Target Detection With Semisupervised Kernel Orthogonal Subspace Projection
- 7 July 2009
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 47 (11), 3822-3833
- https://doi.org/10.1109/tgrs.2009.2020910
Abstract
The orthogonal subspace projection (OSP) algorithm is substantially a kind of matched filter that requires the evaluation of a prototype for each class to be detected. The kernel OSP (KOSP) has recently demonstrated improved results for target detection in hyperspectral images. The use of kernel methods (KMs) makes the method nonlinear, helps to combat the high-dimensionality problem, and improves robustness to noise. This paper presents a semisupervised graph-based approach to improve KOSP. The proposed algorithm deforms the kernel by approximating the marginal distribution using the unlabeled samples. Two further improvements are presented. First, a contextual selection of unlabeled samples is proposed. This strategy helps in better modeling the data manifold, and thus, improved sensitivity-specificity rates are obtained. Second, given the high computational burden involved, we present two alternative formulations based on the Nystroumlm method and the incomplete Cholesky factorization to achieve operational processing times. The good performance of the proposed method is illustrated in a toy data set and two relevant hyperspectral image target-detection applications: crop identification and thermal hot-spot detection. A clear improvement is observed with respect to the linear and the nonlinear kernel-based OSP, demonstrating good generalization capabilities when a low number of labeled samples are available, which is usually the case in target-detection problems. The relevance of unlabeled samples and the computational cost are also analyzed in detail.Keywords
This publication has 22 references indexed in Scilit:
- Biophysical Parameter Estimation With a Semisupervised Support Vector MachineIEEE Geoscience and Remote Sensing Letters, 2009
- Semi-Supervised LearningPublished by MIT Press ,2006
- Dimensionality Reduction by Learning an Invariant MappingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Kernel orthogonal subspace projection for hyperspectral signal classificationIEEE Transactions on Geoscience and Remote Sensing, 2005
- Kernel-based methods for hyperspectral image classificationIEEE Transactions on Geoscience and Remote Sensing, 2005
- Beyond the point cloudPublished by Association for Computing Machinery (ACM) ,2005
- On the Convergence of Pattern Search AlgorithmsSIAM Journal on Optimization, 1997
- The relative value of labeled and unlabeled samples in pattern recognition with an unknown mixing parameterIEEE Transactions on Information Theory, 1996
- Deflation Techniques for an Implicitly Restarted Arnoldi IterationSIAM Journal on Matrix Analysis and Applications, 1996
- On the exponential value of labeled samplesPattern Recognition Letters, 1995