Spectral-Spatial Methods for Hyperspectral Image Classification. Review
- Authors: Borzov S.M.1, Potaturkin O.I.1
-
Affiliations:
- Institute of Automation and Electrometry
- Issue: Vol 54, No 6 (2018)
- Pages: 582-599
- Section: Analysis and Synthesis of Signals and Images
- URL: https://journals.rcsi.science/8756-6990/article/view/212620
- DOI: https://doi.org/10.3103/S8756699018060079
- ID: 212620
Cite item
Abstract
Various methods of spectral-spatial classification of hyperspectral data are reviewed. Papers devoted to the most popular ways of using spatial information for increasing the accuracy of classification maps are considered. It is shown that the best results are obtained by using preprocessing of “raw” data before the procedures of pixel-wise spectral classification. Disadvantages, limits, and possible directions for developing existing methods are investigated and analyzed.
About the authors
S. M. Borzov
Institute of Automation and Electrometry
Author for correspondence.
Email: borzov@iae.nsk.su
Russian Federation, pr. Akademika Koptyuga 1, Novosibirsk, 630090
O. I. Potaturkin
Institute of Automation and Electrometry
Email: borzov@iae.nsk.su
Russian Federation, pr. Akademika Koptyuga 1, Novosibirsk, 630090
Supplementary files
