Search

This paper addresses the problem of radar-based human gait recognition based on the dual-channel deep convolutional neural network (DC-DCNN). To enrich the limited radar data set of human gaits and provide a benchmark for classifier training, evaluation, and comparison, it proposes an effective method for radar echo generation from the infrared, publicly accessible motion capture (MOCAP) data set. According to the different nonstationary characteristics of micro-Doppler (m-D) for the torso and limbs, it enhances their distinguishable joint time–frequency (JTF) features by applying the short-time Fourier transforms (SFTFs) with varying sliding window length and then designs the DC-DCNN structure to achieve refined human gait recognition by separate feature extraction and fusion. Experiments have shown that compared with the traditional single-channel deep convolutional neural network (SC-DCNN), the proposed method achieves higher recognition accuracy in refined human gait classification without incurring additional radar resources and could be readily extended to refined recognition of other human activities. [ABSTRACT FROM AUTHOR]

With the increasing acquisition ability of hyperspectral remote sensing images, unsupervised cross-temporal classification (UCTC) of hyperspectral images (HSIs) has attracted more and more attention. In this paper, we focus on cross-temporal HSI classification, i.e., using one labeled HSI to classify the other unlabeled HSI. A multiple geodesic flow kernel learning (MGFKL) framework is proposed to exploit both spatial and spectral features for UCTC with bitemporal HSIs and called S2-MGFKL. The proposed S2-MGFKL method first extracts extended multi-attribute profiles (EMAPs) from the original bitemporal HSIs. The spatial features of the bitemporal HSIs obtained by the same attribute filter are paired up, so are the original spectral features. Second, each pair of features from both source and target domains are used to construct multiple geodesic flows. According to the original definition of GFK, we can obtain the construction of Gaussian base GFKs. The base kernels consist of two parts, the spectral part is obtained base on the same geodesic flow (which is constructed on the bitemporal spectral features) by tuning the kernel scale, while the spatial part is obtained under the same kernel scale but different geodesic flows constructed on different spatial feature pairs. After that, the mean rule is adopted to acquire the combined kernel, which is fed into the supervised vector machine (SVM) to implement the cross-temporal classification task. Experiments are conducted on two real HSI data sets, and the results compared with several well-known methods demonstrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Detecting land cover change through very-high-resolution (VHR) remote sensing images is helpful in supporting urban sustainable development, natural disaster evaluation, and environmental assessment. However, the intraclass spectral variance in VHR remote sensing images is usually larger than that of median-low remote sensing images. Furthermore, the bitemporal images are usually acquired under different atmospheric conditions, sun height, soil moisture, and other factors. Consequently, in practical applications, many pseudo changes are presented in the detected map. In this paper, an adaptive histogram trend (AHT) similarity approach is promoted to quantitatively measure the magnitude between the corresponding pixels in bitemporal images in terms of change semantic. In the proposed approach, to reduce the phenological effect on the bitemporal images of land cover change detection (LCCD), we first define the quantitative description of AHT. Second, the change magnitudes between pairwise pixels are quantitatively measured by an improved bin-to-bin (B2B) distance between the corresponding AHTs. Then, the change magnitudes between two entire bitemporal images are measured AHT-by-AHT. Finally, binary threshold methods, such as the Otsu method or the double-window flexible pace search (DFPS) method, are used to divide the change magnitude image into binary change detection maps and obtain the final change detection map. The performance of the AHT-based LCCD approach is verified by four pairs of VHR remote-sensing images that correspond to two types of real land cover change cases. The detected results based on the four pairs of bitemporal VHR images outperformed the compared state-of-the-art LCCD methods. [ABSTRACT FROM AUTHOR]

Radio-frequency systems, such as TV and cellular networks, severely interfere with synthetic aperture radar (SAR) systems. Narrowband radio-frequency interference (RFI) has a special low-rank property in the received signal matrix, because it performs like a sinusoid with nearly invariant frequency as the slow time proceeds. Exploiting this special property, in this paper, we divide the received signal matrix into several small matrices, in each of which the RFI is also low rank. Without losing the connection between these small matrices, we stack them into a three-mode tensor to separate the low-rank RFI tensor and recover the informative signal tensor. Previous studies employed the nuclear norm to regularize the low-rank RFI, which is not a good choice. Hence, we propose two reweighted algorithms, the reweighted tensor nuclear norm (RTNN) and the reweighted tensor Frobenius norm (RTFN) algorithms, to approximate the rank function in a tensor and accurately extract the low-rank RFI tensor from the received signal tensor. As a result, the introduction of the tensor structure dramatically decreases the computational cost. Furthermore, the reweighted scheme helps suppressing the RFI and recovering the useful signal with excellent performance. Finally, real SAR data with measured RFI is employed to demonstrate the effectiveness of the proposed methods for RFI mitigation. [ABSTRACT FROM AUTHOR]

While deep learning technologies for computer vision have developed rapidly since 2012, modeling of remote sensing systems has remained focused around human vision. In particular, remote sensing systems are usually constructed to optimize sensing cost-quality tradeoffs with respect to human image interpretability. While some recent studies have explored remote sensing system design as a function of simple computer vision algorithm performance, there has been little work relating this design to the state of the art in computer vision: deep learning with convolutional neural networks. We develop experimental systems to conduct this analysis, showing results with modern deep learning algorithms and recent overhead image data. Our results are compared to standard image quality measurements based on human visual perception, and we conclude not only that machine and human interpretability differ significantly but also that computer vision performance is largely self-consistent across a range of disparate conditions. This paper is presented as a cornerstone for a new generation of sensor design systems that focus on computer algorithm performance instead of human visual perception. [ABSTRACT FROM AUTHOR]

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

Frequency filtering is widely used in routine processing of seismic data to improve the signal-to-noise ratio (SNR) of recorded signals and by doing so to improve subsequent analyses. In this paper, we develop a new denoising/decomposition method, DeepDenoiser, based on a deep neural network. This network is able to simultaneously learn a sparse representation of data in the time–frequency domain and a non-linear function that maps this representation into masks that decompose input data into a signal of interest and noise (defined as any non-seismic signal). We show that DeepDenoiser achieves impressive denoising of seismic signals even when the signal and noise share a common frequency band. Because the noise statistics are automatically learned from data and require no assumptions, our method properly handles white noise, a variety of colored noise, and non-earthquake signals. DeepDenoiser can significantly improve the SNR with minimal changes in the waveform shape of interest, even in the presence of high noise levels. We demonstrate the effect of our method on improving earthquake detection. There are clear applications of DeepDenoiser to seismic imaging, micro-seismic monitoring, and preprocessing of ambient noise data. We also note that the potential applications of our approach are not limited to these applications or even to earthquake data and that our approach can be adapted to diverse signals and applications in other settings. [ABSTRACT FROM AUTHOR]

Arising from the various object types and scales, diverse imaging orientations, and cluttered backgrounds in optical remote sensing image (RSI), it is difficult to directly extend the success of salient object detection for nature scene image to the optical RSI. In this paper, we propose an end-to-end deep network called LV-Net based on the shape of network architecture, which detects salient objects from optical RSIs in a purely data-driven fashion. The proposed LV-Net consists of two key modules, i.e., a two-stream pyramid module (L-shaped module) and an encoder–decoder module with nested connections (V-shaped module). Specifically, the L-shaped module extracts a set of complementary information hierarchically by using a two-stream pyramid structure, which is beneficial to perceiving the diverse scales and local details of salient objects. The V-shaped module gradually integrates encoder detail features with decoder semantic features through nested connections, which aims at suppressing the cluttered backgrounds and highlighting the salient objects. In addition, we construct the first publicly available optical RSI data set for salient object detection, including 800 images with varying spatial resolutions, diverse saliency types, and pixel-wise ground truth. Experiments on this benchmark data set demonstrate that the proposed method outperforms the state-of-the-art salient object detection methods both qualitatively and quantitatively. [ABSTRACT FROM AUTHOR]

A squinted observation geometry along with long integration time significantly aggravates the range walk and spatial variation of a medium-earth-orbit (MEO) synthetic aperture radar (SAR) signal. Variable pulse repeating frequency (PRF) is recommended to avoid the blockage in echo recording and save storage space. The existing wavenumber algorithms cannot handle the nonlinear and range–azimuth-coupled spatial variation (RACSP) over a large scene. In this paper, we propose a modified Stolt mapping method along with a modified joint time and Doppler resampling (JTDR) for highly squinted MEO SAR data processing. An azimuth timescale transformation is used to deal with the nonlinear spatial variation of the azimuth frequency-modulation (FM) rate. An extended Omega-K is used to linearize the range frequency and achieve range cell migration correction (RCMC). To address the RACSP, the Doppler is linearized in the range-Doppler domain using a range-dependent Doppler scale transformation. The computational complexity and geometry distortion correction (GDC) are also discussed. Simulation results are shown to verify the effectiveness of the developed focusing approaches. [ABSTRACT FROM AUTHOR]

Multi-modal data fusion has recently been shown promise in classification tasks in remote sensing. Optical data and radar data, two important yet intrinsically different data sources, are attracting more and more attention for potential data fusion. It is already widely known that a machine learning-based methodology often yields excellent performance. However, the methodology relies on a large training set, which is very expensive to achieve in remote sensing. The semi-supervised manifold alignment (SSMA), a multi-modal data fusion algorithm, has been designed to amplify the impact of an existing training set by linking labeled data to unlabeled data via unsupervised techniques. In this paper, we explore the potential of SSMA in fusing optical data and polarimetric synthetic aperture radar (SAR) data, which are multi-sensory data sources. Furthermore, we propose a MAPPER-induced manifold alignment (MIMA) for the semi-supervised fusion of multi-sensory data sources. Our proposed method unites SSMA with MAPPER, which is developed from the emerging topological data analysis (TDA) field. To the best of our knowledge, this is the first time that SSMA has been applied on fusing optical data and SAR data, and also the first time that TDA has been applied in remote sensing. The conventional SSMA derives a topological structure using $k$ -nearest neighbor (kNN), while MIMA employs MAPPER, which considers the field knowledge and derives a novel topological structure through the spectral clustering in a data-driven fashion. The experimental results on data fusion with respect to land cover land use classification and local climate zone classification suggest superior performance of MIMA. [ABSTRACT FROM AUTHOR]

Despite the great success of correlation filter-based trackers in visual tracking, it is questionable whether they can still perform on the satellite video data, acquired by a satellite or space station very high above the earth. The difficulty lies in that the targets usually occupy only a few pixels compared with the image size of over one million pixels and almost melt into the similar background. Since correlation filter models strongly depend on the quality of features and the spatial layout of the tracked object, they would probably fail on satellite video tracking tasks. In this paper, we propose a hybrid kernel correlation filter (HKCF) tracker employing two complementary features adaptively in a ridge regression framework. One feature is the optical flow that can detect variation pixels of the target. The other one is the histogram of oriented gradient that can capture the contour and texture information in the target, and an adaptive fusion strategy is proposed to employ the strengths of both features in different satellite videos. Quantitative evaluations are performed on six real satellite video data sets. The results show that our approach outperforms state-of-the-art tracking methods while running at more than 100 frames/s. [ABSTRACT FROM AUTHOR]

In recent years, there has been growing interest in using precipitable water vapor (PWV) derived from global positioning system (GPS) signal delays to predict rainfall. However, the occurrence of rainfall is dependent on a myriad of atmospheric parameters. This paper proposes a systematic approach to analyze various parameters that affect precipitation in the atmosphere. Different ground-based weather features such as Temperature, Relative Humidity, Dew Point, Solar Radiation, PWV along with Seasonal and Diurnal variables are identified, and a detailed feature correlation study is presented. While all features play a significant role in rainfall classification, only a few of them, such as PWV, Solar Radiation, Seasonal, and Diurnal features, stand out for rainfall prediction. Based on these findings, an optimum set of features are used in a data-driven machine learning algorithm for rainfall prediction. The experimental evaluation using a 4-year (2012–2015) database shows a true detection rate of 80.4%, a false alarm rate of 20.3%, and an overall accuracy of 79.6%. Compared to the existing literature, our method significantly reduces the false alarm rates. [ABSTRACT FROM AUTHOR]

Detecting the vertical profile of optical properties is an important task in the remote sensing of the upper ocean, especially for 3-D reconstruction. Ocean color remote sensing can only provide surface information, while the light detection and ranging (lidar) technique can provide depth-resolved data. Lidar can provide global-scale observations of the upper ocean for days and nights with minimal atmospheric correction errors. Unfortunately, due to the strong multiple scattering effects that occur when light propagates in seawater, the simple lidar equation may cause some deviations between the actual measurements and the simulation of the lidar signals. In this paper, we present a shipborne oceanic lidar, which was developed to detect the optical properties of seawater. For evaluating the performance of the lidar system, a Monte Carlo (MC) model was established to simulate lidar signals based on the simultaneous in situ inherent optical properties of seawater. The lidar measurements and the MC simulation can provide both the lidar signals and the retrieved lidar attenuation coefficient $\alpha $. The results of the comparison indicate that the lidar-measured signals correspond well with the MC-simulated signals at different experiment stations in the Yellow Sea and at various receiving fields of view (FOVs). We also observed strong correlations between the lidar-measured $\alpha $ and MC-simulated $\alpha $ at different stations ($r = 0.95$) and at various FOVs ($r = 0.96$). The results indicate the reliability of the developed lidar system. [ABSTRACT FROM AUTHOR]

This paper presents an image-guided end-to-end registration approach for globally consistent 3-D registration of unordered terrestrial laser scanning (TLS) point clouds. The proposed method can handle arbitrary point clouds with reasonable pairwise overlap without knowledge about their initial position and orientation, without requiring artificial targets, and without needing to record the order of the scanning. One of the novel contributions of the proposed approach lies in the optimization of a scanning network. We retrieve the similarities of all scans based on a vocabulary tree using both the geometrically rectified panorama images and the corresponding 3-D point clouds. The approach also highlights the integral optimization in both the coarse and fine registration. A pose graph is introduced to realize global optimization at the end of the coarse step without primitives. After that, the results act as the inputs to start the pairwise fine registration, which is then followed by the minimum loop expansion (MLE) refinement. Comprehensive experiments demonstrated network optimization rates of over 60% using the image-guided strategy. Using the pose-graph optimization method, successful registration rates (SRRs) increased to 100% for all tested cases. The MLE not only accelerates the speed of the convergence but also improves registration accuracy, which reached 0.1 m and 0.1° in the translation and rotation angles, respectively. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel unsupervised change detection method of remote sensing (RS) images based on a unified framework for weighted collaborative representation (WCR) with robust deep dictionary learning (RDDL) and fuzzy clustering. Specifically, WCR is employed to collaboratively represent neighborhood features with lower computational complexity, for which the RDDL model is built to learn more effective and representative overcomplete dictionary and enhance the robustness against the noise and outliers. Meanwhile, in order to make the resulting collaborative coefficients more beneficial for clustering, the unified framework for WCR with RDDL and fuzzy clustering is designed. By doing so, our framework not only precludes the utilization of third-party clustering algorithm, but also achieves better detection performance. Subsequently, the spatial constraint is enforced on the membership matrix to yield the updated one for further improving the accuracy of change detection. Finally, a binary change mask (CM) is achieved by assigning the pixels into the changed and unchanged classes. Experiments are performed on five pairs of RS images, and experimental results demonstrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Current global leaf area index (LAI) products are generally produced from single-temporal satellite observations acquired by a single sensor. These LAI products are usually spatiotemporally discontinuous and inaccurate for some vegetation types in many areas, which limit the applications of these LAI products to the understanding of land dynamics. In this paper, a new data assimilation method was proposed to estimate multiscale and temporally continuous LAI values from multi-sensor time-series satellite observations with different spatial resolutions. An ensemble multiscale tree (EnMsT) was used to establish the conversion relationships between different spatial resolution LAI values, and dynamic models of the LAI at different spatial scales were constructed to evolve LAI at the corresponding spatial scales over time. At each time step, a multiscale Kalman filter (MKF) was introduced to fuse the predicted LAI values from the dynamic models at different spatial scales and to construct a forecasted EnMsT. When satellite observations were available, an ensemble multiscale filter (EnMsF) technique was applied to update the LAI values at each node of the EnMsT. The method was applied to estimate temporally continuous multiscale LAI values from the time series of Thematic Mapper (TM) or Enhanced Thematic Mapper Plus (ETM+) surface reflectance data and Moderate Resolution Imaging Spectroradiometer (MODIS) surface reflectance data at several sites with different vegetation types. The estimated multiscale LAI values were compared with the MODIS and GEOV2 LAI products, and the reference LAI values at the corresponding scales aggregated from the high-resolution LAI surface images. The estimated LAI values with the finest spatial resolution were also validated by ground measurements from the selected sites. The results show that the new method is able to simultaneously estimate temporally continuous multiscale LAI values by assimilating satellite observations with different spatial resolutions, and the estimated multiscale LAI values are well consistent with the reference LAI values at the corresponding scales over the selected sites. The root-mean-square error (RMSE) and coefficient of determination of the retrieved LAI values at the finest spatial scale against the ground measurements over the selected sites are 0.539 and 0.788, respectively. [ABSTRACT FROM AUTHOR]

While hyperspectral (HS) images play a significant role in many applications, they often suffer from issues such as low spatial resolution, low temporal resolution, and some of the acquired spectral bands are either with low signal-to-noise ratio (SNR) or invalid because of the very high-noise level. To address this issue, a spectral super-resolution method is proposed in this paper to recover a high-spectral-resolution HS image from multispectral (MS) images. The reconstructed HS image will have the same spatial resolution and coverage as the input MS image. The proposed method involves spectral improvement strategy and spatial preservation strategy. For spectral improvement strategy, auxiliary MS/HS image pairs of different landscapes are exploited to estimate spectral response relationship so that an HS image is obtained as an intermediate result. Then, spectral dictionary learning is exploited to recover a more accurate spectral reconstruction result. Spatial preservation strategy is used as a spatial constraint to ensure spatial consistency. In addition, the low-rank property of HS image is also introduced to make the use of global spectral coherence among HS bands. Experiments are conducted on both simulated and real datasets including spectral enhancement of RGB image and the MS image generated by AVIRIS data and real MS/HS data (ALI and Hyperion) captured by Earth Observing-1 (EO-1) satellite. Experiment results demonstrate the superiority of our proposed method to other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Remote sensing images play important roles in various earth surface observation applications. However, the hazy state of surface atmosphere can visually decrease the contrast and availability of remote sensing images. In this paper, we propose a haze and thin cloud removal method for single visible remote sensing images, which aims to robustly estimate haze thickness, atmospheric light, and transmission value from a remote sensing image with dense haze or thin cloud, and finally recovers a haze-free image. An elliptical boundary prior (EBP) is proposed to transform the haze thickness in each local patch from the pixels cluster in the spectral space, which is surrounded by an ellipse. With the aim of preventing highlight objects influences, an atmospheric light estimation approach is presented. The correlation of transmission and haze thickness is reconstructed to develop the scattering model for remote sensing images. The experimental results demonstrate that the proposed method can not only significantly improve the contrast and restore textures of various kinds of hazy remote sensing images but also well preserve the spectral information of visible bands. [ABSTRACT FROM AUTHOR]

Recently, deep neural networks have received intense interests in polarimetric synthetic aperture radar (PolSAR) image classification. However, its success is subject to the availability of large amounts of annotated data which require great efforts of experienced human annotators. Aiming at improving the classification performance with greatly reduced annotation cost, this paper presents an active deep learning approach for minimally supervised PolSAR image classification, which integrates active learning and fine-tuned convolutional neural network (CNN) into a principled framework. Starting from a CNN trained using a very limited number of labeled pixels, we iteratively and actively select the most informative candidates for annotation, and incrementally fine-tune the CNN by incorporating the newly annotated pixels. Moreover, to boost the performance and robustness of the proposed method, we employ Markov random field (MRF) to enforce class label smoothness, and data augmentation technique to enlarge the training set. We conducted extensive experiments on four real benchmark PolSAR images, and experiments demonstrated that our approach achieved state-of-the-art classification results with significantly reduced annotation cost. [ABSTRACT FROM AUTHOR]

The Earth-Observing One Hyperion sensor was decommissioned on March 20, 2017. Analysis of Libya 4 Pseudo-Invariant Calibration Sites (PICSs) image data acquired from 2004 to final decommissioning indicated statistically significant drifts in sensor response in the bands 8 to 16 (426.82, 436.99, 447.17, 457.34, 467.52, 477.69, 487.87, 498.04, and 508.22 nm) and bands 206 (2213.93 nm), 209 (2244.22 nm), and 210 (2254.22 nm). The estimated yearly drift in these bands ranges between −0.136% and −0.049%. After correction accounting for the estimated drift, the absolute radiometric calibration of the sensor was evaluated through vicarious reflectance-based calibrations performed at the South Dakota State University (SDSU) test site and the Radiometric Calibration Network (RadCalNet) Railroad Valley site using data from 2002 to 2015. Calibration correction coefficients including gain as much as 1.40 and bias as large as 0.132 were found except absorption bands (890–980, 1090–1180, 1305–1520, and 1750–2050 nm). Finally, the yearly drift and calibration correction coefficients were validated by comparison of the banded multispectral Hyperion data after any significant drift and calibration coefficient correction with Landsat 7 data. The validation showed that after drift and calibration coefficient correction, there is no significant gain and bias using different test sites at different signal levels. The drift and calibration correction coefficients of each band are provided in this paper. [ABSTRACT FROM AUTHOR]

There are many approaches to fuse panchromatic (PAN) and multispectral (MS) images for classification, mainly including sharpening-then-classification methods, classification-then-sharpening methods, and segmentation-then-classification methods. The generalized Chinese restaurant franchise (gCRF) is a segmentation-then-classification-like method to fuse very high resolution (VHR) PAN and MS images for classification, which has the limitation the same as that of the general segmentation-then-classification methods that segmentation errors will affect the subsequent classification. The problems of gCRF are that during the segmentation step, the spatial coherence in the image plane is deficient and the global clusters without spatial position information are used for segmentation, which may lead to undersegmented and disconnected regions in the segmentation results and decrease classification accuracy. In this paper, we propose an improved model, which overcomes the problems of the gCRF during the segmentation step, to increase the classification accuracy by the following two ways: 1) building the spatial coherence in the image plane by introducing neighborhood information of superpixels to construct the subimages and 2) using localized clusters with spatial location information instead of global clusters to measure the similarity between superpixels and segments. The experimental results show that the problems of undersegmentation and disconnected segments are both alleviated, resulting in better classification results in terms of the visual and quantitative aspects. [ABSTRACT FROM AUTHOR]

For hyperspectral remote sensing image (HSI) classification, the learning process of deep neural networks has been progressively advanced in depth, but the fine features are often largely lost or even disappear in the process of depth transfer. With the increase in feature aggregation and connectivity, the complexity of the network and the training parameters increases greatly, requiring more training time. This paper proposed a multi-scale dense network (MSDN) for HSI classification that made full use of different scale information in the network structure and combined scale information throughout the network. It implemented feature extraction of HSIs in two dimensions, including the features at fine and coarse levels. In the horizontal direction, it considered the deep extraction of HSI features, and the 3-D dense connection structure was used for aggregating features at different levels. In the vertical direction, scale information was considered, and three-scale feature maps at low, middle, and high levels were generated based on the first layer of the network. The MSDN used stride convolution for downsampling and combined feature information at different scale levels. The MSDN extracted features along the diagonal line. The network implemented the reconstruction of deep feature extraction and multi-scale fusion for HSI classification. The MSDN model performed well on representative HSI datasets, namely, the Indian Pines, Pavia University, Salinas, Botswana, and Kennedy Space Center datasets. It improved the training speed and accuracy for HSI classification and especially improved the convergence speed, which effectively saved computing resources and had high stability. [ABSTRACT FROM AUTHOR]

This paper presents a tensor alignment (TA) based domain adaptation (DA) method for hyperspectral image (HSI) classification. To be specific, HSIs in both domains are first segmented into superpixels, and tensors of both domains are constructed to include neighboring samples from a single superpixel. Then the subspace alignment (SA) between the two domains is achieved through alignment matrices, and the original tensors are projected as core tensors with lower dimensions into the invariant tensor subspace by applying projection matrices. To preserve the geometric information of original tensors, we employ a manifold regularization term for core tensors into the optimization process. The alignment matrices, projection matrices, and core tensors are solved in the framework of Tucker decomposition with an alternating optimization strategy. In addition, a postprocessing strategy is defined via pure samples extraction for each superpixel to further improve classification performance. Experimental results on four real HSIs demonstrate that the proposed method can achieve better performance compared with the state-of-the-art subspace learning methods when a limited amount of source labeled samples are available. [ABSTRACT FROM AUTHOR]

Although the deep convolutional neural network (DCNN) has been successfully applied to target classification of military vehicles based on synthetic aperture radar (SAR), most of the available methods do not fully exploit the characteristics of continuous SAR imaging and only utilize single image for recognition. To extract significant identification features contained in the image sequence, this paper proposes a sequence of SAR target classification method based on bidirectional convolution-recurrent network. In this network, we extract spatial features of each image through DCNNs without the fully connected layer, and then learn sequence features by bidirectional long short-term memory networks. Finally, we design the average softmax classifier to obtain the classification results. Compared with the available methods, the proposed network takes advantage of the significant information in the image sequence and achieves higher classification accuracy in the moving and stationary target acquisition and recognition data set. In addition, it has shown robustness to large depression angle variants, configuration variants, and version variants. [ABSTRACT FROM AUTHOR]

Multibaseline (MB) phase unwrapping (PU) is a critical processing step for the MB synthetic aperture radar interferometry (InSAR). Compared with the traditional single-baseline (SB) PU, MB PU has wider application scope on the study area with strong phase variation, because it can overcome the limitation of the Itoh condition. Since most of the MB PU methods need to process multiple interferograms simultaneously, the size of the input interferograms will pose unique challenges when it exceeds the limit of computational capabilities. Until now, the research achievements related to large-scale (LS) MB PU have been quite limited. To deal with such case, we propose a technique for applying the two-stage programming-based MB PU method (TSPA) proposed by Yu and Lan to the LS MB InSAR data set in this paper. To be specific, the MB $L^\kappa $ -norm envelope-sparsity theorem is proposed and proved first, which gives a sufficient condition to exactly guarantee the consistency between local and global TSPA solutions. Afterward, based on the MB $L^\kappa $ -norm envelope-sparsity theorem, we put forward an interferogram tiling strategy, whereby each LS interferogram in the input MB InSAR data set is partitioned into a set of several smaller sub-interferograms that can be unwrapped individually by TSPA in parallel or in series. Both theoretical analysis and experimental results show that the proposed tiling strategy is effective for the LS MB PU problem. [ABSTRACT FROM AUTHOR]

In order to better interpret polarimetric synthetic aperture radar (PolSAR) images, many scholars tend to do target decomposition for PolSAR images and utilize the obtained features to perform subsequent classification. These target decomposition features play an important role in terrain classification but completely utilizing them produces a high computational complexity. Furthermore, some features have a negative impact on the classification task. Therefore, selecting the appropriate amount of high-quality features is of great significance to the classification task. In this paper, we propose a convolutional neural network (CNN)-based feature selection algorithm for PolSAR image classification. First, we design a 1-D CNN for feature selection, then train the designed network with all the decomposition features to obtain a trained model. Second, the Kullback–Leibler distance (KLD) between different features is utilized as a standard to select feature subsets. Third, feature subsets with excellent performance form the final results. Due to the special structure of the 1-D CNN, repetitively training model is avoided when the input changes. Different from traditional feature selection methods, our method considers the performance of features combination rather than single feature contribution. To this end, the feature subsets selected by the proposed method are more useful to the classification task. Innovatively introducing KLD in the selection stage avoids random selection and improves the selection efficiency. Finally, we validate the performance of selected feature subsets in traditional and deep learning classification frameworks. Experiments demonstrate that features selected by the proposed method have a good performance comparing with others on three real PolSAR data sets. [ABSTRACT FROM AUTHOR]

In this paper, an efficient and accurate imaging algorithm is presented for Ground-Based Synthetic Aperture Radar (GB-SAR) or other radar systems that could be formed by a physical or synthetic linear aperture. The imaging algorithm is based on the fractional Fourier transform (FrFT) for the azimuth compression. A mathematical framework is derived according to the projection of a sample reflectivity image onto the pseudopolar coordinate, and its implementation was presented. With the data acquisition geometry and the pseudopolar imaging coordinate, the phase of a point target can be expressed as a quadratic phase exponential. It makes that only 1-D FrFT is needed for the azimuth compression of the time-domain backscatter data for the GB-SAR imaging problem. By further research, the optimal transformation order that represents the spatial frequency changes by the FrFT was given subsequently. Taking advantage of this optimal representation, the proposed approach avoids the large calculation that occurs in the time-domain back projection (TDBP). Comparing to the far-field pseudopolar format algorithm (FPFA), the accuracy of the proposed algorithm is much improved. Meanwhile, the proposed approach holds almost the same computational cost and complexity as the FPFA. The proposed approach keeps the advantages of the imaging quality of the TDBP and the computational cost of the FPFA that are two important aspects of the GB-SAR applications. Both the numerical simulation and the field GB-SAR experiment show that the algorithm is more suitable for the high-precision GB-SAR imaging, especially for the near field. [ABSTRACT FROM AUTHOR]

Lightweight hyperspectral cameras based on frame geometry have been used for several applications in unmanned aerial vehicles (UAVs). The camera used in this investigation is based on a tunable Fabry–Pérot interferometer (FPI) and works on the time-sequential principle for band acquisition. Due to this feature, when collecting images in movement, hypercubes are generated with unregistered bands, and consequently, the individual bands in each hypercube have different exterior orientation parameters (EOPs), which must be estimated by an image orientation procedure. The objective of this paper was to develop an approach for bundle block adjustment (BBA) using time-dependent polynomial models for simultaneous image orientation of all bands. The procedure consists of using a minimum number of bands to estimate the polynomial parameters. From the estimated polynomial parameters, the EOPs (position and attitude) of all bands can be determined. In tests with backprojecting ground points to interpolated bands, the average error was smaller than 1 pixel, which indicates excellent potential for orthomosaic generation. The polynomial technique was also compared to the conventional BBA. The discrepancies assessed at checkpoints indicated a similar error for both techniques, which were approximately less than the pixel size in planimetry and less than 2.8 times the pixel size in height. Therefore, the results show that the spectral band orientation can be performed with the proposed technique, assuming that the trajectory during the cube can be modeled with the polynomial model, which reduces the workload while achieving the same accuracy as conventional BBA for all bands. [ABSTRACT FROM AUTHOR]

Time-series remote sensing (RS) images are often corrupted by various types of missing information such as dead pixels, clouds, and cloud shadows that significantly influence the subsequent applications. In this paper, we introduce a new low-rank tensor decomposition model, termed tensor ring (TR) decomposition, to the analysis of RS data sets and propose a TR completion method for the missing information reconstruction. The proposed TR completion model has the ability to utilize the low-rank property of time-series RS images from different dimensions. To further explore the smoothness of the RS image spatial information, total-variation regularization is also incorporated into the TR completion model. The proposed model is efficiently solved using two algorithms, the augmented Lagrange multiplier (ALM) and the alternating least square (ALS) methods. The simulated and real-data experiments show superior performance compared to other state-of-the-art low-rank related algorithms. [ABSTRACT FROM AUTHOR]

Earthquake early warning system uses high-speed computer network to transmit earthquake information to population center ahead of the arrival of destructive earthquake waves. This short (10 s of seconds) lead time will allow emergency responses such as turning off gas pipeline valves to be activated to mitigate potential disaster and casualties. However, the excessive false alarm rate of such a system imposes heavy cost in terms of loss of services, undue panics, and diminishing credibility of such a warning system. At the current, the decision algorithm to issue an early warning of the onset of an earthquake is often based on empirically chosen features and heuristically set thresholds and suffers from excessive false alarm rate. In this paper, we experimented with three advanced machine learning algorithms, namely, $K$ -nearest neighbor (KNN), classification tree, and support vector machine (SVM) and compared their performance against a traditional criterion-based method. Using the seismic data collected by an experimental strong motion detection network in Taiwan for these experiments, we observed that the machine learning algorithms exhibit higher detection accuracy with much reduced false alarm rate. [ABSTRACT FROM AUTHOR]

Wildfires are one of the most destructive disasters on the planet. They also significantly impact the land surface. Satellite data have been widely used to detect the outbreak and monitor the expansion of fire incidents for damage assessment and disaster management. Polar-orbiting satellite data have been used for several decades but data from geostationary satellites, which can provide observations with a high temporal resolution, have received much less attention. This paper utilizes data from FengYun-2G, a Chinese geostationary satellite, to detect wildfires in two selected research regions in January 2016. The detection algorithm systemizes image-based analysis to filter out obvious nonfire pixels and temporal analysis to confirm the true detections. Fire detection is based on comparisons between predicted and observed values. The results show that the proposed method has some advantages compared with the use of polar-orbiting satellite data, including early detection and continuous observation. The validation work is conducted based on the collection 6.1 Global Monthly Fire Location Product generated from fire detections by Moderate Resolution Imaging Spectroradiometer (MODIS) sensors. The average accuracy within the target time is 56%, while the omission error rate is over 78%. In detail, the algorithm has a lower omission error rate in Australia while it fails in detecting most of the fire pixels in India. The dominance of small fire incidents, as well as low spatial resolution greatly limit the detection ability. Many small fires were beyond the ability of Stretched Visible and Infrared Spin Scan Radiometer (S-VISSR) data when no significant fire characteristics could be captured. Future development of the algorithm will focus on improving the results by enhancing the adaption to different regions, as well as, including multisource data sets. [ABSTRACT FROM AUTHOR]

Remotely sensed images represent an important source of information for monitoring land changes that may occur. There is, therefore, a need to analyze and interpret such information in order to extract useful semantic change interpretations. However, extracting such semantics from satellite images is a complex task that requires prior and contextual knowledge. In this paper, we focus on the issue of semantic scene interpretation for change interpretation. Consequently, a strategy for semantic remote-sensing imagery scene interpretation is proposed. This strategy is based on a representative framework that is structured around several levels of interpretation: the pixel level, the visual primitive level, the object level, the scene level, and the change interpretation level. Each level integrates a logical mechanism to extract useful knowledge for interpretation. The proposed model has been evaluated using two Landsat scene images acquired in 2000 [Landsat Enhanced Thematic Mapper plus (ETM+)] and 2017 (Landsat 8) in order to check its relevance for semantic scene and change interpretation. Precision, recall, and F-measure metrics were used in order to show the capacity of the proposed methodology for semantic classification. A visual evaluation was also performed to evaluate the performance of the presented interpretation strategy, and the query results for each level show a promising capability for semantic object classification, spatial and temporal relations’ extraction, and change interpretation. [ABSTRACT FROM AUTHOR]

This paper presents a new technique for automated detection of multi-year (MY) and first-year (FY) sea ice from RADARSAT-2 dual-polarization HH–HV ScanSAR Wide images under cold environmental conditions. The approach is applied to 2.05 km $\times2.05$ km ($41 \times 41$ pixels) spatial window in the situation where the area is labeled as ice by our recently introduced ice and open water detection approach. The probability of the presence of MY ice is modeled as a function of the two selected predictor parameters computed over each spatial window: the HV/HH polarization ratio and the standard deviation of the HV signal. The proposed MY ice probability model was built based on thousands of synthetic aperture radar (SAR) images and corresponding Canadian Ice Service (CIS) Image Analysis products covering the 2010–2016 time period, not including 2013. Our verification results for the independent testing subset for the year 2013 against the CIS Image Analysis products suggest that approximately 50% of pure MY and FY ice samples were classified with an accuracy of 98.2%. The incidence angle correction of HH and HV backscatter does not improve MY and FY ice detection results in the space of the selected predictor parameters. The proposed technique will be used as part of the Environment and Climate Change Canada Regional Ice-Ocean Prediction System in support of assimilation of ice thickness retrievals from Cryosat-2 and Soil Moisture and Ocean Salinity mission data. [ABSTRACT FROM AUTHOR]

For numerous applications in image registration, sub-pixel translation estimation is a fundamental task, and increasing attention has been given to methods based on image phase information. However, we have found that none of these methods is universal. In other words, for any one of these methods, we can always find some image pairs which will not be well matched. In this paper, by introducing the cyclic shift matrix (CSM), we present a new model for the translation matching problem and derive a least squares solution for the model. In addition, by repeatedly applying the CSM to the matching image, an iterative CSM method is proposed to further improve the matching accuracy. Furthermore, we show that the traditional phase-based matching algorithms can only achieve an exact solution when there is a cyclic shift relationship between the images to be matched. The proposed method is evaluated using simulated and real images and demonstrates a better performance in both accuracy and robustness compared with the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

In recent years, anomaly detection (AD) has enjoyed a growing interest in hyperspectral data analysis. However, most state-of-the-art detectors need to work with the entire hyperspectral cube, what prevents their use for applications under real-time constraints, especially when the hyperspectral data are collected by push-broom scanners that acquire the hyperspectral images (HSIs) in a line-by-line fashion. In this paper, a Line-by-Line Fast Anomaly Detector for Hyperspectral Imagery (LbL-FAD) is proposed, which is capable of processing each sensed line as soon as it is captured. The LbL-FAD works under the assumption that anomalous pixels cannot be well represented by the background distribution. It uses an orthogonal projection strategy for extracting a set of pixels from the first captured hyperspectral frames, i.e., lines of pixels, that are used for representing the background distribution. Using these pixels, the LbL-FAD proposes a hardware-friendly alternative to compute the orthogonal subspace to that spanned by the selected background samples, making the anomalous pixels better detectable. In addition, the LbL-FAD incorporates an automatic thresholding method which provides line-by-line and real-time binary maps where anomalous targets are segmented from the background. This novelty clearly differentiates the proposed LbL-FAD from the conventional anomaly detectors, which usually are not able to automatically discriminate anomalous pixels from background pixels until the entire image is processed. Several experiments have been carried out using real HSIs collected by different sensors. The obtained results clearly support the benefits of our proposal, both in terms of the accuracy of the detection performance and the computational complexity. [ABSTRACT FROM AUTHOR]

Feature learning-based polarimetric synthetic aperture radar (PolSAR) classification model will generally suffer from the challenge of deficient labeled pixels. In this paper, we propose a novel generative-discriminative network for PolSAR polar-spatial feature fusion learning and classification, which comprises of a deep generative network and a discriminative network with their bottom layers shared. With this architecture, it enables to make use of both labeled and unlabeled pixels in a PolSAR image for model learning in a semisupervised way. Moreover, the proposed network imposes a Gaussian random field prior and a conditional random field posterior on the learned fusion features and the output label configuration, respectively. Without the need of the complicated recurrent iterations, our network can still efficiently produce the structured fusion feature as well as a smoothed classification map by involving some auxiliary variables, and it is specifically optimized via variational inference within an alternating direction method of multipliers iteration scheme. Extensive experiments on different benchmark PolSAR imageries demonstrate the effectiveness and superiority of the proposed network. Compared with other state-of-the-art algorithms of PolSAR feature learning and classification, our model can achieve a much better performance in terms of the visual quality of the label map and overall classification accuracy, facilitating the much less labeling pixels. [ABSTRACT FROM AUTHOR]

This paper presents a class information (CI)-based band selection (BS) approach to hyperspectral image classification (HSIC). It introduces a new concept from an information theory point of view, CI which can be used to determine an appropriate weight imposed on each class of interest. Specifically, two types of criteria, intraclass information criterion (IC) and interclass IC are derived as CI probabilities to measure CI that can be used to determine the number of training samples required to be selected for each class. With such CI-calculated probabilities, another new concept called class self-information (CSI) is also defined for each class that can be further used to define the class entropy (CE) so that CSI and CE can be used to determine the number of bands required for BS, $n_{\text {BS}}$. In order to find desired $n_{\text {BS}}$ bands, two types of BS methods based on CSI and CE are custom-designed, called single class signature-constrained BS (SCSC-BS) which utilizes the constrained energy minimization (CEM) to constrain each individual class signature to select bands for a particular class according to its CSI-determined $n_{\text {BS}}$ and a multiple class signatures-constrained BS (MCSC-BS) which takes advantage of linearly constrained minimum variance (LCMV) to constrain all class signatures to select CE-determined $n_{\text {BS}}$ bands for all classes. These SCSC-BS and MCSC-BS selected bands are then used to perform classification and evaluated by CI-weighted classification measures by real image experiments. The results show that HSIC using judiciously selected partial bands as well as CI-weighted measures can improve HSIC with using full bands. [ABSTRACT FROM AUTHOR]

The filtered backprojection (FBP) algorithm is a popular choice for complicated trajectory synthetic aperture radar (SAR) image formation processing due to its inherent nonlinear motion compensation capability. However, how to efficiently refocus the defocused FBP imagery when the motion measurement is not accurate enough is still a challenging problem. In this paper, a new interpretation of the FBP derivation is presented from the Fourier transform point of view. Based on this new viewpoint, the property of the residual 2-D phase error in FBP imagery is analyzed in detail. Then, by incorporating the derived a priori knowledge on the 2-D phase error, an accurate and efficient 2-D autofocus approach is proposed. This new approach performs the parameter estimation in a dimension-reduced parameter subspace by exploiting the a priori analytical structure of the 2-D phase error, therefore it possesses much higher accuracy and efficiency than the conventional blind methods. Finally, experimental results clearly demonstrate the effectiveness and robustness of the proposed method. [ABSTRACT FROM AUTHOR]

Microwave radiometers are the key sensors to globally monitor environmental parameters; however, it suffers from its low and nonuniform spatial resolution. In this paper, a superresolution (SR) technique based on image degradation and residual network is proposed to enhance the spatial resolution of microwave radiometer data. Specifically, an improved degradation model is proposed to construct pairs of high-resolution (HR) and low-resolution (LR) data for training and testing. In addition, a new residual network connected by the SR main and gradient auxiliary branches in parallel is designed to achieve SR reconstructions, where eight-channel gradient maps extracted from LR data are input into the auxiliary branch to help to reconstruct. SR results are eventually generated by the trained SR network. Experiments executed on both simulated and actual data demonstrate the soundness and the superiority of the proposed SR technique. [ABSTRACT FROM AUTHOR]

It is a difficult task for high-resolution maritime radars operating at a fast scan mode to find sea-surface floating and low-velocity small targets due to ubiquitous sea clutter, sporadic sea spikes like target returns, and shortage of shared database. In this paper, a simulation method is presented to generate high-resolution radar returns of a local sea surface with a structural trend in texture and sea spikes by integrating the existing results on large-scale sea surface generation, sea surface reflectivity, Doppler characteristics of sea clutter, and properties of sea spikes. Generally, sea-surface small target detection at a fast scan mode is composed of intrascan integration to suppress sea clutter and interscan integration to exclude false alarms and sea spikes. Based on the Doppler difference between targets and sea clutter at the two time scales of a coherent processing interval (CPI) of tens of milliseconds and a scan period of several seconds, a Doppler-guided retrospective filter (DGRF) detector is proposed, which uses the optimum coherent detection in intrascan integration and a DGRF in interscan binary and test statistic integrations. The two integrations and Doppler consistency of integrated plots are fused for the final decision. Owing to the Doppler guidance, the proposed detector effectively impedes the integration of false alarms of the intrascan processing and provides significant detection performance improvement, which is verified by the simulated data and real radar data with test small targets. [ABSTRACT FROM AUTHOR]

Pixel selection is a crucial step of all advanced Differential Interferometric Synthetic Aperture Radar (DInSAR) techniques that have a direct impact on the quality of the final DInSAR products. In this paper, a full-resolution phase quality estimator, i.e., the temporal phase coherence (TPC), is proposed for DInSAR pixel selection. The method is able to work with both distributed scatterers (DSs) and permanent scatterers (PSs). The influence of different neighboring window sizes and types of interferograms combinations [both the single-master (SM) and the multi-master (MM)] on TPC has been studied. The relationship between TPC and phase standard deviation (STD) of the selected pixels has also been derived. Together with the classical coherence and amplitude dispersion methods, the TPC pixel selection algorithm has been tested on 37 VV polarization Radarsat-2 images of Barcelona Airport. Results show the feasibility and effectiveness of TPC pixel selection algorithm. Besides obvious improvements in the number of selected pixels, the new method shows some other advantages comparing with the other classical two. The proposed pixel selection algorithm, which presents an affordable computational cost, is easy to be implemented and incorporated into any advanced DInSAR processing chain for high-quality pixels’ identification. [ABSTRACT FROM AUTHOR]

Synthetic aperture radar (SAR) is an active microwave imaging sensor with the capability of working in all-weather, all-day to provide high-resolution SAR images. Recently, SAR images have been widely used in civilian and military fields, such as ship detection. The scales of different ships vary in SAR images, especially for small-scale ships, which only occupy few pixels and have lower contrast. Compared with large-scale ships, the current ship detection methods are insensitive to small-scale ships. Therefore, the ship detection methods are facing difficulties with multi-scale ship detection in SAR images. A novel multi-scale ship detection method based on a dense attention pyramid network (DAPN) in SAR images is proposed in this paper. The DAPN adopts a pyramid structure, which densely connects convolutional block attention module (CBAM) to each concatenated feature map from top to bottom of the pyramid network. In this way, abundant features containing resolution and semantic information are extracted for multi-scale ship detection while refining concatenated feature maps to highlight salient features for specific scales by CBAM. Then, the salient features are integrated with global unblurred features to improve accuracy effectively in SAR images. Finally, the fused feature maps are fed to the detection network to obtain the final detection results. Experiments on the data set of SAR ship detection data set (SSDD) including multi-scale ships in various SAR images show that the proposed method can detect multi-scale ships in different scenes of SAR images with extremely high accuracy and outperforms other ship detection methods implemented on SSDD. [ABSTRACT FROM AUTHOR]

Hyperspectral remote sensing imagery provides valuable and rich information to distinguish the characteristics of materials. However, this advantage of hyperspectral imagery often encounters the problem of a limited amount of training samples, which is caused by the difficulty of manually labeling. Fortunately, the spatial distribution of surface objects can be integrated with the spectral signature to improve the discriminative ability. In this paper, a 3-D Gaussian–Gabor feature extraction and selection framework has been proposed for hyperspectral image classification. First, a bank of 3-D Gaussian–Gabor filters are convolved with the concatenated data of both extended multi-attribute profile (EMAP) features and raw hyperspectral data. Second, an improved fast density peak clustering (IFDPC) method is introduced to select the most representative features from each extracted 3-D Gaussian–Gabor feature cube. Finally, the retained features are combined together to accomplish the classification task. The proposed method is thus named as GG-IFDPC. Three real hyperspectral imagery data sets have been utilized, and the experiments demonstrate the advantages of the proposed GG-IFDPC approach over the compared ones. [ABSTRACT FROM AUTHOR]

The Soil Moisture Active Passive (SMAP) mission currently provides three surface soil moisture products based solely on instrument measurements. The three soil moisture products are: 1) the radiometer-only 36 km gridded; 2) a radiometer-only enhanced product gridded at 9 km; and 3) a high-resolution (3 km) SMAP-Sentinel active–passive product. It is important to validate these released SMAP soil moisture products over various land covers and hydroclimatic domains before they are routinely used in scientific research and applications. This paper evaluates SMAP-based soil moisture products for typical Indian conditions of extreme seasonal variability that leads to changes from very wet to dry soil, especially for the paddy dominated region. The assessment metrics indicate that the enhanced passive-only soil moisture product meets the SMAP accuracy requirement of 0.04 m3/m3 during the nongrowing season (NGS) with unbiased root-mean-square error (ubRMSE) values ranging between 0.025 and 0.036 m3/m3. However, this product underperformed during the paddy growing season (GS) with ubRMSE values ranging between 0.063 and 0.097 m3/m3. In addition, the SMAP-Sentinel active–passive soil moisture product shows satisfactory performance during the NGS (ubRMSE, 0.017–0.051 m3/m3), but during the GS, ubRMSE ranged between 0.089 and 0.104 m3/m3. Use of the vegetation water content climatology and low clay fraction in SMAP baseline algorithm (auxiliary database) that mismatched with the actual values may be the possible source of errors and biases in the SMAP soil moisture products. The reported study provides guidelines for the application of enhanced SMAP soil moisture products in India, especially for the tropical region, and provides information that can be used to improve the retrieval algorithm. [ABSTRACT FROM AUTHOR]

Nonvolume decorrelation ($\gamma _{\mathrm {Nonvol}}$) united with the unknown ground contribution will bring a 2-D ambiguity to volume-only coherence, making the inversion underdetermined even when multiple baselines are available. In the context of random volume over ground (RVoG) model and three-stage algorithm, this paper theoretically presented the varied response of different baselines to both $\gamma _{\mathrm {Nonvol}}$ and ground contribution, and then proposed a new multi-baseline inversion method to reduce the 2-D ambiguity. The proposed method includes two steps, calculating the common overlapped ambiguity from different baselines and fixing the extinction coefficient, to more accurately retrieve the volume-only coherence and forest height. It makes no assumptions on $\gamma _{\mathrm {Nonvol}}$ and ground contribution. The method was validated and compared with three single-baseline inversions and two published multi-baseline inversions by using the airborne P-band polarimetric SAR interferometry (PolInSAR) data and the reference data of LiDAR canopy height model (CHM) over a dense rainforest site. Results showed that the developed multi-baseline method successfully reduced the combined influence of both $\gamma _{\mathrm {Nonvol}}$ and ground contribution, and performed better than any single baseline, improving the ${R}^{2}$ from 0.60 to 0.77 and unbiased root-mean-square error (RMSE) from 1.32 to 1.04 m at the scale of ca. $100 \times 140\,\,\text{m}^{2}$. Moreover, the multi-baseline scheme is relatively robust among different baseline combinations. [ABSTRACT FROM AUTHOR]

Reconstructing a 3-D scene from aerial sensor data creating a textured digital surface model (TDSM), consisting of a LiDAR point cloud and an overlaid image, is valuable in many applications including agriculture, military, surveying, and natural disaster response. When collecting LiDAR from an aircraft, the navigation system accuracy must exceed the LiDAR accuracy to properly reference returns in 3-D space. Precision navigation systems can be expensive and often require full-scale aircraft to house such systems. Synchronizing the LiDAR sensor and a camera, using a texel camera calibration, provides additional information that reduces the need for precision navigation equipment. This paper describes a bundle adjustment technique for aerial texel images that allows for relatively low-accuracy navigation systems to be used with low-cost LiDAR and camera data to form higher fidelity terrain models. The bundle adjustment objective function utilizes matching image points, measured LiDAR distances, and the texel camera calibration and does not require overlapping LiDAR scans or ground control points. The utility of this method is proven using a simulated texel camera and unmanned aerial system (UAS) flight data created from aerial photographs and elevation data. A small UAS is chosen as the target vehicle due to its relatively inexpensive hardware and operating costs, illustrating the power of this method in accurately referencing the LiDAR and camera data. In the 3-D reconstruction, the 1- $\sigma $ accuracy between LiDAR measurements across the scene is on the order of the digital camera pixel size. [ABSTRACT FROM AUTHOR]

In this paper, we developed a unified and operational cloud mask algorithm for the new-generation geostationary (GEO) meteorological satellite imagers of the Advanced Geostationary Radiation Imager (AGRI) aboard Fengyun-4A (FY-4A) and the Advanced Himawari Imager (AHI) aboard Himawari-8 (H08). We investigated the all-round performance of the cloud mask algorithm. Spatiotemporally, the algorithm matches the official Collection-6 cloud mask products of a Moderate Resolution Imaging Spectroradiometer (MODIS) from both the Terra and Aqua platforms, which we employed as the benchmark for performing intercomparisons and validations. The robust cloud mask algorithm can show high consistency between FY-4A/AGRI and H08/AHI. The MODIS-based validation results suggest that cloudy scene identification is better than that observed for clear skies for both FY-4A/AGRI and H08/AHI; there is also a relatively low false-alarm ratio (FAR). Moreover, the algorithm is more reliable during daytime hours, with a hit rate (HR) of approximately 92% for both FY-4A/AGRI and H08/AHI. We found slightly higher accuracy in cloud-masking results over water than those over land. Furthermore, we found that more than 67% of the matched pixels for both advanced GEO imagers had no bias when taking MODIS as the benchmark. Overall, HR values were approximately 91.04% and 91.82% for FY-4A/AGRI and H08/AHI, respectively. These results confirm the high quality of the algorithm for retrieving real-time cloud mask products. [ABSTRACT FROM AUTHOR]

Efficient and accurate simulation of ground penetrating radar (GPR) in the open region helps immensely in both grasping the features of echoes and facilitating the interpretation of real GPR data. Due to the limitation of the computer model, however, the strong artificial boundary reflections, especially the low-frequency propagating waves encountered at the late stage of simulation greatly affect the simulation accuracy of GPR. This paper presents an innovative optimized unsplit-field convolutional perfectly matched layer (UCPML) based on rotated staggered grid (RSG) scheme to truncate the finite-difference time-domain (FDTD) lattices. Rather than obey the sharp variation based on an ${m}$ th-order polynomial, the optimized approach employs a novel optimized term and an adjustment factor to seek a gentle variation on optimal constitutive coefficients. This guarantees that the determination of optimal constitutive coefficients can be less influenced by the order of polynomial and especially, to improve the absorptive performance on low-frequency propagating waves. The calculating efficiency and accuracy of the RSG-FDTD scheme, as well as the absorbing performance of the optimized UCPML, are verified by two numerical examples. In particular, the analysis of the amplitude-frequency features of low-frequency clutters at steady state of the electromagnetic (EM) field and the corresponding global reflection error in the time–frequency domain is also presented. [ABSTRACT FROM AUTHOR]

Enhancing the contrast of target and clutter is a crucial issue in synthetic aperture radar (SAR) image target detection. In this paper, we define a novel subspace, called minimal clutter-to-signal ratio (MCSR) subspace, which can minimize the clutter-to-signal ratio (CSR) by projecting the feature vector to the subspace. Based on MCSR, a novel polarimetric contrast enhancement method is proposed. The MCSR subspace is learned based on the commonly used polarimetric feature vectors extracted from the labeled training SAR image pixels. The feature vectors extracted form candidate SAR image pixels are projected to the MCSR subspace. By calculating the square norm of each transformed feature vector, an enhanced image can be obtained. It is demonstrated that the existing optimization of polarimetric contrast enhancement (OPCE) is a special case of the proposed method to some extent. Experimental results show that our method outperforms the traditional OPCE method on the RadarSat-2 SAR data. [ABSTRACT FROM AUTHOR]

Applications of fully polarimetric synthetic aperture radar (POLSAR) have increased in the past few decades. The potential of model-based decompositions is coupled with polarimetric information extraction from the POLSAR data for target identification and classification. The coherency matrix $[T]$ with nine independent parameters, and associated with some physical scattering models, serves as input to these decompositions. This paper attempts to assign one such physical scattering model to the real part of $T_{23}$ ($\text {Re}\{{T}_{23}\}$) and develop a new scattering power decomposition model, called as the seven-component scattering decomposition (7SD). Previously developed scattering power models have eliminated $\text {Re}\{T_{23}\}$ , assuming the orientation angle compensation condition, to reduce the number of independent $[T]$ parameters. The proposed 7SD model has been tested on fully polarimetric SAR data sets acquired by the spaceborne Advanced Land Observing Satellite-2/Phased Array type L-band Synthetic Aperture Radar-2 (ALOS-2/PALSAR-2) and airborne F-SAR, and the results are compared with the existing scattering power decompositions. The physical scattering model for $\text {Re}\{T_{23}\}$ is derived from a particular configuration of dipoles (referred to as “mixed dipole” configuration), which gives rise to compound scattering. The mixed-dipole scattering occurs in urban areas that are highly oriented to the radar illumination direction as well as in vegetation areas. 7SD also delivers an additional mixed dipole scattering power compared to the previous six-component scattering model. The mixed-dipole scattering model reduces the contribution of volume scattering power in double-bounce predominant areas (such as oriented urban blocks), thereby imparting improved understanding of the polarimetric information contained in the coherency matrix. [ABSTRACT FROM AUTHOR]