Cargando…

Automated object-based classification of topography from SRTM data

We introduce an object-based method to automatically classify topography from SRTM data. The new method relies on the concept of decomposing land-surface complexity into more homogeneous domains. An elevation layer is automatically segmented and classified at three scale levels that represent domain...

Descripción completa

Detalles Bibliográficos
Autores principales: Drăguţ, Lucian, Eisank, Clemens
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Elsevier 2012
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3312788/
https://www.ncbi.nlm.nih.gov/pubmed/22485060
http://dx.doi.org/10.1016/j.geomorph.2011.12.001
_version_ 1782227886573355008
author Drăguţ, Lucian
Eisank, Clemens
author_facet Drăguţ, Lucian
Eisank, Clemens
author_sort Drăguţ, Lucian
collection PubMed
description We introduce an object-based method to automatically classify topography from SRTM data. The new method relies on the concept of decomposing land-surface complexity into more homogeneous domains. An elevation layer is automatically segmented and classified at three scale levels that represent domains of complexity by using self-adaptive, data-driven techniques. For each domain, scales in the data are detected with the help of local variance and segmentation is performed at these appropriate scales. Objects resulting from segmentation are partitioned into sub-domains based on thresholds given by the mean values of elevation and standard deviation of elevation respectively. Results resemble reasonably patterns of existing global and regional classifications, displaying a level of detail close to manually drawn maps. Statistical evaluation indicates that most of classes satisfy the regionalization requirements of maximizing internal homogeneity while minimizing external homogeneity. Most objects have boundaries matching natural discontinuities at regional level. The method is simple and fully automated. The input data consist of only one layer, which does not need any pre-processing. Both segmentation and classification rely on only two parameters: elevation and standard deviation of elevation. The methodology is implemented as a customized process for the eCognition® software, available as online download. The results are embedded in a web application with functionalities of visualization and download.
format Online
Article
Text
id pubmed-3312788
institution National Center for Biotechnology Information
language English
publishDate 2012
publisher Elsevier
record_format MEDLINE/PubMed
spelling pubmed-33127882012-04-04 Automated object-based classification of topography from SRTM data Drăguţ, Lucian Eisank, Clemens Geomorphology (Amst) Article We introduce an object-based method to automatically classify topography from SRTM data. The new method relies on the concept of decomposing land-surface complexity into more homogeneous domains. An elevation layer is automatically segmented and classified at three scale levels that represent domains of complexity by using self-adaptive, data-driven techniques. For each domain, scales in the data are detected with the help of local variance and segmentation is performed at these appropriate scales. Objects resulting from segmentation are partitioned into sub-domains based on thresholds given by the mean values of elevation and standard deviation of elevation respectively. Results resemble reasonably patterns of existing global and regional classifications, displaying a level of detail close to manually drawn maps. Statistical evaluation indicates that most of classes satisfy the regionalization requirements of maximizing internal homogeneity while minimizing external homogeneity. Most objects have boundaries matching natural discontinuities at regional level. The method is simple and fully automated. The input data consist of only one layer, which does not need any pre-processing. Both segmentation and classification rely on only two parameters: elevation and standard deviation of elevation. The methodology is implemented as a customized process for the eCognition® software, available as online download. The results are embedded in a web application with functionalities of visualization and download. Elsevier 2012-03-01 /pmc/articles/PMC3312788/ /pubmed/22485060 http://dx.doi.org/10.1016/j.geomorph.2011.12.001 Text en © 2012 Elsevier B.V. https://creativecommons.org/licenses/by-nc-nd/3.0/ Open Access under CC BY-NC-ND 3.0 (https://creativecommons.org/licenses/by-nc-nd/3.0/) license
spellingShingle Article
Drăguţ, Lucian
Eisank, Clemens
Automated object-based classification of topography from SRTM data
title Automated object-based classification of topography from SRTM data
title_full Automated object-based classification of topography from SRTM data
title_fullStr Automated object-based classification of topography from SRTM data
title_full_unstemmed Automated object-based classification of topography from SRTM data
title_short Automated object-based classification of topography from SRTM data
title_sort automated object-based classification of topography from srtm data
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3312788/
https://www.ncbi.nlm.nih.gov/pubmed/22485060
http://dx.doi.org/10.1016/j.geomorph.2011.12.001
work_keys_str_mv AT dragutlucian automatedobjectbasedclassificationoftopographyfromsrtmdata
AT eisankclemens automatedobjectbasedclassificationoftopographyfromsrtmdata