parameter estimation and multiscale fuzzy line process,” Remote Sens. Environ. 97(1), 127–136 (2005).
[Crossref]

1997 (1)

F. G. Hall, D. E. Knapp, and K. F. Huemmrich, “Physically based classification and satellite mapping of biophysical characteristic in the southern boreal forest,” J. Geophys. Res. 102(D24), 29567–29580 (1997).
[Crossref]

1993 (1)

J. Besag and P. J. Green, “Spatial statistics and Bayesian computation,” J. R. Stat. Soc., B 55(1), 25–37 (1993).

1992 (2)

S. Z. Li, “Object recognition from range data prior to segmentation,” Image Vis. Comput. 10(8), 566–576 (1992).
[Crossref]

N. S. Friedland and A. Rosenfeld, “Compact object recognition using energy-based optimization,” IEEE Trans. Pattern Anal. Mach. Intell. 14(7), 770–777 (1992).
[Crossref]

1988 (1)

M. Bertero, T. A. Poggio, and V. Torre, “Ill-posed problems in early vision,” Proc. IEEE 76(8), 869–889 (1988).
[Crossref]

1981 (1)

A. K. Jain, “Advances in mathematical models in image processing,” Proc. IEEE 69(5), 502–528 (1981).
[Crossref]

Bertero, M.

M. Bertero, T. A. Poggio, and V. Torre, “Ill-posed problems in early vision,” Proc. IEEE 76(8), 869–889 (1988).
[Crossref]

Besag, J.

J. Besag and P. J. Green, “Spatial statistics and Bayesian computation,” J. R. Stat. Soc., B 55(1), 25–37 (1993).

Bolton, J.

J. Bolton and P. Gader, “Random set framework for context-based classification with hyperspectral imagery,” IEEE Trans. Geosci. Rem. Sens. 47(11), 3810–3821 (2009).
[Crossref]

Bruzzone, L.

M. Dalponte, L. Bruzzone, L. Vescovo, and D. Gianelle, “The role of spatial resolution and classifier complexity in the analysis of hyperspectral images of forest areas,” Remote Sens. Environ. 113(11), 2345–2355 (2009).
[Crossref]

M. Dalponte, L. Bruzzone, and D. Gianelle, “Fusion of hyperspectral and LIDAR remote sensing data for classification of complex forest areas,” IEEE Trans. Geosci. Rem. Sens. 113, 1416–1427 (2009).

Chen, Y.

Dalponte, M.

M. Dalponte, L. Bruzzone, and D. Gianelle, “Fusion of hyperspectral and LIDAR remote sensing data for classification of complex forest areas,” IEEE Trans. Geosci. Rem. Sens. 113, 1416–1427 (2009).

M. Dalponte, L. Bruzzone, L. Vescovo, and D. Gianelle, “The role of spatial resolution and classifier complexity in the analysis of hyperspectral images of forest areas,” Remote Sens. Environ. 113(11), 2345–2355 (2009).
[Crossref]

Dmitriev, E. V.

V. V. Kozoderov, E. V. Dmitriev, and V. P. Kamentsev, “A system of airborne remote sensing data processing of high spectral and spatial resolution,” Issledovanie Zemli Iz Kosmosa. 6, 57–64 (2013).

E. V. Dmitriev and V. V. Kozoderov, “Optimization of spectral bands for hyperspectral remote sensing of forest vegetation,” Proc. SPIE 8887, 888705 (2013).
[Crossref]

V. V. Kozoderov, T. V. Kondranin, E. V. Dmitriev, and V. P. Kamentsev, “Mapping forest and peat fires using hyperspectral airborne remote-sensing data,” Izv., Atmos. Ocean. Phys. 48(9), 941–948 (2012).
[Crossref]

V. V. Kozoderov and E. V. Dmitriev, “Remote sensing of soils and vegetation: pattern recognition and forest stand structure assessment,” Int. J. Remote Sens. 32(3), 5699–5717 (2011).
[Crossref]

V. V. Kozoderov and E. V. Dmitriev, “Remote sensing of soils and vegetation: regional aspects,” Int. J. Remote Sens. 29(9), 2733–2748 (2008).
[Crossref]

Friedland, N. S.

N. S. Friedland and A. Rosenfeld, “Compact object recognition using energy-based optimization,” IEEE Trans. Pattern Anal. Mach. Intell. 14(7), 770–777 (1992).
[Crossref]

Gader, P.

J. Bolton and P. Gader, “Random set framework for context-based classification with hyperspectral imagery,” IEEE Trans. Geosci. Rem. Sens. 47(11), 3810–3821 (2009).
[Crossref]

Gianelle, D.

M. Dalponte, L. Bruzzone, L. Vescovo, and D. Gianelle, “The role of spatial resolution and classifier complexity in the analysis of hyperspectral images of forest areas,” Remote Sens. Environ. 113(11), 2345–2355 (2009).
[Crossref]

M. Dalponte, L. Bruzzone, and D. Gianelle, “Fusion of hyperspectral and LIDAR remote sensing data for classification of complex forest areas,” IEEE Trans. Geosci. Rem. Sens. 113, 1416–1427 (2009).

Green, P. J.

J. Besag and P. J. Green, “Spatial statistics and Bayesian computation,” J. R. Stat. Soc., B 55(1), 25–37 (1993).

Hakala, T.

T. Hakala, J. Suomalainen, S. Kaasalainen, and Y. Chen, “Full waveform hyperspectral LiDAR for terrestrial laser scanning,” Opt. Express 20(7), 7119–7127 (2012).
[Crossref] [PubMed]

J. Suomalainen, T. Hakala, H. Kaartinen, E. Räikkönen, and S. Kaasalainen, “Demonstration of a virtual active hyperspectral LiDAR in automated point cloud classification,” ISPRS J. Photogramm. Remote Sens. 66(5), 637–641 (2011).
[Crossref]

Hall, F. G.

F. G. Hall, D. E. Knapp, and K. F. Huemmrich, “Physically based classification and satellite mapping of biophysical characteristic in the southern boreal forest,” J. Geophys. Res. 102(D24), 29567–29580 (1997).
[Crossref]

Huemmrich, K. F.

F. G. Hall, D. E. Knapp, and K. F. Huemmrich, “Physically based classification and satellite mapping of biophysical characteristic in the southern boreal forest,” J. Geophys. Res. 102(D24), 29567–29580 (1997).
[Crossref]

Jain, A. K.

A. K. Jain, “Advances in mathematical models in image processing,” Proc. IEEE 69(5), 502–528 (1981).
[Crossref]

Kaartinen, H.

J. Suomalainen, T. Hakala, H. Kaartinen, E. Räikkönen, and S. Kaasalainen, “Demonstration of a virtual active hyperspectral LiDAR in automated point cloud classification,” ISPRS J. Photogramm. Remote Sens. 66(5), 637–641 (2011).
[Crossref]

Kaasalainen, S.

T. Hakala, J. Suomalainen, S. Kaasalainen, and Y. Chen, “Full waveform hyperspectral LiDAR for terrestrial laser scanning,” Opt. Express 20(7), 7119–7127 (2012).
[Crossref] [PubMed]

J. Suomalainen, T. Hakala, H. Kaartinen, E. Räikkönen, and S. Kaasalainen, “Demonstration of a virtual active hyperspectral LiDAR in automated point cloud classification,” ISPRS J. Photogramm. Remote Sens. 66(5), 637–641 (2011).
[Crossref]

Kamentsev, V. P.

V. V. Kozoderov, E. V. Dmitriev, and V. P. Kamentsev, “A system of airborne remote sensing data processing of high spectral and spatial resolution,” Issledovanie Zemli Iz Kosmosa. 6, 57–64 (2013).

V. V. Kozoderov, T. V. Kondranin, E. V. Dmitriev, and V. P. Kamentsev, “Mapping forest and peat fires using hyperspectral airborne remote-sensing data,” Izv., Atmos. Ocean. Phys. 48(9), 941–948 (2012).
[Crossref]

Knapp, D. E.

F. G. Hall, D. E. Knapp, and K. F. Huemmrich, “Physically based classification and satellite mapping of biophysical characteristic in the southern boreal forest,” J. Geophys. Res. 102(D24), 29567–29580 (1997).
[Crossref]

Kondranin, T. V.

V. V. Kozoderov, T. V. Kondranin, E. V. Dmitriev, and V. P. Kamentsev, “Mapping forest and peat fires using hyperspectral airborne remote-sensing data,” Izv., Atmos. Ocean. Phys. 48(9), 941–948 (2012).
[Crossref]

Kozoderov, V. V.

V. V. Kozoderov, E. V. Dmitriev, and V. P. Kamentsev, “A system of airborne remote sensing data processing of high spectral and spatial resolution,” Issledovanie Zemli Iz Kosmosa. 6, 57–64 (2013).

E. V. Dmitriev and V. V. Kozoderov, “Optimization of spectral bands for hyperspectral remote sensing of forest vegetation,” Proc. SPIE 8887, 888705 (2013).
[Crossref]

V. V. Kozoderov, T. V. Kondranin, E. V. Dmitriev, and V. P. Kamentsev, “Mapping forest and peat fires using hyperspectral airborne remote-sensing data,” Izv., Atmos. Ocean. Phys. 48(9), 941–948 (2012).
[Crossref]

V. V. Kozoderov, “Application of optical remote sensing data to study natural and climatic processes,” Climate and Nature 2(3), 3–16 (2012).

V. V. Kozoderov and E. V. Dmitriev, “Remote sensing of soils and vegetation: pattern recognition and forest stand structure assessment,” Int. J. Remote Sens. 32(3), 5699–5717 (2011).
[Crossref]

V. V. Kozoderov and E. V. Dmitriev, “Remote sensing of soils and vegetation: regional aspects,” Int. J. Remote Sens. 29(9), 2733–2748 (2008).
[Crossref]

Li, S. Z.

S. Z. Li, “Object recognition from range data prior to segmentation,” Image Vis. Comput. 10(8), 566–576 (1992).
[Crossref]

Olsen, R. C.

B. Tso and R. C. Olsen, “A contextual classification scheme based on MRF model with improved parameter estimation and multiscale fuzzy line process,” Remote Sens. Environ. 97(1), 127–136 (2005).
[Crossref]

Poggio, T. A.

M. Bertero, T. A. Poggio, and V. Torre, “Ill-posed problems in early vision,” Proc. IEEE 76(8), 869–889 (1988).
[Crossref]

Räikkönen, E.

J. Suomalainen, T. Hakala, H. Kaartinen, E. Räikkönen, and S. Kaasalainen, “Demonstration of a virtual active hyperspectral LiDAR in automated point cloud classification,” ISPRS J. Photogramm. Remote Sens. 66(5), 637–641 (2011).
[Crossref]

Rosenfeld, A.

N. S. Friedland and A. Rosenfeld, “Compact object recognition using energy-based optimization,” IEEE Trans. Pattern Anal. Mach. Intell. 14(7), 770–777 (1992).
[Crossref]

Suomalainen, J.

T. Hakala, J. Suomalainen, S. Kaasalainen, and Y. Chen, “Full waveform hyperspectral LiDAR for terrestrial laser scanning,” Opt. Express 20(7), 7119–7127 (2012).
[Crossref] [PubMed]

J. Suomalainen, T. Hakala, H. Kaartinen, E. Räikkönen, and S. Kaasalainen, “Demonstration of a virtual active hyperspectral LiDAR in automated point cloud classification,” ISPRS J. Photogramm. Remote Sens. 66(5), 637–641 (2011).
[Crossref]

Torre, V.

M. Bertero, T. A. Poggio, and V. Torre, “Ill-posed problems in early vision,” Proc. IEEE 76(8), 869–889 (1988).
[Crossref]

Tso, B.

B. Tso and R. C. Olsen, “A contextual classification scheme based on MRF model with improved parameter estimation and multiscale fuzzy line process,” Remote Sens. Environ. 97(1), 127–136 (2005).
[Crossref]

Vescovo, L.

M. Dalponte, L. Bruzzone, L. Vescovo, and D. Gianelle, “The role of spatial resolution and classifier complexity in the analysis of hyperspectral images of forest areas,” Remote Sens. Environ. 113(11), 2345–2355 (2009).
[Crossref]

Climate and Nature (1)

V. V. Kozoderov, “Application of optical remote sensing data to study natural and climatic processes,” Climate and Nature 2(3), 3–16 (2012).

IEEE Trans. Geosci. Rem. Sens. (2)

J. Bolton and P. Gader, “Random set framework for context-based classification with hyperspectral imagery,” IEEE Trans. Geosci. Rem. Sens. 47(11), 3810–3821 (2009).
[Crossref]

M. Dalponte, L. Bruzzone, and D. Gianelle, “Fusion of hyperspectral and LIDAR remote sensing data for classification of complex forest areas,” IEEE Trans. Geosci. Rem. Sens. 113, 1416–1427 (2009).

IEEE Trans. Pattern Anal. Mach. Intell. (1)

N. S. Friedland and A. Rosenfeld, “Compact object recognition using energy-based optimization,” IEEE Trans. Pattern Anal. Mach. Intell. 14(7), 770–777 (1992).
[Crossref]

Image Vis. Comput. (1)

S. Z. Li, “Object recognition from range data prior to segmentation,” Image Vis. Comput. 10(8), 566–576 (1992).
[Crossref]

Int. J. Remote Sens. (2)

V. V. Kozoderov and E. V. Dmitriev, “Remote sensing of soils and vegetation: regional aspects,” Int. J. Remote Sens. 29(9), 2733–2748 (2008).
[Crossref]

V. V. Kozoderov and E. V. Dmitriev, “Remote sensing of soils and vegetation: pattern recognition and forest stand structure assessment,” Int. J. Remote Sens. 32(3), 5699–5717 (2011).
[Crossref]

ISPRS J. Photogramm. Remote Sens. (1)

J. Suomalainen, T. Hakala, H. Kaartinen, E. Räikkönen, and S. Kaasalainen, “Demonstration of a virtual active hyperspectral LiDAR in automated point cloud classification,” ISPRS J. Photogramm. Remote Sens. 66(5), 637–641 (2011).
[Crossref]

Issledovanie Zemli Iz Kosmosa. (1)

V. V. Kozoderov, E. V. Dmitriev, and V. P. Kamentsev, “A system of airborne remote sensing data processing of high spectral and spatial resolution,” Issledovanie Zemli Iz Kosmosa. 6, 57–64 (2013).

Izv., Atmos. Ocean. Phys. (1)

V. V. Kozoderov, T. V. Kondranin, E. V. Dmitriev, and V. P. Kamentsev, “Mapping forest and peat fires using hyperspectral airborne remote-sensing data,” Izv., Atmos. Ocean. Phys. 48(9), 941–948 (2012).
[Crossref]

J. Geophys. Res. (1)

F. G. Hall, D. E. Knapp, and K. F. Huemmrich, “Physically based classification and satellite mapping of biophysical characteristic in the southern boreal forest,” J. Geophys. Res. 102(D24), 29567–29580 (1997).
[Crossref]

J. R. Stat. Soc., B (1)

J. Besag and P. J. Green, “Spatial statistics and Bayesian computation,” J. R. Stat. Soc., B 55(1), 25–37 (1993).

Opt. Express (1)

Proc. IEEE (2)

M. Bertero, T. A. Poggio, and V. Torre, “Ill-posed problems in early vision,” Proc. IEEE 76(8), 869–889 (1988).
[Crossref]

A. K. Jain, “Advances in mathematical models in image processing,” Proc. IEEE 69(5), 502–528 (1981).
[Crossref]

Proc. SPIE (1)

E. V. Dmitriev and V. V. Kozoderov, “Optimization of spectral bands for hyperspectral remote sensing of forest vegetation,” Proc. SPIE 8887, 888705 (2013).
[Crossref]

Remote Sens. Environ. (2)

B. Tso and R. C. Olsen, “A contextual classification scheme based on MRF model with improved parameter estimation and multiscale fuzzy line process,” Remote Sens. Environ. 97(1), 127–136 (2005).
[Crossref]

M. Dalponte, L. Bruzzone, L. Vescovo, and D. Gianelle, “The role of spatial resolution and classifier complexity in the analysis of hyperspectral images of forest areas,” Remote Sens. Environ. 113(11), 2345–2355 (2009).
[Crossref]

Other (5)

V. V. Kozoderov, T. V. Kondranin, and E. V. Dmitriev, “ An apparatus and programmatic system of hyperspectral airspace imagery processing,” Proc. Int. Symp. Atm. Radiation and Dynamics (ISARD), 41 (2013).

S. Z. Li, Markov Random Field Modeling in Computer Vision (Springer-Verlag, 1995).

V. V. Kozoderov, T. V. Kondranin, and E. V. Dmitriev, Thematic processing of multispectral and hyperspectral airspace images (MIPT Publication, 2013).

R. Kohavi, “A study of cross-validation and bootstrap for accuracy estimation and model selection,” Int. Joint Conf. on Artificial Intell. (IJCAI), 528–535 (1995).

T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning (Springer, 2001).

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 (8)

Fig. 1
Fig. 1 The central wavelengths (a) and the spectral resolution (b) of the imaging spectrometer.
Fig. 2
Fig. 2 Optimization of the feature space: a) – scheme of the selection of the subset of the most informative features; b) – an example of the selection of the most probable sequence of features. Data corresponding to different levels are highlighted by the grey scale.
Fig. 3
Fig. 3 The test area investigated during the airborne campaign of hyperspectral measurements in Tver region (Russia). Locations of the tracks obtained are indicated by the red lines.
Fig. 4
Fig. 4 Contribution of the noise variability to the signal variability for the hyperspectral measurements used. a) – no binning; b) – binning to 2 nm; c) – binning to 5 nm; d) – binning to 30 nm. The horizontal dashed line signifies 5% level of the noise variability.
Fig. 5
Fig. 5 The along-channel distribution of the normalized spectral radiances for the sunlit end-members relating to the pine (a) and birch (b) forest classes of different ages. The colors presented correspond to central wavelengths of HSC spectral channels. All spectra are on the left side and spectra in the visible region only are on the right side.
Fig. 6
Fig. 6 Confusion matrix (probabilities of true classification) of the broad age - class recognition for the pine and birch species with the fully illuminated parts of their crowns.
Fig. 7
Fig. 7 Results of the forest tree species recognition for the selected 20 test regions. Location of the test area on the forest inventory map of the Savvatyevskoe forestry (a): orange – pine dominance, blue – birch dominance, magenta – spruce dominance; the RGB-synthesized image (b) of the area; the forest species composition of the area (c): 1 – for the pixels corresponding to the completely shaded background, 2 – for the pixels with half of the forested environment illuminated by the Sun and half of the shaded background, 3 – for the pixels referenced as the sunlit tops.
Fig. 8
Fig. 8 The color curves represent the regional classification errors of the species composition (measured in percents) for the pixels corresponding to the shaded, semi-sunlit and sunlit areas and for all pixels. The black curve corresponds to the natural uncertainty because of the pixels on the boundaries between different regions.

Tables (1)

Tables Icon

Table 1 Parameters of the Spectral Radiance Ensembles for Homogeneous Forest Areas

Equations (2)

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

ε(i)= (p (i) pine p ^ (i) pine ) 2 + (p (i) birch p ^ (i) birch ) 2 2 ,
ε total = i=1 20 ε(i)W(i) ,

Metrics