Abstract
It is experimentally demonstrated that the classification of fragments of a hyperspectral image with preliminary transformation of the spectral features of the image into the principal components and with the use of the Hilbert-Huang spectral transform is fairly effective in the case of vegetation types that are difficult-to-distinguish on the basis of hyperspectra. This classification is compared with traditional methods, where hyperspectral features transformed to the principal components without using spatial information are used. RBF neural networks are used in all methods at the final stage of the classification.
Article PDF
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Avoid common mistakes on your manuscript.
References
Promising Information Technologies of Remote Sensing of the Earth, Ed. by V. A. Soifer (Novaya Tekhnika, Samara, 2015) [in Russian].
V. G. Bondur, “Advanced Approaches to Processing Large Fluxes of Hyperspectral and Multispectral Aerospace Information,” Issled. Zemli iz Kosmosa, No. 1, 4–16 (2014).
A. V. Kuznetsov and V. V. Myasnikov, “Comparison of Algorithms of Controlled Elemental Classification of Hyperspectral Images,” Komp. Optika 38 (3), 494–502 (2014).
V. A. Fursov, S. A. Bibikov, and O. A. Baida, “Topical Classification of Hyperspectral Images Based on the Conjugation Criterion,” Komp. Optika 38 (1), 154–158 (2014).
S. M. Borzov, A. O. Potaturkin, O. I. Potaturkin, and A. M. Fedotov, “Analysis of the Efficiency of Classification of Hyperspectral Satellite Images of Natural and Man-Made Areas,” Avtometriya 52 (1), 3–14 (2016) [Optoelectron., Instrum. Data Process. 52 (1), 1–10 (2016)].
S. M. Borzov and A. O. Potaturkin, “Efficiency of the Spectral-Spatial Classification of Hyperspectral Imaging Data,” Avtometriya 53 (1), 32–42 (2017) [Optoelectron., Instrum. Data Process. 53 (1), 26–34 (2017)].
S. M. Borzov and A. O. Potaturkin, “Classification of Hyperspectral Images with Different Methods of Training Set Formation,” Avtometriya 54 (1), 89–97 (2018) [Optoelectron., Instrum. Data Process. 54 (1), 76–82 (2018)].
S. M. Borzov and A. O. Potaturkin, “Spectral-Spatial Methods for Hyperspectral Image Classification. Review,” Avtometriya 54 (6), 64–86 (2018) [Optoelectron., Instrum. Data Process. 54 (6), 582–599 (2018)].
E. S. Nezhevenko, A. S. Feoktistov, and O. Yu. Dashevskii, “Neural Network Classification of Hyperspectral Images on the Basis of the Hilbert-Huang Transform,” Avtometriya 53 (2), 79–85 (2017) [Optoelectron., Instrum. Data Process. 53 (2), 165–170 (2017)].
Lena. Material from Wikipedia. https://ru.wikipedia.org/wiki/Lena_(image).
S. Beucher, “Geodesic Reconstruction, Saddle Zones and Hierarchical Segmentation,” Image Anal. Stereol. 20 (2), 137–141 (2001).
L. Vincent, “Morphological Grayscale Reconstruction in Image Analysis: Applications and Efficient Algorithms,” IEEE Trans. Image Process. 2 (2), 176–201 (1993).
J. C. Carr, W. R. Fright, and R. K. Beatson, “Surface Interpolation with Radial Basis Functions for Medical Imaging,” in Proc. of the Conf. ACM SIGGRAPH, Los Angeles, USA, August 12–17, 2001, pp. 67–76.
Author information
Authors and Affiliations
Corresponding author
Additional information
Russian Text © The Author(s), 2019, published in Avtometriya, 2019, Vol. 55, No. 3, pp. 62–70.
About this article
Cite this article
Nezhevenko, E.S. Neural Network Classification of Difficult-to-Distinguish Types of Vegetation on the Basis of Hyperspectral Features. Optoelectron.Instrument.Proc. 55, 263–270 (2019). https://doi.org/10.3103/S8756699019030087
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S8756699019030087