for Journals by Title or ISSN
for Articles by Keywords
help
Followed Journals
Journal you Follow: 0
 
Sign Up to follow journals, search in your chosen journals and, optionally, receive Email Alerts when new issues of your Followed Journals are published.
Already have an account? Sign In to see the journals you follow.
Journal Cover IEEE Geoscience and Remote Sensing Letters
  [SJR: 1.203]   [H-I: 60]   [145 followers]  Follow
    
   Hybrid Journal Hybrid journal (It can contain Open Access articles)
   ISSN (Print) 1545-598X
   Published by IEEE Homepage  [191 journals]
  • [Front cover]
    • Abstract: Presents the cover/table of contents for this issue of the periodical.
      PubDate: April 2018
      Issue No: Vol. 15, No. 4 (2018)
       
  • IEEE Geoscience and Remote Sensing Letters publication information
    • Abstract: Provides a listing of current staff, committee members and society officers.
      PubDate: April 2018
      Issue No: Vol. 15, No. 4 (2018)
       
  • IEEE Geoscience and Remote Sensing Letters information for authors
    • Abstract: Provides instructions and guidelines to prospective authors who wish to submit manuscripts.
      PubDate: April 2018
      Issue No: Vol. 15, No. 4 (2018)
       
  • IEEE Geoscience and Remote Sensing Letters Institutional Listings
    • Abstract: Advertisements.
      PubDate: April 2018
      Issue No: Vol. 15, No. 4 (2018)
       
  • Unusual Premonsoon Eddy and Kelvin Wave Activities in the Bay of Bengal
           During Indian Summer Monsoon Deficit in June 2009 and 2012
    • Authors: Subhra Prakash Dey;Mihir K. Dash;Pranab Deb;Dhrubajyoti Samanta;Rashmi Sharma;Rakesh Mohan Gairola;Raj Kumar;Prem Chand Pandey;
      Pages: 483 - 487
      Abstract: An investigation of the eddy and coastal Kelvin wave activities in the Bay of Bengal (BoB) is carried out during premonsoon season in two years of Indian summer monsoon deficit in June (2009 and 2012), occurred in the recent warming hiatus period. Using altimeter observations, our study reveals that over the northern BoB cyclonic eddy kinetic energy is reduced by 35% and 50% from the climatology during premonsoon seasons in 2009 and 2012, respectively, while the cyclonic eddy area is reduced by 18% and 24%, respectively. A concurrent reduction is observed in the first upwelling Kelvin wave (uKW) activities in the eastern equatorial Indian Ocean as well as in the coastal BoB for these years. The reduction in the generation of the first uKW in the eastern equatorial Indian Ocean is attributed to the westerly wind anomalies in January-March of these years. Additionally, meridional wind stress anomalies during March-April in these years are found to be southerly, causing anomalous coastal downwelling in the eastern rim of BoB. This coastal downwelling blocks the propagation of the first uKW. The decrease in the first uKW activities in the coastal waveguide of the BoB reduces the radiation of upwelling Rossby waves, thereby decreasing the cyclonic eddy activities in the northern BoB. The results from this letter could be helpful for further understanding of upper ocean mixing processes in the BoB during monsoon deficit years.
      PubDate: April 2018
      Issue No: Vol. 15, No. 4 (2018)
       
  • Seasonal Impact of Adjacency Effects on Ocean Color Radiometry at the AAOT
           Validation Site
    • Authors: Barbara Bulgarelli;Giuseppe Zibordi;
      Pages: 488 - 492
      Abstract: The seasonal impact of adjacency effects (AE) on satellite ocean color data at visible and near-infrared (NIR) wavelengths by the Sea-Viewing Wide Field-of-View Sensor, the Moderate Resolution Imaging Spectroradiometer onboard the Aqua platform (MODISA), the Medium Resolution Imaging Spectrometer, the Ocean and Land Color Instrument, the Operational Land Imager (OLI), and the MultiSpectral Imagery (MSI) was theoretically evaluated at a validation site in the northern Adriatic Sea. The analysis made use of comprehensive simulations accounting for multiple scattering, sea surface roughness, sensor viewing geometry, actual coastline, typical and extreme atmospheric conditions, and the seasonal variability of solar illumination and, land and water optical properties. Results, obtained by relying on the normalization of the radiometric sensitivity of each sensor to the same input radiance, show that the spectral and seasonal impacts of AE considerably vary among sensors. AE significantly exceed the radiometric sensitivity of MSI at its sole blue band in winter, whereas they significantly outdo the noise threshold of OLI and MODISA high-resolution data exclusively in the NIR in summer. Conversely, for all other sensors and for MODISA low-resolution data, AE are particularly significant at NIR bands between March and October and at the blue-green bands in winter.
      PubDate: April 2018
      Issue No: Vol. 15, No. 4 (2018)
       
  • A Bi-Iterative Model for Electromagnetic Scattering From a PEC Object
           Partially Buried in Rough Sea Surface
    • Authors: Juan Li;Ke Li;Li-Xin Guo;Ze-Lin Ren;
      Pages: 493 - 497
      Abstract: A bi-iterative physical optics (PO) method is presented in this letter to investigate the composite scattering from a perfectly electric conducting object partially buried in the dielectric rough sea surface. In the present method, both the scatterings of a partially buried object and the underlying sea surface are calculated by the PO method. And a bi-iterative strategy is considered, including the mutual interaction among points on the object in direct scattering and the mutual interaction between the object and the sea surface in coupling scattering. In addition, the coupling interaction between the partially buried object and the sea surface contains two parts: 1) the upper surface of the sea surface and the upper part of the object and 2) the lower surface of sea surface and the lower part of the object. In numerical simulations, the bistatic normalized radar cross sections of the composite model are computed by the bi-iterative PO method and are compared with those by the conventional method of moments for different object types and polarizations. The results show that the proposed method has a good accuracy and can greatly reduce the computational time and memory requirement.
      PubDate: April 2018
      Issue No: Vol. 15, No. 4 (2018)
       
  • Correction of Forcing-Related Spatial Artifacts in a Land Surface Model by
           Satellite Soil Moisture Data Assimilation
    • Authors: Clay B. Blankenship;Jonathan L. Case;William L. Crosson;Bradley T. Zavodsky;
      Pages: 498 - 502
      Abstract: Retrieved soil moisture estimates from the National Aeronautics and Space Administration (NASA) Soil Moisture Active Passive (SMAP) radiometer are assimilated into the Noah land surface model (LSM) within the NASA Land Information System. The experimental testbed is based on a real-time LSM system produced by the NASA Short-Term Prediction Research and Transition Center. A nonlocalized cumulative distribution function-matching bias correction (BC) is applied to the SMAP retrievals, with separate correction curves calculated based on soil texture categories. We show that the assimilation of SMAP soil moisture retrievals with nonlocalized BC can mitigate two types of artifacts due to spatially varying errors in the forcing data from: 1) bad point (rain gauge) data and 2) strong gradients along the eastern U.S.-Canada border, resulting from blending different observing systems.
      PubDate: April 2018
      Issue No: Vol. 15, No. 4 (2018)
       
  • Frequency Domain Inverse Profiling of Buried Dielectric
           Elliptical-Cylindrical Objects Using Evolutionary Programming
    • Authors: Maryam Hajebi;Ahad Tavakoli;Ahmad Hoorfar;
      Pages: 503 - 507
      Abstract: An efficient method based on the evolutionary programming (EP) technique is proposed for inverse profiling of 2-D buried dielectric objects with elliptical cross sections. In particular, EP with Cauchy mutation operator (EP-CMO), as its first reported implementation to inverse problems, is utilized as a stochastic optimization tool for quantitatively reconstructing buried objects. Moreover, the method of moments technique in conjunction with conjugate gradient-fast Fourier transform method is used, as a fast and simple frequency domain forward solver, in each iteration of the proposed method. Numerical results for different case studies are presented and analyzed. To assess the proposed EP-CMO method, the results are also compared statistically with that of three other well-known optimization techniques, namely, EP with Gaussian mutation, particle swarm optimization, and genetic algorithms. The results reveal that EP-CMO is a significantly more robust and efficient optimization tool in reconstruction of this class of buried objects.
      PubDate: April 2018
      Issue No: Vol. 15, No. 4 (2018)
       
  • Doppler Profile Tracing Using MPCF on MU Radar and Sodar: Performance
           Analysis
    • Authors: Swati Sinha;Mary Lourde Regeena;T. V. Chandrasekhar Sarma;Hiroyuki Hashiguchi;Kushal R. Tuckley;
      Pages: 508 - 511
      Abstract: Wind profilers (WPs) are ground-based pulsed Doppler radars operating in the UHF/very high frequency (VHF) bands. They use backscatter from clear-air turbulence as a tracer of background wind in the troposphere and up to mesosphere. Wind profiling systems range from large research radar systems to smaller operational units. In recent times, multiparameter cost function (MPCF) has emerged as a computationally efficient Doppler profile estimation method. It has been claimed that the MPCF method can be easily migrated to any vertically sounding clear-air wind profiling system that works in Doppler beam swinging mode. In order to investigate this claim, MPCF was applied to the following wind profiling systems: the middle and upper atmosphere (MU) radar, located at Shigaraki, Japan, which is an active phased array VHF radar system with 475 transceivers, and Doppler sodar, located at Pune, India, which uses acoustic frequency to obtain echoes in the planetary boundary layer. Both these systems are complementary in the sense that they cover ranges from ground to about 80 km. During the experimentation, the MPCF algorithm did not need any change of parameters except the matching of the data reading formats. The results of MPCF on the MU radar were validated with Radiosonde data. These results indicate that the MPCF works seamlessly on all types of WP systems irrespective of the carrier, range, and radar type.
      PubDate: April 2018
      Issue No: Vol. 15, No. 4 (2018)
       
  • Detection of Magnetic Anomaly Signal Based on Information Entropy of
           Differential Signal
    • Authors: Ying Tang;Zhongyan Liu;Mengchun Pan;Qi Zhang;Chengbiao Wan;Feng Guan;Fenghe Wu;Dixiang Chen;
      Pages: 512 - 516
      Abstract: Magnetic anomaly detection is an effective approach for detecting the visually obscured ferromagnetic target, and its performance is mainly limited by background geomagnetic noise. In contrast to the traditional detection methods that rely on several a priori assumptions regarding the target or the probability of magnetic noise consisting of external geomagnetic noise and intrinsic sensor noise, we present, in this letter, a new estimator of information entropy for differential signal acquired by a pair of magnetic sensors to detect any changes in the magnetic noise pattern. First, the magnetic noise probability density function (PDF) of differential signal is estimated by using the kernel smoothing method. Then, the minimum entropy detector based on the magnetic noise PDF of differential signal is used to detect the magnetic anomaly target. Finally, according to the probabilities of false alarm, the detection threshold can be obtained to be used for abnormal judgment. In order to verify the effectiveness of the proposed method, the experiment is conducted, and the results demonstrate that the proposed method has better detection performance than that of traditional methods.
      PubDate: April 2018
      Issue No: Vol. 15, No. 4 (2018)
       
  • Human Target Localization Algorithm Using Energy Operator and Doppler
           Processing
    • Authors: Xiaoyi Lin;Yipeng Ding;Xuemei Xu;Kehui Sun;
      Pages: 517 - 521
      Abstract: In this letter, a localization algorithm, which combines energy operator with Doppler processing, is proposed for Doppler radar human sensing applications. For this algorithm, the energy operator is first used to extract the target components of interest from radar echoes and estimate their instantaneous frequencies (IFs). Then, on the basis of the IF estimation result, Doppler processing is applied to synthesize the target movement trajectories. Compared with the traditional localization methods, the proposed algorithm can more precisely estimate the target movement trajectory. Besides, it can further avoid the frequency ambiguity issue, and thus can be very promising for multitarget sensing applications. Experimental results are shown to demonstrate the performance of the proposed algorithm.
      PubDate: April 2018
      Issue No: Vol. 15, No. 4 (2018)
       
  • Quantitative Stability Analysis of Ground Penetrating Radar Systems
    • Authors: Hai Liu;Bangan Xing;Jinfeng Zhu;Bin Zhou;Fei Wang;Xiongyao Xie;Qing Huo Liu;
      Pages: 522 - 526
      Abstract: The hardware instability of a ground penetrating radar (GPR) system has a severe impact on the quantitative analysis of GPR data, which is aimed for material characterization and subsurface monitoring. In this letter, an instability index is proposed to quantify the stability performance of a GPR system and the influences of the GPR system type, warm-up time, environmental noise, and the antenna vibration on it are evaluated through a series of laboratory experiments on a sandbox model. It is found that the GPR signal recorded by a stepped-frequency GPR system based on a vector network analyzer is much more stable than that by a commercial impulse GPR system at a cost of more sweep time. A warm-up time of several minutes is enough for an impulse GPR system. Environmental noise has a negligible influence on the stability performance of a GPR system. Mechanical vibrations of GPR antennas have a severe impact on the stability performance of the GPR system, and the instability index and timing jitter can be increased by more than one order of magnitude in a vibrating condition over those in a static condition. The instability index of the direct signal has a negligible difference with that of the reflection signal from a metal plate; thus, a simple measurement of direct signal on the ground surface is suggested for the evaluation of the instability of a GPR system in field in the future.
      PubDate: April 2018
      Issue No: Vol. 15, No. 4 (2018)
       
  • Knowledge-Aided Covariance Matrix Estimation via Kronecker Product
           Expansions for Airborne STAP
    • Authors: Guohao Sun;Zishu He;Jun Tong;Xuejing Zhang;
      Pages: 527 - 531
      Abstract: This letter proposes a new approach for knowledge-aided estimation of structured clutter covariance matrices (CCMs) in airborne radar systems with limited training data. First, we model the CCM in space–time adaptive processing (STAP) as a sum of low-rank Kronecker products. We then apply a permutation operation to convert the Kronecker factors into linear structures and propose a novel CCM estimation method under the maximum-likelihood framework. Employing a proximal gradient algorithm, the proposed method simultaneously exploits the knowledge about the clutter and the Kronecker structure of the CCM. We finally evaluate the performance of the proposed method using real data from airborne STAP.
      PubDate: April 2018
      Issue No: Vol. 15, No. 4 (2018)
       
  • Brewster Angle Damping Observed in the TerraSAR-X Synthetic Aperture Radar
           Images of Man-Made Targets
    • Authors: Kazuo Ouchi;Chan-Su Yang;
      Pages: 532 - 536
      Abstract: This letter shows the phenomena of Brewster angle damping and its implication observed in the synthetic aperture radar (SAR) images of concrete constructions, such as a bridge and seawalls over the sea. The Fresnel reflection coefficient of concrete material is close to zero at the Brewster angle for X-band V-polarization microwave. The TerraSAR-X images of Tokyo Bay, Japan, at small incidence angles (20.1°-21.4°) showed strong double-bounce reflection between the sea surface and coastal structure with HH-polarization, whereas very little radar backscatter was observed with VV-polarization. The same little radar backscatter was seen in the images of concrete walls on ground and swamp areas covered with reeds. This effect is illustrated with HH/VV intensity and phase difference images, and ground survey data; its implication is also suggested for a better understanding of polarimetric SAR images.
      PubDate: April 2018
      Issue No: Vol. 15, No. 4 (2018)
       
  • An Image Transform Based on Temporal Decomposition
    • Authors: Felix Cremer;Mikhail Urbazaev;Christian Berger;Miguel D. Mahecha;Christiane Schmullius;Christian Thiel;
      Pages: 537 - 541
      Abstract: Today, very dense synthetic aperture radar (SAR) time series are available through the framework of the European Copernicus Programme. These time series require innovative processing and preprocessing approaches including novel speckle suppression algorithms. Here we propose an image transform for hypertemporal SAR image time stacks. This proposed image transform relies on the temporal patterns only, and therefore fully preserves the spatial resolution. Specifically, we explore the potential of empirical mode decomposition (EMD), a data-driven approach to decompose the temporal signal into components of different frequencies. Based on the assumption that the high-frequency components are corresponding to speckle, these effects can be isolated and removed. We assessed the speckle filtering performance of the transform using hypertemporal Sentinel-1 data acquired over central Germany comprising 53 scenes. We investigated speckle suppression, ratio images, and edge preservation. For the latter, a novel approach was developed. Our findings suggest that EMD features speckle suppression capabilities similar to that of the Quegan filter while preserving the original image resolution.
      PubDate: April 2018
      Issue No: Vol. 15, No. 4 (2018)
       
  • Tensorization of Multifrequency PolSAR Data for Classification Using an
           Autoencoder Network
    • Authors: Shaunak De;Debanshu Ratha;Dikshya Ratha;Avik Bhattacharya;Subhasis Chaudhuri;
      Pages: 542 - 546
      Abstract: A novel tensorization framework is proposed, which utilizes the Kronecker product to combine multifrequency polarimetric synthetic aperture radar data in conjunction with an artificial neural network (ANN) for classification. The ANN comprises of two stages, where an unsupervised stochastic sampling autoencoder learns an efficient representation and a supervised feed forward network performs classification. The proposed framework is demonstrated using multifrequency (C-, L-, and P-bands) data sets collected by the AIRSAR system. The classification performance of single tensor product of dual- and triple-band combinations is evaluated. It is observed that the classification accuracy of the tensor products outperforms single, as well as, the simple augmentation of the frequency bands.
      PubDate: April 2018
      Issue No: Vol. 15, No. 4 (2018)
       
  • Focus High-Resolution Highly Squint SAR Data Using Azimuth-Variant
           Residual RCMC and Extended Nonlinear Chirp Scaling Based on a New Circle
           Model
    • Authors: Hua Zhong;Yanjun Zhang;Yuliang Chang;Erxiao Liu;Xianghong Tang;Jianwu Zhang;
      Pages: 547 - 551
      Abstract: The combination of linear range walk correction and keystone transform is a good choice to focus high-resolution highly squint synthetic aperture radar (SAR) data because it is an effective way to remove linear range cell migration (RCM) completely and mitigate range-azimuth coupling. However, the results of this kind of imaging algorithm produce 2-D-variant residual RCM and variant-dependence Doppler phases. To obtain high-quality SAR image, an improved imaging algorithm using an azimuth-variant residual RCM correction (RCMC) and an extended nonlinear chirp scaling (ENLCS) is proposed in this letter. A new circle model is constructed to analyze the azimuth-variant properties of the residual high-order RCM and the Doppler phases. Based on this circle model, an azimuth-variant residual RCMC is implemented by multiplying a fourth-order phase function, and an improved ENLCS is derived to accomplish the azimuth equalization for azimuth compression. Simulation results validate the excellent performance of the proposed algorithm.
      PubDate: April 2018
      Issue No: Vol. 15, No. 4 (2018)
       
  • Adaptive Probability Thresholding in Automated Ice and Open Water
           Detection From RADARSAT-2 Images
    • Authors: Alexander S. Komarov;Mark Buehner;
      Pages: 552 - 556
      Abstract: In this letter, we introduce adaptive probability thresholding in addition to our previously developed technique for automated detection of ice and open water from RADARSAT-2 ScanSAR dual-polarization HH-HV images. Situations where the probability threshold needs to be modified were identified based on the analysis of misclassified ice and water samples when the static probability threshold of 0.95 is applied. We found that with the use of the proposed approach, the fraction of misclassified ice samples decreased from 0.98% to 0.24% and the fraction of misclassified water samples decreased from 0.35% to 0.09% in the most clean verification scenario against Canadian Ice Service Image Analysis pure ice and water data, while the fraction of correctly classified ice and water samples did not decrease appreciably, from 72.2% to 65.4%. The developed approach will be implemented as a part of the data assimilation component of the operational Environment and Climate Change Canada Regional Ice-Ocean Prediction System.
      PubDate: April 2018
      Issue No: Vol. 15, No. 4 (2018)
       
  • SAR Focus Theory of Complicated Range Migration Signatures Due to Moving
           Targets
    • Authors: David Alan Garren;
      Pages: 557 - 561
      Abstract: Recent studies have revealed that the residual range migration effects of synthetic aperture radar (SAR) imagery smears induced by moving targets can exhibit complicated shapes that are not limited to that of parabolas. This letter demonstrates that automatic focusing methods can remove such range migration effects by estimating and compensating for phase errors directly in the radar video phase history domain. This approach is validated using measured Ku-band SAR clutter data containing buildings and foliage.
      PubDate: April 2018
      Issue No: Vol. 15, No. 4 (2018)
       
  • Target Detection by Exploiting Superpixel-Level Statistical Dissimilarity
           for SAR Imagery
    • Authors: Tao Li;Zheng Liu;Lei Ran;Rong Xie;
      Pages: 562 - 566
      Abstract: In this letter, we propose a superpixel-level target detection approach for synthetic aperture radar (SAR) images. With superpixel segmentation, SAR image is divided into meaningful patches and more statistical information can be provided in superpixels compared with single pixels. The statistical difference between target and clutter superpixels can be measured with the intensity distributions of pixels in them. With the assumption of SAR data obeying Gamma distribution, the superpixel dissimilarity is defined. With this basis, the global and local contrast can be obtained and integrated to enhance target and suppress clutter simultaneously. Thus, better target detection performance can be achieved. Different from traditional target detection schemes based on backscattering difference between target and clutter pixels, the proposed method relies on the statistical difference of superpixels. The effectiveness of the proposed method can be demonstrated with experimental results on real SAR images.
      PubDate: April 2018
      Issue No: Vol. 15, No. 4 (2018)
       
  • Temporal Analysis of S-Band Microwave Backscattering From an Inland
           Reservoir Surface
    • Authors: James Park;Saba Mudaliar;Panos Tzanos;Kung-Hau Ding;
      Pages: 567 - 571
      Abstract: This letter presents an analysis of the temporal characteristics of electromagnetic waves scattered from a time-varying reservoir surface at low grazing angles. The data collection campaigns were conducted using a polarimetric S-band radar at Wachusett Reservoir in MA, USA, and VV and HH polarized radar returns were simultaneously captured. The temporal behavior of the backscattering from the reservoir surface was analyzed for 180 distinct radar geometries, focusing in particular on the impact of polarization, radar geometry, and wind condition. To understand the shape of the Doppler spectrum, the power spectral density is estimated by a periodogram. In addition, decorrelation time, Doppler centroid, and variance are estimated and compared with the associated Doppler spectral width and peak Doppler frequency. Results show that Doppler spectral width, decorrelation time, and the standard deviation of Doppler spectra are correlated. In addition, the Doppler frequency shift induced by the motion of the water surface is analyzed by peak Doppler frequency and Doppler centroid, which show dependence on radar geometry and wind direction.
      PubDate: April 2018
      Issue No: Vol. 15, No. 4 (2018)
       
  • A Saliency-Based Band Selection Approach for Hyperspectral Imagery
           Inspired by Scale Selection
    • Authors: Peifeng Su;Daizhi Liu;Xihai Li;Zhigang Liu;
      Pages: 572 - 576
      Abstract: This letter presents a band selection method relying on saliency bands and scale selection (SBSS). The SBSS method is used to excavate the hidden information of hyperspectral images effectively, while its underlying assumptions are: 1) it is reasonable to combine spectral and spatial information to excavate the intrinsic property of a hyperspectral image; 2) there are some saliency bands that can represent a hyperspectral image without significant information loss in data exploitation; and 3) saliency, scale, and image description have an intrinsic connection. The computational complexity of the SBSS method is linear, and experimental results demonstrate that the proposed method obtains competitively good results compared with other state-of-the-art band selection techniques, in terms of classification accuracy.
      PubDate: April 2018
      Issue No: Vol. 15, No. 4 (2018)
       
  • Anomaly Detection of Hyperspectral Imagery Using Modified Collaborative
           Representation
    • Authors: Maryam Vafadar;Hassan Ghassemian;
      Pages: 577 - 581
      Abstract: Hyperspectral images in remote sensing systems with rich spatial and spectral information provide an opportunity for researchers to discover the world. Anomaly detection is one of the most interesting topics over the last two decades in hyperspectral imagery (HSI). In this letter, we propose a modified collaborative-representation-based with outlier removal anomaly detector (CRBORAD) for anomaly detection. We use both spectral and spatial information for detecting anomalies since that is more precise than using only spectral information. The proposed detector can adaptively estimate the background by its adjacent pixels within a sliding dual-window. We remove outlier pixels that are significantly different from majority of pixels, before estimating background pixels. It can lead us to precise detection of anomalies in subsequent stages. By subtracting the predicted background from the original HSI, the residual image is resulted and anomalies can be determined, finally. Kernel extension of the proposed approach is also presented. CRBORAD results on San Diego airport and the Rochester Institute of Technology data are illustrated using intuitive images, receiver operating characteristic curves, and area under curve values. The results are compared with four popular and previous methods and prove the superiority of the proposed CRBORAD method.
      PubDate: April 2018
      Issue No: Vol. 15, No. 4 (2018)
       
  • A Supervised Geometry-Aware Mapping Approach for Classification of
           Hyperspectral Images
    • Authors: Ramanarayan Mohanty;S. L. Happy;Aurobinda Routray;
      Pages: 582 - 586
      Abstract: The lack of proper class discrimination among the hyperspectral (HS) data points poses a potential challenge in HS classification. To address this issue, this letter proposes an optimal geometry-aware transformation for enhancing the classification accuracy. The underlying idea of this method is to obtain a linear projection matrix by solving a nonlinear objective function based on the intrinsic geometrical structure of the data. The objective function is constructed to quantify the discrimination between the points from dissimilar classes on the projected data space. Then, the obtained projection matrix is used to linearly map the data to more discriminative space. The effectiveness of the proposed transformation is illustrated with three benchmark real-world HS data sets. The experiments reveal that the classification and dimensionality reduction methods on the projected discriminative space outperform their counterpart in the original space.
      PubDate: April 2018
      Issue No: Vol. 15, No. 4 (2018)
       
  • Hyperspectral Image Classification With Discriminative Kernel
           Collaborative Representation and Tikhonov Regularization
    • Authors: Yong Ma;Chang Li;Hao Li;Xiaoguang Mei;Jiayi Ma;
      Pages: 587 - 591
      Abstract: Recently, collaborative representation has received much attention in the hyperspectral image (HSI) classification due to its simplicity and effectiveness. However, the existing collaborative representation-based HSI classification methods ignore the correlation among different classes. To overcome this problem, we propose a discriminative kernel collaborative representation and Tikhonov regularization method (DKCRT) for HSI classification, which can make the kernel collaborative representation of different classes to be more discriminative. Specifically, the kernel trick is adopted to map the original HSI into a high space to improve the class separability. Besides, distance-weighted kernel Tikhonov regularization is adopted to enforce these training samples to have large representation coefficients, which are similar to the test sample in the high-dimensional feature space. Moreover, we add a discriminative regularization term to further enhance the separability of different classes, which can take the correlation among different classes into consideration. Furthermore, to take the spatial information of HSI into consideration, we extend the DKCRT to a joint version named JDKCRT. Experiments on real HSIs demonstrate the efficiency of the proposed DKCRT and JDKCRT.
      PubDate: April 2018
      Issue No: Vol. 15, No. 4 (2018)
       
  • Nonrigid Image Registration for Low-Altitude SUAV Images With Large
           Viewpoint Changes
    • Authors: Su Zhang;Kun Yang;Yang Yang;Yi Luo;
      Pages: 592 - 596
      Abstract: Low-altitude aerial photography using small unmanned aerial vehicles (SUAVs) with large viewpoint changes causes nonrigid distortions and low overlap ratios. We present a nonrigid feature-based low-altitude SUAV image-registration method. The key idea of our method is to maintain a high matching ratio on inliers while taking advantage of outliers for varying the warping grids. Thus, accurate image transformation over the overlapping areas as well as a good approximation of the real transformation over the nonoverlapping areas can be obtained. Experiments on feature matching and image registration are performed using 42 pairs of SUAV images. Our method exhibited a favorable performance as compared with four state-of-the-art methods, even with up to 80% outliers.
      PubDate: April 2018
      Issue No: Vol. 15, No. 4 (2018)
       
  • Asymmetric Adaptation of Deep Features for Cross-Domain Classification in
           Remote Sensing Imagery
    • Authors: Nassim Ammour;Laila Bashmal;Yakoub Bazi;M. M. Al Rahhal;Mansour Zuair;
      Pages: 597 - 601
      Abstract: In this letter, we introduce an asymmetric adaptation neural network (AANN) method for cross-domain classification in remote sensing images. Before the adaptation process, we feed the features obtained from a pretrained convolutional neural network to a denoising autoencoder (DAE) to perform dimensionality reduction. Then the first hidden layer of AANN (placed on the top of DAE) maps the labeled source data to the target space, while the subsequent layers control the separation between the available land-cover classes. To learn its weights, the network minimizes an objective function composed of two losses related to the distance between the source and target data distributions and class separation. The results of experiments conducted on six scenarios built from three benchmark scene remote sensing data sets (i.e., Merced, KSA, and AID data sets) are reported and discussed.
      PubDate: April 2018
      Issue No: Vol. 15, No. 4 (2018)
       
  • Automatic Water-Body Segmentation From High-Resolution Satellite Images
           via Deep Networks
    • Authors: Ziming Miao;Kun Fu;Hao Sun;Xian Sun;Menglong Yan;
      Pages: 602 - 606
      Abstract: Water-body segmentation is an important issue in remote sensing and image interpretation. Classic methods for counteracting this problem usually include the construction of index features by combining different spectra, however, these methods are essentially rule-based and fail to take advantage of context information. Additionally, as the quality of image resolution improves, these methods are proved to be inadequate. With the rise of convolutional neural networks (CNN), the level of research about segmentation has taken a huge leap, but the field is still facing an increasing demand for data and the problem of blurring boundaries. In this letter, a new segmentation network called restricted receptive field deconvolution network (RRF DeconvNet) is proposed, with which to extract water bodies from high-resolution remote sensing images. Compared with natural images, remote sensing images have a weaker pixel neighborhood relativity; in consideration of this challenge, an RRF DeconvNet compresses the redundant layers in the original DeconvNet and no longer relies on a pretrained model. In addition, to tackle the blurring boundaries that occur in CNN, a new loss function called edges weighting loss is proposed to train segmentation networks, which has been shown to significantly sharpen the segmentation boundaries in results. Experiments, based on Google Earth images for water-body segmentation, are presented in this letter to prove our method.
      PubDate: April 2018
      Issue No: Vol. 15, No. 4 (2018)
       
  • Very High Resolution Object-Based Land Useā€“Land Cover Urban
           Classification Using Extreme Gradient Boosting
    • Authors: Stefanos Georganos;Tais Grippa;Sabine Vanhuysse;Moritz Lennert;Michal Shimoni;Eléonore Wolff;
      Pages: 607 - 611
      Abstract: In this letter, the recently developed extreme gradient boosting (Xgboost) classifier is implemented in a very high resolution (VHR) object-based urban land use–land cover application. In detail, we investigated the sensitivity of Xgboost to various sample sizes, as well as to feature selection (FS) by applying a standard technique, correlation-based FS. We compared Xgboost with benchmark classifiers such as random forest (RF) and support vector machines (SVMs). The methods are applied to VHR imagery of two sub-Saharan cities of Dakar and Ouagadougou and the village of Vaihingen, Germany. The results demonstrate that Xgboost parameterized with a Bayesian procedure, systematically outperformed RF and SVM, mainly in larger sample sizes.
      PubDate: April 2018
      Issue No: Vol. 15, No. 4 (2018)
       
  • Infrared Small Target Detection Utilizing the Multiscale Relative Local
           Contrast Measure
    • Authors: Jinhui Han;Kun Liang;Bo Zhou;Xinying Zhu;Jie Zhao;Linlin Zhao;
      Pages: 612 - 616
      Abstract: Infrared (IR) small target detection with high detection rate, low false alarm rate, and high detection speed has a significant value, but it is usually very difficult since the small targets are usually very dim and may be easily drowned in different types of interferences. Current algorithms cannot effectively enhance real targets and suppress all the types of interferences simultaneously. In this letter, a multiscale detection algorithm utilizing the relative local contrast measure (RLCM) is proposed. It has a simple structure: first, the multiscale RLCM is calculated for each pixel of the raw IR image to enhance real targets and suppress all the types of interferences simultaneously; then, an adaptive threshold is applied to extract real targets. Experimental results show that the proposed algorithm can deal with different sizes of small targets under complex backgrounds and has a better effectiveness and robustness against existing algorithms. Besides, the proposed algorithm has the potential of parallel processing, which is very useful for improving the detection speed.
      PubDate: April 2018
      Issue No: Vol. 15, No. 4 (2018)
       
  • Multiscale Fully Convolutional Network for Foreground Object Detection in
           Infrared Videos
    • Authors: Dongdong Zeng;Ming Zhu;
      Pages: 617 - 621
      Abstract: Accurate and fast infrared (IR) foreground object detection is one of the most significant issues to be solved due to its important meaning for IR target recognition, IR precise guidance, IR video surveillance, and so on. A common approach for such tasks is “background subtraction,” which aims to detect foreground object through background modeling. Thus far, many background subtraction methods have been proposed and have achieved good performance. However, due to the special characteristics of IR images, a few algorithms are suitable for IR foreground object detection. Recently, features learned from convolutional neural networks (CNNs) have demonstrated great success in many vision tasks, such as classification and recognition. In this letter, we propose a novel multiscale fully convolutional network architecture for IR foreground object detection. Given a CNN model pretrained on a large-scale image data set, our method takes output features from different layers of the network. With features from multiple scales, our feature representation contains both category-level semantics and fine-grain details. The experimental results on IR image sequences show that the proposed method achieves the state-of-the-art performance while operating in real time.
      PubDate: April 2018
      Issue No: Vol. 15, No. 4 (2018)
       
  • Feature Adaptation and Augmentation for Cross-Scene Hyperspectral Image
           Classification
    • Authors: Jiayi Shen;Xianbin Cao;Yan Li;Dong Xu;
      Pages: 622 - 626
      Abstract: Cross-scene hyperspectral image (HSI) classification has recently become increasingly popular due to its crucial use in various applications. It poses great challenges to existing domain adaptation methods because of the data set shift, that is, two scenes exhibit huge distribution discrepancy. To tackle this problem, we propose a new domain adaptation method called hyperspectral feature adaptation and augmentation (HFAA) for cross-scene HSI classification. The proposed HFAA method learns a common subspace by introducing two different projection matrices to extract the transferable knowledge from the source domain to the target domain. To further enhance the common subspace representation, we propose to augment it by the feature selection strategy. HFAA can make full use of the original features from both source and target domains, and increase the similarity of the samples with the same label from the two domains. Our proposed HFAA method achieves compact but discriminative feature representations, which make it well suited for data sets with a large number of classes and huge interclass ambiguity. Experimental results on the Earth Observing 1 hyperspectral data set show that HFAA can produce state-of-the-art performance and surpass previous methods.
      PubDate: April 2018
      Issue No: Vol. 15, No. 4 (2018)
       
  • PolSAR Image Classification Using Polarimetric-Feature-Driven Deep
           Convolutional Neural Network
    • Authors: Si-Wei Chen;Chen-Song Tao;
      Pages: 627 - 631
      Abstract: Polarimetric synthetic aperture radar (PolSAR) image classification is an important application. Advanced deep learning techniques represented by deep convolutional neural network (CNN) have been utilized to enhance the classification performance. One current challenge is how to adapt deep CNN classifier for PolSAR classification with limited training samples, while keeping good generalization performance. This letter attempts to contribute to this problem. The core idea is to incorporate expert knowledge of target scattering mechanism interpretation and polarimetric feature mining to assist deep CNN classifier training and improve the final classification performance. A polarimetric-feature-driven deep CNN classification scheme is established. Both classical roll-invariant polarimetric features and hidden polarimetric features in the rotation domain are used to drive the proposed deep CNN model. Comparison studies validate the efficiency and superiority of the proposal. For the benchmark AIRSAR data, the proposed method achieves the state-of-the-art classification accuracy. Meanwhile, the convergence speed from the proposed polarimetric-feature-driven CNN approach is about 2.3 times faster than the normal CNN method. For multitemporal UAVSAR data sets, the proposed scheme achieves comparably high classification accuracy as the normal CNN method for train-used temporal data, while for train-not-used data it obtains an average of 4.86% higher overall accuracy than the normal CNN method. Furthermore, the proposed strategy can also produce very promising classification accuracy even with very limited training samples.
      PubDate: April 2018
      Issue No: Vol. 15, No. 4 (2018)
       
  • Unsupervised Hyperspectral Remote Sensing Image Clustering Based on
           Adaptive Density
    • Authors: Huan Xie;Ang Zhao;Shengyu Huang;Jie Han;Sicong Liu;Xiong Xu;Xin Luo;Haiyan Pan;Qian Du;Xiaohua Tong;
      Pages: 632 - 636
      Abstract: Hyperspectral remote sensing image (HSI) clustering can be defined as the process of segmenting pixels into different sets that satisfy the requirement that the differences between sets are much greater than the differences within sets. According to the fast density peak-based clustering algorithm, we propose an unsupervised HSI clustering method based on the density of pixels in the spectral space and the distance between pixels. For the metric of the density, we present an adaptive-bandwidth probability density function using pixel numbers as the input and the calculated pixel local density as the output, which determines the bandwidth on the basis of the Gaussian assumption. For the metric of the distance, in order to obtain a pixel-level spectral distance, we calculate the Euclidean distance between pixel vectors from the multiple bands. In the proposed approach: 1) use the least-squares method for the curve fitting of the two results; 2) eliminate outliers based on the Pauta criterion; 3) adopt regression calculation; and 4) obtain the cluster centers according to the classification criteria of the local density and the distance between pixel vectors. The other noncluster center points are clustered based on their similarities with the cluster centers by iteration. Finally, we compare the results with those of other unsupervised clustering methods and the reference data sets.
      PubDate: April 2018
      Issue No: Vol. 15, No. 4 (2018)
       
 
 
JournalTOCs
School of Mathematical and Computer Sciences
Heriot-Watt University
Edinburgh, EH14 4AS, UK
Email: journaltocs@hw.ac.uk
Tel: +00 44 (0)131 4513762
Fax: +00 44 (0)131 4513327
 
Home (Search)
Subjects A-Z
Publishers A-Z
Customise
APIs
Your IP address: 54.196.47.145
 
About JournalTOCs
API
Help
News (blog, publications)
JournalTOCs on Twitter   JournalTOCs on Facebook

JournalTOCs © 2009-