By Topic

Geoscience and Remote Sensing, IEEE Transactions on

Issue 1  Part 1 • Date Jan. 2013

Filter Results

Displaying Results 1 - 25 of 38
  • [Front cover]

    Page(s): C1
    Save to Project icon | Request Permissions | PDF file iconPDF (734 KB)  
    Freely Available from IEEE
  • IEEE Transactions on Geoscience and Remote Sensing publication information

    Page(s): C2
    Save to Project icon | Request Permissions | PDF file iconPDF (141 KB)  
    Freely Available from IEEE
  • Table of contents

    Page(s): 1 - 2
    Save to Project icon | Request Permissions | PDF file iconPDF (130 KB)  
    Freely Available from IEEE
  • Editorial

    Page(s): 3 - 4
    Save to Project icon | Request Permissions | PDF file iconPDF (46 KB)  
    Freely Available from IEEE
  • Editorial

    Page(s): 5
    Save to Project icon | Request Permissions | PDF file iconPDF (22 KB)  
    Freely Available from IEEE
  • Experimental Study on the Atmospheric Delay Based on GPS, SAR Interferometry, and Numerical Weather Model Data

    Page(s): 6 - 11
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1228 KB) |  | HTML iconHTML  

    In this paper, we present the results of an experiment aiming to compare measurements of atmospheric delay by synthetic aperture radar (SAR) interferometry and GPS techniques to estimates by numerical weather prediction. Maps of the differential atmospheric delay are generated by processing a set of interferometric SAR images acquired by the ENVISAT-ASAR mission over the Lisbon region from April to November 2009. GPS measurements of the wet zenith delay are carried out over the same area, covering the time interval between the first and the last SAR acquisition. The Weather Research and Forecasting (WRF) model is used to model the atmospheric delay over the study area at about the same time of SAR acquisitions. The analysis of results gives hints to devise mitigation approaches of atmospheric artifacts in SAR interferometry applications. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Estimation of the Radio Refractivity Gradient From Diffraction Loss Measurements

    Page(s): 12 - 18
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1010 KB) |  | HTML iconHTML  

    The aim of this paper is to show that the gradient of the vertical radio refractivity profile of air near the ground can be estimated from measurements of electromagnetic wave strength. Diffraction can be used as the basic physical principle for non-line-of-sight radio links, where an obstacle covers some parts of the Fresnel zones, and therefore, the strength of electromagnetic wave is proportional to the ratio of coverage. The method, which is simple and easy to implement, is verified by measured data, and comparisons with meteorological measurements are presented. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Preliminary SMOS Salinity Measurements and Validation in the Indian Ocean

    Page(s): 19 - 27
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1948 KB) |  | HTML iconHTML  

    Global sea surface salinity (SSS) measurements retrieved from the European Space Agency's Soil Moisture and Ocean Salinity (SMOS) mission are the first highest resolution salinity data available from space. There are many challenges to measuring salinity from space and obtaining a targeted accuracy of 0.1 psu. Comparisons of Level 2 (L2) SMOS SSS data with the 1/12° high resolution HYbrid Coordinate Ocean Model (HYCOM) simulations of SSS reveal large differences. These differences are minimized for an extent during the creation of Level 3 (L3) SMOS data through spatial and temporal averaging. Depending on the retrieval algorithm used, there are differences between ascending and descending passes with data collected during the descending pass exhibiting a bias toward lower SSS. It is challenging to process SMOS SSS data in the northern Indian Ocean due to radio frequency interference and large seasonal variability due to monsoonal circulation. Comparisons of SMOS L3 data with Argo float SSS and HYCOM SSS indicate the lowest discrepancies in SSS for these data sets occur in the southern tropical Indian Ocean and the largest differences between the compared salinity products are noticed in the Arabian Sea and Bay of Bengal with an erratic root mean square error in the latter region. Higher errors in SSS occurred in coastal areas compared to the open ocean. The accuracy of SMOS salinity measurements is increasing with the maturity of the data and new algorithms. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Real 3-D Monte Carlo Model for the Simulation of Radiative Transfer in Waters

    Page(s): 28 - 37
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (986 KB) |  | HTML iconHTML  

    A forward Monte Carlo 3-D (FMC3D) model is developed for simulating light fields in a volume of water where the boundary conditions for radiance values can be expressed by mathematical formulas, which cannot be done using the radiative transfer models currently available such as HydroLight. Water is assumed parallel homogenous for these models, which are incapable of investigating the sidewall reflectance effect on the light fields. These ones are called quasi-3-D radiative transfer models. The FMC3D model perfects the assumption and the incapability and is validated using the in situ data measured in the tank experiment. The FMC3D model is first applied to investigate the sidewall reflectance effect on the remote sensing reflectance Rrs for waters in a fabricated tank with infinite depth and different radii. The investigation shows that the effect is decreasing with the increase in the tank radius and that the minimum radius that the effect is negligible for highly scattering water is bigger than that for highly absorbing water. Taking the tank used in the experiment carried out in a previous work by Han and Rundquist as an example, the FMC3D model is second applied to investigate the combining effects on Rrs from bottom and sidewall reflectances. Compared with Rrs for open water, the Rrs for tank water having the same inherent optical properties is underestimated. The underestimation is increasing with the increase in the single scattering albedo ω and can be up to 32% for water with ω = 0.88, showing that the effects cannot be removed by the black inside wall, which is a method commonly used in tank experiments. The potential applications of the FMC3D model are discussed, taking the examples of the correction for the wall reflectance effect on apparent spectra measured in tank experiments and of the scattering error correction for the reflective tube absorption coefficient me- sured using a WET Labs AC-9 or AC-S device. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Sea-Ice Lead Detection Algorithm for Use With High-Resolution Airborne Visible Imagery

    Page(s): 38 - 56
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2218 KB) |  | HTML iconHTML  

    The detection of leads, or cracks, in sea ice is critical for the derivation of sea-ice freeboard from altimetric measurements of sea-ice elevation. We present an approach for lead detection in sea ice using high-resolution visible imagery from airborne platforms. We develop a new algorithm, i.e., the sea-ice lead detection algorithm using minimal signal (SILDAMS), that detects clouds, extracts leads, and classifies ice types within leads from airborne visible imagery. Cloud detection is based on an assessment of local variances of pixel brightness across image scenes and where available coincident altimetric measurements are used to confirm suspected cloudy scenes. The lead extraction step computes affine time-frequency distributions (minimal signal) for the Red, Green, and Blue channels of each image. The transformed outputs are combined to take advantage of three channels simultaneously. Finally, lead pixel geolocations are extracted using a set of uniform thresholds for ice typing (including open water, thin ice, and gray ice) within leads along each flight line. SILDAMS was tested using data from the Digital Mapping System (DMS). DMS digital photographs represent the highest resolution ( ≈10 cm) visible imagery available over sea ice and were collected during NASA Operation IceBridge sea-ice flights in the Antarctic and the Arctic in 2009 and 2010, respectively. We demonstrate that SILDAMS has a high lead detection capability of 99%. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Calibration of the CryoSat-2 Interferometer and Measurement of Across-Track Ocean Slope

    Page(s): 57 - 72
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1551 KB) |  | HTML iconHTML  

    This paper describes the calibration of the CryoSat-2 interferometer, whose principal purpose is to accurately measure the height of the Antarctic and Greenland ice sheets. A sequence of CryoSat-2 data acquisitions over the tropical and midlatitude oceans were obtained between June and September 2010, from the SIRAL “A” and redundant SIRAL “B” radars operating in their “SARIN” mode, during a sequence of satellite rolls between -0.6° and 0.4°. Using the arrival angle of the echo relative to the interferometer baseline, the attitude of the satellite determined by the star trackers, and estimates of the ocean surface across-track slope from the EGM08 geoid, we determined the errors in the interferometer estimate of surface slope as functions of the roll angle and ocean surface waveheight. These were found to be in close agreement with the theoretical description. The scale factor of the interferometric measurement of angle was determined to be 0.973 ± 0.002. We estimate the accuracy of the across-track slope measurement of the interferometer by applying this scale factor to the measured phase. In applying this scale factor to the measurements, the across-track slope of the marine geoid was obtained with an accuracy of 26 μrad at 10 km and 10 μrad at 1000 km. We conclude that the instrument performance considerably exceeds that needed for the accurate determination of height over the sloping surfaces of the continental ice sheets. The results also demonstrate that CryoSat-2 provides the first observations of the instantaneous vector gradient of the ocean surface, and that the normal-incidence interferometric configuration has a greater potential for the measurement of the ocean across-track slope than has been previously recognized. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Tree Species Discrimination in Tropical Forests Using Airborne Imaging Spectroscopy

    Page(s): 73 - 84
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (1108 KB) |  | HTML iconHTML  

    We identify canopy species in a Hawaiian tropical forest using supervised classification applied to airborne hyperspectral imagery acquired with the Carnegie Airborne Observatory-Alpha system. Nonparametric methods (linear and radial basis function support vector machine, artificial neural network, and k-nearest neighbor) and parametric methods (linear, quadratic, and regularized discriminant analysis) are compared for a range of species richness values and training sample sizes. We find a clear advantage in using regularized discriminant analysis, linear discriminant analysis, and support vector machines. No unique optimal classifier was found for all conditions tested, but we highlight the possibility of improving support vector machine classification with a better optimization of its free parameters. We also confirm that a combination of spectral and spatial information increases accuracy of species classification: we combine segmentation and species classification from regularized discriminant analysis to produce a map of the 17 discriminated species. Finally, we compare different methods to assess spectral separability and find a better ability of Bhattacharyya distance to assess separability within and among species. The results indicate that species mapping is tractable in tropical forests when using high-fidelity imaging spectroscopy. View full abstract»

    Open Access
  • Improvement of Stepped-Frequency Continuous Wave Ground-Penetrating Radar Cross-Range Resolution

    Page(s): 85 - 92
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (677 KB) |  | HTML iconHTML  

    This paper presents some experimental results obtained with newly developed stepped-frequency continuous wave (SFCW) ground-penetrating radar in a frequency range from 400 to 4845 MHz. This paper describes the procedures to remove the delays within the transmitter, the receiver, and the antenna system and analyzes the experimental results obtained after processing the measured data. The measured system footprint and the experimental results show that using an ultrawideband (UWB) Archimedean spiral antenna decreases the coupling signal but does not provide the needed cross-range resolution. Based on the measured dimensions of the footprint, a synthetic aperture procedure is used to improve the radar cross-range resolution from around 60 cm to about 6 cm. This paper shows the ability of the radar to detect dielectric objects and to exhibit their shape as it works with circularly polarized waves. What makes this paper different from prior work, which presents some experiments using a vector network analyzer set up to work as an SFCW radar, is that the data were acquired with a real system working with circular polarization and using two UWB Archimedean spirals. The calibration procedures as well as the synthetic aperture procedure were developed and validated based on measured data with the SFCW radar. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The First-Order Symplectic Euler Method for Simulation of GPR Wave Propagation in Pavement Structure

    Page(s): 93 - 98
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (646 KB) |  | HTML iconHTML  

    Construction of electromagnetic wave propagation model in layered pavement structure is a key problem for applying ground penetrating radar (GPR) to the road quality detection. A first-order explicit symplectic Euler method with Higdon absorbing boundary condition is presented to simulate GPR wave propagation in 2-D pavement structure. The incident wave is considered as line source and plane wave source, respectively. The total-field/scatter-field technique is used to simulate plane wave excitation. Numerical examples are provided to verify the accuracy and efficiency of the proposed algorithm. It can be observed that the symplectic Euler method achieves almost the same level of accuracy as the finite-difference time-domain scheme, while saving CPU time considerably. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An Approximate Hybrid Method for Electromagnetic Scattering From an Underground Target

    Page(s): 99 - 107
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (335 KB) |  | HTML iconHTML  

    A hybrid method for modeling marine controlled-source electromagnetics, simplified integral equation (IE) (SIE) modeling, has shown very promising results in 2-D. The computational gain of SIE is very large for large problems in 3-D. We assess the accuracy and range of validity of SIE modeling in 3-D through order-of-magnitude analysis and through an extensive numerical comparison with rigorous IE modeling. A previously proposed order-of-magnitude analysis results in a dimensionless parameter which is easy to use as an a priori indicator for when SIE is valid. Unfortunately, this parameter is found to be sometimes inconsistent with our numerical results. Order-of-magnitude analysis for Maxwell's equations is then reassessed in an attempt to rectify the shortcomings of the parameter adapted from the work “Electrical Impedance Tomography” by Cheney The dimensionless parameter resulting from the novel order-of-magnitude analysis is found to have generally good predictive capability. Unfortunately, this parameter is not suitable for deciding a priori if the use of SIE is justified for a particular case, since it depends on numerical results from IE modeling. For future use of SIE, it is therefore recommended to compare the problem characteristics of the case at hand with those covered by the extensive numerical comparison in this paper. From the numerical investigation, it is found that the accuracy of SIE is very good for resistive targets and for frequencies lower than about 10 Hz. For conductive targets, the accuracy is mostly very good for frequencies lower than about 5 Hz but somewhat more dependent also on other problem characteristics. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Partially Supervised Approach for Detection and Classification of Buried Radioactive Metal Targets Using Electromagnetic Induction Data

    Page(s): 108 - 121
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1515 KB)  

    The analysis of the data obtained from electromagnetic induction (EMI) sensors is one of the most viable tools for the detection of metallic objects buried under soil. The existing detection methods usually consist of sophisticated EM modeling of the source/target geometry to build suitable discriminators. The major technical challenge in this field is the reduction of false alarms with an increase of the detection probability. In this paper, we propose a partially supervised approach to detect buried radioactive targets, i.e., depleted uranium, without sophisticated EM modeling. Using the EMI data obtained by a GEM-3 sensor for a field survey, our proposed algorithm can successfully detect and discriminate the targets from nontarget metals, compared to other unsupervised and supervised approaches. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Measurement of Complex Permittivity of Cylindrical Objects in the E-Plane of a Rectangular Waveguide

    Page(s): 122 - 131
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (666 KB) |  | HTML iconHTML  

    Remote sensing of dielectric properties is used for numerous applications such as the field evaluation of soil water, salinity, or the organic matter content. The objective of this study is to measure dielectric properties of cylindrical shaped samples for the previously specified applications. The proposed method employs an analytical approach for determining the complex permittivity of cylindrical dielectric objects placed in the E-plane of a rectangular waveguide. The overall procedure is based on the measurement of reflection and transmission coefficients of the test specimen by placing it inside a section of rectangular waveguide. The reconstruction of dielectric properties of the test sample from the measured scattering coefficients is carried out using the newly proposed closed-form expressions, which are derived by transforming the actual circular cross section of the cylindrical sample into the equivalent multilayered rectangular cross sections. The dielectric properties of a number of specimens, including typical plastics and vegetation samples, are determined using the proposed approach. The typical error in the reconstruction of the dielectric constant of these samples having moderate permittivity values is found to be less than 5%. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automatic Detection of a Subsurface Wire Using an Electromagnetic Gradiometer

    Page(s): 132 - 139
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (795 KB) |  | HTML iconHTML  

    A model-based correlation detection scheme is presented with the aim of detecting and localizing subsurface tunnel infrastructure in an automated fashion. Our goal is to develop a comprehensive detection technology that can be fielded and successfully used by nonexperts, while simultaneously being sufficiently robust as to be effective. Our correlation detection algorithm relies on a library of model signals that are generated using an analytical model of a thin subsurface wire in a homogeneous half-space. The wire is illuminated using an active transmitter source (12, 20, or 200 kHz), and its response is sensed using a man-portable electromagnetic gradiometer (EMG) system. The performance of the detector is assessed using synthetic data and receiver operating characteristic (ROC) analysis as well as experimental data collected during a field test. Preliminary ROC results indicate that at sufficient signal-to-noise ratio, the detector can achieve detection probabilities greater than 0.9 with corresponding false alarm rates of less than one every 1000 m. Results from the field tests revealed that the responses from the EMG can be used to detect and localize (to within 0.5 m in the horizontal) a wire target down to a depth of at least 7 m. We believe the EMG system and correlation detector combine to form a promising technology for detecting tunnel infrastructure that can be used by experts and, more importantly, nonexperts as well. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A New Time Series Mining Approach Applied to Multitemporal Remote Sensing Imagery

    Page(s): 140 - 150
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1026 KB) |  | HTML iconHTML  

    In this paper, we present a novel unsupervised algorithm, called CLimate and rEmote sensing Association patteRns Miner, for mining association patterns on heterogeneous time series from climate and remote sensing data integrated in a remote sensing information system developed to improve the monitoring of sugar cane fields. The system, called RemoteAgri, consists of a large database of climate data and low-resolution remote sensing images, an image preprocessing module, a time series extraction module, and time series mining methods. The preprocessing module was projected to perform accurate geometric correction, what is a requirement particularly for land and agriculture applications of satellite images. The time series extraction is accomplished through a graphical interface that allows easy interaction and high flexibility to users. The time series mining method transforms series to symbolic representation in order to identify patterns in a multitemporal satellite images and associate them with patterns in other series within a temporal sliding window. The validation process was achieved with agroclimatic data and NOAA-AVHRR images of sugar cane fields. Results show a correlation between agroclimatic time series and vegetation index images. Rules generated by our new algorithm show the association patterns in different periods of time in each time series, pointing to a time delay between the occurrences of patterns in the series analyzed, corroborating what specialists usually forecast without having the burden of dealing with many data charts. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multitask Remote Sensing Data Classification

    Page(s): 151 - 161
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1152 KB) |  | HTML iconHTML  

    Many remote sensing data processing problems are inherently constituted by several tasks that can be solved either individually or jointly. For instance, each image in a multitemporal classification setting could be taken as an individual task. Here, the relation to previous acquisitions should be properly considered because of the nonstationary behavior of temporal, spatial, and angular image features which gives rise to distribution changes. This phenomenon is known as covariate shift. Additionally, when labeled data are scarce or expensive to obtain, the small sample-set problem arises, which makes solving the problems independently in each domain difficult. Multitask learning (MTL) aims at jointly solving a set of prediction problems by sharing information across tasks. This paper introduces MTL in remote sensing data classification. The proposed methods alleviate the data set shift by imposing cross-information in the classifiers through matrix regularization. We consider the support vector machine (SVM) as the core learner and two different regularization schemes: 1) the inclusion of relational operators between tasks and 2) the pairwise Euclidean distance of the predictors in the Hilbert space. These methods rely on simple and intuitive modifications of the kernel used in the standard SVM. Experiments are conducted in three challenging remote sensing problems: cloud screening from multispectral images, land-mine detection using radar data, and multitemporal and multisource image classification. The pairwise method consistently outperforms standard independent and aggregate approaches by about +2% to 4% in all problems at no additional cost. Also, the solutions found give us information about the distribution shift among tasks. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Crop Yield Estimation Based on Unsupervised Linear Unmixing of Multidate Hyperspectral Imagery

    Page(s): 162 - 173
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1508 KB) |  | HTML iconHTML  

    Hyperspectral imagery, which contains hundreds of spectral bands, has the potential to better describe the biological and chemical attributes on the plants than multispectral imagery and has been evaluated in this paper for the purpose of crop yield estimation. The spectrum of each pixel in a hyperspectral image is considered as a linear combinations of the spectra of the vegetation and the bare soil. Recently developed linear unmixing approaches are evaluated in this paper, which automatically extracts the spectra of the vegetation and bare soil from the images. The vegetation abundances are then computed based on the extracted spectra. In order to reduce the influences of this uncertainty and obtain a robust estimation results, the vegetation abundances extracted on two different dates on the same fields are then combined. The experiments are carried on the multidate hyperspectral images taken from two grain sorghum fields. The results show that the correlation coefficients between the vegetation abundances obtained by unsupervised linear unmixing approaches are as good as the results obtained by supervised methods, where the spectra of the vegetation and bare soil are measured in the laboratory. In addition, the combination of vegetation abundances extracted on different dates can improve the correlations (from 0.6 to 0.7). View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Spatial Contextual Postclassification Method for Preserving Linear Objects in Multispectral Imagery

    Page(s): 174 - 183
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2075 KB) |  | HTML iconHTML  

    Classification of remote sensing multispectral data is important for segmenting images and thematic mapping and is generally the first step in feature extraction. Per-pixel classification, based on spectral information alone, generally produces noisy classification results. The introduction of spatial information has been shown to be beneficial in removing most of this noise. Probabilistic label relaxation (PLR) has proved to be advantageous using second-order statistics; here, we present a modified contextual probabilistic relaxation method based on imposing directional information in the joint probability with third-order statistics. The proposed method was tested in synthetic images and real images; the results are compared with a “Majority” algorithm and the classical PLR method. The proposed third-order method gives the best results, both visually and numerically. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Semisupervised Local Discriminant Analysis for Feature Extraction in Hyperspectral Images

    Page(s): 184 - 198
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (3298 KB)  

    We propose a novel semisupervised local discriminant analysis method for feature extraction in hyperspectral remote sensing imagery, with improved performance in both ill-posed and poor-posed conditions. The proposed method combines unsupervised methods (local linear feature extraction methods and supervised method (linear discriminant analysis) in a novel framework without any free parameters. The underlying idea is to design an optimal projection matrix, which preserves the local neighborhood information inferred from unlabeled samples, while simultaneously maximizing the class discrimination of the data inferred from the labeled samples. Experimental results on four real hyperspectral images demonstrate that the proposed method compares favorably with conventional feature extraction methods. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multi-Spectro-Temporal Analysis of Hyperspectral Imagery Based on 3-D Spectral Modeling and Multilinear Algebra

    Page(s): 199 - 216
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1483 KB)  

    Multitemporal hyperspectral images are gaining an ever-increasing importance revealed by the ambition of the remote sensing community to develop new generation of sensors. Therefore, multitemporal images classification and change detection issues are greatly relevant in several research topics. In this paper, we propose a novel approach for modeling the temporal variation of the reflectance response as a function of time period and wavelength; summarizing the spectral signature of hyperspectral pixels as a 3-D mesh. This approach is adopted for hyperspectral time series analysis leading to the main following contribution: an advanced form of the temporal spectral signature defining the reflectance at each pixel as a congregation of the spatial/spectral/temporal dimensions. Afterward, by formulating the temporal data set in an adequate multidimensional feature space of contextual data, an innovative processing scheme exploiting the theoretical backgrounds of 3-D surface reconstruction and matching is adopted for data interpretation. Finally, an improved method for multitemporal endmember extraction and spectral unmixing based on multilinear algebra methods is introduced. A case study, in a region located in southern Tunisia, is conducted on a multitemporal subset of Hyperion images. Up to 89.86% of sampling sites have been correctly predicted by the proposed approach, outperforming conventional classifiers. The good performances obtained, on simulated multitemporal images and over various real experimental scenarios, illustrate the effectiveness and the generalization capacities of the proposed approach. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hyperspectral Image Classification via Kernel Sparse Representation

    Page(s): 217 - 231
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (3087 KB) |  | HTML iconHTML  

    In this paper, a novel nonlinear technique for hyperspectral image (HSI) classification is proposed. Our approach relies on sparsely representing a test sample in terms of all of the training samples in a feature space induced by a kernel function. For each test pixel in the feature space, a sparse representation vector is obtained by decomposing the test pixel over a training dictionary, also in the same feature space, by using a kernel-based greedy pursuit algorithm. The recovered sparse representation vector is then used directly to determine the class label of the test pixel. Projecting the samples into a high-dimensional feature space and kernelizing the sparse representation improve the data separability between different classes, providing a higher classification accuracy compared to the more conventional linear sparsity-based classification algorithms. Moreover, the spatial coherency across neighboring pixels is also incorporated through a kernelized joint sparsity model, where all of the pixels within a small neighborhood are jointly represented in the feature space by selecting a few common training samples. Kernel greedy optimization algorithms are suggested in this paper to solve the kernel versions of the single-pixel and multi-pixel joint sparsity-based recovery problems. Experimental results on several HSIs show that the proposed technique outperforms the linear sparsity-based classification technique, as well as the classical support vector machines and sparse kernel logistic regression classifiers. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.

Aims & Scope

 

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (TGRS) is a monthly publication that focuses on the theory, concepts, and techniques of science and engineering as applied to sensing the land, oceans, atmosphere, and space; and the processing, interpretation, and dissemination of this information.

 

Full Aims & Scope

Meet Our Editors

Editor-in-Chief
Antonio J. Plaza
University of Extremadura