Title :
Spectral information divergence for hyperspectral image analysis
Author_Institution :
Remote Sensing Signal & image Process. Lab., Maryland Univ., Baltimore, MD, USA
Abstract :
The authors propose an information theoretic criterion, called spectral information divergence (SID) for spectral similarity and discriminability. It is derived from the concept of divergence arising in information theory and can be used to describe the statistics of a spectrum. Unlike spectral angle mapper (SAM) which extracts geometric features between two spectra, SID views each pixel spectrum as a random variable and then measures the discrepancy of probabilistic behaviors between two spectra. In order to evaluate SID, SAM is used for comparison via hyperspectral data. Experimental results show that SID can characterise spectral similarity and variability more effectively than SAM
Keywords :
geophysical signal processing; geophysical techniques; multidimensional signal processing; remote sensing; terrain mapping; discriminability; geophysical measurement technique; hyperspectral image analysis; information theoretic criterion; land surface; multidimensional signal processing; multispectral remote sensing; optical imaging; remote sensing; spectral information divergence; spectral similarity; terrain mapping; Data mining; Hyperspectral imaging; Hyperspectral sensors; Image analysis; Information theory; Interference; Pattern classification; Pixel; Random variables; Remote sensing;
Conference_Titel :
Geoscience and Remote Sensing Symposium, 1999. IGARSS '99 Proceedings. IEEE 1999 International
Conference_Location :
Hamburg
Print_ISBN :
0-7803-5207-6
DOI :
10.1109/IGARSS.1999.773549