Land cover time profiles from linear mixture models applied to MODIS images

P. Oliveira, P. Gonçalves, Mário Caetano

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A multi-temporal extension of Linear Mixture Models (LMM) is investigated. Applied to a full year sequence of MODIS 500 meters resolution images, time-varying Linear Mixture Models provide us with the inter-annua evouton of "vegetaton", "soil" and "shadow" sub-pixel components. Reported work is a descriptive analysis of the results and stands as a preliminary study towards automatic multi-temporal LMM based characterization and classification of land cover.

Original languageEnglish
Title of host publicationProceedings, 31st International Symposium on Remote Sensing of Environment, ISRSE 2005
Subtitle of host publicationGlobal Monitoring for Sustainability and Security
Publication statusPublished - 1 Dec 2005
Event31st International Symposium on Remote Sensing of Environment, ISRSE 2005: Global Monitoring for Sustainability and Security - St. Petersburg, Russian Federation
Duration: 20 Jun 200524 Jun 2005

Conference

Conference31st International Symposium on Remote Sensing of Environment, ISRSE 2005: Global Monitoring for Sustainability and Security
CountryRussian Federation
CitySt. Petersburg
Period20/06/0524/06/05

Keywords

  • Land cover
  • MODIS
  • Spectral mixture analysis
  • Temporal remote sensing
  • Time series

Fingerprint Dive into the research topics of 'Land cover time profiles from linear mixture models applied to MODIS images'. Together they form a unique fingerprint.

Cite this