Multi-source image fusion combines infrared and visible information to improve scene perception in applications such as drone reconnaissance and autonomous driving. However, most existing infrared-visible image fusion methods are developed under ideal imaging assumptions. In adverse environments, visible images often lose structural and textural details, whereas infrared images are affected by noise, stripe artifacts, and low contrast, leading to degraded fusion quality and weakened downstream perception performance. To address these limitations, we propose a unified Degradation-aware Restoration and Detail-preserving Fusion Network (DRDFNet), which consists of a Degradation-Aware Restoration Transformer and a Detail-Preserving Fusion Mamba. The restoration branch uses a Compound Degradation Restoration Module (CDRM) to remove complex degradations, while the fusion branch employs a Dynamic Feature Fusion Module (DFFM) to integrate local complementary cues and global correlations across modalities. A two-stage training strategy is further introduced to reduce the optimization conflict between restoration and fusion. In addition, we construct DIVIF, a large-scale degraded IVIF benchmark generated by a physics-based imaging simulator. Experiments on the DIVIF and AWMM-100k benchmarks demonstrate that DRDFNet achieves robust and competitive performance compared with SOTA methods. Both the dataset and source code will be made publicly available at https://github.com/Liupeng97/DRDFNet.

Global Navigation Satellite System (GNSS) positioning is widely used in various applications, but its positioning accuracy is often compromised by Non-Line-of-Sight (NLOS) signals, particularly in urban environments. To address this challenge, we conduct a physical analysis to construct features that reflect NLOS signals. Based on this, we propose a hybrid architecture that integrates Transformer-based self-attention mechanisms with a Mixture-of-Experts (MoE) framework, referred to as TransMoE, for NLOS signal detection. Additionally, to enhance the interpretability of TransMoE, we assign each feature with learnable parameters that dynamically update their weights. Furthermore, we propose an adaptive NLOS weighting algorithm that prioritizes satellites with favorable geometric distributions while mitigating NLOS-contaminated measurements in positioning solutions. Experimental validation on Hong Kong UrbanNav datasets demonstrates that TransMoE achieves consistent detection accuracy exceeding 90% across varying urban canyon scenarios. When integrated into positioning workflows, the adaptive correction algorithm reduces 2D positioning errors by 42.73%, 27.43%, and 40.68% compared to the conventional weighted least squares method.

Pixel-level classification of remote sensing images is a fundamental task in Earth science-related research. However, current automated models inevitably produce some segmentation errors. In practical applications, manual review and correction are often required. To address the inevitable segmentation errors in automated remote sensing image segmentation, this letter proposes a remote sensing segmentation correction model. This model is based on the segment anything (SAM) model and requires training only a small number of parameters to enable the model to perceive click prompt. The model consists of two main components: one part is responsible for automated segmentation and the other part is dedicated to refine the results of the automated segmentation. Considering that click-based correction is difficult to learn during training, we designed a two-stage training process for the network. Through experiments on two widely used datasets, it was found that the proposed remote sensing image correction network significantly improves mIOU after incorporating the correction process. After applying fewer than six corrective clicks per category, the mIOU is improved by 12.99% in ISPRS Vaihingen dataset and 6.93% in ISPRS Postam dataset.

Pixel-level annotation tasks are important in the intelligent processing of remote sensing images. For these tasks, Interactive Image Segmentation (IIS) models using click prompts are developing fast in the field of natural images. However, most interactive segmentation models using click prompts are unsuitable for remote sensing images with their current design of click prompts and their interaction schemes with image information. Based on the situation, we used a DETR-like model as the basic framework and redesigned the pixel decoder and the transformer decoder to better suit the task of IIS for remote sensing images. In the pixel decoder, we designed a click prompt with feature encoding to learn click information and a composite attention structure to facilitate interaction between click and image information, allowing the image feature at the click locations to more easily dominate annotation masks. In the transformer decoder, we utilized deformable attention, using only a single initialized query to obtain annotation masks and IoU prediction. In this paper, we trained our model on a composite remote sensing dataset and evaluated its performance on external datasets. The results showcased the model’s adaptability, achieving superior performance compared to existing methods. The code will be available at https://github.com/songbingze/ClickPromptRSIIS.

Infrared small-target detection (IRSTD) is a critical, yet challenging task with significant applications in both military and civilian domains. Despite advancements in existing methods, two major limitations remain: the difficulty of achieving an optimal balance between detection probability and false alarm rate, and the lack of specialized datasets for air-to-ground scenarios. To address these limitations, this article presents a dual-pronged solution. At the algorithmic level, we propose a novel dual-branch attention-guided and bi-directional feature enhancement network (DABF-Net). First, we design a dual-branch high-low frequency attention (DHLA), which enhances the discriminability between the target and the background by preserving high-frequency edge features and modeling low-frequency contextual information in a complementary manner. Subsequently, we construct a bi-directional fusion module (BFM) to optimize multiscale feature compatibility while suppressing redundant information propagation. Furthermore, we introduce a small-target feature enhancement branch (STEB) employing space-to-depth (SPD) convolution and a feature integration module (FIM) to amplify latent target signatures through exponentially expanding receptive fields. At the data level, we contribute the NCHU-A2G-SIRST benchmark, the first comprehensive dataset specifically designed for the air-to-ground IRSTD task. The dataset contains four different scenes with two types of annotations, enabling evaluation and training of detection models in real-world conditions. Extensive experiments on several challenging datasets, including the self-built NCHU-A2G-SIRST dataset and three public datasets (NCHU-SIRST, NUAA-SIRST, and IRSTD-1K), demonstrate that the DABF-Net can outperform many state-of-the-art competing methods. The code and dataset are publicly available athttps://github.com/PCwenyue/DABF-Net

Numerous studies have been conducted on missing data recovery in remote sensing images, such as cloud removal and dead pixels restoration. Nevertheless, reconstructing continuous, extensive, and complete missing areas still poses a significant challenge. In this letter, we propose a new architecture named Extend-generative adversarial network (GAN), which leverages only a low-resolution image with relaxed requirements on spatial resolution and acquisition time as a condition to reconstruct a high-resolution image with large-scale missing areas. We equip Extend-GAN with learnable adaptive region normalization (LARN) to adjust the intensity distribution of pixels to reduce color distortion. We also introduce a new loss function into the training process of Extend-GAN, namely the structural similarity (SSIM)-based triplet loss, which helps to preserve the between missing parts and known regions. Gaofen-2 and Landsat-9 image pairs are used to validate the proposed method. Extend-GAN performs better when comprehensively evaluated on visual effect, quantitative metrics, processing speed, etc. Code is available athttps://github.com/yc-cui/Extend-GAN.

Nighttime light (NTL) remote sensing images record various light information. However, it is often difficult for NTL remote sensing images to have both high temporal and high spatial resolution. To solve the above problem, this letter proposes a spatiotemporal fusion model for NTL images. Based on the convolutional neural network (CNN), we designed a new multivariate activation function and introduced adaptive instance normalization (AdaIN) to improve the quality of image fusion. Specifically, this multivariate activation function captures the abrupt changes from reference time to target time, removes redundant information, and retains complementary information. Meanwhile, the AdaIN effectively reduces the systematic errors caused by different sensors. To verify the effectiveness of the model, this letter uses Luojia1-01 and VNP46A1 remote sensing images to construct an NTL remote sensing dataset for fusion and carry out comparative experiments and ablation experiments. The results show that our method has a better performance.

Pansharpening requires the fusion of a low-spatial-resolution multispectral (LRMS) image and a panchromatic (PAN) image with rich spatial details to obtain a high-spatial-resolution multispectral (HRMS) image. Recently, deep learning (DL)-based models have been proposed to tackle this problem and have made considerable progress. However, most existing methods rely on the conventional observation model, which treats LRMS as a blurred and downsampled version of HRMS. This observation model may lead to unsatisfactory performance and limited generalization ability at full-resolution evaluation, resulting in severe spectral and spatial distortion, as we observed that while DL-based models show significant improvement over traditional models on reduced-resolution evaluation, their performances deteriorate significantly at full resolution. In this article, we rethink the observation model and present a novel perspective from HRMS to LRMS and propose a pixel-wise ensembled masked autoencoder (PEMAE) to restore HRMS. Specifically, we consider LRMS as the result of pixel-wise masking on HRMS. Thus, LRMS can be seen as a natural input of a masked autoencoder. By ensembling the reconstruction results of multiple masking patterns, PEMAE obtains HRMS with both spectral information of LRMS and spatial details of PAN. In addition, we employ a linear cross-attention mechanism to replace the regular self-attention to reduce the computation to linear time complexity. Extensive experiments demonstrate that PEMAE outperforms state-of-the-art (SOTA) methods in terms of quantitative and visual performance at both reduced- and full-resolution evaluations. The codes are available athttps://github.com/yc-cui/PEMAE.

In hyperspectral image classification, a large number of labeled samples are necessary for deep network training. However, labeling of hyperspectral images is tedious, difficult, and time-consuming work. In this letter, a new active learning (AL) framework for deep networks is proposed. An auxiliary deep network for the basic learner is constructed to learn the uncertainty of unlabeled samples in the candidate data set. Both the features of the original training data and the features of the middle hidden layer of the basic learner are gathered into a fully connected network with a newly defined loss function. In order to avoid the problem of an insufficient number of samples or a large amount of computation in AL, data sampling is performed on a candidate data set, and augmentation is conducted on newly selected samples. The proposed model is evaluated on different data sets and compared with other related methods. The results show that the proposed model performs better on different data sets than other methods.

Change detection of high-resolution remote sensing images is an important task in earth observation and was extensively investigated. Recently, deep learning has shown to be very successful in plenty of remote sensing tasks. The current deep learning-based change detection method is mainly based on conventional long short-term memory (Conv-LSTM), which does not have spatial characteristics. Since change detection is a process with both spatiality and temporality, it is necessary to propose an end-to-end spatiotemporal network. To achieve this, Conv-LSTM, an extension of the Conv-LSTM structure, is introduced. Since it shares similar spatial characteristics with the convolutional layer, L-UNet, which substitutes partial convolution layers of UNet-to-Conv-LSTM and Atrous L-UNet (AL-UNet), which further using Atrous structure to multiscale spatial information is proposed. Experiments on two data sets are conducted and the proposed methods show the advantages both in quantity and quality when compared with some other methods.

Due to the limitation of technology and budget, it is often difficult for sensors of a single remote sensing satellite to have both high temporal resolution and high spatial (HTHS) resolution at the same time. In this paper, we proposed a new Multi-level Feature Fusion with Generative Adversarial Network (MLFF-GAN) for generating fusion HTHS images. MLFF-GAN mainly uses U-net-like architecture and its generator is composed of three stages: feature extraction, feature fusion, and image reconstruction. In feature extraction and reconstruction stage, the generator employs the encoding and decoding structure to extract three groups of multi-level features, which can cope with the huge difference of resolution between high-resolution images and low-resolution images. In the feature fusion stage, Adaptive Instance Normalization (AdaIN) block is designed to learn the global distribution relationship between multi-temporal images, and an attention module (AM) is used to learn the local information weights for the change of small areas. The proposed MLFF-GAN was tested on two Landsat and MODIS datasets. Some state-of-the-art algorithms are comprehensively compared with MLFF-GAN. We also carried on the ablation experiment to test the effectiveness of different sub-module in MLFF-GAN. The experiment results and ablation analysis show the better performances of the proposed method when compared with other methods. The code is available at https://github.com/songbingze/MLFF-GAN.

Due to the trade-off of temporal resolution and spatial resolution, spatiotemporal image-fusion uses existing high-spatial-low-temporal (HSLT) and high-temporal-low-spatial (HTLS) images as prior knowledge to reconstruct high-temporal-high-spatial (HTHS) images. However, some existing spatiotemporal image-fusion algorithms ignore the issue that the spatial information of HTLS images is insufficient to support the acquisition of spatial information, which leads to the unsatisfactory accuracy of the fusion result. To introduce more spatial information, the algorithm in this article uses Cycle-generative adversarial networks (GANs) to simulate the change process of two HSLT images at k-1 and k+1, and to generate some simulated images between k-1 and k+1. Then, the generated images are selected under the help of HTLS images, and the selected ones are then enhanced with wavelet transform. Finally, the image with spatial information is introduced into the Flexible Spatiotemporal DAta Fusion (FSDAF) framework to improve the performance of spatiotemporal image-fusion. Extensive experiments on two real data sets demonstrate that our proposed method outperforms current state-of-the-art spatiotemporal image-fusion methods.

Synthetic aperture radar (SAR) can provide stable data source for earth observation due to its advantages of all day and night, all-weather, and strong penetration. SAR image classification as a fundamental procedure has been proved its great value in plenty of remote sensing applications. Conventional classification algorithms mainly rely on hand-designed features, which are susceptible to widespread coherent speckle noise and geometric distortion in high-resolution SAR images. Inspired by the recent impressive success in data mining and deep learning, a greedy hierarchical convolutional neural network (GHCNN) is developed. It aims at obtaining optimized feature representation, relieving the effect of speckle noise, and promoting the local pattern recognition of geometric distortion in single-polarized SAR image classification. First, a series of convolutional autoencoders (CAEs) is trained in the greedy layer-wise unsupervised strategy. This step provides an unbiased regularizer anda prioridistribution derived from large volumes of unlabeled SAR patches. Then, to optimize multiple parameter subspaces globally, several CAEs are coupled together to form a deeper hierarchical structure in a stacked and unsupervised fashion. Afterward, a convolutional network with identical topology inherits the pretrained weights. After supervised finetuning, it realizes class prediction. Synchronously, t-distributed stochastic neighbor embedding (t-SNE) algorithm is applied to monitor the efficiency of feature representation during the training period. Experimental results demonstrate that the proposed method has competitive advantages over involved contrast methods.

In most of the existing studies on the band selection using the convolutional neural networks (CNNs), there is no exact explanation of how feature learning helps to find the important bands. In this letter, a CNN-based band selection method is presented, and the process of feature tracing is explained in detail. First, a 1-D CNN model is designed and trained to reach high accuracy. Next, the derivative of the sum of partial output combinations of a layer is obtained with respect to the input layer of the CNN. Then, the derivative maps are used to obtain the sample saliency maps and class saliency maps (CSMs). Finally, the bands are selected using the CSMs. The proposed model is verified by experiments on different data sets and compared with other related methods. The results show that the proposed model can achieve better performance than the other methods.

The fusion of remote sensing images with different spatial and temporal resolutions is needed for diverse Earth observation applications. A small number of spatiotemporal fusion methods that use sparse representation appear to be more promising than weighted- and unmixing-based methods in reflecting abruptly changing terrestrial content. However, none of the existing dictionary-based fusion methods consider the downsampling process explicitly, which is the degradation and sparse observation from high-resolution images to the corresponding low-resolution images. In this paper, the downsampling process is described explicitly under the framework of compressed sensing for reconstruction. With the coupled dictionary to constrain the similarity of sparse coefficients, a new dictionary-based spatiotemporal fusion method is built and named compressed sensing for spatiotemporal fusion, for the spatiotemporal fusion of remote sensing images. To deal with images with a high-resolution difference, typically Landsat-7 and Moderate Resolution Imaging Spectrometer (MODIS), the proposed model is performed twice to shorten the gap between the small block size and the large resolution rate. In the experimental procedure, the near-infrared, red, and green bands of Landsat-7 and MODIS are fused with root mean square errors to check the prediction accuracy. It can be concluded from the experiment that the proposed methods can produce higher quality than five state-of-the-art methods, which prove the feasibility of incorporating the downsampling process in the spatiotemporal model under the framework of compressed sensing.

In this paper, the blind restoration of a degraded image with an auxiliary image from another sensor is considered. In a typical multispectral satellite imaging system, multiple images from different sensors of the same area are available. When one of those images in a multiple image set is degraded, another image in the set can be used as a prior image for restoration. A hybrid algorithm based on the sparse representation using an auxiliary image is proposed in this paper. In this approach, the cost function for regularization has two terms: regularization from the degraded image being restored and the regularization from the auxiliary image. The amount of prior information from the auxiliary image to be used in the hybrid algorithm is determined based on the similarity between the auxiliary image and the degraded image. The proposed algorithm is applied to both simulated and real multispectral images, and the performance of the proposed algorithm is compared with those of other image restoration algorithms. In both quantitative and qualitative comparisons, the proposed algorithm performed better than other algorithms.

Basic compressed-sensing algorithms for image reconstructions mainly deal with the computation of sparse regularization. Remote sensing applications often have multisource or multitemporal images whose different components are acquired separately. Therefore, this letter considers the reconstruction of a remote sensing image using an auxiliary image from another sensor or another time as the reference. For this application, a new compressed-sensing object function is developed that uses a reference image as a prior. In the new model, the sparsity constraints in the transform domain come from the target image, and the gradient priors in the spatial domain come from the auxiliary reference image. The hybrid regularization is optimized by basing the algorithm on the Bregman split method. The proposed method shows better performances when compared with other three popular compressed-sensing algorithms.

In this paper, we propose a new compressed sensing based approach to enhance the spatial-temporal resolution of the remote sensing images with a pair of time-continuous spatial-temporal images and a low spatial resolution image at the same place. In compressed sensing, the measurement matrix is a key element to success. This paper presents a novel solution space model for designing the measurement matrix by establishing the correspondence between the spatial-temporal image pair to enhance the spatial-temporal resolution. The matrix we get does not only reflect the relationship between the high- and the low-spatial resolution images, but also have high randomness, thus satisfies the reconstruction requirements (e.g., RIP restriction) in compressed sensing. To verify the effectiveness of our method, we give the experimental reconstructed results and compare our results with the traditional Gaussian Random matrix and the Toplitz matrix. The experiment demonstrates the effectiveness and superiority of the proposed method.

In remote sensing applications, there are often multi-source or multi-temporal images whose different components are acquired separately. Therefore, a part of the acquired images in multi-component data can be used as priors. In this paper, the reconstruction of a remote sensing image using an auxiliary image from another sensor or another time as the reference is considered. For this application, a new compressed sensing object function with an reference image as a prior is developed. In the new model, the sparsity constraints in transform domain comes from the target image, and the gradient priors in spatial domain comes from auxiliary reference image. To optimizing the the hybrid regularization, the algorithm is based on Bregman split method. The performance of the algorithm is evaluated both qualitatively and quantitatively. The results of experiment confirm that the proposed algorithm gets higher peak signal to noise ratio (PSNR) than other approaches without reference images as priors.

Adaptive sparse representations of signals have drawn considerable interest in the past decade. In this paper, we address the problem of training dictionaries for massive images and propose a new algorithm for adapting dictionaries by extending the classical K-SVD based on only a single image. The approach presented in this paper aims at training the adapting dictionary from massive samples, other dictionary learning methods such as Online Dictionary Learning (ODL) and Recursive Least Squares Dictionary Learning Algorithm (RLS-DLA) also could train the dictionary by using relative large samples. Our method is competed with the above two state-of-the-art dictionary learning methods. Experiments demonstrate the effectiveness of the proposed dictionary learning in dealing with massive spatial-temporal remote sensing.

In remote sensing applications, we often encounter data loss issue. When calculating NDVI of some regions, remote sensing data set from Landsat should be used. However, the data set is maybe incomplete. Our empirical method to deal with this problem is to use data set from HJ-1 instead. Naturally, we surmise that the data set obtained by HJ-1 must correlate with the data set obtained by Landsat on condition that the data sets from two satellites have been registered. In this work, We first learned a dictionary and defined a metric under this dictionary to measure NDVI of data set in sparse domain. Through the experiments we can draw the conclusion that NDVI also can be calculated in sparse domain by our method and there is a high correlation between NDVI and NDVI calculated in sparse domains denoted as S NDVI. Based on this, we use the difference of S NDVIs of two data sets to measure the correlation of them in sparse domain which has a linear relationship with the correlation of NDVIs of two data sets.

Compressive sensing of noisy multispectral images is considered in this letter. Multispectral images in remote sensing applications are multichannel and inherently noisy. An approach using Bregman split method for optimization in both spatial and transform domains is proposed. The performance of the proposed algorithm is evaluated by comparing with other approaches. It is shown that the proposed algorithm performs favorably compared with other approaches with noisy multispectral images in experiments.

We reconstruct the multispectral image based on compressive sensing theory. Both spatial domain regularization and transform domain regularization are employed in the proposed objective function. Bregman split method is used to optimize the proposed objective function. In order to making use of the correlation features between different channels of multispectral image, principal component analysis (PCA) is introduced into the shrinkage step of the spatial domain regularization. For further enhance the performance of CS reconstruction, the similarity of wavelet coefficients between different channels are also explored in the shrinkage step of transform domain. We compare the proposed method with some other methods. Experiments validate the better performances of the proposed method, and it is attributed to combine two regularizations and employ the spectral correlation between channels.

SUMMARY The remotely sensed images continuously acquired by satellite and airborne sensors are increasing dramatically. Remote sensing applications are overwhelmed with tons of remote sensing data with complex data structures. Efficient programming in parallel systems for data‐intensive applications like massive remote sensing data processing will be a challenge. We propose a generic data‐structure oriented programming template to support massive remote sensing data processing in high‐performance clusters. These templates provide distributed abstractions for large remote sensing image data with complex data structure and allow these distributed data to be accessed as a global one. Through data serialization and one‐sided message passing primitives provided by message passing interface, the distributed remote sensing data template whose sliced data blocks are scattered among nodes could offer a simple and effective way to distribute and communicate massive remote sensing data. Efficient parallel input/output directly to and from the distributed data structure will also be offered to address the input/output bottleneck caused by massive image data. Developers can take the advantage of our templates to program efficient parallel remote sensing algorithms without dealing with data slicing and communication through low‐level message passing interface APIs. Through experiments on remote sensing applications, we confirmed that our templates were productive and efficient. Copyright © 2012 John Wiley & Sons, Ltd.

SUMMARY Earth observation applications are now facing the challenges of managing and processing massive data sets from multiple sources from large‐scale distributed data centers (DCs). To solve this research problem, this paper presents an infrastructure of multiple data centers (MDC) for managing and processing massive remote sensing images. The proposed system is built on both groups of distributed DCs/clusters, which are equipped with DC or cluster resource manager. Access security and information service are introduced to support this architecture of MDC. We collaboratively organized the algorithm, and data belonged to the MDC in the manner of workflow. In practice, we succeeded in working out the concrete problems regarding procedures in processing applications collaboratively and transfer the massive remote sensing dataset fast and with stable cross‐MDC. On the basis of the previously mentioned research work, we will investigate the platform integration of MDC. Copyright © 2012 John Wiley & Sons, Ltd.

Remote Sensing (RS) data processing is characterized by massive remote sensing images and increasing amount of algorithms of higher complexity. Parallel programming for data-intensive applications like massive remote sensing image processing on parallel systems is bound to be especially trivial and challenging. We propose a C++ template mechanism enabled generic parallel programming skeleton for these remote sensing applications in high performance clusters. It provides both programming templates for distributed RS data and generic parallel skeletons for RS algorithms. Through one-side communication primitives provided by MPI, the distributed RS data template could provide a global view of the big RS data whose sliced data blocks are scattered among the distributed memory of cluster nodes. Moreover, by data serialization and RMA (Remote Memory Access), the data templates could also offer a simple and effective way to distribute and communicate massive remote sensing data with complex data structures. Furthermore, the generic parallel skeletons implement the recurring patterns of computation, performance optimization and pass the user-defined sequential functions as parameters of templates for type genericity. With the implemented skeletons, Developers without extensive parallel computing technologies can implement efficient parallel remote sensing programs without concerning for parallel computing details. Through experiments on remote sensing applications, we confirmed that our templates were productive and efficient.

In this paper, inspiring by the idea of non-local means filter, the non-local information is introduced into the Markov Random Field Models (MRF) based change detection. A new distance based on non-local information of the neighborhood area of remote sensing image is defined. Then the image information is map to a higher dimension feather space. The initial cluster classification is performed in the high dimension non local space. And it provides the initial value for the MRF change detection. Both the data term and the smoothing term in the MRF based change detection are defined in this frame of non-local information. Different multi-temporal images with different resolutions and different locations are experimented. And better performances are achieved in the experiments when comparing with two other method.

In this letter, a new method for denoising remote-sensing images based on partial differential equations (PDEs) is proposed. The method employs the similarity between the different band images in a multicomponent image. Initially, one of the noise-free images in multicomponent remote-sensing images as a prior is introduced into the PDE denoising method. To make use of the priors of the noise-free image in denoising, we construct a new smoothing term for the PDE so as to compute the total variation. The new smoothing term refers to a specific smoothing direction and a specific smoothing intensity of the reference image when denoising the noisy image. The proposed smoothing term is added as a new constraint into the PDE denoising method. Based on the proposed method, the similarity of the directions of the edges between the noisy image and the reference image enables the new algorithm to smooth out more noise and conserve more detail in the denoising process. We also present the discrete form of the proposed denoising model. Multispectral remote-sensing images and hyperspectral remote-sensing images are experimented in this letter. A better performance is achieved by the proposed method when compared with other methods.