Multiple endmember unmixing of CHRIS/Proba imagery for mapping impervious surfaces in urban and suburban environments
- Author
- Luca Demarchi, Frank Canters, Jonathan Cheung-Wai Chan and Tim Van de Voorde (UGent)
- Organization
- Abstract
- In this paper, the potential of Compact High-Resolution Imaging Spectrometer (CHRIS)/Project for On-Board Autonomy data for impervious surface mapping is tested in a mixed urban/suburban/rural environment including part of the city of Leuven (Belgium) using multiple endmember unmixing. Various unmixing scenarios are compared, using different threshold values for the RMSE criterion applied to select the proper model for unmixing each pixel. Validation based on 25-cm aerial photography shows that the use of threshold values that favor the application of models with a small number of endmembers performs better compared to scenarios that make use of models with more endmembers. Detailed analysis of model selection for pixels with different land-cover composition indicates that the error in fraction estimation is partly related to spectral confusion between impervious surface types and bare soil, leading to the selection of inappropriate models for the unmixing. In spite of the spectral similarity of soil and impervious surface endmembers, average fractional error for impervious surfaces, vegetation, and bare soil is around 15%, which demonstrates the potential of CHRIS data for mapping the major physical components of the urban/suburban environment at the subpixel scale.
- Keywords
- SPECTRAL MIXTURE ANALYSIS, SNOW-COVERED AREA, HYPERSPECTRAL IMAGERY, GRAIN-SIZE, MODEL, SELECTION, ETM+, TREE, Compact High-Resolution Imaging Spectrometer/Project for On Board, Autonomy (CHRIS/Proba), impervious surface mapping, multiple endmember, unmixing
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-8645284
- MLA
- Demarchi, Luca, et al. “Multiple Endmember Unmixing of CHRIS/Proba Imagery for Mapping Impervious Surfaces in Urban and Suburban Environments.” IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, vol. 50, no. 9, 2012, pp. 3409–24, doi:10.1109/TGRS.2011.2181853.
- APA
- Demarchi, L., Canters, F., Chan, J. C.-W., & Van de Voorde, T. (2012). Multiple endmember unmixing of CHRIS/Proba imagery for mapping impervious surfaces in urban and suburban environments. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 50(9), 3409–3424. https://doi.org/10.1109/TGRS.2011.2181853
- Chicago author-date
- Demarchi, Luca, Frank Canters, Jonathan Cheung-Wai Chan, and Tim Van de Voorde. 2012. “Multiple Endmember Unmixing of CHRIS/Proba Imagery for Mapping Impervious Surfaces in Urban and Suburban Environments.” IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 50 (9): 3409–24. https://doi.org/10.1109/TGRS.2011.2181853.
- Chicago author-date (all authors)
- Demarchi, Luca, Frank Canters, Jonathan Cheung-Wai Chan, and Tim Van de Voorde. 2012. “Multiple Endmember Unmixing of CHRIS/Proba Imagery for Mapping Impervious Surfaces in Urban and Suburban Environments.” IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 50 (9): 3409–3424. doi:10.1109/TGRS.2011.2181853.
- Vancouver
- 1.Demarchi L, Canters F, Chan JC-W, Van de Voorde T. Multiple endmember unmixing of CHRIS/Proba imagery for mapping impervious surfaces in urban and suburban environments. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING. 2012;50(9):3409–24.
- IEEE
- [1]L. Demarchi, F. Canters, J. C.-W. Chan, and T. Van de Voorde, “Multiple endmember unmixing of CHRIS/Proba imagery for mapping impervious surfaces in urban and suburban environments,” IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, vol. 50, no. 9, pp. 3409–3424, 2012.
@article{8645284,
abstract = {{In this paper, the potential of Compact High-Resolution Imaging Spectrometer (CHRIS)/Project for On-Board Autonomy data for impervious surface mapping is tested in a mixed urban/suburban/rural environment including part of the city of Leuven (Belgium) using multiple endmember unmixing. Various unmixing scenarios are compared, using different threshold values for the RMSE criterion applied to select the proper model for unmixing each pixel. Validation based on 25-cm aerial photography shows that the use of threshold values that favor the application of models with a small number of endmembers performs better compared to scenarios that make use of models with more endmembers. Detailed analysis of model selection for pixels with different land-cover composition indicates that the error in fraction estimation is partly related to spectral confusion between impervious surface types and bare soil, leading to the selection of inappropriate models for the unmixing. In spite of the spectral similarity of soil and impervious surface endmembers, average fractional error for impervious surfaces, vegetation, and bare soil is around 15%, which demonstrates the potential of CHRIS data for mapping the major physical components of the urban/suburban environment at the subpixel scale.}},
author = {{Demarchi, Luca and Canters, Frank and Chan, Jonathan Cheung-Wai and Van de Voorde, Tim}},
issn = {{0196-2892}},
journal = {{IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING}},
keywords = {{SPECTRAL MIXTURE ANALYSIS,SNOW-COVERED AREA,HYPERSPECTRAL IMAGERY,GRAIN-SIZE,MODEL,SELECTION,ETM+,TREE,Compact High-Resolution Imaging Spectrometer/Project for On Board,Autonomy (CHRIS/Proba),impervious surface mapping,multiple endmember,unmixing}},
language = {{eng}},
number = {{9}},
pages = {{3409--3424}},
title = {{Multiple endmember unmixing of CHRIS/Proba imagery for mapping impervious surfaces in urban and suburban environments}},
url = {{http://doi.org/10.1109/TGRS.2011.2181853}},
volume = {{50}},
year = {{2012}},
}
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: