A methodology is proposed for extracting information on land cover based on hyperspectral reflectance data derived from satellite image, without supervising with ground truth. The reflectance percentage, being a characteristic feature of the ground object acts as an indirect guidance to the classification and hence the method is named semi-supervised classification. It is tried with IRS LISS IV...

Dimensionality Reduction (DR) is a crucial first step in many hyperspectral processing algorithms. In some applications, such as target detection, change detection and classification, it is important to preserve the information associated to rare pixels, i.e. pixels scarcely represented in the data and containing spectral components that are linearly independent of the background. This paper pr...

When a three-dimensional wavelet decomposition is used for compression of hyperspectral images, spectral ringing artifacts can arise, manifesting themselves as systematic biases in some reconstructed spectral bands. More generally, systematic differences in signal level in different spectral bands can hurt compression effectiveness of spatially low-pass subbands. The mechanism by which this occ...

A hyperspectral sensor and a full waveform LiDAR were flown over a temperate Eucalyptus forest in Australia, at the location of the Tumbarumba Ozflux site. Ground cover and leaf area index were derived from the LiDAR dataset while chlorophyll content maps were generated from the hyperspectral imagery using 3D radiative transfer models and the structural information derived from the LiDAR. These...

We describe a proof of concept for class knowledge transfer from a labeled hyperspectral image to an unlabeled image, captured with a different (hyper-/multi-spectral) sensor, when the spatial extents of the images partially overlap. By defining a set of spatio-spectral correspondences between the labeled source image and the unlabeled target image, we create a mapping between the images we can...