Urban features classification using 3D hyperspectral data

Michal Shimoni, Mahamadou Idrissa, Dirk Borghys, Trym Haavardsholm, Thomas Olsvik Opsahl, Christiaan Perneel

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The surface classification of heterogeneous urban areas can be refined using the integration of spectral and 3D information. However, pixel-classification based fusion requires semi-pixel geo-registration accuracy. In this paper the 3D information is obtained from the hyperspectral data set itself. This study presents an adaptation of optimized MRF based stereo matching for the creation of 3D scenes using hyperspectral data. The obtained 3D information is integrated into a SVM classifier procedure. The results obtained in this study show the potential in the creation of 3D scenes using hyperspectral data and the benefit of combining this data with spectral information for better classification of the urban materials.

Original languageEnglish
Title of host publication2013 5th Workshop on Hyperspectral Image and Signal Processing
Subtitle of host publicationEvolution in Remote Sensing, WHISPERS 2013
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781509011193
DOIs
Publication statusPublished - 28 Jun 2013
Event5th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2013 - Gainesville, United States
Duration: 26 Jun 201328 Jun 2013

Publication series

NameWorkshop on Hyperspectral Image and Signal Processing, Evolution in Remote Sensing
Volume2013-June
ISSN (Print)2158-6276

Conference

Conference5th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2013
Country/TerritoryUnited States
CityGainesville
Period26/06/1328/06/13

Keywords

  • Disparity map
  • Hyperspectral
  • Markov Random Field
  • Stochastic Expectation Maximization
  • Support Vector Machine

Fingerprint

Dive into the research topics of 'Urban features classification using 3D hyperspectral data'. Together they form a unique fingerprint.

Cite this