Title :
The fully adaptive GMRF anomaly detector for hyperspectral imagery
Author :
Thornton, Susan M. ; Moura, José M F
Author_Institution :
Dept. of Electr. & Comput. Eng., Carnegie Mellon Univ., Pittsburgh, PA, USA
Abstract :
The use of hyperspectral imagery for remote sensing detection applications has received attention due to the ability of the hyperspectral sensor to provide registered information in both space and frequency. However, this coupling of spatial and spectral information leads to an immense amount of data for which it has proven difficult to develop an efficient implementation of the maximum-likelihood (ML) detector. We present the Gauss-Markov random field (GMRF) detector which we have developed for detecting man-made anomalies in hyperspectral imagery. The GMRF detector is the first computationally efficient ML-detector for hyperspectral imagery. We compare the detection performance and the computational requirements of our detector implementation to the benchmark RX detection algorithm for hyperspectral imagery
Keywords :
Gaussian processes; Markov processes; image processing; maximum likelihood detection; object detection; random processes; remote sensing; spectral analysis; Gauss-Markov random field; benchmark RX detection algorithm; computational requirements; computationally efficient ML-detector; detection performance; fully adaptive GMRF anomaly detector; hyperspectral imagery; hyperspectral sensor; man-made anomalies; maximum-likelihood detector; object detection; receiver detection; registered information; remote sensing detection applications; spatial information; spectral information; Detection algorithms; Detectors; Equations; Frequency; Gaussian processes; Hyperspectral imaging; Hyperspectral sensors; Lattices; Maximum likelihood detection; Remote sensing;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 2000. ICASSP '00. Proceedings. 2000 IEEE International Conference on
Conference_Location :
Istanbul
Print_ISBN :
0-7803-6293-4
DOI :
10.1109/ICASSP.2000.861855
