Geo HU Berlin Reference Database -- Query Results
toggle visibility Search & Display Options

Select All    Deselect All
  Record Links
Author (up) Okujeni, A.; van der Linden, S.; Suess, S.; Hostert, P. doi  openurl
  Title Ensemble Learning From Synthetically Mixed Training Data for Quantifying Urban Land Cover With Support Vector Regression Type Journal Article
  Year 2017 Publication IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Abbreviated Journal  
  Volume 10 Issue 4 Pages 1640-1650  
  Keywords land cover; regression analysis; remote sensing by radar; set theory; spaceborne radar; support vector machines; terrain mapping; Berlin; Germany; SVR; bootstrap aggregation; empirical regression model; ensemble learning; image data; multiple endmember spectral mixture analysis; quantitative urban mapping methodology; spaceborne imaging spectrometer data; subpixel composition; support vector regression; synthetic mixture generation; synthetically mixed training data; training sample; urban land cover; Data models; Imaging; Libraries; Remote sensing; Training; Training data; hyperspectral; imaging spectrometry; machine learning; subpixel mapping; support vector regression (SVR); urban remote sensing  
  Abstract Generating synthetically mixed data from library spectra provides a direct means to train empirical regression models for subpixel mapping. In order to best represent the subpixel composition of image data, the generation of synthetic mixtures must incorporate a multitude of mixing possibilities. This can lead to an excessive amount of training samples. We show that increasing mixing complexity in the training set improves model performance when quantifying urban land cover with support vector regression (SVR). To cope with the challenging increase in the number of training samples, we propose the use of ensemble learning based on bootstrap aggregation from synthetically mixed training data. The workflow is tested on simulated spaceborne imaging spectrometer data acquired over Berlin, Germany. Comparisons to SVR without bagging and multiple endmember spectral mixture analysis reveal the usefulness of the methodology for quantitative urban mapping.  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN 1939-1404 ISBN Medium  
  Area Expedition Conference  
  Notes Approved no  
  Call Number geomatics @ Serial 521  
Permanent link to this record
Select All    Deselect All