Kernel-based invariant subspace method for hyperspectral target detection

In this paper, a kernel-based invariant subspace detection method is proposed for small target detection of hyperspectral images. The method combines kernel principal component analysis (KPCA) and the linear mixture model (LMM). The LMM is used to describe each pixel in the hyper-spectral image as a mixture of target, background and noise. The KPCA is used to build subspaces of the target and background. A generalized likelihood ratio test is used to detect whether each pixel in the hyperspectral image includes the target. Numerical experiments are performed on AVIRIS hyperspectral data with 126 bands. The experimental results show the effectiveness of the proposed method and prove that this method can commendably overcome spectral variability in hyperspectral target detection, and it has good ability to separate target from background.

[1]  John F. Mustard,et al.  Spectral unmixing , 2002, IEEE Signal Process. Mag..

[2]  Bernhard Schölkopf,et al.  Nonlinear Component Analysis as a Kernel Eigenvalue Problem , 1998, Neural Computation.

[3]  Gary A. Shaw,et al.  Hyperspectral adaptive matched-filter detectors: practical performance comparison , 2001, SPIE Defense + Commercial Sensing.

[4]  Bea Thai,et al.  Invariant subpixel material detection in hyperspectral imagery , 2002, IEEE Trans. Geosci. Remote. Sens..

[5]  Dimitris G. Manolakis,et al.  Detection algorithms for hyperspectral imaging applications , 2002, IEEE Signal Process. Mag..

[6]  Bea Thai,et al.  Invariant subpixel target identification in hyperspectral imagery , 1999, Defense, Security, and Sensing.

[7]  Gary A. Shaw,et al.  Hyperspectral subpixel target detection using the linear mixing model , 2001, IEEE Trans. Geosci. Remote. Sens..

[8]  Choen Kim,et al.  Spectral angle mapper classification and vegetation indices analysis for winter cover monitoring using JERS-1 OPS data , 1996, IGARSS '96. 1996 International Geoscience and Remote Sensing Symposium.