Bi-temporal Synthetic Aperture Radar Images Research Articles

D‐CDA: A Denoise and Change Detection Approach for Flood Disaster Location From SAR Images

AbstractFloods are among the most devastating natural disasters worldwide. Such disasters are often accompanied by strong precipitation and other weather factors, making it more difficult to identify affected areas. Moreover, synthetic aperture radar (SAR) technology can capture images in a 24‐hr window and penetrate clouds and fog. Change detection (CD) technology based on SAR images is generally utilized to locate disaster‐stricken areas by analyzing the differences between pre‐ and post‐disaster images. However, this method faces two main challenges: the presence of speckle noise, which reduces the difference detection accuracy, and the lack of a suitable SAR data set for flood disaster CD. Therefore, this study proposes a novel two‐stage approach for locating flood disaster areas, known as the denoising‐change detection approach (D‐CDA). The first stage comprises a nine‐layer denoising network with an encoder‐decoder structure known as the SAR denoising network (SDNet). It utilizes a multiresidual block and a parallel convolutional block attention module to extract features during the encoding process to suppress the noise component. In the second stage, a novel convolution neural network is proposed to detect the changes between bitemporal SAR images, namely, the coordinate attention fused network, which combines the siamese network and UNet++ as the backbone, and fuses coordinate attention modules to enhance the change features. Moreover, a CD data set (Zhengzhou flood data set) was constructed using Sentinel‐1 SAR images based on the 2021 flood disaster in Zhengzhou, China. Simulations verify the effectiveness of the proposed method. The experimental results indicate that D‐CDA achieves favorable detection performance in locating flood disaster areas.

TransUNet++SAR: Change Detection with Deep Learning about Architectural Ensemble in SAR Images

In the application of change detection satellite remote sensing images, synthetic aperture radar (SAR) images have become a more important data source. This paper proposes a new end-to-end SAR image change network architecture—TransUNet++SAR—that combines Transformer with UNet++. First, the convolutional neural network (CNN) was used to obtain the feature maps of the single time SAR images layer by layer. Tokenized image patches were encoded to extract rich global context information. Using improved Transformer for effective modeling of global semantic relations can generate rich contextual feature representations. Then, we used the decoder to upsample the encoded features, connected the encoded multi-scale features with the high-level features by sequential connection to learn the local-global semantic features, recovered the full spatial resolution of the feature map, and achieved accurate localization. In the UNet++ structure, the bitemporal SAR images are composed of two single networks, which have shared weights to learn the features of the single temporal image layer by layer to avoid the influence of SAR image noise and pseudo-change on the deep learning process. The experiment results show that the experimental effect of TransUNet++SAR on the Beijing, Guangzhou, and Qingdao datasets were significantly better than other deep learning SAR image change detection algorithms. At the same time, compared with other Transformer related change detection algorithms, the description of the changed area edge was more accurate. In the dataset experiments, the model had higher indices than the other models, especially the Beijing building change datasets, where the IOU was 9.79% higher and F1-score was 4.38% higher.

Improving Deforestation Detection on Tropical Rainforests Using Sentinel-1 Data and Convolutional Neural Networks

Detecting early deforestation is a fundamental process in reducing forest degradation and carbon emissions. With this procedure, it is possible to monitor and control illegal activities associated with deforestation. Most regular monitoring projects have been recently proposed, but most of them rely on optical imagery. In addition, these data are seriously restricted by cloud coverage, especially in tropical environments. In this regard, Synthetic Aperture Radar (SAR) is an attractive alternative that can fill this observational gap. This work evaluated and compared a conventional method based on time series and a Fully Convolutional Network (FCN) with bi-temporal SAR images. These approaches were assessed in two regions of the Brazilian Amazon to detect deforestation between 2019 and 2020. Different pre-processing techniques, including filtering and stabilization stages, were applied to the C-band Sentinel-1 images. Furthermore, this study proposes to provide the network with the distance map to past-deforestation as additional information to the pair of images being compared. In our experiments, this proposal brought up to 4% improvement in average precision. The experimental results further indicated a clear superiority of the DL approach over a time series-based deforestation detection method used as a baseline in all experiments. Finally, the study proved the benefits of pre-processing techniques when using detection methods based on time series. On the contrary, the analysis revealed that the neural network could eliminate noise from the input images, making filtering innocuous and, therefore, unnecessary. On the other hand, the stabilization of the input images brought non-negligible accuracy gains to the DL approach.

Hybrid Variability Aware Network (HVANet): A Self-Supervised Deep Framework for Label-Free SAR Image Change Detection

Synthetic aperture radar (SAR) image change detection (CD) aims to automatically recognize changes over the same geographic region by comparing prechange and postchange SAR images. However, the detection performance is usually subject to several restrictions and problems, including the absence of labeled SAR samples, inherent multiplicative speckle noise, and class imbalance. More importantly, for bitemporal SAR images, changed regions tend to present highly variable sizes, irregular shapes, and different textures, typically referred to as hybrid variabilities, further bringing great difficulties to CD. In this paper, we argue that these internal hybrid variabilities can also be used for learning stronger feature representation, and we propose a hybrid variability aware network (HVANet) for completely unsupervised label-free SAR image CD by taking inspiration from recent developments in deep self-supervised learning. First, since different changed regions may exhibit hybrid variabilities, it is necessary to enrich distinguishable information within the input features. To this end, in shallow feature extraction, we generalize the traditional spatial patch (SP) feature to allow for each pixel in bitemporal images to be represented at diverse scales and resolutions, called extended SP (ESP). Second, with the carefully customized ESP features, HVANet performs local spatial structure information extraction and multiscale–multiresolution (MS-MR) information encoding simultaneously through a local spatial stream and a scale-resolution stream, respectively. Intrinsically, HVANet projects the ESP features into a new high-level feature space, where the change identification becomes easier. Third, to train the framework effectively, a self-supervision layer is attached to the top of the HVANet to enable the two-stream feature learning and recognition of changed pixels in the corresponding feature space, in a self-supervised manner. Experimental results on three low/medium-resolution SAR datasets demonstrate the effectiveness and superiority of the proposed framework in unsupervised SAR CD tasks.

SAR Image Change Detection Based on Heterogeneous Graph With Multiattributes and Multirelationships

The performance of change detection between synthetic aperture radar (SAR) images mainly depends on the selection and utilization of image attributes. Nevertheless, most existing change detection approaches merely take the intensity attribute into consideration, constraining their capacities of detecting changes in complex situations. To solve this problem, this study develops an unsupervised SAR image change detection approach based on heterogeneous graph with multi-attributes and multi-relationships. First, the structural attribute, obtained by removing the complex texture, can be used to reflect the overall features of a SAR image. A heterogeneous graph is then constructed to encode the structural and intensity attributes as vertices, and two types of edges are hence connected to capture the intra-relationships and inter-relationships from these different attributes. With the support of this graph, the hyper-adjacency characteristics are proposed to quantify the multi-relationships and describe the global heterogeneous information. Constructing heterogeneous graphs respectively on bi-temporal SAR images, the changes of both intensity and structural attributes can be measured via comparing the hyper-adjacency characteristics of the bi-temporal graphs, thereby generating a difference image with good separability. Finally, the change map is obtained by cutting off the weakly related edges of heterogeneous graph on the difference image. Experiments on four real SAR datasets prove the effectiveness of the proposed graph-driven approach in improving the accuracy and robustness of change detection.

CocoNet: a hybrid machine learning framework for coconut farm identification and its cyclonic damage assessment on bitemporal SAR images

The coconut tree is an important cash crop in coastal tropical regions. These trees undergo substantial damage during annual cyclones. Early and effective assessment of damage is important to farmers for appropriate monetary compensation. However, the identification of coconut trees presents multiple challenges: (i) the trees are with other vegetation and (ii) cloud cover during monsoons and cyclones precludes using simple imaging techniques. Although automated approaches based on classical machine learning techniques have been attempted for other crops on remote sensed images, these are not adequate for identifying coconut trees from different land cover. We present a hybrid approach termed CocoNet that combines (i) unsupervised K-means for pixel-based coarse classification of land cover and (ii) a patch-based convolutional neural network for fine classification of vegetation to identify coconut farms. The challenge presented by cloud cover is addressed using synthetic aperture radar (SAR) images. Change detection is then performed on bitemporal Sentinel-1 SAR images taken before and after a cyclone to obtain the change map depicting the damage caused. Experimental results show that the proposed two-phase CocoNet model gives a classification accuracy of 92.5% and a change detection accuracy of 89.1%.

SAR Image Classification Using Contrastive Learning and Pseudo-Labels With Limited Data

Synthetic aperture radar (SAR) image classification based on deep learning methods has attracted huge enthusiasm among researchers. Sufficient training data guarantee the generalization ability of neural networks. However, it is quite difficult to collect large amount of high-quality and labeled SAR data in real situations. In this letter, a method based on contrastive learning and pseudo-labels is proposed to solve the few-shot SAR image classification problem. First, a siamese structure is introduced to learn semantic representations of SAR target images. The feature vectors obtained in this stage can reveal the similarity between bi-temporal SAR images. Then, the backbone network of the siamese network is connected to a classification head for instance-level classification. The pseudo-label strategy is adopted to gradually improve the performance. A loss function that changes with iteration is designed to optimize the training process with true labels and pseudo-labels. Besides, considering the imprecision of single-network architecture, we adopt dual-networks and cross-training strategies. The final result is obtained by integrating the results of the dual-networks. Ablation studies show that the designed components of the proposed method are effective. Comparative experiments on the moving and stationary target acquisition and recognition (MSTAR) data set demonstrate the superior performance of the proposed method when dealing with limited training data in the SAR classification.

Lightweight convolutional neural network for bitemporal SAR image change detection

Recently, many convolutional neural networks (CNN) have been successfully employed in bitemporal synthetic aperture radar (SAR) image change detection. However, most of the existing networks are too heavy and occupy a large volume of memory for storage and calculation. Motivated by this, we propose a lightweight neural network to reduce the computational and spatial complexity and facilitate the change detection on an edge device. We replace normal convolutional layers with bottleneck layers that keep the same number of channels between input and output. Next, we employ dilated convolutional kernels with a few non-zero entries that reduce the running time in convolutional operators. Comparing with the conventional convolutional neural network, our lightweight neural network will be more efficient with fewer parameters. We verify our light-weighted neural network on four sets of bitemporal SAR images. The experimental results show that the proposed network can obtain better performance than the conventional CNN and has better model generalization, especially on the challenging datasets with complex scenes.

Building Change Detection in VHR SAR Images via Unsupervised Deep Transcoding

Building change detection (CD), important for its application in urban monitoring, can be performed in near real time by comparing prechange and postchange very-high-spatial-resolution (VHR) synthetic-aperture-radar (SAR) images. However, multitemporal VHR SAR images are complex as they show high spatial correlation, prone to shadows, and show an inhomogeneous signature. Spatial context needs to be taken into account to effectively detect a change in such images. Recently, convolutional-neural-network (CNN)-based transfer learning techniques have shown strong performance for CD in VHR multispectral images. However, its direct use for SAR CD is impeded by the absence of labeled SAR data and, thus, pretrained networks. To overcome this, we exploit the availability of paired unlabeled SAR and optical images to train for the suboptimal task of transcoding SAR images into optical images using a cycle-consistent generative adversarial network (CycleGAN). The CycleGAN consists of two generator networks: one for transcoding SAR images into the optical image domain and the other for projecting optical images into the SAR image domain. After unsupervised training, the generator transcoding SAR images into optical ones is used as a bitemporal deep feature extractor to extract optical-like features from bitemporal SAR images. Thus, deep change vector analysis (DCVA) and fuzzy rules can be applied to identify changed buildings (new/destroyed). We validate our method on two data sets made up of pairs of bitemporal VHR SAR images on the city of L’Aquila (Italy) and Trento (Italy).

A Convolutional Neural Network with Parallel Multi-Scale Spatial Pooling to Detect Temporal Changes in SAR Images

In synthetic aperture radar (SAR) image change detection, it is quite challenging to exploit the changing information from the noisy difference image subject to the speckle. In this paper, we propose a multi-scale spatial pooling (MSSP) network to exploit the changed information from the noisy difference image. Being different from the traditional convolutional network with only mono-scale pooling kernels, in the proposed method, multi-scale pooling kernels are equipped in a convolutional network to exploit the spatial context information on changed regions from the difference image. Furthermore, to verify the generalization of the proposed method, we apply our proposed method to the cross-dataset bitemporal SAR image change detection, where the MSSP network (MSSP-Net) is trained on a dataset and then applied to an unknown testing dataset. We compare the proposed method with other state-of-arts and the comparisons are performed on four challenging datasets of bitemporal SAR images. Experimental results demonstrate that our proposed method obtain comparable results with S-PCA-Net on YR-A and YR-B dataset and outperforms other state-of-art methods, especially on the Sendai-A and Sendai-B datasets with more complex scenes. More important, MSSP-Net is more efficient than S-PCA-Net and convolutional neural networks (CNN) with less executing time in both training and testing phases.

Unsupervised change detection between SAR images based on hypergraphs

The performance of synthetic aperture radar (SAR) image change detection is mainly relied on the quality of the difference image and the accuracy of the classification method. Considering the above mentioned issues, this paper proposes an unsupervised framework for SAR image change detection in which each pixel is taken as a vertex and the collection of pixels is represented by hyperedges in a hypergraph. Thus, the task of SAR image change detection is formulated as the problem of hypergraph matching and hypergraph partition. First, instead of using the K nearest neighbour rule, we propose a coupling neighbourhood based on the spatial-intensity constraint to gather the neighbours for each vertex. Then, hyperedges are constructed on the pixels and their coupling neighbours. The weight of hyperedge is computed via the sum of the patch-based pairwise affinities within the hyperedge. Through modelling the two hypergraphs on the bi-temporal SAR images, not only the change level of vertices is described, but also the changes of local grouping and consistency within hyperedge are excavated. Thus, the difference image with a good separability can be obtained by matching each vertex and hyperedge between the two hypergraphs. Finally, a generalized hypergraph partition technique is employed to classify changed and unchanged areas in the generated difference image. Experimental results on real SAR datasets confirm the validity of the proposed framework in improving the robustness and accuracy of change detection.

A hierarchical spatial-temporal graph-kernel for high-resolution SAR image change detection

ABSTRACTEffective utilization of structural information is important for high-resolution synthetic aperture radar (SAR) image change detection. For comprehensively utilizing the local and global structures in SAR images, a hierarchical spatial-temporal graph kernel (STGK) method is proposed in this paper for high-resolution SAR image change detection. First, the bi-temporal hierarchical graph models are constructed for extracting the local-global structures in the bi-temporal SAR images. Then, a STGK function, which measures the spatial and temporal similarities between the local-global structures, is constructed for indicating the change levels between the bi-temporal images. Finally, a support vector machine (SVM) is implemented with the STGK function for producing the final change detection results. Experimental results on real GaoFen-3 SAR data sets demonstrate the effectiveness of the proposed method, and prove that the STGK method is capable of detecting changed areas with relatively complex structures.

SAR Image Change Detection via Spatial Metric Learning With an Improved Mahalanobis Distance

The log-ratio (LR) operator has been widely employed to generate the difference image for synthetic aperture radar (SAR) image change detection. However, the difference image generated by this pixel-wise operator can be subject to SAR images speckle and unavoidable registration errors between bitemporal SAR images. In this letter, we proposed a spatial metric learning method to obtain a difference image more robust to the speckle by learning a metric from a set of constraint pairs. In the proposed method, spatial context is considered in constructing constraint pairs, each of which consists of patches in the same location of bitemporal SAR images. Then, a semi-definite positive metric matrix $\bf M$ can be obtained by the optimization with the max-margin criterion. Finally, we verify our proposed method on four challenging datasets of bitemporal SAR images. Experimental results demonstrate that the difference map obtained by our proposed method outperforms than other state-of-art methods.

How Can Despeckling and Structural Features Benefit to Change Detection on Bitemporal SAR Images?

Change detection on bitemporal synthetic aperture radar (SAR) images is a key branch of SAR image interpretation. However, it is challenging due to speckle and unavoidable registration errors within bitemporal SAR images. A key issue is whether and how despeckling and structural features can improve accuracy. In this paper, we investigate how despeckling and structural features can benefit change detection for SAR images. Several change detection methods were performed on both input images and the corresponding despeckled images, where despeckling was achieved by different methods. The comparisons demonstrate that despeckling methods that preserve the structures can suppress noise in difference images and can improve the accuracy of change detection. We also developed a sparse model to exploit structural features from the difference images while reducing the influence of misalignment between bitemporal SAR images. The comparisons were performed on five datasets of bitemporal SAR images, and the experimental results show that our proposed sparse model outperforms other traditional methods, demonstrating the advantages of change detection.

Pointwise SAR image change detection based on stereograph model with multiple-span neighbourhood information

ABSTRACTIn this article, a novel pointwise approach is proposed for change detection in bi-temporal synthetic aperture radar (SAR) images using stereograph model. Due to the fact that SAR image suffers from the speckle noise, a pointwise approach based on a set of characteristic points only, not on the whole pixels, seems to be more efficient. Moreover, the correlations of neighbourhood points which have different locations in bi-temporal SAR images should be studied to repress the speckle in change detection. Therefore, the stereograph model, which extends the graph model to three-dimensional space, is designed to connect the local maximum pixels on bi-temporal SAR images and can be used to capture the multiple-span neighbourhood information from the edges. Furthermore, a specialized change measure function is presented to quantify the neighbourhood information from stereograph model, and thus, a novel nondense difference image (NDI) is generated. Finally, a traditional classification method is used to analyse the NDI into changed class and unchanged class. Experiments on real SAR images show that the proposed NDI can improve separability between changed and unchanged areas, and the final results possess high accuracy and strong noise immunity for change detection tasks with noise-contaminated SAR images.

Regional tropical deforestation detection using ALOS PALSAR 50 m mosaics in Riau province, Indonesia

ALOS PALSAR has provided a five-year archive of systematic global tropical forest coverage, released as slope-corrected and ortho-rectified 50 m mosaic products by JAXA, which are of great help to monitor forest changes. Based on the mosaics, a map of deforestation between the years 2007 and 2008 is built for Riau province, Indonesia, achieving a detection rate of over 86% at a false alarm rate of 20%, calculated by treating independent World Wildlife Fund (WWF) 2007 and 2008 maps as a reference. Non-forest is discriminated from forest by thresholding the HH/HV ratio in the PALSAR data. Deforestation is then estimated by detecting non-forest in the 2008 synthetic aperture radar (SAR) image (acquired close in time to the WWF 2008 reference map) within the region identified as natural forest in the WWF 2007 reference map. This reduces the errors caused by comparing the change detection between the bi-temporal SAR images with the WWF reference maps that are temporally mismatched with the SAR data, leading to more realistic estimates of the ability of PALSAR to detect deforestation than was previously reported.