Search

This paper discusses an image processing architecture and tools to address the problem of ship detection in synthetic-aperture radar images. The detection strategy relies on a tree-based representation of images, here a Maxtree, and graph signal processing tools. Radiometric as well as geometric attributes are evaluated and associated with the Maxtree nodes. They form graph attribute signals which are processed with graph filters. The goal of this filtering step is to exploit the correlation existing between attribute values on neighboring tree nodes. Considering that trees are specific graphs where the connectivity toward ancestors and descendants may have a different meaning, we analyze several linear, nonlinear, and morphological filtering strategies. Beside graph filters, two new filtering notions emerge from this analysis: tree and branch filters. Finally, we discuss a ship detection architecture that involves graph signal filters and machine learning tools. This architecture demonstrates the interest of applying graph signal processing tools on the tree-based representation of images and of going beyond classical graph filters. The resulting approach significantly outperforms state-of-the-art algorithms. Finally, a MATLAB toolbox allowing users to experiment with the tools discussed in this paper on Maxtree or Mintree has been created and made public. [ABSTRACT FROM AUTHOR]

Linear spectral unmixing is the practice of decomposing the mixed pixel into a linear combination of the constituent endmembers and the estimated abundances. This paper focuses on unsupervised spectral unmixing where the endmembers are unknown a priori. Conventional approaches use either geometrical- or statistical-based approaches. In this paper, we address the challenges of spectral unmixing with unsupervised deep learning models, in specific, the autoencoder models, where the decoder serves as the endmembers and the hidden layer output serves as the abundances. In several recent attempts, part-based autoencoders have been designed to solve the unsupervised spectral unmixing problem. However, the performance has not been satisfactory. In this paper, we first discuss some important findings we make on issues with part-based autoencoders. By proof of counterexample, we show that all existing part-based autoencoder networks with nonnegative and tied encoder and decoder are inherently defective by making these inappropriate assumptions on the network structure. As a result, they are not suitable for solving the spectral unmixing problem. We propose a so-called untied denoising autoencoder with sparsity, in which the encoder and decoder of the network are independent, and only the decoder of the network is enforced to be nonnegative. Furthermore, we make two critical additions to the network design. First, since denoising is an essential step for spectral unmixing, we propose to incorporate the denoising capacity into the network optimization in the format of a denoising constraint rather than cascading another denoising preprocessor in order to avoid the introduction of additional reconstruction error. Second, to be more robust to the inaccurate estimation of a number of endmembers, we adopt an $l_{21}$ -norm on the encoder of the network to reduce the redundant endmembers while decreasing the reconstruction error simultaneously. The experimental results demonstrate that the proposed approach outperforms several state-of-the-art methods, especially for highly noisy data. [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 proposes a novel method based on deformable dictionary learning for detecting the regions of change between multitemporal image pairs. We build on our previous work, which constructed a pair of dictionaries. The main shortcoming of this method was its dependence on a large amount of training data. In practice, there is often a shortage of ground-truthed training images, which limits the expression capability of the resulting dictionaries. This paper overcomes this challenge by incorporating the concept of deformation, wherein each atom of a dictionary is no longer a simple image patch, but instead is a flexible image deformation function. This enables the creation of more expressive dictionaries, capable of generalizing to a far greater variety of image patterns, while using a far smaller amount of ground-truthed images for supervised dictionary training. Deformation similarity is employed for patch matching to find the best set of atoms in the difference image (DI) dictionary for reconstructing image patches for a new input DI. Each such atom can be deformed to achieve a better match, thus extending generality while reducing the number of atoms needed in the dictionary. Multiple deformed atoms are weighted and combined to best reconstruct the input DI patch. Then, the same set of deformations and weights is projected to the corresponding atoms in the CD dictionary to obtain the output change-detection map. Experiments in six realistic synthetic aperture radar data sets demonstrate the robustness and efficiency of the proposed method in comparison with five other state-of-the-art methods from the literature. [ABSTRACT FROM AUTHOR]

Under the umbrella of tensor algebra, this paper proposes a new sparse-coding-based classifier (SCC) for hyperspectral imagery classification (HIC). By utilizing the tensor forms of hyperspectral pixels, we advance a tensor sparse-coding model which preserves as many original spatial constraints of a pixel and its spatial neighbors as possible. Furthermore, to alleviate the classification uncertainty resulted from widely existing mixed pixels, this paper constructs a regularization term for maximizing the likelihood of sparse-coding tensor defined on the posterior class probability. By combining the tensor sparse coding with maximizing likelihood estimation, a hybrid probabilistic SCC with spatial neighbor tensor (HPSCC-SNT) is proposed, which makes the pixels be well represented by the training pixels belonging to the same class. The performance of HPSCC-SNT is evaluated on three real hyperspectral imagery data sets, and the results show that it can achieve accurate and robust HIC results, and outperforms the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Recently, multifeature learning in collaborative representation classification (CRC) for hyperspectral images has generated promising performance. In this paper, two novel multifeature learning algorithms that update dictionary directly and indirectly are proposed. In order to offer the complementarity of multifeature, four different types of features—global feature (i.e., Gabor feature), local feature (i.e., local binary pattern), shape feature (i.e., extended multiattribute profiles), and spectral feature—are adopted in this paper. Under the hypothesis that most of the features should share the same coding pattern in CRC, this paper proposes to learn proper dictionaries for each feature until obtaining stable codes in a linear classifier. Furthermore, to avoid the explicit mapping of infinite-dimensional dictionaries in a nonlinear kernelized classifier, an indirect approach to construct the transformation matrix from original dictionaries to learn new dictionaries is developed. Three real hyperspectral images acquired from different sensors are adopted for performance evaluation. The experimental results demonstrate that the proposed methods can provide superior performance compared with those of the state-of-the-art classifiers. [ABSTRACT FROM AUTHOR]

Supervised approaches classify input data using a set of representative samples for each class, known as training samples. The collection of such samples is expensive and time demanding. Hence, unsupervised feature learning, which has a quick access to arbitrary amounts of unlabeled data, is conceptually of high interest. In this paper, we propose a novel network architecture, fully Conv-Deconv network, for unsupervised spectral-spatial feature learning of hyperspectral images, which is able to be trained in an end-to-end manner. Specifically, our network is based on the so-called encoder-decoder paradigm, i.e., the input 3-D hyperspectral patch is first transformed into a typically lower dimensional space via a convolutional subnetwork (encoder), and then expanded to reproduce the initial data by a deconvolutional subnetwork (decoder). However, during the experiment, we found that such a network is not easy to be optimized. To address this problem, we refine the proposed network architecture by incorporating: 1) residual learning and 2) a new unpooling operation that can use memorized max-pooling indexes. Moreover, to understand the "black box," we make an in-depth study of the learned feature maps in the experimental analysis. A very interesting discovery is that some specific "neurons" in the first residual block of the proposed network own good description power for semantic visual patterns in the object level, which provide an opportunity to achieve "free" object detection. This paper, for the first time in the remote sensing community, proposes an end-to-end fully Conv-Deconv network for unsupervised spectral-spatial feature learning. Moreover, this paper also introduces an in-depth investigation of learned features. Experimental results on two widely used hyperspectral data, Indian Pines and Pavia University, demonstrate competitive performance obtained by the proposed methodology compared with other studied approaches. [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 deals with semantic segmentation of high-resolution (aerial) images where a semantic class label is assigned to each pixel via supervised classification as a basis for automatic map generation. Recently, deep convolutional neural networks (CNNs) have shown impressive performance and have quickly become the de-facto standard for semantic segmentation, with the added benefit that task-specific feature design is no longer necessary. However, a major downside of deep learning methods is that they are extremely data hungry, thus aggravating the perennial bottleneck of supervised classification, to obtain enough annotated training data. On the other hand, it has been observed that they are rather robust against noise in the training labels. This opens up the intriguing possibility to avoid annotating huge amounts of training data, and instead train the classifier from existing legacy data or crowd-sourced maps that can exhibit high levels of noise. The question addressed in this paper is: can training with large-scale publicly available labels replace a substantial part of the manual labeling effort and still achieve sufficient performance? Such data will inevitably contain a significant portion of errors, but in return virtually unlimited quantities of it are available in larger parts of the world. We adapt a state-of-the-art CNN architecture for semantic segmentation of buildings and roads in aerial images, and compare its performance when using different training data sets, ranging from manually labeled pixel-accurate ground truth of the same city to automatic training data derived from OpenStreetMap data from distant locations. We report our results that indicate that satisfying performance can be obtained with significantly less manual annotation effort, by exploiting noisy large-scale training data. [ABSTRACT FROM PUBLISHER]

The multispectral instrument (MSI) carried by Sentinel-2A has 13 spectral bands with various spatial resolutions (i.e., four 10-m, six 20-m, and three 60-m bands). A wide range of applications requires a 10-m resolution for all spectral bands, including the 20- and 60-m bands. To achieve this requirement, previous studies used conventional pansharpening techniques, which require a simulated 10-m panchromatic (PAN) band from four 10-m bands [blue, green, red, and near infrared (NIR)]. The simulated PAN band may not have all the information from the original four bands and may have no spectral response function that overlaps the 20- or 60-m bands to be sharpened, which may degrade fusion quality. This paper presents a machine learning method that can directly use the information from multiple 10-m resolution bands for fusion. The method first learns the spectral relationship between the 20- or 60-m band to be sharpened and the selected 10-m bands degraded to 20 or 60 m using the support vector regression (SVR) model. The model is then applied to the selected 10-m bands to predict the 10-m-resolution version of the 20- or 60-m band. The image degradation process was tuned to closely match the Sentinel-2A MSI modulation transfer function (MTF). We applied our method to three data sets in Guangzhou, China, New South Wales, Australia, and St. Louis, USA, and achieved better fusion results than other commonly used pansharpening methods in terms of both visual and quantitative factors. [ABSTRACT FROM AUTHOR]

Sparse unmixing has become a popular tool for hyperspectral imagery interpretation. It refers to finding the optimal subset of a spectral library to reconstruct the image data and further estimate the proportions of different materials. Recently, multi-objective based sparse unmixing methods have presented promising performance because of their advantages in addressing combinatorial problems. A spectral and multi-objective based sparse unmixing (SMoSU) algorithm was proposed in our previous work, which solves the decision-making problem well. However, it does not show outstanding advantages in strong noise cases. To solve the problem, in this paper, SMoSU is improved based on the estimation of distribution algorithms (EDAs). The machine learning based EDAs have been a reliable approach in solving multi-objective problems. However, most of them are for special problems and relatively weak in theoretical foundations. Thus, it is unreliable to extend it directly to sparse unmixing. Here, we improve EDA on the basis of classification and propose a classification-based model for individual generating under the framework of SMoSU (CM-MoSU). In CM-MoSU, the whole population is divided to be positive and negative. Then, the macroinformation of positive individuals is used to guide the generation of new individuals. Therefore, the optimization task could pay more attention to the feasible space with high quality. Moreover, some theoretical analyses are presented to prove the reliability of CM-MoSU. In experiments, several state-of-the-art sparse unmixing algorithms are compared. Both synthetic and real-world experiments demonstrate the effectiveness of CM-MoSU. [ABSTRACT FROM AUTHOR]

Linear hyperspectral unmixing (HU) aims at factoring the observation matrix into an endmember matrix and an abundance matrix. Linear HU via variational minimum volume (MV) regularization has recently received considerable attention in the remote sensing and machine learning areas, mainly owing to its robustness against the absence of pure pixels. We put some popular linear HU formulations under a unifying framework, which involves a data-fitting term and an MV-based regularization term, and collectively solve it via a nonconvex optimization. As the former and the latter terms tend, respectively, to expand (reducing the data-fitting errors) and to shrink the simplex enclosing the measured spectra, it is critical to strike a balance between those two terms. To the best of our knowledge, the existing methods find such balance by tuning a regularization parameter manually, which has little value in unsupervised scenarios. In this paper, we aim at selecting the regularization parameter automatically by exploiting the fact that a too large parameter overshrinks the volume of the simplex defined by the endmembers, making many data points be left outside of the simplex and hence inducing a large data-fitting error, while a sufficiently small parameter yields a large simplex making data-fitting error very small. Roughly speaking, the transition point happens when the simplex still encloses the data cloud but there are data points on all its facets. These observations are systematically formulated to find the transition point that, in turn, yields a good parameter. The competitiveness of the proposed selection criterion is illustrated with simulated and real data. [ABSTRACT FROM AUTHOR]

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

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]

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

The time-consuming modeling of physical remote sensing models restricts their application to parameter estimation from satellite observations. Machine learning techniques have become highly developed in recent years and show good capacity for model fitting. Based on our previously developed coupled soil–canopy–atmosphere radiative transfer model (RTM) and a multiple parameters estimation scheme, this paper evaluates the performance of four machine learning algorithms [Gaussian process regression (GPR), back-propagation neural networks (NNs), random forest regression, and general regression NN] on emulating the coupled RTM, where the traditional lookup table (LUT) algorithm is also compared. The results show that the GPR algorithm can emulate complex RTMs with excellent accuracy and efficiency. GPR emulators of photosynthetically active radiation (PAR), fraction of absorbed PAR, and incident shortwave radiation were applied to the multi-parameter estimation scheme to replace the traditional LUT algorithm, which avoids the need to integrate over the spectra while achieving an acceleration ratio of 16. A test of the updated multi-parameter estimation scheme at the Bondville site using 18 years of clear-sky observations demonstrates that replacing the computationally expensive integration processes with GPR emulators is practical. The emulators can also be used to simulate the corresponding parameters independently, and this GPR acceleration method for complex models is universal and can be easily applied to other time-consuming models. [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]

In the literature of remote sensing, deep models with multiple layers have demonstrated their potentials in learning the abstract and invariant features for better representation and classification of hyperspectral images. The usual supervised deep models, such as convolutional neural networks, need a large number of labeled training samples to learn their model parameters. However, the real-world hyperspectral image classification task provides only a limited number of training samples. This paper adopts another popular deep model, i.e., deep belief networks (DBNs), to deal with this problem. The DBNs allow unsupervised pretraining over unlabeled samples at first and then a supervised fine-tuning over labeled samples. But the usual pretraining and fine-tuning method would make many hidden units in the learned DBNs tend to behave very similarly or perform as “dead” (never responding) or “potential over-tolerant” (always responding) latent factors. These results could negatively affect description ability and thus classification performance of DBNs. To further improve DBN’s performance, this paper develops a new diversified DBN through regularizing pretraining and fine-tuning procedures by a diversity promoting prior over latent factors. Moreover, the regularized pretraining and fine-tuning can be efficiently implemented through usual recursive greedy and back-propagation learning framework. The experiments over real-world hyperspectral images demonstrated that the diversity promoting prior in both pretraining and fine-tuning procedure lead to the learned DBNs with more diverse latent factors, which directly make the diversified DBNs obtain much better results than original DBNs and comparable or even better performances compared with other recent hyperspectral image classification methods. [ABSTRACT FROM PUBLISHER]

This paper presents spiking neural networks (SNNs) for remote sensing spatiotemporal analysis of image time series, which make use of the highly parallel and low-power-consuming neuromorphic hardware platforms possible. This paper illustrates this concept with the introduction of the first SNN computational model for crop yield estimation from normalized difference vegetation index image time series. It presents the development and testing of a methodological framework which utilizes the spatial accumulation of time series of Moderate Resolution Imaging Spectroradiometer 250-m resolution data and historical crop yield data to train an SNN to make timely prediction of crop yield. The research work also includes an analysis on the optimum number of features needed to optimize the results from our experimental data set. The proposed approach was applied to estimate the winter wheat (Triticum aestivum L.) yield in Shandong province, one of the main winter-wheat-growing regions of China. Our method was able to predict the yield around six weeks before harvest with a very high accuracy. Our methodology provided an average accuracy of 95.64%, with an average error of prediction of 0.236 t/ha and correlation coefficient of 0.801 based on a nine-feature model. [ABSTRACT FROM PUBLISHER]

Hyperspectral image (HSI) classification has become a hot topic in the field of remote sensing. In general, the complex characteristics of hyperspectral data make the accurate classification of such data challenging for traditional machine learning methods. In addition, hyperspectral imaging often deals with an inherently nonlinear relation between the captured spectral information and the corresponding materials. In recent years, deep learning has been recognized as a powerful feature-extraction tool to effectively address nonlinear problems and widely used in a number of image processing tasks. Motivated by those successful applications, deep learning has also been introduced to classify HSIs and demonstrated good performance. This survey paper presents a systematic review of deep learning-based HSI classification literatures and compares several strategies for this topic. Specifically, we first summarize the main challenges of HSI classification which cannot be effectively overcome by traditional machine learning methods, and also introduce the advantages of deep learning to handle these problems. Then, we build a framework that divides the corresponding works into spectral-feature networks, spatial-feature networks, and spectral–spatial-feature networks to systematically review the recent achievements in deep learning-based HSI classification. In addition, considering the fact that available training samples in the remote sensing field are usually very limited and training deep networks require a large number of samples, we include some strategies to improve classification performance, which can provide some guidelines for future studies on this topic. Finally, several representative deep learning-based classification methods are conducted on real HSIs in our experiments. [ABSTRACT FROM AUTHOR]

Radar-based human motion recognition is crucial for many applications, such as surveillance, search and rescue operations, smart homes, and assisted living. Continuous human motion recognition in real-living environment is necessary for practical deployment, i.e., classification of a sequence of activities transitioning one into another, rather than individual activities. In this paper, a novel dynamic range-Doppler trajectory (DRDT) method based on the frequency-modulated continuous-wave (FMCW) radar system is proposed to recognize continuous human motions with various conditions emulating real-living environment. This method can separate continuous motions and process them as single events. First, range-Doppler frames consisting of a series of range-Doppler maps are obtained from the backscattered signals. Next, the DRDT is extracted from these frames to monitor human motions in time, range, and Doppler domains in real time. Then, a peak search method is applied to locate and separate each human motion from the DRDT map. Finally, range, Doppler, radar cross section (RCS), and dispersion features are extracted and combined in a multidomain fusion approach as inputs to a machine learning classifier. This achieves accurate and robust recognition even in various conditions of distance, view angle, direction, and individual diversity. Extensive experiments have been conducted to show its feasibility and superiority by obtaining an average accuracy of 91.9% on continuous classification. [ABSTRACT FROM AUTHOR]

Craters are dominant geomorphological features on the surfaces of the moon, Mars, and other planets. The distribution of craters provides valuable information on the planetary surface geology. Machine learning is a widely used approach to detect craters on planetary surface data. A critical step in machine learning is the determination of training samples. In previous studies, the training samples were mainly selected manually, which usually leads to insufficient numbers due to the high cost and unfavorable quality. Surface imagery and digital elevation models (DEMs) are now commonly available for planetary surfaces; this offers new opportunities for crater detection with better performance. This paper presents a novel active machine learning approach, in which the imagery and DEMs covering the same region are used for collecting training samples with more automation and better performance. In the training process, the approach actively asks for annotations for the 2-D features derived from imagery with inputs from 3-D features derived from the DEMs. Thus, the training pool can be updated accordingly, and the model can be retrained. This process can be conducted several times to obtain training samples in sufficient number and of favorable quality, from which a classifier with better performance can be generated, and it can then be used for automatic crater detection in other regions. The proposed approach highlights two advantages: 1) automatic generation of a large number of high-quality training samples and 2) prioritization of training samples near the classification boundary so as to learn more quickly. Two sets of test data on the moon and Mars were used for the experimental validation. The performance of the proposed approach was superior to that of a regular machine learning method. [ABSTRACT FROM AUTHOR]

Turbulence has been one of the major concerns for aviation safety. This paper applies evolutionary machine learning (ML) technology to turbulence level classification for civil aviation. An artificial neural network ML approach based on radar observation is developed for classifying the cubed root of the Eddy Dissipation Rate (EDR)1/3, an accepted measure of turbulence intensity. The approach is validated using Typhoon weather data collected by Hong Kong Observatory’s Terminal Doppler Weather Radar (TDWR) located near Hong Kong International Airport and comparing TDWR EDR1/3 detections and predictions with in situ EDR1/3 measured by commercial aircraft. The testing results verified that the ML approach performs reasonably well for both detecting and predicting tasks. [ABSTRACT FROM AUTHOR]

This paper implements a novel approach to automatically detect and classify rockfalls in Lunar Reconnaissance Orbiter narrow angle camera (NAC) images using a single-stage dense object detector (RetinaNet). The convolutional neural network has been trained with a data set of 2932 original rockfall images. In order to avoid overfitting, the initial training data set has been augmented during training using random image rotation, scaling, and flipping. Testing images have been labelled by human operators and have been used for RetinaNet performance evaluation. Testing shows that RetinaNet is capable to reach recall values between 0.98 and 0.39, precision values between 1 and 0.25, and average precisions ranging from 0.89 to 0.69, depending on the used confidence threshold and intersection-over-union values. Mean processing time of a single NAC image in RetinaNet is around 10 s using a GeForce GTX 1080 Ti and GeForce Titan Xp, which is in orders of magnitudes faster than a human operator. The processing speed allows to efficiently exploit the currently available NAC data stack with more than 1 million images in a reasonable timeframe. The combination of speed and detection performance can be used to produce lunar rockfall distribution maps on large spatial scales for utilization by the scientific and engineering community. [ABSTRACT FROM AUTHOR]

While the analysis of airborne laser scanning (ALS) data often provides reliable estimates for certain forest stand attributes-such as total volume or basal area-there is still room for improvement, especially in estimating species-specific attributes. Moreover, while the information on the estimate uncertainty would be useful in various economic and environmental analyses on forests, a computationally feasible framework for uncertainty quantifying in ALS is still missing. In this paper, the species-specific stand attribute estimation and uncertainty quantification (UQ) is approached using Gaussian process regression (GPR), which is a nonlinear and nonparametric machine learning method. Multiple species-specific stand attributes are estimated simultaneously: tree height, stem diameter, stem number, basal area, and stem volume. The cross-validation results show that GPR yields on average an improvement of 4.6% in estimate root mean square error over a state-of-the-art $k$ -nearest neighbors (kNNs) implementation, negligible bias and well performing UQ (credible intervals), while being computationally fast. The performance advantage over kNN and the feasibility of credible intervals persists even when smaller training sets are used. [ABSTRACT FROM AUTHOR]

Despite the availability of an increasing amount of remote sensing images, problems still arise in that the knowledge from existing images is underutilized and the collection of reference knowledge for each newly obtained image is expensive. Recently, an attractive solution called “transfer learning” has received increasing attention in the remote sensing field, by transferring knowledge from source domains to help improve the learning procedure in the target domain. In this paper, we propose a sparse subspace correlation analysis-based supervised classification (SSCA-SC) method for transfer learning in hyperspectral remote sensing image classification, which is not restricted by the data dimensionality or the data acquisition sensors. Specifically, we first propose a sparse subspace correlation analysis (SSCA) method to simultaneously learn the optimal projection matrices for heterogeneous domains into a common subspace and obtain sparse reconstruction coefficients over a shared self-expressive dictionary in the derived subspace. In order to fully utilize the label information to improve the class separability, the SSCA-SC framework learns more discriminative representations for the input data by training a corresponding SSCA model for each class. As a result, the projected data belonging to the same class are maximally correlated and represented well, while those from different classes will have a low correlation. Another advantage of the SSCA-SC framework lies in the fact that it not only learns new representations for the data from different domains but it also designs a discriminative and robust classifier that properly adapts to the new representation. The proposed method was tested with three hyperspectral remote sensing data sets, and the experimental results confirm the effectiveness and reliability of the proposed SSCA-SC method. [ABSTRACT FROM AUTHOR]

High-spectral resolution imaging systems play a critical role in the identification and characterization of objects in a scene of interest. Unfortunately, multiple factors impair spectral resolution, as in the case of modern snapshot spectral imagers that associate each hyperpixel with a specific spectral band. In this paper, we introduce a novel postacquisition computational technique aiming to enhance the spectral dimensionality of imaging systems by exploiting the mathematical frameworks of sparse representations and dictionary learning. We propose a coupled dictionary learning model which considers joint feature spaces, composed of low- and high-spectral resolution hypercubes, in order to achieve spectral superresolution performance. We formulate our spectral coupled dictionary learning optimization problem within the context of the alternating direction method of multipliers, and we manage to update the involved quantities via closed-form expressions. In addition, we consider a realistic spectral subsampling scenario, taking into account the spectral response functions of different satellites. Moreover, we apply our spectral superresolution algorithm on real satellite data acquired by Landsat-8 and Sentinel-2 sensors. Finally, we have investigated the problem of hyperspectral image unmixing using the recovered high-spectral resolution data cube, and we are able to demonstrate that the proposed scheme provides significant value in hyperspectral image understanding techniques. Experimental results demonstrate the ability of the proposed approach to synthesize high-spectral-resolution 3-D hypercubes, achieving better performance compared to state-of-the-art resolution enhancement methods. [ABSTRACT FROM AUTHOR]

Simultaneous-source acquisition, breaking the limit of conventional seismic acquisition, is a rapidly evolving research field, due to its advantage in reducing survey time and improving data quality. The benefits of simultaneous-source acquisition are compromised by the intense blending interference. Separating a blended record into a group of individual records, known as “deblending” is one of the most popular solution to the problem. However, the blended records are often corrupted by random noise, which causes difficulties in separation. In an iterative deblending algorithm, the incoherent interference can be simulated and subtracted from the blended record. When the random noise is strong, it is difficult to simulate the incoherent interference. In this paper, we propose a hybrid-sparsity constraint model that applies the dictionary learning into the deblending framework that is based on the sparsity-promoting transform to deal with extremely noisy simultaneous source data. The dictionary learning with fine-tuned adaptation can learn the incoherent interference into atoms and reject random noise. Then, the sparse transform-based framework is implemented to iteratively separate the signal and interference. We use two synthetic examples to demonstrate the advantage of the proposed method in extremely noisy situations. Two field examples further confirm the superior deblending performance of the proposed method for the noisy simultaneous-source data over the curvelet transform-based and rank reduction-based methods. [ABSTRACT FROM AUTHOR]

This paper presents a statistical detection theory approach to hyperspectral image (HSI) classification which is quite different from many conventional approaches reported in the HSI classification literature. It translates a multi-target detection problem into a multi-class classification problem so that the well-established statistical detection theory can be readily applicable to solving classification problems. In particular, two types of classification, a priori classification and a posteriori classification, are developed in corresponding to Bayes detection and maximum a posteriori (MAP) detection, respectively, in detection theory. As a result, detection probability and false alarm probability can also be translated to classification rate and false classification rate derived from a confusion classification matrix used for classification. To evaluate the effectiveness of a posteriori classification, a new a posteriori classification measure, to be called precision rate (PR), is also introduced by MAP classification in contrast to overall accuracy (OA) that can be considered as a priori classification measure and has been used for Bayes classification. The experimental results provide evidence that a priori classifier as Bayes classifier which performs well in terms of OA does not necessarily perform well as a posteriori classifier in terms of PR. That is, PR is the only criterion that can be used as a posteriori classification measure to evaluate how well a classifier performs. [ABSTRACT FROM AUTHOR]

In this paper, we propose a new anomaly detection method for hyperspectral images based on two well-designed dictionaries: background dictionary and potential anomaly dictionary. In order to effectively detect an anomaly and eliminate the influence of noise, the original image is decomposed into three components: background, anomalies, and noise. In this way, the anomaly detection task is regarded as a problem of matrix decomposition. Considering the homogeneity of background and the sparsity of anomalies, the low-rank and sparse constraints are imposed in our model. Then, the background and potential anomaly dictionaries are constructed using the background and anomaly priors. For the background dictionary, a joint sparse representation (JSR)-based dictionary selection strategy is proposed, assuming that the frequently used atoms in the overcomplete dictionary tend to be the background. In order to make full use of the prior information of anomalies hidden in the scene, the potential anomaly dictionary is constructed. We define a criterion, i.e., the anomalous level of a pixel, by using the residual calculated in the JSR model within its local region. Then, it is combined with a weighted term to alleviate the influence of noise and background. Experiments show that our proposed anomaly detection method based on potential anomaly and background dictionaries construction can achieve superior results compared with other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) have recently exhibited an excellent performance in hyperspectral image classification tasks. However, the straightforward CNN-based network architecture still finds obstacles when effectively exploiting the relationships between hyperspectral imaging (HSI) features in the spectral–spatial domain, which is a key factor to deal with the high level of complexity present in remotely sensed HSI data. Despite the fact that deeper architectures try to mitigate these limitations, they also find challenges with the convergence of the network parameters, which eventually limit the classification performance under highly demanding scenarios. In this paper, we propose a new CNN architecture based on spectral–spatial capsule networks in order to achieve a highly accurate classification of HSIs while significantly reducing the network design complexity. Specifically, based on Hinton’s capsule networks, we develop a CNN model extension that redefines the concept of capsule units to become spectral–spatial units specialized in classifying remotely sensed HSI data. The proposed model is composed by several building blocks, called spectral–spatial capsules, which are able to learn HSI spectral–spatial features considering their corresponding spatial positions in the scene, their associated spectral signatures, and also their possible transformations. Our experiments, conducted using five well-known HSI data sets and several state-of-the-art classification methods, reveal that our HSI classification approach based on spectral–spatial capsules is able to provide competitive advantages in terms of both classification accuracy and computational time. [ABSTRACT FROM AUTHOR]

Polarimetric synthetic aperture radar (PolSAR) image classification plays an important role in remote sensing image processing. In recent years, stacked auto-encoder (SAE) has obtained a series of excellent results in PolSAR image classification. The recently proposed projective dictionary pair learning (DPL) model takes both accuracy and time consumption into consideration, and another recently proposed semicoupled dictionary learning (SCDL) model gives a new way to fit different features. Based on the SAE, DPL, and SCDL models, we propose a novel semicoupled projective DPL method with SAE (SAE-SDPL) for PolSAR image classification. Our method can get the classification result efficiently and correctly and meanwhile giving a new method to fit different features. In this paper, three PolSAR images are used to test the performance of SAE-SDPL. Compared with some state-of-the-art methods, our method obtains excellent results in PolSAR image classification. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel sparsity-based algorithm for anomaly detection in hyperspectral imagery. The algorithm is based on the concept that a background pixel can be approximately represented as a sparse linear combination of its spatial neighbors while an anomaly pixel cannot if the anomalies are removed from its neighborhood. To be physically meaningful, the sum-to-one and nonnegativity constraints are imposed to abundance vector based on the linear mixture model, and the upper bound constraint on sparsity level is removed for better recovery of the test pixel. First, the proposed method utilizes the redundant background information to automatically remove anomalies from the background dictionary. Then, the reconstruction error obtained by the new background dictionary is directly used for anomaly detection. Moreover, a kernel version of the proposed method is also derived to completely exploit the nonlinear feature of hyperspectral data. An important advantage of the proposed methods is their capability to adaptively model the background even when some anomaly pixels are involved. Extensive experiments have been conducted on three real hyperspectral data sets. It is demonstrated that the proposed detectors achieve a promising detection performance with a relatively low computational cost. [ABSTRACT FROM AUTHOR]

With the rapid increase of remote sensing images in temporal, spectral, and spatial resolutions, it is urgent to develop effective techniques for joint interpretation of spatial-temporal images. Multitype change detection (CD) is a significant research topic in multitemporal remote sensing image analysis, and its core is to effectively measure the difference degree and represent the difference among the multitemporal images. In this paper, we propose a novel difference representation learning (DRL) network and present an unsupervised learning framework for multitype CD task. Deep neural networks work well in representation learning but rely too much on labeled data, while clustering is a widely used classification technique free from supervision. However, the distribution of real remote sensing data is often not very friendly for clustering. To better highlight the changes and distinguish different types of changes, we combine difference measurement, DRL, and unsupervised clustering into a unified model, which can be driven to learn Gaussian-distributed and discriminative difference representations for nonchange and different types of changes. Furthermore, the proposed model is extended into an iterative framework to imitate the bottom-up aggregative clustering procedure, in which similar change types are gradually merged into the same classes. At the same time, the training samples are updated and reused to ensure that it converges to a stable solution. The experimental studies on four pairs of multispectral data sets demonstrate the effectiveness and superiority of the proposed model on multitype CD. [ABSTRACT FROM AUTHOR]

In this paper, we propose a hierarchical polarization feature generation using a self-organizing codebook to realize unsupervised land classification that fully utilizes the detailed polarization information contained in high-resolution polarimetric synthetic aperture radar (PolSAR) data. PolSAR has reached a decimeter-level high resolution. In general, conventional methods lower the resolution of the PolSAR data to 10–20 m in the real-space distance to classify observation regions into land classes such as farm, forest, and town. However, lowering resolution prevents us from discovering new land classes potentially enabled by the resolution enhancement. The hierarchical method we propose here not only classifies observation regions successfully into land classes such as farm, forest, and town that humans can naturally distinguish but also discovers new land subclasses findable only in high-resolution PolSAR data. We explain these two types of our achievements (classification/discovery) through experimental results for Japan Aerospace Exploration Agency’s polarimetric and interferometric airborne SAR-L2 data having decimeter resolution. [ABSTRACT FROM AUTHOR]

Aiming at improving the classification accuracy with limited numbers of labeled pixels in polarimetric synthetic aperture radar (PolSAR) image classification task, this paper presents a graph-based semisupervised deep learning model for PolSAR image classification. It models the PolSAR image as an undirected graph, where the nodes correspond to the labeled and unlabeled pixels, and the weighted edges represent similarities between the pixels. Upon the graph, we design an energy function incorporating a semisupervision term, a convolutional neural network (CNN) term, and a pairwise smoothness term. The employed CNN extracts abstract and data-driven polarimetric features and outputs class label predictions to the graph model. The semisupervision term enforces the category label constraints on the human-labeled pixels. The pairwise smoothness term encourages class label smoothness and the alignment of class label boundaries with the image edges. Starting from an initialized class label map generated based on $K$ -Wishart distribution hypothesis or superpixel segmentation of PauliRGB images, we iteratively and alternately optimize the defined energy function until it converges. We conducted experiments on two real benchmark PolSAR images, and extensive experiments demonstrated that our approach achieved the state-of-the-art results for PolSAR image classification. [ABSTRACT FROM AUTHOR]

In this paper, we propose a spectral-spatial feature extraction and classification framework based on an artificial neuron network in the context of hyperspectral imagery. With limited labeled samples, only spectral information is exploited for training and spatial context is integrated posteriorly at the testing stage. Taking advantage of recent advances in face recognition, a joint supervision symbol that combines softmax loss and center loss is adopted to train the proposed network, by which intraclass features are gathered while interclass variations are enlarged. Based on the learned architecture, the extracted spectrum-based features are classified by a center classifier. Moreover, to fuse the spectral and spatial information, an adaptive spectral-spatial center classifier is developed, where multiscale neighborhoods are considered simultaneously, and the final label is determined using an adaptive voting strategy. Finally, experimental results on three well-known data sets validate the effectiveness of the proposed methods compared with the state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Deep learning has recently attracted significant attention in the field of hyperspectral images (HSIs) classification. However, the construction of an efficient deep neural network mostly relies on a large number of labeled samples being available. To address this problem, this paper proposes a unified deep network, combined with active transfer learning (TL) that can be well-trained for HSIs classification using only minimally labeled training data. More specifically, deep joint spectral–spatial feature is first extracted through hierarchical stacked sparse autoencoder (SSAE) networks. Active TL is then exploited to transfer the pretrained SSAE network and the limited training samples from the source domain to the target domain, where the SSAE network is subsequently fine-tuned using the limited labeled samples selected from both source and target domains by the corresponding active learning (AL) strategies. The advantages of our proposed method are threefold: 1) the network can be effectively trained using only limited labeled samples with the help of novel AL strategies; 2) the network is flexible and scalable enough to function across various transfer situations, including cross data set and intraimage; and 3) the learned deep joint spectral–spatial feature representation is more generic and robust than many joint spectral–spatial feature representations. Extensive comparative evaluations demonstrate that our proposed method significantly outperforms many state-of-the-art approaches, including both traditional and deep network-based methods, on three popular data sets. [ABSTRACT FROM AUTHOR]

Remote sensing image scene classification is a fundamental problem, which aims to label an image with a specific semantic category automatically. Recently, deep learning methods have achieved competitive performance for remote sensing image scene classification, especially the methods based on a convolutional neural network (CNN). However, most of the existing CNN methods only use feature vectors of the last fully connected layer. They give more importance to global information and ignore local information of images. It is common that some images belong to different categories, although they own similar global features. The reason is that the category of an image may be highly related to local features, other than the global feature. To address this problem, a method based on rearranged local features is proposed in this paper. First, outputs of the last convolutional layer and the last fully connected layer are employed to depict the local and global information, respectively. After that, the remote sensing images are clustered to several collections using their global features. For each collection, local features of an image are rearranged according to their similarities with local features of the cluster center. In addition, a fusion strategy is proposed to combine global and local features for enhancing the image representation. The proposed method surpasses the state of the arts on four public and challenging data sets: UC-Merced, WHU-RS19, Sydney, and AID. [ABSTRACT FROM AUTHOR]

Satellite images are widely applied in humanitarian mapping that labels buildings, roads, and so on for humanitarian aid and economic development. However, the labeling now is mostly done by volunteers. In this paper, we utilize deep learning to solve humanitarian mapping tasks of a mobile software named MapSwipe. The current deep learning techniques, e.g., convolutional neural network (CNN), can recognize ground objects from satellite images but rely on numerous labels for training for each specific task. We solve this problem by fusing multiple freely accessible crowdsourced geographic data and propose an active learning-based CNN training framework named MC-CNN to deal with the quality issues of the labels extracted from these data, including incompleteness (e.g., some kinds of object are not labeled) and heterogeneity (e.g., different spatial granularities). The method is evaluated with building mapping in South Malawi and road mapping in Guinea with level-18 satellite images provided by Bing Map and volunteered geographic information from OpenStreetMap, MapSwipe, and OsmAnd. The results based on multiple metrics, including Precision, Recall, F1 Score, and area under the receiver operating characteristic curve, show that MC-CNN can fuse the crowdsourced labels for higher prediction performance and be successfully applied in MapSwipe for humanitarian mapping with 85% labor saved and an overall accuracy of 0.86 achieved. [ABSTRACT FROM AUTHOR]

High-spatial hyperspectral (HH) image reconstruction using both high-spatial multispectral (HM) image and low-spatial hyperspectral (LH) image over the same scene is widely used in many real applications. Nevertheless, the pair of HM image and LH image over the same scene is hard to obtain. To solve this problem, a new HH image reconstruction method using spectral library-based dictionary learning (named as HIRSL) is proposed in this paper, only from one HM image. The above reconstruction problem is formulated in the framework of sparse representation, as an estimation of the band matching matrix, the spectral dictionary, and the sparse coefficients. More specifically, a band matching method is proposed for mapping the common spectral library to a specific spectral library corresponding to the reconstructed HH image in spectral domain. Then, an efficient spectral dictionary learning method is proposed for the construction of spectral dictionary using the matched specific spectral library, which avoids the dependence of the LH image over the same scene. Finally, the sparse coefficients of the HM image with respect to the learned spectral dictionary are estimated using the alternating direction method of multipliers without nonnegative constraint. Comparison results on simulated and real data sets with the relative state-of-the-art methods demonstrate that even only using one HM image, our proposed method achieves a comparable reconstruction quality of high-spatial hyperspectral image both in spatial and spectral domains. [ABSTRACT FROM AUTHOR]

In this paper, a self-paced joint sparse representation (SPJSR) model is proposed for the classification of hyperspectral images (HSIs). It replaces the least-squares (LS) loss in the standard joint sparse representation (JSR) model with a weighted LS loss and adopts a self-paced learning (SPL) strategy to learn the weights for neighboring pixels. Rather than predefining a weight vector in the existing weighted JSR methods, both the weight and sparse representation (SR) coefficient associated with neighboring pixels are optimized by an alternating iterative strategy. According to the nature of SPL, in each iteration, neighboring pixels with nonzero weights (i.e., easy pixels) are included for the joint SR of a testing pixel. With the increase of iterations, the model size (i.e., the number of selected neighboring pixels) is enlarged and more neighboring pixels from easy to complex are gradually added into the JSR learning process. After several iterations, the algorithm can be terminated to produce a desirable model that includes easy homogeneous pixels and excludes complex inhomogeneous pixels. Experimental results on two benchmark hyperspectral data sets demonstrate that our proposed SPJSR is more accurate and robust than existing JSR methods, especially in the case of heavy noise. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) exhibit good performance in image processing tasks, pointing themselves as the current state-of-the-art of deep learning methods. However, the intrinsic complexity of remotely sensed hyperspectral images still limits the performance of many CNN models. The high dimensionality of the HSI data, together with the underlying redundancy and noise, often makes the standard CNN approaches unable to generalize discriminative spectral–spatial features. Moreover, deeper CNN architectures also find challenges when additional layers are added, which hampers the network convergence and produces low classification accuracies. In order to mitigate these issues, this paper presents a new deep CNN architecture specially designed for the HSI data. Our new model pursues to improve the spectral–spatial features uncovered by the convolutional filters of the network. Specifically, the proposed residual-based approach gradually increases the feature map dimension at all convolutional layers, grouped in pyramidal bottleneck residual blocks, in order to involve more locations as the network depth increases while balancing the workload among all units, preserving the time complexity per layer. It can be seen as a pyramid, where the deeper the blocks, the more feature maps can be extracted. Therefore, the diversity of high-level spectral–spatial attributes can be gradually increased across layers to enhance the performance of the proposed network with the HSI data. Our experiments, conducted using four well-known HSI data sets and 10 different classification techniques, reveal that our newly developed HSI pyramidal residual model is able to provide competitive advantages (in terms of both classification accuracy and computational time) over the state-of-the-art HSI classification methods [ABSTRACT FROM AUTHOR]

Hyperspectral image (HSI) classification, which aims to assign an accurate label for hyperspectral pixels, has drawn great interest in recent years. Although low-rank representation (LRR) has been used to classify HSI, its ability to segment each class from the whole HSI data has not been exploited fully yet. LRR has a good capacity to capture the underlying low-dimensional subspaces embedded in original data. However, there are still two drawbacks for LRR. First, the LRR does not consider the local geometric structure within data, which makes the local correlation among neighboring data easily ignored. Second, the representation obtained by solving LRR is not discriminative enough to separate different data. In this paper, a novel locality- and structure-regularized LRR (LSLRR) model is proposed for HSI classification. To overcome the above-mentioned limitations, we present locality constraint criterion and structure preserving strategy to improve the classical LRR. Specifically, we introduce a new distance metric, which combines both spatial and spectral features, to explore the local similarity of pixels. Thus, the global and local structures of HSI data can be exploited sufficiently. In addition, we propose a structural constraint to make the representation have a near-block-diagonal structure. This helps to determine the final classification labels directly. Extensive experiments have been conducted on three popular HSI data sets. And the experimental results demonstrate that the proposed LSLRR outperforms other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

With the large amount of high-spatial resolution images now available, scene classification aimed at obtaining high-level semantic concepts has drawn great attention. The convolutional neural networks (CNNs), which are typical deep learning methods, have widely been studied to automatically learn features for the images for scene classification. However, scene classification based on CNNs is still difficult due to the scale variation of the objects in remote sensing imagery. In this paper, a multiscale CNN (MCNN) framework is proposed to solve the problem. In MCNN, a network structure containing dual branches of a fixed-scale net (F-net) and a varied-scale net (V-net) is constructed and the parameters are shared by the F-net and V-net. The images and their rescaled images are fed into the F-net and V-net, respectively, allowing us to simultaneously train the shared network weights on multiscale images. Furthermore, to ensure that the features extracted from MCNN are scale invariant, a similarity measure layer is added to MCNN, which forces the two feature vectors extracted from the image and its corresponding rescaled image to be as close as possible in the training phase. To demonstrate the effectiveness of the proposed method, we compared the results obtained using three widely used remote sensing data sets: the UC Merced data set, the aerial image data set, and the google data set of SIRI-WHU. The results confirm that the proposed method performs significantly better than the other state-of-the-art scene classification methods. [ABSTRACT FROM AUTHOR]

In this paper, we present tensor-based linear and nonlinear models for hyperspectral data classification and analysis. By exploiting the principles of tensor algebra, we introduce new classification architectures, the weight parameters of which satisfy the rank-1 canonical decomposition property. Then, we propose learning algorithms to train both linear and nonlinear classifiers. The advantages of the proposed classification approach are that: 1) it significantly reduces the number of weight parameters required to train the model (and thus the respective number of training samples); 2) it provides a physical interpretation of model coefficients on the classification output; and 3) it retains the spatial and spectral coherency of the input samples. The linear tensor-based model exploits the principles of logistic regression, assuming the rank-1 canonical decomposition property among its weights. For the nonlinear classifier, we propose a modification of a feedforward neural network (FNN), called rank-1 FNN, since its weights satisfy again the rank-1 canonical decomposition property. An appropriate learning algorithm is also proposed to train the network. Experimental results and comparisons with state-of-the-art classification methods, either linear (e.g., linear support vector machine) or nonlinear (e.g., deep learning), indicate the outperformance of the proposed scheme, especially in the cases where a small number of training samples is available. [ABSTRACT FROM AUTHOR]

In this paper, we consider hybrid-polarimetric synthetic aperture radar (SAR) data of ocean surface slicks, and hypothesize that we can design a system that is able to discriminate between mineral oil, plant oil, and clean sea. We focus particularly on challenges related to data set shift between the training and test data. In SAR images of ocean surfaces, data set shift is typically caused by the variation of wind level and incident angles that directly impact the backscatter intensities. We evaluate several classifiers, domain adaptation strategies, and multilooking strategies. Hybrid-polarimetric SAR data are simulated from the Radarsat-2 quad-pol images. The proposed methodology was trained using five different Radarsat-2 quad-pol images that cover slicks of known types, and tested on 10 different Radarsat-2 quad-pol images covering various ocean surface slicks. The results show that we were able, to a large degree, to classify the type of various surface slicks. The average classification accuracy obtained from cross-validation on the training data was 91%. The results also show that we were able to correctly classify surface slick in new test images, even if the wind, surface, and acquisition conditions were different from the training images. We conclude that hybrid polarity is an attractive mode for future enhanced SAR-based oil spill monitoring; however, to fully exploit the imaging mode, single-look complex images are necessary. [ABSTRACT FROM AUTHOR]

Super-resolution (SR) brings an excellent opportunity to improve a wide range of different remote sensing applications. SR techniques are concerned about increasing the image resolution while providing finer spatial details than those captured by the original acquisition instrument. Therefore, SR techniques are particularly useful to cope with the increasing demand remote sensing imaging applications requiring fine spatial resolution. Even though different machine learning paradigms have been successfully applied in SR, more research is required to improve the SR process without the need of external high-resolution (HR) training examples. This paper proposes a new convolutional generator model to super-resolve low-resolution (LR) remote sensing data from an unsupervised perspective. That is, the proposed generative network is able to initially learn relationships between the LR and HR domains throughout several convolutional, downsampling, batch normalization, and activation layers. Then, the data are symmetrically projected to the target resolution while guaranteeing a reconstruction constraint over the LR input image. An experimental comparison is conducted using 12 different unsupervised SR methods over different test images. Our experiments reveal the potential of the proposed approach to improve the resolution of remote sensing imagery. [ABSTRACT FROM AUTHOR]

Hyperspectral image (HSI) classification is an active and important research task driven by many practical applications. To leverage deep learning models especially convolutional neural networks (CNNs) for HSI classification, this paper proposes a simple yet effective method to extract hierarchical deep spatial feature for HSI classification by exploring the power of off-the-shelf CNN models, without any additional retraining or fine-tuning on the target data set. To obtain better classification accuracy, we further propose a unified metric learning-based framework to alternately learn discriminative spectral–spatial features, which have better representation capability and train support vector machine (SVM) classifiers. To this end, we design a new objective function that explicitly embeds a metric learning regularization term into SVM training. The metric learning regularization term is used to learn a powerful spectral–spatial feature representation by fusing spectral feature and deep spatial feature, which has small intraclass scatter but big between class separation. By transforming HSI data into new spectral–spatial feature space through CNN and metric learning, we can pull the pixels from the same class closer, while pushing the different class pixels farther away. In the experiments, we comprehensively evaluate the proposed method on three commonly used HSI benchmark data sets. State-of-the-art results are achieved when compared with the existing HSI classification methods. [ABSTRACT FROM AUTHOR]