Search

In this paper, a feature extraction technique based on the electromagnetic (EM) representation of radar signals is presented. In particular, we focus on ground-penetrating radar (GPR) imaging, where we model the backscatter from varying 2-D geometric shapes with arbitrary local coordinate rotations. Due to the electrically small nature of buried targets and the bending of the radar signal at the air–soil interface, we focus on exact methods to model the surface current density induced on scattering surfaces. Overcomplete basis sets are derived from the EM descriptions to represent the scene sparsely. From this proposed modeling framework, we devise a novel methodology to exploit the prediction of scattering behavior to extract features for classification from radar scenes when multiple buried scattering surfaces are present. We see that our method can identify and reconstruct buried scattering geometries in the presence of false targets that are brought about by the nonlinear nature of the exact EM modeling methods. A noniterative algorithm based on the conjugate of Green’s function is developed to solve for the surface current in an unknown domain using multifrequency, multiaperture data. Our modeling and feature extraction algorithms are numerically validated for different target shapes buried in lossy soil profiles. [ABSTRACT FROM AUTHOR]

The nonstationary and non-Gaussian distribution of the high-resolution (HR) synthetic aperture radar (SAR) image provides much valuable information. However, the current methods, especially deep learning models, directly learn spatial features from HR SAR data while ignoring global statistical information. Combining the local spatial features and global statistical properties of HR SAR images is urgently needed to capture complete HR SAR characteristics. In this paper, a feature fusion network (Fusion-Net) using both deep spatial context encoder and nonstationary joint statistical model (NS-JSM) is proposed for the first time. Fusion-Net realizes the fusion description of local spatial and global statistical features in an end-to-end supervised classification framework. First, a deep spatial context encoder network (DSCEN) is designed based on multiscale group convolution (MSGC) module and channel attention (CA) module. The DSCEN expands the scope of context information extraction with few parameters and increases the interaction between high- level feature channels. Then, the NS-JSM is adopted to capture the unique SAR statistical information. Specifically, the SAR image is transformed into the Gabor wavelet domain. The produced sub-band magnitudes and phases are modeled by the log-normal and uniform distribution. The covariance matrix (CM) is calculated for mapped sub-band data to capture the interscale and intrascale nonstationary correlation. Finally, the group compression and smooth normalization units are introduced into Fusion-Net to fuse the statistical features and spatial features, which not only exploits the complementary information between different features but also optimizes the fusion feature representation. Experiments on four real HR SAR images validate the superiority of the proposed method over other related algorithms. [ABSTRACT FROM AUTHOR]

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

This paper proposes a complex-valued convolutional neural network for land form classification and discovery in interferometric synthetic aperture radar (InSAR). Since the amount of satellite-borne SAR data has been increasing drastically, it is necessary to structurize the local features contained in observation data prior to utilization in the so-called big data framework for higher usability. Convolutional neural networks have such potential in general. However, there exists no network that can deal with complex amplitude data obtained in InSAR consistently. In this paper, we propose a complex-valued convolutional neural network to deal with InSAR. We demonstrate that the network classifies slopes and plains adaptively and, moreover, indicates small volcanos similar to a sample volcano (Omuroyama) included in the InSAR data. We also find their characteristic features emerging in the kernels in the convolution layers. These results reveal that the proposed complex-valued convolutional neural network is capable of successfully discovering unidentified lands similar to a prepared sample, which is highly useful for the InSAR data structurization. [ABSTRACT FROM AUTHOR]

Craters are among the most abundant features on the surface of many planets with great importance for planetary scientists. They reveal chronology information about planets and may be used for autonomous spacecraft navigation and landing. Although numerous research efforts have been carried out in the field of crater detection, existing crater detection algorithms (CDAs) are only helpful in a limited number of applications. A promising crater detection approach involves two main steps: 1) hypothesis generation (HG) and 2) hypothesis verification (HV). During HG, potential crater locations are detected. The validity of the hypothesized crater locations is then tested in a HV step. In this context, we discuss some commonly used algorithms for HG such as highlight-shadow region detection and Hough transform as well as our novel and enhanced algorithms based on interest point detection and convex grouping. A key objective of this paper is to analyze their performance while paying special attention to how they affect the accuracy of the verification step. To deal with different size craters, we focus on multiscale HG. For HV, we have chosen convolutional neural networks which have recently achieved state-of-the-art performance in many computer vision applications. Due to the variation of test sets in the literature, it is often challenging to compare the performance of different CDAs in a fair way. In this paper, we present a comprehensive performance evaluation and comparison of CDAs. Each algorithm has been trained/tested using common data sets generated by a systematic approach. [ABSTRACT FROM AUTHOR]

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

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

Recently, researchers have shown the powerful ability of deep methods with multilayers to extract high-level features and to obtain better performance for hyperspectral image classification. However, a common problem of traditional deep models is that the learned deep models might be suboptimal because of the limited number of training samples, especially for the image with large intraclass variance and low interclass variance. In this paper, novel convolutional neural networks (CNNs) with multiscale convolution (MS-CNNs) are proposed to address this problem by extracting deep multiscale features from the hyperspectral image. Moreover, deep metrics usually accompany with MS-CNNs to improve the representational ability for the hyperspectral image. However, the usual metric learning would make the metric parameters in the learned model tend to behave similarly. This similarity leads to obvious model’s redundancy and, thus, shows negative effects on the description ability of the deep metrics. Traditionally, determinantal point process (DPP) priors, which encourage the learned factors to repulse from one another, can be imposed over these factors to diversify them. Taking advantage of both the MS-CNNs and DPP-based diversity-promoting deep metrics, this paper develops a CNN with multiscale convolution and diversified metric to obtain discriminative features for hyperspectral image classification. Experiments are conducted over four real-world hyperspectral image data sets to show the effectiveness and applicability of the proposed method. Experimental results show that our method is better than original deep models and can produce comparable or even better classification performance in different hyperspectral image data sets with respect to spectral and spectral–spatial features. [ABSTRACT FROM AUTHOR]

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

This paper addresses the highly challenging problem of automatically detecting man-made structures especially buildings in very high-resolution (VHR) synthetic aperture radar (SAR) images. In this context, this paper has two major contributions. First, it presents a novel and generic workflow that initially classifies the spaceborne SAR tomography (TomoSAR) point clouds—generated by processing VHR SAR image stacks using advanced interferometric techniques known as TomoSAR—into buildings and nonbuildings with the aid of auxiliary information (i.e., either using openly available 2-D building footprints or adopting an optical image classification scheme) and later back project the extracted building points onto the SAR imaging coordinates to produce automatic large-scale benchmark labeled (buildings/nonbuildings) SAR data sets. Second, these labeled data sets (i.e., building masks) have been utilized to construct and train the state-of-the-art deep fully convolution neural networks with an additional conditional random field represented as a recurrent neural network to detect building regions in a single VHR SAR image. Such a cascaded formation has been successfully employed in computer vision and remote sensing fields for optical image classification but, to our knowledge, has not been applied to SAR images. The results of the building detection are illustrated and validated over a TerraSAR-X VHR spotlight SAR image covering approximately 39 km 2—almost the whole city of Berlin— with the mean pixel accuracies of around 93.84%. [ABSTRACT FROM AUTHOR]

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

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

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

This paper introduces an extension of morphological attribute profiles (APs) by extracting their local features. The so-called local feature-based APs (LFAPs) are expected to provide a better characterization of each APs' filtered pixel (i.e., APs' sample) within its neighborhood, and hence better deal with local texture information from the image content. In this paper, LFAPs are constructed by extracting some simple first-order statistical features of the local patch around each APs' sample such as mean, standard deviation, and range. Then, the final feature vector characterizing each image pixel is formed by combining all local features extracted from APs of that pixel. In addition, since the self-dual APs (SDAPs) have been proved to outperform the APs in recent years, a similar process will be applied to form the local feature-based SDAPs (LFSDAPs). In order to evaluate the effectiveness of LFAPs and LFSDAPs, supervised classification using both the random forest and the support vector machine classifiers is performed on the very high resolution Reykjavik image as well as the hyperspectral Pavia University data. Experimental results show that LFAPs (respectively, LFSDAPs) can considerably improve the classification accuracy of the standard APs (respectively, SDAPs) and the recently proposed histogram-based APs. [ABSTRACT FROM AUTHOR]

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

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

The automatic detection of buried threats in ground penetrating radar (GPR) data is an active area of research due to GPR's ability to detect both metal and nonmetal subsurface objects. Recent work on algorithms designed to distinguish between threats and nonthreats in GPR data has utilized computer vision methods to advance the state-of-the-art detection and discrimination performance. Feature extractors, or descriptors, from the computer vision literature have exhibited excellent performance in representing 2-D GPR image patches and allow for robust classification of threats from nonthreats. This paper aims to perform a broad study of feature extraction methods in order to identify characteristics that lead to improved classification performance under controlled conditions. The results presented in this paper show that gradient-based features, such as the edge histogram descriptor and the scale invariant feature transform, provide the most robust performance across a large and varied data set. These results indicate that various techniques from the computer vision literature can be successfully applied to target detection in GPR data and that more advanced techniques from the computer vision literature may provide further performance improvements. [ABSTRACT FROM PUBLISHER]

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

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

Dimensionality reduction (DR) has attracted extensive attention since it provides discriminative information of hyperspectral images (HSI) and reduces the computational burden. Though DR has gained rapid development in recent years, it is difficult to achieve higher classification accuracy while preserving the relevant original information of the spectral bands. To relieve this limitation, in this paper, a different DR framework is proposed to perform feature extraction on the selected bands. The proposed method uses determinantal point process to select the representative bands and to preserve the relevant original information of the spectral bands. The performance of classification is further improved by performing multiple Laplacian eigenmaps (LEs) on the selected bands. Different from the traditional LEs, multiple Laplacian matrices in this paper are defined by encoding spatial–spectral proximity on each band. A common low-dimensional representation is generated to capture the joint manifold structure from multiple Laplacian matrices. Experimental results on three real-world HSIs demonstrate that the proposed framework can lead to a significant advancement in HSI classification compared with the state-of-the-art methods. [ABSTRACT FROM PUBLISHER]

In this paper, we propose a feature-tracking algorithm for sea ice drift retrieval from a pair of sequential satellite synthetic aperture radar (SAR) images. The method is based on feature tracking comprising feature detection, description, and matching steps. The approach exploits the benefits of nonlinear multiscale image representations using accelerated-KAZE (A-KAZE) features, a method that detects and describes image features in an anisotropic scale space. We evaluated several state-of-the-art feature-based algorithms, including A-KAZE, Scale Invariant Feature Transform (SIFT), and a very fast feature extractor that computes binary descriptors known as Oriented FAST and Rotated BRIEF (ORB) on dual polarized Sentinel-1A C-SAR extra wide swath mode data over the Arctic. The A-KAZE approach outperforms both ORB and SIFT up to an order of magnitude in ice drift. The experimental results showed high relevance of the proposed algorithm for retrieval of ice drift at subkilometre resolution from a pair of SAR images with 100-m pixel size. From this paper, we found that feature tracking using nonlinear scale-spaces is preferable due to its high efficiency against noise with respect to image features compared with other existing feature tracking alternatives that make use of Gaussian or linear scale spaces. [ABSTRACT FROM PUBLISHER]

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

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

This paper proposes a multi-scale rotation-invariant haar-like (MSRI-HL) feature integrated convolutional neural network (MSRIHL-CNN)-based ship detection algorithm of the multiple-target environment in synthetic aperture radar (SAR) imagery. Usually, ship detection includes preprocessing, prescreening, discrimination, and classification. Among them, prescreening and discrimination are the most two important stages so that they catch great intention. Based on our previous work, we propose a truncated-clutter-statistics-based joint, constant false alarm rate (CFAR) detector (TCS-JCFAR) for ship target prescreening in the multiple-target environment. TCS-JCFAR greatly enhances the prescreening rate in the multiple-target environment while achieving a low observed FAR. In the discrimination stage, conventional CNN extracts the deep features (high-level features); however, it will lose the local texture and edge information (low-level features) which are of great significance for target discrimination. Hence, the MSRI-HL features are used to represent the multi-scale, rotation-invariant texture, and edge information that conventional CNN fails to capture. The extracted low-level MSRI-HL features and the high-level deep features are optimally fused to a multi-layered feature vector. Finally, the multi-layered feature vector is fed into a typical support vector machine (SVM) classifier for ship target discrimination. The proposed MSRIHL-CNN combines the low-level texture and edge features and the high-level deep features; moreover, they are optimally fused to fully represent the ship targets. Undoubtedly, MSRIHL-CNN has better discrimination performance. The superiority of the proposed TCS-JCFAR-based prescreener and MSRIHL-CNN-based discriminator is validated on the Chinese Gaofen-3 SAR imagery. [ABSTRACT FROM AUTHOR]

This paper proposes a fast target indexing method based on target geometric models and further conceives a forward method based coarse-to-fine hierarchical synthetic aperture radar (SAR) automatic target recognition (ATR) system. The proposed fast SAR target indexing method is employed for coarse classification before the implementation of fine classification and recognition, resulting in significant acceleration of target recognition. Furthermore, the fast SAR target indexing method is purely based on target geometric models without resorting to any time-consuming electromagnetic (EM) computation, which enables the online and real-time classification. The binary target region and shadow region are selected as the indexing features, and a forward feature prediction method based on optical visibility is developed to predict the features from the target geometric model in real time. Then, the features extracted from the testing SAR image are aligned with the predicted features to establish correlation ship and a fused similarity based on four types of complementary similarity criteria is designed to further implement target indexing. The effectiveness of the proposed fast SAR target indexing method is demonstrated by using the MSTAR dataset. [ABSTRACT FROM AUTHOR]

Compressive spectral imaging (CSI) has emerged as an alternative acquisition framework that simultaneously senses and compresses spectral images. In this context, the spectral image classification from CSI compressive measurements has become a challenging task since the feature extraction stage usually requires reconstructing the spectral image. Moreover, most approaches do not consider multi-sensor compressive measurements. In this paper, an approach for fusing features obtained from multi-sensor compressive measurements is proposed for spectral image classification. To this end, linear models describing low-resolution features as degraded versions of the high-resolution features are developed. Furthermore, an inverse problem is formulated aiming at estimating high-resolution features including both a sparsity-inducing term and a total variation (TV) regularization term to exploit the correlation between neighboring pixels of the spectral image, and therefore, to improve the performance of pixel-based classifiers. An algorithm based on the alternating direction method of multipliers (ADMM) is described for solving the fusion problem. The proposed feature fusion approach is tested for two CSI architectures: three-dimensional coded aperture snapshot spectral imaging (3D-CASSI) and colored CASSI (C-CASSI). Extensive simulations on various spectral image data sets show that the proposed approach outperforms other classification approaches under different performance criteria. [ABSTRACT FROM AUTHOR]

For hyperspectral image classification, there is a large gap between the theoretical method and the practical application. Hyperspectral image classification in theoretical research trains a new classifier for each data set, which is ineffective and even infeasible in large-scale applications. In this paper, we make a preliminary attempt to recycle the classification model to new data sets in an unsupervised way. Specially, we propose a cross-data set hyperspectral image classification method based on deep domain adaptation. The proposed method contains three modules: domain alignment module that learns to minimize the domain discrepancy with the guide of an irrelevant task, task allocation module that learns to classify on the source domain with the regulation of domain alignment, and domain adaptation module that transfers both the alignment ability and classification ability to the target domain by an adaptation strategy. As a result, with the information of an irrelevant task on dual-domain data sets, we can minimize the domain discrepancy and transfer the task-relevant knowledge from the source domain to the target domain in an unsupervised way. Extensive experiments on three hyperspectral images demonstrate the effectiveness of our method compared with other related methods when dealing with new data sets. [ABSTRACT FROM AUTHOR]

Although the deep convolutional neural network (DCNN) has been successfully applied to automatic target recognition (ATR) of ground vehicles based on synthetic aperture radar (SAR), most of the available techniques are not suitable for inverse synthetic aperture radar (ISAR) because they cannot tackle the inherent unknown deformation (e.g., translation, scaling, and rotation) among the training and test samples. To achieve robust polarimetric-ISAR (Pol-ISAR) ATR, this paper proposes the spatial transformer-multi-channel-deep convolutional neural network, i.e., ST-MC-DCNN. In this structure, we adopt the double-layer spatial transformer network (STN) module to adjust the image deformation of each polarimetric channel and then perform a robust hierarchical feature extraction by MC-DCNN. Finally, we carry out feature fusion in the concatenation layer and output the recognition result by the softmax classifier. The proposed network is end-to-end trainable and could learn the optimal deformation parameters automatically from training samples. For the fully Pol-ISAR image database generated from electromagnetic (EM) echoes of four satellites, the proposed structure achieves higher recognition accuracy than traditional DCNN and MC-DCNN. Additionally, it has shown robustness to image scaling, rotation, and combined deformation. [ABSTRACT FROM AUTHOR]

Accurate and robust detection of multi-class objects in optical remote sensing images is essential to many real-world applications, such as urban planning, traffic control, searching, and rescuing. However, the state-of-the-art object detection techniques designed for images captured using ground-level sensors usually experience a sharp performance drop when directly applied to remote sensing images, largely due to the object appearance differences in remote sensing images in terms of sparse texture, low contrast, arbitrary orientations, and large-scale variations. This paper presents a novel object detection network [(context-aware detection network (CAD-Net)] that exploits attention-modulated features as well as global and local contexts to address the new challenges in detecting objects from remote sensing images. The proposed CAD-Net learns global and local contexts of objects by capturing their correlations with the global scene (at scene level) and the local neighboring objects or features (at object level), respectively. In addition, it designs a spatial-and-scale-aware attention module that guides the network to focus on more informative regions and features as well as more appropriate feature scales. Experiments over two publicly available object detection data sets for remote sensing images demonstrate that the proposed CAD-Net achieves superior detection performance. The implementation codes will be made publicly available for facilitating future works. [ABSTRACT FROM AUTHOR]

Compressive sensing enables efficient acquisition of hyperspectral images (HSIs) by assuming high redundancy on natural scenes. Several reconstruction algorithms have been proposed to retrieve the underlying image, and most of them take advantage of the spatial and spectral correlations. However, reconstruction may not be necessary in certain applications such as land cover classification. Instead of knowing the full image, researchers are interested in features that could be extracted directly from the compressed measurements, which provide high inference capabilities. Low-rank (LR) matrix approximation has been widely used in feature extraction (FE), because it reduces the data dimension and computational cost. Therefore, in this paper, compressive hyperspectral imaging and FE are combined in a framework for HSI classification using an LR matrix approximation model. In the proposed framework, the compressed measurements are acquired from a single-pixel spectrometer. Instead of using the traditional high-complexity reconstruction model, an LR matrix factorization problem is formulated. The LR problem maximizes the posterior distribution with respect to the feature space and coefficients, and it is numerically solved based on an alternating optimization strategy. By incorporating spatial information, the numerical procedure minimizes the total variational of the feature coefficients subject to an orthogonality constraint for the feature space. Experiments on real HSIs show that the proposed approach can provide equally competitive classification results when compared to the traditional approach that performs FE and classification on the recovered images. [ABSTRACT FROM AUTHOR]

The synthetic aperture radar (SAR) target detection method in the background of a complex scene and extremely low signal-to-noise ratio (EL-SNR) is studied in this paper. With theoretical derivation and analysis, the singularity power spectrum (SPS) is developed into two-dimensional SPS (2D-SPS). Developed from the 2-D Holder exponent and the SPS, the 2D-SPS can be applied for the singularity power analysis of images. Furthermore, a novel SAR target detection method based on 2D-SPS is proposed. The proposed methodology is tested on sea clutters, both with and without SAR ship target, from the OpenSAR data sets. The experimental results indicate that the SAR target detection based on 2D-SPS performs better than conventional multifractal spectrum (MFS) and constant false alarm rate (CFAR) methods, and can achieve more than 95% and 98% detection probability, respectively, under EL-SNR with SNR = −30 dB, SNR = −10 dB, and $P_{f} = 10^{-2}$ , and almost 100% detection probability for weak and multiple targets within sea clutters. The proposed method can be applied to target detection under the background of fractal noise and provides a reference for target detection in related fields. [ABSTRACT FROM AUTHOR]

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]

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]

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]

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]

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]

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]

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]

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]

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]

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]

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]

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]

Point cloud classification is one of the most important and time-consuming stages of airborne LiDAR (Light Detection and Ranging) data processing, playing a key role in the generation of cartographic products. This paper describes an innovative algorithm to perform LiDAR point-cloud classification, which relies on Convolutional Neural Networks (CNNs) and takes advantage of full-waveform data registered by modern laser scanners. The proposed method consists of two steps. First, a simple CNN is used to preprocess each waveform, providing a compact representation of the data. By exploiting the coordinates of the points associated with the waveforms, output vectors generated by the first CNN are then mapped into an image that is subsequently segmented by a Fully Convolutional Network (FCN): a label is assigned to each pixel and, consequently, to the point falling in the pixel. In this way, spatial positions and geometrical relationships between neighboring data are taken into account. These particular architectures allow to accurately identify even challenging classes such as power line and transmission tower. [ABSTRACT FROM AUTHOR]

The whole-sky imager has been increasingly used for ground-based cloud automatic observation. Many approaches based on image processing have been applied to detect or classify clouds in whole-sky images (WSIs). However, most of the studies only focus on image segmentation for cloud detection or image classification for cloud recognition separately. The cloud detection only does the binary segmentation (sky and cloud) without cloud types, while the cloud recognition only gives the single image-level label without cloud coverage. In this paper, a fine-grained cloud detection and recognition task with a solution is proposed to fill the gap, which can simultaneously detect and classify clouds in a WSI. It can be regarded as a pixel-level fine-grained dense prediction for images. First, a new data set is built with pixel-level annotation of nine different types. Then, a solution based on supervised learning is proposed, in which the pixel-level prediction problem is converted to a superpixel classification problem. Multiview features are extracted, including color, inside texture, neighbor texture, and global relation, to represent the superpixels. Moreover, a class-specific feature space transformation method based on metric learning and subspace alignment is proposed to overcome the challenge brought by the high similarity among cloud types and the feature shifting. Finally, several experiments have verified that our approach is effective to the challenging new task and also outperforms some other methods in the normal tasks of cloud detection and cloud classification, respectively. [ABSTRACT FROM AUTHOR]

Currently, deep neural networks (DNNs) are an important method for handling hyperspectral image (HSI) classification because of their good performance in image processing. However, DNNs’ performance depends on a massive number of training data and hyperparameters that are carefully fine-tuned, which results in structural complexity and a time-consuming process. Deep forest is a novel deep learning method that does not need much training data and has a simple structure. In this paper, we first design a deep forest for spectral-based HSI classification and then propose an improved deep forest algorithm, named deep multigrained cascade forest (dgcForest), for spatial-based HSI classification. On the one hand, the cascade forest in dgcForest is used in multigrained scanning, which enhances the performance; on the other hand, a pooling layer is added after the multigrained scanning to reduce the output dimensions. To demonstrate that our proposed algorithm presents a good performance in HSI classification, we analyze the hyperparameters of deep forest and dgcForest and compare them with other methods on the biased and unbiased data sets, which illustrates that our method is superior to other state-of-the-art deep learning methods. [ABSTRACT FROM AUTHOR]

Hyperspectral anomaly detection faces various levels of difficulty due to the high dimensionality of hyperspectral images (HSIs), redundant information, noisy bands, and the limited capability of utilizing spectral–spatial information. In this paper, we address these problems and propose a novel approach, called spectral–spatial feature extraction (SSFE), which is based on two main aspects. In the spectral domain, we assume that the anomalous pixels are rarely present and all (or most) of the samples around the anomalies belong to background (BKG). Using this fact, we introduce a suppression function to construct a discriminative feature space and utilize a deep brief network to learn spectral representation and abstraction automatically that are used as inputs to the Mahalanobis distance (MD)-based detector. In the spatial domain, the anomalies appear as a small area grouped by pixels with high correlation among them compared to BKG. Therefore, the objects appearing as a small area are extracted based on attribute filtering, and a guided filter is further employed for local smoothness. More specifically, we extract spatial features of anomalies only from one single band obtained by fusing all bands in the visible wavelength range. Finally, we detect anomalies by jointly considering the spectral and spatial detection results. Several experiments are performed, which show that our proposed method outperforms the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Deep neural networks (DNNs), including convolutional neural networks (CNNs) and residual networks (ResNets) models, are able to learn abstract representations from the input data by considering a deep hierarchy of layers that perform advanced feature extraction. The combination of these models with visual attention techniques can assist with the identification of the most representative parts of the data from a visual standpoint, obtained through more detailed filtering of the features extracted by the operational layers of the network. This is of significant interest for analyzing remotely sensed hyperspectral images (HSIs), characterized by their very high spectral dimensionality. However, few efforts have been conducted in the literature in order to adapt visual attention methods to remotely sensed HSI data analysis. In this paper, we introduce a new visual attention-driven technique for the HSI classification. Specifically, we incorporate attention mechanisms to a ResNet in order to better characterize the spectral–spatial information contained in the data. Our newly proposed method calculates a mask that is applied to the features obtained by the network in order to identify the most desirable ones for classification purposes. Our experiments, conducted using four widely used HSI data sets, reveal that the proposed deep attention model provides competitive advantages in terms of classification accuracy when compared to other state-of-the-art methods. [ABSTRACT FROM AUTHOR]