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 language | English |
---|---|
Title of host publication | Proceedings, 31st International Symposium on Remote Sensing of Environment, ISRSE 2005 |
Subtitle of host publication | Global Monitoring for Sustainability and Security |
Publication status | Published - 1 Dec 2005 |
Event | 31st International Symposium on Remote Sensing of Environment, ISRSE 2005: Global Monitoring for Sustainability and Security - St. Petersburg, Russian Federation Duration: 20 Jun 2005 → 24 Jun 2005 |
Conference
Conference | 31st International Symposium on Remote Sensing of Environment, ISRSE 2005: Global Monitoring for Sustainability and Security |
---|---|
Country/Territory | Russian Federation |
City | St. Petersburg |
Period | 20/06/05 → 24/06/05 |
Keywords
- Land cover
- MODIS
- Spectral mixture analysis
- Temporal remote sensing
- Time series