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.
Similar Journals
Journal Cover
IEEE Geoscience and Remote Sensing Letters
Journal Prestige (SJR): 1.486
Citation Impact (citeScore): 4
Number of Followers: 204  
 
  Hybrid Journal Hybrid journal (It can contain Open Access articles)
ISSN (Print) 1545-598X
Published by IEEE Homepage  [229 journals]
  • IEEE Geoscience and Remote Sensing Letters publication information
    • PubDate: June 2020
      Issue No: Vol. 17, No. 6 (2020)
       
  • IEEE Geoscience and Remote Sensing Letters information for authors
    • PubDate: June 2020
      Issue No: Vol. 17, No. 6 (2020)
       
  • IEEE Geoscience and Remote Sensing Letters Institutional Listings
    • PubDate: June 2020
      Issue No: Vol. 17, No. 6 (2020)
       
  • Potential Application of 205-MHz Stratosphere–Troposphere Wind Profiling
           Radar in Ionospheric Studies: Preliminary Results
    • Authors: M. C. Neethu Mohan;V. Rakesh;M. G. Manoj;Titu K. Samson;Rejoy Rebello;Binu Paul;K. Mohankumar;P. Mohanan;
      Pages: 918 - 922
      Abstract: A state-of-the-art 205-MHz wind profiling radar designed for measuring both the horizontal and vertical wind components from 315 m to beyond 20 km has been installed at the Cochin University of Science and Technology (CUSAT), India (10.04°N, 76.33°E, dip angle ~7.1°N). Subsequently, the radar was operated with special configuration to probe the ionosphere. After a series of experiments, the radar was successfully configured to receive ionospheric reflections from about 90 to 500 km range covering the E and F layers, with high resolution (45 m for the 90–110 km region). The received echoes are identified as signatures of field-aligned irregularities (FAIs) of the E and F regions of the ionosphere. The E region echoes were observed at an altitude range of 90–110 km. Both continuous and quasi-periodic structures were identified. Further analysis from the spectrum shows that the E region FAIs are Type 2 in nature. The night time spread-F observed so far is of either bottom type or bottom side in nature. This letter portrays the scope of employing 200 MHz range of very high frequency (VHF) band for ionospheric observations, and the technical details and the initial results of the experiment conducted with this stratosphere–troposphere (ST) Radar.
      PubDate: June 2020
      Issue No: Vol. 17, No. 6 (2020)
       
  • Evaluating Chinese HY-2B HSCAT Ocean Wind Products Using Buoys and Other
           Scatterometers
    • Authors: He Wang;Jianhua Zhu;Mingsen Lin;Youguang Zhang;Yiting Chang;
      Pages: 923 - 927
      Abstract: This letter preliminarily assesses the accuracy of ocean wind products from the Ku-band scatterometer (HSCAT) onboard the recently launched Chinese satellite HY-2B. The wind vectors derived from HSCAT during the period from November 15, 2018 to April 30, 2019 are evaluated. The reference wind data include in situ measurements from the offshore meteorological buoys of the National Data Buoy Center, USA, and westerlies mooring of the National Ocean Technology Center, China, and scatterometer winds from the European Advanced Scatterometer (ASCAT) and Indian SCATSAT-1 Oceansat Scatterometer (OSCAT). The spatial difference is limited to $25/surd 2$ km, while the HSCAT winds are temporally collocated with buoys and other scatterometers by less than 0.5 and 1.5 h, respectively. The comparison results show that the HSCAT data have a root-mean-square error (RMSE) of 0.95–1.20 m/s (14.7°–25.7°) regarding the wind speed and direction, respectively, indicating consistency between the HSCAT winds and the reference. Furthermore, better agreement is found for the HY-2B HSCAT winds processed using the Pencil-beam Wind Processor (PWP) algorithm, regarding wind speed (RMSE of 0.95–1.07 m/s) and particularly with respective to the wind direction (RMSE of 14.7°–19.6°), both satisfying the mission specification (< 2 m/s and < 20 for wind speed and direction, respectively). The encouraging validation results over the first 5 months demonstrate that the HY-2B HSCAT wind products will be useful for the scientific community.
      PubDate: June 2020
      Issue No: Vol. 17, No. 6 (2020)
       
  • Temporal Decorrelation of Tropical Dense Forest at C-Band: First Insights
           From the TropiScat-2 Experiment
    • Authors: S. El Idrissi Essebtey;L. Villard;P. Borderies;T. Koleck;J. P. Monvoisin;B. Burban;T. Le Toan;
      Pages: 928 - 932
      Abstract: Following the past TropiScat and AfriScat tower-based scatterometer experiments conducted as part of the European Space Agency (ESA) BIOMASS mission preparation activities, a follow-on experiment referred to as TropiScat-2 has been undertaken in French Guiana since March 2018. Based on new capabilities including C-band acquisitions, this letter addresses the question of temporal decorrelation variability at several time scales using a period of 67 days dating back to early August 2018. Overall, C-band coherences have been found very dependent on the reference hour and higher than expected at night (15-min coherences above 0.75 and 1-h coherences above 0.5 75% of the time). Supported by meteorological data from the flux-tower, clear evidence about diurnal convective effects is shown. For the first time, the link with evapotranspiration is pointed out based on a drop of the 15-min coherences going from about 0.8 to 0.2 in less than 1 h (around 7h30) and before the rise of convective winds. Furthermore, the specific impacts of convective winds during the day have been demonstrated using very short timescales (with the spread of coherences at 1 s from 0 to 0.9), whereas it is more difficult to separate these effects from those of water transfer for longer timescales. In addition to providing new insights for the understanding of microwave interactions with dense vegetation, these results should also contribute to widen the capabilities of future companion or high revisit space-borne missions at C-band.
      PubDate: June 2020
      Issue No: Vol. 17, No. 6 (2020)
       
  • Full-Wave Indoor Measurements’ Cross-Validation With the Model Demos for
           Foliage Penetrating Applications
    • Authors: L. Hettak;H. Saleh;C. Dahon;M. Casaletti;O. Meyer;J.-M. Geffrin;H. Roussel;
      Pages: 933 - 937
      Abstract: For foliage penetrating (FoPen) radar development, we previously developed a hybrid volume–surface model, named Domain dEcomposition Model (DEMOS), to evaluate the electromagnetic scattering from large scenes composed by targets (metallic objects) placed in a natural environment (dielectric object). In this letter, we compare the scattered field obtained by DEMOS with the quasi-monostatic measurements done in an anechoic chamber on scaled models composed of dielectric and metallic structures. For all measurements, we consider both polarizations, HH and VV. Our final objective is to determine the optimal configurations for the detection of a target placed in a forest environment in the very high-frequency (VHF)-UHF frequency bands.
      PubDate: June 2020
      Issue No: Vol. 17, No. 6 (2020)
       
  • A Novel 3-D Imaging Method for Subsurface Targets Based on Time-Domain
           Electromagnetic Induction System
    • Authors: Wupeng Xie;Xiaojuan Zhang;Yaxin Mu;
      Pages: 938 - 942
      Abstract: In recent years, the time-domain electromagnetic (TEM) method has played an important role in the detection and identification of subsurface targets, but the imaging of underground limited volume targets has always been a major problem. In this letter, we propose a novel 3-D imaging method to image subsurface targets using the TEM induction (TEMI) system. The method is based on the discretization of the underground into several grids which represent the independent magnetic dipoles contribution to the measured responses collectively. The strength of every dipole is obtained by minimizing the mismatch between computed and observed secondary response from the targets using the iterative optimization method. Then, the simulation and field experiments are done to verify the feasibility of this method. The results show that the method proposed herein has a small amount of computation and strong robustness, which help visualize the underground targets in three dimensions accurately and rapidly.
      PubDate: June 2020
      Issue No: Vol. 17, No. 6 (2020)
       
  • Positional Context Aggregation Network for Remote Sensing Scene
           Classification
    • Authors: Dong Zhang;Nan Li;Qiaolin Ye;
      Pages: 943 - 947
      Abstract: To capture the long-range dependence of an input image for remote sensing scene (RSS) classification, in this letter, we propose a general positional context aggregation (PCA) module in deep convolutional neural networks. The PCA module is with the form of self-attention mechanism, in which two proposed blocks, the spatial context aggregation (SCA) and the relative position encoding (RPE), are used to capture the spatial-dipartite contextual aggregation information and the RPE information. Therefore, compared with the classical self-attention mechanism, global attention maps extracted by PCA not only have the advantage of regional distinction but also satisfy the translation equivariance that is proven to benefit scene classification. To demonstrate the superiority of the PCA module, we implement it on the pretrained ResNet [i.e., the so-called PCA network (PCANet)] and report the results on five popular RSS classification benchmarks. Experimental results show that the PCA module can improve the RSS classification performance significantly, and PCANet50 achieves the state-of-the-art results on these data sets.
      PubDate: June 2020
      Issue No: Vol. 17, No. 6 (2020)
       
  • Spectral Reflectance Processing via Local Wavelength-Direction
           Correlations
    • Authors: Guanglang Xu;Maria Gritsevich;Jouni Peltoniemi;Antti Penttilä;Olli Wilkman;Olli Ihalainen;Karri Muinonen;
      Pages: 948 - 952
      Abstract: The spectral bidirectional reflectance distribution function (BRDF) maps incident radiation of a surface to its outgoing counterpart at different wavelengths. This function plays a fundamental role in characterizing the various types of earth surfaces. Due to its high dimensionality, the measurements, analysis, and simulation of spectral BRDF are challenging. In this letter, we introduce a new method for processing spectral reflectance using the so-called data-adjacency, i.e., the correlation between adjacent wavelengths and viewing directions. The results show that the benefits of efficient representation, noise reduction, and analysis capability can all be integrated to the data.
      PubDate: June 2020
      Issue No: Vol. 17, No. 6 (2020)
       
  • An Improved Two-Scale Model for Electromagnetic Backscattering From Sea
           Surface
    • Authors: Dongfang Li;Zhiqin Zhao;Conghui Qi;Yuan Huang;Yanwen Zhao;Zaiping Nie;
      Pages: 953 - 957
      Abstract: Based on composite rough surface and stochastic multiscale models, an improved two-scale model (TSM) is proposed. Different from the classical TSM, the proposed method adopts the integral equation method (IEM) to replace the small perturbation method (SPM) for calculating the contribution from small-scale roughness. Kirchhoff approximation (KA) is still kept in the model to calculate the contribution from large-scale roughness. Because the IEM has wider application range than the SPM, the proposed model exhibits a higher accuracy and has a wider application range in terms of sea surface roughness compared with the classical TSM. Usually, the classical TSM is sensitive to the cutoff wavenumber. The proposed model adopts an adaptive cutoff wavenumber instead of choosing a cutoff wavenumber in the classical TSM. The effectiveness of the proposed model is demonstrated through comparisons with the simulation results of multilevel fast multipole algorithm (MLFMA) and the measured results. Different roughness at different frequencies is analyzed as well.
      PubDate: June 2020
      Issue No: Vol. 17, No. 6 (2020)
       
  • Improved Clutter Removal in GPR by Robust Nonnegative Matrix Factorization
    • Authors: Deniz Kumlu;Isin Erer;
      Pages: 958 - 962
      Abstract: The clutter encountered in the ground-penetrating radar (GPR) system severely decreases the visibility of subsurface objects, thus highly degrading the performance of the target detection algorithms. This letter presents a new clutter removal method based on nonnegative matrix factorization (NMF). The raw GPR data are represented as the sum of low-rank and sparse matrices, which correspond to the clutter and target components, respectively. The low-rank and sparse decomposition is performed using a robust version of NMF called RNMF. Although similar to the robust principal component analysis (PCA) (RPCA), which is recently widely used in image processing applications as well as in GPR, the proposed method is faster and has enhanced results. The state-of-the-art clutter removal methods, morphological component analysis (MCA), RPCA, besides the conventional PCA, have been included for comparison for both simulated and real data sets. The visual and quantitative results demonstrate that the proposed RNMF method outperforms the others. Moreover, it is 25 times faster than the RPCA for the given regularization parameter values.
      PubDate: June 2020
      Issue No: Vol. 17, No. 6 (2020)
       
  • CRInSAR Using Two-Step LAMBDA Algorithm for Nonlinear Deformation
           Estimation: Case Study of Monitoring Xiangtan Converter Station, China
    • Authors: Changjiang Yang;Jun Hu;Zhengfeng Cheng;Zhiwei Li;Lei Zhang;Qian Sun;
      Pages: 963 - 967
      Abstract: Deformation monitoring of a converter station of an electrical power transmission system will help to prevent potential damages to power facilities and properties. Corner reflector InSAR (CRInSAR) enables local deformation measurements in low coherence areas like construction-engineering projects. However, the accuracy of CRInSAR will be degraded by the phase unwrapping errors, especially when the deformation is large or dominated by nonlinear component. This letter reports a study that employs CRInSAR technique to monitor the deformations of ten CRs installed in Xiangtan converter station, China, with seven TerraSAR-X Spotlight images. A two-step phase unwrapping tactics is proposed based on the least squares ambiguity decorrelation adjustment (LAMBDA) algorithm to focus on estimating nonlinear deformation without being affected by unwrapping errors. The results reveal that the two-step LAMBDA algorithm can achieve an accuracy of less than 2 mm for CRInSAR deformation monitoring regardless of small- or large-scale deformations, as validated by the trigonometric leveling measurements.
      PubDate: June 2020
      Issue No: Vol. 17, No. 6 (2020)
       
  • Marginal Center Loss for Deep Remote Sensing Image Scene Classification
    • Authors: Tianyu Wei;Jue Wang;Wenchao Liu;He Chen;Hao Shi;
      Pages: 968 - 972
      Abstract: Recently, remote sensing image scene classification technology has been widely applied in many applicable industries. As a result, several remote sensing image scene classification frameworks have been proposed; in particular, those based on deep convolutional neural networks have received considerable attention. However, most of these methods have performance limitations when analyzing images with large intraclass variations. To overcome this limitation, this letter presents the marginal center loss with an adaptive margin. The marginal center loss separates hard samples and enhances the contributions of hard samples to minimize the variations in features of the same class. Experimental results on public remote sensing image scene data sets demonstrate the effectiveness of our method. After the model is trained using the marginal center loss, the variations in the features of the same class are reduced. Furthermore, a comparison with state-of-the-art methods proves that our model has competitive performance in the field of remote sensing image scene classification.
      PubDate: June 2020
      Issue No: Vol. 17, No. 6 (2020)
       
  • A Half-Cut Compact Monopole Antenna for SFCW Radar-Based Concrete Wall
           Monitoring With a Passive Cooperative Target
    • Authors: Jiyu Guo;Weike Feng;Jean-Michel Friedt;Qing Zhao;Motoyuki Sato;
      Pages: 973 - 977
      Abstract: Stepped frequency continuous wave (SFCW)-based radar with passive cooperative target is a promising nondestructive method to monitor the concrete temperature change. By burying a surface acoustic wave (SAW) sensor in the concrete to act as the cooperative target, the physical properties of the concrete can be measured by analyzing the reflections of the probing SFCW signal. Because the SAW sensor should be connected to an antenna to convert the electromagnetic wave into the acoustic wave, a half-cut compact monopole antenna is designed and fabricated in this letter. Taking the advantages of corrugated edge and half-structure technologies, the size of the monopole antenna decreases significantly without sacrificing the performance, which makes the SAW sensor together with antenna suitable to be inserted into the concrete. The experimental results show that the proposed antenna can work well with the SAW sensor in the concrete and the proposed method can measure the temperature change in concrete continuously.
      PubDate: June 2020
      Issue No: Vol. 17, No. 6 (2020)
       
  • Fast Detection Method for Low-Observable Maneuvering Target via Robust
           Sparse Fractional Fourier Transform
    • Authors: Xiaohan Yu;Xiaolong Chen;Yong Huang;Jian Guan;
      Pages: 978 - 982
      Abstract: In this letter, a novel fast detection algorithm, known as robust sparse fractional Fourier transform (RSFRFT), is proposed for low-observable maneuvering target detection in a clutter background. The discrete FRFT (DFRFT)-based detection method is time-consuming for large data volumes and the detection performance of sparse FRFT (SFRFT)-based algorithm will be significantly degraded in a heavy clutter background. Using two levels of detection, the defects of DFRFT and SFRFT algorithms are overcome using the proposed algorithm. The first-level detection is performed on the subsampled spectrum to estimate the target frequencies. The second-level detection is carried out after reconstruction for target detection. The simulation analysis and experiments using marine radar data show that the proposed method can achieve a good detection performance for low-observable maneuvering target detection in the clutter background with lower computational complexity.
      PubDate: June 2020
      Issue No: Vol. 17, No. 6 (2020)
       
  • Denoising FMCW Ladar Signals via EEMD With Singular Spectrum Constraint
    • Authors: Rongrong Wang;Maosheng Xiang;Chuang Li;
      Pages: 983 - 987
      Abstract: Frequency-modulation continuous-wave (FMCW) Laser radar (Ladar) signals may be polluted by noise, which reduces the recognition precision of the targets. This letter proposes an ensemble empirical modal decomposition (EEMD) denoising method with singular spectrum constraint for FMCW Ladar signals. In our approach, we apply EEMD to adaptively decompose the noisy FMCW Ladar signals into several intrinsic mode functions (IMFs) and decompose these IMFs into several singular value components by using the singular spectrum analysis. The singular values are then used to calculate the energy probability of each IMF, which serves as an indicator to detect the IMFs containing useful signals. The energy probability represents the coherence of the IMFs such that we could sort these IMFs into noisy and useful components according to their coherence differences. To suppress the residual noise that is interfered with the selected IMFs, we use a low-rank approximation to reconstruct the useful signals. Finally, the reconstructed IMFs are stacked together to obtain the denoised signals. Tests on synthetic and real data demonstrate that the proposed method, compared to the EEMD denoising method, could suppress more noise but filter out less useful signals in the FMCW Ladar signal denoising.
      PubDate: June 2020
      Issue No: Vol. 17, No. 6 (2020)
       
  • Calibration and Evaluation of a Circular Antenna Array for HF Radar Based
           on AIS Information
    • Authors: Zezong Chen;Lina Zhang;Chen Zhao;Jian Li;
      Pages: 988 - 992
      Abstract: High-frequency (HF) ground-wave radars employing compact antenna arrays are advantageous in practical applications because of their convenient deployment. However, the direction-of-arrival (DOA) estimation accuracy may significantly degrade in the presence of array errors for compact phased-array HF radars. Consequently, wind, wave, and current measurements would become unavailable for further applications. In this letter, an array calibration method is proposed for an HF radar system based on a circular antenna array. First, an array manifold model containing array errors is established. Second, a calibrated array manifold is obtained by fitting and interpolating the responses of ship echoes using a least squares fitting method. Finally, the calibrated array manifold and the noise subspace matrix are substituted into the multiple signal classification (MUSIC) method to estimate the DOA of each ship echo. The results indicate that this calibration method significantly reduces the DOA estimation errors with the root-mean-square errors of less than 10°.
      PubDate: June 2020
      Issue No: Vol. 17, No. 6 (2020)
       
  • Deformation Monitoring Using Ground-Based Differential SAR Tomography
    • Authors: Huiming Chai;Xiaolei Lv;Ping Xiao;
      Pages: 993 - 997
      Abstract: This letter presents the first differential synthetic aperture radar (SAR) tomography (D-TomoSAR) results using ground-based SAR (GB-SAR) data sets. GB-SAR provides an important deformation monitoring technology for glacier movements, landslides, and infrastructures because of its real-time monitoring capability compared with the airborne and spaceborne SAR sensors. A D-TomoSAR processing framework using region growing is proposed, which does not require the preliminary removal of atmospheric phase screen. The most reliable single-scatterers are identified as seeds, whereas the double-scatterers and unstable single-scatterers are resolved iteratively using region growing. First experimental results on 89 GB-SAR images over the Aletsch glacier, Switzerland, demonstrate the effectiveness of GB D-TomoSAR and the proposed method.
      PubDate: June 2020
      Issue No: Vol. 17, No. 6 (2020)
       
  • Oil Tank Extraction Based on Joint-Spatial Saliency Analysis for Multiple
           SAR Images
    • Authors: Libao Zhang;Congyang Liu;
      Pages: 998 - 1002
      Abstract: The lack of true color and the presence of background clutter reduce the accuracy rate of the saliency analysis for oil tank extraction in the synthetic aperture radar (SAR) images. This letter proposes a specially designed unsupervised method to extract oil tanks using the joint-spatial saliency analysis (JSSA) for multiple SAR images. First, the intrasaliency analysis is established on a saliency driven iterative clustering. This considers the spatial intensity and texture feature within a single image and suppresses most backgrounds. Second, the cospatial residual and the local grayscale statistics are considered independently in the intersaliency analysis. The common salient parts among the input series are extracted and used to overcome the problem of the lack of true color. Third, to make the fusion of the two kinds of saliency maps, the low-rank matrix is introduced. The weights of different maps are calculated and the saliency cues are integrated efficiently. Finally, after the statistics of the highlight points within the candidates, the location of the oil tanks is refined. The experiments show the superiority of the proposed method in both the pixel level and the geometric segmentation. The result of the JSSA model appears to improve the accuracy with fewer missing objects compared with the competing algorithms.
      PubDate: June 2020
      Issue No: Vol. 17, No. 6 (2020)
       
  • An Eigenvalue-Based Approach for Structure Classification in Polarimetric
           SAR Images
    • Authors: Filippo Biondi;Carmine Clemente;Danilo Orlando;
      Pages: 1003 - 1007
      Abstract: In this letter, we design a novel unsupervised architecture for automatic classification of the dominant polarization in polarimetric SAR images. To this end, we leverage the ideas developed in [1] and suitably exploit them to build a decision logic capable of recognizing the dominant scattering mechanism which characterizes the pixel under test. Specifically, we combine the original data to generate three different sets of reduced-size vectors, which feed dominant eigenvalues classifier based upon the model order selection rules. Then, the outputs of the latter classification schemes are exploited to infer, according to a specific criterion, the dominant polarization. The performance analysis is conducted on the measured data and points out the effectiveness of the newly proposed classification architecture also showing that information about the dominant polarization can be representative of the type of structure which gives raise to the dominant backscattering mechanism.
      PubDate: June 2020
      Issue No: Vol. 17, No. 6 (2020)
       
  • SAR Target Small Sample Recognition Based on CNN Cascaded Features and
           AdaBoost Rotation Forest
    • Authors: Fan Zhang;Yunchong Wang;Jun Ni;Yongsheng Zhou;Wei Hu;
      Pages: 1008 - 1012
      Abstract: Automatic target recognition (ATR) has made great progress with the development of deep learning. However, the target feature in synthetic aperture radar (SAR) image is not consistent with human vision, and the SAR training samples are always limited. These hard issues pose new challenges to the SAR ATR based on convolutional neural network (CNN). In this letter, we propose an improved CNN model to solve the limited sample issue via the feature augmentation and ensemble learning strategies. Normally, the high-level features that are more comprehensive and discriminative than the middle-level and low-level features are always employed for category discrimination. In order to make up the insufficient training features in the limited sample case, the cascaded features from optimally selected convolutional layers are concatenated to provide more comprehensive representation for the recognition. To take full advantage of these cascaded features, the ensemble learning-based classifier, namely, the AdaBoost rotation forest (RoF), is introduced to replace the original softmax layer to realize a more accurate limited sample recognition. Through the AdaBoost RoF method, not only are these features further enhanced by the rotation matrix but also a strong classifier is constructed by several weak classifiers with different adjusted weights. The experimental results on MSTAR data set show that the cascaded features and ensemble weak classifiers can fully exploit effective information in limited samples. Compared with the existing CNN method, the proposed method can improve the recognition accuracy by about 20% under the condition of ten training samples per class.
      PubDate: June 2020
      Issue No: Vol. 17, No. 6 (2020)
       
  • Investigation of Integrated Twin Corner Reflectors Designed for 3-D InSAR
           Applications
    • Authors: László Bányai;Lajos Nagy;Andrew Hooper;István Bozsó;Eszter Szűcs;Viktor Wesztergom;
      Pages: 1013 - 1016
      Abstract: There are potentially dangerous areas where InSAR technology cannot be applied routinely in the absence of proper persistent or distributed scatterers. Here, we planned and investigated the use of truncated trihedral triangle corner reflectors (CRs) oriented to ascending and descending directions for Sentinel-1 orbit, which were mounted on the optimal concrete basement including an additional global navigation satellite system (GNSS) adapter. These integrated benchmarks were designed to produce a signal-to-clutter ratio of about 100 (i.e., 20 dB). The mechanical design allows optimal orientation of the reflectors and resistance against dynamic effects. We investigated 1:5 models of the CRs and integrated benchmarks in an anechoic chamber to estimate the effects of truncation and the interference of the twin reflectors. The main effect of the interference is the asymmetric monostatic radar cross section, which can be neglected. The integrated benchmarks were also investigated in two recent landslide areas in Hungary using Sentinel-1 single look complex (SLC) scenes, which confirmed that the preliminary requirements can be met.
      PubDate: June 2020
      Issue No: Vol. 17, No. 6 (2020)
       
  • Sequential Estimation of Dynamic Deformation Parameters for SBAS-InSAR
    • Authors: Baohang Wang;Chaoying Zhao;Qin Zhang;Zhong Lu;Zhenhong Li;Yuanyuan Liu;
      Pages: 1017 - 1021
      Abstract: The synthetic aperture radar (SAR) interferometry (InSAR) has been developed for more than 20 years for historical surface deformation reconstruction. In particular, the onboard Sentinel-1/A/B satellite, newly planned NASA-ISRO SAR (NISAR), and Germany Tandem-L will continue to provide unprecedented SAR data with an increased number of acquisitions. However, processing of real-time SAR data has been experiencing challenges regarding the InSAR deformation parameter estimation over a long time with the small baseline subsets (SBAS) InSAR technology. We use sequential adjustment for the estimation of the deformation parameters, which uses Bayesian estimation theory under the least square criteria to inverse long time-series deformation dynamically. Finally, both simulated and real Sentinel-1A SAR data verify the performance of the sequential estimation. It can be regarded as an effective data processing tool in the coming era of SAR big data.
      PubDate: June 2020
      Issue No: Vol. 17, No. 6 (2020)
       
  • Complex-Valued 3-D Convolutional Neural Network for PolSAR Image
           Classification
    • Authors: Xiaofeng Tan;Ming Li;Peng Zhang;Yan Wu;Wanying Song;
      Pages: 1022 - 1026
      Abstract: Recently, convolutional neural network (CNN) has been successfully utilized in the terrain classification of polarimetric synthetic aperture radar (PolSAR) images. However, most CNN-based models are currently limited to handle 2-D real-valued inputs, and therefore, the physical scattering mechanism contained in the complex-valued (CV) covariance/coherency matrix cannot be extracted effectively. For this reason, CV 3-D CNN (CV-3D-CNN) is proposed for PolSAR image classification. Compared with CNN, CV-3D-CNN simultaneously extracts hierarchical features in both the spatial and the scattering dimensions by performing 3-D CV convolutions, thereby capturing the physical property from polarimetric adjacent resolution cells. Experiments on real PolSAR images classification demonstrate the effectiveness and the superiorities of CV-3D-CNN and illustrate that CV-3D-CNN can deal with scattering characteristic in a more complete manner and achieve better performance in PolSAR image classification.
      PubDate: June 2020
      Issue No: Vol. 17, No. 6 (2020)
       
  • Channel Compressive Aperture Synthesis
    • Authors: Tao Zheng;Fei Hu;Hao Hu;Peng Fu;
      Pages: 1027 - 1031
      Abstract: Aperture synthesis (AS) passive imaging technique has been proven effective in remote sensing for high resolution. Generally, a synthetic aperture radiometer needs the same number of channels as the antennas. As a consequence, the system complexity, volume, and cost increase rapidly as the size of the array expands. In this letter, the channel compressive AS (CCAS) method is proposed to reduce the receiver channels and correlators. Every channel connects to several different antennas by a selected connection network, and the visibilities are rebuilt from the cross correlation between output signals of the channels. Also, the principles of choosing connection network are discussed to guarantee the performance of the reconstructed brightness temperature (BT) images. Simulation results have shown the validation of the proposed method. It is of great application potential for very large-scale array in the future.
      PubDate: June 2020
      Issue No: Vol. 17, No. 6 (2020)
       
  • Neighboring Region Dropout for Hyperspectral Image Classification
    • Authors: Mercedes E. Paoletti;Juan M. Haut;Javier Plaza;Antonio Plaza;
      Pages: 1032 - 1036
      Abstract: Deep neural networks (DNNs) exhibit great performance in the task of hyperspectral image (HSI) classification. However, these models are usually overparameterized and require large amounts of training data in order to properly avoid the curse of dimensionality and the variability of spectral signatures, thus suffering from overfitting problems when very few training samples are available, due to poor generalization ability in this particular case. The traditional regularization dropout (DO) strategy has been shown to be effective in fully connected DNNs but not in convolutional-based ones. This is mainly due to the way these architectures manage the spatial information. In this letter, we introduce a new approach to improve the generalization of convolutional-based models for HSI classification. Specifically, we develop a neighboring region DO technique that selectively cuts off certain neighboring outputs, creating spatial dropped regions. Our experimental results with two well-known HSIs reveal that the newly proposed method helps to achieve better classification accuracy than the traditional DO strategy, with a low computational cost.
      PubDate: June 2020
      Issue No: Vol. 17, No. 6 (2020)
       
  • Hyperspectral Image Restoration via Local Low-Rank Matrix Recovery and
           Moreau-Enhanced Total Variation
    • Authors: Yanhong Yang;Jianwei Zheng;Shengyong Chen;Meiyu Zhang;
      Pages: 1037 - 1041
      Abstract: In this letter, we present a hyperspectral image (HSI) mixed-noise removal method named Moreau-enhanced total variation (TV) regularized local low-rank matrix recovery (LLRMTV). The rank-fixed matrix recovery is first adopted to separate the low-rank clean HSI patches from the sparse noise. Then, a Moreau-enhanced TV regularized image reconstruction strategy is utilized to ensure the piecewise smoothness of the reconstructed image from the low-rank patches. The proposed Moreau-enhanced TV restoration method involves a nonconvex penalty designed to maintain the convexity of the objective function. Moreover, the proposed model is integrated into an augmented Lagrange multiplier (ALM) algorithm to produce final results, leading to a complete HSI restoration framework. Examples of restoration illustrate the improvement over the typical TV regularization.
      PubDate: June 2020
      Issue No: Vol. 17, No. 6 (2020)
       
  • Hyperspectral Image Classification With Deep Metric Learning and
           Conditional Random Field
    • Authors: Yi Liang;Xin Zhao;Alan J. X. Guo;Fei Zhu;
      Pages: 1042 - 1046
      Abstract: To improve the classification performance in the context of hyperspectral image (HSI) processing, many works have been developed based on two common strategies, namely, the spatial–spectral information integration and the utilization of neural networks. However, both strategies typically require more training data than the classical algorithms, aggregating the shortage of labeled samples. In this letter, we propose a novel framework that organically combines the spectrum-based deep metric learning (DML) model and the conditional random field (CRF) algorithm. The DML model is supervised by the center loss to produce spectrum-based features that gather more tightly in Euclidean space within classes. The CRF with Gaussian edge potentials, which is first proposed for image segmentation tasks, is introduced to give the pixel-wise classification over the HSI by utilizing both the geographical distances between pixels and the Euclidean distances between the features produced by the DML model. The proposed framework is trained by spectral pixels at the DML stage and utilizes the half handcrafted spatial features at the CRF stage. This settlement alleviates the shortage of training data to some extent. Experiments on two real HSIs demonstrate the advantages of the proposed method in terms of both classification accuracy and computation cost.
      PubDate: June 2020
      Issue No: Vol. 17, No. 6 (2020)
       
  • Subspace-Based Target Detection in LWIR Hyperspectral Imaging
    • Authors: N. Acito;M. Moscadelli;M. Diani;G. Corsini;
      Pages: 1047 - 1051
      Abstract: This letter presents a new method to detect materials with known spectral emissivity in data acquired by longwave infrared hyperspectral sensors. The proposed approach differs from existing methods because it takes into account the uncertainty of the downwelling radiance. Such uncertainty is addressed assuming that the downwelling radiance spans a low-rank subspace whose basis matrix is learned, regardless of the analyzed image, from MODTRAN simulated spectra. The analysis, carried out over data simulated by considering different atmospheric conditions, surface temperatures, and emissivity spectra, shows the effectiveness of the proposed algorithm.
      PubDate: June 2020
      Issue No: Vol. 17, No. 6 (2020)
       
  • A 91-Channel Hyperspectral LiDAR for Coal/Rock Classification
    • Authors: Hui Shao;Yuwei Chen;Zhirong Yang;Changhui Jiang;Wei Li;Haohao Wu;Zhijie Wen;Shaowei Wang;Eetu Puttnon;Juha Hyyppä;
      Pages: 1052 - 1056
      Abstract: During the mining operation, it is a critical task in coal mines to significantly improve the safety by precision coal mining sorting and rock classification from different layers. It implies that a technique for rapidly and accurately classifying coal/rock in-site needs to be investigated and established, which is of significance for improving the coal mining efficiency and safety. In this letter, a 91-channel hyperspectral LiDAR (HSL) using an acousto-optic tunable filter (AOTF) as the spectroscopic device is designed, which operates based on the wide-spectrum emission laser source with a 5-nm spectral resolution to tackle this issue. The spectra of four-type coal/rock specimens collected by HSL are used to classify with three multi-label classifiers: naive Bayes (NB), logistic regression (LR), and support vector machine (SVM). Furthermore, we discuss and explore whether Gaussian fitting (GF) method and calibration with the reference whiteboard (RB) can enhance the classification accuracy. The experimental results show that the GF technique not only improves the accuracy of range measurement but also optimizes the classification performance using the spectra collected by the HSL. In addition, calibration with RB can improve classification accuracy as well. In addition, we also discuss methods to improve the calibration-free classification accuracy preliminarily.
      PubDate: June 2020
      Issue No: Vol. 17, No. 6 (2020)
       
  • FRF-Net: Land Cover Classification From Large-Scale VHR Optical Remote
           Sensing Images
    • Authors: Qianbo Sang;Yin Zhuang;Shan Dong;Guanqun Wang;He Chen;
      Pages: 1057 - 1061
      Abstract: Deep learning (DL) technique is widely applied in remote sensing (RS) applications because of its outstanding nonlinear feature extraction ability. However, with regard to the issues of large-scale and very high-resolution (VHR) land cover classification, multi-object distributions and clear appearance with large intraclass difference become challenges for refined pixelwise land cover mapping. Focusing on these problems, the letter proposed a novel encoding-to-decoding method called the full receptive field (RF) network (FRF-Net) based on two types of attention mechanism. In the FRF-Net, ResNet-101 is used as the basic backbone. Then, the ensemble feature is generated by encoding the high-level features based on the self-attention mechanism which could achieve full RF to capture long-range semantic. Next, the encoding result is decoded by the fusion attention mechanism combined with the low-level feature to produce a fusion feature which contains a refined semantic description for accurate land cover mapping. Extensive experiments based on the GID and ISPRS data sets proved that the proposed network outperforms the state-of-the-art methods. The FRF-Net achieved 66.71% and 64.17% of the mean of classwise Intersection over Union (mIOU) with smaller computation cost on ISPRS and GID, respectively.
      PubDate: June 2020
      Issue No: Vol. 17, No. 6 (2020)
       
  • Deep Learning for Multiple-Image Super-Resolution
    • Authors: Michal Kawulok;Pawel Benecki;Szymon Piechaczek;Krzysztof Hrynczenko;Daniel Kostrzewa;Jakub Nalepa;
      Pages: 1062 - 1066
      Abstract: Super-resolution (SR) reconstruction is a process aimed at enhancing the spatial resolution of images, either from a single observation, based on the learned relation between low and high resolution, or from multiple images presenting the same scene. SR is particularly important, if it is not feasible to acquire images at the desired resolution, while there are single or many observations available at lower resolution—this is inherent to a variety of remote sensing scenarios. Recently, we have witnessed substantial improvement in single-image SR attributed to the use of deep neural networks for learning the relation between low and high resolution. Importantly, deep learning has not been widely exploited for multiple-image super-resolution, which benefits from information fusion and in general allows for achieving higher reconstruction accuracy. In this letter, we introduce a new approach to combine the advantages of multiple-image fusion with learning the low-to-high resolution mapping using deep networks. The results of our extensive experiments indicate that the proposed framework outperforms the state-of-the-art SR methods.
      PubDate: June 2020
      Issue No: Vol. 17, No. 6 (2020)
       
  • A Convolutional Capsule Network for Traffic-Sign Recognition Using Mobile
           LiDAR Data With Digital Images
    • Authors: Haiyan Guan;Yongtao Yu;Daifeng Peng;Yufu Zang;Jianyong Lu;Aixia Li;Jonathan Li;
      Pages: 1067 - 1071
      Abstract: Traffic-sign recognition plays an important role in road transportation systems. This letter presents a novel two-stage method for detecting and recognizing traffic signs from mobile Light Detection and Ranging (LiDAR) point clouds and digital images. First, traffic signs are detected from mobile LiDAR point cloud data according to their geometrical and spectral properties, which have been fully studied in our previous work. Afterward, the traffic-sign patches are obtained by projecting the detected points onto the registered digital images. To improve the performance of traffic-sign recognition, we apply a convolutional capsule network to the traffic-sign patches to classify them into different types. We have evaluated the proposed framework on data sets acquired by a RIEGL VMX-450 system. Quantitative evaluations show that a recognition rate of 0.957 is achieved. Comparative studies with the convolutional neural network (CNN) and our previous supervised Gaussian–Bernoulli deep Boltzmann machine (GB-DBM) classifier also confirm that the proposed method performs effectively and robustly in recognizing traffic signs of various types and conditions.
      PubDate: June 2020
      Issue No: Vol. 17, No. 6 (2020)
       
  • Fourier Spectrum Guidance for Stripe Noise Removal in Thermal Infrared
           Imagery
    • Authors: Qingjie Zeng;Hanlin Qin;Xiang Yan;Huixin Zhou;
      Pages: 1072 - 1076
      Abstract: Thermal infrared (TIR) imaging has been an indispensable tool in surveillance and remote sensing fields due to the characteristic of this spectrum that enables the sensing system to detect relatively warm targets, especially in low-light conditions. However, the acquired TIR images often suffer from observable stripe noise, which reduces the target detectability to some extent. To remove the noise and keep the image details, this letter proposes a novel method that combines the spectral processing technology with the image-guidance mechanism. Specifically, the frequency band contaminated by stripe noise is corrected with the corresponding Fourier coefficients of a guided image, which can be estimated by existing smoothing methods. Various experiments on the simulated and real TIR images show high performance and efficiency of the proposed method. In addition, in the application of small target detection, it is demonstrated that local contrast between the target and its background is well maintained and the signal-to-clutter ratio is increased when our method is performed.
      PubDate: June 2020
      Issue No: Vol. 17, No. 6 (2020)
       
  • Feature Extraction of Hyperspectral Images Based on Deep Boltzmann Machine
    • Authors: Jiangong Yang;Yanhui Guo;Xili Wang;
      Pages: 1077 - 1081
      Abstract: High dimensionality and lack of labeled samples are the difficulties in feature extraction for hyperspectral image (HSI) processing. In this letter, a deep-learning-based feature extraction method is proposed. First, the guided filter is used to preprocess the original HSI data. The result data contain the joint spectral and spatial information of the objects. Second, the local receptive field and weight sharing are introduced into deep Boltzmann machine(DBM) to establish a novel feature extractor, called local-global DBM (LGDBM). The LGDBM has two advantages: 1) it can learn both the local and global features of the high-dimensional input data and 2) it has much fewer parameters than the DBM. Therefore, only a few labeled samples are needed for training, and the local and global spectral–spatial features are extracted intrinsically. A group of classification experiments are performed to evaluate the advantages of the feature extraction method.
      PubDate: June 2020
      Issue No: Vol. 17, No. 6 (2020)
       
  • Sparse-Adaptive Hypergraph Discriminant Analysis for Hyperspectral Image
           Classification
    • Authors: Fulin Luo;Liangpei Zhang;Xiaocheng Zhou;Tan Guo;Yanxiang Cheng;Tailang Yin;
      Pages: 1082 - 1086
      Abstract: Hyperspectral image (HSI) contains complex multiple structures. Therefore, the key problem analyzing the intrinsic properties of an HSI is how to represent the structure relationships of the HSI effectively. Hypergraph is very effective to describe the intrinsic relationships of the HSI. In general, Euclidean distance is adopted to construct the hypergraph. However, this method cannot effectively represent the structure properties of high-dimensional data. To address this problem, we propose a sparse-adaptive hypergraph discriminant analysis (SAHDA) method to obtain the embedding features of the HSI in this letter. SAHDA uses the sparse representation to reveal the structure relationships of the HSI adaptively. Then, an adaptive hypergraph is constructed by using the intraclass sparse coefficients. Finally, we develop an adaptive dimensionality reduction mode to calculate the weights of the hyperedges and the projection matrix. SAHDA can adaptively reveal the intrinsic properties of the HSI and enhance the performance of the embedding features. Some experiments on the Washington DC Mall hyperspectral data set demonstrate the effectiveness of the proposed SAHDA method, and SAHDA achieves better classification accuracies than the traditional graph learning methods.
      PubDate: June 2020
      Issue No: Vol. 17, No. 6 (2020)
       
  • Remote Sensing Image Classification via Improved Cross-Entropy Loss and
           Transfer Learning Strategy Based on Deep Convolutional Neural Networks
    • Authors: Ali Bahri;Sina Ghofrani Majelan;Sina Mohammadi;Mehrdad Noori;Karim Mohammadi;
      Pages: 1087 - 1091
      Abstract: Recently, deep convolutional neural networks (DCNNs) have gained great success in classifying aerial images, but in this area, the existence of the hard images, due to their innate characteristics, and weak focus of the network on them, due to the use of the cross-entropy (CE) loss, lead to reducing the accuracy of classification of aerial images. Moreover, since the last convolutional layer in a CNN has highly class-specific information, giving equal importance to all the channels causes to extract less discriminative features in comparison to weighting each of the channels adaptively. The fact that data labeling as well as creating ground truth on large data set is expensive is another point of concern in this regard. To address these problems, we have proposed a novel method for classification of aerial images. Our method includes proposing a new loss function, which enhances the focus of the network on hard examples by adding a new term to CE as a penalty term, bringing about the state-of-the-art results; designing a new multilayer perceptron (MLP) as a classifier, in which the used attention mechanism extracts more discriminative features by weighting each of the channels adaptively; and applying transfer learning strategy by adopting neural architecture search network mobile (NASNet Mobile) as a feature descriptor for the first time in the field of aerial images, which can mitigate the aforementioned costs. As indicated in the results, our proposed method outperforms the existing baseline methods and achieves state-of-the-art results on all three data sets.
      PubDate: June 2020
      Issue No: Vol. 17, No. 6 (2020)
       
  • EM Simulation-Aided Zero-Shot Learning for SAR Automatic Target
           Recognition
    • Authors: Qian Song;Hui Chen;Feng Xu;Tie Jun Cui;
      Pages: 1092 - 1096
      Abstract: A zero-shot learning (ZSL) method of automatic target recognition (ATR) in synthetic aperture radar (SAR) image is proposed to address the scenario, where no SAR sample of a particular target is available for training. To learn features of the unseen target, physics-based electromagnetic (EM) simulated images of the target under different azimuth angles are used as the training data instead. The challenge lies in the fact that the simulated image has a distinct but nonessential texture that the real images do not have and, thus, can easily result in an overfitted discriminator network. To overcome this problem, all images are first preprocessed with a nonessential factor suppression step and then fed into a pretrained convolutional neural network for feature extraction. Finally, the feature vector is fed into a trainable fully-connected network for classification. The low-dimensional embedding of feature vectors suggests that the nonessential factor suppression can align the simulated samples with true samples effectively. We propose the max-tolerability principle and averaged margin index for ZSL, which is a useful indicator for selecting optimal classifier. We validated our method on ten-type target recognition task on MSTAR data sets and achieved 91.93% accuracy on nine known targets and 79.08% accuracy on zero-shot target.
      PubDate: June 2020
      Issue No: Vol. 17, No. 6 (2020)
       
  • Frost Filtering Algorithm of SAR Images With Adaptive Windowing and
           Adaptive Tuning Factor
    • Authors: Zengguo Sun;Zhihua Zhang;Yuli Chen;Shigang Liu;Yunjing Song;
      Pages: 1097 - 1101
      Abstract: The traditional Frost filter is improved by the adaptive windowing and adaptive tuning factor for the synthetic aperture radar (SAR) images in this letter. The proposed double-adaptive Frost filter simultaneously makes the window size and the tuning factor adaptively adjusted in terms of the regional characteristics, leading to an effective balance between speckle suppression and edge preservation. The despeckling experiments on the simulated and real SAR images demonstrate that in comparison to the Lee filter, the Gamma maximum a posteriori (MAP) filter, the traditional Frost filter, and the Frost filter only with the adaptive tuning factor, the double-adaptive Frost filter sufficiently suppresses the speckle in homogeneous regions and in edge regions and effectively preserves the edges and fine details.
      PubDate: June 2020
      Issue No: Vol. 17, No. 6 (2020)
       
  • Correction to “Seismic Time-Frequency Analysis via Adaptive Mode
           Separation-Based Wavelet Transform”
    • Authors: Fangyu Li;Bangyu Wu;Naihao Liu;Ying Hu;Hao Wu;
      Pages: 1102 - 1102
      Abstract: In [1], the grant number in the first footnote for the National Postdoctoral Program for Innovative Talents should be BX20190279.
      PubDate: June 2020
      Issue No: Vol. 17, No. 6 (2020)
       
  • Correction to “The Improved Empirical Wavelet Transform and Applications
           to Seismic Reflection Data”
    • Authors: Naihao Liu;Zhen Li;Fengyuan Sun;Qian Wang;Jinghuai Gao;
      Pages: 1103 - 1103
      Abstract: In [1], the grant number in the first footnote for the National Postdoctoral Program for Innovative Talents should be BX20190279.
      PubDate: June 2020
      Issue No: Vol. 17, No. 6 (2020)
       
  • Introducing IEEE Collabratec
    • Pages: 1104 - 1104
      PubDate: June 2020
      Issue No: Vol. 17, No. 6 (2020)
       
  • Together, we are advancing technology
    • Pages: 1105 - 1105
      PubDate: June 2020
      Issue No: Vol. 17, No. 6 (2020)
       
  • IEEE Open Access
    • Pages: 1106 - 1106
      PubDate: June 2020
      Issue No: Vol. 17, No. 6 (2020)
       
 
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
 


Your IP address: 3.231.220.225
 
Home (Search)
API
About JournalTOCs
News (blog, publications)
JournalTOCs on Twitter   JournalTOCs on Facebook

JournalTOCs © 2009-