Nonlinear estimation of subpixel proportion via kernel least square regression
Authors:
- 23 August 2007
- journal article
- research article
- Published by Taylor & Francis in International Journal of Remote Sensing
- Vol. 28 (18) , 4157-4172
Abstract
Spectral mixture analysis is an efficient approach to spectral decomposition of hyperspectral remotely sensed imagery, using land cover proportions which can be estimated from pixel values through model inversion. In this paper, a kernel least square regression algorithm has been developed for nonlinear approximation of subpixel proportions. This procedure includes two steps. The first step is to select the feature vectors by defining a global criterion to characterize the image data structure in the feature space and the second step is the projection of pixels onto the feature vectors and the application of classical linear regressive algorithm. Experiments using simulated data, synthetic data and Enhanced Thematic Mapper (ETM)+ data have been carried out, and the results demonstrate that the proposed method can improve proportion estimation. By using the simulated and synthetic data, over 85% of the total pixels in the image are found to lie between the 10% difference lines, and the root mean square error (RMSE) is less than 0.09. Using the real data, the proposed method can also perform satisfactorily with an average RMSE of about 0.12. This algorithm was also compared with other widely used kernel based algorithms, i.e. support vector regression and radial basis function neutral network and the results show that the proposed algorithm outperforms other algorithms about 5% in subpixel proportion estimation.Keywords
This publication has 23 references indexed in Scilit:
- Comparison of non-linear mixture models: sub-pixel classificationRemote Sensing of Environment, 2005
- Kernel-Based Nonlinear Blind Source SeparationNeural Computation, 2003
- A quantitative and comparative analysis of linear and nonlinear spectral mixture models using radial basis function neural networksIEEE Transactions on Geoscience and Remote Sensing, 2001
- Optimal linear spectral unmixingIEEE Transactions on Geoscience and Remote Sensing, 1999
- Nonlinear spectral mixture modeling of lunar multispectral data: Implications for lateral transportJournal of Geophysical Research, 1998
- Unmixing AVHRR imagery to assess clearcuts and forest regrowth in OregonIEEE Transactions on Geoscience and Remote Sensing, 1995
- Forest canopy closure from classification and spectral unmixing of scene components-multisensor evaluation of an open canopyIEEE Transactions on Geoscience and Remote Sensing, 1994
- Simple algorithms for remote determination of mineral abundances and particle sizes from reflectance spectraJournal of Geophysical Research, 1992
- Subpixel measurement of tropical forest cover using AVHRR dataInternational Journal of Remote Sensing, 1991
- Bidirectional reflectance spectroscopy: 1. TheoryJournal of Geophysical Research, 1981