Synthetic Aperture Radar Intensity Images Research Articles

Urban Impervious Surface Extraction Based on Deep Convolutional Networks Using Intensity, Polarimetric Scattering and Interferometric Coherence Information from Sentinel-1 SAR Images

Urban impervious surface area is a key indicator for measuring the degree of urban development and the quality of an urban ecological environment. However, optical satellites struggle to effectively play a monitoring role in the tropical and subtropical regions, where there are many clouds and rain all year round. As an active microwave sensor, synthetic aperture radar (SAR) has a long wavelength and can penetrate clouds and fog to varying degrees, making it very suitable for monitoring the impervious surface in such areas. With the development of SAR remote sensing technology, a more advanced and more complex SAR imaging model, namely, polarimetric SAR, has been developed, which can provide more scattering information of ground objects and is conducive to improving the extraction accuracy of impervious surface. However, the current research on impervious surface extraction using SAR data mainly focuses on the use of SAR image intensity or amplitude information, and rarely on the use of phase and polarization information. To bridge this gap, based on Sentinel-1 dual-polarized data, we selected UNet, HRNet, and Deeplabv3+ as impervious surface extraction models; and we input the intensity, coherence, and polarization features of SAR images into the respective impervious surface extraction models to discuss their specific performances in urban impervious surface extraction. The experimental results show that among the intensity, coherence, and polarization features, intensity is the most useful feature in the extraction of urban impervious surface based on SAR images. We also analyzed the limitations of extracting an urban impervious surface based on SAR images, and give a simple and effective solution. This study can provide an effective solution for the spatial-temporal seamless monitoring of an impervious surface in cloudy and rainy areas.

On the Use of Ocean Surface Doppler Velocity for Oceanic Front Extraction From Chinese Gaofen-3 SAR Data

Oceanic front extraction from synthetic aperture radar (SAR) images is of great significance to the study of marine ecosystems. At present, the methods for oceanic front extraction are usually based on SAR intensity images, which treat oceanic fronts as edge-like features in the SAR images. However, affected by radar parameters and sea state, sometimes, oceanic front signatures may not be clearly visible in the SAR intensity images. Therefore, existing methods are limited. In order to solve this problem, a method combining intensity and Doppler information for oceanic front extraction is proposed. Using Chinese Gaofen-3 single-look complex (SLC) data, three cases where oceanic front signatures are clearly visible, partially visible, and extremely weak in the SAR intensity images are investigated, which demonstrate how the Doppler velocity gradient across a front can be leveraged to enhance the extraction of oceanic fronts from SAR data. The results show that the Doppler data, as supplementary information, not only can complement the oceanic fronts extracted from SAR intensity images, but also can be used as a reference for the oceanic fronts extracted from SAR intensity images.

Deep-learning-based single-image height reconstruction from very-high-resolution SAR intensity data

Originally developed in fields such as robotics and autonomous driving with image-based navigation in mind, deep learning-based single-image depth estimation (SIDE) has found great interest in the wider image analysis community. Remote sensing is no exception, as the possibility to estimate height maps from single aerial or satellite imagery bears great potential in the context of topographic reconstruction. A few pioneering investigations have demonstrated the general feasibility of single image height prediction from optical remote sensing images and motivate further studies in that direction. With this paper, we present the first-ever demonstration of deep learning-based single image height prediction for the other important sensor modality in remote sensing: synthetic aperture radar (SAR) data. Besides the adaptation of a convolutional neural network (CNN) architecture for SAR intensity images, we present a workflow for the generation of training data, and extensive experimental results for different SAR imaging modes and test sites. Since we put a particular emphasis on transferability, we are able to confirm that deep learning-based single-image height estimation is not only possible, but also transfers quite well to unseen data, even if acquired by different imaging modes and imaging parameters.

A Multiscale Joint Deep Neural Network for Glacier Contour Extraction

Rapid and accurate acquisition of glacier regional changes is of great significance to the study of glaciers. Among all satellite images, Synthetic Aperture Radar (SAR) data has a great advantage in monitoring the glaciers in harsh weather conditions. Conventionally, glacier boundaries are manually delineated on images. However, this is a time-consuming process, especially in the batch process of large-area data. In this paper, we propose a Multiscale Joint Deep Neural Network (MJ-DNN) for large-scale glaciers contour extraction using single-polarimetric SAR intensity images. Based on U-Net, the proposed method has been improved in three aspects. First, Atrous Separable Convolution is used instead of convolution with the down-sampling part. Second, we propose a multiscale joint convolution layer to obtain information at multiple scales. Third, we deepen the network with the residual connection structure for higher-level features. At the final layer, we optimize the network result with the conditional random field method. To validate our approach, we test it on three glaciers and we compare the segmentation results of four different methods in parallel. The results show that the intersection over the union of the proposed method is the most efficient.

Detection of Collapsed Bridges from Multi-Temporal SAR Intensity Images by Machine Learning Techniques

Bridges are an important part of road networks in an emergency period, as well as in ordinary times. Bridge collapses have occurred as a result of many recent disasters. Synthetic aperture radar (SAR), which can acquire images under any weather or sunlight conditions, has been shown to be effective in assessing the damage situation of structures in the emergency response phase. We investigate the backscattering characteristics of washed-away or collapsed bridges from the multi-temporal high-resolution SAR intensity imagery introduced in our previous studies. In this study, we address the challenge of building a model to identify collapsed bridges using five change features obtained from multi-temporal SAR intensity images. Forty-four bridges affected by the 2011 Tohoku-oki earthquake, in Japan, and forty-four bridges affected by the 2020 July floods, also in Japan, including a total of 21 collapsed bridges, were divided into training, test, and validation sets. Twelve models were trained, using different numbers of features as input in random forest and logistic regression methods. Comparing the accuracies of the validation sets, the random forest model trained with the two mixed events using all the features showed the highest capability to extract collapsed bridges. After improvement by introducing an oversampling technique, the F-score for collapsed bridges was 0.87 and the kappa coefficient was 0.82, showing highly accurate agreement.

Processing Framework for Landslide Detection Based on Synthetic Aperture Radar (SAR) Intensity-Image Analysis

We present an object-based image analysis (OBIA) approach to identify temporal changes in radar-intensity images and to locate land-cover changes caused by mass-wasting processes at small to large scales, such as landslides. Our approach is based upon change detection in SAR intensity images that remain in their original imaging coordinate system rather than being georeferenced and map-projected, in order to reduce accumulation of filtering artifacts and other unwanted effects that would deteriorate the detection efficiency. Intensity images in their native slant-range coordinate frame allow for a consistent level of detection of land-cover changes. By analyzing intensity images, a much faster response can be achieved and images can be processed as soon as they are made publicly available. In this study, OBIA was introduced to systematically and semiautomatically detect landslides in image pairs with an overall accuracy of at least 60% when compared to in-situ landslide inventory data. In this process, the OBIA feature extraction component was supported by derived data from a polarimetric decomposition as well as by texture indices derived from the original image data. The results shown here indicate that most of the landslide events could be detected when compared to a closer visual inspection and to established inventories, and that the method could therefore be considered as a robust detection tool. Significant deviations are caused by the limited geometric resolution when compared to field data and by an additional detection of stream-related sediment redeposition in our approach. This overdetection, however, turns out to be potentially beneficial for assessing the risk situation after landslide events.

Retrieving Soil Moisture Over Soybean Fields During Growing Season Through Polarimetric Decomposition

Soil moisture ( Mv ) estimation and monitoring over agricultural areas using Synthetic Aperture Radar (SAR) are often affected by vegetation cover during the growing season. Volume scattering and vegetation attenuation can complicate the received SAR backscatter signal when microwave interacts with the vegetation canopy. To address the existing problems, this article employed the model-based polarimetric decomposition method considering the two-way attenuation to remove the volume scattering and vegetation attenuation. A deorientation process of SAR data was applied to remove the influence of randomly distributed target orientation angles before the polarimetric decomposition. To parameterize the two-way attenuation, Radar Vegetation Index derived from the SAR intensity images was adopted. The Dubois model was used to describe backscattering from the underlying bare soil. Since the soil roughness parameters are difficult to measure under vegetation cover, the optimum surface roughness method was used to parameterize the Dubois model. This soil moisture retrieval algorithm was applied to the polarimetric multitemporal RADARSAT-2 SAR data over soybean fields. The validation indicates the root-mean-square error of 9.2 vol.% and 8.2 vol.% at HH and VV polarization, respectively, over the entire soybean growing period, suggesting that the proposed method is capable of reducing the effect of vegetation cover for soil moisture monitoring over the soybean field.

Ship Detection from X-Band SAR Images Using M2Det Deep Learning Model

Synthetic aperture radar (SAR) images have been used in many studies for ship detection because they can be captured without being affected by time and weather. In recent years, the development of deep learning techniques has facilitated studies on ship detection in SAR images using deep learning techniques. However, because the noise from SAR images can negatively affect the learning of the deep learning model, it is necessary to reduce the noise through preprocessing. In this study, deep learning vessel detection was performed using preprocessed SAR images, and the effects of the preprocessing of the images on deep learning vessel detection were compared and analyzed. Through the preprocessing of SAR images, (1) intensity images, (2) decibel images, and (3) intensity difference and texture images were generated. The M2Det object detection model was used for the deep learning process and preprocessed SAR images. After the object detection model was trained, ship detection was performed using test images. The test results are presented in terms of precision, recall, and average precision (AP), which were 93.18%, 91.11%, and 89.78% for the intensity images, respectively, 94.16%, 94.16%, and 92.34% for the decibel images, respectively, and 97.40%, 94.94%, and 95.55% for the intensity difference and texture images, respectively. From the results, it can be found that the preprocessing of the SAR images can facilitate the deep learning process and improve the ship detection performance. The results of this study are expected to contribute to the development of deep learning-based ship detection techniques in SAR images in the future.

Comparison of SAR Backscatter Coefficient and Water Indices for Flooding Detection

With the increasing severity of climate change, intense torrential rains are occurring more frequently globally. Flooding due to torrential rain not only causes substantial damage directly, but also via secondary events such as landslides. Therefore, accurate and prompt flood detection is required. Because it is difficult to directly access flooded areas, previous studies have largely used satellite images. Traditionally, water indices such as the normalized difference water index (NDWI) and modified normalized difference water index (MNDWI) which are based on different optical bands acquired by satellites, are used to detect floods. In addition, as flooding likelihood is greatly influenced by the weather, synthetic aperture radar (SAR) images have also been used, because these are less influenced by weather conditions. In this study, we compared flood areas calculated from SAR images and water indices derived from Landsat-8 images, where the images were acquired at similar times. The flooded area was calculated from Landsat-8 and Sentinel-1 images taken between the end of May and August 2019 at Lijiazhou Island, China, which is located in the Changjiang (Yangtze) River basin and experiences annual floods. As a result, the flooded area calculated using the MNDWI was approximately 21% larger on average than that calculated using the NDWI. In a comparison of flood areas calculated using water indices and SAR intensity images, the flood areas calculated using SAR images tended to be smaller, regardless of the order in which the images were acquired. Because the images were acquired by the two satellites on different dates, we could not directly compare the accuracy of the water-index and SAR data. Nevertheless, this study demonstrates that floods can be detected using both optical and SAR satellite data.

A Generalized Gaussian Extension to the Rician Distribution for SAR Image Modeling

In this paper, we present a novel statistical model, $\textit{the generalized-Gaussian-Rician}$ (GG-Rician) distribution, for the characterization of synthetic aperture radar (SAR) images. Since accurate statistical models lead to better results in applications such as target tracking, classification, or despeckling, characterizing SAR images of various scenes including urban, sea surface, or agricultural, is essential. The proposed statistical model is based on the Rician distribution to model the amplitude of a complex SAR signal, the in-phase and quadrature components of which are assumed to be generalized-Gaussian distributed. The proposed amplitude GG-Rician model is further extended to cover the intensity SAR signals. In the experimental analysis, the GG-Rician model is investigated for amplitude and intensity SAR images of various frequency bands and scenes in comparison to state-of-the-art statistical models that include $\mathcal{K}$, Weibull, Gamma, and Lognormal. In order to decide on the most suitable model, statistical significance analysis via Kullback-Leibler divergence and Kolmogorov-Smirnov statistics are performed. The results demonstrate the superior performance and flexibility of the proposed model for all frequency bands and scenes and its applicability on both amplitude and intensity SAR images. The Matlab package is available at https://github.com/oktaykarakus/GG-Rician-SAR-Image-Modelling.

SAR Image Despeckling by Deep Neural Networks: from a Pre-Trained Model to an End-to-End Training Strategy

Speckle reduction is a longstanding topic in synthetic aperture radar (SAR) images. Many different schemes have been proposed for the restoration of intensity SAR images. Among the different possible approaches, methods based on convolutional neural networks (CNNs) have recently shown to reach state-of-the-art performance for SAR image restoration. CNN training requires good training data: many pairs of speckle-free/speckle-corrupted images. This is an issue in SAR applications, given the inherent scarcity of speckle-free images. To handle this problem, this paper analyzes different strategies one can adopt, depending on the speckle removal task one wishes to perform and the availability of multitemporal stacks of SAR data. The first strategy applies a CNN model, trained to remove additive white Gaussian noise from natural images, to a recently proposed SAR speckle removal framework: MuLoG (MUlti-channel LOgarithm with Gaussian denoising). No training on SAR images is performed, the network is readily applied to speckle reduction tasks. The second strategy considers a novel approach to construct a reliable dataset of speckle-free SAR images necessary to train a CNN model. Finally, a hybrid approach is also analyzed: the CNN used to remove additive white Gaussian noise is trained on speckle-free SAR images. The proposed methods are compared to other state-of-the-art speckle removal filters, to evaluate the quality of denoising and to discuss the pros and cons of the different strategies. Along with the paper, we make available the weights of the trained network to allow its usage by other researchers.

Glacier Surface Motion Estimation from SAR Intensity Images Based on Subpixel Gradient Correlation.

With the current extensive availability of synthetic-aperture radar (SAR) datasets with high temporal (e.g., a repeat cycle of a few or a dozen days) and spatial resolution (e.g., in the order of ∼1 m), radar remote sensing possesses an increasing potential for the monitoring of glacier surface motion thanks to the nearly weather and time-independent advantages. This paper proposes a robust subpixel frequency-based image correlation method for dense matching and integrates the improved matching into a workflow of glacier surface motion estimation using SAR intensity images with specific pre-processing and post-processing steps. The proposed matching method combines complex edge maps and local upsampling in the frequency domain for subpixel intensity tracking, which ensure the accuracy and robustness of glacier surface motion estimation. Experiments were carried out with TerraSAR-X and Sentinel-1 images covering two glacier areas in pole and alpine regions. The results of the monitoring and investigation of glacier motion validate the feasibility and reliability of the presented motion estimation method based on subpixel gradient correlation. The comparative results using both simulated and real SAR data indicate that the proposed matching method outperforms commonly used correlation-based matching methods in terms of matching accuracy and the ability to obtain correct matches.

Irregular Tessellation and Statistical Modeling Based Regionalized Segmentation for SAR Intensity Image

This paper presents a regionalized segmentation method for synthetic aperture radar (SAR) intensity images based on tessellation with irregular polygons. In the proposed method, the image domain is partitioned into a collection of irregular polygons, which are constructed using sets of nodes and are used to fit homogeneous regions with arbitrary shapes. Each partitioned polygon is taken as the basic processing unit. Assuming the intensities of the pixels in the polygon follow an independent and identical gamma distribution, the likelihood of the image intensities is modeled. After defining the prior distributions of the tessellation and the parameters for the likelihood model, a posterior probability model can be built based on the Bayes theorem as a segmentation model. To obtain optimal segmentation, a reversible-jump Markov chain Monte Carlo (RJMCMC) algorithm is designed to simulate from the segmentation model, where the move operations include updating the gamma distribution parameter, updating labels, moving nodes, merging polygons, splitting polygons, adding nodes, and deleting nodes. Experiments were carried out on synthetic and real SAR intensity images using the proposed method while the regular and Voronoi tessellation-based methods were also preformed for comparison. Our results show the proposed method overcomes some intrinsic limitations of current segmentation methods and is able to generate good results for homogeneous regions with different shapes.

A Method for Road Network Extraction from High-Resolution SAR Imagery Using Direction Grouping and Curve Fitting

Roads are an important recognition target in synthetic aperture radar (SAR) image interpretation. Although a considerable number of high-quality SAR images are now available, the method of road extraction is lagging. To extract the road network with low missed and false rates, this paper proposed a road network extraction approach which includes line detection, road segmentation, road network extraction and optimization. First, the linear feature response and direction map are obtained from the SAR intensity image using the multiplicative Duda operation. Then, the backscattering coefficient and coefficient of variation are combined using a support vector machine to eliminate the linear structures of non-roads, and the binary image of road candidates is subsequently achieved by morphological profiles of path openings. Next, with the obtained direction map, a novel thinning method based on binary image decomposition and curve fitting is presented to obtain line segments of the road network. Finally, a series of measures which involve overlap, continuity, and junction optimization are proposed to construct the road network. In the experiments, the proposed method was applied to Radarsat-2 and TerraSAR-X high-resolution images. The experimental results showed that the proposed method had an excellent performance in terms of both completeness and correctness.

SAR and Optical Data Comparison for Detecting Co-Seismic Slip and Induced Phenomena during the 2018 Mw 7.5 Sulawesi Earthquake.

We use both Synthetic Aperture Radar (SAR) and Optical data to constrain the co-seismic ground deformation produced by the 2018 Mw 7.5 Sulawesi earthquake. We exploit data processing techniques mainly based on pixel cross-correlation approach, applied to Synthetic Aperture Radar (SAR) and optical images to estimate the North–South (NS) displacement component. This component is the most significant because of the NNW–SSE geometry of the fault responsible for the seismic event, i.e., the Palu-Koro fault, characterized by a strike-slip faulting mechanism. Our results show a good agreement between the different data allowing to clearly identify the surface rupture due to the fault slip. Moreover, we use SAR and optical intensity images to investigate several secondary phenomena generated by the seismic event such as tsunami, landslides, and coastal retreat. Finally, we discuss differences between SAR and optical outcomes showing strengths and disadvantages of each one according to the investigated phenomenon.

SAR Speckle Nonlocal Filtering With Statistical Modeling of Haar Wavelet Coefficients and Stochastic Distances

Due to the coherent processing of synthetic aperture radar (SAR) systems, multiplicative speckle noise arises providing a granular appearance in SAR images. This kind of noise makes it difficult to analyze and interpret surface images from the earth. Therefore, studying alternatives to attenuate the speckle is a constant task in the image processing literature. Current state-of-the-art filters in remote sensing area explore the philosophy of similarity between patches. This paper aims to expand the traditional nonlocal means (NLM) algorithm originally proposed for the additive white Gaussian noise (AWGN) to deal with the speckle. In our research, we consider the worst scenario, i.e., the single-look speckle noise, and apply the NLM to filter intensity SAR images in the Haar wavelet domain. To accomplish this task, the Haar coefficients were described by exponential-polynomial (EP) and gamma distributions. Furthermore, stochastic distances based on these two mentioned distributions were derived and embedded in the NLM filter by replacing the Euclidean distance of the original method. This represents the main contribution of the proposed research. Finally, this paper analyzes and compares the synthetic and real experiments of the proposed method with some recent filters of the literature demonstrating its competitive performance.

THE USE OF MULTI-TEMPORAL SENTINEL SATELLITES IN THE ANALYSIS OF LAND COVER/LAND USE CHANGES CAUSED BY THE NUCLEAR POWER PLANT CONSTRUCTION

Abstract. Turkey, due to increased demand for energy has made plans for nuclear power generation since 1970. Sinop Nuclear Power Plant, which will be built on Sinop İnceburun peninsula at the Black Sea coast of Turkey, is one of the three different nuclear power plants planned to be built in Turkey. The Sinop Nuclear Power Plant consist of four different reactors. The construction of the first unit is expected to be completed by 2023, and the fourth unit is planned to be activated by 2028. On the other hand, the construction of the nuclear power plant will alter the land use at the actual plant site and its surroundings and hence may cause significant environmental changes. As an indicator, more than 650000 trees have been cut so far for the construction of nuclear power plant, and this can adversely affect the ecological balances of the region by endangering habitats and creating ecological damages. The aim of this study is to analyse the land use/land cover changes (LULC) in the forestry-dominated areas due to the construction of nuclear power plants using the multi-temporal Synthetic Aperture Radar (SAR) and optical satellite images. For this purpose, different change detection methods such as SAR intensity image differencing, supervised image classification method (Support Vector Machine algorithm) were applied to Sentinel 1 satellite image datasets (2016-2019) to evaluate the annual changes due to construction. In addition, a correlation analysis was performed between the canopy structure and vegetation biomass using Sentinel 2 NDVI dataset (2016-2019) and calibrated Sentinel 1 backscatter values. Furthermore, using the Google Earth Engine (GEE), the Landsat 8 NDVI time series of the affected forest area, generated at 8-day intervals, was used to validate changes in vegetation.

Long-short-term-memory-based crop classification using high-resolution optical images and multi-temporal SAR data

Farmland parcel-based crop classification using satellite data plays an important role in precision agriculture. In this study, a deep-learning-based time-series analysis method employing optical images and synthetic aperture radar (SAR) data is presented for crop classification for cloudy and rainy regions. Central to this method is the spatial-temporal incorporation of high-resolution optical images and multi-temporal SAR data and deep-learning-based time-series analysis. First, a precise farmland parcel map is delineated from high-resolution optical images. Second, pre-processed SAR intensity images are overlaid onto the parcel map to construct time series of crop growth for each parcel. Third, a deep-learning-based (using the long short-term memory, LSTM, network) classifier is employed to learn time-series features of crops and to classify parcels to produce a final classification map. The method was applied to two datasets of high-resolution ZY-3 images and multi-temporal Sentinel-1A SAR data to classify crop types in Hunan and Guizhou of China. The classification results, with an 5.0% improvement in overall accuracy compared to those of traditional methods, illustrate the effectiveness of the proposed framework for parcel-based crop classification for southern China. A further analysis of the relationship between crop calendars and change patterns of time-series intensity indicates that the LSTM model could learn and extract useful features for time-series crop classification.

Large-Scale Automatic Vessel Monitoring Based on Dual-Polarization Sentinel-1 and AIS Data

This research addresses the use of dual-polarimetric descriptors for automatic large-scale ship detection and characterization from synthetic aperture radar (SAR) data. Ship detection is usually performed independently on each polarization channel and the detection results are merged subsequently. In this study, we propose to make use of the complex coherence between the two polarization channels of Sentinel-1 and to perform vessel detection in this domain. Therefore, an automatic algorithm, based on the dual-polarization coherence, and applicable to entire large scale SAR scenes in a timely manner, is developed. Automatic identification system (AIS) data are used for an extensive and also large scale cross-comparison with the SAR-based detections. The comparative assessment allows us to evaluate the added-value of the dual-polarization complex coherence, with respect to SAR intensity images in ship detection, as well as the SAR detection performances depending on a vessel’s size. The proposed methodology is justified statistically and tested on Sentinel-1 data acquired over two different and contrasting, in terms of traffic conditions, areas: the English Channel the and Pacific coastline of Mexico. The results indicate a very high SAR detection rate, i.e., >80%, for vessels larger than 60 m and a decrease of detection rate up to 40 % for smaller size vessels. In addition, the analysis highlights many SAR detections without corresponding AIS positions, indicating the complementarity of SAR with respect to cooperative sources for detecting dark vessels.

New Insights into Multiclass Damage Classification of Tsunami-Induced Building Damage from SAR Images

The fine resolution of synthetic aperture radar (SAR) images enables the rapid detection of severely damaged areas in the case of natural disasters. Developing an optimal model for detecting damage in multitemporal SAR intensity images has been a focus of research. Recent studies have shown that computing changes over a moving window that clusters neighboring pixels is effective in identifying damaged buildings. Unfortunately, classifying tsunami-induced building damage into detailed damage classes remains a challenge. The purpose of this paper is to present a novel multiclass classification model that considers a high-dimensional feature space derived from several sizes of pixel windows and to provide guidance on how to define a multiclass classification scheme for detecting tsunami-induced damage. The proposed model uses a support vector machine (SVM) to determine the parameters of the discriminant function. The generalization ability of the model was tested on the field survey of the 2011 Great East Japan Earthquake and Tsunami and on a pair of TerraSAR-X images. The results show that the combination of different sizes of pixel windows has better performance for multiclass classification using SAR images. In addition, we discuss the limitations and potential use of multiclass building damage classification based on performance and various classification schemes. Notably, our findings suggest that the detectable classes for tsunami damage appear to differ from the detectable classes for earthquake damage. For earthquake damage, it is well known that a lower damage grade can rarely be distinguished in SAR images. However, such a damage grade is apparently easy to identify from tsunami-induced damage grades in SAR images. Taking this characteristic into consideration, we have successfully defined a detectable three-class classification scheme.