-
IEEE Transactions on Image Processing. 01/2012; 21:184-195.
-
[show abstract]
[hide abstract]
ABSTRACT: Model-free single-frame blind image deconvolution (BID) method is proposed by converting BID into blind source separation (BSS), whereas sources represent the original image and its spatial derivatives. Continuous wavelet transform (CWT) is used to generate multi-channel image necessary for BSS. As opposed to an approach based on the Gabor filter bank, this brings additional options in adaptability to the problem at hand: through the choice of wavelet function and variation of the scale of the CWT. BSS is performed through orthogonality constrained factorization of the 3D multichannel image tensor by means of the higher-order-orthogonal-iteration algorithm. The proposed method virtually requires no information about blurring kernel: neither model nor size of the support. The method is demonstrated on experimental gray scale images degraded by de-focusing and atmospheric turbulence. A comparable or better performance is demonstrated relative to blind Richardson-Lucy method that, however, requires a priori information about parametric model of the blur.
Image and Signal Processing and Analysis (ISPA), 2011 7th International Symposium on; 10/2011
-
[show abstract]
[hide abstract]
ABSTRACT: The high dimensionality of hyperspectral imagery challenges image processing and analysis. Band selection is a common technique for dimensionality reduction. When the desired object information is unknown, an unsupervised band selection approach is employed to select the most distinctive and informative bands. Although band selection can significantly alleviate the computational burden in the following data processing and analysis, the process itself may induce additional computation complexity, especially when the image spatial size is large; it may be time-consuming for unsupervised band selection methods that need to take all pixels into consideration. Parallel computing techniques are widely adopted to alleviate the computational burden and to achieve real-time processing of data with vast volume. In this paper, we propose parallel implementations via emerging general-purpose graphics processing units (GPUs) for band selection without changing band selection result. Its speedup performance is comparable to the cluster-based parallel implementation. We also propose an approach to using several selected pixels for unsupervised band selection and the number of pixels needed can be equal to the number of selected bands minus one. With whitened pixel signatures (not the original pixels), band selection performance can be comparable to or even better than that from using all the pixels. For this approach, parallel computing is implemented for pixel selection only, since computational complexity in band selection has been greatly reduced.
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 10/2011; · 1.49 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: This study evaluated linear spectral unmixing (LSU), mixture tuned matched filtering (MTMF) and support vector machine (SVM) techniques for detecting and mapping giant reed (Arundo donax L.), an invasive weed that presents a severe threat to agroecosystems and riparian areas throughout the southern United States and northern Mexico. Airborne hyperspectral imagery with 102 usable bands covering a spectral range of 475–845 nm was collected from a giant reed-infested site along the US-Mexican portion of the Rio Grande in 2009 and 2010. The imagery was transformed with minimum noise fraction (MFN) to reduce the spectral dimensionality and noise. The three classification techniques (LSU, MTMF and SVM) were applied to the transformed MNF imagery based 11 endmember spectra extracted from the images for each of the two years. Accuracy assessment and kappa analysis were performed to compare the differences in classification accuracies among the three classification methods. Results showed that SVM and MTMF performed better than LSU, with SVM being the best classifier in both years. The results from this study indicate that hyperspectral imagery in conjunction with image classification techniques is useful for distinguishing giant reed from associated plant species and for monitoring the progression of this invasive weed.
Geoscience and Remote Sensing Symposium (IGARSS), 2011 IEEE International; 08/2011
-
[show abstract]
[hide abstract]
ABSTRACT: The compression of multitemporal hyperspectral imagery is considered, wherein the encoder uses a reference image to effectuate temporal decorrelation for the coding of the current image. Both linear prediction and a spectral concatenation of images are explored to this end. Experimental results demonstrate that, when there are few changes between two images, the gain in rate-distortion performance is achieved over the independent coding of the current image. In addition, a strategy that explicitly removes salient temporal changes and stores them losslessly in the bitstream is proposed, and it is observed that this change-removal process results in a slight decrease in the rate-distortion performance with the benefit of perfect representation of the changed pixels.
IEEE Geoscience and Remote Sensing Letters 06/2011; · 1.56 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: Due to the high data dimensionality of a hyperspectral image, dimensionality reduction algorithm has attracted much attention in hyperspectral image analysis. Band selection algorithm, which selects appropriate bands from the original set of spectral bands, can preserve original information from the data and is useful for image classification and recognition. In the present paper, a novel band selection algorithm based on orthogonal projection divergence (OPD) is proposed, it aims to discriminate the interesting objects from background and noise information, maximize the spectral similarity between different spectral vectors by projecting the original data to feature space. Two HYDICE Washington DC Mall images and an HYMAP Purdue campus image data were experimented, and support vector machine (SVM) classifier was used for classification. The selected band number varies from 5 to 40 in order to study the impacts of different band selection algorithms on different features. For the computation complex, the sequential floating forward search (SFFS) was used to get the appropriate bands. The experiments have proved that our proposed OPD algorithm can outperform other traditional band selection methods such as SAM, ED, SID, and LCMV-BCC for hyperspectral image analysis. It is proven that OPD band selection is effective and robust in hyperspectral remote sensing dimensionality reduction
Guang pu xue yu guang pu fen xi = Guang pu 05/2011; 31(5):1309-13. · 0.84 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: High-dimensional data such as hyperspectral imagery is traditionally acquired in full dimensionality before being reduced
in dimension prior to processing. Conventional dimensionality reduction on-board remote devices is often prohibitive due to
limited computational resources; on the other hand, integrating random projections directly into signal acquisition offers
an alternative to explicit dimensionality reduction without incurring sender-side computational cost. Receiver-side reconstruction
of hyperspectral data from such random projections in the form of compressive-projection principal component analysis (CPPCA)
as well as compressed sensing (CS) is investigated. Specifically considered are single-task CS algorithms which reconstruct
each hyperspectral pixel vector of a dataset independently as well as multi-task CS in which the multiple, possibly correlated
hyperspectral pixel vectors are reconstructed simultaneously. These CS strategies are compared to CPPCA reconstruction which
also exploits cross-vector correlations. Experimental results on popular AVIRIS datasets reveal that CPPCA outperforms various
CS algorithms in terms of both squared-error as well as spectral-angle quality measures while requiring only a fraction of
the computational cost.
KeywordsHyperspectral data-Principal component analysis (PCA)-Random projections-Rayleigh-Ritz theory
03/2011: pages 31-48;
-
[show abstract]
[hide abstract]
ABSTRACT: Displaying the abundant information contained in a remotely sensed hyperspectral image is a challenging problem. Currently
no approach can satisfactorily render the desired information at arbitrary levels of detail. This chapter discusses user studies
on several approaches for representing the information contained in hyperspectral information. In particular, we compared
four visualization methods: grayscale side-by-side display (GRAY), hard visualization (HARD), soft visualization (SOFT), and
double-layer visualization (DBLY). We designed four tasks to evaluate these techniques in their effectiveness at conveying
global and local information in an effort to provide empirical guidance for better visual analysis methods. We found that
HARD is less effective for global pattern display and conveying local detailed information. GRAY and SOFT are effective and
comparable for showing global patterns, but are less effective for revealing local details. Finally, DBLY visualization is
efficient in conveying local detailed information and is as effective as GRAY and SOFT for global pattern depiction.
KeywordsHyperspectral data visualization-Color display
03/2011: pages 81-98;
-
[show abstract]
[hide abstract]
ABSTRACT: Band selection is often applied to reduce the dimensionality of hyperspectral imagery. When the desired object information is known, it can be achieved by finding the bands that contain the most object information. It is expected that these bands can provide an overall satisfactory detection and classification performance. In this letter, we propose a new supervised band-selection algorithm that uses the known class signatures only without examining the original bands or the need of class training samples. Thus, it can complete the task much faster than traditional methods that test bands or band combinations. The experimental result shows that our approach can generally yield better results than other popular supervised band-selection methods in the literature.
IEEE Geoscience and Remote Sensing Letters 02/2011; · 1.56 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: We present a noise-adjusted principal component analysis (NAPCA)-based approach to the detection and classification of buried radioactive targets with short sensor dwell time. The data used in the experiments is the gamma spectroscopy collected by a Sodium Iodide (NAI) scintillation detector. Spectral transformation methods are first applied to the data, followed by NAPCA. Then k -nearest neighbor ( k NN) clustering is applied to the NAPCA-transformed feature subspace to achieve detection or classification. This method is evaluated using a database of 240 spectral measurements consisting of background (construction sand), benign material measurements (uranium ore), and target measurements (depleted uranium) at various depths. Compared to other widely used algorithms for depleted uranium, the proposed technique can provide better performance.
IEEE Transactions on Nuclear Science 01/2011; · 1.45 Impact Factor
-
IEEE Geosci. Remote Sensing Lett. 01/2011; 8:416-420.
-
2011 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2011, Vancouver, BC, Canada, July 24-29, 2011; 01/2011
-
IEEE Geosci. Remote Sensing Lett. 01/2011; 8:138-142.
-
IEEE Geosci. Remote Sensing Lett. 01/2011; 8:1135-1139.
-
2011 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2011, Vancouver, BC, Canada, July 24-29, 2011; 01/2011
-
2011 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2011, Vancouver, BC, Canada, July 24-29, 2011; 01/2011
-
[show abstract]
[hide abstract]
ABSTRACT: A decision fusion approach is developed to combine the results from supervised and unsupervised classifiers. The final output takes advantage of the power of a support-vector-machine-based supervised classification in class separation and the capability of an unsupervised classifier, such as K -means clustering, in reducing trivial spectral variation impact in homogeneous regions. This approach can simply adopt the majority voting (MV) rule to achieve the same objective of object-based classification. In this letter, we propose a weighted MV (WMV) rule for decision fusion, where pixels in the same segment contribute differently according to their distance to the spectral centroid. The WMV rule can further improve the performance of the original MV rule. A series of unsupervised classifiers is investigated in the use of decision fusion, and recommendations are provided on the best unsupervised classifiers to be selected.
IEEE Geoscience and Remote Sensing Letters 11/2010; · 1.56 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: Nonlinear spectral mixture analysis for hyperspectral imagery is investigated without prior information about the image scene. A simple but effective nonlinear mixture model is adopted, where the multiplication of each pair of endmembers results in a virtual endmember representing multiple scattering effect during pixel construction process. The analysis is followed by linear unmixing for abundance estimation. Due to a large number of nonlinear terms being added in an unknown environment, the following abundance estimation may contain some errors if most of the endmembers do not really participate in the mixture of a pixel. We take advantage of the developed endmember variable linear mixture model (EVLMM) to search the actual endmember set for each pixel, which yields more accurate abundance estimation in terms of smaller pixel reconstruction error, smaller residual counts, and more pixel abundances satisfying sum-to-one and nonnegativity constraints.
IEEE Geoscience and Remote Sensing Letters 11/2010; · 1.56 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: We investigate buried depleted uranium detection and classification using data collected with short sensor dwell time (i.e., less than or equal to 1s). Under this circumstance, the gamma spectroscope collected by a NaI detector can be sparse and random, and may be severely affected by energy counts from the background. Several spectral transformations using binned energy windows can help alleviate the negative effect from background spectral noisy variation. The simplest way for such spectral partition is to use a fixed bin-width for uniform partition. In this paper, we propose a particle swarm optimization (PSO)-based optimization method to automatically determine the varied bin-width for each energy window. The experimental result shows that the spectral transformation methods using PSO-selected bins with variable widths can outperform those with a fixed bin-width.
Computational Intelligence for Measurement Systems and Applications (CIMSA), 2010 IEEE International Conference on; 10/2010
-
[show abstract]
[hide abstract]
ABSTRACT: Displaying the abundant information contained in a remotely sensed hyperspectral image is a challenging problem. Currently, no approach can satisfactorily render the desired information at arbitrary levels of detail. In this paper, we present a feature-driven multilayer visualization technique that automatically chooses data visualization techniques based on the spatial distribution and importance of the endmembers. It can simultaneously visualize the overall material distribution, subpixel level details, and target pixels and materials. By incorporating interactive tools, different levels of detail can be presented per users' request. This scheme employs five layers from the bottom to the top: the background layer, data-driven spot layer, pie-chart layer, oriented sliver layer, and anomaly layer. The background layer provides the basic tone of the display; the data-driven spot layer manifests the overall material distribution in an image scene; the pie-chart layer presents the precise abundances of endmember materials in each pixel; the oriented sliver layer emphasizes the distribution of important anomalous materials; and the anomaly layer highlights anomaly pixels (i.e., potential targets). Displays of the airborne AVIRIS data and spaceborne Hyperion data demonstrate that the proposed multilayer visualization scheme can efficiently display more information globally and locally.
IEEE Transactions on Geoscience and Remote Sensing 10/2010; · 2.89 Impact Factor
