Synthetic Aperture Radar Image Change Detection Research Articles

Change Detection in Multitemporal SAR Images Based on Slow Feature Analysis Combined With Improving Image Fusion Strategy

Change detection in multitemporal synthetic aperture radar (SAR) images has been an important research content in the field of remote sensing for a long time. In this article, based on the slow feature analysis (SFA) theory and the nonsubsampled contourlet transform (NSCT) algorithm, we propose a novel unsupervised change detection method called NSCT nonlocal means (NSCT-NLM). The powerful extraction to the changed information of SFA and the superior information fusion of NSCT are jointly adopted in this method. The main framework consists of the following parts. First, SFA and the log-ratio operator are used to generate difference images (DIs) independently. Then, the NSCT is used to fuse two DIs into a new higher quality DI. The newly fused DI combines the complementary information of the two kinds of original DI. Therefore, the contrast of the changed regions and unchanged regions is greatly enhanced, as well as the changed details are preserved more completely. Furthermore, an NLM filtering algorithm is employed to suppress the strong speckles in the fused DI. We use the fuzzy C-means algorithm to generate the final binary change map. The experiments are carried out on two public datasets and three real-world SAR datasets from different scenarios. The results demonstrate that the proposed method has higher detection accuracy by comparing with the reference methods.

SAR Image Change Detection Based on Joint Dictionary Learning With Iterative Adaptive Threshold Optimization

Synthetic aperture radar (SAR) image change detection is still a challenge due to inherent speckle noise and scarce datasets. This article proposes a joint-related dictionary learning algorithm based on the k-singular value decomposition (K-SVD) algorithm called JR-KSVD and an iterative adaptive threshold optimization (IATO) algorithm for unsupervised change detection. The JR-KSVD algorithm adds dictionary correlation learning to the K-SVD algorithm to generate a uniform initial dictionary for dual-temporal SAR images, thereby reducing the instability of sparse representations due to atomic correlations and enhancing the extraction of image edges and details. The IATO approach employs thresholds obtained by the “difference-log ratio” fusion image for indefinite residual energy minimization iterations to gradually shrink the threshold variation range and finally generate the change images, which have a high degree of adaptivity and strong real-time performance. Finally, experiments on six real datasets demonstrate that the proposed algorithm exhibits superior detection performance and robustness against some state-of-the-art algorithms.

Change Detection From Synthetic Aperture Radar Images via Dual Path Denoising Network

Benefited from the rapid and sustainable development of synthetic aperture radar (SAR) sensors, change detection from SAR images has received increasing attentions over the past few years. Existing unsupervised deep learning-based methods have made great efforts to exploit robust feature representations, but they consume much time to optimize parameters. Besides, these methods use clustering to obtain pseudolabels for training, and the pseudolabeled samples often involve errors, which can be considered as “label noise.” To address these issues, we propose a dual path denoising network (DPDNet) for SAR image change detection. In particular, we introduce the random label propagation to clean the label noise involved in preclassification. We also propose the distinctive patch convolution for feature representation learning to reduce the time consumption. Specifically, the attention mechanism is used to select distinctive pixels in the feature maps, and patches around these pixels are selected as convolution kernels. Consequently, the DPDNet does not require a great number of training samples for parameter optimization, and its computational efficiency is greatly enhanced. Extensive experiments have been conducted on five SAR datasets to verify the proposed DPDNet. The experimental results demonstrate that our method outperforms several state-of-the-art methods in change detection results.

RF-HoDRF: High-Order Hybrid Discriminative Random Field Improved by Two-Layer Random Forest for SAR Image Change Detection

For better exploiting discriminative texture features and encoding high-level structures, this letter presents a high- order hybrid discriminative random field improved by two-layer random forest, abbreviated as RF-HoDRF, for synthetic aperture radar (SAR) image change detection. First, RF-HoDRF constructs a two-layer random forest (TL-RF) model to realize the selection of high-dimensional texture features, and then provides the class probabilities for constructing the unary potential in RF-HoDRF. Second, it defines a high-order potential on high-order cliques generated by superpixels to encode the high-level structures and maintain the region consistency. Finally, considering the pairwise potential by improved generalized Ising model and the statistics by generalized Gamma distribution (GΓD), the RF-HoDRF model is derived under the discriminative model framework. Then, by iteratively maximizing the local posterior probabilities, the class labels and the parameters are optimally estimated until they converge. Extensive comparisons and ablation experiments on measured SAR images verify the effectiveness of our method, and demonstrate that discriminative features selection and high-order structures maintenance have great contributions to improving change detection performances.

Spatial–Temporal Gray-Level Co-Occurrence Aware CNN for SAR Image Change Detection

Deep learning-based synthetic aperture radar (SAR) image change detection has recently achieved remarkable success due to its great potential for extracting abstract features. However, the existing methods still have room for improvement in dealing with the speckle of SAR images. In this letter, a deep spatial–temporal gray-level co-occurrence aware convolutional neural network (STGCNet) is proposed, which can effectively mine the spatial–temporal information of the bitemporal images and obtain the speckle-robust results by introducing the 3-D gray-level co-occurrence matrix (3-D-GLCM) as auxiliary feature. Specifically, representative features are extracted from original image pairs and their corresponding 3-D-GLCM through two-stream network, followed by an adaptive fusion module to balance the contribution of each branch. Then, the final binary change detection results are obtained by a fully connected layer. The training process relies on reliable labels generated by unsupervised models rather than manually annotated data, and therefore, the proposed STGCNet is practical in reality. Experiments on synthesized and real SAR data sets demonstrate the robustness and competitiveness of the proposed method compared with the state-of-the-art algorithms.

Unsupervised Multi-Look SAR Image Change Detection Driven by Dual-Layer Graph With Intensity and Texture Attributes

This letter proposes a novel graph-guided approach for unsupervised change detection between multi-look synthetic aperture radar (SAR) images. The dual-layer graph (DG) is proposed to combine both the intensity and texture attributes of an SAR image. It can not only preserve the characteristics of each attribute in the single layer, but also excavate the multiple affinities of attributes from different layers. With the support of DG, change measure is achieved through comparing the graphs based on the supra-adjacency matrix, thus generating the difference image with good separability. The final change detection results are obtained via a traditional binary classification algorithm. Experimental results on two real SAR datasets demonstrate the effectiveness of the proposed graph-guided approach in which DG and multiple affinities provide great contributions for improving the accuracy and robustness of change detection.

Unsupervised SAR Image Change Detection for Few Changed Area Based on Histogram Fitting Error Minimization

Change detection in synthetic aperture radar (SAR) images is an essential task of remote sensing image analysis. However, the thresholding procedure is the main difficulty in change detection for few changed areas for traditional change detection methods. In this paper, we propose a novel change detection method for very few changed or even none changed areas. The proposed method contains three procedures: difference image (DI) generation, thresholding, and spatial analysis. In the second procedure, a new thresholding method called Histogram Fitting Error Minimization (HFEM) is proposed for few changed areas. HFEM is derived under the assumption that the unchanged class in the absolute-valued difference image follows the Half-Normal distribution, and the changed class follows the Gaussian distribution. In the spatial analysis procedure, a new conditional random fields (CRF) method based on Half-Normal distribution is proposed to model the mutual influences among image pixels. The proposed CRF method is called Half-Normal CRF (HNCRF). Experiments carried out on both synthetic datasets and four real SAR datasets demonstrate the superiority of our method. Not only few changed datasets but datasets with lots of changes are used in the experiments. The Kappa coefficients of the proposed method can reach up to ten times that of the traditional method under extreme conditions. The results prove that the proposed method outperforms the traditional methods in the case of few changed areas. Meanwhile, the proposed method can get similar results compared to traditional methods under normal conditions.

SAR Image Change Detection via Multiple-Window Processing with Structural Similarity.

In this paper, a synthetic aperture radar (SAR) change detection approach is proposed based on a structural similarity index measure (SSIM) and multiple-window processing (MWP). The proposed scheme is performed in two steps: (1) generation of a coherence image based on MWP associated with SSIM and (2) gamma correction (GC) filtering. The proposed method is capable of providing a high-quality coherence image because the MWP operation based on SSIM has high sensitivity to the similarity measure for intensity between two SAR images. By finding an optimum value of order of GC, the proposed method can considerably reduce the effect of speckle noise on the coherence image, while retaining nearly all the information related to changed region involved in the change detection map. Several experimental results are presented to demonstrate the effectiveness of the proposed scheme.

Semisupervised SAR image change detection based on a siamese variational autoencoder

In synthetic aperture radar (SAR) image change detection, the deep learning has attracted increasingly more attention because the difference images (DIs) of traditional unsupervised technology are vulnerable to speckle noise. However, most of the existing deep networks do not constrain the distributional characteristics of the hidden space, which may affect the feature representation performance. This paper proposes a variational autoencoder (VAE) network with the siamese structure to detect changes in SAR images. The VAE encodes the input as a probability distribution in the hidden space to obtain regular hidden layer features with a good representation ability. Furthermore, subnetworks with the same parameters and structure can extract the spatial consistency features of the original image, which is conducive to the subsequent classification. The proposed method includes three main steps. First, the training samples are selected based on the false labels generated by a clustering algorithm. Then, we train the proposed model with the semisupervised learning strategy, including unsupervised feature learning and supervised network fine-tuning. Finally, input the original data instead of the DIs in the trained network to obtain the change detection results. The experimental results on four real SAR datasets show the effectiveness and robustness of the proposed method.

Change Detection from SAR Images Based on Convolutional Neural Networks Guided by Saliency Enhancement

Change detection is an important task in identifying land cover change in different periods. In synthetic aperture radar (SAR) images, the inherent speckle noise leads to false changed points, and this affects the performance of change detection. To improve the accuracy of change detection, a novel automatic SAR image change detection algorithm based on saliency detection and convolutional-wavelet neural networks is proposed. The log-ratio operator is adopted to generate the difference image, and the speckle reducing anisotropic diffusion is used to enhance the original multitemporal SAR images and the difference image. To reduce the influence of speckle noise, the salient area that probably belongs to the changed object is obtained from the difference image. The saliency analysis step can remove small noise regions by thresholding the saliency map, and interest regions can be preserved. Then an enhanced difference image is generated by combing the binarized saliency map and two input images. A hierarchical fuzzy c-means model is applied to the enhanced difference image to classify pixels into the changed, unchanged, and intermediate regions. The convolutional-wavelet neural networks are used to generate the final change map. Experimental results on five SAR data sets indicated the proposed approach provided good performance in change detection compared to state-of-the-art relative techniques, and the values of the metrics computed by the proposed method caused significant improvement.

Synthetic aperture radar image change detection based on convolutional‐curvelet neural network and partial graph‐cut

Synthetic aperture radar (SAR) images are widely applied in change detection tasks because of SAR's active imaging mechanism. However, SAR images suffer from speckle noise due to SAR reception coherence from distributed targets. This property of SAR increases the uncertainty of the image pixels, making it difficult to accurately detect the changed regions from the background. To address this issue, this letter proposes a novel SAR image change detection method based on a convolutional-curvelet neural network (CurveCNet) and partial graph-cut. The curvelet transform is introduced into the convolutional neural network to retain the structural information in the SAR images and to suppress the speckle noise. In addition, to combine the merits of various difference images, training samples are jointly constructed and fed into the neural network for it to learn the implicit common hierarchical features. Finally, the partial graph-cut approach is proposed to refine the pixel labels in the fuzzy region and inhibit outliers on the background for the resultant change map. Visual and quantitative results obtained on two real SAR image datasets have demonstrated the effectiveness and robustness of the proposed method.

SAR image change detection based on sparse representation and a capsule network

ABSTRACT Synthetic aperture radar (SAR) image change detection has good application prospects in the domain of remote sensing image processing. However, the accuracy of change detection is negatively affected by the inherent speckle noise in SAR images. To solve this problem, a method based on sparse representation (SR) and a capsule network is proposed. Firstly, sparse features of the difference image (DI) are extracted by the SR method. Secondly, a lightweight capsule network (L-CapsNet) is constructed, which is used to mine the spatial relationship between features. The network classifies the changed and unchanged pixels. Finally, the change map (CM) is generated. The proposed method can obtain more robust features while reducing the influence of speckle noise. Experiments are performed on four SAR data sets to compare the proposed method with related methods. The results confirm the superior performance of the proposed method.

A Multiscale Self-Attention Deep Clustering for Change Detection in SAR Images

Synthetic aperture radar (SAR) image change detection (CD) is an important application in the field of remote sensing. Due to the lack of labeled data especially in the pixelwise task, it is urgent to develop unsupervised techniques to effectively detect changes. In this article, we propose a novel unsupervised representation learning framework for CD in SAR images, called multiscale self-attention (SA) deep clustering based on octave convolution. The main motivation is that a convolutional neural network (CNN) has the ability to extract significant feature hidden in input images, but it relies heavily on annotated data. Clustering is typically free from supervision; however, SAR images always suffer from speckle noise, which is unfriendly for clustering. Thus, we integrate unsupervised clustering with CNN to learn clustering-friendly feature representations. In the unified framework, CNN feature learning and clustering can be optimized end-to-end without supervision. To better suppress speckle noise and boost the joint optimization for distinguishing changes and unchanges, we use the K-means++ algorithm that is robust to noise as the clustering algorithm. In the meanwhile, we introduce the octave convolution and SA mechanism into the network to fully mine important spatial structure information for enhancing noise resistance of the network. Moreover, multiscale fusion modules are proposed to fuse multiscale input into a complementary feature representation that contains more context and semantic information around each pixel so that it refines the difference feature extraction while reducing speckle noise. Experiments on challenging SAR data sets demonstrate the effectiveness and potential of the proposed model compared with the current state-of-the-art algorithms.

SAR Image Change Detection Based on Multi-scale Feature Extraction

In order to improve the contrast of the difference image and reduce the interference of the speckle noise in the synthetic aperture radar (SAR) image, this paper proposes a SAR image change detection algorithm based on multi-scale feature extraction. In this paper, a kernel matrix with weights is used to extract features of two original images, and then the logarithmic ratio method is used to obtain the difference images of two images, and the change area of the images are extracted. Then, the different sizes of kernel matrix are used to extract the abstract features of different scales of the difference image. This operation can make the difference image have a higher contrast. Finally, the cumulative weighted average is obtained to obtain the final difference image, which can further suppress the speckle noise in the image.

Multiple Kernel Graph Cut for SAR Image Change Detection

Complementary information between two difference images (DI’s) has great contribution to improve change detection performances. Based on the effectiveness and flexibility of the multiple kernel learning (MKL) in information fusion, we develop a multiple kernel graph cut (MKGC) algorithm for synthetic aperture radar (SAR) image change detection. An energy function containing a weighted summation kernel is proposed for fusing the complementary information between the subtraction image and the ratio image. By iteratively minimizing the energy function, the kernel weights, region parameters and region labels are estimated automatically and optimally. Besides of it avoids modeling, MKGC also has a complete description of the changed areas and the strong noise immunity. Experiments on real GaoFen-3 SAR data set demonstrate the effectiveness of the MKGC algorithm, and illustrate that it is a good candidate for SAR image change detection.

SAR Image Change Detection Based on Semisupervised Learning and Two-Step Training

Change detection, as an essential part of synthetic aperture radar (SAR) automatic target recognition (ATR) systems, remains a challenging problem. The lack of labeled data seriously impedes the development of deep learning-based methods in SAR applications. In this letter, we propose a patch-based semisupervised method to detect changed pixels from limited training data in the field of SAR. The complete approach includes the unsupervised pretraining stage and the iterative discrimination stage. The states of pixels are determined by comparing the corresponding image patches. First, to reduce the impact of insufficient data, we train a trapezium U-Net-like structure to extract representative and generalized features by unsupervised training on all pixels. Feature maps contain detailed and semantic information due to repetitive feature fusions. A designed feature activation module is utilized to recalibrate fused features. Finally, the discrimination is finished by a simple classification convolutional neural network (CNN) following a two-step training strategy. Ablation studies indicate the function provided by the proposed modifications. Experiments on real SAR images demonstrate that the proposed method can improve the detection accuracy by more than 1.2% compared with other state-of-the-art deep learning-based methods.

Change Detection in SAR Images Based on Improved Non-Subsampled Shearlet Transform and Multi-Scale Feature Fusion CNN

Traditional methods for change detection in synthetic aperture radar (SAR) images have difficulty in obtaining results from the generated differential image (DI) owing to speckle noise. In recent years, many deep learning (DL)-based methods have emerged because of their outstanding anti-noise and self-learning ability. However, they are limited by the requirement of abundant high-precision labels. Therefore, in this paper, we propose a novel unsupervised method based on improved non-subsampled shearlet transform (NSST) and multi-scale feature fusion convolutional neural network (CNN) for change detection. First, this method improves the traditional NSST algorithm and proposes a novel pseudo-label generator to obtain more pseudo-labels with higher confidence. It is noteworthy that the more accurate the pseudo-labels are, the better the change detection results will be. Second, this method designs a multi-scale feature fusion block in the network to make the feature images contain more complete information and reduces the number of pooling layers to avoid losing feature image details. The main idea of this method is to eliminate the step of generating the DI and directly obtain results from the original images. The theoretical analysis and final results conducted on three real data sets prove its validity. Furthermore, to verify the generality and potential of the propose method, we apply it to the cross-region change detection and compare it with the supervised method, which achieve satisfactory results.

LCS-EnsemNet: A Semisupervised Deep Neural Network for SAR Image Change Detection With Dual Feature Extraction and Label-Consistent Self-Ensemble

Change detection (CD) in synthetic aperture radar (SAR) images faces two challenging problems: 1) inherent speckle noise in SAR data causes the class confusion and affects the image understanding for inferring category of each image pixel; and 2) adequate labeled samples are quite hard to collect, which is the major limitation for supervised methods. In this article, we develop a novel deep learning-based semisupervised method to address these challenges. The method firstly incorporates a pixel-wise log-ratio difference image (DI) and its saliency map to produce a spatially enhanced (SE) DI using a reweighting scheme based on the fact that changed pixels exhibit higher saliency than unchanged pixels. As a result, prominent changed regions are highlighted and the interclass separability is increased. We construct pixel-wise and context-wise features based on the log-ratio DI and SE DI to jointly express the dissimilarity at each pixel. Second, a two-branch deep neural network taking the dual features as input is devised to reveal and refine underlying label information from abundant unlabeled samples with the help of a two-stage refinement strategy for improving generalization ability, called LCS-EnsemNet. The refinement strategy, namely label-consistent self-ensemble, exploits label consistency between dual features and across multiple classifiers to ensure the reliability of pseudo labels. Finally, the cross-entropy loss is calculated with the limited labeled data and selected pseudo labeled samples to optimize the LCS-EnsemNet. The proposed method is evaluated on three low/medium- resolution and one high-resolution SAR data sets, and experimental results have demonstrated its effectiveness.

Synthetic Aperture Radar Image Change Detection via Siamese Adaptive Fusion Network

Synthetic aperture radar (SAR) image change detection is a critical yet challenging task in the field of remote sensing image analysis. The task is nontrivial due to the following challenges: First, intrinsic speckle noise of SAR images inevitably degrades the neural network because of error gradient accumulation. Furthermore, the correlation among various levels or scales of feature maps is difficult to be achieved through summation or concatenation. Toward this end, we proposed a siamese adaptive fusion (AF) network for SAR image change detection. To be more specific, two-branch CNN is utilized to extract high-level semantic features of multitemporal SAR images. Besides, an AF module is designed to adaptively combine multiscale responses in convolutional layers. Therefore, the complementary information is exploited, and feature learning in change detection is further improved. Moreover, a correlation layer is designed to further explore the correlation between multitemporal images. Thereafter, robust feature representation is utilized for classification through a fully connected layer with softmax. Experimental results on four real SAR datasets demonstrate that the proposed method exhibits superior performance against several state-of-the-art methods. Our codes are available at https://github.com/summitgao/SAR_CD_SAFNet .

Change detection in SAR images based on superpixel segmentation and image regression

Change detection (CD) is one of the most important application in remote sensing domain. The difference image (DI) generated by traditional change detection methods are sensitive to several factors, such as atmospheric condition changes, illumination variations, sensor calibration, and speckle noise, greatly affecting the detection performance. To avoid the aforementioned problem, in this paper, a novel approach based on superpixel segmentation and image regression is proposed to detect changes between bitemporal synthetic aperture radar (SAR) images. Specifically, the bitemporal images are firstly divided into a number of superpixel pairs under the guidance of segmentation result of a pre-DI. Next, each pixel in pre-event image is reconstructed utilizing its nearest neighbor to reduce the influence of noise. Then, a set of preselected unchanged sample are selected to learn the local regression model and to estimate the post-event image. After that, the final DI can be obtained by measuring the difference between estimated post-event image and the actual one. Finally, the fuzzy c-means (FCM) clustering algorithm is adopted to generate the binary change map. Adequate experiments on four SAR datasets have been tested, and the experimental results compared with the state-of-the-art methods have proved the superiority of the proposed method.