Application of Hyperspectral Data for Land Cover Classification

DOI

10.2991/aer.k.211029.016How to use a DOI?

Keywords

Hyperspectral image; advanced classification; land cover

Abstract

At present, hyperspectral imaging techniques are widely used for a variety of different thematic applications, because they record a detailed spectrum of incoming radiation for every pixel and provide an invaluable source of information related to the physical nature of the Earth’s surface features. Generating accurate land cover maps using remote sensing (RS) datasets is one of the most important applications of digital image processing. For the generation of accurate maps, diverse supervised, unsupervised and hybrid classification methods can be applied. As hyperspectral images contain abundant spectral information, it makes them possible to distinguish various objects that would not be distinguishable by multispectral sensors. The aim of this study is to discriminate the land cover types in northern Mongolia using some advanced hyperspectral image classification techniques. As data sources, a Hyperion image of 2014 and some other ground truth information have been used. Overall, the research indicated that modern advanced hyperspectral data analysis methods could be successfully used for the land cover classification.

Copyright

© 2021 The Authors. Published by Atlantis Press International B.V.

Open Access

This is an open access article under the CC BY-NC license.

Download article (PDF)

TY  - CONF
AU  - Amarsaikhan Damdinsuren
AU  - Byambadolgor Batdorj
AU  - Jargaldalai Enkhtuya
AU  - Enkhjargal Damdinsuren
AU  - Tsogzol Gurjav
PY  - 2021
DA  - 2021/11/01
TI  - Application of Hyperspectral Data for Land Cover Classification
BT  - Proceedings of the Environmental Science and Technology International Conference (ESTIC 2021)
PB  - Atlantis Press
SP  - 86
EP  - 90
SN  - 2352-5401
UR  - https://doi.org/10.2991/aer.k.211029.016
DO  - 10.2991/aer.k.211029.016
ID  - Damdinsuren2021
ER  -