Search

Nominal grid data of geostationary remote sensing satellites are fundamental for generating the subsequent products. It can be obtained by normalized projection models, mainly based on the imaging mode. However, there are only definitions and primary descriptive equations for the normalized geostationary projection (NGP) model in the existing literature, while the corresponding imaging mode and the physical interpretation are missing, thus hindering the understanding of the produced nominal grid dataset as well as the subsequent products based on the grid. This paper first derived the imaging mode for NGP based on the limited literature. In addition, another new imaging mode was introduced and analyzed based on NGP. The corresponding projection model [nonstandard normalized geostationary projection (NNGP)] was proposed, which is entirely consistent with the situation of America’s Geostationary Operational Environmental Satellite-R Series (GOES-R) and Chinese Fengyun-4A (FY-4A). Furthermore, this paper proposed a novel nominal projection model for frame imaging, which is consistent with the imaging mode of China’s Gaofen-4. Finally, extensive experiments were designed to comparatively analyze the three nominal grids and demonstrate a detailed difference. By providing a theoretical basis for nominal grid selection, this research is highly significant for the efficient near-real-time production and further applications of geostationary images, as well as the conversion between different datasets resulting from different nominal grid data. In addition, our models are sufficiently tested during the on-orbit running of FY-4A, the first satellite of China’s second-generation three-axis stabilized geostationary meteorological satellite series. The algorithms provide the technical support for the high-precision image navigation and registration and play a significant role in robustly producing the meteorological data with similar quality to those from GOES-R. [ABSTRACT FROM AUTHOR]

Canopy height models (CHMs) were utilized to detect treetops and estimate individual-tree parameters. The treetop detection based on CHMs was affected by surface topography and crown characteristics. However, their effects have not been well studied. Therefore, this paper aimed at assessing the impacts of aforementioned factors to facilitate treetop identification from LiDAR-derived CHMs. To fulfill this objective, we first extended and improved the previous models for cases with various terrains. Then, a new theoretical model was developed to quantify treetop displacements for ellipsoidal tree crowns. Finally, we further analyzed the treetop displacements due to terrain slope, crown radius, crown shape, and offset distance to the slope surface. Our analysis indicates that the vertical displacement increases exponentially with terrain slope; thus, the effect of terrain slope must be considered over extremely steep areas; larger errors are observed for trees with a large crown radius; the treetop displacements are highly correlated with crown shape, the effect of topographic normalization can be neglected for conical crowns with a large crown angle, and the elliptical crown shape can reduce the treetop detection errors; and treetop displacements increases with offset distance to the slope surface in , while opposite results are observed in. In addition, the results also demonstrate that the effect of slope-distorted CHMs may be quite different for different types of tree crowns and terrains. Overall, this paper makes a significant contribution to the development of theoretical models for quantifying treetop displacements. Furthermore, our findings provide a theoretical basis and guidance for better identifying treetops from LiDAR-derived CHMs. [ABSTRACT FROM AUTHOR]

Convolutional neural network (CNN)-based methods have been successfully applied to SAR target detection. Different from prevalently used detection approaches with rectangle bounding box, rotatable bounding box (RBox)-based methods, such as DRBox-v1, can effectively reduce the interference of background pixels and locate the targets more finely for geospatial object detection. Although DRBox-v1 has achieved impressive detected performance, there still exist some remaining problems and room for improvement. In this paper, an improved RBox-based target detection framework is proposed to boost precision and recall rates of detection, and we refer to the method as DRBox-v2 and apply it to target detection in SAR images. The main improvements of DRBox-v2 as well as the contributions of this paper are fourfold. First, a multi-layer prior box generation strategy is designed for detecting small-scale targets. Since shallow layers lack strong sematic information, the feature pyramid network (FPN) module is applied. Second, a modified encoding scheme for RBox is proposed for more precisely estimating the position of RBox and orientation of targets. Third, a focal loss (FL) combined with hard negative mining (HNM) technique is proposed to mitigate the issue of the imbalance between positive and negative samples, which produces better results than solely employing either one. Fourth, comprehensive ablation studies are conducted to reveal the effect of each improvement on detected results. The results of the target detection on three data sets are illustrated and our method obtains 0.135, 0.081, 0.115 gains in average precision compared with three state-of-the-art methods, respectively. [ABSTRACT FROM AUTHOR]

This paper focuses on the blind unmixing technique for analyzing hyperspectral images (HSIs). A joint deconvolution and blind hyperspectral unmixing (DBHU) algorithm is proposed, which is aimed at eliminating the impact of the adjacency effect (AE) on unmixing. In remote sensing imagery, the AE occurs in the presence of atmospheric scattering over a heterogeneous surface. The AE leads to blurring and additional mixing of HSIs and makes it difficult to estimate endmembers and abundances accurately. In this paper, we first model the blurred HSIs by the use of a bilinear mixing model (BMM), where a blurring kernel is used to model the mixing caused by the AE. Based on the BMM, the DBHU problem is formulated as a constrained and biconvex optimization problem. Specifically, the minimum-volume simplex (MVS) is incorporated to deal with the additional mixing caused by the AE, and 3-D total variation (TV) priors are adopted to model the spectral–spatial correlation of the data. In DBHU, the biconvex problem is efficiently solved by a nonstandard application of the alternating direction method of multipliers (ADMM) algorithm, where a block coordinate descent scheme is applied by splitting the original problem into two saddle point subproblems, and then minimizing the subproblems alternately via the ADMM until convergence. The experimental results obtained with both simulated and real data confirm the viability of the proposed algorithm, and DBHU works well, even where both blurring and noise are present in the scene. [ABSTRACT FROM AUTHOR]

The knowledge of the water vapor (WV) distribution in the Earth’s atmosphere is of great importance for weather prediction. Meteorological models, in particular, the so-called limited area models, can assimilate humidity measurements, increasing the reliability of the simulated atmospheric dynamics. An important improvement can be achieved, for instance, if we are able to provide the total column with a sufficient precision and accuracy. In this paper, the novel normalized differential spectral attenuation (NDSA) approach is applied to retrieve the vertical profile of WV—and thus the total column—from measurements of differential attenuation signals at microwaves. A forward model (FM) has been used to simulate the ray-tracing of a microwave signal from a transmitter to a receiver in the atmosphere by using the 3-D atmospheric parameters as provided by a numerical weather prediction (NWP) model. From the NDSA measurement, the integrated WV (IWV) content can be directly derived. A further retrieval code is able to invert the measurements of IWV along the path length, providing the vertical humidity profile, which is directly related to the total vertical column assimilated by weather prediction models. In this paper, we show that the values of the total column can be retrieved with a precision and accuracy up to about 0.6% and 2.1%, respectively, which could have a positive impact on NWP models at short time scale. [ABSTRACT FROM AUTHOR]

In this paper, we analyze the effect of spatial and spectral compression on the performance of statistically based retrieval. Although the quality of the information is not completely preserved during the coding process, experiments reveal that a certain amount of compression may yield a positive impact on the accuracy of retrievals. We unveil two strategies, both with interesting benefits: either to apply a very high compression, which still maintains the same retrieval performance as that obtained for uncompressed data; or to apply a moderate to high compression, which improves the performance. As a second contribution of this paper, we focus on the origins of these benefits. On the one hand, we show that a certain amount of noise is removed during the compression stage, which benefits the retrievals performance. On the other hand, we analyze the effect of compression on spectral/spatial regularization (smoothing). We quantify the amount of information shared among the spatial neighbors for the different methods and compression ratios. We also propose a simple strategy to specifically exploit spectral and spatial relations and find that, when these relations are taken into account beforehand, the benefits of compression are reduced. These experiments suggest that compression can be understood as an indirect way to regularize the data and exploit spatial neighbors information, which improves the performance of pixelwise statistics-based retrieval algorithms. [ABSTRACT FROM AUTHOR]

Most convolutional neural network (CNN)-based cloud detection methods are built upon the supervised learning framework that requires a large number of pixel-level labels. However, it is expensive and time-consuming to manually annotate pixelwise labels for massive remote sensing images. To reduce the labeling cost, we propose an unsupervised domain adaptation (UDA) approach to generalize the model trained on labeled images of source satellite to unlabeled images of the target satellite. To effectively address the domain shift problem on cross-satellite images, we develop a novel UDA method based on grouped features alignment (GFA) and entropy minimization (EM) to extract domain-invariant representations to improve the cloud detection accuracy of cross-satellite images. The proposed UDA method is evaluated on “Landsat- $8~\rightarrow $ ZY-3” and “GF- $1\rightarrow $ ZY-3” domain adaptation tasks. Experimental results demonstrate the effectiveness of our method against existing state-of-the-art UDA approaches. The code of this paper has been made available online (https://github.com/nkszjx/grouped-features-alignment). [ABSTRACT FROM AUTHOR]

Beginning with 2013 IEEE Geoscience and Remote Sensing Society has a new publication: the IEEE Geoscience and Remote Sensing Magazine. The magazine provides a new venue to publish high quality technical articles that by their very nature do not find a home in journals requiring scientific innovation but that provide relevant information to scientists, engineers, end-users, and students who interact in different ways with the geoscience and remote sensing disciplines. The magazine will publish tutorial papers and technical papers on geoscience and remote sensing topics, as well as papers that describe relevant applications of and projects based on topics addressed by our society. This call for papers is to encourage all readers to prepare and submit articles and technical content for review to be published in the IEEE Geoscience and Remote Sensing Magazine. Contributions for the above-mentioned columns of the magazine are also welcome. All technical papers will undergo blind review by multiple reviewers. The submission and the review process are managed at the IEEE Manuscript Central as it is already done for the three GRSS journals. Prospective authors are required to submit electronically using the website http://mc.manuscriptcentral.com/grs and selecting the "Geoscience and Remote Sensing Magazine" option from the drop-down list. Instructions for creating new user accounts, if necessary, are available on the login screen. No other manners of submission are accepted. Papers should be submitted in single column, double-spaced format. The review process will assess the technical quality and/or the tutorial value of the contributions. The magazine will publish also special issues. Readers who are interested to propose a special issue can contact the Editor-in-Chief (EiC). [ABSTRACT FROM PUBLISHER]

Dense stereo image matching in remotely sensed images is a challenging problem, though it has been studied for more than two decades, due to occlusions, discontinuities, geometric, and radiometric distortions. A novel multiobjective fitness function-based dense stereo matching approach using genetic algorithms (GAs) is proposed in this paper. The proposed method is useful for estimating dense disparity map with an improved number of inliers for a stereo image pair, despite the constraint of finding correct disparity at depth discontinuities. In this paper, the steps of GA, such as initialization of the population, fitness function, and crossover and mutation operation, are designed and implemented to effectively deal with the problem of dense stereo image matching. To initialize the population, a Scale Invariant Feature Transform (SIFT) descriptor is computed for each pixel and multiple-size window-based matching is performed, using the similarity measures: 1) Euclidean distance and 2) spectral angle mapper. The generated disparity maps are pruned to choose a suitable subset using the designed fitness functions, considering the constraints related to stereo image pair, such as epipolar constraint, which encodes the epipolar geometry and the similarity measure that is useful to decide accuracy of the correspondences. The two objective functions are the number of inliers computed using the fundamental matrix and an energy minimization function, considering discontinuities and occlusions. The usefulness of this approach for remotely sensed stereo image pairs is demonstrated by improving the number of inliers and favorably comparing with state-of-the-art dense stereo image matching methods. [ABSTRACT FROM AUTHOR]

Remotely sensed sea-surface temperature (SST) retrievals with a significant positive bias during the occurrence of upwelling phenomena along the southeastern coast of Brazil were reported in our companion paper. As a result, this paper proposes an automated bias correction algorithm to improve the MODIS long-wave multichannel SST (MCSST) retrievals during the abovementioned conditions in this region. In this paper, MODIS daytime SST data (SSTMODIS) and differences between brightness temperatures in MODIS channels 31 and 32 (BT31 − BT32) are analyzed simultaneously with hourly wind surface conditions, in situ SST at 0.3 and 10 m in depth (SSTbuoy03 and SSTbuoy10), and sensible and latent heat fluxes from the Cabo Frio buoy data (at 23° S, 42° W) during 2014. The obtained results show that some upwelling events present air temperature ($T_{\mathrm {air}}$) greater than SSTbuoy03 and low-atmospheric water vapor content. A simultaneous occurrence of these factors during upwelling conditions may lead to a warm-skin layer effect and may cause BT31 to be greater than SSTbuoy03 and BT31 − BT32 to be small (−0.18 °C ± 0.22 °C), affecting the MCSST performance. The proposed bias correction algorithm uses a least-squares curve between SSTbuoy03 and SSTMODIS retrievals when BT31 − BT32 ≤ 0.5 °C (i.e., dry atmospheric conditions). The bias correction algorithm has significantly improved the SSTMODIS bias (RMSE) from 1.43 °C to −0.2 °C (1.60 °C to 0.58 °C) when applied to 22 cloud-free pixels of MODIS during January–March of 2015. [ABSTRACT FROM AUTHOR]

The knowledge about the placement and appearance of lane markings is a prerequisite for the creation of maps with high precision, necessary for autonomous driving, infrastructure monitoring, lanewise traffic management, and urban planning. Lane markings are one of the important components of such maps. Lane markings convey the rules of roads to drivers. While these rules are learned by humans, an autonomous driving vehicle should be taught to learn them to localize itself. Therefore, accurate and reliable lane-marking semantic segmentation in the imagery of roads and highways is needed to achieve such goals. We use airborne imagery that can capture a large area in a short period of time by introducing an aerial lane marking data set. In this paper, we propose a symmetric fully convolutional neural network enhanced by wavelet transform in order to automatically carry out lane-marking segmentation in aerial imagery. Due to a heavily unbalanced problem in terms of a number of lane-marking pixels compared with background pixels, we use a customized loss function as well as a new type of data augmentation step. We achieve a high accuracy in pixelwise localization of lane markings compared with the state-of-the-art methods without using the third-party information. In this paper, we introduce the first high-quality data set used within our experiments, which contains a broad range of situations and classes of lane markings representative of today’s transportation systems. This data set will be publicly available, and hence, it can be used as the benchmark data set for future algorithms within this domain. [ABSTRACT FROM AUTHOR]

So far, the problem of unmixing large or multitemporal hyperspectral data sets has been specifically addressed in the remote sensing literature only by a few dedicated strategies. Among them, some attempts have been made within a distributed estimation framework, in particular, relying on the alternating direction method of multipliers. In this paper, we propose to study the interest of a partially asynchronous distributed unmixing procedure based on a recently proposed asynchronous algorithm. Under standard assumptions, the proposed algorithm inherits its convergence properties from recent contributions in nonconvex optimization, while allowing the problem of interest to be efficiently addressed. Comparisons with a distributed synchronous counterpart of the proposed unmixing procedure allow its interest to be assessed on synthetic and real data. Besides, thanks to its genericity and flexibility, the procedure investigated in this paper can be implemented to address various matrix factorization problems. [ABSTRACT FROM AUTHOR]

This paper examines the attainable performance of various Doppler sublook or subband cross correlation techniques for vessel detection in synthetic aperture radar images. Research from the past two decades claims that these techniques were capable of improving the detection of small ships in challenging maritime environments. Despite many published experimental examples, a thorough analytical investigation corroborating this claim is noticeably absent. This paper is based on a rigorous theoretical analysis founded on the statistical properties of a textured sea surface model in thermal noise with simultaneous consideration of a constant false alarm rate. Emphasis has been placed on the correct accounting for detrimental physical effects caused by the Doppler spectrum being split into nonoverlapping parts, which have not been sufficiently considered in the literature to date. The theoretical results are confirmed via simulations and are substantiated with real RADARSAT-2 data. The analysis in this paper has neither found theoretical nor empirical evidence that sublook correlation techniques outperform the classical detector based on the image magnitude. [ABSTRACT FROM AUTHOR]

Underground hydrocarbon reservoir rocks comprise numerous multiscale irregular pores that significantly affect the mechanical and fluid transport properties of the rock. It is considerably challenging for in situ geological monitoring and laboratory tests to accurately characterize the changes in the interior structure and the corresponding mechanical properties of the rock mass during dynamic excavation processes. The 3-D numerical reconstruction models that are based on the statistical information extracted from X-ray computed tomography (XCT) images provide a feasible method to obtain and characterize the interior pore structures and their effects on the physical responses of reservoir rocks. However, obtaining sufficient high-resolution 2-D XCT images is economically expensive by the traditional fan beam CT scan system. Reconstructing 3-D porous structures by computational methods using statistical information extracted from XCT images usually has low efficiency. Therefore, in this paper, we introduce a novel method to numerically reconstruct natural sandstone rock using a small number of 2-D XCT images. The Bayesian information criterion was used to determine the minimum number of 2-D XCT images required to ensure the expected reconstruction accuracy. A multithread parallel reconstruction scheme was employed to improve the efficiency. The accuracy of the proposed method was verified by comparing the statistical correlation functions, geometrical and topological characteristics, and mechanical properties of pore structures between the reconstructed model and a sandstone prototype. This paper provides a method to achieve fast, economic, and accurate 3-D reconstruction of porous rock. [ABSTRACT FROM AUTHOR]

This paper is devoted to solving a full-wave inverse scattering problem (ISP), which is aimed at retrieving permittivities of dielectric scatterers from the knowledge of measured scattering data. ISPs are highly nonlinear due to multiple scattering, and iterative algorithms with regularizations are often used to solve such problems. However, they are associated with heavy computational cost, and consequently, they are often time-consuming. This paper proposes the convolutional neural network (CNN) technique to solve full-wave ISPs. We introduce and compare three training schemes based on U-Net CNN, including direct inversion, backpropagation, and dominant current schemes (DCS). Several representative tests are carried out, including both synthetic and experimental data, to evaluate the performances of the proposed methods. It is demonstrated that the proposed DCS outperforms the other two schemes in terms of accuracy and is able to solve typical ISPs quickly within 1 s. The proposed deep-learning inversion scheme is promising in providing quantitative images in real time. [ABSTRACT FROM AUTHOR]

The ozone mapping and profiler suite (OMPS) is carried onboard the Suomi National Polar-orbiting Partnership satellite that was launched on October 28, 2011. The OMPS mission objectives concern atmospheric ozone concentrations and their variations in the earth atmosphere. A successful thorough on-orbit sensor calibration enabled current validated operational sensor data record (SDR) stage, providing quality sensor data that meet the requirements and users’ expectations. The calibration coefficients derived from this paper have been successfully used in a life-cycle SDR reprocessing to improve sensor data quality. In this paper, we present our qualitative analyses and the results of OMPS nadir mapper SDR on-orbit calibration, and address current SDR data quality in relation to instrument detector performance, stray light correction, and wavelength registration. Our OMPS SDR calibration experience sets a reference for the successor instruments for accurate long-term monitoring of ozone total column concentrations. [ABSTRACT FROM AUTHOR]

Scene classification of remote sensing images has drawn great attention because of its wide applications. In this paper, with the guidance of the human visual system (HVS), we explore the attention mechanism and propose a novel end-to-end attention recurrent convolutional network (ARCNet) for scene classification. It can learn to focus selectively on some key regions or locations and just process them at high-level features, thereby discarding the noncritical information and promoting the classification performance. The contributions of this paper are threefold. First, we design a novel recurrent attention structure to squeeze high-level semantic and spatial features into several simplex vectors for the reduction of learning parameters. Second, an end-to-end network named ARCNet is proposed to adaptively select a series of attention regions and then to generate powerful predictions by learning to process them sequentially. Third, we construct a new data set named OPTIMAL-31, which contains more categories than popular data sets and gives researchers an extra platform to validate their algorithms. The experimental results demonstrate that our model makes great promotion in comparison with the state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Snow albedo plays an important role in the global climate system. There are notable missing data and error uncertainties in the current remote sensing snow albedo products that are attributed to the limits of remote-sensing technology. Due to the uncertainties of meteorological factors and the differences in various forward model simulation methods, snow albedo forward simulations also have considerable uncertainties. This paper suggests a long-time-series reconstruction of snow albedo utilizing a forward radiation-transferring model and a remote-sensing retrieval model together with multisource remotely sensed data and meteorological data. The key to this paper is to estimate snow information for areas lacking data utilizing a forward model for snow albedo with clear physical mechanisms. The estimated snow information can be used as reliable data for snow albedo reconstructions. The results indicate that the long time series of snow albedo data obtained by coupling the snow albedo retrieval model and forward simulation model is highly accurate. The mean absolute error, root mean square error, Pearson’s correlation coefficient (R), and Nash–Sutcliffe efficiency coefficient of the observed and reconstructed snow albedos are 0.11, 0.14, 0.79, and 0.69, respectively. The reconstructed snow albedo data are underestimated by only 11% relative to the in situ snow surface albedo measurements. In the alpine mountain regions, the proposed method has a simulation accuracy that is 6% greater than that of the MOD10A1 SAD. This paper provides an effective reconstruction solution that improves the accuracy of estimations of snow albedo and fills gaps in the data. [ABSTRACT FROM AUTHOR]

This paper presents a novel approach to automatically detect and count cars in different aerial images, which can be satellite or unmanned aerial vehicle (UAV) images. Variations in satellite and/or UAV data make it particularly challenging to have a robust method that works properly on a variety of images. A solution based on the bag-of-words (BoW) model is explored in this paper due to its invariance characteristic and highly stable performance in object/scene categorization. Different from categorization tasks, vehicle detection needs to localize the positions of cars in images. To make BoW suitable for this purpose, we extensively improve the methodology in three aspects, namely, by introducing a recently proposed feature representation, i.e., the local steering kernel descriptor, adding spatial structure constraints, and developing an orientation aware scanning mechanism to produce detection with “one-window-one-car” results. Experiments are conducted on various aerial images with large variations, which consist of data from two public databases, e.g., the Overhead Imagery Research Data Set and Vehicle Detection in Aerial Imagery, as well as other satellite and UAV images. The results demonstrate the effectiveness and robustness of the proposed method. Compared with existing techniques, the proposed method is applicable to a wider range of aerial images. [ABSTRACT FROM AUTHOR]

A generalized continuous wave synthetic aperture radar (GCW-SAR) concept is proposed in this paper. By using full-duplex radio frontend and continuous wave signaling, the GCW-SAR system can overcome a number of limitations inherent within the existing SAR systems and achieve high-resolution and wide-swath remote sensing with low-power signal transmission. Unlike the conventional pulsed SAR and the frequency-modulated continuous-wave SAR, the GCW-SAR reconstructs a radar image by directly correlating the received 1-D raw data after self-interference cancellation with predetermined location-dependent reference signals. A fast imaging algorithm, called the piecewise constant Doppler (PCD) algorithm, is also proposed, which produces the radar image recursively in the azimuth direction without any intermediate step, such as range compression and migration compensation, as required by conventional algorithms. By removing the stop-and-go assumption or slow-time sampling in azimuth, the PCD algorithm not only achieves better imaging quality but also allows for more flexible waveform and system designs. Analyses and simulations show that the GCW-SAR tolerates significant self-interference and works well with a large selection of various system parameters. The work presented in this paper establishes a solid theoretical foundation for next-generation imaging radars. [ABSTRACT FROM AUTHOR]

In this paper, a new joint spectral–spatial subpixel mapping model is proposed for hyperspectral remotely sensed imagery. Conventional approaches generally use an intermediate step based on the derivation of fractional abundance maps obtained after a spectral unmixing process, and thus the rich spectral information contained in the original hyperspectral data set may not be utilized fully. In this paper, a concept of subpixel abundance map, which calculates the abundance fraction of each subpixel to belong to a given class, was introduced. This allows us to directly connect the original (coarser) hyperspectral image with the final subpixel result. Furthermore, the proposed approach incorporates the spectral information contained in the original hyperspectral imagery and the concept of spatial dependence to generate a final subpixel mapping result. The proposed approach has been experimentally evaluated using both synthetic and real hyperspectral images, and the obtained results demonstrate that the method achieves better results when compared to other seven subpixel mapping methods. The numerical comparisons are based on different indexes such as the overall accuracy and the CPU time. Moreover, the obtained results are statistically significant at 95% confidence. [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]

The infrared atmospheric sounder interferometer (IASI) onboard the Metop-A and Metop-B satellites is an essential instrument for numerical weather prediction centers. The IASI, with its 8461 channels, enables the observation of the surface and atmospheric geophysical variables twice a day around the world. This data volume will increase in the future, stressing the need for practical and efficient dimension reduction techniques for storage and transmission but also for inversion or assimilation. In a previous paper by Aires et al., a new dimension reduction method, the so-called bottleneck channel (BC), has been introduced. BCs are a good compromise between compression and channel selection techniques. In this paper, we introduce several new technical configurations of the BC approach, comparing their advantages/drawbacks. Comparisons are also made with two classical methodologies widely used in the satellite community: principal component analysis (PCA) compression and entropy reduction channel selection. Beyond the compression ability, the methodologies are tested on the temperature, water vapor, and ozone retrieval application using IASI measurements. Two approaches have been tested. First, theoretical retrieval improvement has been measured when using the various data reduction techniques. The BC achieves good theoretical improvements, comparable to noise-adjusted PCA (NAPCA), for the retrieval of the temperature, water vapor, and ozone. Second, a neural network inversion scheme is tested on real IASI observations using the several data reduction techniques. It is shown that BCs provide similar or better results than the other methods. The BCs present compression, denoising, and information content results comparable to the NAPCA, while preserving the physical meaning (i.e., actual channel brightness temperatures) of a channel selection approach. This has numerous advantages for inversion and assimilation: the mixing problem, contamination effects, minor constituents representation, or radiative transfer speed, and each of these will be discussed. [ABSTRACT FROM AUTHOR]

In this paper, monitoring of metal-cased oil wells using the ultrawideband (UWB) radar is proposed. The inspection includes the detection and imaging of perforations and corroded areas in a metal pipe. Detection of small anomalies/ perforations on the surface of a narrow metal pipe is very challenging. Here, we present a method for imaging such small anomalies based on the extra time delay of the reflected pulse due to the effect of perforation in the radar near field. In this paper, the necessary concepts for the use of UWB radar specified for this application are developed and proved based on different measurement and simulation scenarios. We have experimentally demonstrated the effect of the perforations’ size on the time delay of reflected pulses. The distance between the perforation and the radar, for the near-field phenomenon, is critical for an effective detection and imaging. Therefore, we also studied the optimal distance between the radar and the perforation. Perforations with a size range of 1–3 cm are considered for the experiments and simulations. The experiments are done both in air and diesel. Synthetic aperture radar processing is used to reconstruct the images of the perforations and corroded area. Measurement and simulation results demonstrate the potential of UWB radar systems for oil well monitoring applications. [ABSTRACT FROM AUTHOR]

Salt marsh vegetation extent and zonation are often controlled by bottom up factors determined in part by the frequency and duration of tidal inundation. Tidal inundation during remote-sensing mapping of salt marsh resources can alter the resulting image classification. The degree of this impact on mapping with very high resolution (VHR) imagery has yet to be determined. This paper utilizes topobathymetric light detection and ranging (LiDAR) data and bathtub models of a tidal stage at 5 cm intervals from mean low water (MLW) to mean high water (MHW) and determines the impact of tidal variation in salt marsh mapping within Jamaica Bay, NY, USA. Tidal inundation models were compared with the Worldview-2 and Quickbird-2 imageries acquired at a range of tidal stages. The modeled inundation of normalized difference vegetation index and smooth cordgrass (S. alterniflora) maps was compared from MLW to MHW. This paper finds that at 0.6 m above MLW, only 3.5% of S. alterniflora is inundated. This paper demonstrates a modeling approach integrating VHR satellite remote-sensing data and topobathymetric LiDAR data to address tidal variation in salt marsh mapping. The incremental modeling of the tidal stage is important for understanding areas most at risk from sea level rise and informs management decisions in accordance with this. [ABSTRACT FROM AUTHOR]

This paper proposes a novel method based on deformable dictionary learning for detecting the regions of change between multitemporal image pairs. We build on our previous work, which constructed a pair of dictionaries. The main shortcoming of this method was its dependence on a large amount of training data. In practice, there is often a shortage of ground-truthed training images, which limits the expression capability of the resulting dictionaries. This paper overcomes this challenge by incorporating the concept of deformation, wherein each atom of a dictionary is no longer a simple image patch, but instead is a flexible image deformation function. This enables the creation of more expressive dictionaries, capable of generalizing to a far greater variety of image patterns, while using a far smaller amount of ground-truthed images for supervised dictionary training. Deformation similarity is employed for patch matching to find the best set of atoms in the difference image (DI) dictionary for reconstructing image patches for a new input DI. Each such atom can be deformed to achieve a better match, thus extending generality while reducing the number of atoms needed in the dictionary. Multiple deformed atoms are weighted and combined to best reconstruct the input DI patch. Then, the same set of deformations and weights is projected to the corresponding atoms in the CD dictionary to obtain the output change-detection map. Experiments in six realistic synthetic aperture radar data sets demonstrate the robustness and efficiency of the proposed method in comparison with five other state-of-the-art methods from the literature. [ABSTRACT FROM AUTHOR]

Classification is an important technique for remote sensing data interpretation. In order to enhance the performance of a supervised classifier and ensure the lowest possible cost of the training samples used in the process, active learning (AL) can be used to optimize the training sample set. At the same time, integrating spatial information can help to enhance the separability between similar classes, which can in turn reduce the need for training samples in AL. To effectively integrate spatial information into the AL framework, this paper proposes a new active relearning (ARL) model for remote sensing image classification. In particular, our model is used to relearn the spatial features on the classification map, which contributes significantly to enhancing the performance of the classifier. We integrate the relearning model into the AL framework, with the aim to accelerate the convergence of AL and further reduce the labeling cost. Under the newly developed ARL framework, we propose two spatial–spectral uncertainty criteria to optimize the procedure for selecting new training samples. Furthermore, an adaptive multiwindow ARL model is also introduced in this paper. Our experiments with two hyperspectral images and two very high resolution images indicate that the ARL model exhibits faster convergence speed with fewer samples than traditional AL methods. Our results also suggest that the proposed spatial–spectral uncertainty criteria and the multiwindow version can further improve the performance when implementing ARL. [ABSTRACT FROM AUTHOR]

It has been previously demonstrated that it is possible to perform remote vibrometry using synthetic aperture radar (SAR) in conjunction with the discrete fractional Fourier transform (DFrFT). Specifically, the DFrFT estimates the chirp parameters (related to the instantaneous acceleration of a vibrating object) of a slow-time signal associated with the SAR image. However, ground clutter surrounding a vibrating object introduces uncertainties in the estimate of the chirp parameter retrieved via the DFrFT method. To overcome this shortcoming, various techniques based on subspace decomposition of the SAR slow-time signal have been developed. Nonetheless, the effectiveness of these techniques is limited to values of signal-to-clutter ratio ≥5 dB. In this paper, a new vibrometry technique based on displaced-phase-center antenna (DPCA) SAR is proposed. The main characteristic of a DPCA-SAR is that the clutter signal can be canceled, ideally, while retaining information on the instantaneous position and velocity of a target. In this paper, a novel method based on the extended Kalman filter (EKF) is introduced for performing vibrometry using the slow-time signal of a DPCA-SAR. The DPCA-SAR signal model for a vibrating target, the mathematical characterization of the EKF technique, and vibration estimation results for various types of vibration dynamics are presented. [ABSTRACT FROM AUTHOR]

Recently, multifeature learning in collaborative representation classification (CRC) for hyperspectral images has generated promising performance. In this paper, two novel multifeature learning algorithms that update dictionary directly and indirectly are proposed. In order to offer the complementarity of multifeature, four different types of features—global feature (i.e., Gabor feature), local feature (i.e., local binary pattern), shape feature (i.e., extended multiattribute profiles), and spectral feature—are adopted in this paper. Under the hypothesis that most of the features should share the same coding pattern in CRC, this paper proposes to learn proper dictionaries for each feature until obtaining stable codes in a linear classifier. Furthermore, to avoid the explicit mapping of infinite-dimensional dictionaries in a nonlinear kernelized classifier, an indirect approach to construct the transformation matrix from original dictionaries to learn new dictionaries is developed. Three real hyperspectral images acquired from different sensors are adopted for performance evaluation. The experimental results demonstrate that the proposed methods can provide superior performance compared with those of the state-of-the-art classifiers. [ABSTRACT FROM AUTHOR]

Focusing on open forests and woodlands within the Injune Landscape Collaborative Project research area in central southeast Queensland, Australia, and using dual-pol (HH and HV) ALOS PALSAR repeat-pass InSAR data (temporal baseline of 92 days), this paper explores the detection of forest disturbance from the spaceborne repeat-pass InSAR correlation magnitude by developing a simple and efficient forest disturbance detection approach. In particular, a generic physical InSAR scattering model is derived by accounting for the forest disturbance information as well as the normal temporal decorrelation effects that are later compensated for using the modified Random Volume over Ground model. Based on the generic model, a quantitative indicator of forest disturbance is retrieved, namely, disturbance index that varies from 0 (no disturbance) to 1 (complete deforestation). This index is compared with that identified using a time series of Landsat sensor data over a selective logging area and has a relative root mean square error of 13% at a spatial resolution of 0.8 ha. This paper highlights the use of the co-pol InSAR correlation magnitude for forest disturbance detection, which serves as a complimentary application to using the cross-pol counterpart for forest height inversion in a companion work. Given the global availability of this type of data (e.g., Japanese Aerospace Exploration Agency’s ALOS-1/2 and NASA-ISRO’s NISAR), the method is anticipated to contribute to the range of tools being developed for large-scale forest disturbance assessment and monitoring. [ABSTRACT FROM AUTHOR]

Surface roughness is a land-surface parameter that is widely used in terrain analysis. Some typical roughness details, which have important effects on surface analysis, fail to be characterized on previous roughness maps. The objective of this paper is to provide a more accurate small-to-large scale roughness overview. The new roughness method is designed based on a complete orthogonal system called the V-system. The V-system roughness utilizes the special functions to detect and extract the roughness characteristics from high-resolution digital elevation models (DEMs). In this paper, Lunar Orbiter Laser Altimeterderived DEMs are used as the source data for the roughness calculation. Compared with the global root-mean-square slope and Fourier-based roughness maps, the V-system roughness maps show that more typical roughness details have been added to clearly indicate the small roughness variations on the large map. Furthermore, the reliability and practicability of V-system roughness are demonstrated based on the multiresolution DEMs. As an example, the statistical parameters of the roughness characteristics in the lunar Maria and highlands identify the fact that the highlands are rougher at all scales than the Maria. And this difference corresponds to the basic roughness property. [ABSTRACT FROM AUTHOR]

This paper investigated the sensitivity of passive microwave L-band soil moisture (SM) retrieval from multiangle airborne brightness temperature data obtained under morning and afternoon conditions from the National Airborne Field Experiment conducted in southeast Australia in 2006. Ground measurements at a dryland focus farm including soil texture, soil temperature, and vegetation water content were used as ancillary data to drive the retrieval model. The derived SM was then in turn evaluated with the ground-measured near-surface SM patterns. The results of this paper show that the Soil Moisture and Ocean Salinity target accuracy of 0.04 m3·m-3 for single-SM retrievals is achievable irrespective of the 6 A.M. and 6 P.M. overpass acquisition times for moisture conditions≥0.15 m3·m-3. Additional tests on the use of the air temperature as proxy for the vegetation temperature also showed no preference for the acquisition time. The performance of multiparameter retrievals of SM and an additional parameter proved to be satisfactory for SM modeling--independent of the acquisition time--with root-mean-square errors less than 0.06 m3·m-3 for the focus farm. [ABSTRACT FROM AUTHOR]

Pansharpening usually refers to the fusion of a high spatial resolution panchromatic (PAN) image with a higher spectral resolution but coarser spatial resolution multispectral (MS) image. Owing to the wide applicability of related products, the literature has been populated by many papers proposing several approaches and studies about this issue. Many solutions require a preliminary spectral matching phase wherein the PAN image is matched with the MS bands. In this paper, we propose and properly justify a new approach for performing this step, demonstrating that it yields state-of-the-art performance. The comparison with existing spectral matching procedures is performed by employing four data sets, concerning different kinds of landscapes, acquired by the Pléiades, WorldView-2, and GeoEye-1 sensors. [ABSTRACT FROM AUTHOR]

This paper continues an overview of the validation of operational profile retrievals from the Suomi National Polar-Orbiting Partnership (SNPP), with focus here given to the infrared (IR) ozone profile environmental data record (EDR) product. The SNPP IR ozone profile EDR is retrieved using the cross-track IR sounder (CrIS), a Fourier transform spectrometer that measures high-resolution IR earth radiance spectra containing atmospheric state information, namely, vertical profiles of temperature, moisture, and trace gas constituents. The SNPP CrIS serves as the U.S. low earth orbit (LEO) satellite IR sounding system and will be featured on future Joint Polar Satellite System (JPSS) LEO satellites. The operational sounding algorithm is the National Oceanic and Atmospheric Administration-Unique Combined Atmospheric Processing System (NUCAPS), a legacy sounder science team algorithm that retrieves atmospheric profile EDR products, including ozone and carbon trace gases, with optimal vertical resolution under nonprecipitating (clear to partly cloudy) conditions. The NUCAPS ozone profile product is assessed in this paper using extensive global in situ truth data sets, namely, ozonesonde observations launched from ground-based networks and from ocean-based intensive field campaigns, along with numerical weather prediction model output. Based upon rigorous statistical analyses using these data sets, the NUCAPS ozone profile EDRs are determined to meet the JPSS Level 1 global performance requirements. [ABSTRACT FROM AUTHOR]

Supervised approaches classify input data using a set of representative samples for each class, known as training samples. The collection of such samples is expensive and time demanding. Hence, unsupervised feature learning, which has a quick access to arbitrary amounts of unlabeled data, is conceptually of high interest. In this paper, we propose a novel network architecture, fully Conv-Deconv network, for unsupervised spectral-spatial feature learning of hyperspectral images, which is able to be trained in an end-to-end manner. Specifically, our network is based on the so-called encoder-decoder paradigm, i.e., the input 3-D hyperspectral patch is first transformed into a typically lower dimensional space via a convolutional subnetwork (encoder), and then expanded to reproduce the initial data by a deconvolutional subnetwork (decoder). However, during the experiment, we found that such a network is not easy to be optimized. To address this problem, we refine the proposed network architecture by incorporating: 1) residual learning and 2) a new unpooling operation that can use memorized max-pooling indexes. Moreover, to understand the "black box," we make an in-depth study of the learned feature maps in the experimental analysis. A very interesting discovery is that some specific "neurons" in the first residual block of the proposed network own good description power for semantic visual patterns in the object level, which provide an opportunity to achieve "free" object detection. This paper, for the first time in the remote sensing community, proposes an end-to-end fully Conv-Deconv network for unsupervised spectral-spatial feature learning. Moreover, this paper also introduces an in-depth investigation of learned features. Experimental results on two widely used hyperspectral data, Indian Pines and Pavia University, demonstrate competitive performance obtained by the proposed methodology compared with other studied approaches. [ABSTRACT FROM AUTHOR]

Forward-looking ground-penetrating radar (FLGPR) has recently been investigated as a remote-sensing modality for buried target detection (e.g., landmines). In this context, raw FLGPR data are beamformed into images, and then, computerized algorithms are applied to automatically detect subsurface buried targets. Most existing algorithms are supervised, meaning that they are trained to discriminate between labeled target and nontarget imagery, usually based on features extracted from the imagery. A large number of features have been proposed for this purpose; however, thus far it is unclear as to which are the most effective. The first goal of this paper is to provide a comprehensive comparison of detection performance using existing features on a large collection of FLGPR data. Fusion of the decisions resulting from processing each feature is also considered. The second goal of this paper is to investigate two modern feature learning approaches from the object recognition literature: the bag-of-visual words and the Fisher vector for FLGPR processing. The results indicate that the new feature learning approaches lead to the best performing FLGPR algorithm. The results also show that fusion between existing features and new features yields no additional performance improvements. [ABSTRACT FROM AUTHOR]

Panchromatic (PAN) and multispectral (MS) imagery classification is one of the hottest topics in the field of remote sensing. In recent years, deep learning techniques have been widely applied in many areas of image processing. In this paper, an end-to-end learning framework based on deep multiple instance learning (DMIL) is proposed for MS and PAN images' classification using the joint spectral and spatial information based on feature fusion. There are two instances in the proposed framework: one instance is used to capture the spatial information of PAN and the other is used to describe the spectral information of MS. The features obtained by the two instances are concatenated directly, which can be treated as simple fusion features. To fully fuse the spatial-spectral information for further classification, the simple fusion features are fed into a fusion network with three fully connected layers to learn the high-level fusion features. Classification experiments carried out on four different airborne MS and PAN images indicate that the classifier provides feasible and efficient solution. It demonstrates that DMIL performs better than using a convolutional neural network and a stacked autoencoder network separately. In addition, this paper shows that the DMIL model can learn and fuse spectral and spatial information effectively, and has huge potential for MS and PAN imagery classification. [ABSTRACT FROM AUTHOR]

Corner feature matching remains a difficult task for wide-baseline images because of viewpoint distortion, surface discontinuities, and partial occlusions. In this paper, we propose a robust Harris corner matching method based on the quasi-homography transform (QHT) and self-adaptive window. Our method is divided into three steps. First, high-quality Harris corners were extracted from stereo images using optimal detecting, and initial matches were simultaneously acquired by integrating complementary affine-invariant features and the scale-invariant feature transform descriptor. Second, the pair of fundamental matrices was estimated based on the initial matches and improved random sample consensus algorithm. Subsequently, the global QHT was produced by duplicate epipolar geometries. Third, conjugate Harris corners were obtained by combining QHT and normalized cross correlation, and the accuracy of the corresponding points was further improved based on self-adaptive least-squares matching (SALSM). Experiments on six groups of wide-baseline images demonstrate the effectiveness of the proposed method, and a comprehensive comparison with the existing corner matching algorithms indicates that our method has notable superiority in terms of accuracy and distribution. The main contribution of this paper is that the proposed global QHT can reduce the search range effectively for candidates, and the proposed SALSM can notably improve the accuracy of the corresponding corners. [ABSTRACT FROM AUTHOR]

Polarimetric synthetic aperture radar (PolSAR) image classification is a vital application in remote sensing image processing. In general, PolSAR image classification is actually a high-dimensional nonlinear mapping problem. The methods based on sparse representation and deep learning have shown a great potential for PolSAR image classification. Therefore, a novel PolSAR image classification method based on multilayer projective dictionary pair learning (MDPL) and sparse auto encoder (SAE) is proposed in this paper. First, MDPL is used to extract features, and the abstract degree of the extracted features is high. Second, in order to get the nonlinear relationship between elements of feature vectors in an adaptive way, SAE is also used in this paper. Three PolSAR images are used to test the effectiveness of our method. Compared with several state-of-the-art methods, our method achieves very competitive results in PolSAR image classification. [ABSTRACT FROM PUBLISHER]

This paper describes a new model of the seawater dielectric constant as a function of salinity and temperature at L-band. The model function is developed by fitting the accurate measurement data made at 1.413 GHz to a third-order polynomial. The purpose of this study is to provide an accurate model for earth-observing satellites to retrieve seawater salinities from remote sensing data. In this paper, the development of the model function is introduced along with an analysis of the goodness of fit. The model function is then compared with the model functions of Klein-Swift and Meissner-Wentz. Finally, the comparison is made between the retrieved salinity from the satellite data with the in situ data measured by Argo floats. [ABSTRACT FROM PUBLISHER]

The ocean surface current is a very important parameter of ocean dynamic environment. It is connected to global climate change, marine environment forecasting, marine navigation, engineering security, and so on. The observation and prediction of ocean surface current have attracted more and more concern. Doppler Scatterometer (DopScat) is a new type of radar for ocean surface wind and current field remote sensing. The ocean surface current inversion method of DopScat impacts the measurement accuracy directly. In this paper, we establish the simulation model of a DopScat and provide the radial velocity error model. The numerical ocean surface Doppler spectrum model is also introduced and validated with the empirical geophysical model function in C-band (CDOP). The suitable ocean wave elevation spectrum and directional distribution function are selected. What is more, this paper establishes the maximum likelihood estimation (MLE) method to retrieve the ocean surface current and wind simultaneously. The retrieval accuracy for different positions in cross track, different wind speeds, and different current speeds are analyzed. At last, the global ocean current field is observed by DopScat and the ocean current is retrieved. In our simulation, the orbit parameters and observation geometry of DopScat are the same as that of HY-2A scatterometer. The retrieval results show that global current speed standard deviation can be smaller than 0.18 m/s for five days and 0.5 ^\circ \times 0.5 ^\circ grid average. [ABSTRACT FROM PUBLISHER]

This paper analyzes the large positive bias of sea surface temperature (SST) retrievals of selected remotely sensed algorithms recorded during the simultaneous occurrence of upwelling and atmospheric subsidence along the coastal waters of Rio de Janeiro, Brazil. The optimal estimator (OE) for retrieving SST and the multichannel (MCSST) and nonlinear (NLSST) estimators are compared using Advanced Very High Resolution Radiometer-3 data. The in situ SST (SSTbuoy) data set used to validate the remotely sensed SST retrievals was collected from five moored buoys (four in the open sea and one in coastal waters). The principal results of this paper are as follows. First, the sensitivity analyses show that OE is quite susceptible to the first-guess SST rather than to the humidity profiles. Second, the comparison between the SSTOE and 365 cloud-free SSTbuoy measurements in open sea waters presents an root mean squared error (RMSE), bias, and standard deviation (STD) with the intervals of [0.5, 0.6], [−0.51, 0.13], and [0.27, 0.48], respectively. Third, the MCSST, NLSST, and OE SST produce a positive bias that can reach 5 K during simultaneous upwelling and atmospheric subsidence in coastal waters. Such unexpected errors are due to low SST values and water vapor compression in the lower layer of the atmosphere related to a temperature inversion. Fourth, an alternative approach using SSTbuoy obtained on the previous day as a first guess instead of the climatological SST significantly improves the errors (SSTOE–SSTbuoy) by reducing RMSE, bias, and STD by 58% (from 3.30 to 1.39 K), 73% (from 3.00 to 0.80 K), and 19% (from 1.38 to 1.12 K), respectively. [ABSTRACT FROM PUBLISHER]

This paper aims to achieve computationally efficient and high-accuracy subpixel image registration with large displacements under the rotation–scale–translation model. This paper employs the classical phase correlation algorithm and the Lucas–Kanade (LK) algorithm in a two-stage coarse-to-fine framework, for which the motivation is from the observation that the two algorithms exhibit strong complementary property between convergence range and subpixel accuracy. In this framework, the LK algorithm will also become computationally efficient owing to the small residual displacement. On the other hand, this paper takes into account the residual model with respect to the compensation scheme explicitly, and deduces formulas for the final results combination, which is expected to be closer to the true displacement vector and thus further improve the estimation accuracy. Since the compensation can be applied to either the target image or the reference image, two algorithms are presented accordingly, and analysis as well as comparison are also performed. Finally, both simulations and real image experiments are performed to verify the motivation, and the results are consistent with the analysis. [ABSTRACT FROM PUBLISHER]

Detection of small targets, more specifically cars, in aerial images of urban scenes, has various applications in several domains, such as surveillance, military, remote sensing, and others. This is a tremendously challenging problem, mainly because of the significant interclass similarity among objects in urban environments, e.g., cars and certain types of nontarget objects, such as buildings’ roofs and windows. These nontarget objects often possess very similar visual appearance to that of cars making it hard to separate the car and the noncar classes. Accordingly, most past works experienced low precision rates at high recall rates. In this paper, a novel framework is introduced that achieves a higher precision rate at a given recall than the state of the art. The proposed framework adopts a sliding-window approach and it consists of four stages, namely, window evaluation, extraction and encoding of features, classification, and postprocessing. This paper introduces a new way to derive descriptors that encode the local distributions of gradients, colors, and texture. Image descriptors characterize the aforementioned cues using adaptive cell distributions, wherein the distribution of cells within a detection window is a function of its dominant orientation, and hence, neither the rotation of the patch under examination nor the computation of descriptors at different orientations is required. The performance of the proposed framework has been evaluated on the challenging Vaihingen and Overhead Imagery Research data sets. Results demonstrate the superiority of the proposed framework to the state of the art. [ABSTRACT FROM PUBLISHER]

Twelve years (1991–2003) of ERS-1 and ERS-2 altimetry data have been reprocessed within the European Space Agency (ESA) reprocessing altimeter products for ERS (REAPER) project using an updated, modern set of algorithms and auxiliary models. The reprocessed data set (identified as RP01) has been cross-calibrated against the reprocessed ENVISAT V2.1 data. The format of this reprocessed data set is network common data form (version 3). The new data set shows a clear improvement in data quality beyond that of previous releases. The product validation shows reduction of the mean standard deviation of the sea-surface height differences from 8.1 (previously available product) to 6.7 cm (RP01). This paper presents the details of how the reprocessing was conducted and shows selected results from the validation and quality-assurance processes. The major improvements of the REAPER RP01 data set with respect to the previous ESA ERS radar altimetry (RA) products are due to the use of four ENVISAT RA-2 retrackers, RA calibration improvements, new reprocessed precise orbit solutions, ECMWF ERA-interim model for meteorological corrections, new ionospheric corrections, and new sea state. The intent of this paper is to aid the reader in understanding the benefits of the new data set for their particular use-case. [ABSTRACT FROM PUBLISHER]

In this paper, the authors investigate the statistical matching of the panchromatic (Pan) image to the multispectral (MS) bands, also known as the histogram matching, for the two main classes of pansharpening methods, i.e., those based on component substitution (CS) or spectral methods and those based on multiresolution analysis (MRA) or spatial methods. Also, hybrid methods combining CS with MRA, like the widespread additive wavelet luminance proportional (AWLP), are investigated. It is shown that all spectral, spatial, and hybrid methods must perform a dynamics matching of the enhancing Pan to the individual MS bands for MRA or a combination of them (the component that shall be substituted) for CS. For hybrid methods, the problem is more complex and both types of histogram matching may be suitable. Such an intersensor balance may be either explicit or implicitly performed by the detail-injection model, e.g., the popular projective and multiplicative injection models. An experimental setup exploiting IKONOS and WorldView-2 data sets demonstrates that a correct histogram matching is the key to attain extra performance from established methods. As a first result of this paper, the AWLP method has been revisited and its performance significantly improved by simply performing the histogram matching of Pan to the individual MS bands, rather than to the intensity component, thereby losing the original proportionality feature. [ABSTRACT FROM PUBLISHER]

Remote sensing (RS) scene classification is a challenging task due to various land covers contained in RS scenes. Recent RS classification methods demonstrate that aggregating the multilayer convolutional features, which are extracted from different hierarchical layers of a convolutional neural network, can effectively improve classification accuracy. However, these methods treat the multilayer convolutional features as equally important and ignore the hierarchical structure of multilayer convolutional features. Multilayer convolutional features not only provide complementary information for classification but also bring some interference information (e.g., redundancy and mutual exclusion). In this paper, a gated bidirectional network is proposed to integrate the hierarchical feature aggregation and the interference information elimination into an end-to-end network. First, the performance of each convolutional feature is quantitatively analyzed and a superior combination of convolutional features is selected. Then, a bidirectional connection is proposed to hierarchically aggregate multilayer convolutional features. Both the top–down direction and the bottom–up direction are considered to aggregate multilayer convolutional features into the semantic-assist feature and appearance-assist feature, respectively, and a gated function is utilized to eliminate interference information in the bidirectional connection. Finally, the semantic-assist feature and appearance-assist feature are merged for classification. The proposed method can compete with the state-of-the-art methods on four RS scene classification data sets (AID, UC-Merced, WHU-RS19, and OPTIMAL-31). [ABSTRACT FROM AUTHOR]

Change detection has been a hotspot in the remote sensing technology for a long time. With the increasing availability of multi-temporal remote sensing images, numerous change detection algorithms have been proposed. Among these methods, image transformation methods with feature extraction and mapping could effectively highlight the changed information and thus has a better change detection performance. However, the changes of multi-temporal images are usually complex, and the existing methods are not effective enough. In recent years, the deep network has shown its brilliant performance in many fields, including feature extraction and projection. Therefore, in this paper, based on the deep network and slow feature analysis (SFA) theory, we proposed a new change detection algorithm for multi-temporal remotes sensing images called deep SFA (DSFA). In the DSFA model, two symmetric deep networks are utilized for projecting the input data of bi-temporal imagery. Then, the SFA module is deployed to suppress the unchanged components and highlight the changed components of the transformed features. The change vector analysis pre-detection is employed to find unchanged pixels with high confidence as training samples. Finally, the change intensity is calculated with chi-square distance and the changes are determined by threshold algorithms. The experiments are performed on two real-world data sets and a public hyperspectral data set. The visual comparison and the quantitative evaluation have shown that DSFA could outperform the other state-of-the-art algorithms, including other SFA-based and deep learning methods. [ABSTRACT FROM AUTHOR]

Change detection (CD) in heterogeneous multitemporal satellite images is an emerging and challenging topic in remote sensing. In particular, one of the main challenges is to tackle the problem in an unsupervised manner. In this paper, we propose an unsupervised framework for bitemporal heterogeneous CD based on the comparison of affinity matrices and image regression. First, our method quantifies the similarity of affinity matrices computed from colocated image patches in the two images. This is done to automatically identify pixels that are likely to be unchanged. With the identified pixels as pseudotraining data, we learn a transformation to map the first image to the domain of the other image and vice versa. Four regression methods are selected to carry out the transformation: Gaussian process regression, support vector regression, random forest regression (RFR), and a recently proposed kernel regression method called homogeneous pixel transformation. To evaluate the potentials and limitations of our framework and also the benefits and disadvantages of each regression method, we perform experiments on two real data sets. The results indicate that the comparison of the affinity matrices can already be considered a CD method by itself. However, image regression is shown to improve the results obtained by the previous step alone and produces accurate CD maps despite of the heterogeneity of the multitemporal input data. Notably, the RFR approach excels by achieving similar accuracy as the other methods, but with a significantly lower computational cost and with fast and robust tuning of hyperparameters. [ABSTRACT FROM AUTHOR]

The NASA/JAXA Global Precipitation Measurement (GPM) Core Observatory (CO) carries, for the first time, a dual-frequency precipitation radar (DPR) designed to provide insights into the 3-D structure of precipitating clouds and rain intensity by using its Ka- and Ku-band frequencies. Single-frequency (SF) (both Ku- and Ka-only) and double-frequency (DF) based products provide particle-size distribution (PSD) parameters, as well as precipitation rates. Background surface type, precipitation type and phase, and vertical extension of the storm are also provided. In this paper, an intercomparison between the SF and DF DPR outputs over the Mediterranean area during rainfall events in the first four years of GPM-CO mission is carried out. The goal is to investigate the reliability of SF-based products by assessing their quality compared to the DF-based ones, treated as a reference. The vertical profiles and the near-surface values of the corrected reflectivity of the PSD parameters (mean mass-weighted diameter and normalized intercept) and of the rainfall rate have been analyzed. The data have been categorized for surface type (land and sea) and precipitation type (stratiform and convective). The results show a more marked difference between the DF and SF Ka-only based products than between DF and SF Ku-only based products. The feature is confirmed by the analysis of vertical profiles of the SF- and DF-based retrieved parameters. The statistical scores do not differ significantly between land and sea while they differ noticeably between stratiform and convective precipitation. [ABSTRACT FROM AUTHOR]