By Topic

Geoscience and Remote Sensing Letters, IEEE

Issue 4 • Date July 2013

Filter Results

Displaying Results 1 - 25 of 72
  • Front cover

    Page(s): C1
    Save to Project icon | Request Permissions | PDF file iconPDF (375 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): 645 - 968
    Save to Project icon | Request Permissions | PDF file iconPDF (136 KB)  
    Freely Available from IEEE
  • Initial Validation of SMOS Vegetation Optical Thickness in Iowa

    Page(s): 647 - 651
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (376 KB) |  | HTML iconHTML  

    The European Space Agency's Soil Moisture and Ocean Salinity (SMOS) satellite mission provides microwave L-band measurements of vegetation optical thickness over the Earth. Optical thickness is related to water held in vegetation. The water content of crops varies over the growing season from a minimum during planting to a maximum during reproduction and back to a minimum during senescence. We found that in Iowa in 2010 the change in SMOS optical thickness over the growing season can be related to crop yields. However, there are inconsistencies in the optical thickness data, particularly high-frequency variation and unexpected changes outside of the growing season. We hypothesize that the unexpected changes during the dormant periods are due to changes in soil surface roughness caused by land management activities and show a relationship between changes in roughness and changes in optical thickness, which may be confusing the SMOS retrieval algorithm. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automatic Annotation of Satellite Images via Multifeature Joint Sparse Coding With Spatial Relation Constraint

    Page(s): 652 - 656
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1071 KB) |  | HTML iconHTML  

    In this letter, we propose a novel framework for large-satellite-image annotation using multifeature joint sparse coding (MFJSC) with spatial relation constraint. The MFJSC model imposes an l1, 2-mixed-norm regularization on encoded coefficients of features. The regularization will encourage the coefficients to share a common sparsity pattern, which will preserve the cross-feature information and eliminate the constraint that they must have identical coefficients. Spatial dependences between patches of large images are useful for the annotation task but are usually ignored or insufficiently exploited in other methods. In this letter, we design a spatial-relation-constrained classifier to utilize the output of MFJSC and the spatial dependences to annotate images more precisely. Experiments on a data set of 21 land-use classes and QuickBird images show the discriminative power of MFJSC and the effectiveness of our annotation framework. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Registration of Optical and SAR Satellite Images by Exploring the Spatial Relationship of the Improved SIFT

    Page(s): 657 - 661
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (753 KB) |  | HTML iconHTML  

    Although feature-based methods have been successfully developed in the past decades for the registration of optical images, the registration of optical and synthetic aperture radar (SAR) images is still a challenging problem in remote sensing. In this letter, an improved version of the scale-invariant feature transform is first proposed to obtain initial matching features from optical and SAR images. Then, the initial matching features are refined by exploring their spatial relationship. The refined feature matches are finally used for estimating registration parameters. Experimental results have shown the effectiveness of the proposed method. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • FFT-Accelerated Analysis of Scattering From Complex Dielectrics Embedded in Uniaxial Layered Media

    Page(s): 662 - 666
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (434 KB) |  | HTML iconHTML  

    An efficient integral-equation method is presented for the analysis of electromagnetic scattering from arbitrarily shaped 3-D dielectric objects embedded in a single layer of a uniaxial planar-layered medium. The proposed method employs a mixed-potential volume electric-field integral equation (VEFIE) that permits the object of interest to be dispersive, anisotropic, inhomogeneous, and of arbitrary shape. The VEFIE is solved by an iterative frequency-domain method-of-moments procedure. The object is discretized by tetrahedral elements, and the procedure is accelerated by the adaptive integral method, which reduces the computational costs by enclosing the tetrahedral mesh with an auxiliary regular grid and performing anterpolation (mesh to grid), propagation (grid to grid), interpolation (grid to mesh), and near-zone correction (mesh to mesh) steps. The computationally dominant propagation step of the method is accelerated by decomposing the Green's functions into convolution and correlation terms in the stratification direction and using 3-D fast Fourier transforms to multiply the resulting propagation matrices with the necessary vectors. If the object of interest is meshed using N tetrahedra that are of a single length scale, then the setup time, memory requirement, and the iterative matrix-solution time (per iteration) of the proposed method scale as O(N), O(N), and O(NlogN), respectively. Numerical results validate the method's accuracy and efficiency for various problems relevant to geophysical exploration. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Side-Lobe Cancelation in DInSAR Pixel Selection With SVA

    Page(s): 667 - 671
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (489 KB) |  | HTML iconHTML  

    Synthetic aperture radar (SAR) systems are inherently band limited in both range and azimuth, and hence, the point spread function (PSF) has the shape of a bidimensional sinc function. In addition, all SAR images are slightly oversampled, and as a consequence, the contribution of a single target extends to more than a single cell. The main lobe and the side lobes of strong scatterers are sometimes clearly visible in the images. This characteristic of the SAR images must be considered when applying differential interferometric synthetic aperture radar (DInSAR) pixel selection algorithms. For persistent scatterers, the properties, for instance, the amplitude stability, are preserved in both redundant information around the main lobe and side lobes. For this reason, a cluster of pixels rather than just the pixel position corresponding to the exact location of the target will be detected. Spatially variant apodization (SVA) is a nonlinear filter based on cosine-on-pedestal weighting functions able to achieve a total side-lobe cancelation without degrading the original image resolution. When working with complex data under complex scattering scenarios, the PSF moves away from the ideal bidimensional sinc, and the SVA performance worsens. The amplitude and phase of the original images could be distorted by the SVA filtering compromising the pixel selection and the quality of the final DInSAR results. In this letter, SVA is used to method locate in the image the side lobes of high-power scatterers and generate a mask while preserving the amplitude and phase of the original images. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multimodal Remote Sensing Data Fusion via Coherent Point Set Analysis

    Page(s): 672 - 676
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (643 KB) |  | HTML iconHTML  

    We present a novel fusion algorithm for electronic-reconnaissance (ER) satellite and optical imaging satellite data using coherent point set (CPS) analysis. This work is motivated by a large-scale maritime surveillance problem, where ship groups in the observations are of particular interest for tactical and strategic operations. Fusion of observations from ER satellite and optical imaging satellite is a challenging task. On the one hand, dense and continuous measurement is not available for optical imagery. On the other hand, it is difficult to extract robust features from ER measurements. Considering that the size of a ship is often less than the distance among different ships, we treat each ship as a mass point. The contributions of our work are threefold. First, multisensor data fusion is accomplished by CPS association. To the best of our knowledge, this letter is the first to investigate CPS for multimodal remote sensing data fusion. Second, a novel geometry descriptor, which encodes the topological characteristics of a point set, is presented. Third, we combine both topological features and attributive features within the framework of Dempster-Shafer theory for CPS analysis. The proposed method has been tested using different sets of simulated data and recorded data. Experimental results demonstrate the effectiveness of the proposed method. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Bridge Thermal Dilation Monitoring With Millimeter Sensitivity via Multidimensional SAR Imaging

    Page(s): 677 - 681
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1239 KB) |  | HTML iconHTML  

    The new generation of synthetic aperture radar (SAR) sensors is providing images with very high spatial resolution, improved up to the meter scale. Such a resolution increase allows more accurate monitoring capabilities by means of interferometric approaches. The use of higher frequency enhances the sensitivity of the system even to minute changes, such as thermal dilations. This phenomenon has an impact on the interferometric products, particularly on the deformation velocity maps, if not properly handled. Man-made structures, such as steel core bridges and specific buildings, may be very sensible to thermal dilation effects. By extending the multitemporal differential interferometry SAR processing chains, in our case based on the multidimensional imaging (MDI) approach, an additional parameter related to temperature differences at acquisition instants, the thermal coefficient, can be accurately estimated. This parameter provides interesting perspectives in application to infrastructure monitoring: It brings information about the thermal behavior of the imaged objects. In this letter, we investigate the thermal response of the Musmeci bridge (Potenza, Italy), by experimenting the extended MDI approach on a real TerraSAR-X data set. Results highlight the possibility of such a technique to obtain measurements of the motion that is highly correlated with temperature, thus providing useful information about the static structure of bridges. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Wavelet Packet Analysis and Gray Model for Feature Extraction of Hyperspectral Data

    Page(s): 682 - 686
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (586 KB) |  | HTML iconHTML  

    Wavelet packet analysis (WPA) and gray model (GM) are investigated for nonlinear unsupervised feature extraction of hyperspectral remote sensing data in this letter. Treated as derivative series, a hyperspectral response curve of each pixel is decomposed into an approximation and various detailed compositions by WPA, and then, GM is continuously applied to find the relationship among those detailed compositions. Cluster-space representation is used for determining the optimal wavelet. New extracted features can reveal the intrinsic identities of hyperspectral data. Experimental results show the feasibility and reliability of our proposed method in terms of classification accuracy. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Two-Stage Fuzzy Fusion With Applications to Through-the-Wall Radar Imaging

    Page(s): 687 - 691
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (531 KB) |  | HTML iconHTML  

    A two-stage fuzzy image fusion approach, which combines multiple radar images of the same scene, is proposed to produce a more informative image. In this approach, two different image fusion methods are first applied. Then, a fuzzy logic fusion method is applied to the outputs of the first fusion stage. The performance of the proposed approach is evaluated on through-the-wall radar images obtained using different polarizations. Experimental results show that the proposed approach enhances image quality by producing outputs with high target intensity values and low clutter. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Azimuth Overlapped Subaperture Algorithm in Frequency Domain for Highly Squinted Synthetic Aperture Radar

    Page(s): 692 - 696
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (673 KB) |  | HTML iconHTML  

    The high-resolution imaging of a highly squinted synthetic aperture radar remains difficult because of the severe coupling between the range and the azimuth. “Squint minimization” compensates for the range walking in the azimuth time domain, which efficiently increases the orthogonality between the range and the azimuth. However, this “squint minimization” introduces the azimuth space-variant phases, which can be compensated by the azimuth nonlinear chirp-scaling (ANCS) algorithm using large computational loads. In this letter, an azimuth overlapped subaperture algorithm (AOSA) is proposed to compensate for these phases in the Doppler frequency domain. The validity constraint of this algorithm is then analyzed. The AOSA has an advantage over ANCS in terms of the computational load and is considerably more suitable for real-time processing. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Unsupervised Change Detection on SAR Images Using Triplet Markov Field Model

    Page(s): 697 - 701
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (711 KB) |  | HTML iconHTML  

    The triplet Markov field (TMF) model is powerful in the nonstationary synthetic aperture radar (SAR) image analysis. Taking the speckle noise and the correlation of nonstationarities in two multitemporal SAR images into account, we propose a change-detection method based on the TMF model in this letter. The third field U in the TMF model is redefined to describe the nonstationary textural similarity between the two images for change detection. The corresponding prior energy of (X, U) is reconstructed. The adaptive weight parameter in prior energy is introduced to cope with the detection tradeoff issue. An automatic estimation of the parameter is obtained with low level of complexity. The Bayesian maximum posterior marginal criterion is utilized with the TMF model to obtain change detection. Experimental results on real SAR images validate the superiority of the proposed TMF method over the Markov random field method. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Linear Feature Extraction for Hyperspectral Images Based on Information Theoretic Learning

    Page(s): 702 - 706
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (396 KB) |  | HTML iconHTML  

    This letter proposes a new supervised linear feature extractor for hyperspectral image classification. The criterion for feature extraction is a modified maximal relevance and minimal redundancy (MRMD), which has been used for feature selection until now. The MRMD is a function of mutual information terms, which possess higher order statistics of data; thus, it is effective for hyperspectral data with informative higher order statistics. The batch and stochastic versions of the gradient ascent are performed on the MRMD to find the optimal parameters of a linear feature extractor. Preliminary results achieve better classification performance than the traditional methods based on the first- and second-order moments of data. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Using MODIS NDVI Time Series to Identify Geographic Patterns of Landslides in Vegetated Regions

    Page(s): 707 - 710
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (716 KB) |  | HTML iconHTML  

    The 2008 Wenchuan Earthquake that occurred in a mountainous region of China induced massive landslides and caused numerous casualties and property losses. Analyzing the disturbances on vegetation detected from the abnormal sudden drops of the normalized difference vegetation index (NDVI) within a short period can be used for the purpose of rapid landslide identification. Although much research has confirmed the necessity of high-resolution satellite images in landslides identification, Moderate Resolution Imaging Spectroradiometry (MODIS) products still have their usefulness for high temporal resolution, as investigated by the authors. Using MODIS MOD09Q1 NDVI products at a temporal interval of 8 days during 2008, this letter presents a method that has been developed to identify landslide distribution and evolution patterns. First, to find the optimal threshold, the MODIS NDVI time series are analyzed in a training area by an iteration searching procedure. Second, the chosen threshold is used in a larger validation area. To examine the effectiveness of the proposed method, the results are compared to interpreted landslides using SPOT5 images with a spatial resolution of 2.5 m acquired before and after the main shock. An overall 75% accuracy is achieved, and better consistency is observed for landslides extending over one MODIS pixel. The proposed method has also been applied to the Wenchuan earthquake affected areas with seismic intensity IX and greater, and the similar spatial pattern of landslides distribution is obtained when compared with results by using high-resolution images and field investigation. This technique can be applied practically for rapid landslide assessment at a relatively large region after a major earthquake or other severe disturbance events. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Selection of Landmark Points on Nonlinear Manifolds for Spectral Unmixing Using Local Homogeneity

    Page(s): 711 - 715
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (547 KB) |  | HTML iconHTML  

    Endmember extraction and unmixing methods that exploit nonlinearity in hyperspectral data are receiving increased attention, but they have significant challenges. Global feature extraction methods such as isometric feature mapping have significant computational overhead, which is often addressed for the classification problem via landmark-based methods. Because landmark approaches are approximation methods, experimental results are often highly variable. We propose a new robust landmark selection method for the purpose of pixel unmixing that exploits spectral and spatial homogeneity in a local window kernel. We compare the performance of the method to several landmark selection methods in terms of reconstruction error and processing time. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Seasonal Snow Cover Mapping in Alpine Areas Through Time Series of COSMO-SkyMed Images

    Page(s): 716 - 720
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (289 KB) |  | HTML iconHTML  

    A time series of COSMO-SkyMed (CSK) images is exploited for detection of seasonal snow cover in alpine areas. For the first time, a complete time series of CSK images acquired during snow fall and melt periods in winter 2010-2011 is addressed to verify the snow cover mapping capabilities of X-band radar images under different conditions (from dry to wet snow). The algorithm for snow detection is based on a multitemporal approach with the concept that free water in the snowpack attenuates the X-band synthetic aperture radar signal and wet snow can be classified by comparing images acquired under wet snow and snow-free conditions. Thresholds to make this distinction are compared across all the images to check sensitivity to different winter conditions and land-use classes. The impact of variable and fixed thresholds on the retrieved snow-covered areas is assessed. Snow maps from CSK images compared with Landsat Enhanced Thematic Mapper Plus snow maps indicate a constant underestimation in the detection of snow extent, particularly during winter season, thus showing a scarce sensitivity of X-band signals to snow in dry conditions. Probability of error maps are also calculated for each CSK snow map, thus providing information on the classification error associated to each pixel labeled as snow. The analysis of the snow line variation during spring determines good time consistency in the determination of snow maps from CSK images. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • RFI Mitigation Using Two-Scale Estimators for Statistical Variance

    Page(s): 721 - 725
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (311 KB) |  | HTML iconHTML  

    The well-known sample variance estimator utilizes N samples from a random process to first estimate the process mean. The estimator then uses the same N samples to estimate variance from this mean. Process variance could also be estimated by first using less than N samples to estimate the mean, followed by using all N samples to estimate variance. Two-scale estimators of this type, both causal and noncausal, are defined. Statistics for these estimators are derived, which are valid for samples from any statistical distribution. These statistics are used to improve analysis of a previously reported device called the double detector. In microwave radiometry, the double detector senses the presence of deterministic signals, often called radio-frequency interference, that corrupt the usual measurement consisting only of Planck radiation. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Airborne Dual-Polarization Observations of the Sea Surface NRCS at C-Band in High Winds

    Page(s): 726 - 730
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1108 KB) |  | HTML iconHTML  

    Airborne dual-polarization observations of sea surface normalized radar cross section (NRCS) were conducted over the North Atlantic during January-February 2011. Observations were made using the University of Massachusetts' Imaging Wind and Rain Airborne Profiler radar system installed on the National Oceanic and Atmospheric Administration's WP-3D research aircraft during several winter storm events to determine the high-wind response of the sea surface NRCS for both horizontal and vertical polarizations. During the flights, the aircraft performed several constant-roll circle maneuvers to allow collection of NRCS over a range of incidence angles. We find consistency with prior reports in the polarization ratio observed at moderate incidence angles at the winds encountered. For larger incidence angles, we observe a measurable decrease in polarization ratio with increasing wind speed. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Sensitivity of Main Polarimetric Parameters of Multifrequency Polarimetric SAR Data to Soil Moisture and Surface Roughness Over Bare Agricultural Soils

    Page(s): 731 - 735
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (471 KB) |  | HTML iconHTML  

    The potential of polarimetric synthetic aperture radar data for the soil surface characterization of bare agricultural soils was investigated by using air- and spaceborne data acquired by Radar Aéroporté Multi-Spectral d'Etude des Signatures (RAMSES), Système Expérimental de Télédétection Hyperfréquence Imageur (SETHI), and RADARSAT-2 sensors over several study sites in France. Fully polarimetric data at ultrahigh frequency, X-, C-, L-, and P-bands were compared. The results show that the main polarimetric parameters studied (entropy, α angle, and anisotropy) are not very sensitive to the variation of the soil surface parameters. Low correlations are observed between the polarimetric and soil parameters (moisture content and surface roughness). Thus, the polarimetric parameters are not very relevant to the characterization of the soil surface over bare agricultural areas. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Interactive Domain Adaptation for the Classification of Remote Sensing Images Using Active Learning

    Page(s): 736 - 740
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (582 KB) |  | HTML iconHTML  

    This letter presents a novel interactive domain-adaptation technique based on active learning for the classification of remote sensing (RS) images. The proposed method aims at adapting the supervised classifier trained on a given RS source image to make it suitable for classifying a different but related target image. The two images can be acquired in different locations and/or at different times. The proposed approach iteratively selects the most informative samples of the target image to be labeled by the user and included in the training set, whereas the source image samples are reweighted or possibly removed from the training set on the basis of their disagreement with the target image classification problem. This way, the consistent information available from the source image can be effectively exploited for the classification of the target image and for guiding the selection of new samples to be labeled, whereas the inconsistent information is automatically detected and removed. This approach can significantly reduce the number of new labeled samples to be collected from the target image. Experimental results on both a multispectral very high resolution and a hyperspectral data set confirm the effectiveness of the proposed method. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An Improved SAC Algorithm Based on the Range-Keystone Transform for Doppler Rate Estimation

    Page(s): 741 - 745
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (614 KB) |  | HTML iconHTML  

    Doppler rate is an important parameter in synthetic aperture radar (SAR) signal processing since it affects the SAR image focusing. There are many approaches to estimate the Doppler rate from SAR data; however, some approaches are not appropriate for spotlight SAR, which is focused with the two-step algorithm, since, after azimuth preprocessing, the signal is aliased in the azimuth time domain. Although the shift-and-correlation (SAC) algorithm may be suitable for such signals, it is proposed for the stripmap imaging mode; and when it is used to estimate the Doppler rate for spotlight SAR, some problems, such as the high computational load from zero padding and the constraint of the focus depth, may occur. In this letter, an improved Doppler rate estimation approach, which is called the Keystone-SAC algorithm, is proposed. An iterative scheme is presented to estimate the ambiguity number, and a special case when the ambiguity number splits into two numbers is analyzed. The real spotlight SAR data processing results are used to validate the effectiveness of the proposed algorithm. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • LiDAR Point Cloud Registration by Image Detection Technique

    Page(s): 746 - 750
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (361 KB) |  | HTML iconHTML  

    In this letter, a novel approach that utilizes the spectrum information (i.e., images) provided in a modern light detection and ranging (LiDAR) sensor is proposed for the registration of multistation LiDAR data sets. First, the conjugate points in the images collected at varied LiDAR stations are extracted through the speedup robust feature technique. Then, by applying the image-object space mapping technique, the 3-D coordinates of the conjugate image points can be obtained. Those identified 3-D conjugate points are then fed into a registration model so that the transformation parameters can be immediately solved using the efficient noniterative solution to linear transformations technique. Based on numerical results from a case study, it has been demonstrated that, by implementing the proposed approach, a fully automatic and reliable registration of multistation LiDAR point clouds can be achieved without the need for any human intervention. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Development and Demonstration of an Artificial Immune Algorithm for Mangrove Mapping Using Landsat TM

    Page(s): 751 - 755
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (536 KB) |  | HTML iconHTML  

    Mangroves are valuable contributors to coastal ecosystems; knowledge of the dynamics of mangrove ecosystems is important in the context of global change. To obtain this knowledge, remote sensing is an indispensable means, yet it poses challenges since the accuracy is sometimes unsatisfactory in distinguishing mangroves from other land cover types with traditional classification methods. In this letter, we proposed a modified artificial immune algorithm (AIA), in which the antibodies represent the candidate solutions and the antigens are expressed by the fitness function. Multiclass coevolution was combined with the concept of clonal selection to ensure computation of an optimal clustering center in parallel for each land cover type. A cluster-center-oriented decimal encoding method for antibodies was adopted, and the inner class variance and the between-class difference together were used to formulate the fitness function. Furthermore, a design of the antibody solubility-based selection operator and nonuniform mutation operator was undertaken. Applying this modified AIA to a Landsat Thematic Mapper multispectral remote sensing imagery in the Zhangjiang estuary in southeastern China, we found that the AIA substantially improved classification accuracy over traditional methods, showing an overall accuracy of 90% (kappa coefficient = 0.88) and was capable to discern mangrove well (commission of 10% and omission of 22%). View full abstract»

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

Aims & Scope

IEEE Geoscience and Remote Sensing Letters (GRSL) is a monthly publication for short papers (maximum length 5 pages) addressing new ideas and formative concepts in remote sensing as well as important new and timely results and concepts.

 

Full Aims & Scope

Meet Our Editors

Editor-in-Chief
Alejandro C. Frery
Universidade Federal de Alagoas