Kernel matched subspace detectors for hyperspectral target detection
- 19 December 2005
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 28 (2), 178-194
- https://doi.org/10.1109/tpami.2006.39
Abstract
In this paper, we present a kernel realization of a matched subspace detector (MSD) that is based on a subspace mixture model defined in a high-dimensional feature space associated with a kernel function. The linear subspace mixture model for the MSD is first reformulated in a high-dimensional feature space and then the corresponding expression for the generalized likelihood ratio test (GLRT) is obtained for this model. The subspace mixture model in the feature space and its corresponding GLRT expression are equivalent to a nonlinear subspace mixture model with a corresponding nonlinear GLRT expression in the original input space. In order to address the intractability of the GLRT in the feature space, we kernelize the GLRT expression using the kernel eigenvector representations as well as the kernel trick where dot products in the feature space are implicitly computed by kernels. The proposed kernel-based nonlinear detector, so-called kernel matched subspace detector (KMSD), is applied to several hyperspectral images to detect targets of interest. KMSD showed superior detection performance over the conventional MSD when tested on several synthetic data and real hyperspectral imagery.Keywords
This publication has 15 references indexed in Scilit:
- Kernel RX-algorithm: a nonlinear anomaly detector for hyperspectral imageryIEEE Transactions on Geoscience and Remote Sensing, 2005
- Shape statistics in kernel space for variational image segmentationPattern Recognition, 2003
- Invariant subpixel material detection in hyperspectral imageryIEEE Transactions on Geoscience and Remote Sensing, 2002
- Mercer kernel-based clustering in feature spaceIEEE Transactions on Neural Networks, 2002
- Generalization performance of regularization networks and support vector machines via entropy numbers of compact operatorsIEEE Transactions on Information Theory, 2001
- An introduction to kernel-based learning algorithmsIEEE Transactions on Neural Networks, 2001
- The Elements of Statistical LearningPublished by Springer Science and Business Media LLC ,2001
- Nonlinear kernel-based statistical pattern analysisIEEE Transactions on Neural Networks, 2001
- Generalized Discriminant Analysis Using a Kernel ApproachNeural Computation, 2000
- Adaptive multiple-band CFAR detection of an optical pattern with unknown spectral distributionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1990