Journal Cover
IEEE Geoscience and Remote Sensing Letters
Journal Prestige (SJR): 1.486
Citation Impact (citeScore): 4
Number of Followers: 184  
 
  Hybrid Journal Hybrid journal (It can contain Open Access articles)
ISSN (Print) 1545-598X
Published by IEEE Homepage  [191 journals]
  • IEEE Geoscience and Remote Sensing Letters publication information
    • Abstract: Presents a listing of the editorial board, board of governors, current staff, committee members, and/or society editors for this issue of the publication.
      PubDate: Sept. 2019
      Issue No: Vol. 16, No. 9 (2019)
       
  • IEEE Geoscience and Remote Sensing Letters information for authors
    • Abstract: These instructions give guidelines for preparing papers for this publication. Presents information for authors publishing in this journal.
      PubDate: Sept. 2019
      Issue No: Vol. 16, No. 9 (2019)
       
  • IEEE Geoscience and Remote Sensing Letters Institutional Listings
    • Abstract: Presents a listing of institutions relevant for this issue of the publication.
      PubDate: Sept. 2019
      Issue No: Vol. 16, No. 9 (2019)
       
  • Deep Learning Architecture for Estimating Hourly Ground-Level PM2.5 Using
           Satellite Remote Sensing
    • Authors: Yibo Sun;Qiaolin Zeng;Bing Geng;Xinwen Lin;Bilige Sude;Liangfu Chen;
      Pages: 1343 - 1347
      Abstract: The prediction of PM2.5 concentration is a canonical predictive challenge due to the distribution of $PM_{2.5}$ appears serious spatiotemporal variability at multiple scales. Currently, using satellite-based remote sensing data to estimate ground-level PM2.5 is a promising method for providing spatiotemporal continuous information of PM2.5. In this letter, we proposed a deep neural network (DNN)-based PM2.5 prediction model to capture the spatiotemporal variability of ground-level PM2.5 using the remote sensing aerosol optical depth (AOD) data from the Himawari-8 satellite along with the conventional meteorological observation variables (denoted as PM25-DNN). The PM25-DNN model was trained and tested using the data from Beijing–Tianjin–Hebei region of China in 2017, and we compared the prediction performance between the PM25-DNN and the current state-of-the-art methods in this field. The results show that the PM25-DNN outperforms the other models with the cross-validated coefficient of determination ( $text{R}^{2}$ ), root-mean-square error (RMSE), mean prediction error (MPE), and relative prediction error (RPE) were 0.84, $19.9~mu text{g}/text{m}^{3}$ , $11.89~mu text{g}/text{m}^{3}$ , and 41.21%, respectively. Then, the trained PM25-DNN model was applied to estimate the hourly gridded PM2.5 with 1-km spatial resolution. Our results indicate that the DNN architecture can capture the essential spatiotemporal distribution associated with PM2.5 only using AOD data and conventional meteorological observational variables without more handcrafted fe-tures. The proposed PM25-DNN model can greatly improve the accuracy of PM2.5 estimation, and it provides a new perspective for PM2.5 monitoring using end-to-end deep learning method.
      PubDate: Sept. 2019
      Issue No: Vol. 16, No. 9 (2019)
       
  • Application of an STFT-Based Seismic Even and Odd Decomposition Method for
           Thin-Layer Property Estimation
    • Authors: Jian Zhou;Jing Ba;John P. Castagna;Qiang Guo;Cun Yu;Ren Jiang;
      Pages: 1348 - 1352
      Abstract: For seismically thin-reservoir layers, variations in rock properties may not be directly linked to seismic amplitude due to the wave interference of layer top and base reflections. In addition, thin-layer reflection signal locally has a different phase from that of the signal wavelet. Signal even and odd components can be considered as amplitudes at different signal phases, which may have a different sensitivity to the variations in thin layer and surrounding layer properties. A novel extension of the spectral decomposition concept is proposed that decomposes seismic signal into its even and odd components via the short-time Fourier transform. Amplitude attributes for the original signal and even and odd part components are compared for their ability to restore the correct “amplitude-layer property” correlation without resolving the thin layer. Numerical modeling analysis shows that amplitude at peak frequency (APF) of the seismic data odd component APF (OAPF) is more sensitive to thin-reservoir property change compared to the conventional APF and even component APF attributes. When applied in analyzing real seismic data in a tight-dolomite reservoir, conventional APF and conventional acoustic impedance inversion did not provide a correct relationship to porosity variations. Meanwhile, the OAPF attribute responds well to porosity measured in boreholes. This suggests that the interpretability of amplitude attributes in thin layers can be improved by signal even and odd decomposition.
      PubDate: Sept. 2019
      Issue No: Vol. 16, No. 9 (2019)
       
  • Pseudoinvariant Feature Selection Using Multitemporal MAD for Optical
           Satellite Images
    • Authors: Bo-Yi Lin;Zhi-Jia Wang;Muhammad Aldila Syariz;Lino Garda Denaro;Chao-Hung Lin;
      Pages: 1353 - 1357
      Abstract: Pseudoinvariant features (PIFs) are ground objects with invariant or near-invariant reflectance during data acquisition. The extraction of PIFs from optical satellite images generally plays a crucial role in relative radiometric normalization (RRN) and landcover change detection. Previous studies extract PIFs from bitemporal images while can generally obtain satisfactory results. However, they do not fully consider the problem of inconsistent PIF selection caused by performing pairwise PIF selection on more than two images. To decrease this inconsistency problem, a novel method called multitemporal and multivariate alteration detection (MMAD) is proposed. This method is based on a weighted generalized canonical correlation analysis, which solves canonical coefficients for multivariable and multitemporal data, thereby resulting in consistent PIF selection and RRN. In addition, a new weighting scheme based on pixel similarity, image quality, and temporal coherence is introduced into MMAD to reduce the sensitivity of PIF selection to landcover changes and to stably distinguish PIFs from non-PIFs. Qualitative and quantitative analyses of several multitemporal images acquired by Satellite Pour l’Observation de la Terre 5 are conducted to evaluate the proposed method. Experimental results demonstrate the superiority of the proposed method over related methods in terms of extracted PIF quality and radiometric consistency, particularly for image sequences with considerable landcover changes.
      PubDate: Sept. 2019
      Issue No: Vol. 16, No. 9 (2019)
       
  • Attitude Jitter Compensation for Remote Sensing Images Using Convolutional
           Neural Network
    • Authors: Zhang Zhaoxiang;Akira Iwasaki;Guodong Xu;
      Pages: 1358 - 1362
      Abstract: Attitude jitter of satellites and unmanned aerial vehicle (UAV) platforms is a problem that degenerates the imaging quality in high-resolution remote sensing. This letter proposes a deep learning architecture that automatically learns essential scene features from a single image to estimate the attitude jitter, which is used to compensate deformed images. The proposed methodology consists of a convolutional neural network and a jitter compensation model. The neural network analyzes the deformed images and generates the attitude jitter vectors in two directions, which are utilized to correct the images through interpolation and resampling. The PatternNet and the small UAV data sets are introduced to train the neural network and to validate its effectiveness and accuracy. The compensation results on distorted remote sensing images obtained by satellites and UAVs reveal that the image distortion due to attitude jitter is clearly reduced and that the geometric quality is effectively improved. Compared to the existing methods that primarily rely on sensor data or parallax observation, no auxiliary information is required in our framework.
      PubDate: Sept. 2019
      Issue No: Vol. 16, No. 9 (2019)
       
  • Remote Sensing Image Registration Based on Modified SIFT and Feature Slope
           Grouping
    • Authors: Herng-Hua Chang;Guan-Long Wu;Mao-Hsiung Chiang;
      Pages: 1363 - 1367
      Abstract: In feature-based remote sensing image registration, the scale-invariant feature transform (SIFT) algorithm has been one of the most popular solutions. However, it is still a challenge to possess an appropriate amount of correct matches while eliminating mismatches. In this letter, inspired by SIFT, an accurate and robust feature matching framework based on feature slope grouping (FSG) for remote sensing image registration is proposed. Our FSG-SIFT algorithm consists of four major phases: modified SIFT, feature slope computation, feature point grouping, and outlier removal and transformation. Specifically, the random sample consensus is adopted to refine the matches followed by the affine transform. The proposed remote sensing image registration algorithm has been validated on a wide variety of high-resolution orthoimagery data. Experimental results with multispectral and multitemporal images suggested that this new image registration algorithm well improved the feature matching accuracy with better registration performance over five state-of-the-art methods.
      PubDate: Sept. 2019
      Issue No: Vol. 16, No. 9 (2019)
       
  • Instance Segmentation of Auroral Images for Automatic Computation of Arc
           Width
    • Authors: Chuang Niu;Qiuju Yang;Shenghan Ren;Haihong Hu;Desheng Han;Ze-Jun Hu;Jimin Liang;
      Pages: 1368 - 1372
      Abstract: The width of auroral arc is one of the most important factors in understanding and examining its physical mechanisms. In this letter, we propose a fully automatic method for computing the width of auroral arcs based on the instance segmentation of auroral images. To accurately detect and segment auroral arcs with oriented bounding boxes, we adapt a state-of-the-art instance segmentation model, Mask region-based convolutional neural network, by designing a two-stage inference process combined with an indispensable random rotation training strategy and designing an effective feature extraction architecture. Given the segmented masks of individual auroral arcs, we present a method for computing the arc width automatically. In our experiments, the instance segmentation model achieves 86.8% of mean average precision on the human-labeled data set. By automatically evaluating the width of 29 938 detected auroral arcs in 18 417 auroral arc images, we obtain a similar arc width distribution to that evaluated by the semiautomatic approach, which demonstrates the effectiveness of our proposed method.
      PubDate: Sept. 2019
      Issue No: Vol. 16, No. 9 (2019)
       
  • Fast Resistivity Imaging of Transient Electromagnetic Using ANN
    • Authors: Shanqiang Qin;Yao Wang;Zhengyu Xu;Xian Liao;Longhuan Liu;Zhihong Fu;
      Pages: 1373 - 1377
      Abstract: Transient electromagnetic (TEM) soundings are being increasingly used in engineering applications of environmental and regional surveys and shallow metal detection. Efficient and real time of the processing of the observed TEM data is the trend for the engineering geophysical prospecting and detection instrument in modern times. This letter presents a fast resistivity imaging method of TEM using artificial neural networks. The input–output mapping relations of neural networks are established based on the TEM response characteristics under different transmitter loop devices. The built network could map the recorded TEM data and quickly obtain the resistivity image. The proposed method offers accuracy and fast computation for resistivity imaging, and only 9.003 s costs for the calculation of 142 measured points’ data. Feasibility and technical attractiveness of the proposed method in fast resistivity imaging of TEM mean that it is well suited for instantaneous of survey results to a client. The proposed TEM imaging method can be used in real time so that the recorded TEM data can be calculated without retraining, which avoids time-consuming iteration and inversion computation.
      PubDate: Sept. 2019
      Issue No: Vol. 16, No. 9 (2019)
       
  • Filtering out Antenna Effects From GPR Data by an RBF Neural Network
    • Authors: Jing Wei Zhang;Sheng Bo Ye;Hai Liu;Li Yi;Guang You Fang;
      Pages: 1378 - 1382
      Abstract: When sounding pavement layers using ground penetrating radar (GPR), antenna effects including dispersion and multiple reflections usually degrade the vertical resolution. In far-field conditions, these effects can be analytically filtered out by a linear method. However, for near-field operation, the antenna model tends to be nonlinear, and thus, these unwanted effects cannot be analytically removed anymore. In this letter, a method based on the radial basis function (RBF) neural network is proposed to filter out antenna effects under near-field conditions. A well-developed GPR model is used to simulate the input training data, and the corresponding zero-offset Green’s function is calculated as the desired output for each training data. The trained RBF network is applied to the simulated and measured data. The results show that the proposed method is effective in filtering out the antenna effects and increasing the vertical resolution of GPR.
      PubDate: Sept. 2019
      Issue No: Vol. 16, No. 9 (2019)
       
  • An Interferometric MIMO Radar for Bridge Monitoring
    • Authors: Massimiliano Pieraccini;Lapo Miccinesi;
      Pages: 1383 - 1387
      Abstract: The authors propose an interferometric multiple-input multiple-output radar specifically designed for monitoring/testing bridges. It makes use of compressive sensing and synthetic aperture radar techniques for providing coherent images of its field of view. The radar prototype has been tested in controlled environment and in operative conditions during the static test of a pedestrian bridge.
      PubDate: Sept. 2019
      Issue No: Vol. 16, No. 9 (2019)
       
  • Cross-Spectral Metric Smoothing-Based GIP for Space-Time Adaptive
           Processing
    • Authors: Huadong Yuan;Hong Xu;Keqing Duan;Wenchong Xie;Yongliang Wang;
      Pages: 1388 - 1392
      Abstract: As training samples are not always target-free in heterogeneous environments, the generalized inner product (GIP) method is usually used to censor the training samples contaminated by targetlike signals (outliers). However, the GIP method incurs significant performance degradation when there are multiple outliers in the original training sample set. To deal with this problem, this letter proposes a novel GIP method. First, the principal component, which results in performance degradation of the GIP method, is obtained via extracting the maximum of cross-spectral metric (CSM) between the target steering vector and the eigenspace of the GIP’s test covariance matrix (TCM). Second, taking a sample covariance matrix (SCM) as the initial TCM, a new TCM is reconstructed by setting the eigenvalue of SCM that corresponds to the largest CSM between the target steering vector and the SCM’s eigenspace to be noise variance. Finally, the new TCM is combined with the conventional GIP method to form a novel GIP statistic to eliminate the contaminated training samples. Numerical results with both simulated and mountain-top data confirm the improvement of the proposed method.
      PubDate: Sept. 2019
      Issue No: Vol. 16, No. 9 (2019)
       
  • A Bayesian Joint Decorrelation and Despeckling of SAR Imagery
    • Authors: Caifeng Wang;Linlin Xu;David A. Clausi;Alexander Wong;
      Pages: 1393 - 1397
      Abstract: Despeckling of synthetic aperture radar (SAR) is a known research challenge. A novel solution to this problem has been developed and evaluated via an iterative maximum a posterior estimation incorporating a Bayesian joint decorrelation and despeckling based on a correlation model. This model realistically explores the physical correlation process of SAR speckle noise and is determined automatically via Bayesian estimation in the log-Fourier domain. A patchwise computation is used to account for the spatial nonstationarity associated with SAR image data. The proposed approach is compared to the existing despeckling techniques using both simulated and real SAR data, and the experimental results demonstrate the improvement in preserving the structural details while suppressing speckle noise.
      PubDate: Sept. 2019
      Issue No: Vol. 16, No. 9 (2019)
       
  • C-Band Right-Circular Polarization Ocean Wind Retrieval
    • Authors: Guosheng Zhang;Biao Zhang;William Perrie;Yijun He;Haiyan Li;He Fang;Shahid Khurshid;Kerri Warner;
      Pages: 1398 - 1401
      Abstract: We report an investigation of ocean-surface wind speed retrieval from C-band RADARSAT Constellation Mission (RCM) Synthetic Aperture Radar (SAR) images using a new channel of coright-circular polarization (RR-pol) in compact polarimetry (CP) option. The analysis of simulated RCM quad-polarized CP SAR data and collocated in situ buoy measurements suggests that the RR-pol is much less sensitive to wind directions than the other three polarizations in the CP option. A method is proposed for the RR-pol radar signal as a function of wind speed and incidence angle. We demonstrate that C-band RR-pol has the potential for ocean high wind retrieval, especially for cyclone studies.
      PubDate: Sept. 2019
      Issue No: Vol. 16, No. 9 (2019)
       
  • Surface Water Microwave Product Series Version 3: A Near-Real Time and
           25-Year Historical Global Inundated Area Fraction Time Series From Active
           and Passive Microwave Remote Sensing
    • Authors: Katherine Jensen;Kyle Mcdonald;
      Pages: 1402 - 1406
      Abstract: This letter summarizes substantial modifications made to the Surface Water Microwave Product Series (SWAMPS), a coarse-resolution (~25 km) global inundated area fraction data record derived from active and passive microwave remote sensing. SWAMPS is the most temporally dense, long-term record of global surface water dynamics publicly available today. This update improves upon the original release by: 1) incorporating a customized, consistent resampling and assembly of the Special Sensor Microwave Imager and Special Sensor Microwave Imager Sounder brightness temperature record; 2) eliminating signal contamination from ocean waters along coastlines; 3) inclusion of permanent surface waters as a component of the data record; and 4) reducing anomalous inundation retrievals over arid and semiarid regions. This update provides for the enhanced scientific utility of the full 25+ years of data records. Remaining uncertainties in the surface water fraction retrievals are principally in areas with bare, sandy surface cover and in areas with dense vegetation cover that diminishes radiometric sensitivity to surface water. This data record and associated documentation are freely available through the Alaska Satellite Facility, Fairbanks, AK, USA.
      PubDate: Sept. 2019
      Issue No: Vol. 16, No. 9 (2019)
       
  • Assessment of Soil Moisture SMAP Retrievals and ELBARA-III Measurements in
           a Tibetan Meadow Ecosystem
    • Authors: Donghai Zheng;Xin Wang;Rogier van der Velde;Mike Schwank;Paolo Ferrazzoli;Jun Wen;Zuoliang Wang;Andreas Colliander;Rajat Bindlish;Zhongbo Su;
      Pages: 1407 - 1411
      Abstract: This letter presents the results evaluating retrievals of liquid water content ( $theta _{mathrm {liq}}$ ) performed with a zero-order radiative transfer ( $tau $ – $omega$ ) model under frozen and thawed soil conditions from Soil Moisture Active Passive (SMAP) and ELBARA-III brightness temperature ( $T_{mathrm {B}}^{p}$ ) measurements collected over a Tibetan meadow ecosystem. A good agreement is found between time series of the SMAP and ELBARA-III measured $T_{mathrm {B}}^{p}$ resulting in a Pearson product-moment coefficient ( $R$ ) larger than 0.87. Differences noted between the two data sets can be associated with discrepancies in $theta _{mathrm {liq}}$ measured in the specific footprints, whereby the SMAP measurements are best explained by the in situ $theta _{mathrm {liq}}$ . Furthermore, the in situ $theta _{mathrm {liq}}$ has a better agreement with the horizontally polarized SMAP and ELBARA-III measurements ( $T_{mathrm {B}}^{mathrm {H}}$ ) in the cold season, whereas the vertically polarized measurements ( $T_{mathrm {B}}^{mathrm {V}}$ ) are better correlated with $the-a _{mathrm {liq}}$ in the warm season. With the implementation of new vegetation and surface roughness parameterizations for the $tau $ – $omega $ model, the dynamics of in situ $theta _{mathrm {liq}}$ is better reproduced by corresponding retrievals for both frozen and thawed soil conditions, leading to the reduction in the unbiased root-mean-square error (ubRMSE) by more than 31% in comparison with these retrievals using SMAP default parameterizations. Notably, the single-channel algorithm configured with the new parameterizations using SMAP $T_{mathrm {B}}^{mathrm {V}}$ measured during the ascending overpass provides the best $theta _{mathrm {liq}}$ retrievals with a ubRMSE of 0.035 $text{m}^{3}cdot text{m}^{-3}$ that is well within the SMAP mission requirements.
      PubDate: Sept. 2019
      Issue No: Vol. 16, No. 9 (2019)
       
  • Deep Hashing Neural Networks for Hyperspectral Image Feature Extraction
    • Authors: Leyuan Fang;Zhiliang Liu;Weiwei Song;
      Pages: 1412 - 1416
      Abstract: Recently, deep learning has been recognized as a powerful tool to extract hierarchical features of hyperspectral images (HSIs). The existing deep learning-based methods exploit label information of land classes as the supervised information to train deep networks. However, considering that HSIs exhibit very complex spectral–spatial characteristic, e.g., the large intraclass variations and small interclass variations, these semantic information (i.e., label information)-based deep networks may not effectively cope with the above problem. In this letter, we propose a novel deep model, named deep hashing neural network (DHNN), to learn similarity-preserving deep features (SPDFs) for HSI classification. First, a well-pretrained network is introduced to simultaneously extract features of a pair of input samples. Second, a novel hashing layer is inserted after the last fully connected layer to transfer the real-value features into binary features, which can significantly speed up the computation for feature distance. Then, a loss function is elaborately designed to minimize the feature distance of similar pairs and maximize the feature distance of dissimilar pairs in Hamming space. Finally, the SPDF extracted by propagating the samples through the trained DHNN are fed into a support vector machine (SVM) classifier for HSI classification. Experimental results on two real HSIs demonstrate that the proposed feature extraction method in conjunction with a linear SVM classifier outperforms other feature extraction methods and competitive classifiers.
      PubDate: Sept. 2019
      Issue No: Vol. 16, No. 9 (2019)
       
  • Frequency Domain-Based Features for Hyperspectral Image Classification
    • Authors: Ke Wang;Bin Yong;Zhaohui Xue;
      Pages: 1417 - 1421
      Abstract: Frequency spectrum has been proven to have the potential in hyperspectral image classification and ground object recognition. The characteristics of the frequency spectrum, such as dc component, descent rate, and spectrum oscillation, are different from each other; thus, based on the discrepancy in the frequency spectrum, 14 frequency spectrum features, including frequency spectrum integration area, spectral centroid ( $C_{k}$ and $C_{k-textrm {log}}$ ), spectral rolloff ( $C_{t}$ ), spectral flux, spectral gradient of peaks, and valley, number of crosspoint, and first three peaks and valleys position, are proposed. To evaluate the performance of the proposed features, two commonly used hyperspectral images were taken as experimental data sets. Then, we employed three frequently used classification methods to perform the experiment based on spectral-only and frequency-spectral features. The results show that the proposed features can distinctly prompt the classification accuracies by combining the original spectral features.
      PubDate: Sept. 2019
      Issue No: Vol. 16, No. 9 (2019)
       
  • Hyperspectral Image Classification Using Kernel Fused Representation via a
           Spatial-Spectral Composite Kernel With Ideal Regularization
    • Authors: Guichi Liu;Lin Qi;Yun Tie;Long Ma;
      Pages: 1422 - 1426
      Abstract: To adequately exploit spectral, spatial, and label information of the given hyperspectral data, a kernel fused representation-based classifier via a spatial-spectral composite kernel with ideal regularization (CKIR) method is proposed in this letter. Specifically, the learned CKIR is embedded into the kernel version of representation-based classifiers, i.e., kernel sparse representation-based classifier (KSRC) and kernel collaborative representation-based classifier (KCRC), to obtain more discriminative representation coefficients. Furthermore, to benefit from both sparsity and data correlation in representation, KSRC and KCRC are combined in the CKIR-based residual domain to further enhance the discriminative ability of the proposed classifier. The experimental results on two real hyperspectral images demonstrate that the proposed method outperforms the other state-of-the-art classifiers.
      PubDate: Sept. 2019
      Issue No: Vol. 16, No. 9 (2019)
       
  • Endmember Extraction Using Minimum Volume and Information Constraint
           Nonnegative Matrix Factorization
    • Authors: Yue Shi;Hongqi Wang;Xinyi Guo;Guangluan Xu;
      Pages: 1427 - 1431
      Abstract: Simplex volume is the most commonly used parameter for nonnegative matrix factorization (NMF)-based endmember estimation methods, and one of the most popular methods is the NMF method with minimum volume constraint (MVC-NMF). However, when outliers exist in the image, MVC-NMF tends to extract them as endmembers. In most cases, those outlier endmembers could be either physically meaningless or not representative enough for prevalent land covers. So how to extract prevalent land covers instead of outliers as endmembers is a very challenging question. In this letter, we propose a new NMF method with the dual constraints of simplex volume and information content, named the “minimum volume and information constraint NMF” (MIVC-NMF). The method is based on the following facts: when a real endmember is replaced by an outlier, it will cause some pixels containing the replaced endmember not to locate within the endmember hyperplane, and the overall information content contained in the endmember hyperplane will be reduced. The experimental results based on the simulated and real data show that the proposed method outperforms several other commonly used endmember extraction approaches.
      PubDate: Sept. 2019
      Issue No: Vol. 16, No. 9 (2019)
       
  • Remote Sensing Single-Image Superresolution Based on a Deep Compendium
           Model
    • Authors: J. M. Haut;M. E. Paoletti;R. Fernandez-Beltran;J. Plaza;A. Plaza;Jun Li;
      Pages: 1432 - 1436
      Abstract: This letter introduces a novel remote sensing single-image superresolution (SR) architecture based on a deep efficient compendium model. The current deep learning-based SR trend stands for using deeper networks to improve the performance. However, this practice often results in the degradation of visual results. To address this issue, the proposed approach harmonizes several different improvements on the network design to achieve state-of-the-art performance when superresolving remote sensing imagery. On the one hand, the proposal combines residual units and skip connections to extract more informative features on both local and global image areas. On the other hand, it makes use of parallelized $1times 1$ convolutional filters (network in network) to reconstruct the superresolved result while reducing the information loss through the network. Our experiments, conducted using seven different SR methods over the well-known UC Merced remote sensing data set, and two additional GaoFen-2 test images, show that the proposed model is able to provide competitive advantages.
      PubDate: Sept. 2019
      Issue No: Vol. 16, No. 9 (2019)
       
  • A Mixture Likelihood Model of the Anisotropic Gaussian and Uniform
           Distributions for Accurate Oblique Image Point Matching
    • Authors: Xunwei Xie;Yongjun Zhang;Xiang Wang;Daifeng Peng;
      Pages: 1437 - 1441
      Abstract: In this letter, we propose a mixture likelihood model for accurate oblique image point matching. The basic prior assumption is that the noises are anisotropic with zero mean and different covariances in $x$ - and $y$ -directions for inliers, while the outliers have uniform distribution, which is more suitable for tilted scenes or viewpoint changes. Furthermore, the oblique image point matching problem is formulated as an improved maximum a posteriori (IMAP) estimation of a Bayesian model. In this model, based on the vector field interpolation framework, we combined the mixture likelihood model and our previous adaptive image mismatch removal method, where a two-order term of the regularization coefficient is introduced into the regularized risk function, and a parameter self-adaptive Gaussian kernel function is imposed to construct the regularization term. Subsequently, the expectation–maximization algorithm is utilized to solve the IMAP estimation, in which all the latent variances are able to obtain excellent estimation. Experimental results on real data sets verified that our method was superior to some similar methods in terms of precision and also had better self-adaptability characteristic than some hypothesis-and-verify methods. More experiments on viewpoint changes demonstrated our method’s effectiveness without loss of precision–recall tradeoffs, besides significant efficiency improvement.
      PubDate: Sept. 2019
      Issue No: Vol. 16, No. 9 (2019)
       
  • A Local Contrast Method Combined With Adaptive Background Estimation for
           Infrared Small Target Detection
    • Authors: Jinhui Han;Sibang Liu;Gang Qin;Qian Zhao;Honghui Zhang;Nana Li;
      Pages: 1442 - 1446
      Abstract: Local contrast has been proven as an efficient method for infrared (IR) small target detection, but existing local contrast algorithms just directly choosing the neighboring area of a current position as the reference when calculating the local contrast of the current position, which may bring an inaccurate result. Meanwhile, existing algorithms are either ratio form or difference form, they cannot effectively enhance true target and suppress all the types of complex backgrounds simultaneously. In this letter, a new local contrast scheme that introduces the adaptive background estimation is proposed to provide a more accurate reference, and the multidirectional 2-D least mean square (MDTDLMS) algorithm that is more suitable for small target detection is presented. Then, a new ratio-difference joint local contrast measure (RDLCM) is proposed between raw IR image and the MDTDLMS result to enhance true small target and suppress all the types of complex backgrounds simultaneously. Experimental results show that the proposed MDTDLMS-RDLCM algorithm can achieve a good detection performance for different types of backgrounds and targets.
      PubDate: Sept. 2019
      Issue No: Vol. 16, No. 9 (2019)
       
  • Ground and Top of Canopy Extraction From Photon-Counting LiDAR Data Using
           Local Outlier Factor With Ellipse Searching Area
    • Authors: Bowei Chen;Yong Pang;Zengyuan Li;Hao Lu;Luxia Liu;P. R. J. North;J. A. B. Rosette;
      Pages: 1447 - 1451
      Abstract: The Ice, Cloud, and land Elevation Satellite (ICESat)-2 is the next generation of National Aeronautics and Space Administration (NASA)’s ICESat mission launched in September 2018. The new photon-counting LiDAR onboard ICESat-2 introduces new challenges to the estimation of forest parameters and their dynamics, the greatest being the abundant photon noise appearing in returns from the atmosphere and below the ground. To identify the potential forest signal photons, we propose an approach by using a local outlier factor (LOF) modified with ellipse searching area. Six test data sets from two types of photon-counting LiDAR data in the USA are used to test and evaluate the performance of our algorithm. The classification results for noise and signal photons showed that our approach has a good performance not only in lower noise rate with relatively flat terrain surface but also works even for a quite high noise rate environment in relatively rough terrain. The quantitative assessment indicates that the horizontal ellipse searching area gives the best results compared with the circle or vertical ellipse searching area. These results demonstrate our methods would be useful for ICESat-2 vegetation study.
      PubDate: Sept. 2019
      Issue No: Vol. 16, No. 9 (2019)
       
  • Sensor-Based Optimization of Terrestrial Laser Scanning Measurement Setup
           on GPU
    • Authors: Mikhail Giorgini;Stefano Marini;Riccardo Monica;Jacopo Aleotti;
      Pages: 1452 - 1456
      Abstract: A novel formulation of the set cover problem is presented to find the optimal placement of the scan stations in a terrestrial laser scanning survey. The problem is formulated in 2-D by including sensor-based constraints such as coverage and overlap. The coverage constraint ensures a minimum density of horizontal scan lines on the ground. The overlap constraint enables automatic scan alignment and registration. The optimization problem takes into account both environment occlusions and a maximum allowed incidence angle of the laser beams. The adopted laser model includes fixed parameters such as laser height, angular resolution, field of view, and minimum and maximum sensor range. The sensor placement problem is solved using a numerical approach implemented on graphics processing unit (GPU). Thanks to the GPU acceleration, experiments have been performed in large-scale environments with internal structures.
      PubDate: Sept. 2019
      Issue No: Vol. 16, No. 9 (2019)
       
  • $Q$+ +Estimation+by+Combining+ISD+With+LSR+Method+Based+on+Shaping-Regularized+Inversion&rft.title=IEEE+Geoscience+and+Remote+Sensing+Letters&rft.issn=1545-598X&rft.date=2019&rft.volume=16&rft.spage=1457&rft.epage=1461&rft.aulast=Wei;&rft.aufirst=Cong&rft.au=Cong+Luo;Guantan+Huang;Xiangyang+Li;Qing+Wei;">$Q$ Estimation by Combining ISD With LSR Method Based on
           Shaping-Regularized Inversion
    • Authors: Cong Luo;Guantan Huang;Xiangyang Li;Qing Wei;
      Pages: 1457 - 1461
      Abstract: The quality factor $Q$ is an indispensable parameter for studying wave propagation in viscoelastic media. $Q$ can not only be implemented for improving the quality of wave records but can also be used for directly indicating frequency-dependent anomalies induced by fluids, so it is widely used in seismic exploration and clinical medicine. $Q$ estimation here refers to the extraction of $Q$ information from seismic data; it has aroused lots of attention but is still somewhat controversial due to the limitations of existing methods. In this letter, combined with a logarithmic spectral ratio (LSR) algorithm, we have introduced a sparse-constrained inversion spectral decomposition (ISD) method for average- $Q$ estimation (LSR-ISD), and have used shaping regularization to solve for the spectrum ratio. Then, through regularized linear inversion, average- $Q$ was converted to an interval- $Q$ value. Finally, we have applied this method to synthetic data and field data. Numerical examples and field data application demonstrate that the proposed method produces a series of results with high resolution and good stability.
      PubDate: Sept. 2019
      Issue No: Vol. 16, No. 9 (2019)
       
  • Discriminative Feature Learning With Distance Constrained Stacked Sparse
           Autoencoder for Hyperspectral Target Detection
    • Authors: Yanzi Shi;Jie Lei;Yaping Yin;Kailang Cao;Yunsong Li;Chein-I Chang;
      Pages: 1462 - 1466
      Abstract: Target detection (TD) is one of the major tasks in hyperspectral image (HSI) processing, and its performance is greatly affected by the background. Feature extraction (FE) has been an effective way to mine discriminative information, especially FE based on deep learning, which can learn the intrinsic properties of data to further improve the detection performance. Unlike supervised networks, unsupervised stacked sparse autoencoders (SSAEs) can learn deep and nonlinear features without any labeled data. However, SSAEs usually require a supervised fine-tuned model to obtain better discrimination, which is not feasible for TD, since the prior information is generally insufficient. In this letter, we introduce a distance constraint that is added to the SSAE to form a new distance constrained SSAE (DCSSAE) network. Specifically, the distance constraint maximizes the distinction between the target pixels and other background pixels in the feature space. Then, using the discriminative features learned from the DCSSAE, a simple detector using radial basis function kernel is derived for background suppression. Experiments on two HSIs demonstrate that the deep spectral features learned from the DCSSAE are more distinguishable, and our proposed detector, namely, the DCSSAE detector, outperforms several popular detectors, especially in background suppression.
      PubDate: Sept. 2019
      Issue No: Vol. 16, No. 9 (2019)
       
  • Nonlinear Unmixing of Hyperspectral Data via Deep Autoencoder Networks
    • Authors: Mou Wang;Min Zhao;Jie Chen;Susanto Rahardja;
      Pages: 1467 - 1471
      Abstract: Nonlinear spectral unmixing is an important and challenging problem in hyperspectral image processing. Classical nonlinear algorithms are usually derived based on specific assumptions on the nonlinearity. In recent years, deep learning shows its advantage in addressing general nonlinear problems. However, existing ways of using deep neural networks for unmixing are limited and restrictive. In this letter, we develop a novel blind hyperspectral unmixing scheme based on a deep autoencoder network. Both encoder and decoder of the network are carefully designed so that we can conveniently extract estimated endmembers and abundances simultaneously from the nonlinearly mixed data. Because an autoencoder is essentially an unsupervised algorithm, this scheme only relies on the current data and, therefore, does not require additional training. Experimental results validate the proposed scheme and show its superior performance over several existing algorithms.
      PubDate: Sept. 2019
      Issue No: Vol. 16, No. 9 (2019)
       
  • Lifelong Learning for Scene Recognition in Remote Sensing Images
    • Authors: Min Zhai;Huaping Liu;Fuchun Sun;
      Pages: 1472 - 1476
      Abstract: The development of visual sensing technologies has made it possible to obtain some high resolution and to gather many high-resolution satellite images. To make the best use of these images, it is essential to be able to recognize and retrieve their intrinsic scene information. The problem of scene recognition in remote sensing images has recently aroused considerable interest, mainly due to the great success achieved by deep learning methods in generic image classification. Nevertheless, such methods usually require large amounts of labeled data. By contrast, remote sensing images are relatively scarce and expensive to obtain. Moreover, data sets from different aerospace research institutions exhibit large disparities. In order to address these problems, we propose a model based on a meta-learning method with the ability of learning a classifier from just few-shot samples. With the proposed model, the knowledge learned from one data set can be easily adapted to a new data set, which, in turn, would serve in the lifelong few-shot learning. Scene-level image recognition experiments, on public high-resolution remote sensing image data sets, validate our proposed lifelong few-shot learning model.
      PubDate: Sept. 2019
      Issue No: Vol. 16, No. 9 (2019)
       
  • Unsupervised Multitemporal Domain Adaptation With Source Labels Learning
    • Authors: Baisen Liu;Guoming Gao;Yanfeng Gu;
      Pages: 1477 - 1481
      Abstract: Multitemporal domain adaptation (DA) is very useful for solving the spectral drift problem between different images and is a basis step of multitemporal classification. However, for high-resolution images, they always have a few spectral bands. A few spectral bands are difficult to establish accurate alignment model. In order to achieving accurate multitemporal alignment on a few spectral bands’ high-resolution images, source label learning step is proposed in this letter and used to optimize traditional manifold alignment (MA). The core of this method is to improve the erroneous manifold structure by combining majority voting and weighting coefficients. Besides, this method is a universal step and can be used for optimizing all MA methods. Two groups of data sets captured by Chinese GF1 and GF2 satellites are used for performance evaluation. The experimental results demonstrate the effectiveness of our method and indicate our method significantly outperforms the traditional DA methods.
      PubDate: Sept. 2019
      Issue No: Vol. 16, No. 9 (2019)
       
  • SAR Image Retrieval Based on Unsupervised Domain Adaptation and Clustering
    • Authors: Famao Ye;Wei Luo;Meng Dong;Hailin He;Weidong Min;
      Pages: 1482 - 1486
      Abstract: Efficiently retrieving synthetic aperture radar (SAR) image is an important yet challenging task in the remote sensing field. Due to the shortage of labeled SAR images for fine-tuning convolutional neural network (CNN) models, this letter presents an unsupervised domain adaptation model based on CNN to learn the domain-invariant feature between SAR images and optical aerial images for SAR image retrieving, which can alleviate the burden of manual labeling. We extend a deep CNN to a novel adversarial network by adding the domain discriminator and the pseudolabel predictor. We improve the adaptation capacity of the adversarial network by utilizing the class information of SAR training images, which is obtained by clustering. Compared with the other related methods, the proposed method can enhance retrieval performance with our SAR data set.
      PubDate: Sept. 2019
      Issue No: Vol. 16, No. 9 (2019)
       
  • An Adaptive Nonlocal Gaussian Prior for Hyperspectral Image Denoising
    • Authors: Zhentao Hu;Zhiqiang Huang;Xinjian Huang;Fulin Luo;Renzhen Ye;
      Pages: 1487 - 1491
      Abstract: Nonlocal similar patches are effectively used in the Gaussian prior denoising model. However, it is difficult to learn an accurate Gaussian model for hyperspectral image (HSI) with noisy and limited similar patches, which will result in unstable Gaussian parameters (mean and covariance). In this letter, several techniques are proposed to overcome the noisy and small sample problems for HSI denoising. For Gaussian parameters, we propose the adaptive weighted mean of nonlocal similar patches and use a positive semidefinite constraint on the covariance parameter. In addition, an iterative manner is used to achieve more accurate parameters. The proposed method can achieve more robust Gaussian model for HSI denoising. Experiments on a HSI demonstrate the effectiveness of the proposed algorithm compared with the traditional methods for HSI denoising.
      PubDate: Sept. 2019
      Issue No: Vol. 16, No. 9 (2019)
       
  • Semantic Segmentation of Remote Sensing Images Using Multiscale Decoding
           Network
    • Authors: Xiaoqin Zhang;Zhiheng Xiao;Dongyang Li;Mingyu Fan;Li Zhao;
      Pages: 1492 - 1496
      Abstract: In this letter, we propose a practical convolutional neural network architecture for semantic pixelwise segmentation of remote sensing images, named Multiscale Decoding Network. The proposed method is built on the success of fully convolutional networks (FCNs) and the transfer of pretrained networks. The decoding network of our architecture utilizes the combination of three paths, namely, unpooling path, transposed convolution path, and dilated convolution path, in the form of an inception module. The whole network is trained in the end-to-end manner and the parameters of the three paths are learned automatically. Since the proposed method transfers the feature of pretrained networks and has three simplified decoding paths with fewer parameters, it requires less training data and training time. Compared with the classical networks FCN, SegNet, and U-net, our network shows better performance on remote sensing images segmentation.
      PubDate: Sept. 2019
      Issue No: Vol. 16, No. 9 (2019)
       
  • Classification Assessment of Real Versus Simulated Compact and Quad-Pol
           Modes of ALOS-2
    • Authors: Vineet Kumar;Yalamanchili Subrahmanyeswara Rao;Avik Bhattacharya;Shane R. Cloude;
      Pages: 1497 - 1501
      Abstract: Compact polarimetry (CP) offers a tradeoff with fully polarimetric modes in terms of swath width, power budget, and polarimetric information content. In this letter, a classification comparison is made among real CP, simulated CP (SCP), and quad polarimetric (QP) data acquired from the L-band SAR system onboard the ALOS-2 satellite. The Wishart supervised classification scheme is used to compare data modes over two regions of a mixed test site in India. The quantitative classification assessment indicates that the QP data have higher classification accuracy than any other polarimetric combinations for both regions. The comparative classification accuracy of real versus SCP data is different for the two regions. The overall accuracy of the real CP data is slightly higher ~1% than SCP for region 1, which is dominated by urban and rice classes, whereas it is lower by ~9% for the agricultural crop dominated region 2.
      PubDate: Sept. 2019
      Issue No: Vol. 16, No. 9 (2019)
       
  • Label-Consistent Transform Learning for Hyperspectral Image Classification
    • Authors: Jyoti Maggu;Hemant K. Aggarwal;Angshul Majumdar;
      Pages: 1502 - 1506
      Abstract: This letter proposes a new image analysis tool called label-consistent transform learning. Transform learning is a recent unsupervised representation learning approach; we add supervision by incorporating a label consistency constraint. The proposed technique is especially suited for hyperspectral image classification problems owing to its ability to learn from fewer samples. We have compared our proposed method with the state-of-the-art techniques such as label-consistent K-singular value decomposition, stacked autoencoder, deep belief network, convolutional neural network, and generative adversarial network. Our method yields considerably better results than all the aforesaid techniques.
      PubDate: Sept. 2019
      Issue No: Vol. 16, No. 9 (2019)
       
  • Introducing IEEE Collabratec
    • Pages: 1507 - 1507
      Abstract: Advertisement, IEEE.
      PubDate: Sept. 2019
      Issue No: Vol. 16, No. 9 (2019)
       
  • IEEE Open Access
    • Pages: 1508 - 1508
      Abstract: Advertisement, IEEE.
      PubDate: Sept. 2019
      Issue No: Vol. 16, No. 9 (2019)
       
 
 
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: 3.227.254.12
 
About JournalTOCs
API
Help
News (blog, publications)
JournalTOCs on Twitter   JournalTOCs on Facebook

JournalTOCs © 2009-