Search

In this article, we propose a polarimetric calibration (PolCal) algorithm to estimate the system crosstalk, cross-polarization (x-pol), and co-polarization (co-pol) channel imbalance (CI) when ground corner reflectors (CRs) are unavailable. The current PolCal process requires at least one trihedral CR to determine the co-pol CI. However, the deployment of ground CRs is costly and may even be impossible in some areas. To calibrate a polarimetric image without CRs, our proposed method automatically extracts the volume-dominated and Bragg-like pixels as a reference to estimate the crosstalk, x-pol, and co-pol CI values. Then, a first-order polynomial model is exploited to fit the co-pol CI to further improve calibration accuracy. In the experimental section, we demonstrate the effectiveness of our proposed method with data from two of China’s newly developed very high-resolution systems. The experiments confirmed that the proposed workflow can be considered as a feasible calibration scheme when the ground deployment of CRs is impossible, and it is also an effective analysis tool for the assessment of calibrated products. [ABSTRACT FROM AUTHOR]

The Chinese Gaofen-3 satellite was launched into space in 2016. Based on the corner reflector (CR) evaluation, it was found that the co-pol channel imbalance phase may exceed the maximum tolerance in the distributed standard product, i.e., ± 10°. The ground-deployed CRs are the most precise way to calibrate the phase error. However, the Mongolia calibration site of Gaofen-3 is a temporal calibration field, and the calibration time is limited for the periodic evaluation over the 8-year satellite life. In this paper, to accelerate the Gaofen-3 calibration mission, we propose an improved unitary zero helix (IUZH) framework to fully replace the use of CRs when estimating the co-pol channel imbalance phase by the use of natural media. Compared with our previous works (Shi et al., 2014; Shi et al., 2020), this novel algorithm presents three main contributions to remote sensing society. Firstly, we believe that this natural media calibration technique could replace the use of CRs, to satisfy the radar design specification, and that this natural media calibration technique could be more than just a substitute in an emergency event when there are no CRs deployed in-scene. Secondly, the IUZH framework is less dependent on choosing the particular reference targets, such as isolated point-like objects or Amazon forest. As a result, it will help radar researchers to relax the constraint of selecting references, and will make the non-CR calibration task easier in satellite or airborne cases. Last but not least, the proposed technique simultaneously derives the calibration phase after the sensor has completed a long-strip observation, which will significantly accelerate the Gaofen-3 external calibration mission, at little cost and time-consuming. The experiments with more than 500 images demonstrate that the phase bias of the Gaofen-3 standard product can be robustly calibrated, even when CRs are unavailable in the scene. The HH and VV imbalance phase with the IUZH method is generally found to be less than 4°. The potential phase error of the Gaofen-3 product is thus significantly suppressed, and the calibration accuracy satisfies the 10° design specification. [ABSTRACT FROM AUTHOR]

Abstract Polarimetric calibration is a critical step to suppress the potential system distortion before implementing any applications for polarimetric synthetic aperture radar (PolSAR). Among all the distortion elements, the crosstalk and cross-pol channel imbalance are generally estimated by the use of natural media, and the co-pol channel imbalance is traditionally solved by the use of corner reflectors (CRs). However, the deployment of ground CRs is costly and may even be impossible in some areas. Many bright point targets, such as poles, lamps, and corner points of structures, are commonly found in manmade regions. In particular, if the object orientation is parallel or perpendicular to the radar flight direction, some points will present similar polarimetric responses to trihedral or dihedral CRs. These points, which are referred to here as "CR-like targets", can be treated as a supplement to approximately solve the system distortion elements when CRs are unavailable. In this paper, we propose a novel step-by-step algorithm to determine the CR-like targets and estimate the co-pol channel imbalance phase in uncalibrated PolSAR imagery. Chinese X-band airborne and C-band satellite PolSAR data were used to test the proposed method. Compared with the CR-derived co-pol channel imbalance phase, the solution errors of the CR-like targets were 1.305° and 0.03° for the X- and C-band experiments, respectively. The results of the experiments confirm that the solutions of the CR-like targets are very close to those of ground-deployed CRs, and the proposed method can be considered as an effective way to calibrate PolSAR images when sufficient CR-like point targets are detected in manmade regions. [ABSTRACT FROM AUTHOR]

The GaoFen-3 (GF-3) satellite is the first fully polarimetric synthetic aperture radar (SAR) satellite designed for civil use in China. The satellite operates in the C-band and has 12 imaging modes for various applications. Three fully polarimetric SAR (PolSAR) imaging modes are provided with a resolution of up to 8 m. Although polarimetric calibration (PolCAL) of the SAR system is periodically undertaken, there is still some residual distortion in the images. In order to assess the polarimetric accuracy of this satellite and improve the image quality, we analyzed the polarimetric distortion errors and performed a PolCAL experiment based on scattering properties and corner reflectors. The experiment indicates that the GF-3 images can meet the satellite’s polarimetric accuracy requirements, i.e., a channel imbalance of 0.5 dB in amplitude and ±10 degrees in phase and a crosstalk accuracy of -35 dB. However, some images still contain residual polarimetric distortion. The experiment also shows that the residual errors of the GF-3 standard images can be diminished after further PolCAL, with a channel imbalance of 0.26 dB in amplitude and ±0.2 degrees in phase and a crosstalk accuracy of -42 dB. [ABSTRACT FROM AUTHOR]

At present SAR polarimetric calibration algorithm are assumed to satisfy reciprocity from distributed targets. But not all distributed targets satisfy the principle of reciprocity. Aiming to solve this problem, this paper presents a method to calibration based on reciprocity judgment of distributed targets. According to the angle between the polarization scattering matrix and the reciprocal matrix of each pixel, we select pixels with small angle as the initial reciprocity calibration samples. Then, on the basis of the coherence of targets, some pixels are selected as the final calibration samples. CECT-38 X-band fully polarimetric data were completed by combining a typical calibration algorithm and selected distributed targets using the proposed method. Experiments show that this method, using distributed targets, can be well applied to SAR polarimetric calibration. [ABSTRACT FROM AUTHOR]

Time series analysis (TSA) based on multi-temporal polarimetric synthetic aperture radar (PolSAR) images can deeply mine the scattering characteristics of objects in different stages and improve the interpretation effect, or help to extract the range of surface changes. However, as far as classification is concerned, it is difficult to directly generate the classification map for a new temporal image, by the use of conventional TSA or change detection methods. Once some labeled samples exist in historical temporal images, semi-supervised domain adaptation (DA) is able to use historical label information to infer the categories of pixels in the new image, which is a potential solution to the above problem. In this paper, a novel semi-supervised DA algorithm is proposed, which inherits the merits of maximum margin criterion and principal component analysis in the DA learning scenario. Using a kernel mapping function established on the statistical distribution of PolSAR data, the proposed algorithm aims to find an optimal subspace for eliminating domain influence and keeping the key information of bi-temporal images. Experiments on both UAVSAR and Radarsat-2 multi-temporal datasets show that, superior classification results with the average accuracy of about 80% can be obtained by a simple classifier trained with historical labeled samples in the learned low- dimensional subspaces. [ABSTRACT FROM AUTHOR]

• Model-based polarimetric decomposition method for soil moisture estimation (SME). • Dihedral scattering component is neglected in bare soil and sparse vegetation areas. • SME results of C- and L-band full polarimetric data are analyzed. • SME accuracies of bare soil, sparse, and dense grassland are evaluated. Polarimetric synthetic aperture radar (PolSAR), as an advanced active sensor, can penetrate vegetation to detect ground information. The multimode observation data can provide more information to interpret different scattering mechanisms and have great application potential in soil moisture estimation (SME). In this paper, a modified method of soil moisture inversion from PolSAR data based on a two-component polarimetric decomposition model is introduced. The proposed method neglects the dihedral scattering component in the case of sparse vegetation cover and no-building areas, compensates the orientation angle by considering the influence of surface roughness and terrain slope, and calculates the dielectric constant with the hybrid X-Bragg/Fresnel model. Gaofen-3 (C-band) data from Ordos, Inner Mongolia, and Soil Moisture Experiment 2003 (SMEX03) airborne synthetic aperture radar (AIRSAR) (C- and L-band) data from Southern Oklahoma were applied in the experimental research. Furthermore, the performance and validity limits were assessed by comparing the retrieval results with in situ measurements and Soil Moisture Active Passive (SMAP) soil moisture products. The results reveal a root-mean-square error (RMSE) of 8.66% with an inversion rate of up to 61% when using the Gaofen-3 data from Ordos. For the Southern Oklahoma study area, the inversion RMSE of the AIRSAR C- and L-band data is 8.57% and 8.95%, respectively. The tendency of the inversion results is also consistent with the change trend of the site observations. In the bare soil and sparse vegetation covered areas, the retrieval error is relatively small, while in dense vegetation covered areas, soil moisture is underestimated in both the C- and L-band data, and the former is more underestimated than the latter. [ABSTRACT FROM AUTHOR]

A new approach in polarimetric synthetic aperture radar (PolSAR) speckle filtering is proposed in this article. The proposed method preserves both point targets and dominant scattering mechanisms. The point targets are detected based on the span image, and they are then neither filtered nor involved in the other pixels’ filtering. To achieve the protection of the dominant scattering mechanism of each pixel, only pixels of the same dominant scattering mechanism as the centre pixel are included in the selection of the homogeneous pixels. Both point targets not being filtered and fact that only pixels of the same dominant scattering mechanism are included in the selection of the homogeneous pixels, which greatly improves the filtering efficiency. A likelihood-ratio test statistic based on the PolSAR covariance matrices is applied to determine the homogeneous pixels. Finally, the speckle filtering is processed using the weighted minimum mean square error estimator on the homogeneous pixels. We demonstrate the obvious advantages of the proposed method over other algorithms in the preservation of point targets and dominant scattering mechanisms, speckle suppression, protection of detail information, and maintenance of polarization information, by the use of both simulated and real PolSAR data. [ABSTRACT FROM AUTHOR]

Automated medical image segmentation plays an important role in many clinical applications, which however is a very challenging task, due to complex background texture, lack of clear boundary and significant shape and texture variation between images. Many researchers proposed an encoder–decoder architecture with skip connections to combine low-level feature maps from the encoder path with high-level feature maps from the decoder path for automatically segmenting medical images. The skip connections have been shown to be effective in recovering fine-grained details of the target objects and may facilitate the gradient back-propagation. However, not all the feature maps transmitted by those connections contribute positively to the network performance. In this paper, to adaptively select useful information to pass through those skip connections, we propose a novel 3D network with self-supervised function, named selective information passing network. We evaluate our proposed model on the MICCAI Prostate MR Image Segmentation 2012 Grant Challenge dataset, TCIA Pancreas CT-82 and MICCAI 2017 Liver Tumor Segmentation Challenge dataset. The experimental results across these datasets show that our model achieved improved segmentation results and outperformed other state-of-the-art methods. The source code of this work is available at https://github.com/ahukui/SIPNet. [ABSTRACT FROM AUTHOR]

GaoFen-3 was the first Chinese civilian C-band synthetic aperture radar (SAR) satellite, launched in August 2016. The need for monitoring the satellite's image quality has been boosted by its widespread applications in various fields. The efficient and scientific assessment of the system's radiometric and polarimetric performance has been essential in its more than five years of service. The authors collected 90 images of the Inner Mongolia calibration site, 888 images of the Amazon rainforest, and 39,929 images of the Chinese mainland from 2017 to 2021. This was achieved whilst covering the leading imaging modes, such as the spotlight mode, stripmap mode, ultra-fine mode, wave imaging mode, etc. In this study, we derive a framework that incorporates the man-made corner reflectors (CRs) in Mongolia, the traditional Amazon rainforest datasets, and even the long-strip data in the Chinese mainland (known as CRAS) for the purposes of GaoFen-3 radiometric quality analysis and polarimetric validation over its five years of operation. Polarimetric calibration without recourse to the CRs is utilized to measure the polarimetric distortions regardless of the region, and thus requires a higher calibration accuracy for the GaoFen-3 polarimetric monitoring task. Consequently, the modified Quegan method is developed by relaxing the target azimuth symmetry constraint with the Amazon forest datasets. The experiments based on the CRAS demonstrate that the main radiometric characteristics could reach the international level, with an estimated noise-equivalent sigma zero of approximately −30 dB, a radiometric resolution that is better than 2.9 dB, and a single-imagery relative radiation accuracy that is better than 0.51 dB. For polarimetric validation, the modified Quegan method was utilized to measure the crosstalk for quad-pol products to ensure that it was than −40 dB. Meanwhile, non-negligible channel imbalance errors were found in the QPSII and WAV modes, and they were effectively well-calibrated with strip estimators to satisfy the system design. [ABSTRACT FROM AUTHOR]

Crops are vulnerable to strong winds, and the resulting lodging damage can have a great effect on the yield. We characterize lodged wheat and canola using polarimetric features derived from a series of polarimetric synthetic aperture radar data. Reflection asymmetry and reduced differential extinction are observed for lodged wheat, but not for canola, whose canopy structure has a high degree of randomness. The circular-pol correlation coefficient is explored as an indicator for the lodging damage of wheat. The results demonstrate that the capability of PolSAR in lodging damage monitoring is related to the canopy structure of crops. [ABSTRACT FROM PUBLISHER]

This article investigates the scattering characteristics of ridging patterns in agriculture by the use of C-band polarimetric synthetic aperture radar (PolSAR) images. The polarimetric signatures of periodic potato fields and row wheat in different directions are highlighted using a set of polarimetric parameters. Enhanced coherent scattering is observed when the alignment direction of the ridging patterns is perpendicular to the radar’s line of sight (LOS). The dominant backscattering mechanism of the ridging patterns is deduced by evaluating different polarimetric parameters. The increased copolarized backscattering coefficients and copolarized correlation coefficient, and the reduced entropy and polarimetric alpha angle, indicate a strong contribution of odd scattering to ridging patterns aligned perpendicular to the LOS. We also compare the dominant contributions to the backscattering of ridging patterns in different phenological stages. Although the canopy changes of potato and wheat with time are significant, the underlying periodic surface changes the dominant scattering mechanism of potato fields over all the phenological stages, and the wheat aligned parallel with the flight direction of radar still has relatively high coherent scattering in the different vegetation development stages. The variability analyses undertake in this study allow a more detailed documentation of the physical scattering process of the ridging patterns in agriculture, and will improve the applicability of synthetic aperture radar images in agriculture. [ABSTRACT FROM PUBLISHER]

Airborne SAR is an important data source for crop mapping and has important applications in agricultural monitoring and food safety. However, the incidence-angle effects of airborne SAR imagery decrease the crop mapping accuracy. An active pairwise constraint learning method (APCL) is proposed for constrained time-series clustering to address this problem. APCL constructs two types of instance-level pairwise constraints based on the incidence angles of the samples and a non-iterative batch-mode active selection scheme: the must-link constraint, which links two objects of the same crop type with large differences in backscattering coefficients and the shapes of time-series curves; the cannot-link constraint, which links two objects of different crop types with only small differences in the values of backscattering coefficients. Experiments were conducted using 12 time-series images with incidence angles ranging from 21.2° to 64.3°, and the experimental results prove the effectiveness of APCL in improving crop mapping accuracy. More specifically, when using dynamic time warping (DTW) as the similarity measure, the kappa coefficient obtained by APCL was increased by 9.5%, 8.7%, and 5.2% compared to the results of the three other methods. It provides a new solution for reducing the incidence-angle effects in the crop mapping of airborne SAR time-series images. [ABSTRACT FROM AUTHOR]

Synthetic aperture radar (SAR) has often been used in earthquake damage assessment due to its extreme versatility and almost all-weather, day-and-night capability. In this article, we demonstrate the potential to use only post-event, high-resolution airborne polarimetric SAR (PolSAR) imagery to estimate the damage level at the block scale. Intact buildings with large orientation angles have a similar scattering mechanism  to collapsed buildings; they are all volume-scattering dominant and reflection asymmetric, which seriously hampers the process of damage assessment. In this article, we propose a new damage assessment method combining polarimetric and spatial texture information to eliminate this deficiency. In the proposed method, the normalized circular-pol correlation coefficient is used first to identify intact buildings aligned parallel with the flight direction of the radar. The ‘homogeneity’ feature of the grey-level co-occurrence matrix (GLCM) is then introduced to distinguish building patches with large orientation angles from the severely damaged class. Furthermore, a new damage assessment index is also introduced to handle the assessment at the level of the block scale. To demonstrate the effectiveness of the proposed approach, the high-resolution airborne PolSAR imagery acquired after the earthquake that hit Yushu County, Qinghai Province of China, is investigated. By comparison with the damage validation map, the results confirm the validity of the proposed method and the advantage of further improving the assessment accuracy without external ancillary optical or SAR data. [ABSTRACT FROM PUBLISHER]

The deep convolutional neural network (CNN) has been extensively applied to polarimetric synthetic radar (PolSAR) imagery classification. However, its success is greatly dependent on numerous labeled samples for revealing and modeling the characteristics of different targets, thus remaining a challenge in maintaining high accuracy in limited sample cases. To address this issue, a deep reinforcement learning (RL)-based PolSAR image classification framework, named deep Q-fully CNN (DQFCN), is proposed in this article. In this framework, two ways are adopted to boost the classification performance while reducing training samples. On the information utilization hand, the spatial neighboring information and polarimetric decomposition information of PolSAR data are both extracted to enrich the feature representation of the sample. Meanwhile, the 3-D CNN architecture is adopted to learn the spatial-polarimetric jointed characteristics simultaneously. On the model learning hand, two RL learning strategies are employed to promote classification performance. The first one is learning from scratch, which does not use any label information as prior knowledge but learns from its self-generated experience. Learning from pretraining is the second strategy in which the networks are sequentially trained from labeled samples and experience data to reduce the time cost. As far as we know, it is the first time that an RL-based fully CNN has been proposed for PolSAR image classification. Experiments on three benchmark datasets prove the effectiveness of the proposed framework, suggesting that the two adopted strategies achieve boosted performance in all experiments, particularly in a limited sample size. [ABSTRACT FROM AUTHOR]

Hyperspectral image (HSI) clustering is extremely challenging because of the complexity of the image structure. Recently, the subspace clustering algorithms have achieved competitive performance for HSIs. However, these methods generally are computationally complex and time-and-memory-consuming, given their reliance on large-scale adjacency matrix learning and graph segmentation, which limits their application to large HSIs and reduces their attractiveness in real applications. In this article, in view of this, two novel sparsity-based clustering algorithms are proposed for large HSIs, named sparse coding-based clustering (SCC) and joint SCC (JSCC). To the best of our knowledge, we are the first to use the sparse representation recovery residual to cluster HSIs. Based on a structured dictionary constructed by $k$ -means and $k$ -nearest neighbor (KNN), an SCC model is constructed to cluster HSIs according to the recovery residual minimization criterion. By dealing with a pixel-wise sparse recovery problem instead of the large-scale graph optimization problem of the whole image, the computational complexity and the time-and-memory cost are reduced to a large degree, which makes sense for practical applications. Then, by introducing the super-pixel neighborhood, a JSCC model is constructed to better explore the interpixel correlation of HSIs and further improve the clustering performance. The proposed algorithms were verified on three widely used HSIs. All the three experiments confirm the effectiveness of the proposed algorithms, which can be considered as competitive tools for use with large HSIs. [ABSTRACT FROM AUTHOR]

Clustering is a common method for hyperspectral image (HSI) interpretation in the case of no labeled samples. Many subspace clustering methods have now been proposed for HSIs and have obtained remarkable success. However, because of the prohibitively large computational complexity induced by the self-dictionary representation, these methods suffer from the scalability issue and are ineffective for large HSIs. In this article, to address this issue, we focus on a scalable subspace clustering scheme and introduce the recently developed sketched subspace clustering (sketched-SC) model to HSI. The sketched-SC model is computationally inexpensive and is suitable for the large HSI clustering task as it constructs a compact yet expressive dictionary. However, several problems degrade the performance of sketched-SC, i.e., the inadequate mining of the structural information and no consideration of spatial information. In view of this, a novel scalable nonlocal means regularized sketched reweighted sparse and low-rank (NL-SSLR) SC algorithm is proposed for use with large HSIs. On the one hand, the SSLR representation model is constructed to explore the underlying local and global structural information of the HSIs at the same time. On the other hand, the nonlocal means regularization is used to fully explore the spatial correlation information and better account for the self-similarity of HSIs, to further boost the clustering performance. The experimental results obtained on two well-known hyperspectral data sets corroborate the superiority of the proposed algorithm over the other state-of-the-art HSI clustering methods. [ABSTRACT FROM AUTHOR]

Additive noise results from the thermal noise of the radar receiver or antenna, and often has an adverse effect on the subsequent applications. To weaken the influence of additive noise, it is crucial to know the actual additive noise level. However, the system noise level is not always provided in some single- or full-polarimetric synthetic aperture radar (PolSAR) products. As one of the typical low backscattering objects (LBOs) in PolSAR images, shadow occurs as soon as the depression angle of the synthetic aperture radar (SAR) system reaches a more value than the slope away from the radar illumination, and thus provides a feasible way to measure additive noise. This paper proposes a framework to automatically extract shadow regions by a trained model using the bag of words (BoW) model with data from different scenes. The additive noise can then be estimated across a large area based on the extracted shadow. The experiments based on single- and full-polarimetric Radarsat-2 data suggest that the shadow-based framework is an effective way to estimate additive noise. [ABSTRACT FROM AUTHOR]

This paper presents a spherically invariant random vector (SIRV)-based dual-domain filter for polarimetric synthetic aperture radar (PolSAR) speckle suppression. The SIRV model is a simple clutter decomposition model designed for heterogeneous scenes that decomposes the clutter into two independent domains: the texture domain and the polarimetric domain (also known as the speckle domain). The dual-domain filter takes full advantage of the SIRV model to decompose the task of PolSAR speckle suppression into polarimetric domain filtering and texture domain filtering. The polarimetric domain filtering involves estimating a stable state of the normalized coherency matrix with similar samples via fixed-point iteration. For this purpose, the nonlocal patch matching distance measure and the cutoff threshold in the SIRV model case are defined to select similar samples. The texture domain filtering involves reconstructing a sparse texture image without the effect of speckle. For this purpose, patch ordering-based SAR image despeckling via transform-domain filtering (SAR-POTDF), which is based on simultaneous sparse coding (SSC), is applied for the texture filtering. After the dual-domain filtering, a speckle-free PolSAR image can be reconstructed by the product of the texture and the normalized coherency matrix. The effectiveness and robustness of the proposed method was demonstrated by experiments undertaken with CETC-38 X-band, DLR F-SAR S-band, and IECAS C-band high-resolution PolSAR images. The DLR E-SAR L-band medium-resolution data were also used for comparison. The results showed that the dual-domain filtering is effective for the speckle suppression of high-resolution PolSAR images with heterogeneous and detailed scenes. [ABSTRACT FROM AUTHOR]

The combination of transfer learning and remote sensing image processing technology can effectively improve the automation level of image information extraction from a remote sensing time series. However, in the processing of polarimetric synthetic aperture radar (PolSAR) time-series images, the existing transfer learning methods often cannot make full use of the time-series information of the images, relying too much on the labeled samples in the target domain. Furthermore, the speckle noise inherent in synthetic aperture radar (SAR) imagery aggravates the difficulty of the manual selection of labeled samples, so these methods have difficulty in meeting the processing requirements of large data volumes and high efficiency. In lieu of these problems and the spatio-temporal relational knowledge of objects in time-series images, this paper introduces the theory of time-series clustering and proposes a new three-phase time-series clustering algorithm. Due to the full use of the inherent characteristics of the PolSAR images, this algorithm can accurately transfer the labels of the source domain samples to those samples that have not changed in the whole time series without relying on the target domain labeled samples, so as to realize transductive sample label transfer for PolSAR time-series images. Experiments were carried out using three different sets of PolSAR time-series images and the proposed method was compared with two of the existing methods. The experimental results showed that the transfer precision of the proposed method reaches a high level with different data and different objects and it performs significantly better than the existing methods. With strong reliability and practicability, the proposed method can provide a new solution for the rapid information extraction of remote sensing image time series. [ABSTRACT FROM AUTHOR]

Band selection is an effective approach to mitigate the “Hughes phenomenon” of hyperspectral image (HSI) classification. Recently, sparse representation (SR) theory has been successfully introduced to HSI band selection, and many SR-based methods have been developed and shown great potential and superiority. However, due to the inherent limitations of the SR scheme, i.e., individually representing each band with only a few other bands from the same subspace, the SR-based methods cannot effectively capture the global structures of the data, which limit the band selection performance. In this paper, to overcome this obstacle, the novel Laplacian-regularized low-rank subspace clustering (LLRSC) algorithm is proposed for HSI band selection. On the one hand, the low-rank subspace clustering model is introduced to capture the global structure information for the learned representation coefficient matrix and deal with the HSI band selection task in the clustering framework. On the other hand, considering the high correlation between adjacent bands, 1-D Laplacian regularization is utilized to incorporate the neighboring band information and further reduce the representation bias. Lastly, an eigenvalue analysis algorithm based on band mutation information is utilized to estimate the appropriate size of the band subset. The experimental results indicate that the proposed LLRSC algorithm outperforms the other state-of-the-art methods and achieves a very competitive band selection performance for HSIs. [ABSTRACT FROM AUTHOR]

This paper presents a global weighted least-squares (GWLS) optimization framework for polarimetric synthetic aperture radar (PolSAR) despeckling. GWLS is simpler than other optimization methods because it does not lead to complex optimization and iterative convergence problems. Solving the PolSAR despeckling problem based on GWLS is equivalent to solving nine sparse linear systems. First, the guidance image is constructed by the span image of the PolSAR data to calculate the five-point spatially inhomogeneous Laplacian matrix. Next, the weighted sum of the Laplacian matrix and an identity matrix is used to construct a coefficient matrix for the nine linear systems. Finally, each speckle-free channel of PolSAR data is reconstructed equally and globally by solving the linear systems with the same coefficient matrix. Filtering each element of the coherency matrix equally preserves the scattering property inherent in PolSAR data. The performance of the GWLS-based method is demonstrated by both simulated and real PolSAR data. Refined Lee filter, intensity-driven adaptive-neighborhood, improved sigma filter, and nonlocal pretest filter are used in qualitative and quantitative comparison. The experiments show that the proposed method can reach a good tradeoff between noise suppressing and detail preservation and has relatively high processing efficiency. [ABSTRACT FROM AUTHOR]

Abstract Cloud and cloud shadow detection is a necessary preprocessing step for optical remote sensing applications because of the huge negative influence cloud and cloud shadow can have on data analysis. However, most of the existing cloud/shadow detection methods are designed based on specific band configurations of certain sensors, and their working mechanisms are relatively complex and computationally complicated, which limits their application. In view of this, in this paper, a unified cloud/shadow detection algorithm based on spectral indices (CSD-SI) is proposed for most of the widely used multi/hyperspectral optical remote sensing sensors with both visible and infrared spectral channels. On the one hand, the cloud index (CI) and cloud shadow index (CSI) are proposed to indicate the potential clouds and cloud shadows based on their physical reflective characteristics. In addition, considering the spatial coexistence of cloud and cloud shadow, a spatial matching strategy is utilized to remove the pseudo cloud shadows. The effectiveness of the proposed CSD-SI algorithm is demonstrated on eight different types of widely used multi/hyperspectral optical sensors, with different spectral and spatial resolution levels. Overall, in the experiments undertaken in this study, CSD-SI achieved a mean overall accuracy of 98.52% for cloud, with a mean producer’s accuracy of 93.13% and a mean user’s accuracy of 98.13%. For cloud shadow, CSD-SI achieved a means producer’s accuracy of 84.33% and a mean user’s accuracy of 89.12%. The experimental results show that the proposed CSD-SI method based on spectral indices can obtain a comparable cloud/shadow detection performance to that of the other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Most of the traditional supervised classification methods using full-polarimetric synthetic aperture radar (PolSAR) imagery are dependent on sufficient training samples, whereas the results of pixel-based supervised classification methods show a high false alarm rate due to the influence of speckle noise. In this paper, to solve these problems, an object-based supervised classification method with an active learning (AL) method and random forest (RF) classifier is presented, which can enhance the classification performance for PolSAR imagery. The first step of the proposed method is used to reduce the influence of speckle noise through the generalized statistical region merging (GSRM) algorithm. A reliable training set is then selected from the different polarimetric features of the PolSAR imagery by the AL method. Finally, the RF classifier is applied to identify the different types of land cover in the three PolSAR images acquired by different sensors. The experimental results demonstrate that the proposed method can not only better suppress the influence of speckle noise, but can also significantly improve the overall accuracy and Kappa coefficient of the classification results, when compared with the traditional supervised classification methods. [ABSTRACT FROM AUTHOR]

A novel segmentation algorithm for polarimetric synthetic aperture radar (PolSAR) images is proposed in this paper. The method is composed of two essential components: a merging order and a merging predicate. The similarity measured by the complex-kind Hotelling–Lawley trace (HLT) statistic is used to decide the merging order. The merging predicate is determined by the scattering characteristics and the revised Wishart distance between adjacent pixels, which can greatly improve the performance in speckle suppression and detail preservation. A postprocessing step is applied to obtain a satisfactory result after the merging operation. The decomposition and merging processes are iteratively executed until the termination criterion is met. The superiority of the proposed method was verified with experiments on two RADARSAT-2 PolSAR images and a Gaofen-3 PolSAR image, which demonstrated that the proposed method can obtain more accurate segmentation results and shows a better performance in speckle suppression and detail preservation than the other algorithms. [ABSTRACT FROM AUTHOR]

Clustering for hyperspectral images (HSIs) is a very challenging task due to its inherent complexity. In this paper, we propose a novel spectral–spatial sparse subspace clustering (\textS^4\textC) algorithm for hyperspectral remote sensing images. First, by treating each kind of land-cover class as a subspace, we introduce the sparse subspace clustering (SSC) algorithm to HSIs. Then, considering the spectral and spatial properties of HSIs, the high spectral correlation and rich spatial information of the HSIs are taken into consideration in the SSC model to obtain a more accurate coefficient matrix, which is used to build the adjacent matrix. Finally, spectral clustering is applied to the adjacent matrix to obtain the final clustering result. Several experiments were conducted to illustrate the performance of the proposed \textS^4\textC algorithm. [ABSTRACT FROM AUTHOR]

Abstract: In this paper, the linear discriminative Laplacian eigenmaps (LDLE) dimensionality reduction (DR) algorithm is introduced to C-band polarimetric synthetic aperture radar (PolSAR) agricultural classification. A collection of homogenous areas of the same crop class usually presents physical parameter variation, such as the biomass and soil moisture. Furthermore, the local incidence angle also impacts a lot on the same crop category when the vegetation layer is penetrable with C-band radar. We name this phenomenon as the “observed variation of the same category” (OVSC). The most common PolSAR features, e.g., the Freeman–Durden and Cloude–Pottier decompositions, show an inadequate performance with OVSC. In our research, more than 40 coherent and incoherent PolSAR decomposition models are stacked into the high-dimensionality feature cube to describe the various physical parameters. The LDLE algorithm is then performed on the observed feature cube, with the aim of simultaneously pushing the local samples of the same category closer to each other, as well as maximizing the distance between local samples of different categories in the learnt subspace. Finally, the classification result is obtained by nearest neighbor (NN) or Wishart classification in the reduced feature space. In the simulation experiment, eight crop blocks are picked to generate a test patch from the 1991 Airborne Synthetic Aperture Radar (AIRSAR) C-band fully polarimetric data from of Flevoland test site. Locality preserving projections (LPP) and principal component analysis (PCA) are then utilized to evaluate the DR results of the proposed method. The classification results show that LDLE can distinguish the influence of the physical parameters and achieve a 99% overall accuracy, which is better than LPP (97%), PCA (88%), NN (89%), and Wishart (88%). In the real data experiment, the Chinese Hailaer nationalized farm RadarSat2 PolSAR test set is used, and the classification accuracy is around 94%, which is again better than LPP (90%), PCA (88%), NN (89%), and Wishart (85%). Both experiments suggest that the LDLE algorithm is an effective way of relieving the OVSC phenomenon. [Copyright &y& Elsevier]

Image super-resolution (SR) reconstruction has been a hot research topic in recent years. This technique allows the recovery of a high-resolution (HR) image from several low-resolution (LR) images that are noisy, blurred and down-sampled. Among the available reconstruction frameworks, the maximum a posteriori (MAP) model is widely used. In this model, the regularization parameter plays an important role. If the parameter is too small, the noise will not be effectively restrained; conversely, the reconstruction result will become blurry. Therefore, how to adaptively select the optimal regularization parameter has been widely discussed. In this paper, we propose an adaptive MAP reconstruction method based upon a U-curve. To determine the regularization parameter, a U-curve function is first constructed using the data fidelity term and prior term, and then the left maximum curvature point of the curve is regarded as the optimal parameter. The proposed algorithm is tested on both simulated and actual data. Experimental results show the effectiveness and robustness of this method, both in its visual effects and in quantitative terms. [ABSTRACT FROM AUTHOR]

In mountainous areas, irregular terrain significantly affects spatial variations of climatic variables and the reflectance of pixels in remote sensing imagery. Consequently, the variations may affect the estimation of net primary productivity (NPP). The light-use efficiency (LUE) model is used to analyse topographic influence on NPP by evaluating topographic effects on primary input data to the model, including both Normalized Difference Vegetation Index (NDVI) and climatic data. A typical green coniferous forest in Yoshino Mountain, Japan, was employed as the study area. The results show that the average NPP is significantly increased after removing topographic influences on NDVI; the average NPP has a relatively minimal change when only topographic effects on climatic data are considered. When both topographic effects on NDVI and climatic data are considered, the average NPP is 1.80 kg m-2 yr-1, which is very similar to the ground measurement result of 1.74 kg m-2 yr-1. [ABSTRACT FROM AUTHOR]

Abstract: In many surveillance video applications, it is of interest to recognize a region of interest (ROI), which often occupies a small portion of a low-resolution, noisy video. This paper proposes an edge-preserving maximum a posteriori (MAP) estimation based super-resolution algorithm using a weighted directional Markov image prior model for a ROI from more than one low-resolution surveillance image. Conjugate gradient (CG) optimization based on standard operations on images is then developed to improve the computational efficiency of the algorithm. The proposed algorithm is tested on different series of surveillance images. The experimental results indicate that the proposed algorithm has considerable effectiveness in terms of both objective measurements and visual evaluation. [Copyright &y& Elsevier]

Marine ship detection by synthetic aperture radar (SAR) is an important remote sensing technology. The rapid development of big data and artificial intelligence technology has facilitated the wide use of deep learning methods in SAR imagery for ship detection. Although deep learning can achieve a much better detection performance than traditional methods, it is difficult to achieve satisfying performance for small-sized ships nearshore due to the weak scattering caused by their material and simple structure. Another difficulty is that a huge amount of data needs to be manually labeled to obtain a reliable CNN model. Manual labeling each datum not only takes too much time but also requires a high degree of professional knowledge. In addition, the land and island with high backscattering often cause high false alarms for ship detection in the nearshore area. In this study, a novel method based on candidate target detection, boundary box optimization, and convolutional neural network (CNN) embedded with active learning strategy is proposed to improve the accuracy and efficiency of ship detection in nearshore areas. The candidate target detection results are obtained by global threshold segmentation. Then, the strategy of boundary box optimization is defined and applied to reduce the noise and false alarms caused by island and land targets as well as by sidelobe interference. Finally, a lightweight CNN embedded with active learning scheme is used to classify the ships using only a small labeled training set. Experimental results show that the performance of the proposed method for small-sized ship detection can achieve 97.78% accuracy and 0.96 F1-score with Sentinel-1 images in complex nearshore areas. [ABSTRACT FROM AUTHOR]

Surface soil moisture (SM) retrieval over agricultural areas from polarimetric synthetic aperture radar (PolSAR) has long been restricted by vegetation attenuation, simplified polarimetric scattering modelling, and limited SAR measurements. This study proposes a modified polarimetric decomposition framework to retrieve SM from multi-incidence and multitemporal PolSAR observations. The framework is constructed by combining the X-Bragg model, the extended double Fresnel scattering model and the generalised volume scattering model (GVSM). Compared with traditional decomposition models, the proposed framework considers the depolarisation of dihedral scattering and the diverse vegetation contribution. Under the assumption that SM is invariant for the PolSAR observations at two different incidence angles and that vegetation scattering does not change between two consecutive measurements, analytical parameter solutions, including the dielectric constant of soil and crop stem, can be obtained by solving multivariable nonlinear equations. The proposed framework is applied to the time series of L-band uninhabited aerial vehicle synthetic aperture radar data acquired during the Soil Moisture Active Passive Validation Experiment in 2012. In this study, we assess retrieval performance by comparing the inversion results with in-situ measurements over bean, canola, corn, soybean, wheat and winter wheat areas and comparing the different performance of SM retrieval between the GVSM and Yamaguchi volume scattering models. Given that SM estimation is inherently influenced by crop phenology and empirical parameters which are introduced in the scattering models, we also investigate the influence of surface depolarisation angle and co-pol phase difference on SM estimation. Results show that the proposed retrieval framework provides an inversion accuracy of RMSE<6.0% and a correlation of R ≥0.6 with an inversion rate larger than 90%. Over wheat and winter wheat fields, a correlation of 0.8 between SM estimates and measurements is observed when the surface scattering is dominant. Specifically, stem permittivity, which is retrieved synchronously with SM also shows a linear relationship with crop biomass and plant water content over bean, corn, soybean and wheat fields. We also find that a priori knowledge of surface depolarisation angle, co-pol phase difference and adaptive volume scattering could help to improve the performance of the proposed SM retrieval framework. However, the GVSM model is still not fully adaptive because the co-pol power ratio of volume scattering is potentially influenced by ground scattering. • A new framework for soil moisture (SM) retrieval from multiple PolSAR observations. • The soil and crop stem permittivity are derived from the proposed framework. • SM estimates over selected crop fields show an accuracy of RMSE≤6.0%. • The surface depolarization angle influences the SM inversion performance. • The optimal selection of co-pol phase difference improves the SM estimation. [ABSTRACT FROM AUTHOR]

Abstract: The mixed pixel is a common problem in remote sensing classification. Even though the composition of these pixels for different classes can be estimated with a pixel un-mixing model, the output provides no indication of how such classes are distributed spatially within these pixels. Sub-pixel mapping is a technique designed to use the output information with the assumption of spatial dependence to obtain a sharpened image. Pixels are divided into sub-pixels, representing the land cover class fractions. This paper proposes a new algorithm based on a back-propagation (BP) network combined with an observation model. This method provides an effective method of obtaining the sub-pixel mapping result and can provide an approximation of the reference classification image. With the upscale factor, the model was tested on both a simple artificial image and a remote sensing image, and the results confirm that the proposed mapping algorithm has better performance than the original BPNN model. [Copyright &y& Elsevier]

Synthetic aperture radar (SAR) is a significant application in maritime monitoring, which can provide SAR data throughout the day and in all weather conditions. With the development of artificial intelligence and big data technologies, the data-driven convolutional neural network (CNN) has become widely used in ship detection. However, the accuracy, feature visualization, and analysis of ship detection need to be improved further, when the CNN method is used. In this letter, we propose a two-stage ship detection for land-contained sea area without a traditional sea-land segmentation process. First, to decrease the possibly existing false alarms from the island, an island filter is used as the first step, and then threshold segmentation is used to quickly perform candidate detection. Second, a two-layer lightweight CNN model-based classifier is built to separate false alarms from the ship object. Finally, we discuss the CNN interpretation and visualize in detail when the ship is predicted in vertical–horizontal (VH) and vertical–vertical (VV) polarization. Experiments demonstrate that the proposed method can reach an accuracy of 99.4% and an F1 score of 0.99 based on the Sentinel-1 images for a ship with a size of less than 32 × 32. [ABSTRACT FROM AUTHOR]

The information extraction of polarimetric synthetic aperture radar (PolSAR) images typically requires a great number of training samples; however, the training samples from historical images are less reusable due to the distribution differences. Consequently, there is a significant manual cost to collecting training samples when processing new images. In this paper, to address this problem, we propose a novel active transfer learning method, which combines active learning and the deep forest model to perform transfer learning. The main idea of the proposed method is to gradually improve the performance of the model in target domain tasks with the increase of the levels of the cascade structure. More specifically, in the growing stage, a new active learning strategy is used to iteratively add the most informative target domain samples to the training set, and the augmented features generated by the representation learning capability of the deep forest model are used to improve the cross-domain representational capabilities of the feature space. In the filtering stage, an effective stopping criterion is used to adaptively control the complexity of the model, and two filtering strategies are used to accelerate the convergence of the model. We conducted experiments using three sets of PolSAR images, and the results were compared with those of four existing transfer learning algorithms. Overall, the experimental results fully demonstrated the effectiveness and robustness of the proposed method. [ABSTRACT FROM AUTHOR]

Unsupervised change detection approaches, which are relatively straightforward and easy to implement and interpret, and which require no human intervention, are widely used in change detection. Polarimetric synthetic aperture radar (PolSAR), which has an all-weather response capability with increased polarimetric information, is a key tool for change detection. However, for PolSAR data, inadequate evaluation of the difference image (DI) map makes the threshold-based algorithms incompatible with the true distribution model, which causes the change detection results to be ineffective and inaccurate. In this paper, to solve these problems, we focus on the generation of the DI map and the selection of the optimal threshold. An omnibus test statistic is used to generate the DI map from multi-temporal PolSAR images, and an improved Kittler and Illingworth algorithm based on either Weibull or gamma distribution is used to obtain the optimal threshold for generating the change detection map. Multi-temporal PolSAR data obtained by the Radarsat-2 sensor over Wuhan in China are used to verify the efficiency of the proposed method. The experimental results using our approach obtained the best performance in East Lake and Yanxi Lake regions with false alarm rates of 1.59% and 1.80%, total errors of 2.73% and 4.33%, overall accuracy of 97.27% and 95.67%, and Kappa coefficients of 0.6486 and 0.6275, respectively. Our results demonstrated that the proposed method is more suitable than the other compared methods for multi-temporal PolSAR data, and it can obtain both effective and accurate results. [ABSTRACT FROM AUTHOR]