Multitemporal Synthetic Aperture Radar Images Research Articles

Two-Phase Object-Based Deep Learning for Multi-Temporal SAR Image Change Detection

Change detection is one of the fundamental applications of synthetic aperture radar (SAR) images. However, speckle noise presented in SAR images has a negative effect on change detection, leading to frequent false alarms in the mapping products. In this research, a novel two-phase object-based deep learning approach is proposed for multi-temporal SAR image change detection. Compared with traditional methods, the proposed approach brings two main innovations. One is to classify all pixels into three categories rather than two categories: unchanged pixels, changed pixels caused by strong speckle (false changes), and changed pixels formed by real terrain variation (real changes). The other is to group neighbouring pixels into superpixel objects such as to exploit local spatial context. Two phases are designed in the methodology: (1) Generate objects based on the simple linear iterative clustering (SLIC) algorithm, and discriminate these objects into changed and unchanged classes using fuzzy c-means (FCM) clustering and a deep PCANet. The prediction of this Phase is the set of changed and unchanged superpixels. (2) Deep learning on the pixel sets over the changed superpixels only, obtained in the first phase, to discriminate real changes from false changes. SLIC is employed again to achieve new superpixels in the second phase. Low rank and sparse decomposition are applied to these new superpixels to suppress speckle noise significantly. A further clustering step is applied to these new superpixels via FCM. A new PCANet is then trained to classify two kinds of changed superpixels to achieve the final change maps. Numerical experiments demonstrate that, compared with benchmark methods, the proposed approach can distinguish real changes from false changes effectively with significantly reduced false alarm rates, and achieve up to 99.71% change detection accuracy using multi-temporal SAR imagery.

SAR Image Change Detection Based on Nonlocal Low-Rank Model and Two-Level Clustering

Change detection (CD) has found a wide range of applications in many fields. In this article, we propose a novel nonlocal low-rank (NLR) based method for multitemporal synthetic aperture radar image CD. This method jointly exploits the powerful NLR-based despeckling and the effective cascade clustering. First, the NLR model is used to generate the difference image (DI), which consists of a patch grouping process and a low-rank minimizing process. Especially, the NLR minimization model contains a data fidelity term, which is based on the statistical distribution of speckle noise, and a regularization term, which uses the weighted nuclear norm. Then, the alternating direction methods of multipliers is introduced to solve this minimization problem. Second, after DI is generated, the principal component analysis is employed to extract the feature and a two-level clustering method is used to generate the final change map, which separates the intermediate class by using the neighbor information with Gaussian weighted distance. Experiment results demonstrate the effectiveness of the proposed method by comparing with some state-of-the-art methods.

An Approach to Unsupervised Detection of Fully and Partially Destroyed Buildings in Multitemporal VHR SAR Images

In the presence of abrupt change events, multitemporal synthetic aperture radar (SAR) data represent a precious supporting tool for quantifying changes, in particular in urban areas. A large amount of SAR data also exists at very high resolution (VHR). Over urban areas, the introduction of the VHR imagery moves the analysis down to the single building scale. However, VHR imagery is also characterized by a large heterogeneity and a more complex representation of the building. In this work, we propose a geometrical model for describing partially destroyed buildings and derive the corresponding multitemporal backscattering signature by applying the ray-tracing method. The model is integrated into an unsupervised automatic approach for the detection of both fully and partially destroyed buildings. The strategy considers a hierarchical structure of the changes. Experimental results conducted on two multitemporal VHR SAR datasets show a large robustness of the approach and good accuracy in the detection of the classes for damaged buildings with different severity levels.

Differentially Deep Subspace Representation for Unsupervised Change Detection of SAR Images

Temporal analysis of synthetic aperture radar (SAR) time series is a basic and significant issue in the remote sensing field. Change detection as well as other interpretation tasks of SAR images always involves non-linear/non-convex problems. Complex (non-linear) change criteria or models have thus been proposed for SAR images, instead of direct difference (e.g., change vector analysis) with/without linear transform (e.g., Principal Component Analysis, Slow Feature Analysis) used in optical image change detection. In this paper, inspired by the powerful deep learning techniques, we present a deep autoencoder (AE) based non-linear subspace representation for unsupervised change detection with multi-temporal SAR images. The proposed architecture is built upon an autoencoder-like (AE-like) network, which non-linearly maps the input SAR data into a latent space. Unlike normal AE networks, a self-expressive layer performing like principal component analysis (PCA) is added between the encoder and the decoder, which further transforms the mapped SAR data to mutually orthogonal subspaces. To make the proposed architecture more efficient at change detection tasks, the parameters are trained to minimize the representation difference of unchanged pixels in the deep subspace. Thus, the proposed architecture is namely the Differentially Deep Subspace Representation (DDSR) network for multi-temporal SAR images change detection. Experimental results on real datasets validate the effectiveness and superiority of the proposed architecture.

Mapping and assessing spatial extent of floods from multitemporal synthetic aperture radar images: a case study on Brahmaputra River in Assam State, India.

Brahmaputra is one of the perennial rivers in India which causes floods every year in the north-east state of Assam causing hindrance to normal life and damage to crops. The availability of temporal Remote Sensing (RS) data helps to study the periodical changes caused by flood event and its eventual effect on natural environment. Integrating RS and GIS methods paved a way for effective flood mapping over a large spatial extent which helps to assess the damage accurately for mitigation. In the present study, multitemporal Sentinel-1A data is exploited to assess the 2017 flood situation of Brahmaputra River in Assam state. Five data sets that are taken during flood season and one reference data taken during the non-monsoon season are used to estimate the area inundated under floods for the quantification of damage assessment. A visual interpretation map is produced using colour segmentation method by estimating the thresholds from histogram analysis. A new method is developed to identify the optimum value for threshold from statistical distribution of Synthetic Aperture Radar (SAR) data that separates flooded water and non-flooded water. From this method, the range of backscatter values for normal water are identified as - 18 to - 30 dB and the range is identified as - 19 to - 24 dB for flooded water. The results showed that the method is able to separate the flooded and non-flooded region on the microwave data set, and the derived flood extent using this method shows the inundated area of 3873.14 Km2 on peak flood date for the chosen study area.

FLOOD MAPPING AND PERMANENT WATER BODIES CHANGE DETECTION USING SENTINEL SAR DATA

Abstract. Producing flood maps that can be carried out quickly for disaster management applications is essential to reduce the human and socio-economic losses. In addition, mapping and change detection of water bodies as an essential natural resource is imperative for robust operations and sustainable management. Synthetic Aperture Radar (SAR) sensors with long wavelengths have a high potential for delineating the extent of the flooded areas and providing timely and accurate maps of surface water for risk mitigation and disaster or sustainable management. In this study, multi-temporal Sentinel-1 C-band SAR images were utilized to investigate the performance of the sensor backscatter image on permanent water bodies monitoring and flooded areas mapping. Lake Urmia as a permanent water system and two floods in Golestan and Khuzestan provinces of Iran have been investigated. The backscatter values of an image acquired before the event that is referred as an Archive image and another one after the event as a Crisis image are analysed. As a preliminary result, it is concluded that with overlaying of the two bands from Archive and Crisis images and creating a color composite image, the permanent water bodies have a uniformly dark return due to the very low backscatter in both images. The flooded areas and changes in water level show relatively higher backscatter in the Crisis image, whereas the other land cover features indicate very high backscatter values with tones of grey. Therefore, Sentinel-1 SAR data provides beneficial information on flood risk management and change detection.

Sea Ice Change Detection in SAR Images Based on Convolutional-Wavelet Neural Networks

Sea ice change detection from synthetic aperture radar (SAR) images can be regarded as a classification procedure, in which pixels are classified into changed and unchanged classes. However, existing methods usually suffer from the intrinsic speckle noise of multitemporal SAR images. To solve the problem, this letter presents a change detection method based on convolutional-wavelet neural networks (CWNNs). In CWNN, dual-tree complex wavelet transform is introduced into convolutional neural networks for changed and unchanged pixels’ classification, and then, the effect of speckle noise is effectively reduced. In addition, a virtual sample generation scheme is employed to create samples for CWNN training, and the problem of limited samples is alleviated. Experimental results on two real SAR image data sets demonstrate the effectiveness and robustness of the proposed method.

Adaptive Generalized Likelihood Ratio Test for Change Detection in SAR Images

Generalized likelihood ratio test (GLRT) was widely used in the change detection of synthetic aperture radar (SAR) images and employed as a competitive method in many studies. GLRT is applied to the neighborhood areas corresponding to the same geographical area in multitemporal SAR images. Generally, the difference image is acquired by applying the GLRT on a moving window empirically determined by the user, which is clearly unreasonable because the different pixels in an image may have different optimal windows. To overcome this drawback, we propose an adaptive GLRT (AGLRT) method for change detection in SAR images. AGLRT adaptively selects the homogeneity window for each pixel and can decrease the uncertainty of change detection due to manual selection of the moving window. Experiments are conducted on two data sets to confirm the performance of the proposed method. Experimental results show that AGLRT can both suppress the influence of noise and preserve edge details and improve the accuracy of change detection.

Multitemporal SAR Image Despeckling Based on a Scattering Covariance Matrix of Image Patch.

This paper presents a despeckling method for multitemporal images acquired by synthetic aperture radar (SAR) sensors. The proposed method uses a scattering covariance matrix of each image patch as the basic processing unit, which can exploit both the amplitude information of each pixel and the phase difference between any two pixels in a patch. The proposed filtering framework consists of four main steps: (1) a prefiltering result of each image is obtained by a nonlocal weighted average using only the information of the corresponding time phase; (2) an adaptively temporal linear filter is employed to further suppress the speckle; (3) the final output of each patch is obtained by a guided filter using both the original speckled data and the filtering result of step 3; and (4) an aggregation step is used to tackle the multiple estimations problem for each pixel. The despeckling experiments conducted on both simulated and real multitemporal SAR datasets reveal the pleasing performance of the proposed method in both suppressing speckle and retaining details, when compared with both advanced single-temporal and multitemporal SAR despeckling techniques.

Automatically delineating the calving front of Jakobshavn Isbræ from multitemporal TerraSAR-X images: a deep learning approach

Abstract. The calving fronts of many tidewater glaciers in Greenland have been undergoing strong seasonal and interannual fluctuations. Conventionally, calving front positions have been manually delineated from remote sensing images. But manual practices can be labor-intensive and time-consuming, particularly when processing a large number of images taken over decades and covering large areas with many glaciers, such as Greenland. Applying U-Net, a deep learning architecture, to multitemporal synthetic aperture radar images taken by the TerraSAR-X satellite, we here automatically delineate the calving front positions of Jakobshavn Isbræ from 2009 to 2015. Our results are consistent with the manually delineated products generated by the Greenland Ice Sheet Climate Change Initiative project. We show that the calving fronts of Jakobshavn's two main branches retreated at mean rates of -117±1 and -157±1 m yr−1, respectively, during the years 2009 to 2015. The interannual calving front variations can be roughly divided into three phases for both branches. The retreat rates of the two branches tripled and doubled, respectively, from phase 1 (April 2009–January 2011) to phase 2 (January 2011–January 2013) and then stabilized to nearly zero in phase 3 (January 2013–December 2015). We suggest that the retreat of the calving front into an overdeepened basin whose bed is retrograde may have accelerated the retreat after 2011, while the inland–uphill bed slope behind the bottom of the overdeepened basin has prevented the glacier from retreating further after 2012. Demonstrating through this successful case study on Jakobshavn Isbræ and due to the transferable nature of deep learning, our methodology can be applied to many other tidewater glaciers both in Greenland and elsewhere in the world, using multitemporal and multisensor remote sensing imagery.

An Unsupervised SAR Change Detection Method Based on Stochastic Subspace Ensemble Learning

As synthetic aperture radar (SAR) is playing an increasingly important role in Earth observations, many new methods and technologies have been proposed for change detection using multi-temporal SAR images. Especially with the development of deep learning, numerous methods have been proposed in recent years. However, the requirement to have a certain number of high-quality samples has become one of the main reasons for the limited development of these methods. Thus, in this paper, we propose an unsupervised SAR change detection method that is based on stochastic subspace ensemble learning. The proposed method consists of two stages: The first stage involves the automatic determination of high-confidence samples, which includes a fusion strategy and a refinement process; and the second stage entails using the stochastic subspace ensemble learning module, which contains three steps: obtaining the subsample sets, establishing and training a two-channel network, and applying the prediction results and an ensemble strategy. The subsample sets are used to solve the problem of imbalanced samples. The two-channel networks are used to extract high-dimensional features and learn the relationship between the neighborhood of the pixels in the original images and the labels. Finally, by using an ensemble strategy, the results predicted by all patches reclassified in each network are integrated as the detection result. The experimental results of different SAR datasets prove the effectiveness and the feasibility of the proposed method.

Small-Target Detection between SAR Images Based on Statistical Modeling of Log-Ratio Operator.

The log-ratio (LR) operator is well suited for change detection in synthetic aperture radar (SAR) amplitude or intensity images. In applying the LR operator to change detection in multi-temporal SAR images, a crucial problem is how to develop precise models for the LR statistics. In this study, we first derive analytically the probability density function (PDF) of the LR operator. Subsequently, the PDF of the LR statistics is parameterized by three parameters, i.e., the number of looks, the coherence magnitude, and the true intensity ratio. Then, the maximum-likelihood (ML) estimates of parameters in the LR PDF are also derived. As an example, the proposed statistical model and corresponding ML estimation are used in an operational application, i.e., determining the constant false alarm rate (CFAR) detection thresholds for small target detection between SAR images. The effectiveness of the proposed model and corresponding ML estimation are verified by applying them to measured multi-temporal SAR images, and comparing the results to the well-known generalized Gaussian (GG) distribution; the usefulness of the proposed LR PDF for small target detection is also shown.

Efficient Identification of Corn Cultivation Area with Multitemporal Synthetic Aperture Radar and Optical Images in the Google Earth Engine Cloud Platform

The distribution of corn cultivation areas is crucial for ensuring food security, eradicating hunger, adjusting crop structures, and managing water resources. The emergence of high-resolution images, such as Sentinel-1 and Sentinel-2, enables the identification of corn at the field scale, and these images can be applied on a large scale with the support of cloud computing technology. Hebei Province is the major production area of corn in China, and faces serious groundwater overexploitation due to irrigation. Corn was mapped using multitemporal synthetic aperture radar (SAR) and optical images in the Google Earth Engine (GEE) cloud platform. A total of 1712 scenes of Sentinel-2 data and 206 scenes of Sentinel-1 data acquired from June to October 2017 were processed to composite image metrics as input to a random forest (RF) classifier. To avoid speckle noise in the classification results, the pixel-based classification result was integrated with the object segmentation boundary completed in eCognition software to generate an object-based corn map according to crop intensity. The results indicated that the approach using multitemporal SAR and optical images in the GEE cloud platform is reliable for corn mapping. The corn map had a high F1-Score of 90.08% and overall accuracy of 89.89% according to the test dataset, which was not involved in model training. The corn area estimated from optical and SAR images was well correlated with the census data, with an R2 = 0.91 and a root mean square error (RMSE) of 470.90 km2. The results of the corn map are expected to provide detailed information for optimizing crop structure and water management, which are critical issues in this region.

INTEGRATING MULTI-TEMPORAL SAR IMAGES AND GPS DATA TO MONITOR THREE-DIMENSIONAL LAND SUBSIDENCE

Abstract. Synthetic aperture radar (SAR) is an effective means of monitoring land subsidence, and differential interferometric SAR (DInSAR) is commonly used to acquire the necessary data. In particular, persistent scatterer interferometry (PSI) can be used to measure land subsidence accurately over a wide area from multi-temporal SAR images. However, the estimated displacement is obtained only in the radar line-of-sight (LOS) direction, making it necessary to develop a method for measuring three-dimensional displacements by combining multidirectional observations. Therefore, we propose herein a method for estimating three-dimensional displacement velocities by combining the results from PSI and geodetic deformation measurements, namely, Global Positioning System and leveling data. We apply the least-squares method to Kansai International Airport in Japan by using 13 ALOS-2/PALSAR-2 ascending images from 2014 to 2018 and 17 ALOS-2/PALSAR-2 descending images from 2015 to 2018. In validation, the rootmean- square errors are 14, 16, and 14 mm/year for the east–west, north–south, and vertical components, respectively, showing that combining PSI results and geodetic deformation measurements is effective for monitoring land subsidence.

SAR Image Change Detection Using PCANet Guided by Saliency Detection

The selection of training samples is important for the accuracy and efficiency of the synthetic aperture radar (SAR) image change detection task. However, training samples are traditionally extracted from the whole image, which leads to longer training time and an unbalanced number of pixels in the changed and unchanged classes. To overcome this problem, we propose a novel change detection method combining saliency detection with a principal component analysis network, named SDPCANet. To enhance the reliability of the training samples and reduce the amount of training samples, the SDPCANet uses context-aware saliency detection to obtain the salient region, from which the training samples are extracted. In addition, to alleviate the gap between the numbers of training samples in two classes, we regulate the candidate samples using the uniform-selecting strategy to enhance the reliability of the training samples for the SDPCANet. Then, the SDPCANet is trained with the extracted training samples and the remaining pixels are classified in the salient region to obtain the final change map. The experimental results on four sets of multitemporal SAR images demonstrate that the SDPCANet outperforms the reference methods proposed recently.

Detecting Positive and Negative Changes From SAR Images by an Evolutionary Multi-Objective Approach

In general, changes in the multitemporal synthetic aperture radar (SAR) images are detected by classifying the SAR ratio images into the changed and unchanged classes. However, multitemporal SAR images have either increase or decrease in the backscattering values. Therefore, the changed areas can be further classified into positive and negative changed classes. This paper presents an unsupervised change detection approach for detecting the positive and negative changes based on a multi-objective evolutionary algorithm. In this paper, the widely adopted mean-ratio and log-ratio operators are extended to generate SAR ratio images for distinguishing the positive and negative changes. In order to reduce the corruption of speckle noise present in the multitemporal SAR images, a fuzzy cluster validity index is established to exploit local spatial and gray level information. Then the objective functions are simultaneously optimized by a multi-objective evolutionary algorithm. The experimental results on two simulated data sets and three real SAR data sets confirm the effectiveness of the proposed method.

SAR Image Change Detection Based on Mathematical Morphology and the K-Means Clustering Algorithm

Synthetic aperture radar (SAR) images have been applied in disaster monitoring and environmental monitoring. With the objective of reducing the effect of noise on SAR image change detection, this paper presents an approach based on mathematical morphology filtering and K-means clustering for SAR image change detection. First, the multiplicative noise in two SAR images is transformed into additive noise by a logarithmic transformation. Second, the two multitemporal SAR images are denoised by morphological filtering. Third, the mean ratio operator and subtraction operator are used to obtain two difference images. Median filtering is applied to the difference image based on a simple combination of the two difference images. Since an accurate statistical model for the difference image cannot be easily established, the results of change detection are clustered using the K-means algorithm. A comparison of the experimental approach with other algorithms shows that the proposed algorithm can decrease the detection time and improve the detection result.

It is a misunderstanding that log ratio outperforms ratio in change detection of SAR images

ABSTRACT Ratio and log ratio operators were widely used in change detection of synthetic aperture radar (SAR) images. It is well known for the researchers who focus on change detection of SAR images that log ratio outperforms ratio because logarithmic transformation can not only transform multiplicative noise into additive noise but also compress the value range of ratio. Nevertheless, this is a misunderstanding because 1) we have proven that the difference images before and after logarithmic transformation have the same receiver operating characteristic (ROC) curve; and 2) by comparing their capability in detecting different change types, we figured out the reason of the inaccurate results is that there are two intensity change types in multi-temporal SAR images and many scholars regarded them as one type (intensity increasing or decreasing). Experimental results on three original and stitched data sets confirm that: log ratio outperforms ratio is a misunderstanding in change detection of SAR images.

Laplacian pyramid-based change detection in multitemporal SAR images

ABSTRACT The Synthetic Aperture Radar (SAR) has many attractive and desired features to cope with uncertain weather conditions and also provides superlative resolution in images. In this paper, a unique multiscale approach of change detection (CD) that integrates the preprocessing and CD technique of SAR imagery is discussed. Condensed anisotropic diffusion method is employed as a preprocessing tool for despeckling, and the resultant image is processed by multiscale approach in the Laplacian pyramid (LP) domain. In each layer of LP, the difference between the pyramid coefficient of two images of the same area obtained at different periods is estimated through log ratio operation. Each layer of pyramid coefficient has explicit features at particular scale. Fine scale related to a band pass layer localizes edges of the change area and the coarse scale related to a low pass layer preserves more detail information of the change region. Reconstruction of LP provides exact difference image with perfect boundary. Otsu's algorithm is used to generate binary change map to distinguish changed and unchanged pixels. The efficiency of the proposed method is tested by using simulated and real SAR image datasets. The confusion matrix parameters are used to prove competence of the proposed CD method.

Multi-temporal SAR image classification of coastal plain wetlands using a new feature selection method and random forests

ABSTRACTEfficient and reliable wetland mapping is essential for wetland resource management and conservation planning. Repeated attempts at classifying dense wetland vegetation has often failed to produce a high-quality product because of poor penetration of electromagnetic signals that cannot detect sub-surface water, and because of associated redundant information. In this study, a two-step classification procedure was developed for classifying typical coastal plain wetlands from multi-temporal Advanced Land Observing Satellite (ALOS)/Phased Array type L-band Synthetic Aperture Radar (PALSAR)-1 data. First, a new statistical strategy for feature selection was proposed by combining manual and automatic selection according to the backscattering mechanism differences between various land-cover types. Then the Random Forest (RF) classifier was applied to evaluate the established feature combinations for wetland classification. The experimental results show that the method described has high classification accuracies over the test site, with overall accuracies and kappa coefficients (κ) of above 89.79% and 0.88, respectively. This indicates that the presented technique is effective in dealing with high-dimensional feature space and may lead to significant improvements in multi-temporal Synthetic Aperture Radar (SAR) image-based wetland classification.