Title :
Automatic modeling of nonlinear signal source variations in hyperspectral data
Author :
Gross, Wolfgang ; Keskin, Goksu ; Schilling, Hendrik ; Lenz, Andreas ; Middelmann, Wolfgang
Abstract :
Nonlinear effects in hyperspectral data complicate classification and other data analysis procedures. Transforming the data onto manifolds can help to improve the results while simultaneously reducing the dimensionality due to the high correlation among the spectral bands. Methods like ISOMAP or Locally Linear Embedding are not ideal when the data is degraded by noise. In this paper, a method is introduced to automatically generate support points for skeletonizing a high-dimensional point cloud. The skeleton is identified with multiple signal source variations of distinct materials and can be used to transform the data to improve further analysis procedures.
Keywords :
clouds; geophysical signal processing; remote sensing; ISOMAP; airborne data; automatic model; data analysis procedures; data transform; high-dimensional point cloud; hyperspectral data; hyperspectral remote sensing data; locally linear embedding method; nonlinear signal source variations; satellite data; spectral bands; Data mining; Data models; Hyperspectral imaging; Manifolds; Materials; Noise; Hyperspectral; manifold learning; nonlinear modeling; skeletonizing;
Conference_Titel :
Geoscience and Remote Sensing Symposium (IGARSS), 2014 IEEE International
Conference_Location :
Quebec City, QC
DOI :
10.1109/IGARSS.2014.6947099
