Powered by OpenAIRE graph
Found an issue? Give us feedback
addClaim

OBIA in the Neusiedlersee region

OBIA in der Region Neusiedlersee
Authors: Yaroshenko, Anna;

OBIA in the Neusiedlersee region

Abstract

In dieser Arbeit geht es darum, wie die objektorientierte Bildanalyse (OBIA) in der eCognition Developer Software durchgeführt werden kann - es wird beschrieben, wie das Satellitenbild mit verschiedenen Werkzeugen des Programms segmentiert und klassifiziert werden kann. Es ist immer wichtiger geworden, die Forschungsergebnisse zu kategorisieren und die Leser mit einem Überblick über die existierenden Segmentationstechniken in jeder Kategorie und mit der ständig wachsenden Forschung über die Bildsegmentierung zu versorgen. Das Programm eCognition Developer ist eines der komfortabelsten Programme, die für diesen Ansatz verwendet werden können. Die OBIA kann aufgrund weniger gut definierter Kanten und Grenzen zwischen verschiedenen Klassen eine aussagekräftigere Informationsquelle als die pixelbasierte Bildanalyse darstellen. Hier wird eine formale Definition von OBIA vorgeschlagen und demonstriert, wie es in der eCognition Developer Software funktioniert. OBIA in der eCognition Developer Software besteht aus zwei Teilen: Segmentierung und Klassifizierung. In dieser Arbeit werden verschiedene Bildsegmentierung und Klassifikationstechniken für optische Fernerkundungsbilder untersucht. Zur Demonstration wurde das RapidEye-Satellitenbild der Region Neusiedler See ausgewählt. Die Auswahl der Stichproben basiert auf der Klassifizierung einer Landbedeckungskarte, die von Spatial Indicators for Land Use Sustainability (SINUS) genommen wurde und auf einer visuellen Interpretation basiert. Die Multi-Resolution-Segmentierung und Klassifizierung des nächsten Nachbarn als die bequemsten Methoden wurde durch die Abbildung des RapidEye-Satellitenbildes in eCognition Developer realisiert. Um alle Vor- und Nachteile von OBIA in der eCognition Developer Software zu sehen, wurde schließlich einen Vergleich unseres segmentierten und klassifizierten Satellitenfotos im eCognition Developer mit der Karte, die von SINUS genommen wurde gemacht.

This work is about how can Object-based image analysis (OBIA) can be performed in the eCognition Developer software - it is described how a satellite image could be segmented and classified, using different tools of the program. Categorizing of outcomes of research, providing users with overview of existing segmentation techniques becomes more and more in-demand task. The program eCognition Developer is one of rather few software suitable to fulfil this task. OBIA can provide a more meaningful source of information than pixel-based image analysis due to less well-defined edges and borders between different classes. Here a formal definition of OBIA is proposed and demonstrated how it works in the eCognition Developer software step by step. OBIA in eCognition Developer software consists of two parts: segmentation and classification. In this work, different techniques intended for image segmentation and classification applied to optical remote sensing images has been studied and reviewed. The RapidEye satellite image of the Neusiedlersee region has been selected for the goals of demonstration. The selection of samples is based on a classification of a land cover map which was taken from Spatial Indicators for Land Use Sustainability (SINUS) and which is based on a visual interpretation. Multi-resolution segmentation and classification of the nearest neighbor as the most convenient methods were implemented by mapping of the RapidEye satellite image in eCognition Developer. The most convenient methods - multi-resolution segmentation and classification of the nearest neighbour - were implemented by mapping of the RapidEye satellite image in eCognition Developer. At last, to analyze OBIA pro-s and contra-s in eCognition Developer Software it has been provided a comparison of the segmented and classified satellite photo in eCognition Developer with the other one taken from SINUS.

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Upload OA version
Are you the author of this publication? Upload your Open Access version to Zenodo!
It’s fast and easy, just two clicks!