Synthetic Aperture Radar Change Detection Research Articles

Synthetic Aperture Radar Image Change Detection Based on Principal Component Analysis and Two-Level Clustering

Synthetic aperture radar (SAR) change detection provides a powerful tool for continuous, reliable, and objective observation of the Earth, supporting a wide range of applications that require regular monitoring and assessment of changes in the natural and built environment. In this paper, we introduce a novel SAR image change detection method based on principal component analysis and two-level clustering. First, two difference images of the log-ratio and mean-ratio operators are computed, then the principal component analysis fusion model is used to fuse the two difference images, and a new difference image is generated. To incorporate contextual information during the feature extraction phase, Gabor wavelets are used to obtain the representation of the difference image across multiple scales and orientations. The maximum magnitude across all orientations at each scale is then concatenated to form the Gabor feature vector. Following this, a cascading clustering algorithm is developed within this discriminative feature space by merging the first-level fuzzy c-means clustering with the second-level neighbor rule. Ultimately, the two-level combination of the changed and unchanged results produces the final change map. Five SAR datasets are used for the experiment, and the results show that our algorithm has significant advantages in SAR change detection.

A Semi-Supervised Deep Learning Framework for Change Detection in Open-Pit Mines Using SAR Imagery

Detecting and monitoring changes in open-pit mines is crucial for efficient mining operations. Indeed, these changes comprise a broad spectrum of activities that can often lead to significant environmental impacts such as surface damage, air pollution, soil erosion, and ecosystem degradation. Conventional optical sensors face limitations due to cloud cover, hindering accurate observation of the mining area. To overcome this challenge, synthetic aperture radar (SAR) images have emerged as a powerful solution, due to their unique ability to penetrate clouds and provide a clear view of the ground. The open-pit mine change detection task presents significant challenges, justifying the need for a model trained for this specific task. First, different mining areas frequently include various features, resulting in a diverse range of land cover types within a single scene. This heterogeneity complicates the detection and distinction of changes within open-pit mines. Second, pseudo changes, e.g., equipment movements or humidity fluctuations, which show statistically reliable reflectivity changes, lead to false positives, as they do not directly correspond to the actual changes of interest, i.e., blasting, collapsing, or waste pile operations. In this paper, to the best of our knowledge, we present the first deep learning model in the literature that can accurately detect changes within open-pit mines using SAR images (TerraSAR-X). We showcase the fundamental role of data augmentations and a coherence layer as a critical component in enhancing the model’s performance, which initially relied solely on amplitude information. In addition, we demonstrate how, in the presence of a few labels, a pseudo-labeling pipeline can improve the model robustness, without degrading the performance by introducing misclassification points related to pseudo changes. The F1-Score results show that our deep learning approach is a reliable and effective method for SAR change detection in the open-pit mining sector.

SAR Change Detection Algorithm Combined with FFDNet Spatial Denoising

Objectives: When detecting changes in synthetic aperture radar (SAR) images, the quality of the difference map has an important impact on the detection results, and the speckle noise in the image interferes with the extraction of change information. In order to improve the detection accuracy of SAR image change detection and improve the quality of the difference map, this paper proposes a method that combines the popular deep neural network with the clustering algorithm.Methods: Firstly, the SAR image with speckle noise was constructed, and the FFDNet architecture was used to retrain the SAR image, and the network parameters with better effect on speckle noise suppression were obtained. Then the log ratio operator is generated by using the reconstructed image output from the network. Finally, K-means and FCM clustering algorithms are used to analyze the difference images, and the binary map of change detection results is generated. Results: The experimental results have high detection accuracy on Bern and Sulzberger's real data, which proves the effectiveness of the method.

A Hierarchical Fusion SAR Image Change-Detection Method Based on HF-CRF Model

The mainstream methods for change detection in synthetic-aperture radar (SAR) images use difference images to define the initial change regions. However, methods can suffer from semantic collapse, which makes it difficult to determine semantic information about the changes. In this paper, we proposed a hierarchical fusion SAR image change-detection model based on hierarchical fusion conditional random field (HF-CRF). This model introduces multimodal difference images and constructs the fusion energy potential function using dynamic convolutional neural networks and sliding window entropy information. By using an iterative convergence process, the proposed method was able to accurately detect the change-detection regions. We designed a dynamic region convolutional semantic segmentation network with a two-branch structure (D-DRUNet) to accomplish feature fusion and the segmentation of multimodal difference images. The proposed network adopts a dual encoder–single decoder structure where the baseline is the UNet network that utilizes dynamic convolution kernels. D-DRUNet extracts multimodal difference features and completes semantic-level fusion. The Sobel operator is introduced to strengthen the multimodal difference-image boundary information and construct the dynamic fusion pairwise potential function, based on local boundary entropy. Finally, the final change result is stabilized by iterative convergence of the CRF energy potential function. Experimental results demonstrate that the proposed method outperforms existing methods in terms of the overall number of detection errors, and reduces the occurrence of false positives.

A Novel End-to-End Unsupervised Change Detection Method with Self-Adaptive Superpixel Segmentation for SAR Images

Change detection (CD) methods using synthetic aperture radar (SAR) data have received significant attention in the field of remote sensing Earth observation, which mainly involves knowledge-driven and data-driven approaches. Knowledge-driven CD methods are based on the physical theoretical models with strong interpretability, but they lack the robust features of being deeply mined. In contrast, data-driven CD methods can extract deep features, but require abundant training samples, which are difficult to obtain for SAR data. To address these limitations, an end-to-end unsupervised CD network based on self-adaptive superpixel segmentation is proposed. Firstly, reliable training samples were selected using an unsupervised pre-task. Then, the superpixel generation and Siamese CD network were integrated into the unified framework to train them end-to-end until the global optimal parameters were obtained. Moreover, the backpropagation of the joint loss function promoted the adaptive adjustment of the superpixel. Finally, the binary change map was obtained. Several public SAR CD datasets were used to verify the effectiveness of the proposed method. The transfer learning experiment was implemented to further explore the ability to detect the changes and generalization performance of our network. The experimental results demonstrate that our proposed method achieved the most competitive results, outperforming seven other advanced deep-learning-based CD methods. Specifically, our method achieved the highest accuracy in OA, F1-score, and Kappa, and also showed superiority in suppressing speckle noise, refining change boundaries, and improving detection accuracy in a small area change.

Fast Flood Extent Monitoring With SAR Change Detection Using Google Earth Engine

Flooding is one of the most frequent and disastrous natural hazards triggered by extreme precipitation, high river runoff, hurricane storm surges, and the compounding effects of various flood drivers. This study introduces a new multisource remote sensing approach that leverages both multispectral optical imagery and the weather- and illumination-independent characteristics of synthetic aperture radar (SAR) data to streamline, automate, and map geographically reliable flood inundation extents. Utilizing the near real-time and cloud computing capabilities of Google Earth Engine (GEE), this process facilitates data acquisition and enables large-scale flood monitoring in an expeditious manner. Two major hurricanes along the U.S. Gulf Coast were evaluated: 1) the 2021 Hurricane Ida to the south of New Orleans, LA, USA, and 2) the 2017 Hurricane Harvey to the east of Houston, TX, USA. We devised a change detection and thresholding framework using multitemporal SAR imagery and validated the results with flood extent maps derived from Landsat 8 and Sentinel-2 optical imagery. We demonstrate that constant threshold values for flood extraction from SAR change detection indices are not ubiquitously suitable for all geographies; thus, we outline a heuristic that can be used to select thresholds suitable for specific sites through a fully automated sensitivity analysis. The results indicated high agreement between the SAR and optical imagery (77%–80%), with SAR providing the benefit of under-cloud detection. Furthermore, our results contribute to scaling the SAR approach to produce rapid and accurate information for decision-makers and emergency responders during time-sensitive flood events.

PCBA-Net: Pyramidal Convolutional Block Attention Network for Synthetic Aperture Radar Image Change Detection

Synthetic aperture radar (SAR) imagery change detection (CD) is still a crucial and challenging task. Recently, with the boom of deep learning technologies, many deep learning methods have been presented for SAR CD, and they achieve superior performance to traditional methods. However, most of the available convolutional neural networks (CNN) approaches use diminutive and single convolution kernel, which has a small receptive field and cannot make full use of the context information and some useful detail information of SAR images. In order to address the above drawback, pyramidal convolutional block attention network (PCBA-Net) is proposed for SAR image CD in this study. The proposed PCBA-Net consists of pyramidal convolution (PyConv) and convolutional block attention module (CBAM). PyConv can not only extend the receptive field of input to capture enough context information, but also handles input with incremental kernel sizes in parallel to obtain multi-scale detailed information. Additionally, CBAM is introduced in the PCBA-Net to emphasize crucial information. To verify the performance of our proposed method, six actual SAR datasets are used in the experiments. The results of six real SAR datasets reveal that the performance of our approach outperforms several state-of-the-art methods.

Unsupervised change detection in SAR images based on generalized likelihood ratio test and a two-stage morphological filter

ABSTRACT Generalized likelihood ratio test (GLRT) is an efficient method to generate difference image (DI) for change detection (CD) using synthetic aperture radar (SAR) images. GLRT is usually applied with a fixed-size moving window to the neighbourhood regions in multitemporal SAR images. The fixed window may be however not optimal for all the pixels under test. To solve disadvantages of the GLRT method, an adaptive circular window is proposed in this work. While the adaptive square window and the best fixed square window achieve an average Kappa coefficient of 83.55% and 82.12%, respectively, the adaptive circular window improves the average Kappa coefficient by 83.65% in six datasets. As another difficulty, speckle noise reduces quality of DI in SAR change detection. Three steps are considered to minimize effects of the speckle noise: (1) a two-stage morphological filter is suggested to reduce the speckle noise; (2) to generate DI, the adaptive circular window for generalized likelihood ratio test (ACWGLRT) is proposed that reduces influence of the speckle noise while preserves the edge details of multitemporal images; and (3) spatial fuzzy c-means (SFCM) is used to reduce effects of the residual speckle-noise during DI classification. The experimental results show superior performance of the proposed change detection method with respect to several competitors. The proposed method has the best Kappa coefficient and percentage correct classification (PCC) in four datasets of Ottawa, San Francisco, Farmland C, and Inland water.

UNSUPERVISED SAR CHANGE DETECTION METHOD BASED ON REFINED SAMPLE SELECTION

Abstract. In deep learning based synthetic aperture radar (SAR) change detection, selecting samples of high quality is a crucial step. In this work, we have proposed a refined sample selection algorithm for unsupervised SAR change detection. The propose and incorporation of volume control factors and multi-hierarchical fuzzy c-means (MH-FCM) algorithm generate samples of large diversity and high confidence, thus satisfying the needs for high quality samples. The method includes two phases: firstly, an enhanced difference image is constructed according to the difference consistency between single pixels and their neighbourhoods, and a triangular threshold segmentation method is then proposed to determine the volume control factors for sample selection. MH-FCM is developed to classify the log mean ratio difference image into 4 classes. Secondly, a dual-channel convolution neural network with an adaptive weighted loss is adopted to learn and predict the input and to obtain the change detection result. Experimental results of the Gaofen-3 dataset in Beijing have validated the effectiveness and usefulness of the proposed method.

A SAR change detection method based on an iterative guided filter and the log mean ratio

ABSTRACT Change detection is an essential step for synthetic aperture radar (SAR) image interpretation. We propose a change detection method that included a denoising method and a difference operator to improve the change precision. The SAR images are first transformed into logarithmic domain before filtering. And then, the log-intensity image is filtered by the iterative guided filter that is the combination of a traditional guided filter and iterative regularization technique. The operator based on the log-ratio (LR) and neighbourhood pixels is developed to generate the difference image, which can reflect the change trends between images effectively. The final image that consisted of changed pixels and unchanged pixels is obtained by using the fuzzy c-means (FCM) algorithm. The experimental results accomplished over two real SAR datasets demonstrate that the proposed method can improve the accuracy of change detection.

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.

An Adaptive and Adjustable Maximum-Likelihood Estimator for SAR Change Detection

Synthetic aperture radar (SAR) change detection can be broadly classified into two categories: noncoherent intensity change detection and coherent change detection (CCD). The former methods, belonging to the field of image processing, are theoretically suitable for all SAR images since only utilize the information of SAR magnitude, however, the detection precision cannot be guaranteed. The latter methods can show effective performances for most SAR image pairs using identical collection geometrics because of the basis of the probability and statistics theory. In this paper, we propose a novel change estimator to combine the advantages of the two kinds of algorithms in a theoretical derivation way. An intensity-based estimator, inspired by the derivation of the coherence estimator in CCD, is first proposed. It is a new maximum-likelihood (ML) change estimator maximizing the probability distribution function (pdf) of the ratio change statistic instead of SAR complex data. In addition, the simple linear iterative cluster (SLIC) algorithm is introduced to make the new estimator adjustable because changes at different degrees can be extracted with varying settings of the superpixels number, which is further demonstrated in real SAR images. Finally, experiments in SAR image pairs of different statistical characteristics show that the proposed estimator can yield higher-contrast SAR change detection images than the other five common change statistics and obtain better change detection maps than the other four classic thresholding methods.

Change Type Recognition for SAR Images Using Statistical Bidirectional LSTM Network With Few Labeled Samples

Change detection in synthetic aperture radar (SAR) images has garnered significant research interest. However, to date, only the change area can be obtained, which seriously restricts further development of SAR image applications. To solve this problem, this paper proposes a change type recognition method for SAR images based on a statistical bidirectional long short-term memory (LSTM) network. The proposed method can obtain the changed area and identify the land type change between pairs of SAR images. Considering the statistical characteristics and sample number of SAR images, change detection and type recognition are realized in a unified framework. First, feature extraction is performed through the statistical features of the original SAR image and difference image (DI). Then, a bidirectional LSTM network is used to identify the change types and obtain the change detection results under the small sample deep learning network. On two sets of medium-low resolution SAR image data and one set of GaoFen-3 high-resolution real SAR image data, our method produced high-quality results under small sample conditions.

Mapping the 2021 October Flood Event in the Subsiding Taiyuan Basin by Multitemporal SAR Data

A flood event induced by heavy rainfall hit the Taiyuan basin in north China in early October of 2021. In this study, we map the flood event process using the multi-temporal synthetic aperture radar (SAR) images acquired by Sentinel-1. First, we develop a spatiotemporal filter based on low-rank tensor approximation (STF-LRTA) for removing the speckle noise in SAR images. Next, we employ the classic log-ratio change indicator and the minimum error threshold algorithm to characterize the flood using the filtered images. Finally, we relate the flood inundation to the land subsidence in the Taiyuan basin by jointly analyzing the multi-temporal SAR change detection results and interferometric SAR (InSAR) time-series measurements (pre-flood). The validation experiments compare the proposed filter with the Refined-Lee filter, Gamma filter, and an SHPS-based multi-temporal SAR filter. The results demonstrate the effectiveness and advantage of the proposed STF-LRTA method in SAR despeckling and detail preservation, and the applicability to change scenes. The joint analyses reveal that land subsidence might be an important contributor to the flood event, and the flood recession process linearly correlates with time and subsidence magnitude.

FLOOD MONITORING USING SENTINEL-1 SAR DATA: A CASE STUDY BASED ON AN EVENT OF 2018 AND 2019 SOUTHERN PART OF KERALA

Abstract. Flood is a natural hazard influenced by rainfall and dam collapse, which propels release of enormous amount of water. In the last two decades flood is the second largest natural hazards occurred worldwide, which caused serious damage to life properties, settlements and economic activities. Flood mapping is a process that is useful for assessment and reduces the risk factor during the flood. An effective monitoring of flood prone area is necessary to handle GIS techniques and without remote sensing data it is difficult to identify the flooded area in this study Microwave remote sensing plays a lead role in natural hazards, here Synthetic Aperture Radar (SAR) data is the best way for monitoring flood hazards. In this study Southern part of the Kerala is chosen as the study area, In August 2018, during the south west monsoon due to heavy rainfall a severe flood affected the southern part of Kerala which saw a 37% increase in the rate of normal rainfall. The objective of the study is to find the flood zone area using SAR data and estimate the flood occurrence over a period of time. However a satellite imagery of optical data is used to analyse the pre and post event of flood, but during a heavy rainfall, cloud may interrupt the data acquisition. SAR satellite imagery fromSentinel-1A is a cloud penetrating data available in all kind of weather conditions during day and night time, which provides a good source of high resolution data sets. To identify the flood affected area an adapted technology of threshold methodology developed by using SAR data and change detection for the year 2018 and 2019, will illustrate flood extended part in southern part of Kerala. The result shows the estimation of flood extended part of the study area and the damages occurred during a flooded time period of post and pre event, vulnerability assessing of crop and agriculture is to obtain an intensity of the damaged areas which is closely associated with the river channel, the Polarization displays a similar sequence for amount of flooding. The study helps to find the reason of flood extent and to equip with better planning for risk reduction and management during a flooding period.

Winter wheat planting area extraction using SAR change detection

ABSTRACT With its all-day and all-weather imaging capability, Synthetic Aperture Radar (SAR) has shown great potential in crop identification. This letter puts forward a novel method of extracting winter wheat planting area by means of SAR change detection. Based on the phenological differences between winter wheat and other crops, the Difference Image (DI) is generated firstly by the different temporal SAR images. Then, Object Markov Random Field (OMRF) model is used to DI pre-classification. Finally, Convolutional Neural Network (CNN) is utilized to obtain the better area extraction result of winter wheat. The area extraction accuracy is proved by the field survey data, with an accuracy of 90.53%. This research can provide a new idea and method for agricultural remote sensing monitoring.

A Wavelength-Resolution SAR Change Detection Method Based on Image Stack through Robust Principal Component Analysis

Recently, it was demonstrated that low-frequency wavelength-resolution synthetic aperture radar (SAR) images could be considered to follow an additive mixing model due to their backscatter characteristics. This simplification allows for the use of source separation methods, such as robust principal component analysis (RPCA) via principal component pursuit (PCP), for detecting changes in those images. In this manuscript, a change detection method for wavelength-resolution SAR images based on image stack through RPCA is proposed. The method aims to explore both the temporal and flight heading diversity of a set of wavelength-resolution multitemporal SAR images in order to detect concealed targets in forestry areas. A heuristic based on three rules for better exploring the RPCA results is introduced, and a new configurable parameter for false alarm reduction based on the analysis of image windows is proposed. The method is evaluated using real data obtained from measurements of the ultrawideband (UWB) very high-frequency (VHF) SAR system CARABAS-II. Experiments for stacks of four and seven reference images are conducted, and the use of reference images acquired with different flight headings is explored. The results indicate that a gain in performance can be achieved by using large image stacks containing, at least, one image of each possible flight heading of the data set, which can result in a probability of detection (PD) above 99% for a false alarm rate (FAR) as low as one false alarm per three square kilometers. Furthermore, it is demonstrated that high PD and low FAR can be achieved, also considering images from similar flight headings as reference images.

Earth Environmental Monitoring Using Multi-Temporal Synthetic Aperture Radar: A Critical Review of Selected Applications

Microwave remote sensing has widely demonstrated its potential in the continuous monitoring of our rapidly changing planet. This review provides an overview of state-of-the-art methodologies for multi-temporal synthetic aperture radar change detection and its applications to biosphere and hydrosphere monitoring, with special focus on topics like forestry, water resources management in semi-arid environments and floods. The analyzed literature is categorized on the base of the approach adopted and the data exploited and discussed in light of the downstream remote sensing market. The purpose is to highlight the main issues and limitations preventing the diffusion of synthetic aperture radar data in both industrial and multidisciplinary research contexts and the possible solutions for boosting their usage among end-users.

New Forms of Likelihood Ratio Test for SAR Change Detection

The Neyman-Pearson lemma, i.e., the likelihood ratio test and its generalized version, have been used for the development of the synthetic aperture radar (SAR) change detection methods. For detecting changes caused by targets on the ground such as vehicles, a target model, or at least certain assumptions concerning the targets, is always required for deriving a statistical hypothesis test. Without the prior knowledge on targets, it is difficult to make any assumption. An inappropriate assumption can degrade change detection performance significantly. To avoid this technical issue, some new forms of likelihood ratio test for SAR change detection are introduced in this paper. The proposed forms are shown to be flexible. They can be utilized to develop change detection methods for different types of data, e.g., data in scalar form, data in vector form, data represented in complex number, and data represented in real number. The flexibility of the proposed forms is also shown by the capability to implement change detection methods in the iterative and non-iterative ways. For the illustration purpose, a new change detection method is developed on one of the introduced forms and tested with TanDEM-X data measured in Karlshamn, Sweden in 2016.

Multitemporal Polarimetric SAR Change Detection for Crop Monitoring and Crop Type Classification

The interpretation of multidimensional Synthetic Aperture Radar (SAR) data often requires expert knowledge. In fact, it requires to simultaneously consider several time series of polarimetric features to understand the physical changes of a target and its temporal evolution. To characterise the changes over time, Multitemporal Polarimetric SAR (MTPolSAR) change detection has been introduced in the literature in [1] and [2]. However, previous methods either only exploit intensity of changes or the resulting changed scattering mechanisms are not guaranteed to represent physical changes of the target. This paper presents a variation in the change detector used in [2] based on the difference of covariance matrices that characterise the polarimetric information, allowing for an intuitive representation and characterisation of physical changes of a target and its dynamics. We show the results of this method for monitoring growth stages of rice crops and present a novel application of the method for crop type mapping from MT-PolSAR data. We compare its performance with a neural network-based classifier that uses time series of PolSAR features derived from a target covariance matrix decomposition as input. Experimental results show that the classification performance of the proposed method and the baseline are comparable, with differences between the two methods in the overall balanced accuracy and the F1-macro metrics of around 2% and 3%, respectively. The method presented here achieves similar classification performances of a traditional PolSAR data classifier while providing additional advantages in terms of interpretability and insights about the physical changes of a target over time.