| Paper: | SS-12.5 | ||
| Session: | Hyperspectral Signal Processing | ||
| Time: | Friday, May 19, 17:50 - 18:10 | ||
| Presentation: | Special Session Lecture | ||
| Topic: | Special Sessions: Hyperspectral signal processing | ||
| Title: | Parametric Adaptive Signal Detection for Hyperspectral Imaging | ||
| Authors: | Hongbin Li, Stevens Institute of Technology, United States; James H. Michels, JHM Technologies, United States | ||
| Abstract: | In this paper, we introduce a class of training-efficient adaptive signal detectors that exploit a parametric model taking into account the non-stationarity of HSI data in the spectral dimension. A maximum likelihood (ML) estimator is presented for estimation of the parameters associated with the proposed parametric model. Several important issues are discussed, including model order selection, training screening, and time-series based whitening and detection, which are intrinsic parts of the proposed parametric adaptive detectors. Experimental results using real HSI data reveal that the proposed parametric detectors are more training-efficient and outperform conventional covariance-matrix based detectors when the training size is limited. | ||
©2018 Conference Management Services, Inc. -||- email: webmaster@icassp2006.org -||- Last updated Friday, August 17, 2012