IEEE Geoscience and Remote Sensing Letters

Deep learning (DL) is a powerful state-of-the-art technique for image processing including remote sensing (RS) images. This letter describes a multilevel DL architecture that targets land cover and crop type classification from multitemporal multisource satellite imagery. The pillars of the architecture are unsupervised neural network (NN) that is used for optical imagery segmentation and missing ... View full abstract»

In this letter, we propose a pseudo-siamese convolutional neural network architecture that enables to solve the task of identifying corresponding patches in very high-resolution optical and synthetic aperture radar (SAR) remote sensing imagery. Using eight convolutional layers each in two parallel network streams, a fully connected layer for the fusion of the features learned in each stream, and a... View full abstract»

Random Forests variable importance measures are often used to rank variables by their relevance to a classification problem and subsequently reduce the number of model inputs in high-dimensional data sets, thus increasing computational efficiency. However, as a result of the way that training data and predictor variables are randomly selected for use in constructing each tree and splitting each no... View full abstract»

With the popular use of high-resolution satellite images, more and more research efforts have been placed on remote sensing scene classification/recognition. In scene classification, effective feature selection can significantly boost the final performance. In this letter, a novel deep-learning-based feature-selection method is proposed, which formulates the feature-selection problem as a feature ... View full abstract»

Detecting small objects such as vehicles in satellite images is a difficult problem. Many features (such as histogram of oriented gradient, local binary pattern, scale-invariant feature transform, etc.) have been used to improve the performance of object detection, but mostly in simple environments such as those on roads. Kembhavi et al. proposed that no satisfactory accuracy has been achieved in ... View full abstract»

This letter presents a new algorithm that allows the retrieval of the aerosol optical depth (AOD) at a high (500 m) spatial resolution from Landsat 8 Operational Land Imager (OLI) data over urban areas. Because of the complex structure over urban surfaces, the bidirectional reflectance characteristic is obvious; however, most of the current aerosol retrieval algorithms over land do not account for... View full abstract»

Many methods have been proposed to improve the performance of synthetic aperture radar (SAR) target recognition but seldom consider the issues in real-world recognition systems, such as the invariance under target translation, the invariance under speckle variation in different observations, and the tolerance of pose missing in training data. In this letter, we investigate the capability of a deep... View full abstract»

We propose the use of deep convolutional neural networks (DCNNs) for human detection and activity classification based on Doppler radar. Previously, proposed schemes for these problems remained in the conventional supervised learning paradigm that relies on the design of handcrafted features. Whereas these schemes attained high accuracy, the requirement for domain knowledge of each problem limits ... View full abstract»

In this letter, we present a new approach for object classification in continuously streamed Lidar point clouds collected from urban areas. The input of our framework is raw 3-D point cloud sequences captured by a Velodyne HDL-64 Lidar, and we aim to extract all vehicles and pedestrians in the neighborhood of the moving sensor. We propose a complete pipeline developed especially for distinguishing... View full abstract»

Remote sensing image retrieval (RSIR) is a fundamental task in remote sensing. Most content-based RSIR approaches take a simple distance as similarity criteria. A retrieval method based on weighted distance and basic features of convolutional neural network (CNN) is proposed in this letter. The method contains two stages. First, in offline stage, the pretrained CNN is fine-tuned by some labeled im... View full abstract»

For synthetic aperture radar (SAR) image land cover classification, traditional feature-based methods are not always effective because of the heavy multiplicative noise. To solve this problem, we herein propose a new classification method for SAR images considering adaptive spatial contextual information. In contrast to preceding studies, the spatial contextual information of the SAR images is exp... View full abstract»

Deep convolutional neural networks (DCNNs) have recently emerged as a dominant paradigm for machine learning in a variety of domains. However, acquiring a suitably large data set for training DCNN is often a significant challenge. This is a major issue in the remote sensing domain, where we have extremely large collections of satellite and aerial imagery, but lack the rich label information that i... View full abstract»

The detection of failures (DF) in coffee crops is fundamental in evaluating product quality and the optimal occupation of planted areas. The use of unmanned aerial vehicles (UAVs) in precision agriculture has great potential as a tool to analyze critical parameters in cultivation, among them the detection of planting failures. This letter presents a novel methodology for DF from aerial images, obt... View full abstract»

Road extraction from aerial images has been a hot research topic in the field of remote sensing image analysis. In this letter, a semantic segmentation neural network, which combines the strengths of residual learning and U-Net, is proposed for road area extraction. The network is built with residual units and has similar architecture to that of U-Net. The benefits of this model are twofold: first... View full abstract»

Deep convolutional neural networks have achieved great success in computer vision and many other areas. They automatically extract translational-invariant spatial features and integrate with neural network-based classifier. This letter investigates the suitability and potential of deep convolutional neural network in supervised classification of polarimetric synthetic aperture radar (POLSAR) image... View full abstract»

Polarimetric synthetic aperture radar (PolSAR) image classification is an important application. Advanced deep learning techniques represented by deep convolutional neural network (CNN) have been utilized to enhance the classification performance. One current challenge is how to adapt deep CNN classifier for PolSAR classification with limited training samples, while keeping good generalization per... View full abstract»

Synthetic aperture radar (SAR) image classification is a hot topic in the interpretation of SAR images. However, the absence of effective feature representation and the presence of speckle noise in SAR images make classification difficult to handle. In order to overcome these problems, a deep convolutional autoencoder (DCAE) is proposed to extract features and conduct classification automatically.... View full abstract»

We solve the problem of scene recognition from very high-resolution optical satellite remote sensing (RS) images by exploring the notion of mid-level feature mining. The existing mid-level feature extraction techniques are based on applying feature encodings over a set of discriminatively selected localized feature descriptors from the images. Such techniques inherently suffer from two shortcoming... View full abstract»

We consider the tensor-based spectral-spatial feature extraction problem for hyperspectral image classification. First, a tensor framework based on circular convolution is proposed. Based on this framework, we extend the traditional principal component analysis (PCA) to its tensorial version tensor PCA (TPCA), which is applied to the spectral-spatial features of hyperspectral image data. The exper... View full abstract»

We are witnessing daily acquisition of large amounts of aerial and satellite imagery. Analysis of such large quantities of data can be helpful for many practical applications. In this letter, we present an automatic content-based analysis of aerial imagery in order to detect and mark arbitrary objects or regions in high-resolution images. For that purpose, we proposed a method for automatic object... View full abstract»

Because the collection of ground-truth labels is difficult, expensive, and time-consuming, classifying hyperspectral images (HSIs) with few training samples is a challenging problem. In this letter, we propose a novel semisupervised algorithm for the classification of hyperspectral data by training a customized generative adversarial network (GAN) for hyperspectral data. The GAN constructs an adve... View full abstract»

In this letter, different from traditional methods using original spectral features or handcraft spectral-spatial features, we propose to adaptively learn a suitable feature representation from unlabeled data. This is achieved by learning a feature mapping function based on stacked sparse autoencoder. Considering that hyperspectral imagery (HSI) is intrinsically defined in both the spectral and sp... View full abstract»

In this letter, a novel anomaly detection framework with transferred deep convolutional neural network (CNN) is proposed. The framework is designed by considering the following facts: 1) a reference data with labeled samples are utilized, because no prior information is available about the image scene for anomaly detection and 2) pixel pairs are generated to enlarge the sample size, since the adva... View full abstract»

Remote sensing image fusion has a potential spectral distortion problem due to the global/local spectral and spatial correlations between panchromatic (PAN) and multispectral (MS) images. To overcome this problem, in this letter, a compensation details-based injection (CDI) fusion model is presented from a new perspective of compensatory learning. In contrast to the traditional method, the two cat... View full abstract»

Deep learning methods such as convolutional neural networks (CNNs) can deliver highly accurate classification results when provided with large enough data sets and respective labels. However, using CNNs along with limited labeled data can be problematic, as this leads to extensive overfitting. In this letter, we propose a novel method by considering a pretrained CNN designed for tackling an entire... View full abstract»

In this letter, multisource earth observation (EO) data sets, including multitemporal Landsat-8, digital surface model, and spatial information, were integrated for land-cover classification by random forest (RF) and support vector machines (SVMs). We demonstrated in this letter that both RF and SVM are useful tools for classification of land cover in the local climate zones featured with highly h... View full abstract»

Infrared (IR) small target detection with high detection rate, low false alarm rate, and high detection speed has a significant value, but it is usually very difficult since the small targets are usually very dim and may be easily drowned in different types of interferences. Current algorithms cannot effectively enhance real targets and suppress all the types of interferences simultaneously. In th... View full abstract»

Cloud and cloud shadow detection in remote sensing imagery is important for its wide range of applications. Traditionally, the detection is usually based on the manually designed thresholds from multiband, which is complicated and of multistage. To simplify the process of cloud and cloud shadow detection and improve the performance, we propose a multilevel feature fused segmentation network (MFFSN... View full abstract»

Ship detection is a challenging problem in complex optical remote-sensing images. In this letter, an effective ship detection framework in remote-sensing images based on the convolutional neural network is proposed. The framework is designed to predict bounding box of ship with orientation angle information. Note that the angle information which is added to bounding box regression makes bounding b... View full abstract»

We propose a drone classification method based on convolutional neural network (CNN) and micro-Doppler signature (MDS). The MDS only presents Doppler information in time domain. The frequency domain representation of MDS is called as cadence-velocity diagram (CVD). To analyze the Doppler information of drone in time and frequency domain, we propose a new image by merging MDS and CVD, as merged Dop... View full abstract»

Most applications of frequency-modulated continuous-wave radar described in the literature involve targets that are in relatively close proximity to the radar. In these cases, the round-trip travel time of the target's radar signature is small relative to the transmit chirp duration, simplifying the processing required for range and velocity extraction. This is not the case for more distant target... View full abstract»

In this letter, we propose a novel supervised change detection method based on a deep siamese convolutional network for optical aerial images. We train a siamese convolutional network using the weighted contrastive loss. The novelty of the method is that the siamese network is learned to extract features directly from the image pairs. Compared with hand-crafted features used by the conventional ch... View full abstract»

Recently, approaches based on fully convolutional networks (FCN) have achieved state-of-the-art performance in the semantic segmentation of very high resolution (VHR) remotely sensed images. One central issue in this method is the loss of detailed information due to downsampling operations in FCN. To solve this problem, we introduce the maximum fusion strategy that effectively combines semantic in... View full abstract»

Accurate and fast infrared (IR) foreground object detection is one of the most significant issues to be solved due to its important meaning for IR target recognition, IR precise guidance, IR video surveillance, and so on. A common approach for such tasks is “background subtraction,” which aims to detect foreground object through background modeling. Thus far, many background subtraction methods ha... View full abstract»

With the development of deep learning, supervised learning has frequently been adopted to classify remotely sensed images using convolutional networks. However, due to the limited amount of labeled data available, supervised learning is often difficult to carry out. Therefore, we proposed an unsupervised model called multiple-layer feature-matching generative adversarial networks (MARTA GANs) to l... View full abstract»

Land cover classification using polarimetric synthetic aperture radar (PolSAR) images is an important tool for remote sensing analysis. In view that PolSAR image effective interpretation is commonly affected by the absence of discriminative features and the presence of speckle noises, this letter proposes an adaptive nonlocal stacked sparse autoencoder (ANSSAE) to achieve PolSAR image classificati... View full abstract»

Synthetic aperture radar (SAR) is one of the most widely employed remote sensing modalities for large-scale monitoring of maritime activity. Ship detection in SAR images is a challenging task due to inherent speckle, discernible sea clutter, and the little exploitable shape information the targets present. Constant false alarm rate (CFAR) detectors, utilizing various sea clutter statistical models... View full abstract»

Convolutional neural network obtains remarkable achievements on target detection, due to its prominent capability on feature extraction. However, it still needs further study for aircraft detection task, since intraclass variation still restricts the accuracy of aircraft detection in remote sensing images. In this letter, we adopt regularity of aircraft circle response to design our end-to-end ful... View full abstract»

The scale-invariant feature transform algorithm and its many variants are widely used in feature-based remote sensing image registration. However, it may be difficult to find enough correct correspondences for remote image pairs in some cases that exhibit a significant difference in intensity mapping. In this letter, a new gradient definition is introduced to overcome the difference of image inten... View full abstract»

In this letter, we propose a novel technique for unsupervised change detection in multitemporal satellite images using principal component analysis (PCA) and k-means clustering. The difference image is partitioned into h times h nonoverlapping blocks. S, S les h2, orthonormal eigenvectors are extracted through PCA of h times h nonoverlapping block set to create an eigenvector space. Eac... View full abstract»

A new feature selection approach that is based on the integration of a genetic algorithm and particle swarm optimization is proposed. The overall accuracy of a support vector machine classifier on validation samples is used as a fitness value. The new approach is carried out on the well-known Indian Pines hyperspectral data set. Results confirm that the new approach is able to automatically select... View full abstract»

In recent years, deep learning-based methods, especially convolutional neural networks (CNNs), have shown their capabilities in remote sensing data processing. The efficacy of light detection and ranging (LiDAR) has been already proven in a wide variety of research areas. Most of the existing methods do not extract the informative features from LiDAR-derived rasterized digital surface models (LiDA... View full abstract»

A framework for image visibility restoration and haze removal is proposed. The proposed technique utilizes hybrid median filtering in conjunction with accelerated local Laplacian filtering for initial dehazing of images. For visual enhancement and correct restoration of colors, constrained l₀-based gradient image decomposition is applied. The proposed technique not only effe... View full abstract»

High-frequency (HF) radars have great potential for maritime surveillance, and the multiple signal classification (MUSIC) algorithm is usually used to estimate the direction of arrival (DOA) of targets for a wide-beam radar. However, the performance of the MUSIC algorithm relies on the precision of the antenna pattern, which could be contaminated by nearby electromagnetic interference. Therefore, ... View full abstract»

In this letter, a binary descriptor-based approach is proposed to provide change detection in bitemporal optical satellite images. Multitemporal satellite images suffer from illumination variation. In order to tackle this problem, a variant of a local binary similarity pattern (LBSP) descriptor, which has a good resistance to illumination variation, is proposed. The proposed technique consists of ... View full abstract»

Through-the-wall radar imaging is a research area which has gathered renewed interest with the development of powerful millimeter-wave sources and detectors. Imaging techniques that require some sort of reconstruction can suffer from slow speeds and lack of complexity in the data acquisition phase of the measurements. These reconstruction methods can be greatly improved using compressive sensing (... View full abstract»

Radio frequency interference (RFI) is a common source of interference for high-frequency surface wave radar (HFSWR) since the HF band is shared among many radio services. The existence of RFI greatly degrades the detection performance of HFSWR. On the basis of a detailed analysis of the characteristics of RFI, a new RFI mitigation method based on joint fractional Fourier transform (FRFT) and compl... View full abstract»

The importance of land surface temperature (LST) retrieved from high to medium spatial resolution remote sensing data for many environmental studies, particularly the applications related to water resources management over agricultural sites, was a key factor for the final decision of including a thermal infrared (TIR) instrument on board the Landsat Data Continuity Mission or Landsat-8. This new ... View full abstract»

A deep neural network (DNN)-based new pansharpening method for the remote sensing image fusion problem is proposed in this letter. Research on representation learning suggests that the DNN can effectively model complex relationships between variables via the composition of several levels of nonlinearity. Inspired by this observation, a modified sparse denoising autoencoder (MSDA) algorithm is prop... View full abstract»

In this letter, we propose two methods for personnel recognition and gait classification using deep convolutional neural networks (DCNNs) based on multistatic radar micro-Doppler signatures. Previous DCNN-based schemes have mainly focused on monostatic scenarios, whereas directional diversity offered by multistatic radar is exploited in this letter to improve classification accuracy. We first prop... View full abstract»