Abstract
Regression-based unmixing for quantifying urban land cover at the subpixel scale requires mixed training spectra for model calibration. In this paper optimization and synthetic mixing of hyperspectral image endmember libraries for the calibration of unmixing models are investigated. APEX and HyMap airborne hyperspectral transects respectively covering Brussels and Berlin are used to produce an endmember library for unmixing, as well as reference land cover fractions for validation. The library is spectrally resampled, optimized and synthetically mixed to produce quantitative training data for unmixing of a Sentinel-2 surface reflectance image of Brussels (Belgium). Support Vector Regression models are developed for vegetation-impervious-soil land cover mapping. Findings may contribute to the use of multi-sensor data and to the demonstration of Sentinel-2's added value for quantitative urban land cover assessment.
Original language | English |
---|---|
Title of host publication | 2017 Joint Urban Remote Sensing Event (JURSE) |
Place of Publication | Dubai, United Arab Emirates |
Publisher | IEEE |
Pages | 1-4 |
Number of pages <span style="color:red"p> <font size="1.5"> ✽ </span> </font> | 4 |
Edition | 2017 |
ISBN (Electronic) | 978-1-5090-5808-2 |
ISBN (Print) | 978-1-5090-5809-9 |
DOIs | |
Publication status | Published - 2017 |
Event | Joint Urban Remote Sensing Event - Ritz-Carlton Hotel Dubai, Dubai, United Arab Emirates Duration: 6 Mar 2017 → 8 Mar 2017 http://www.jurse2017.com/ |
Conference
Conference | Joint Urban Remote Sensing Event |
---|---|
Abbreviated title | JURSE |
Country/Territory | United Arab Emirates |
City | Dubai |
Period | 6/03/17 → 8/03/17 |
Internet address |
Keywords
- endmember libraries, land cover, Sentinel-2, sub-pixel mapping, Support Vector Regression, synthetic mixing, urban remote sensing