Hyperspectral Remote Sensing Image Subpixel Target Detection Based on Supervised Metric Learning
- 8 November 2013
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 52 (8), 4955-4965
- https://doi.org/10.1109/tgrs.2013.2286195
Abstract
The detection and identification of target pixels such as certain minerals and man-made objects from hyperspectral remote sensing images is of great interest for both civilian and military applications. However, due to the restriction in the spatial resolution of most airborne or satellite hyperspectral sensors, the targets often appear as subpixels in the hyperspectral image (HSI). The observed spectral feature of the desired target pixel (positive sample) is therefore a mixed signature of the reference target spectrum and the background pixels spectra (negative samples), which belong to various land cover classes. In this paper, we propose a novel supervised metric learning (SML) algorithm, which can effectively learn a distance metric for hyperspectral target detection, by which target pixels are easily detected in positive space while the background pixels are pushed into negative space as far as possible. The proposed SML algorithm first maximizes the distance between the positive and negative samples by an objective function of the supervised distance maximization. Then, by considering the variety of the background spectral features, we put a similarity propagation constraint into the SML to simultaneously link the target pixels with positive samples, as well as the background pixels with negative samples, which helps to reject false alarms in the target detection. Finally, a manifold smoothness regularization is imposed on the positive samples to preserve their local geometry in the obtained metric. Based on the public data sets of mineral detection in an Airborne Visible/Infrared Imaging Spectrometer image and fabric and vehicle detection in a Hyperspectral Mapper image, quantitative comparisons of several HSI target detection methods, as well as some state-of-the-art metric learning algorithms, were performed. All the experimental results demonstrate the effectiveness of the proposed SML algorithm for hyperspectral target detection.Keywords
Funding Information
- National Basic Research Program of China (973 Program) (2011CB707105, 2012CB719905)
- Program for Changjiang Scholars and Innovative Research Team in University ((IRT1278))
- National Natural Science Foundation of China (41101336, 61102128, 41061130553)
- Program for New Century Excellent Talents in University of China (NCET-11-0396)
This publication has 45 references indexed in Scilit:
- Semisupervised Multiview Distance Metric Learning for Cartoon SynthesisIEEE Transactions on Image Processing, 2012
- A boosting approach for supervised Mahalanobis distance metric learningPattern Recognition, 2012
- Sparse Representation for Target Detection in Hyperspectral ImageryIEEE Journal of Selected Topics in Signal Processing, 2011
- Simultaneous Joint Sparsity Model for Target Detection in Hyperspectral ImageryIEEE Geoscience and Remote Sensing Letters, 2011
- Semisupervised Metric Learning by Maximizing Constraint MarginIEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2011
- Target Detection With Semisupervised Kernel Orthogonal Subspace ProjectionIEEE Transactions on Geoscience and Remote Sensing, 2009
- Learning Distance Metrics with Contextual Constraints for Image RetrievalPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Kernel Spectral Matched Filter for Hyperspectral ImageryInternational Journal of Computer Vision, 2006
- Detection algorithms for hyperspectral imaging applicationsIEEE Signal Processing Magazine, 2002
- Imaging Spectroscopy and the Airborne Visible/Infrared Imaging Spectrometer (AVIRIS)Remote Sensing of Environment, 1998