Nonlinear background estimation and change detection for wide-area search

This tutorial presents a state-of-the-art survey of advanced applications of Synthetic Aperture Radar (SAR). Applications include: the detection and recognition of targets in SAR imagery, and the detection of targets under trees (and in the open) using change detection (coherent change detection, full-polarization change detection, etc). A fully polarimetric SAR sensor is described. Models of clutter and targets are developed from analysis of full-polarization SAR imagery. Algorithms for optimum (GLRT) processing of full-polarization data are derived, including the polarimetric whitening filter (PWF) and the polarimetric matched filter (PMF). Polarization-based discrimination features (polarization entropy, anisotropy, etc.) are developed and applied to SAR image terrain classification. Model-based and template-based target recognition systems are described and classifier performance results versus resolution and polarization are summarized for 10-and 20-target classifiers. Super-resolution algorithms are applied to SAR imagery and target recognition performance improvements demonstrated. Multi-polarization and multi-pass change detection algorithms are developed and demonstrated using UHF SAR imagery of targets under trees; fusion of multi-polarization coherent and non-coherent change detection algorithms is demonstrated. The effect of SAR image compression on change detection performance is quantified. Change detection performance using multi-pass VHF SAR imagery of targets under trees is demonstrated using data gathered by the Swedish CARABAS SAR system.

Synthetic aperture radar (SAR) imaging can penetrate rain, snow, fog, and mist, providing an effective precipitation detector under a wide range of atmospheric conditions. This powerful technique operates under any weather conditions and can detect environmental changes or help in the evaluation of natural disasters. Multi-temporal change detection is important for monitoring disasters, but commonly applied wavelet transforms are not ideal for capturing change information. This paper presents a new multi-directional change detection (MDCD) method designed to improve the change detection accuracy using multiple SAR images. This method employs double-density dual-tree complex wavelet transforms (DDDT-CWT) theory, which allows the capture of multi-directional information. The MDCD method can provide information for 16 directions at any decomposed scale, which allows for change detection in multiple SAR images collected over time. We used the MDCD algorithm method to analyse SAR images from actual natural disasters and successfully identified environmental changes over time using SAR images.

The granular appearance of speckle noise in synthetic aperture radar (SAR) imagery makes it very difficult to visually and automatically interpret SAR data. Therefore, speckle reduction is a prerequisite for many SAR image processing tasks. In this paper, we propose a contourlet-based despeckling method for the SAR image using the hidden Markov tree (HMT) and Gaussian Markov models. The contourlet transform is a recently developed two-dimensional transform technique. It is reported to be more effective than wavelets in representing smooth curvature details typical of natural images. The HMT and Gaussian Markov models will reflect the correlations of the contourlet coefficients not only across scales and directions but also between neighbors. The experimental results show that the proposed method in contrary to other methods can obtain a better trade-off between smoothing the homogeneous areas and keeping the edges and can get better visual effect.

This study explores the Average Treatment Effects (ATE) estimator proposed by Terza (2009)’s Nonlinear Full Endogenous Treatment (NFES) model, where count dependent and binary treatment variables are present. Asymptotic distribution of ATE estimators based on NFES model is provided to show that nonlinear estimators have additional terms in asymptotic variance of which magnitudes depend on population coefficient. Due to their presence, the asymptotic variance of nonlinear estimators can be either larger or smaller than the linear counterparts depending on the values of coefficients. It turns out that the nonlinear ATE estimators are more efficient than linear estimators when the ATE conditional on covariates has small variance. An application to Botswana fertility is given.

ABSTRACTThe speckle noise of synthetic aperture radar (SAR) images limits its application in change detection. Compared with improved ratio (IR) and log-ratio (LR) operators, the neighborhood-based ratio (NR) technique can restrain the influence of speckle noise and is more suitable for change detection in SAR images. However, we find three drawbacks of NR by analyzing this method carefully. To overcome these defects, we propose an improved neighborhood-based ratio (INR) approach for change detection in SAR images. INR restructures the NR operator to exploit the neighborhood information more reasonably and is expected to reduce the impact of speckle noise better. IR, LR, mean ratio operator, NR, and INR are tested on two data sets to compare their performances in change detection of SAR images. Experimental results show that the proposed method can obtain better difference image than other state-of-art methods and improve the accuracy of change detection in SAR images effectively.

Nonparametric hazard rate estimation by orthogonal wavelet methods

This paper explains the underestimation of phase slope and the consequent distortion of the phase surface, observed in two-dimensional (2-D) phase unwrapping by linear estimators, like least squares methods applied to synthetic aperture radar (SAR) interferometry. These methods minimize the difference between the gradient of the unwrapped phase and the wrapped differences of the measured wrapped phase. Using the probability distributions of phase noise and phase differences for a given coherence, the probability of a phase gradient error giving rise to a nonconservative vector field is derived. It is shown that this phase gradient error has nonzero mean in the presence of phase slopes. Linear phase estimators cannot distinguish the mean phase gradient error from a true phase slope; hence, the unwrapped phase shows a slope bias. This bias is quantified as a function of coherence and the number of independent samples that are averaged. The theoretical results are confirmed by simulations.

In this letter, we propose a method to reduce the number of false alarms in a wavelength–resolution synthetic aperture radar (SAR) change detection scheme by using a convolutional neural network (CNN). The detection is performed in two steps: change analysis and object classification. A simple technique for wavelength–resolution SAR change detection is implemented to extract potential targets from the image of interest. A CNN is then used for classifying the change map detections as either a target or nontarget, further reducing the false alarm rate (FAR). The scheme is tested for the CARABAS-II data set, where only three false alarms over a testing area of 96 km <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> are reported while still sustaining a probability of detection above 96%. We also show that the network can still reduce the FAR even when the flight heading of the SAR system measurement campaign differs by up to 100° between the images used for training and test.

Token-Based Adaptive Time-Series Prediction by Ensembling Linear and Non-linear Estimators: A Machine Learning Approach for Predictive Analytics on big Stock Data

Single ended primary inductance converter (SEPIC) is a type of DC–DC converter whose industrial applications include maximum power point tracking and Active power factor correction. Owing to present nonlinear circuit components, SEPIC has discontinuous nonlinearity and for the mathematical model determination, state space averaging or more advanced modeling techniques are required. Once the approximated nonlinear model is obtained, the states of the plant can be estimated using a nonlinear state estimator. Nonlinear estimators are preferred mostly when the real trajectory of the states cannot be estimated accurately by a linear state estimator and the deviation from the linear behavior and nonlinear one is above what is tolerable for the applications. Extended Kalman filter (EKF), being such a state estimator is widely employed in control and fault monitoring applications where a complete or an approximated nonlinear model of the plant is available. EKF especially operates well for the plants where the nonlinearity does not cause the assumptions behind EKF to be violated. In this study, first an approximated nonlinear model for SEPIC is determined. Using the model, EKF is designed to estimate the states of the plant. The efficacy of the designed EKF is demonstrated in a series of numerical MATLAB based simulations where the both open loop and closed loop performances are analyzed, and the results are detailed in the paper.

This study evaluates the performance of a Support Vector Machine (SVM) classifier to learn and detect changes in single- and multi-temporal X- and L-band Synthetic Aperture Radar (SAR) images under varying conditions. The purpose is to provide guidance on how to train a powerful learning machine for change detection in SAR images and to contribute to a better understanding of potentials and limitations of supervised change detection approaches. This becomes particularly important on the background of a rapidly growing demand for SAR change detection to support rapid situation awareness in case of natural disasters. The application environment of this study thus focuses on detecting changes caused by the 2011 Tohoku earthquake and tsunami disaster, where single polarized TerraSAR-X and ALOS PALSAR intensity images are used as input. An unprecedented reference dataset of more than 18,000 buildings that have been visually inspected by local authorities for damages after the disaster forms a solid statistical population for the performance experiments. Several critical choices commonly made during the training stage of a learning machine are being assessed for their influence on the change detection performance, including sampling approach, location and number of training samples, classification scheme, change feature space and the acquisition dates of the satellite images. Furthermore, the proposed machine learning approach is compared with the widely used change image thresholding. The study concludes that a well-trained and tuned SVM can provide highly accurate change detections that outperform change image thresholding. While good performance is achieved in the binary change detection case, a distinction between multiple change classes in terms of damage grades leads to poor performance in the tested experimental setting. The major drawback of a machine learning approach is related to the high costs of training. The outcomes of this study, however, indicate that given dynamic parameter tuning, feature selection and an appropriate sampling approach, already small training samples (100 samples per class) are sufficient to produce high change detection rates. Moreover, the experiments show a good generalization ability of SVM which allows transfer and reuse of trained learning machines.

This paper presents five different statistical methods for ground scene prediction (GSP) in wavelength-resolution synthetic aperture radar (SAR) images. The GSP image can be used as a reference image in a change detection algorithm yielding a high probability of detection and low false alarm rate. The predictions are based on image stacks, which are composed of images from the same scene acquired at different instants with the same flight geometry. The considered methods for obtaining the ground scene prediction include (i) autoregressive models; (ii) trimmed mean; (iii) median; (iv) intensity mean; and (v) mean. It is expected that the predicted image presents the true ground scene without change and preserves the ground backscattering pattern. The study indicates that the the median method provided the most accurate representation of the true ground. To show the applicability of the GSP, a change detection algorithm was considered using the median ground scene as a reference image. As a result, the median method displayed the probability of detection of and a false alarm rate of , when considering military vehicles concealed in a forest.

Change detection (CD) represents a critical task in the analysis of remote sensing (RS) images. In particular, the CD of heterogeneous images that integrate optical and synthetic aperture radar (SAR) modalities has attracted growing attention owing to their complementary characteristics. However, the optical and SAR images (OSIs) CD tasks face specific issues including structural inconsistency between modalities, speckle noise in SAR images, and insufficient utilization of complementary cross-modal features, resulting in limitations in feature representation, temporal causal modeling, and feature fusion for existing methods. Therefore, proposes an end-to-end causal attention and frequency-domain gating fusion enhanced dual-branch OSIs CD network (CAFGFNet). This network adopts a dual-branch encoding architecture with modality-specific designs, where the optical branch emphasizes preserving spectral and texture features, and the SAR branch integrates denoising with deformable convolution to mitigate speckle noise and geometric deformation. On this basis, the Causal Attention (CA) mechanism is introduced to model temporal dependencies to suppress false changes, and the Frequency-domain Gating Fusion Module (FGFM) is designed to adaptively fuse complementary frequency components from optical and SAR features, thus effectively boosting the accuracy and robustness of CD. Compared with six state-of-the-art (SOTA) methods, CAFGFNet has increased the relative suboptimal indicators of Precision by 2.2% and 8.93% on two public datasets. The experimental results show that CAFGFNet can achieve high-precision detection of changes in OSIs while ensuring the full expression and effective fusion of cross-modal features.

Change detection is a hot topic and of great importance in remote sensing. The logarithm operation can be an effective means of eliminating the influence of multiplicative noise in the synthetic aperture radar (SAR) image. However, due to the nature of the logarithmic function, regions of change with high gray values are attenuated. In this study, we propose SAR to detect image changes based on an image fusion strategy by combining two different methods. First, we reduce speckle by non-subsampled shearlet transform in the log-domain, since this logarithmic function has the advantage of transforming multiplicative speckle noise into additive noise. As we know, the difference method always detects the areas with the largest changes. The difference method based on saliency extraction (SE) is applied to the exponent transformational SAR image to complement the disadvantage of WLR. WLR is used to obtain a change map of WLR to reduce the influence of SE when WLR does not detect the changed areas. Finally, two change maps can be added to obtain the final result. Experimental results for real SAR image pairs show the effectiveness of the proposed method in terms of detection rate, false alarm rate, and overall accuracy.

Change detection is an important synthetic aperture radar (SAR) application, usually used to detect changes on the ground scene measurements in different moments in time. Traditionally, change detection algorithm (CDA) is mainly designed for two synthetic aperture radar (SAR) images retrieved at different instants. However, more images can be used to improve the algorithms performance, witch emerges as a research topic on SAR change detection. Image stack information can be treated as a data series over time and can be modeled by autoregressive (AR) models. Thus, we present some initial findings on SAR change detection based on image stack considering AR models. Applying AR model for each pixel position in the image stack, we obtained an estimated image of the ground scene which can be used as a reference image for CDA. The experimental results reveal that ground scene estimates by the AR models is accurate and can be used for change detection applications.