Search

Sea ice has a significant effect on climate change and ship navigation. Hence, it is crucial to draw sea-ice maps that reflect the geographical distribution of different types of sea ice. Many automatic sea-ice classification methods using synthetic aperture radar (SAR) images are based on the polarimetric characteristics or image texture features of sea ice. They either require professional knowledge to design the parameters and features or are sensitive to noise and condition changes. Moreover, ice changes over time are often ignored. In this article, we propose a new SAR sea-ice image classification method based on a combined learning of spatial and temporal features, derived from residual convolutional neural networks (ResNet) and long short-term memory (LSTM) networks. In this way, we achieve automatic and refined classification of sea-ice types. First, we construct a seven-type ice data set according to the Canadian Ice Service ice charts. We extract spatial feature vectors of a time series of sea-ice samples using a trained ResNet network. Then, using the feature vectors as inputs, the LSTM network further learns the variation of the set of sea-ice samples with time. Finally, the extracted high-level features are fed into a softmax classifier to output the most recent ice type. Taking both spatial features and time variation into consideration, our method can achieve a high classification accuracy of 95.7% for seven ice types. Our method can automatically produce more objective sea-ice interpretation maps, allowing detailed sea-ice distribution and improving the efficiency of sea-ice monitoring tasks. [ABSTRACT FROM AUTHOR]

The extraction of river planforms from remotely sensed satellite images is a task of crucial importance to many applications such as land planning, water resource monitoring, or flood prediction. In this article, we present a novel framework for the extraction of rivers from synthetic aperture radar (SAR) images, based on superpixel segmentation and subsequent classification. Superpixel segmentation is achieved by a modeling of the image pixels’ amplitudes and spatial coordinates as a finite mixture model, where the generalized Gamma distribution is used to model accurately a variety of high-resolution SAR scenes. A number of features describing image texture and statistics are extracted on a superpixel level, facilitating the identification of river superpixels—planforms are then extracted by unsupervised, agglomerative clustering, thus eliminating the need for labeled training data. We present the results of our proposed method on the ICEYE-X2 and SENTINEL-1 SAR data, demonstrating its ability to produce pixel-accurate river masks. [ABSTRACT FROM AUTHOR]

Seabed characterization has utility for numerous applications that seek to explore and interact with the seafloor, ranging from coastal habitat monitoring and subbottom profiling to man-made object detection. In this paper, we characterize seabeds based on the texture patterns within synthetic aperture SONAR (SAS) images constructed from high-frequency side-scan sonar. Features are measured from the SAS images (e.g., lacunarity, an established texture feature coding method, and a circularly shifted histogram of oriented gradients). Based on these SAS image features, we perform unsupervised clustering with a hierarchical Bayesian model, which creates categories of seabed textures. Our clustering algorithm is a new variant of the hierarchical Dirichlet process that is both adaptive to changes in seabeds and processes batches of SAS imagery in an online fashion to learn new seabed types as they are encountered. This allows observations to be clustered, as each batch is processed rather than only after all data have been collected. The model’s performance of seabed characterization by SAS image texture is demonstrated in the overall range and internal consistency of textures specific to each learned cluster with data across a variety of sites. [ABSTRACT FROM AUTHOR]

A novel algorithm is proposed for separating multiple moving targets in radar images in the slow time-range domain. Target discrimination is based on an image texture angle that is related to the target's instantaneous velocity. The algorithm efficiency has been successfully verified for targets with variable velocities. [ABSTRACT FROM PUBLISHER]

This paper focuses on the potential accuracy of remote sensing (RS) image registration. We investigate how this accuracy can be estimated without ground truth available and used to improve registration quality of mono- and multimodal pair of images. At the local scale of image fragments, the Cramér–Rao lower bound (CRLB) on registration error is estimated for each local correspondence between coarsely registered pair of images. This CRLB is defined by local image texture and noise properties. Opposite to the standard approach, where registration accuracy is only evaluated at the output of the registration process, such valuable information is used by us as an additional input knowledge. It greatly helps in detecting and discarding outliers and refining the estimation of geometrical transformation model parameters. Based on these ideas, a new area-based registration method called registration with accuracy estimation (RAE) is proposed. In addition to its ability to automatically register very complex multimodal image pairs with high accuracy, the RAE method is able to provide registration accuracy at the global scale as a covariance matrix of estimation error of geometrical transformation model parameters or as pointwise registration standard deviation. This accuracy does not depend on any ground truth availability and characterizes each pair of registered images individually. Thus, the RAE method can identify image areas for which a predefined registration accuracy is guaranteed. This is essential for RS applications imposing strict constraints on registration accuracy such as change detection, image fusion, and disaster management. The RAE method is proved successful with reaching subpixel accuracy while registering eight complex mono-/multimodal and multitemporal image pairs including optical-to-optical, optical-to-radar, optical-to-digital elevation model (DEM) images, and DEM-to-radar cases. Other methods employed in comparisons fail to provide in a stable manner accurate results on the same test cases. [ABSTRACT FROM PUBLISHER]

Remote sensing images exhibit significant contrast and intensity regions and edges, which makes them highly suitable for using different texture features to properly represent and classify the objects that they contain. In this paper, we present a new technique based on multiple morphological component analysis (MMCA) that exploits multiple textural features for decomposition of remote sensing images. The proposed MMCA framework separates a given image into multiple pairs of morphological components (MCs) based on different textural features, with the ultimate goal of improving the signal-to-noise level and the data separability. A distinguishing feature of our proposed approach is the possibility to retrieve detailed image texture information, rather than using a single spatial characteristic of the texture. In this paper, four textural features: content, coarseness, contrast, and directionality (including horizontal and vertical), are considered for generating the MCs. In order to evaluate the obtained MCs, we conduct classification by using both remotely sensed hyperspectral and polarimetric synthetic aperture radar (SAR) scenes, showing the capacity of the proposed method to deal with different kinds of remotely sensed images. The obtained results indicate that the proposed MMCA framework can lead to very good classification performances in different analysis scenarios with limited training samples. [ABSTRACT FROM PUBLISHER]

This paper deals with area-based subpixel image registration under the rotation-isometric scaling-translation transformation hypothesis. Our approach is based on parametrical modeling of geometrically transformed textural image fragments and maximum-likelihood estimation of the transformation vector between them. Due to the parametrical approach based on the fractional Brownian motion modeling of the local fragments' texture, the proposed estimator \mboxML_\mathrmfBm (ML stands for “maximum likelihood” and fBm stands for “fractal Brownian motion”) has the ability to better adapt to real image texture content compared with other methods relying on universal similarity measures such as mutual information or normalized correlation. The main benefits are observed when assumptions underlying the fBm model are fully satisfied, e.g., for isotropic normally distributed textures with stationary increments. Experiments on both simulated and real images and for high and weak correlations between registered images show that the \mboxML_\mathrmfBm estimator offers significant improvement compared with other state-of-the-art methods. It reduces translation vector, rotation angle, and scaling factor estimation errors by a factor of about 1.75–2, and it decreases the probability of false match by up to five times. In addition, an accurate confidence interval for \mboxML_\mathrmfBm estimates can be obtained from the Cramér–Rao lower bound on rotation-scaling-translation parameter estimation error. This bound depends on texture roughness, noise level in reference and template images, correlation between these images, and geometrical transformation parameters. [ABSTRACT FROM AUTHOR]

The thermal noise-induced distortions in a Sentinel-1 terrain observation with progressive scans synthetic aperture radar image cannot be corrected by the noise equivalent sigma nought (NESZ) subtraction only. Since the thermal noise is scaled during synthetic aperture radar processing, it resides not only as an additive noise in each pixel but also as a multiplicative noise in the interpixel contrast. In this paper, we investigate the noise characteristics and propose an efficient method for the multiplicative textural noise correction. The core ideas are to find the optimal coefficient of the noise-induced standard deviation (SD) and model the noise contribution to the local SD as a function of the NESZ and the signal-to-noise ratio. Denoising is accomplished by a subwindow-wise adaptive rescaling of the pixel values. The improvements in the first- and second-order statistical textural features demonstrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

This paper investigates the synthetic aperture radar (SAR) image segmentation in terms of feature analysis and fusion and develops a new algorithm based on multifeature ensemble accordingly. This paper is characterized by two aspects. First, multiple heterogeneous features are extracted to accurately describe the objects in SAR images. These features are then integrated in the feature level and the similarity level, respectively, to avoid the mutual influences between different kinds of features and maximize the discriminability of the similarity measure between objects. Second, a two-stage algorithm consisting of a coarse merging stage and a fine classification stage is proposed. In the coarse merging stage, a context-based region iterative merging algorithm is designed to merge most of the unambiguous superpixels in image domain at a high speed. In the fine classification stage, a fuzzy clustering algorithm incorporating hybrid optimization is developed to balance the efficiency and the robustness of the algorithm by simultaneously searching heuristically in the complete high-dimension feature space and searching along the direction of the gradient steepest descent in each feature subspace. The effectiveness of the proposed method has been successfully validated on synthetic and real SAR images. [ABSTRACT FROM PUBLISHER]

Deep learning (DL) methods usually need to collect a large amount of labeled data to extract deep features. However, due to the difficulty of obtaining numerous labeled data from synthetic aperture radar (SAR) images, unsupervised feature learning has been focused on SAR image processing. In this article, we propose a 3-D sparse model (3-DSM) to extract deep sparse features from SAR images in an unsupervised way. Concretely, 3-DSM learns the convolution kernels by minimizing the error between the features and the constructed sparse maps, without labeled samples. Thus, the discriminative features can be extracted in an unsupervised way by the learned convolution kernels and are able to capture the main structural information of SAR images. Furthermore, to the best of our knowledge, 3-DSM first specifies the sparsity of convolution kernels, with each convolution kernel exhibiting its independence from the others and the redundancy of convolution kernels being diminishing. It means that each convolution kernel extracts its unique structural features of SAR images. Consequently, in the feature extraction, 3-D sparsities have been specified, including width, height, and depth, with the acquisition of discriminative less-redundant features. The effectiveness of 3-DSM is demonstrated by the feature extraction and segmentation of the simulated and real SAR images. [ABSTRACT FROM AUTHOR]

Reducing the feature distribution shift caused by the factor of visual-environment changes, named visual-environment changes (VE-changes), is a hot issue in domain adaptation learning. However, in the semantic segmentation task of remote sensing imageries, besides VE-changes, the change of semantic-scene changes (SS-changes) is another factor raising the domain gap, which brings the label distribution shift. For example, although urban and rural share the same landcover label, there is still a gap in label distribution. If there is little relation that can be found in neither feature nor label space, forcibly adapting to a new domain could have a high risk of negative transfer. Hence, we propose a new Transitive Domain Adaptation method for Remote Sensing (TDARS) images. First, we introduce an intermediate domain to enlarge the relation between the given source and target domains. Second, we learn from primary and nonprimary confident classes to increase the likelihood of transferring valuable information. As a result, TDARS enables the given source and target domains to be connected through the selected intermediate domain and performs effective knowledge transfer among all domains. The proposed method is evaluated on three domain adaptation datasets of remote sensing images. Extensive experiments show that the approach can effectively handle the domain shift problem from remote sensing images compared to other state-of-the-art domain adaptation methods. [ABSTRACT FROM AUTHOR]

Damaged building detection from remote sensing imagery helps to quickly and rapidly assess losses after an earthquake. In recent years, deep learning technology has become a favorable tool for remote sensing image information detection. Based on the characteristics of damaged buildings in remote sensing images, in this article, a framework for damaged building detection that considers heterogeneity characteristics is proposed. First, a local–global context attention module is proposed to improve the feature detection ability of the network, which can extract the features of damaged buildings from different directions and effectively aggregate global and local features. In addition, the module takes the correlation between feature maps at different scales into account while extracting information. Second, a feature fusion module with self-attention is established to replace the simple connection between the encoding and decoding processes, which improves the detail feature recovery ability of the network during the upsampling process. Finally, to fully aggregate semantic and detailed features at different scales, a multibranch auxiliary classifier is established by adding two separate branches in the prediction stage. The effectiveness of the proposed approach is verified based on the data from the 2010 Haiti earthquake, and comparisons with three object-oriented methods and 16 existing excellent deep learning models are performed. The intersection over union (IOU) increase of 0.03%–7.39% is achieved using the proposed approach compared with excellent deep learning models. [ABSTRACT FROM AUTHOR]

The autonomous real-time optical navigation of planetary unmanned aerial vehicle (UAV) is of the key technologies to ensure the success of the exploration. In such a GPS-denied environment, vision-based localization is an optimal approach. In this article, we proposed a terrain aided simultaneous localisation and mapping (SLAM) algorithm, which simultaneously reconstructs the 3-D map point of environment and estimates the location of a planet UAV based on preexisting digital elevation model (DEM). To directly georeference the onboard UAV images to the digital terrain model, a theoretical model is proposed to prove that topographic features of UAV image and DEM can be correlated in the frequency domain via cross power spectrum. To provide the six-DOF of the UAV, we developed an optimization approach, which fuses the geo-referencing result into an SLAM system via local bundle adjustment (LBA) to achieve robust and accurate vision-based navigation even in featureless planetary areas. To test the robustness and effectiveness of the proposed localization algorithm, a new dataset for planetary drone navigation is proposed based on simulation engine. The proposed dataset includes 40 200 synthetic drone images taken from nine planetary scenes with related DEM query images. Comparison experiments are carried out to demonstrate that over the flight distance of 33.8 km, the proposed method achieved an average localization error of 0.45 m, compared to 1.32 m by ORB-SLAM2 and 0.75 m by ORB-SLAM3, with the processing speed of 12 Hz, which will ensure real-time performance. We will make our datasets available to encourage further work on this topic. [ABSTRACT FROM AUTHOR]

Hyperspectral imaging (HSI) greatly improves the capacity to identify and monitor ground objects due to the high spectral resolution. As the real-time remote sensing monitoring and warning tasks are getting more attention, new algorithms for low-power on-board classification are required to reduce the transmission time of satellite downlink. In this article, we propose the multiscale local maximum random forest (MSLM-RF) to significantly reduce energy consumption while retaining high classification accuracy. The proposed MSLM-RF uses multiscale maximum filters for spatial feature extraction and random forest for classification after spectral and spatial features fusion. The spatial features are efficiently extracted with low computational complexity by regarding the maximum light intensity values in different ranges of pixels as anchor points. MSLM-RF only consists of integer comparisons and a few additions, thereby eliminating the energy-hungry operations such as multiplication and exponentiation. According to experimental results on the HSI benchmark datasets, MSLM-RF delivers a better tradeoff in accuracy and computational complexity than the state-of-the-art classification algorithms. Besides, MSLM-RF gets higher average classification accuracy and lower energy consumption than the previous on-board algorithms. The obtained results show the suitability of the proposed algorithm to accomplish practical real-time classification tasks on-board with low energy consumption. [ABSTRACT FROM AUTHOR]

For the design of present and next-generation spaceborne SAR missions, constantly increasing data rates are being demanded, which impose stringent requirements in terms of onboard memory and downlink capacity. In this scenario, the efficient quantization of SAR raw data is of primary importance since the utilized compression rate is directly related to the volume of data to be stored and transmitted to the ground, and at the same time, it affects the resulting SAR imaging performance. In this article, we introduce the performance-optimized block-adaptive quantization (PO-BAQ), a novel approach for SAR raw data compression that aims at optimizing the resource allocation and, at the same time, the quality of the resulting SAR and InSAR products. This goal is achieved by exploiting the a priori knowledge of the local SAR backscatter statistics, which allows for the generation of high-resolution bitrate maps that can be employed to fulfill a predefined performance requirement. Analyses of experimental TanDEM-X interferometric data are presented, which demonstrates the potential of the proposed method as a helpful tool for performance budget definition and data rate optimization of present and future SAR missions. [ABSTRACT FROM AUTHOR]

A major yet largely unsolved problem in the semantic classification of very high resolution remote sensing images is the design and selection of appropriate features. At a ground sampling distance below half a meter, fine-grained texture details of objects emerge and lead to a large intraclass variability while generally keeping the between-class variability at a low level. Usually, the user makes an educated guess on what features seem to appropriately capture characteristic object class patterns. Here, we propose to avoid manual feature selection and let a boosting classifier choose optimal features from a vast Randomized Quasi-Exhaustive (RQE) set of feature candidates directly during training. This RQE feature set consists of a multitude of very simple features that are computed efficiently via integral images inside a sliding window. This simple but comprehensive feature candidate set enables the boosting classifier to assemble the most discriminative textures at different scale levels to classify a small number of broad urban land-cover classes. We do an extensive evaluation on several data sets and compare performance against multiple feature extraction baselines in different color spaces. In addition, we verify experimentally if we gain any classification accuracy if moving from boosting stumps to trees. Cross-validation minimizes the possible bias caused by specific training/testing setups. It turns out that boosting in combination with the proposed RQE feature set outperforms all baseline features while still remaining computationally efficient. Particularly boosting trees (instead of stumps) captures class patterns so well that results suggest to completely leave feature selection to the classifier. [ABSTRACT FROM PUBLISHER]

This paper presents a new spectral-spatial classification method for hyperspectral images via morphological component analysis-based image separation rationale in sparse representation. The method consists of three main steps. First, the high-dimensional spectral domain of hyperspectral images is reduced into a low-dimensional feature domain by using minimum noise fraction (MNF). Second, the proposed separation method is acted on each features to generate the morphological components (MCs), i.e., the content and texture components. To this end, the dictionaries for these two components are built by using local curvelet and Gabor wavelet transforms within the randomly chosen image partitions. Then, sparse coding of one of the MCs and update of the associated dictionary are sequentially performed with the other one fixed. To better direct the separation process, an undecimated Haar wavelet with soft threshold is performed for the content component to make it smooth. This process is repeated until some stopping criterion is met. Finally, a support vector machine is adopted to obtain the classification maps based on the MCs. The experimental results with hyperspectral images collected by the National Aeronautics and Space Administration Jet Propulsion Laboratory's Airborne Visible/Infrared Imaging Spectrometer and the Reflective Optics Spectrographic Imaging System indicate that the proposed scheme provides better performance when compared with other widely used methods. [ABSTRACT FROM PUBLISHER]

As the successors of the overdue HuanjingJianzai-1 (HJ-1) satellites and new members in Chinese Environmental Protection and Disaster Monitoring Satellite Constellation, the first two of HuanjingJianZai-2 series satellites (HJ-2 A/B) have been launched on September 27, 2020. Each satellite carries four sensors, including the polarized scanning atmospheric corrector (PSAC), the charge-coupled device (CCD) camera, the hyperspectral imager (HSI), and the infrared spectroradiometer (IRS). Among them, PSAC is mainly used for the monitoring of atmospheric parameters to provide data support for atmospheric environmental monitoring and atmospheric correction of data from other sensors. To test the in-orbit performance of PSAC, we develop the “day-1” aerosol and water vapor retrieval algorithms. The preliminary validation results based on ground-based observations show that the aerosol optical depth (AOD) and columnar water vapor (CWV) datasets developed based on PSAC data have high accuracy and can effectively characterize the temporal trends of AOD and CWV. The accuracy of PSAC AOD dataset is better than the expected error (EE) ±(0.05 + 0.2 * AODAERONET), and the accuracy of PSAC CWV dataset is better than the EE ±(0.05 + 0.15 * CWVAERONET). To eliminate the negative impact of the atmosphere on CCD data and expand its application range, aerosol and water vapor data developed based on PSAC are used for atmospheric correction of CCD data. Compared with L1 CCD data, the texture details and clarity of CCD data after atmospheric correction have been significantly improved. [ABSTRACT FROM AUTHOR]

Global-scale canopy height mapping is an important tool for ecosystem monitoring and sustainable forest management. Various studies have demonstrated the ability to estimate canopy height from a single spaceborne multispectral image using end-to-end learning techniques. In addition to texture information of a single-shot image, our study exploits multitemporal information of image sequences to improve estimation accuracy. We adopt a convolutional variant of a long short-term memory (LSTM) model for canopy height estimation from multitemporal instances of Sentinel-2 products. Furthermore, we utilize the deep ensembles technique for meaningful uncertainty estimation on the predictions and postprocessing isotonic regression model for calibrating them. Our lightweight model (${\sim }320{\mathrm {k}}$ trainable parameters) achieves the mean absolute error (MAE) of $1.29 ~{\mathrm {m}}$ in a European test area of $79 ~{\mathrm {km}}^{2}$. It outperforms the state-of-the-art methods based on single-shot spaceborne images as well as costly airborne images while providing additional confidence maps that are shown to be well calibrated. Moreover, the trained model is shown to be transferable in a different country of Europe using a fine-tuning area of as low as ${\sim }2 ~{\mathrm {km}}^{2}$ with ${\mathrm {MAE}}=1.94 {\mathrm {m}}$. [ABSTRACT FROM AUTHOR]

The relative radiometric correction for Level-0 images captured by spaceborne push-broom imaging system faces the problems of vignetting, chromatic aberration, brightness saturation difference, misalignment, and so on. This article proposed a general relative radiometric correction method, which was applied to Gaofen series satellite Level-0 images. In the course of vignetting calibration, the proposed method based on the gray-level co-occurrence matrix (GLCM) did not use side-slither data and the DNMAX truncation method can solve brightness saturation difference. During chromatic aberration calibration, the subpixel-based phase correlation algorithm was first used to register adjacent CCDs, and then, the proposed global optimization method was adapted to calibrate multiple CCDs. The fixed calibration parameters for vignetting and chromatic aberration calculated by ridge regression and Newton’s method can be directly applied to correct other orbital Level-0 images. To verify the robustness and universality, Level-0 images of GF-1B, GF-1C, GF-1D, and GF-2 satellites were chosen for experiments, and the results were better than the existing methods. In addition, some official Level-1 products of GF-1B and GF-1C, covering particularly dark or bright surfaces (e.g., snow, sea, and cloud), were used to compare with the calibrated images of the proposed method. Results showed that relative radiometric correction by applying the independently estimated calibration parameters in this work achieved satisfactory results without the defects existing in official Level-1 products. Finally, results of relative radiometric correction of 30 orbital Level-0 images around the world further strengthened the conclusion that the estimated calibration parameters can be reused in other regions or seasons. [ABSTRACT FROM AUTHOR]

Tropical cyclone (TC) intensity estimation is critical for disaster forecasting and severe weather warning. In recent years, the performance of various TC intensity estimation models has been gradually enhanced, but the accuracy still needs to be improved. In this article, 71 intensity-related features are extracted from satellite infrared images of TCs. These features are grouped by eye features, circle features, texture features, and time-series features. Using the random forest model as the underlying algorithm of conformal prediction (CP), an intensity applicable CP framework is proposed. On the one hand, the proposed network can achieve point estimation of the TC intensity. On the other hand, it is also possible to realize the intensity interval estimation that satisfies a given significance level. In the experiments, the root mean square error of the point estimation algorithm is 7.86 kt (1 kt ≈ 0.51 m/s), and the performance of the proposed algorithm is better than the comparison algorithms. In addition, interval estimation enriches decision-making information. The experimental results show that the proposed model is a competitive and promising method for estimating the TC intensity. [ABSTRACT FROM AUTHOR]

In remote sensing imaging systems, pan-sharpening is an important technique to obtain high-resolution multispectral images from a high-resolution panchromatic image and its corresponding low-resolution multispectral image. Due to the powerful learning capability of convolution neural networks (CNNs), CNN-based methods have dominated this field. However, due to the limitation of the convolution operator, long-range spatial features are often not accurately obtained, thus limiting the overall performance. To this end, we propose a novel and effective method by exploiting a customized transformer architecture and information-lossless invertible neural module for long-range dependencies modeling and effective feature fusion in this article. Specifically, the customized transformer formulates the panchromatic (PAN) and multispectral (MS) features as queries and keys to encourage joint feature learning across two modalities, while the designed invertible neural module enables effective feature fusion to generate the expected pan-sharpened results. To the best of our knowledge, this is the first attempt to introduce a transformer and a invertible neural network into the pan-sharpening field. Extensive experiments over different kinds of satellite datasets demonstrate that our method outperforms state-of-the-art algorithms both visually and quantitatively with fewer parameters and flops. Furthermore, the ablation experiments also prove the effectiveness of the proposed customized long-range transformer and effective invertible neural feature fusion module for pan-sharpening. [ABSTRACT FROM AUTHOR]

High-resolution synthetic aperture radar (SAR) as an imaging device becomes more and more like a “camera” at the microwave frequency band. How different objects or object surfaces may visually appear in SAR images becomes an interesting research topic. Inspired by the bidirectional reflectance distribution function (BRDF) models employed in computer graphics (CGs), this article proposes the coherent spatially varying bidirectional scattering distribution function (CSVBSDF) for characterizing the electromagnetic scattering and SAR imaging behavior of surfaces. The CSVBSDF establishes a mapping function from observation parameters and surface local parameters to multidimensional measurements. In this article, CSVBSDF of the randomly rough surface is derived via adapting the integral equation method (IEM) to finite-size pixel cells under the plane wave and tapered wave incidence, respectively. It is then validated against the numerical beam simulation method (BSM) in the SAR image domain. A ground-based rail SAR and a 3-D laser scanner are used to measure the SAR image and the corresponding 3-D geometry of a real ground surface. Surface-local parameters, such as the local slope and roughness, are estimated from the measured 3-D geometry and then fed into the CSVBSDF model to produce a synthetic SAR image. Comparison against the real SAR image preliminarily demonstrates the efficacy of the proposed CSVBSDF model. [ABSTRACT FROM AUTHOR]

In order to more efficiently mine the features of polarimetric synthetic aperture radar (PolSAR) and establish a more appropriate classification model, this article proposes an improved convolutional autoencoder (ICAE) based on texture feature fusion (TFF-ICAE) for PolSAR terrain classification. First, TFF-ICAE specifically designs a multi-indicator squeeze-and-excitation (MI-SE) block and incorporates it into the CAE network. MI-SE can enhance the essential feature information while suppressing the interference information as much as possible, and it can effectively increase the between-class distance while reducing the within-class distance. Then, TFF-ICAE uses gray level co-occurrence matrix (GLCM) to capture the texture features, and it optimally fuses these texture features and the deep features extracted by ICAE to complete the multilevel feature fusion, elevating the feature representation completeness of the terrain. That is, TFF-ICAE effectively enhances the feature separation capability of different categories while greatly elevating the feature representation completeness. Experiments on the datasets of San Francisco, Oberpfaffenhofen, and Flevoland show that the proposed TFF-ICAE, respectively, achieves overall accuracies of 93.44%, 97.61%, and 97.78%, which are at least 0.92%, 1.52%, and 0.97% higher than other algorithms. Undoubtedly, the superiority of TFF-ICAE is verified on these datasets. [ABSTRACT FROM AUTHOR]

The forthcoming spaceborne Ice Cloud Imager (ICI) radiometer has 11 channels in the millimeter (mm) and sub-mm wave range from 183 up to 664 GHz. At some of these frequencies, the atmosphere is very opaque due to strong gaseous and cloud extinction, precluding the observation of the surface. We aim at investigating how to evaluate the ICI channels geolocation error using surface landmark targets. The most transparent ICI channels, i.e., those around 183.3 ± 7.0 GHz at vertical (V) polarization (ICI-1) and around 243.2 ± 2.5 GHz (ICI-4) at horizontal (H)/ V polarization, are considered. Starting from a previous work, we extend the database of the surface landmark targets to cover boreal and austral dry seasons at various latitudes. For testing the geolocation approach, we use satellite Special Sensor Microwave Imager/Sounder (SSMIS) available data at 183.31 ± 6.6 GHz at H-polarization during 2017, obtaining an overall mean error of about 5.0 km and standard deviation of about 2.2 km, well within the ICI geolocation error assessment specifications. Since no imagers are available at 243 GHz, we extrapolate SSMIS data to 243.2 ± 2.5 GHz using a model-based neural-network approach, named Blended Artificial-neural-network Microwave Imager Simulator (BAMIS). The latter is trained by radiative-transfer simulations and global-scale atmospheric reanalyses data as well as SSMIS data. Results confirm that the proposed approach can be successfully exploited for ICI-4 geolocation error assessment at 243.2 ± 2.5 GHz, with results close to those obtained for the SSMIS 183.31 ± 6.6-GHz channel. [ABSTRACT FROM AUTHOR]

The complementarity of synthetic aperture radar (SAR) and optical images allows remote sensing observations to “see” unprecedented discoveries. Image matching plays a fundamental role in the fusion and application of SAR and optical images. However, both the geometric imaging pattern and the physical radiation mechanism of these two sensors are significantly different, so that the images show complex geometric distortion and nonlinear radiation differences. This phenomenon brings great challenges to image matching, which neither the handcrafted descriptors nor the deep learning-based methods have adequately addressed. In this article, a novel image-based matching method for SAR to optical images via an image-based convolutional network with spatial pyramid aggregated pooling (SPAP) and an attention mechanism is proposed, namely MAP-Net. The original image is embedded through the convolutional neural network to generate the feature map. Through the information extraction and abstraction of the original imagery, the embedded features containing the high-level semantic information are more robust to the geometric distortion and radiation variation among the different modal images, which is beneficial to the matching of cross-modal images. The adoption of the SPAP module makes the network more capable of integrating global and local contextual information. The attention block weights the dense features generated from the network to extract the key features that are invariant, distinguishable, repeatable, and suitable for the image matching task. In the experiments, five sets of multisource and multiresolution SAR and optical images with wide and varied ground coverage were used to evaluate the accuracy of MAP-Net, compared to both handcrafted and deep learning-based methods. The experimental results show that the MAP-Net method is superior to the current state-of-the-art image matching methods for SAR to optical images. [ABSTRACT FROM AUTHOR]

Artificial light-at-night (ALAN), emitted from the ground and visible from space, marks human presence on earth. Since the launch of the Suomi National Polar Partnership satellite with the Visible Infrared Imaging Radiometer Suite Day–Night Band (VIIRS/DNB) onboard, global nighttime images have significantly improved; however, they remained panchromatic. Although multispectral images are also available, they are either commercial or free of charge, but sporadic. In this article, we use several machine learning techniques, such as linear, kernel, random forest regressions, and elastic map approach, to transform panchromatic VIIRS/DBN into red, green, blue (RGB) images. To validate the proposed approach, we analyze RGB images for eight urban areas worldwide. We link RGB values, obtained from ISS photographs, to panchromatic ALAN intensities, their pixel-wise differences, and several land-use-type proxies. Each dataset is used for model training, while other datasets are used for model validation. The analysis shows that model-estimated RGB images demonstrate a high degree of correspondence with the original RGB images from the ISS database. Yet, estimates, based on linear, kernel, and random forest regressions, provide better correlations, contrast similarity, and lower WMSEs levels, while RGB images, generated using elastic map approach, provide higher consistency of predictions. [ABSTRACT FROM AUTHOR]

Building segmentation of synthetic aperture radar (SAR) images is a challenging task that has not been solved well. High-resolution interferometric SAR (InSAR) images can provide delicate textures and interferometric phase images useful for building segmentation. However, current semantic segmentation networks in computer vision cannot be directly applied in InSAR building segmentation tasks to get good results because of the InSAR images’ particularity. In this article, we present a novel complex-valued convolutional and multifeature fusion network (CVCMFF Net) specifically for building semantic segmentation of InSAR images. This CVCMFF Net not only learns from the complex-valued SAR images but also considers multiscale and multichannel feature fusion. It can effectively segment the layover, shadow, and background on both the simulated InSAR building images and the real airborne InSAR images. The segmentation performance of CVCMFF Net is significantly improved compared with those of other state-of-the-art networks. By feature visualization, the feature extraction rule and feature fusion mechanism of the network are explored. We hope that the proposed network can be beneficial to InSAR phase filtering, phase unwrapping, and information extraction in urban areas. [ABSTRACT FROM AUTHOR]

With the increased number of synthetic aperture radar (SAR) systems that have been launched in recent years, many high-quality images have been produced for precise earth observation. The number of available images requires new feature extraction techniques to capture enough discriminant information from high-resolution SAR images. To effectively characterize different land covers, a multiscale local Fisher pattern (MLFP) is proposed to extract both statistical and spatial properties in this work. First, the Fisher vector (FV) of each pixel is calculated after the statistical distribution of high-resolution SAR intensities is modeled via a Gamma mixture model. Then, the generative and discriminant information implied in the FV is exploited after the extraction of the geometrical information between neighboring pixels within different scales. Two experiments are conducted to demonstrate the performance of the proposed MLFP, which are high-resolution SAR image land-cover classification and SAR scene classification. Compared with some existing approaches, the proposed MLFP shows superior performance after the statistical and spatial structure information from different land covers is exploited. [ABSTRACT FROM AUTHOR]

Satellite stereo mapping, together with laser altimetry, can be used to obtain three-dimensional geospatial information. Spaceborne laser altimeter can provide high-accuracy elevation information; however, due to the lack of detailed intensity information, its planimetric accuracy is usually worse than the ranging accuracy. The Chinese Gaofen-7 (GF-7) satellite, which was designed for civilian mapping application, was launched on November 3, 2019. The GF-7 satellite’s main payloads are a laser altimeter system (with footprint camera) and a dual-linear charge-coupled device (CCD) mapping camera. According to the pixel coordinate of the laser footprint in the stereo image, the laser altimeter together with the footprint camera can provide planimetric geodetic coordinates for the control points of a higher accuracy than the other traditional satellite laser altimeters, and represents a new technology for satellite mapping. In this article, a laser footprint planimetric location method for the GF-7 satellite is proposed. The method is designed based on the main payload characteristics of GF-7 and the working modes of the laser altimeter by the combined use of subpixel phase correlation image matching and four types of laser spot center detection methods. The planimetric positioning accuracies of the laser spots in urban, suburban, farmland, forest, mountainous, and ice sheet areas were also analyzed. The experimental results show that the accuracy of planimetric location relative to stereo image for the laser footprint is 0.3–1.0 m (except for ice sheets ~12 m) when the footprint camera works under the synchronous mode, and 0.2–0.4 m when the footprint camera works under asynchronous mode (AM). [ABSTRACT FROM AUTHOR]

In this article, we propose a fast superpixel region merging algorithm for synthetic aperture radar (SAR) image segmentation. With our previously proposed adaptive superpixel generation approach (ALFCE), an initial over-segmentation superpixel map for SAR imagery can be obtained. A sketch edge map is used here to eliminate the mixed superpixels to refine the over-segmentation. Then, we focus on rapid superpixel merging for efficient and accurate SAR image segmentation by using the statistical region merging (SRM) framework. This article proposes a new merging order with the consideration of statistical dissimilarity measure and common boundary length penalty, as well as the homogeneity constraint for each superpixel pair. For the merging predicate, we define an adaptive merging threshold according to the image complexity, making the proposed superpixel merging no need to set any merging parameters in advance. Disjoint set is utilized in this article to map the superpixel pairs to pixel pairs for the sake of fast region merging, which has a low computation cost even with the increasing of superpixels. Experimental results on synthetic and real SAR images demonstrate that the segmentation precision of our proposed method can reach more than 85% and also superior to other state-of-the-art methods in terms of computational efficiency. [ABSTRACT FROM AUTHOR]

With the explosive growth of remote sensing big data, large-scale remote sensing image retrieval (RSIR) has become one of the most challenging tasks in data mining, attracting more and more attention from researchers. In recent years, deep learning has achieved fruitful results in RSIR. However, there are three major problems. The first problem is due to the imbalanced categories in RSIR data sets. Accordingly, a novel sample mining method is proposed. This method is based on top- $k$ “misplaced” samples (Top- $k$ MS) along the top- $k$ nearest neighbor decision boundary, rather than setting boundary threshold of sample mining and reducing the impact of artificial and objective factors on network training as usual. The second problem comes from the inconsistency between the loss reduction direction and the optimization direction. In response, we additionally propose a novel result ranking loss (RRL) according to the retrieval results in a batch. RRL is used as a plug-in and combined with other local losses. As a result, the retrieval accuracy improved significantly. For the third problem, processing a large number of high-resolution images will increase training time and cause network freeze. To solve the problem, this article proposes a global optimization model based on feature space and retrieval results (FSRR). More specifically, FSRR consists of local loss based on feature space and RRL based on retrieval results, and can be optimized in an end-to-end manner. Experimental results show that our proposed algorithm achieves the best performance when compared with other state-of-the-art deep RSIR algorithms on two benchmark data sets. [ABSTRACT FROM AUTHOR]

Sentinel-1 (S1) extra-wide (EW) swath data in cross-polarization (horizontal–vertical, HV or vertical–horizontal, VH) are strongly affected by the scalloping effect and thermal noise, particularly over areas with weak backscattered signals, such as sea surfaces. Although noise vectors in both the azimuth and range directions are provided in the standard S1 EW data for subtraction, the residual thermal noise still significantly affects sea ice detection by the EW data. In this article, we improve the denoising method developed in previous studies to remove the additive noise for the S1 EW data in cross-polarization. Furthermore, we propose a new method for eliminating the residual noise (i.e., multiplicative noise) at the subswath boundaries of the EW data, which cannot be well processed by simply subtracting the reconstructed 2-D noise field. The proposed method of removing both the additive and multiplicative noise was applied to EW HV-polarized images processed using different Instrument Processing Facility (IPF) versions. The results suggest that the proposed algorithm significantly improves the quality of EW HV-polarized images under various sea ice conditions and sea states in the marginal ice zone (MIZ) of the Arctic. This is of great support for the utilization of cross-polarization synthetic aperture radar (SAR) images in wide swaths for intensive sea ice monitoring in polar regions. [ABSTRACT FROM AUTHOR]

Synthetic aperture radar (SAR) image classification is a fundamental research direction in image interpretation. With the development of various intelligent technologies, deep learning techniques are gradually being applied to SAR image classification. In this study, a new SAR classification algorithm known as the multiscale convolutional neural network with an autoencoder regularization joint contextual attention network (MCAR-CAN) is proposed. The MCAR-CAN has two branches: the autoencoder regularization branch and the context attention branch. First, autoencoder regularization is used for the reconstruction of the input to regularize the classification in the autoencoder regularization branch. Multiscale input and an asymmetric structure of the autoencoder branch cause the network more to be focused on classification than on reconstruction. Second, the attention mechanism is used to produce an attention map in which each attention weight corresponds to a context correlation in attention branch. The robust features are obtained by the attention mechanism. Finally, the features obtained by the two branches are spliced for classification. In addition, a new training strategy and a postprocessing method are designed to further improve the classification accuracy. Experiments performed on the data from three SAR images demonstrated the effectiveness and robustness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

A new technique for automated retrieval of ice concentration from RADARSAT-2 dual-polarization HH-HV ScanSAR Wide images for subsequent assimilation in ice numerical models is presented. First, we extended our previously introduced ice and water detection approach operating at a 2.05 km $\times2.05$ km spatial scale to a set of 19 different spatial scales ranging from 2.05 km (41 pixels) down to 0.25 km (5 pixels). As the spatial resolution was increased, the overall accuracy of ice and water detection stayed at a very high level across all scales (between 99.5% and 99.8%), but the number of water retrievals substantially dropped. Second, we designed an approach for estimating ice concentration in a 2 km $\times 2$ km ($40\times40$ pixels) area consisting of $64\,\,5 \times 5$ pixel blocks. The $5\times 5$ pixel blocks which are initially classified as unknowns are iteratively combined in clusters with effective spatial scales larger than 5 pixels. The clusters are further classified as ice or water using the ice probability model corresponding to the effective spatial scale. The $40\times40$ pixel area becomes populated with high-resolution ($5\times 5$ pixels) ice and water retrievals, and the ice concentration is estimated based on the number of ice and water retrievals. The proposed approach produces a much better agreement with the Canadian Ice Service Image Analysis ice concentrations (root-mean-square error (RMSE) = 2.2%) compared to the original 2-km ice/water detection approach (RMSE = 19.9%). The developed technique will be adapted to the RADARSAT Constellation Mission data for data assimilation in Environment and Climate Change Canada Regional Ice-Ocean Prediction System. [ABSTRACT FROM AUTHOR]

Due to the tradeoff between spatial and temporal resolutions commonly encountered in remote sensing, no single satellite sensor can provide fine spatial resolution land surface temperature (LST) products with frequent coverage. This situation greatly limits applications that require LST data with fine spatiotemporal resolution. Here, a deep learning-based spatiotemporal temperature fusion network (STTFN) method for the generation of fine spatiotemporal resolution LST products is proposed. In STTFN, a multiscale fusion convolutional neural network is employed to build the complex nonlinear relationship between input and output LSTs. Thus, unlike other LST spatiotemporal fusion approaches, STTFN is able to form the potentially complicated relationships through the use of training data without manually designed mathematical rules making it is more flexible and intelligent than other methods. In addition, two target fine spatial resolution LST images are predicted and then integrated by a spatiotemporal-consistency (STC)-weighting function to take advantage of STC of LST data. A set of analyses using two real LST data sets obtained from Landsat and moderate resolution imaging spectroradiometer (MODIS) were undertaken to evaluate the ability of STTFN to generate fine spatiotemporal resolution LST products. The results show that, compared with three classic fusion methods [the enhanced spatial and temporal adaptive reflectance fusion model (ESTARFM), the spatiotemporal integrated temperature fusion model (STITFM), and the two-stream convolutional neural network for spatiotemporal image fusion (StfNet)], the proposed network produced the most accurate outputs [average root mean square error (RMSE) < 1.40 °C and average structural similarity (SSIM) > 0.971]. [ABSTRACT FROM AUTHOR]

Random Gaussian noise and striping artifacts are common phenomena in hyperspectral images (HSI). In this article, an effective restoration method is proposed to simultaneously remove Gaussian noise and stripes by merging a denoising and a destriping submodel. A denoising submodel performs a multiband denoising, i.e., Gaussian noise removal, considering Gaussian noise variations between different bands, to restore the striped HSI from the corrupted image, in which the striped HSI is constrained by a weighted nuclear norm. For the destriping submodel, we propose an adaptive anisotropy total variation method to adaptively smoothen the striped HSI, and we apply, for the first time, the truncated nuclear norm to constrain the rank of the stripes to 1. After merging the above two submodels, an ultimate image restoration model is obtained for both denoising and destriping. To solve the obtained optimization problem, the alternating direction method of multipliers (ADMM) is carefully schemed to perform an alternative and mutually constrained execution of denoising and destriping. Experiments on both synthetic and real data demonstrate the effectiveness and superiority of the proposed approach. [ABSTRACT FROM AUTHOR]

The rapid increase in the number of remote sensing sensors makes it possible to develop multisource feature extraction and fusion techniques to improve the classification accuracy of surface materials. It has been reported that light detection and ranging (LiDAR) data can contribute complementary information to hyperspectral images (HSIs). In this article, a multiple feature-based superpixel-level decision fusion (MFSuDF) method is proposed for HSIs and LiDAR data classification. Specifically, superpixel-guided kernel principal component analysis (KPCA) is first designed and applied to HSIs to both reduce the dimensions and compress the noise impact. Next, 2-D and 3-D Gabor filters are, respectively, employed on the KPCA-reduced HSIs and LiDAR data to obtain discriminative Gabor features, and the magnitude and phase information are both taken into account. Three different modules, including the raw data-based feature cube (concatenated KPCA-reduced HSIs and LiDAR data), the Gabor magnitude feature cube, and the Gabor phase feature cube (concatenation of the corresponding Gabor features extracted from the KPCA-reduced HSIs and LiDAR data), can be, thus, achieved. After that, random forest (RF) classifier and quadrant bit coding (QBC) are introduced to separately accomplish the classification task on the aforementioned three extracted feature cubes. Alternatively, two superpixel maps are generated by utilizing the multichannel simple noniterative clustering (SNIC) and entropy rate superpixel segmentation (ERS) algorithms on the combined HSIs and LiDAR data, which are then used to regularize the three classification maps. Finally, a weighted majority voting-based decision fusion strategy is incorporated to effectively enhance the joint use of the multisource data. The proposed approach is, thus, named MFSuDF. A series of experiments are conducted on three real-world data sets to demonstrate the effectiveness of the proposed MFSuDF approach. The experimental results show that our MFSuDF can achieve the overall accuracy of 73.64%, 93.88%, and 74.11% for Houston, Trento, and Missouri University and University of Florida (MUUFL) Gulport data sets, respectively, when there are only three samples per class for training. [ABSTRACT FROM AUTHOR]

The water body detection in high-resolution synthetic aperture radar (SAR) images is a challenging task due to the changing interference caused by multiple imaging conditions and complex land backgrounds. Inspired by the excellent adaptability of deep neural networks (DNNs) and the structured modeling capabilities of probabilistic graphical models, the cascaded fully-convolutional network (CFCN) is proposed to improve the performance of water body detection in high-resolution SAR images. First, for the resolution loss caused by convolutions with large stride in traditional convolutional neural network (CNN), the fully-convolutional upsampling pyramid networks (UPNs) are proposed to suppress this loss and realize pixel-wise water body detection. Then considering blurred water boundary, the fully-convolutional conditional random fields (FC-CRFs) are introduced to UPNs, which reduce computational complexity and lead to the automatic learning of Gaussian kernels in CRFs and the higher boundary accuracy. Furthermore, to eliminate the inefficient training caused by imbalanced categorical distribution in the training data set, a novel variable focal loss (VFL) function is proposed, which replaces the constant weighting factor of focal loss with the frequency-dependent factor. The proposed methods can not only improve the pixel accuracy and boundary accuracy but also perform well in detection robustness and speed. Results of GaoFen-3 SAR images are presented to validate the proposed approaches. [ABSTRACT FROM AUTHOR]

Synthetic aperture radar (SAR) sea ice imagery is a promising source of data for sea ice data assimilation. Classification of SAR sea ice imagery into ice and water is of particular relevance due to its relationship with ice concentration, a key variable in sea ice data assimilation systems. With increasing volumes of SAR data, automated methods to carry out these classifications are of particular importance. Although several automated approaches have been proposed, none look at the impact of including an estimate of uncertainty of the model parameters and input features on the classification output. This article uses an established database of SAR image features to train a multilayer perceptron (MLP) neural network to classify pixel locations as either ice, water, or unknown. The classification accuracies are benchmarked using a recently developed logistic regression approach for the same database. The two methods are found to be comparable. The MLP approach is then enhanced to allow uncertainty to be estimated at each pixel location. Following methods proposed in the deep learning community, two kinds of uncertainty are considered. The first, epistemic uncertainty, is that due to uncertainty in the MLP weights. The second kind of uncertainty, aleatoric uncertainty, is that which cannot be explained by the model, and is therefore associated with the input data. It is found that including these uncertainties in the MLP models reduces their accuracies slightly, but also reduces misclassification rates. This is of particular importance for data assimilation applications, where misclassifications could severely degrade the analysis. [ABSTRACT FROM AUTHOR]

Imbalanced training sets are known to produce suboptimal maps for supervised classification. Therefore, one challenge in mapping land cover is acquiring training data that will allow classification with high overall accuracy (OA) in which each class is also mapped onto similar user’s accuracy. To solve this problem, we integrated local adaptive region and box-and-whisker plot (BP) techniques into an iterative algorithm to expand the size of the training sample for selected classes in this article. The major steps of the proposed algorithm are as follows. First, a very small initial training sample (ITS) for each class set is labeled manually. Second, potential new training samples are found within an adaptive region by conducting local spectral variation analysis. Lastly, three new training samples are acquired to capture information regarding intraclass variation; these samples lie in the lower, median, and upper quartiles of BP. After adding these new training samples to the ITS, classification is retrained and the process is continued iteratively until termination. The proposed approach was applied to three very high-resolution (VHR) remote-sensing images and compared with a set of cognate methods. The comparison demonstrated that the proposed approach produced the best result in terms of OA and exhibited superiority in balancing user’s accuracy. For example, the proposed approach was typically 2%-10% more accurate than the compared methods in terms of OA and it generally yielded the most balanced classification. [ABSTRACT FROM AUTHOR]

Due to the dramatically increased volume of remote sensing (RS) image archives, images are usually stored in a compressed format to reduce the storage size. Existing content-based RS image retrieval (CBIR) systems require as input fully decoded images, thus resulting in a computationally demanding task in the case of large-scale CBIR problems. To overcome this limitation, in this article, we present a novel CBIR system that achieves a coarse-to-fine progressive RS image description and retrieval in the partially decoded Joint Photographic Experts Group (JPEG) 2000 compressed domain. The proposed system initially: 1) decodes the code blocks associated only to the coarse wavelet resolution and 2) discards the most irrelevant images to the query image based on the similarities computed on the coarse resolution wavelet features of the query and archive images. Then, the code blocks associated with the subsequent resolution of the remaining images are decoded and the most irrelevant images are discarded by computing similarities considering the image features associated with both resolutions. This is achieved by using the pyramid match kernel similarity measure that assigns higher weights to the features associated with the finer wavelet resolution than to those related to the coarse wavelet resolution. These processes are iterated until the codestreams associated with the highest wavelet resolution are decoded. Then, the final retrieval is performed on a very small set of completely decoded images. Experimental results obtained on two benchmark archives of aerial images point out that the proposed system is much faster while providing a similar retrieval accuracy than the standard CBIR systems. [ABSTRACT FROM AUTHOR]

Hyperspectral unmixing aims at identifying a set of elementary spectra and the corresponding mixture coefficients for each pixel of an image. As the elementary spectra correspond to the reflectance spectra of real materials, they are often very correlated, thus yielding an ill-conditioned problem. To enrich the model and reduce ambiguity due to the high correlation, it is common to introduce spatial information to complement the spectral information. The most common way to introduce spatial information is to rely on a spatial regularization of the abundance maps. In this article, instead of considering a simple but limited regularization process, spatial information is directly incorporated through the newly proposed context of spatial unmixing. Contextual features are extracted for each pixel, and this additional set of observations is decomposed according to a linear model. Finally, the spatial and spectral observations are unmixed jointly through a cofactorization model. In particular, this model introduces a coupling term used to identify clusters of shared spatial and spectral signatures. An evaluation of the proposed method is conducted on synthetic and real data and shows that results are accurate and also very meaningful since they describe both spatially and spectrally the various areas of the scene. [ABSTRACT FROM AUTHOR]

This article proposes a generalized modeling and simulation approach for correlated synthetic aperture radar (SAR) texture based on the Gaussian coherent scatterer model. It is rooted in the physics-based coherent scatterer assumption where each observation in an SAR image is a coherent sum of multiple underlying Gaussian scatterers. The proposal generalizes existing single-point statistical models by allowing the number of scatterers to be a correlated random field. It can also generate the desired spatial correlation texture by stipulating the structure in both the Gaussian scattered field and the number of scatterers. This generalized model is derived theoretically and then validated by both simulations and experiments with SAR data from actual sensors. [ABSTRACT FROM AUTHOR]

Dynamic estimation of spin spacecraft is a challenge and plays a significant role in space situation awareness applications like potential space collision warning. Based on remote sensing technologies of laser and radar sensors, current methods almost adopt a match strategy to estimate the dynamic parameters of a particular target with the long-term measurement collection. These kinds of data-driven methods merely consider the inherent connection between the measured characters and target dynamic patterns, and can hardly be expanded to other spacecraft when the measurement collection is insufficient. Therefore, this article presents a novel approach to interpreting multiple-station inverse synthetic aperture radar (ISAR) images for the dynamic estimation of spin spacecraft. As a unique phenomenon of radar imaging, the imaging plane of ISAR observation not only depends on the change of the relative position between the target and radar, but also changes with the spin of the target. In order to decouple the target dynamic estimation from the determination of the imaging geometry, the angular diversity of multiple-station images is employed. The proposed algorithm deduces an explicit expression of target dynamic parameters under the imaging projection model of the multiple-station observation. By utilizing the chaotic grasshopper optimization algorithm (CGOA), it determines three crucial elements of the target spin motion with a two-step optimization, including instantaneous attitude, rotation shaft and rotation speed. Simulation experiments of a typical spin spacecraft, Tiangong-I (TG-I), illustrate the feasibility of the proposed method under different motion patterns. [ABSTRACT FROM AUTHOR]

Regularization method is an effective tool for synthetic aperture radar (SAR) image despeckling. Design of the effective regularization terms describing the image priors plays a vital role in this kind of method. In this article, a new combinational regularization model for speckle reduction (CRM-SR) is proposed, in which a regularization term is elaborately designed to contain both a fractional-order total variation (FrTV) regularization and a nonlocal low rank (NLR) regularization. The new regularization model inherits both the advantages of FrTV and NLR and improves the performance of SAR despeckling and, therefore, better preserves the edges and geometrical features of the images during the despeckling process. An efficient algorithm based on alternating direction optimization is derived to solve the proposed combinational regularization model. Experimental results show that the proposed model can effectively remove SAR image speckle and preserve the geometrical features of images according to both subjective visual assessment of image quality and objective evaluation. [ABSTRACT FROM AUTHOR]

Infrared (IR) images are often contaminated by obvious intensity bias and stripes, which severely affect the visual quality and subsequent applications. It is challenging to eliminate simultaneously the mixed nonuniformity noise without blurring the fine-image details in low-textured IR images. In this article, we present a new model for simultaneous intensity bias correction and destriping through introducing two sparsity constraints. One is that model fit on the intensity bias should be as accurate as possible. A bivariate polynomial model is built to characterize the global smoothness of the intensity bias. The other constraint is that the unidirectional variational sparse model can concisely represent the direction characteristic of stripe noise. A computationally efficient numerical algorithm based on split Bregman iteration is used to solve the complex optimization problem. The proposed method is fundamentally different from the existing denoising techniques and simultaneously estimates the sharp image, intensity bias, and stripe components. Significant improvement on image quality is achieved on both simulated and real studies. Both qualitative and quantitative comparisons with the state-of-the-art correction methods demonstrate its superiority. [ABSTRACT FROM AUTHOR]

Illumination variation is one of the major problems in multitemporal earth observation (EO) image matching. Despite much research has been focused on illumination invariant image matching, subpixel image matching under large illumination variation without prior knowledge is still a challenge. This paper proposes a phase correlation decomposition (PCD) theory model in order to analyze the joint effects of zenith and azimuth angles of the lighting source. A novel stepwise least-squares fitting-based PC (SLSF-PC) is proposed to accurately calculate the subpixel image shift by a stepwise function in the frequency domain. Our mathematical investigation is validated by image alignment and stereo dense matching experiments using simulated terrain shading images representing four different landscapes and a multi-illumination remotely sensed image data set containing eight different scenes under seasonal and daily illumination variation. Image matching experiments demonstrate the superior performance of the proposed SLSF-PC compared to the state-of-the-art image matching algorithms, such as speeded up robust features (SURF), mutual information (MI), and normalized cross correlation (NCC). Even under great illumination angle change, the proposed SLSF-PC is able to achieve 0.1 subpixel matching accuracy on average while other methods fail to find the correspondence. [ABSTRACT FROM AUTHOR]

The global optimal solution (GOS) has proven to be very accurate for deriving water surface velocities from contemporaneous image pairs, but previous studies have used shore-based radars or satellite measurements with resolutions on the order of a kilometer or tens of meters to establish this. In contrast, the objective of this paper is to derive a GOS velocity field from infrared (IR) (3–5 $\mu \text{m}$) images having a 1-m pixel size. Because IR images can frequently exhibit a low signal-to-noise ratio, a newly developed GOS technique with a local similarity metric is used to retrieve velocities from such low-contrast data sets. To demonstrate the utility of this new method, we use airborne data collected in the tidal Potomac River over 11 days and spatially varying flood, ebb, and slack conditions. The resulting GOS-derived velocity estimates are compared against acoustic Doppler current profiler (ADCP) measurements taken simultaneously with the airborne collections. Velocity magnitudes and directions are found to have GOS versus ADCP correlations of 0.93 and 0.99, respectively. This high correlation suggests that the GOS technique may be applicable to a variety of lower contrast imagery that can now be collected by a low-altitude remotely controlled aircraft. [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]