Search

The natural terrain (e.g., farm and forest) in temperate zones changes dramatically between seasons due to distinct temperatures and precipitation variations from summer to winter. Moreover, built-up areas vary little in this short period. Therefore, extracting built-up areas via change detection on polarimetric synthetic aperture radar (PolSAR) images is feasible. A common type of PolSAR change detection method is based on hypothesis testing theory. However, in these methods, pixels are selected as the processing units; as a result, these models are computationally complex and poorly maintain the boundaries of built-up areas. In this paper, we innovatively introduce superpixels into the hypothesis test theory and propose a superpixelwise PolSAR change detection method for built-up area extraction. First, we oversegment the PolSAR images into a set of superpixels and derive the probability density function (PDF) of a superpixel's reflectivity on a PolSAR image. Based on this distribution, we present a superpixelwise likelihood-ratio test (LRT) statistic to measure the similarity of two superpixelwise covariance matrices for unsupervised change detection. When actually computing the superpixelwise LRT, the large variation in the areas of the superpixels makes the likelihood functions very complex and estimating the parameters difficult. We further simplify the calculation of the LRT statistic and apply it to built-up area extraction. Compared to the state-of-the-art built-up area extraction methods, our approach provides the best results with overall accuracy values of 91.41%, 92.71%, 93.67% and 93.91% for the four studied areas respectively. In addition, the computational complexity of our method is assessed, and the run time (seconds) of the proposed method in the four study cases is 11.14, 6.32, 5.31, and 4.88, respectively, superior to the values of 66.12, 36.26, 33.65, and 29.67 for DRT, respectively. Code and datasets: https://github.com/SunXJ7/Sentinel-1-Datasets-for-Built-up-Area-Extraction. [ABSTRACT FROM AUTHOR]

Due to the high mobility and strong concealment characteristics of synthetic aperture radar (SAR) targets, the corresponding SAR datasets exhibit few-shot data properties, and there is a significant lack of research on few-shot target detection methods in the SAR domain. Furthermore, this study is subject to the following limitations: the scarcity of SAR data and significant sample variations make it difficult to control class centers using existing methods, and the learned models tend to be biased towards base classes while easily confusing novel classes with base classes. These limitations hinder the generalization of knowledge from base classes when detecting novel class targets. In this work, we propose a novel few-shot SAR target detection method based on Gaussian meta-feature balanced aggregation (GMFBA), which is based on meta-learning. Specifically, we first propose two novel feature aggregation methods with Gaussian metrics, namely Gaussian projection distribution metric (GPDM) and Gaussian kernel mean embedding metric (GKMEM). By estimating class distribution with variational autoencoders to replace traditional class prototypes, we sample from robust distributions and measure projection Wasserstein distance and Gaussian kernel mean embedding distance with prior distributions, obtaining the best robust support features under the optimal measurement results. Then, based on GPDM and GKMEM, we propose a novel balanced inter-class uncorrelated aggregation (BICUA) method, which extracts support features of each class according to the proportion of samples and aggregates them with query features in a balanced manner, promoting feature representation between different classes and ensuring no interference between features to significantly reduce confusion between base classes and novel classes. Specifically, GMFBA outperforms the state-of-the-art method G-FSOD significantly in all settings, achieving state-of-the-art performance. In contrast, the novel class detection performance of GMFBA has shown an average improvement of 8.56% on split1 and split2 of the SRSDD-v1.0 dataset, and an average improvement of 1.41% on split1 and split2 of the MSAR-1.0 dataset. The code is available at https://github.com/Caltech-Z/GMFBA. [ABSTRACT FROM AUTHOR]

Deep learning-based methods have demonstrated exceptional performance in the field of synthetic aperture radar automatic target recognition (SAR ATR). However, obtaining a sufficient number of labeled SAR images remains a significant challenge that can negatively affect the performance of these methods. This is because most deep learning models use the entire target image as input. However, but research has shown that with limited training data, the model may not be able to capture discriminative regions of the image. Instead, they might focus on more useless even harmful image regions for recognition, leading to poor recognition results. In this study, we propose a novel SAR ATR framework that addresses the limitation of limited training data. The proposed framework primarily comprises a global assisted branch, locally enhanced branch, feature capture module, and feature discrimination module. The global-assisted branch conducts an initial recognition and provides a loss based on the entire SAR image during each training epoch and the feature capture module automatically segments and captures crucial image regions for current recognition, which we refer to as the "golden key" of the image. The local enhanced branch then performs another recognition and provides another loss function based on the image parts. Instead of updating the model with two basic recognition losses to roughly search for and capture crucial image parts, a feature discrimination module is proposed to combine the global and local branches in a subtle manner to improve local feature separability or compactness for similar inter-class or dissimilar inner-class sample pairs in global features. This adaptively forced the model to capture more crucial image parts and extract more effective features. Experimental results and comparisons of the MSTAR and OpenSARship datasets indicated that the proposed method achieves superior recognition performance compared to existing methods. The effectiveness of our method was further demonstrated through the visualization of the golden key of the testing images and the recognition performance in ablation experiments. We will release our codes and more experimental results at https://github.com/cwwangSARATR/SARATR_FeaCapture_Discrimination. [Display omitted] [ABSTRACT FROM AUTHOR]

Optical and synthetic aperture radar (SAR) images, two standard Earth observation tools, can reflect the characteristics of the surface from different perspectives and provide complementary information for land use classification. However, because they belong to different modes and express land objects differently, it is challenging to effectively fuse and use them to perform a pixel-wise classification. Current methods only focus on the local receptive field to fuse deep features in a single dimension, which is too simple to fully exploit the correlation between different modes. Moreover, the appearance disparities between each modality may induce semantic misalignment and disrupt the conditions of features' fusion. To overcome the above problems, we introduce a spatial-aware circular module to generate a cross-modality receptive field and globally enhance the interaction between each pixel in the spatial dimension. Additionally, we recalibrate the features in the channel dimension to selectively refine and retain the essential things during the process, which can further achieve feature refinement. To reduce the impact of modal appearance disparities, we transform their high-level features into a common latent space and align their distributions to correlate the complementary cues hidden in each modality. The experimental results for the WHU-OPT-SAR dataset show that our method performed better than other state-of-the-art methods, with a mean intersection over union (mIoU) of 58.5% and an overall accuracy (OA) of 84.2%. Furthermore, the method obtained competitive results in Ezhou and Panjin, China. The results demonstrate our method's applicability. [ABSTRACT FROM AUTHOR]

A massive landslide often causes long-lasting instability dynamics that need to be analyzed in detail for risk management and mitigation. Multiple satellite remote sensing observations, in-situ measurements, and geophysical approaches have been jointly implemented to monitor and interpret the life cycle of landslides and their failure mechanisms from various perspectives. In this work, we propose a framework where satellite optical and synthetic aperture radar (SAR) remote sensing techniques are combined with feature extractions using independent component analysis (ICA) and a mathematical relaxation model to assess the complete four-dimensional (4D) spatiotemporal patterns of post-failure slope evolution. The large, deep-seated Aniangzhai landslide in Southwest China that occurred on 17 June 2020 is comprehensively analyzed and characterized for its post-failure mechanism. Time series of Planet high-resolution optical images are first explored to derive the large horizontal motions for the first six months after the failure. Spatiotemporal dynamics of line-of-sight (LOS) displacement in the landslide body are then derived between November 2020 and February 2022 by combining 40 TerraSAR-X (TSX) High-resolution Spotlight (HS) images and 76 medium-resolution Sentinel-1 (S1) SAR datasets using Multi-temporal InSAR (MTI) method. The InSAR-derived results are subsequently analyzed with ICA to find common deformation components of points between optical and MTI results, indicating the same temporal evolution in the deformation pattern. Finally, the complete 4D deformation field for the whole post-failure period is modeled using a decaying exponential model representing stress relaxation after the failure by integrating multiple remote sensing datasets. Cross-correlation analysis of Planet imagery shows a decaying exponential pattern of post-failure displacements with an approximately 94% reduction in the deformation rate after six months with respect to the co-failure event. MTI analysis suggests a maximum LOS displacement rate of approximately 30 cm/year over the main failure body from November 2020 to February 2022; while the high-resolution TSX datasets show irreplaceable advantages in choosing the number of measurement points in MTI analysis with the number of measurement points being five times larger than those obtained by S1 datasets. The ICA analysis reveals three main types of kinematic patterns in the temporal evolution of post-failure deformation in MTI results, the dominant one being an exponential declining pattern similar to the results from Planet observations. Integrated 4D deformation modeling suggests that the most significant post-failure displacement mainly occurred toward the west, amounting to 28 m during the entire post-failure acquisitions from June 2020 until February 2022. Additionally, maximum displacements of 17 m and 19 m occurred in this period toward the north and downward, respectively. [Display omitted] • Monitor Aniangzhai landslide integrating multi-sensor remote sensing data • Derive 4D post-failure slope instability dynamics • Implement ICA to analyze spatiotemporal characteristics of slope deformation • Propose a relaxation model to predict post-failure deformation [ABSTRACT FROM AUTHOR]

This paper addresses the unsupervised classification problem for multilook polarimetric synthetic aperture radar (PolSAR) images via proposing a new spatially variant G p 0 mixture model based on the extended variational inference (SV G p 0 MM-EVI). Specifically, an SV G p 0 MM is constructed by associating data points with their own mixing coefficient vectors rather than sharing the same vector, which provides the additional flexibility to incorporate the spatial context and further effectively deal with the more heterogeneous areas than G p 0 MM. Then, an extended variational inference (EVI) algorithm is derived to facilitate the assignment of the conjugate prior distributions and accurately estimate the underlying parameters, in which two "help" functions are specially designed to solve the intractable variational lower bound. Meanwhile, dual spatial constraints based on the Bartlett distance and the mean template are also explored on polarimetric matrix and the hyperparameter in the posteriori distribution of mixing coefficients, respectively, thus adequately capturing the local correlation from the polarimetric matrix and the geometry perspectives. Furthermore, the learning algorithm with all the closed-form updates is developed and the cluster number could be automatically determined. Five PolSAR data sets (including two labeled data sets), which are obtained by different sensors, are used to verify the effectiveness of the proposed model. Experimental results illustrate that the proposed SV G p 0 MM-EVI is beneficial to classification task of PolSAR images, and achieves higher accuracy (e.g., 95.65% and 97.41% OA values) compared with some widely-used methods (i.e., H/ α -Wishart, Chernoff–Wishart, G p 0 MM, SVWMM and CK-HDRF methods). [ABSTRACT FROM AUTHOR]

[Display omitted] The detectability of wake components is affected by influencing parameters, which can be categorized into ship properties, environmental conditions and image acquisition settings. The characteristics of influences of most influencing parameters on the detectability are established. However, a consequent investigation and systematization of influences regarding differences in settings of various SARs have not been published. In this study, data from four different SARs missions, namely TerraSAR–X (TSX), CosmoSkymed (CSK), Sentinel–1 (S1) and RADARSAT–2 (RS2), were collected and analyzed with focus on detectability of ship wake components. The sensors operate on different orbit altitudes and radar frequency bands: TSX and CSK work with X–Band, S1 and RS2 work with C–Band. Using methods from the field of Data Science, the detectability of wake components is modelled for each of the four sensors using machine leaning by the support vector machine (SVM) method. The created SVM-models are then compared in order to derive statements regarding relative detectability of individual wake components. A measure of detectability model's uncertainty and an alternative analysis based on accumulated backscattering statistics is presented to support the derived statements. In conclusion, sensors with shorter slant ranges and X–Band in comparison to C–Band were found to be better suited for the detection of ship wakes. However, these characteristics only hold for wake components detectable due to the Bragg scattering mechanism, i.e. Kelvin wake arms and V-narrow wakes. No significant difference for near and far field of turbulent wakes is recognized. [ABSTRACT FROM AUTHOR]

Automatic and high-precision extraction of buildings from remote sensing images has a wide range of application and importance. Optical and synthetic aperture radar (SAR) images are typical types of multimodal remote sensing data with different imaging methods. To bridge the huge gap between them and achieve high-precision joint semantic segmentation, this study proposes a progressive fusion learning framework. The framework explicitly extracts the shared features (that is, modal invariants) of multimodal images as the information medium and realizes information fusion through multistage learning. Based on this framework, we design a network called the multistage multimodal fusion network (MMFNet), which uses phase as a modal invariant to joint optical and SAR images to achieve high-precision building extraction. We conducted experiments with the Multi-Sensor All-Weather Mapping aerial dataset and the WHU-OPT-SAR_WuHan satellite dataset. This study shows MMFNet has a significant extraction effect and yields more optimized extraction of the edge details of buildings, which is improved by 0.2% to 9.5% compared to other multimodal joint segmentation methods. [ABSTRACT FROM AUTHOR]

[Display omitted] Precise crop mapping is crucial for guiding agricultural production, forecasting crop yield, and ensuring food security. Integrating optical and synthetic aperture radar (SAR) satellite image time series (SITS) for crop classification is an essential and challenging task in remote sensing. Previously published studies generally employ a dual-branch network to learn optical and SAR features independently, while ignoring the complementarity and correlation between the two modalities. In this article, we propose a novel method to learn optical and SAR features for crop classification through cross-modal contrastive learning. Specifically, we develop an updated dual-branch network with partial weight-sharing of the two branches to reduce model complexity. Furthermore, we enforce the network to map features of different modalities from the same class to nearby locations in a latent space, while samples from distinct classes are far apart, thereby learning discriminative and modality-invariant features. We conducted a comprehensive evaluation of the proposed method on a large-scale crop classification dataset. Experimental results show that our method consistently outperforms traditional supervised learning approaches, no matter the training samples are adequate or not. Our findings demonstrate that unifying the representations of optical and SAR image time series enables the network to learn more competitive features and suppress inference noise. [ABSTRACT FROM AUTHOR]

Snow density is one of the important indicators of snow cover hydrological potential. The application of existing algorithms for retrieving dry snow density using synthetic aperture radar (SAR) data is limited by single scattering mechanism, small terrain fluctuation or narrow incidence angle range. In the study, an improved approach was proposed to retrieve dry snow density from C-band SAR data with a wide range of roughness and local incidence angles. Both the snow-ground interface scattering and volume scattering were considered in the approach. First, the relationship between the backscattering at the snow-ground interface and relative permittivity was obtained based on simulation using the Advanced Integral Equation Model (AIEM) and regression analysis. Then the classical relationship between the volume backscattering and relative permittivity obtained by the first-order volume scattering model was incorporated into the approach. For comparison, the coefficients of the Shi algorithm were redefined by the AIEM model and regression analysis, and the Shi algorithm initially developed for L-band was modified for C-band. In experiments, the RADARSAT-2 data obtained in the Manasi River Basin on December 12–17, 2013 and the C-band GaoFen-3 data obtained in the Kelan River Basin on January 17, 2018 were selected to validate the applicability of the proposed approach under different conditions. The inversion results in the Manasi River Basin using the proposed approach, Singh algorithm, and modified Shi algorithm were compared. The results in the Manasi River Basin show that the correlation coefficients (Rs) between the measured and estimated dry snow density are 0.868, 0.694, and 0.653 for the three methods, respectively. The root mean square errors (RMSEs) are 31.1 kg m−3, 59.1 kg m−3, and 64.7 kg m−3, respectively, and the mean relative errors (MREs) are 12.9%, 21.9%, and 25.5%, respectively. The corresponding R, RMSE, and MRE in the Kelan River Basin using the proposed approach are 0.717, 57.2 kg m−3, and 27.1%, respectively. The results prove that the dry snow density under different C-band SAR data and different areas can be effectively retrieved using the proposed approach superior to the other two algorithms. [ABSTRACT FROM AUTHOR]

• The impact of the geometric approximation errors on the estimated height is re-examined in the context of airborne array InSAR. • A hybrid 3D phase unwrapping scheme with regard to the geometric approximation error compensation is proposed. • The proposed method is extensively validated using both simulated data and real airborne array InSAR images. Multi-temporal synthetic aperture radar interferometry (MT-InSAR) is able to detect surface deformation and reconstruct a 3D surface model with high precision but requires a long observation period to accumulate the multi-baseline SAR images. The airborne array InSAR system is able to acquire a stack of multi-baseline SAR images in a single acquisition, which significantly improves the 3D modeling capability. However, processing the images obtained by the low-altitude platform using the conventional model will lead to geometric approximation (GA) errors, such as flattened phase error and reference error, which degrade the precision of the 3D reconstruction. In this paper, we quantitatively analyze the error sources of the array-InSAR interferograms and design a hybrid 3D phase unwrapping approach for 3D reconstruction. A hypothesis test is developed to identify the phase ambiguity by comparing the initial solution of the least-square with that of the beam-forming. Three indicators are proposed to identify the reliable arcs, achieving a reliable phase unwrapping. The L 1 norm approach is adopted to detect the unwrapping errors during the spatial unwrapping and a two-tie network strategy is used to process the data in the individual blocks from the perspective of global optimization. Furthermore, an iterative scheme is recommended to compensate the geometric approximation errors. The main advantage of the proposed algorithm is the compensation of the GA error and reliable phase unwrapping. The experimental results by both simulated and real SAR data show that the proposed algorithm can eliminate the GA error and provide a viable solution to rapid 3D SAR imaging with an airborne platform. [ABSTRACT FROM AUTHOR]

Touzi decomposition provides more scattering information corresponding to parameters describing different targets. It is possible to explore the selection method of parameters, which plays an important role in polarimetric synthetic aperture radar (PolSAR) image classification. Therefore, this paper presents an innovative parameter ordering scheme based on the histogram of parameters obtained by Touzi decomposition. Then, a parameter selection scheme is proposed by analyzing the influence of the increase of parameters on the overall accuracy obtained by the Softmax classifier. Based on the Gamma distribution, the parameter selection method of eigenvalue decomposition is also given. As the data distribution of the selected parameters does not always satisfy the Gaussian distribution, it may not be sufficient to directly apply the autoencoder network. Thus, the loss function of the autoencoder network is modified by the construction of different data error terms according to a different data distribution form of the selected parameters, and then an improved autoencoder network is proposed. The process of feature extraction and classification can be regarded as a whole network to better accomplish the task of classification. An extensive set of experiments are done on four real PolSAR images. Compared with the classification results of all parameters, the gap in the overall accuracy of the parameters obtained by the proposed selection scheme is only about 1%. In terms of the classification overall accuracy, considering the distribution of parameters in the autoencoder network and the construction of the whole classification network can improve it by about 6–7% for four data sets. Code is available at https://github.com/Justin20220123/ISPRS2022. [ABSTRACT FROM AUTHOR]

Synthetic aperture radar (SAR) is playing an important role in maritime domain awareness. As a fundamental ocean mission, SAR ship detection can offer high-quality services for marine surveillance. It receives widespread concern in the SAR remote sensing community. Recently, deep learning (DL) has greatly improved SAR ship detection accuracy. However, there are still some unperceived imbalance problems that seriously hinder further accuracy improvements among current DL-based SAR ship detectors. Therefore, we propose a novel concept of balance learning (BL) for high-quality SAR ship detection. We first point out the four unperceived imbalance problems, i.e., image sample scene imbalance, positive negative sample imbalance, ship scale feature imbalance, and classification regression task imbalance. Then, we offer some profound insights into these imbalances. Immediately, we propose four effective solutions to handle the above four imbalances correspondingly, i.e., balance scene learning mechanism (BSLM), balance interval sampling mechanism (BISM), balance feature pyramid network (BFPN), and balance classification regression network (BCRN). Finally, combined with the four solutions, a novel balance learning network (BL-Net) is proposed. Ablation studies can confirm each solution's effectiveness. Experimental results on five open datasets (SSDD, Gaofen-SSDD, Sentinel-SSDD, SAR-Ship-Dataset, and HRSID) reveal BL-Net's state-of-the-art SAR ship detection performance compared to the other 30 DL-based SAR ship detectors. Specifically, in contrast to the current most competitive method, the accuracy increase of BL-Net is 2.98% on SSDD, 1.97% on Gaofen-SSDD, 1.49% on Sentinel-SSDD, 0.55% on SAR-Ship-Dataset, and 4.95% on HRSID. Last but not least, the satisfactory ship detection results on another two large-scene Sentinal-1 SAR images confirm BL-Net's strong migration capability. This indicates BL-Net's potential value in marine surveillance. [ABSTRACT FROM AUTHOR]

Synthetic aperture radar (SAR) has great potential for timely monitoring of flood information as it penetrates the clouds during flood events. Moreover, the proliferation of SAR satellites with high spatial and temporal resolution provides a tremendous opportunity to understand the flood risk and its quick response. However, traditional algorithms to extract flood inundation using SAR often require manual parameter tuning or data annotation, which presents a challenge for the rapid automated mapping of large and complex flooded scenarios. To address this issue, we proposed a segmentation algorithm for automatic flood mapping in near-real-time over vast areas and for all-weather conditions by integrating Sentinel-1 SAR imagery with an unsupervised machine learning approach named Felz-CNN. The algorithm consists of three phases: (i) super-pixel generation; (ii) convolutional neural network-based featurization; (iii) super-pixel aggregation. We evaluated the Felz-CNN algorithm by mapping flood inundation during the Yangtze River flood in 2020, covering a total study area of 1,140,300 km2. When validated on fine-resolution Planet satellite imagery, the algorithm accurately identified flood extent with producer and user accuracy of 93% and 94%, respectively. The results are indicative of the usefulness of our unsupervised approach for the application of flood mapping. Meanwhile, we overlapped the post-disaster inundation map with a 10-m resolution global land cover map (FROM-GLC10) to assess the damages to different land cover types. Of these types, cropland and residential settlements were most severely affected, with inundation areas of 9,430.36 km2 and 1,397.50 km2, respectively, results that are in agreement with statistics from relevant agencies. Compared with traditional supervised classification algorithms that require time-consuming data annotation, our unsupervised algorithm can be deployed directly to high-performance computing platforms such as Google Earth Engine and PIE-Engine to generate a large-spatial map of flood-affected areas within minutes, without time-consuming data downloading and processing. Importantly, this efficiency enables the fast and effective monitoring of flood conditions to aid in disaster governance and mitigation globally. [ABSTRACT FROM AUTHOR]

Earth observation (EO) technologies, such as optical imaging and synthetic aperture radar (SAR), provide excellent means to continuously monitor ever-growing urban environments. Notably, in the case of large-scale disasters (e.g., tsunamis and earthquakes), in which a response is highly time-critical, images from both data modalities can complement each other to accurately convey the full damage condition in the disaster aftermath. However, due to several factors, such as weather and satellite coverage, which data modality will be the first available for rapid disaster response efforts is often uncertain. Hence, novel methodologies that can utilize all accessible EO datasets are essential for disaster management. In this study, we developed a global multimodal and multitemporal dataset for building damage mapping. We included building damage characteristics from three disaster types, namely, earthquakes, tsunamis, and typhoons, and considered three building damage categories. The global dataset contains high-resolution (HR) optical imagery and high-to-moderate-resolution SAR data acquired before and after each disaster. Using this comprehensive dataset, we analyzed five data modality scenarios for damage mapping: single-mode (optical and SAR datasets), cross-modal (pre-disaster optical and post-disaster SAR datasets), and mode fusion scenarios. We defined a damage mapping framework for semantic segmentation of damaged buildings based on a deep convolutional neural network (CNN) algorithm. We also compared our approach to another state-of-the-art model for damage mapping. The results indicated that our dataset, together with a deep learning network, enabled acceptable predictions for all the data modality scenarios. We also found that the results from cross-modal mapping were comparable to the results obtained from a fusion sensor and optical mode analysis. [ABSTRACT FROM AUTHOR]

To date, numerous Earth observation datasets from different types of satellites have been widely used in photogrammetric fields, including urban 3D modelling and geographic information systems. The development of small satellites has provided a new way to obtain repeated observations in a short period. However, compared with that of standard satellite imagery, the geometric performance of imagery from small satellites is relatively poor, restricting their photogrammetric applications. Traditional methods can improve the accuracy of optical images with the addition of well-distributed ground control points (GCPs), which require considerable financial and human resources. The collection of multi-view datasets is an alternative method for geometric processing without GCPs, but relies heavily on the stability and revisit period of satellite platforms. Therefore, this paper presents a framework for improving the geopositioning accuracy of multi-source datasets obtained from optical and synthetic aperture radar (SAR) satellites, and a novel heterogeneous weight strategy is proposed based on an analysis of the geometric error sources of SAR and optical images. The geometric performance of multi-source optical imagery from the Jilin-1 (JL-1) small satellite constellation is evaluated and analysed first, and then Gaofen-3 (GF-3) SAR images are calibrated based on statistical analysis for the production of virtual control points (VCPs). Based on our proposed heterogeneous weight strategy, multi-source optical and SAR images are integrated to improve the geopositioning accuracy. Experimental results indicate that our proposed model can achieve the best performance compared with other popular models, producing an accuracy of approximately 3 m in planimetry and 2 m in height, thereby providing a generic way to synergistically use multi-source remote sensing data. [ABSTRACT FROM AUTHOR]

Ship detection from Synthetic Aperture Radar (SAR) imagery is attracting increasing attention due to its great value in ocean. However, existing most studies are frequently improving detection accuracy at the expense of detection speed. Thus, to solve this problem, this paper proposes HyperLi-Net for high-accurate and high-speed SAR ship detection. We propose five external modules to achieve high-accuracy, i.e., Multi-Receptive-Field Module (MRF-Module), Dilated Convolution Module (DC-Module), Channel and Spatial Attention Module (CSA-Module), Feature Fusion Module (FF-Module) and Feature Pyramid Module (FP-Module). We also adopt five internal mechanisms to achieve high-speed, i.e., Region-Free Model (RF-Model), Small Kernel (S-Kernel), Narrow Channel (N-Channel), Separable Convolution (Separa-Conv) and Batch Normalization Fusion (BN-Fusion). Experimental results on the SAR Ship Detection Dataset (SSDD), Gaofen-SSDD and Sentinel-SSDD show that HyperLi-Net's accuracy and speed are both superior to the other nine state-of-the-art methods. Moreover, the satisfactory detection results on two Sentinel-1 SAR images can reveal HyperLi-Net's good migration capability. HyperLi-Net is build from scratch with fewer parameters, lower computation costs and lighter model that can be efficiently trained on CPUs and is helpful for future hardware transplantation, e.g. FPGAs, DSPs, etc. [ABSTRACT FROM AUTHOR]

Stem volume is a key attribute of Eucalyptus forest plantations upon which decision-making is based at diverse levels of planning. Quantifying volume through remote sensing can support a proper management of forests. Because of limitations on spaceborne optical and synthetic aperture radar sensors, this study integrated both types of datasets assembled using support vector regression (SVR) to retrieve the stand volume of Eucalyptus plantations. We assessed different combinations of sensors and a minimum number of plots to develop an SVR model. Finally, the best SVR performance was compared with other analytical methods already tested and in the literature: multilinear regression, artificial neural networks (ANN), and random forest (RF). Here, we introduce a test for comparative analysis of the performance of different methods. We found that SVR accurately predicted stem volume of Brazilian fast-growing Eucalyptus forest plantations. Gaussian radial basis was the most suitable kernel function. Integrating the optical and L-band backscatter data increased the predictive accuracy compared to a single sensor model. Combining NIR-band data from ALOS AVNIR-2 and backscatter of L-band horizontal emitted and vertical received (HV) electric fields from ALOS PALSAR produced the most accurate SVR model (with an R2 of 0.926 and root mean square error of 11.007 m3/ha). The number of field plots sufficient for model development with non-redundant explanatory variables was 77. Under this condition, SVR performed similarly to ANN and outperformed the multiple linear regression and random forest methods. [ABSTRACT FROM AUTHOR]