PRARSHIA 2012 - Pattern Recognition Applications in Remotely Sensed Hyperspectral Image Analysis 2012

Hyperspectral imaging is concerned with the measurement, analysis and interpretation of spectra acquired from a given scene by an airborne or satellite imaging spectrometer providing information in narrow wavelengths.
The special characteristics of remotely sensed hyperspectral images pose different processing problems which must be necessarily tackled under specific mathematical formalisms, such as classification and segmentation, or spectral unmixing. For instance, several machine learning techniques are now actively being applied to extract relevant information (in supervised, semi-supervised or unsupervised fashion) from remotely sensed hyperspectral data. This special session aims at providing an overview of recent advances in the use of pattern recognition and machine learning techniques for hyperspectral data interpretation, with particular attention to specific aspects of hyperspectral image analysis such as the presence of mixed pixels or the high computational requirements introduced by the processing of data sets provided by the latest generation of imaging instruments.