Search

In this paper, we consider the development of algorithms for the automatic detection of buried threats using ground penetrating radar (GPR) measurements. GPR is one of the most studied and successful modalities for automatic buried threat detection (BTD), and a large variety of BTD algorithms have been proposed for it. Despite this, large-scale comparisons of GPR-based BTD algorithms are rare in the literature. In this paper, we report the results of a multi-institutional effort to develop advanced BTD algorithms for a real-world GPR BTD system. The effort involved five institutions with substantial experience with the development of GPR-based BTD algorithms. In this paper, we report the technical details of the advanced algorithms submitted by each institution, representing their latest technical advances, and many state-of-the-art GPR-based BTD algorithms. We also report the results of evaluating the algorithms from each institution on the large experimental data set used for development. The experimental data set comprised 120 000 m2 of GPR data using surface area, from 13 different lanes across two U.S. test sites. The data were collected using a vehicle-mounted GPR system, the variants of which have supplied data for numerous publications. Using these results, we identify the most successful and common processing strategies among the submitted algorithms, and make recommendations for GPR-based BTD algorithm design. [ABSTRACT FROM AUTHOR]

This paper proposes a complex-valued convolutional neural network for land form classification and discovery in interferometric synthetic aperture radar (InSAR). Since the amount of satellite-borne SAR data has been increasing drastically, it is necessary to structurize the local features contained in observation data prior to utilization in the so-called big data framework for higher usability. Convolutional neural networks have such potential in general. However, there exists no network that can deal with complex amplitude data obtained in InSAR consistently. In this paper, we propose a complex-valued convolutional neural network to deal with InSAR. We demonstrate that the network classifies slopes and plains adaptively and, moreover, indicates small volcanos similar to a sample volcano (Omuroyama) included in the InSAR data. We also find their characteristic features emerging in the kernels in the convolution layers. These results reveal that the proposed complex-valued convolutional neural network is capable of successfully discovering unidentified lands similar to a prepared sample, which is highly useful for the InSAR data structurization. [ABSTRACT FROM AUTHOR]

Processing large very high-resolution remote sensing images on resource-constrained devices is a challenging task because of the large size of these data sets. For applications such as environmental monitoring or natural resources management, complex algorithms have to be used to extract information from the images. The memory required to store the images and the data structures of such algorithms may be very high (hundreds of gigabytes) and therefore leads to unfeasibility on commonly available computers. Segmentation algorithms constitute an essential step for the extraction of objects of interest in a scene and will be the topic of the investigation in this paper. The objective of the present work is to adapt image segmentation algorithms for large amounts of data. To overcome the memory issue, large images are usually divided into smaller image tiles, which are processed independently. Region-merging algorithms do not cope well with image tiling since artifacts are present on the tile edges in the final result due to the incoherencies of the regions across the tiles. In this paper, we propose a scalable tile-based framework for region-merging algorithms to segment large images, while ensuring identical results, with respect to processing the whole image at once. We introduce the original concept of the stability margin for a tile. It allows ensuring identical results to those obtained if the whole image had been segmented without tiling. Finally, we discuss the benefits of this framework and demonstrate the scalability of this approach by applying it to real large images. [ABSTRACT FROM PUBLISHER]

Information theory has recently become an interesting topic in earth observation data management and analysis, since it can provide important information on hidden interactions and correlations among the considered data records. Although several methods have been proposed and implemented to efficiently extract a proper set of features and deliver accurate image investigation, classification, and segmentation, these architectures show drawbacks when the data sets are characterized by complex interactions among the samples. In this paper, a new approach based on information theory for automatic pattern recognition is introduced for accurate classification of remotely sensed data. Experimental results carried out on real data sets show the validity of the proposed approach. [ABSTRACT FROM PUBLISHER]

Recently, hyperspectral image (HSI) classification approaches based on deep learning (DL) models have been proposed and shown promising performance. However, because of very limited available training samples and massive model parameters, DL methods may suffer from overfitting. In this paper, we propose an end-to-end 3-D lightweight convolutional neural network (CNN) (abbreviated as 3-D-LWNet) for limited samples-based HSI classification. Compared with conventional 3-D-CNN models, the proposed 3-D-LWNet has a deeper network structure, less parameters, and lower computation cost, resulting in better classification performance. To further alleviate the small sample problem, we also propose two transfer learning strategies: 1) cross-sensor strategy, in which we pretrain a 3-D model in the source HSI data sets containing a greater number of labeled samples and then transfer it to the target HSI data sets and 2) cross-modal strategy, in which we pretrain a 3-D model in the 2-D RGB image data sets containing a large number of samples and then transfer it to the target HSI data sets. In contrast to previous approaches, we do not impose restrictions over the source data sets, in which they do not have to be collected by the same sensors as the target data sets. Experiments on three public HSI data sets captured by different sensors demonstrate that our model achieves competitive performance for HSI classification compared to several state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Deep learning methods have recently been successfully explored for hyperspectral image (HSI) classification. However, training a deep-learning classifier notoriously requires hundreds or thousands of labeled samples. In this paper, a deep few-shot learning method is proposed to address the small sample size problem of HSI classification. There are three novel strategies in the proposed algorithm. First, spectral–spatial features are extracted to reduce the labeling uncertainty via a deep residual 3-D convolutional neural network. Second, the network is trained by episodes to learn a metric space where samples from the same class are close and those from different classes are far. Finally, the testing samples are classified by a nearest neighbor classifier in the learned metric space. The key idea is that the designed network learns a metric space from the training data set. Furthermore, such metric space could generalize to the classes of the testing data set. Note that the classes of the testing data set are not seen in the training data set. Four widely used HSI data sets were used to assess the performance of the proposed algorithm. The experimental results indicate that the proposed method can achieve better classification accuracy than the conventional semisupervised methods with only a few labeled samples. [ABSTRACT FROM AUTHOR]

In this paper, we propose a thresholding method utilizing the mutual relation between the two used features, which should be both robust and of low correlation. The mutual relation is exploited through a histogram subtraction transformation, which tries to reduce only the background part of each of the histograms for the features so that we can easily differentiate between the background part and the target part. A speedup scheme that requires prior knowledge to exclude the possible local minimum(s) is also presented. To sufficiently validate the effectiveness of our histogram subtraction transformation, the two developed thresholding methods are applied to shadow detection and vegetation detection and compared with some state-of-the-art methods in both fields. The comparative results on multiple data sets indicate that with the thresholds automatically provided by the proposed thresholding methods, even the simple binarization methods can obtain good detection results. [ABSTRACT FROM AUTHOR]

Kernel nonnegative matrix factorization (KNMF) is an extension of NMF designed to capture nonlinear dependence features in data matrix through kernel functions. In KNMF, the size of the kernel matrices is closely associated with the input data matrix, of which the calculation consumes a large amount of memory and computing resource. When applied on large-scale hyperspectral data, KNMF often meets the bottleneck of memory and may cause the overflow of memory. And when dealing with dynamically acquired data, KNMF requires recomputation of the whole data set when newly acquired data arrived, which produces huge memory and computing resource requirements. To reduce the usage of memory and improve the computational efficiency when applying KNMF on large scale and dynamic hyperspectral data, we extend KNMF by introducing partition matrix theory and considering the relationships among dividing blocks. The decomposition results of hyperspectral data are derived from much smaller scale matrices containing the formerly achieved results and the newly data blocks incrementally. In this paper, we propose an incremental KNMF (IKNMF) to reduce the computing requirements for large-scale data in hyperspectral unmixing. An improved IKNMF (IIKNMF) is also proposed to further improve the abundance results of IKNMF. Experiments are conducted on both synthetic and real hyperspectral data sets. The experimental results demonstrate that the proposed methods can effectively save memory resources without degrading the unmixing performance and the proposed IIKNMF can achieve better abundance results than IKNMF and KNMF. [ABSTRACT FROM AUTHOR]

Due to the urgent demand for remote sensing big data analysis, large-scale remote sensing image retrieval (LSRSIR) attracts increasing attention from researchers. Generally, LSRSIR can be divided into two categories as follows: uni-source LSRSIR (US-LSRSIR) and cross-source LSRSIR (CS-LSRSIR). More specifically, US-LSRSIR means the inquiry remote sensing image and images in the searching data set come from the same remote sensing data source, whereas CS-LSRSIR is designed to retrieve remote sensing images with a similar content to the inquiry remote sensing image that are from a different remote sensing data source. In the literature, US-LSRSIR has been widely exploited, but CS-LSRSIR is rarely discussed. In practical situations, remote sensing images from different kinds of remote sensing data sources are continually increasing, so there is a great motivation to exploit CS-LSRSIR. Therefore, this paper focuses on CS-LSRSIR. To cope with CS-LSRSIR, this paper proposes source-invariant deep hashing convolutional neural networks (SIDHCNNs), which can be optimized in an end-to-end manner using a series of well-designed optimization constraints. To quantitatively evaluate the proposed SIDHCNNs, we construct a dual-source remote sensing image data set that contains eight typical land-cover categories and 10 000 dual samples in each category. Extensive experiments show that the proposed SIDHCNNs can yield substantial improvements over several baselines involving the most recent techniques. [ABSTRACT FROM AUTHOR]

Linearly derived features have been widely used in hyperspectral image classification to find linear separability of certain classes in recent years. Moreover, nonlinearly transformed features are more effective for class discrimination in real analysis scenarios. However, few efforts have attempted to combine both linear and nonlinear features in the same framework even if they can demonstrate some complementary properties. Moreover, conventional multiple-feature learning-based approaches deal with different features equally, which is not reasonable. This paper proposes an efficient multiple-feature learning-based model with adaptive weights for effectively classifying complex hyperspectral images with limited training samples. A new diversity kernel function is proposed first to simulate the vision perception and analysis procedure of human beings. It could simultaneously evaluate the contrast differences of global features and spatial coherence. Since existing multiple-kernel feature models are always time-consuming, we then design a new adaptive weighted multiple kernel learning method. It employs kernel projection, which could lower the dimensionalities and also learn kernel weights to further discriminate the classification boundaries. For combining both linear and nonlinear features, this paper also proposes a novel decision fusion strategy. The method combines linear and multiple kernel features to balance the classification results of different classifiers. The proposed scheme is tested on several hyperspectral data sets and extended to multisource feature classification environment. The experimental results show that the proposed classification method outperforms most of the existing ones and significantly reduces the computational complexity. [ABSTRACT FROM AUTHOR]

Edge-preserving features (EPFs) obtained by the application of edge-preserving filters to hyperspectral images (HSIs) have been found very effective in characterizing significant spectral and spatial structures of objects in a scene. However, a direct use of the EPFs can be insufficient to provide a complete characterization of spatial information when objects of different scales are present in the considered images. Furthermore, the edge-preserving smoothing operation unavoidably decreases the spectral differences among objects of different classes, which may affect the following classification. To overcome these problems, in this paper, a novel principal component analysis (PCA)-based EPFs (PCA-EPFs) method for HSI classification is proposed, which consists of the following steps. First, the standard EPFs are constructed by applying edge-preserving filters with different parameter settings to the considered image, and the resulting EPFs are stacked together. Next, the spectral dimension of the stacked EPFs is reduced with the PCA, which not only can represent the EPFs in the mean square sense but also highlight the separability of pixels in the EPFs. Finally, the resulting PCA-EPFs are classified by a support vector machine (SVM) classifier. Experiments performed on several real hyperspectral data sets show the effectiveness of the proposed PCA-EPFs, which sharply improves the accuracy of the SVM classifier with respect to the standard edge-preserving filtering-based feature extraction method, and other widely used spectral-spatial classifiers. [ABSTRACT FROM PUBLISHER]

Image reranking is a popular postprocessing method for remote sensing image retrieval (RSIR), which aims at enhancing the initial retrieval performance. In general, it takes either users’ opinions or the relationships between images into consideration to find an optimal reranked list based on the initial retrieved results. In this paper, we present a reranking method for improving RSIR, which is named two-stage reranking (TSR). Suppose the k -nearest neighbors of a query RS image have been obtained by the initial retrieval. The first step of our TSR is to edit these neighbors using the editing scheme. A handful of informative and representative RS images are selected by the active learning algorithm, and their binary labels are provided by the users relative to the query image. Then, a binary classifier is trained using the selected RS images and their labels to classify the rest of the neighbors. Finally, both classification results and rank information in the initial retrieval results are considered to decide which neighbor should be excluded. In the next step, the remaining RS images are reranked by the proposed reranking scheme, i.e., multisimilarity fusion reranking. Both the user’s experience and image relationships are taken into account in TSR to ensure the performance of the reranking. The efficiency and the robustness of our method are validated by experiments conducted on two different types of RS images. Compared with the existing visual reranking approaches, our method achieves improved performance. [ABSTRACT FROM PUBLISHER]

Aerial scene classification, which aims to automatically label an aerial image with a specific semantic category, is a fundamental problem for understanding high-resolution remote sensing imagery. In recent years, it has become an active task in the remote sensing area, and numerous algorithms have been proposed for this task, including many machine learning and data-driven approaches. However, the existing data sets for aerial scene classification, such as UC-Merced data set and WHU-RS19, contain relatively small sizes, and the results on them are already saturated. This largely limits the development of scene classification algorithms. This paper describes the Aerial Image data set (AID): a large-scale data set for aerial scene classification. The goal of AID is to advance the state of the arts in scene classification of remote sensing images. For creating AID, we collect and annotate more than 10000 aerial scene images. In addition, a comprehensive review of the existing aerial scene classification techniques as well as recent widely used deep learning methods is given. Finally, we provide a performance analysis of typical aerial scene classification and deep learning approaches on AID, which can be served as the baseline results on this benchmark. [ABSTRACT FROM PUBLISHER]

Road detection and centerline extraction from very high-resolution (VHR) remote sensing imagery are of great significance in various practical applications. Road detection and centerline extraction operations depend on each other, to a certain extent. The road detection constrains the appearance of the centerline, and the centerline enhances the linear features of the road detection. However, most of the previous works have addressed these two tasks separately and have not considered the symbiotic relationship between them, making it difficult to obtain smooth and complete roads. In this paper, a novel multi-scale and multi-task deep learning framework for automatic road extraction (MSMT-RE) is proposed to build the relationship between them and simultaneously complete the road detection and centerline extraction tasks. U-Net is selected as the basic network for multi-task learning due to its strong ability to preserve spatial details. Multi-scale feature integration is also applied in the framework to increase the robustness of the feature extraction. Meanwhile, an adaptive loss function is introduced to solve the problems of roads taking up a small percentage of the training samples, and the fact that the positive samples of the two tasks are unbalanced. Finally, experiments were conducted on two public road data sets and two large images from Google Earth, and the proposed framework was compared with other state-of-the-art deep learning-based road extraction methods, both quantitatively and qualitatively. The proposed approach outperformed all the compared methods, confirming its advantages in automatic road extraction. [ABSTRACT FROM AUTHOR]

This paper provides improved quantitative estimates of the wind-ruffled roughness contributions to dual co- and cross-polarized radar signals. Expanding previous approaches, 1696 RADARSAT-2 quad-polarized synthetic aperture radar (SAR) measurements, co-located with 65 in situ National Data Buoy Center (NDBC) buoy observations, are analyzed. Considering all wind conditions, the impact of breaking and near-breaking waves on dual co- and cross-polarized radar signals is robustly documented. For VV polarized measurements, the contribution of breaking waves decreased from 60% to 20% with increasing incidence angle, whereas for HH polarization and cross-polarization measurements, it can amount to about 60%–70% for all incidence angles. Building on the large analyzed data set, robust empirical dependencies between breaking waves and their impact on co- and cross-pol signals are then derived, as functions of wind speeds, incidence angles, and azimuth directions. [ABSTRACT FROM AUTHOR]

Pansharpening techniques aim at improving the spatial resolution of a multispectral data set (MS) by using a panchromatic image (Pan) acquired on the same scene with a greater spatial resolution and consequently a lower ground sample distance (GSD). Usually, a quantitative assessment of the fused products cannot be directly performed because of the lack of a reference MS data set with the same GSD of the Pan. A well-known solution is Wald's protocol: The original MS and Pan are spatially degraded, the reducing factor being the ratio between their GSDs. Pansharpening is then performed between the reduced MS and Pan data sets, and the fused products are compared with the original MS, which can be used as reference. In this protocol, fusion performances are assumed to be independent of the scale so that the results at the reduced scale are an estimation of those at the original resolution. This hypothesis can be more or less reliable, depending on the sensor and/or the scene content. The objective of this paper is to propose a new methodology to infer the unknown performances of a pansharpening method at full scale. For this purpose, multiple sets of fused images are computed at degraded scales by downsampling Pan and MS data sets by means of the sensor modulation transfer function. Multiscale quality/distortion measurements are fitted by linear and quadratic polynomials in order to extrapolate their full-scale values. Once the proposed protocol has been assessed in the presence of reference originals, the obtained results are extended to the case where the reference image is not available. [ABSTRACT FROM PUBLISHER]

The intrinsic dimensionality (ID) of multivariate data is a very important concept in spectral unmixing of hyperspectral images. A good estimation of the ID is crucial for a correct retrieval of the number of endmembers (the spectral signatures of macroscopic materials) in the image, for dimensionality reduction or for subspace learning, among others. Recently, some approaches to perform spectral unmixing and superresolution locally have been proposed, which require a local estimation of the number of endmembers to use. However, the role of ID in local regions of hyperspectral images has not been properly addressed. Some important issues when dealing with small regions of hyperspectral data can seriously affect the performance of conventional hyperspectral ID estimators. We show that three factors mainly affect local ID estimation: the number of pixels in the local regions, which has to be high enough for the estimations to be relevant, the number of hyperspectral bands which complicates the estimations if the ambient space has a high dimensionality, and the noise, which can be misinterpreted as a signal when its power is important. Here, we review the hyperspectral ID estimators on the literature for local ID estimation, we show how they behave in a local setting on synthetic and real data sets, and we provide some guidelines to make proper use of these estimators in local approaches. [ABSTRACT FROM AUTHOR]

Surface shortwave net radiation (SSNR) is a key component of the surface radiation budget. In this paper, we refined a direct estimation approach to retrieve daily SSNR estimates from combined Terra and Aqua Moderate Resolution Imaging Spectroradiometer (MODIS) data. The retrieved MODIS SSNR estimates were validated against measurements at seven stations of the Surface Radiation Budget Network. We also compared the MODIS retrievals with three existing SSNR products: the Clouds and the Earth's Radiant Energy System (CERES) products, the North American Regional Reanalysis (NARR) data, and the ERA-Interim reanalysis data from the European Centre for Medium-Range Weather Forecasts. MODIS data at 1 km were upscaled to mitigate the mismatch between site measurements and satellite retrievals. Among the four data sets, the aggregated MODIS retrievals agreed best with in situ measurements, with a root-mean-square error (rmse) of 23.1 W/m2 and a negative bias of 6.7 W/m2. The CERES products have a slightly larger rmse of 24.2 W/m2 and a positive bias of 7.6 W/m2. Both reanalysis data (NARR and ERA-Interim) overestimate daily SSNR and have much larger uncertainties. Monthly satellite SSNR data are more accurate than daily values, and the scaling issue in validating monthly MODIS SSNR retrievals is also less prominent. Averaged with a window size of 23 km, the two MODIS sensors can estimate monthly SSNR with an rmse error of 11.6 W/m 2, representing an improvement of 2.4 W/m2 over the CERES products. [ABSTRACT FROM PUBLISHER]

A novel band discrimination analysis framework for hyperspectral image (HSI) supervised classification is proposed based on dual density (DD). Different from the popular supervised band selection (BS) approaches which measure the discrimination among classes under multivariate normal distribution hypothesis, our work infers the class discrimination degree (overlapping extent) for valid extraction of band subset without any assumed distribution. In the proposed framework, it is crucial to find indexes to measure the discrimination degree of each band, and therefore we develop the DD indexes, including the homogeneity density and the heterogeneity density. Viewing each band of the HSI as a data set, i.e., the data points in each data set are 1-D, and we first obtain the DD value pairs for all data points in each data set. Then, for each data set, we determine its discrimination degree using DD-based zone ratio or score quantify strategy. Finally, the bands, which are determined as the nonoverlapped or have high scores, are chosen as the band subset for the subsequent classification. Superiorities of the proposed BS are demonstrated on the three real-world HSIs over several well-known BS algorithms in terms of classification accuracy and speed. [ABSTRACT FROM AUTHOR]

An algorithm for detecting coherence in Cyclone Global Navigation Satellite System (CYGNSS) mission delay-Doppler maps (DDMs) is presented. Because CYGNSS DDMs report only the observed power without phase information, the algorithm uses estimates of power “spread” within the DDM to flag coherency. Since the estimate used is a ratio of the powers in differing portions of the DDM, it is less sensitive to absolute power calibration and to the GPS C/A code type observed, and is applied to CYGNSS Level-1 uncalibrated DDMs. The basic detector formulation is described along with modifications to improve performance in lower signal-to-noise ratio (SNR) situations. The required detection thresholds are determined using matchups with CYGNSS “Raw I/F” mode measurements for which the DDM phase can be computed and used to identify coherence more precisely. Application of the final detector over a large CYGNSS data set suggests that approximately 8.9% of all inland returns are coherent. Inland regions persistently identified as coherent were found largely to be associated with the presence of water bodies. A smaller set of desert locations apparently having very low surface roughness were also found to be associated with persistent coherence. The detector was also applied to a set of ocean measurements, with the results showing that persistent coherence is limited to areas with sheltered waters. Ocean tests avoiding such regions indicate that the detector’s false-alarm rate is approximately 0.0012% for the detection threshold used. [ABSTRACT FROM AUTHOR]

This article investigates the presence of a new interferometric signal in multilooked synthetic aperture radar (SAR) interferograms that cannot be attributed to the atmospheric or Earth-surface topography changes. The observed signal is short-lived and decays with the temporal baseline; however, it is distinct from the stochastic noise attributed to temporal decorrelation. The presence of such a fading signal introduces a systematic phase component, particularly in short temporal baseline interferograms. If unattended, it biases the estimation of Earth surface deformation from SAR time series. Here, the contribution of the mentioned phase component is quantitatively assessed. The biasing impact on the deformation-signal retrieval is further evaluated. A quality measure is introduced to allow the prediction of the associated error with the fading signals. Moreover, a practical solution for the mitigation of this physical signal is discussed; special attention is paid to the efficient processing of Big Data from modern SAR missions such as Sentinel-1 and NISAR. Adopting the proposed solution, the deformation bias is shown to decrease significantly. Based on these analyses, we put forward our recommendations for efficient and accurate deformation-signal retrieval from large stacks of multilooked interferograms. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) have recently achieved impressive improvements on hyperspectral (HS) pansharpening. However, most of the CNN-based HS pansharpening approaches would have to first upsample the low-resolution hyperspectral image (LR-HSI) using bicubic interpolation or data-driven training strategy, which inevitably lose some details or greatly rely on the learning process. In addition, most previous methods regard the pansharpening as a black-box problem and treat diverse features equally, thus hindering the discriminative ability of CNNs. To conquer these issues, a novel HS pansharpening method using deep hyperspectral prior (DHP) and dual-attention residual network (DARN) is proposed in this article. Specifically, we first upsample the LR-HSI to the scale of the panchromatic (PAN) image through the DHP algorithm, which can better preserve spatial and spectral information without learning from large data sets. The upsampled result is then concatenated with the PAN image to form the input of the DARN, where several channel-spatial attention residual blocks (CSA ResBlocks) are stacked to map the residual HSI between the reference HSI and the upsampled HSI. In each CSA ResBlock, two complementary attention modules, i.e., channel attention and spatial attention modules, are designed to adaptively learn more informative features of spectral channels and spatial locations simultaneously, which can effectively boost the fusion accuracy. Finally, the fused HSI is obtained by the summation of the upsampled HSI and the reconstructed residual HSI. The experimental results of both simulated and real HS data sets demonstrate that the performance of our DHP-DARN method is superior over the state-of-the-art HS pansharpening approaches. [ABSTRACT FROM AUTHOR]

The strong radiative forcing by atmospheric methane has stimulated interest in identifying natural and anthropogenic sources of this potent greenhouse gas. Point sources are important targets for quantification, and anthropogenic targets have the potential for emissions reduction. Methane point-source plume detection and concentration retrieval have been previously demonstrated using data from the Airborne Visible InfraRed Imaging Spectrometer-Next Generation (AVIRIS-NG). Current quantitative methods have tradeoffs between computational requirements and retrieval accuracy, creating obstacles for processing real-time data or large data sets from flight campaigns. We present a new computationally efficient algorithm that applies sparsity and an albedo correction to matched the filter retrieval of trace gas concentration path length. The new algorithm was tested using the AVIRIS-NG data acquired over several point-source plumes in Ahmedabad, India. The algorithm was validated using the simulated AVIRIS-NG data, including synthetic plumes of known methane concentration. Sparsity and albedo correction together reduced the root-mean-squared error of retrieved methane concentration-path length enhancement by 60.7% compared with a previous robust matched filter method. Background noise was reduced by a factor of 2.64. The new algorithm was able to process the entire 300 flight line 2016 AVIRIS-NG India campaign in just over 8 h on a desktop computer with GPU acceleration. [ABSTRACT FROM AUTHOR]

Sparse coding method has been used for seismic denoising, as the data can be sparsely represented by the sparse transform and dictionary learning (DL) methods. DL methods have attracted wide attention because the learned dictionary is adaptive. However, for seismic denoising, the dictionary learned from the noise data is a mix of atoms representing seismic data patterns and atoms representing noise patterns. To make the dictionary contain more atoms to represent seismic data, we consider adding to the dictionary the local and nonlocal similarities of the data via the structured graph and propose a new DL method, namely, the structured graph dictionary learning (SGDL). The atoms of dictionary learned by the SGDL are smooth, which implies smoothness of any signal represented over this dictionary. In addition, in the dictionary domain, we use the nonlocal model, namely, SSC-GSM that connects Gaussian scale mixture (GSM) with simultaneous sparse coding (SSC), to represent the seismic data. We apply the method to the synthetic data and two kinds of field data. Results show that our method can better remove strong noise and retain the seismic weak events also. [ABSTRACT FROM AUTHOR]

Signal decorrelation poses a limitation to multipass SAR interferometry. In pursuit of overcoming this limitation to achieve high-precision deformation estimates, different techniques have been developed, with short baseline subset, SqueeSAR, and CAESAR as the overarching schemes. These different analysis approaches raise the question of their efficiency and limitation in phase and consequently deformation estimation. This contribution first addresses this question and then proposes a new estimator with improved performance, called Eigendecomposition-based Maximum-likelihood-estimator of Interferometric phase (EMI). The proposed estimator combines the advantages of the state-of-the-art techniques. Identical to CAESAR, EMI is solved using eigendecomposition; it is therefore computationally efficient and straightforward in implementation. Similar to SqueeSAR, EMI is a maximum-likelihood-estimator; hence, it retains estimation efficiency. The computational and estimation efficiency of EMI renders it as an optimum choice for phase estimation. A further marriage of EMI with the proposed Sequential Estimator by Ansari et al. provides an efficient processing scheme tailored to the analysis of Big InSAR Data. EMI is formulated and verified in relation to the state-of-the-art approaches via mathematical formulation, simulation analysis, and experiments with time series of Sentinel-1 data over the volcanic island of Vulcano, Italy. [ABSTRACT FROM AUTHOR]

High-quality and large-scale image composites are increasingly important for a variety of applications. Yet a number of challenges still exist in the generation of composites with certain desirable qualities such as maintaining the spectral relationship between bands, reduced spatial noise, and consistency across scene boundaries so that large mosaics can be generated. We present a new method for generating pixel-based composite mosaics that achieves these goals. The method, based on a high-dimensional statistic called the ‘geometric median,’ effectively trades a temporal stack of poor quality observations for a single high-quality pixel composite with reduced spatial noise. The method requires no parameters or expert-defined rules. We quantitatively assess its strengths by benchmarking it against two other pixel-based compositing approaches over Tasmania, which is one of the most challenging locations in Australia for obtaining cloud-free imagery. [ABSTRACT FROM PUBLISHER]

Wide-swath synthetic aperture radar (SAR) missions with short revisit times, such as Sentinel-1 and the planned NISAR and Tandem-L, provide an unprecedented wealth of interferometric SAR (InSAR) time series. However, the processing of the emerging Big Data is challenging for state-of-the-art InSAR analysis techniques. This contribution introduces a novel approach, named Sequential Estimator, for efficient estimation of the interferometric phase from long InSAR time series. The algorithm uses recursive estimation and analysis of the data covariance matrix via division of the data into small batches, followed by the compression of the data batches. From each compressed data batch artificial interferograms are formed, resulting in a strong data reduction. Such interferograms are used to link the “older” data batches with the most recent acquisitions and thus to reconstruct the phase time series. This scheme avoids the necessity of reprocessing the entire data stack at the face of each new acquisition. The proposed estimator introduces negligible degradation compared to the Cramér–Rao lower bound under realistic coherence scenarios. The estimator may therefore be adapted for high-precision near-real-time processing of InSAR and accommodate the conversion of InSAR from an offline to a monitoring geodetic tool. The performance of the Sequential Estimator is compared to state-of-the-art techniques via simulations and application to Sentinel-1 data. [ABSTRACT FROM PUBLISHER]

In this work, the authors investigate the behaviors of the two main classes of pansharpening methods: those based on component substitution (CS) or spectral methods and those based on multiresolution analysis (MRA) or spatial methods, in the presence of temporal and/or instrumental misalignments between the multispectral (MS) and panchromatic (Pan) data sets, that is, whenever MS and Pan are not jointly acquired at the same time and/or from the same platform. Starting from the mathematical formulation of CS and MRA pansharpening and from the spectral model between the Pan and MS channels, estimated through the multivariate linear regression between MS and spatially degraded Pan, it is proven that both CS and MRA methods may lose geometric sharpness in the case of a spectral mismatch, but spatial methods preserve the spectral diversity of the original MS data set regardless of the date or instrument of Pan image acquisition. Conversely, spectral methods also suffer from a loss of spectral fidelity to the original MS data set that is inversely related to the success of the spectral match between MS and Pan, measured by the coefficient of determination of the multivariate regression. An experimental setup exploiting GeoEye-1 and QuickBird data sets demonstrates the validity and intrinsic limitations of the proposed theoretical models. Depending of the target application, one class of methods may be preferred to another: Whenever spectral fidelity of pansharpened products to the original MS data sets is crucial, spectral methods should be avoided, and spatial methods are to be preferred. [ABSTRACT FROM PUBLISHER]

The algorithm of synthetic aperture radar automatic target recognition (SAR-ATR) is generally composed of the extraction of a set of features that transform the raw input into a representation, followed by a trainable classifier. The feature extractor is often hand designed with domain knowledge and can significantly impact the classification accuracy. By automatically learning hierarchies of features from massive training data, deep convolutional networks (ConvNets) recently have obtained state-of-the-art results in many computer vision and speech recognition tasks. However, when ConvNets was directly applied to SAR-ATR, it yielded severe overfitting due to limited training images. To reduce the number of free parameters, we present a new all-convolutional networks (A-ConvNets), which only consists of sparsely connected layers, without fully connected layers being used. Experimental results on the Moving and Stationary Target Acquisition and Recognition (MSTAR) benchmark data set illustrate that A-ConvNets can achieve an average accuracy of 99% on classification of ten-class targets and is significantly superior to the traditional ConvNets on the classification of target configuration and version variants. [ABSTRACT FROM PUBLISHER]

New hyperspectral missions will collect huge amounts of hyperspectral data. In addition, it is possible now to acquire time series and multiangular hyperspectral images. The process and analysis of these big data collections will require common hyperspectral techniques to be adapted or reformulated. The tensor decomposition, which is also known as multiway analysis, is a technique to decompose multiway arrays, i.e., hypermatrices with more than two dimensions (ways). Hyperspectral time series and multiangular acquisitions can be represented as a three-way tensor. Here, we apply canonical polyadic (CP) tensor decomposition techniques to the blind analysis ohyperspectral big data. In order to do so, we use a novel compression-based nonnegative CP decomposition. We show that the proposed methodology can be interpreted as multilinear blind spectral unmixing, i.e., a higher order extension of the widely known spectral unmixing. In the proposed approach, the big hyperspectral tensor is decomposed in three sets of factors, which can be interpreted as spectral signatures, their spatial distribution, and temporal/angular changes. We provide experimental validation using a study case of the snow coverage of the French Alps during the snow season. [ABSTRACT FROM AUTHOR]