A novel technique for adaptive anomalous change detection in airborne hyperspectral imagery

Marco Diani; Salvatore Resta; Nicola Acito; Giovanni Corsini; Sergio Ugo de Ceglie

doi:10.1117/12.974628

Translator Disclaimer

19 November 2012 A novel technique for adaptive anomalous change detection in airborne hyperspectral imagery

Marco Diani, Salvatore Resta, Nicola Acito, Giovanni Corsini, Sergio Ugo de Ceglie

Author Affiliations +

Proceedings Volume 8542, Electro-Optical Remote Sensing, Photonic Technologies, and Applications VI; 854220 (2012) https://doi.org/10.1117/12.974628
Event: SPIE Security + Defence, 2012, Edinburgh, United Kingdom

Abstract

A novel technique for anomalous change detection in hyperspectral images is presented. It adaptively measures the spectral distance between corresponding pixels in multi-temporal images by exploiting the local estimates of the signal to noise ratio for each spectral component of the pixel under test. Different metrics have been compared, based on multidimensional angular distance. Results obtained by applying the new algorithm to real data are presented and discussed. Performance evaluation highlighted the effectiveness of the proposed approach with respect to traditional methods, resulting in a consistent improvement of both the probability of detection of changes and the capability of suppressing the background.

Citation Download Citation

Marco Diani, Salvatore Resta, Nicola Acito, Giovanni Corsini, and Sergio Ugo de Ceglie "A novel technique for adaptive anomalous change detection in airborne hyperspectral imagery", Proc. SPIE 8542, Electro-Optical Remote Sensing, Photonic Technologies, and Applications VI, 854220 (19 November 2012); https://doi.org/10.1117/12.974628

ACCESS THE FULL ARTICLE