Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Sensibility study for optimizing the classification of remote sensing time series
2007 (English)Independent thesis Advanced level (degree of Master (One Year)), 10 credits / 15 HE creditsStudent thesis
Abstract [en]

Sensibility studies are necessary to evaluate if an existing method is optimizable. The present method for classification of land cover uses the course of information about an observed region during one year. The progress of the natural cover of an observed region gets visible by using weekly composites of NDVI measurements. Filling this data in a diagram results in a time curve. This time series can be characterized by minimum, maximum, amplitude, average and standard deviation of the curve and by other parameters. The analysis of this values, for example by utilization of Recursive Partitioning and Regression Trees (RPART) allows a classification of the vegetation. In the sensibility study the effects of the variation of several criteria like temporal segmentation, pre-utilization of curve smoothing are analyzed. Also the impact of changing training data on the classification of specific target classes and the possibility of predicting classes are an objective of this sensibility studies. Therefore the software, developed in a dissertation at the University of W├╝rzburg, is changed and adopted to be able to apply statistics on the input data to provide the output for the analysis.The gained knowledge shows in which extent the results can be used to optimize the existing method. This results are more interesting in the field of segmentation, harmonics, and prediction than in curve smoothing. It is indicated that the correctness of the classification changes a lot by changing the training regions and that segmentation is very a promising approach.

Place, publisher, year, edition, pages
2007.
Keyword [en]
Technology
Keyword [sv]
Teknik
Identifiers
URN: urn:nbn:se:ltu:diva-48626ISRN: LTU-PB-EX--07/085--SELocal ID: 60eeb794-7a57-4d56-97aa-1607c3c6c463OAI: oai:DiVA.org:ltu-48626DiVA: diva2:1021969
Subject / course
Student thesis, at least 15 credits
Educational program
Space Engineering, master's level
Examiners
Note
Validerat; 20101217 (root)Available from: 2016-10-04 Created: 2016-10-04Bibliographically approved

Open Access in DiVA

fulltext(3577 kB)10 downloads
File information
File name FULLTEXT01.pdfFile size 3577 kBChecksum SHA-512
4f77a90460c304a967864568d1ca467de0010b314a0b30fd7a5f5f5037f5ef857ef6a9d93ff8b5ffdcc00a89922f16b10cb077fbe197c9d18fc8b8da3332a802
Type fulltextMimetype application/pdf

Search outside of DiVA

GoogleGoogle Scholar
Total: 10 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 6 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf