As many inverse problems arising in synthetic apertures and computer tomography are ill-posed, prior information about the solution space is incorporated to establish regularity on the solutions of inverse problems. Often, this prior information is a practitioner chosen statistical distribution or structure of the desired inverse problem solution. Recently, the generative network from a generative adversarial network (GAN) has been implemented as a learned prior information in imaging inverse problems. In this paper, we construct a novel deep neural network (DNN), by applying algorithm unrolling to an alternating direction method of multipliers implementation, that is fundamentally informed by a dual-structured prior combining a learned GAN prior with the encompassing compound Gaussian class of statistical distributions. Through empirical analysis of our novel DNN in tomographic imaging, we demonstrate a significant improvement in reconstructed image quality over prior art methods that use a learned GAN prior.

Impact of synchronization errors in stretch processing for ultra-wideband (UWB) bistatic radar imaging is presented through a simulation study. Synchronization errors including phase noise, chirp rate mismatch, time and frequency offsets are discussed and added in a bistatic system model for the analysis. To assess the impact of those errors on image processing, high range resolution profiles (HRRP) and range-Doppler images are generated using point scatterers. The analysis shows that time and frequency offsets cause migration of scattering responses in range window extent of stretch processing resulting in Doppler spread. Also, the chirp rate mismatch degrades the range resolution and the phase noise increases the noise floor of the image. These results demonstrate the manner in which synchronization errors in bistatic stretch processing systems degrade the overall bistatic image quality.

This paper introduces a polarimetric three-dimensional (3-D) interferometric inverse synthetic aperture radar (ISAR) imaging process using multiple phase-centers. This approach takes effective advantage of polarimetric scattering mechanisms in 3-D target representations, which may improve target classification and identification. A Pauli decomposition scheme is considered to study the role of polarimetry in 3-D Interferometric ISAR (InISAR). The polarimetric 3-D InISAR imaging process is validated using the backhoe synthetic data released by the Air Force Research Laboratory (AFRL).

In this paper, a feature extraction technique based on the electromagnetic representation of radar signals is presented. In particular, we focus on ground penetrating radar imaging, where we model the backscatter from varying two dimensional geometric shapes with arbitrary local coordinate rotations. Due to the electrically small nature of buried targets, and the bending of the radar signal at the air-soil interface we focus on exact methods to model the surface current density induced on scattering surfaces. Overcomplete basis sets are derived from the electromagnetic descriptions to represent the scene in a sparse manner. From this proposed modeling framework we devise a novel methodology to exploit the prediction of scattering behavior to extract features for classification from radar scenes when multiple buried scattering surfaces are present. We see that our method can identify and reconstruct buried scattering geometries in the presence of false targets that are brought about from the nonlinear nature of the exact electromagnetic modelling methods. A noniterative algorithm based on the conjugate of Green’s function is developed to solve for the surface current in an unknown domain using multi-frequency, multi-aperture data. Our modeling and feature extraction algorithms are numerically validated for different target shapes buried in lossy soil profiles.

We develop an end-to-end deep learning-based approach for the classification of complex maritime environments via multichannel synthetic aperture radar (MSAR) sensors. In particular, we introduce a novel convolutional neural network (CNN)-based multichannel structure that incorporates a divisive normalization technique that is critical for achieving consistent classification performance across maritime scenes. We evaluate the performance of our technique, called MSAR-Net, using datasets collected by the U.S. Naval Research Laboratory’s experimental airborne MSAR system. Our results demonstrate that MSAR-Net achieves consistently and substantially superior performance compared to conventional amplitude-based scene classification. Finally, though we focus on the specific (yet difficult) problem of maritime surveillance, MSAR-Net, introduced in this article, is a fundamental technique that can potentially result in significant performance improvements in a variety of multichannel surveillance and remote sensing applications.

In this paper, a wideband direct modeling and feature extraction method for two dimensional geometric objects with arbitrary local coordinate rotations is considered. In particular we focus on the problem of performing feature extraction for the case of electrically small objects which is particularly applicable to ground penetrating radar (GPR) applications. We first derive low frequency surface current density solutions for a class of simple two dimensional scatterers buried below a rough stochastic surface in a lossy half-space. Then for the inverse problem, a novel methodology is developed for pose and location invariant feature extraction derived from basis sets emerging from our proposed modeling framework. Our modeling and feature extraction algorithms are validated for different target shapes buried in lossy soil profiles.

We investigate the benefits of employing a wideband low-frequency multiple-band (LFMB) system for classifying targets underneath foliage. While previous work in this area, for both single and multiband scenarios, has been limited to lower bandwidth (500 MHz) LFMB synthetic aperture radar (SAR) system. After describing our novel LFMB SAR system in detail and investigating foliage penetration (FOPEN) phenomenologies in target detection applications, we then focus on the main topic of this letter, viz., classification of targets underneath foliage. In particular, we demonstrate feature-classifier combinations that successfully leverage multiband information and that deliver superior performance to each individual band alone. All our experimental validations are based on data captured by our wideband LFMB SAR system.

The number of applications requiring signal classification continues to climb, fueled at least partly by the increase in sophistication and throughput of mobile devices. One particular use case of interest is when a sensor can record samples, process the samples, and transmit this data. In this paper, we are interested in understanding the design and behavior of these relay-like classification nodes. We propose a system model consisting of a compress-and-forward relay network where the data at a given relay node is quantized and broadcasted to a fusion center which will determine a corresponding class label for the sample data using online process. In this context, we propose and study an online kernel scalar quantization learning strategy to estimate the decision function and associated empirical conditional probabilities to enhance the overall classification accuracy rate. In doing so, we devise a jointly optimum classification quantization approach that can be applied in a variety of settings in signal processing, machine learning, and communications.

This letter introduces novel processing structures enabling the formation of 3-D inverse synthetic aperture radar (ISAR) images from phased arrays. Unlike previous approaches to 3-D ISAR imaging, this approach uses a spatio-sensor multilook processing procedure that takes better advantage of both 1) the range-Doppler structure of the target and 2) the multiple phase center structure of the processing array. Simulation at both X-band and W-band demonstrates the new 3-D imaging algorithm provides robust interferometric calculations for height estimation under noisy sensing conditions.

The U.S. Naval Research Laboratory (NRL) recently developed an X-band airborne multichannel synthetic aperture radar (MSAR) test bed system that consists of 32 along-track phase centers. This system was deployed in September 2014 and again in October 2015 to perform extensive and systematic data collections on a variety of land and maritime scenes under different environmental conditions. This paper presents a detailed experimental analysis of imaging in the maritime domain using data captured by the NRL MSAR system. After presenting some of the important details of our NRL MSAR system, we demonstrate velocity-based imaging of a variety of moving backscatter sources including ships and shoaling ocean waves. Our analysis is based on the velocity SAR (VSAR) technique, which was originally conceived by Friedlander and Porat. Practical application of this algorithm in the maritime domain requires a number of pre- and postprocessing stages, which are described here in detail. Our results are then benchmarked against the traditional along-track interferometry, where it is demonstrated that VSAR processing is better able to correctly compensate motion-induced distortion.

Sonar imaging has seen vast improvements over the last few decades due in part to advances in synthetic aperture sonar. Sophisticated classification techniques can now be used in sonar automatic target recognition (ATR) to locate mines and other threatening objects. Among the most promising of these methods is sparse reconstruction-based classification (SRC), which has shown an impressive resiliency to noise, blur, and occlusion. We present a coherent strategy for expanding upon SRC for sonar ATR that retains SRC's robustness while also being able to handle targets with diverse geometric arrangements, bothersome Rayleigh noise, and unavoidable background clutter. Our method, pose-corrected sparsity (PCS), incorporates a novel interpretation of a spike and slab probability distribution toward use as a Bayesian prior for class-specific discrimination in combination with a dictionary learning scheme for localized patch extractions. Additionally, PCS offers the potential for anomaly detection in order to avoid false identifications of tested objects from outside the training set with no additional training required. Compelling results are shown using a database provided by the U.S. Naval Surface Warfare Center.

Advancements in Sonar image capture have opened the door to powerful classification schemes for automatic target recognition (ATR). Recent work has particularly seen the application of sparse reconstruction-based classification (SRC) to sonar ATR, which provides compelling accuracy rates even in the presence of noise and blur. However, existing sparsity based sonar ATR techniques assume that the test images exhibit geometric pose that is consistent with respect to the training set. This work addresses the outstanding open challenge of handling inconsistently posed Sonar images relative to training. We develop a new localized block-based dictionary design that can enable geometric robustness. Further, a dictionary learning method is incorporated to increase performance and efficiency. The proposed SRC with Localized Pose Management (LPM), is shown to outperform the state of the art SIFT feature and SVM approach, due to its power to discern background clutter in Sonar images.

We present a novel approach to inverse problems in imaging based on a Hierarchical Bayesian-MAP (HB-MAP) formulation. In this paper we specifically focus on the difficult and basic inverse problem of multi-sensor (tomographic) imaging wherein the source image of interest is viewed from multiple directions by independent sensors. We employ a Probabilistic Graphical Modeling extension of the Compound Gaussian (CG) distribution as a global image prior into a Hierarchical Bayesian inference procedure. We first demonstrate the performance of the algorithm on Monte-Carlo trials followed by empirical data involving natural (optical) images. We demonstrate how our algorithm outperforms many of the previous approaches in the literature including Filtered Back-projection (FBP) and a variety of state-of-the-art compressive sensing (CS) algorithms.

We introduce a novel generalization of the compound Gaussian (CG) (or Gaussian Scale Mixture [1]) distribution which extends the Gaussian component of the CG model to a multilinear distribution. The resulting model, which we call the Multilinear Compound Gaussian (MCG) distribution, subsumes both GSM [1] and the previously developed MICA [3-4] distributions as complementary special cases; thereby allowing us to model a richer class of stochastic phenomena. First we derive the structural characterization of the MCG distribution and develop some of its important theoretical properties. Thereafter we describe a parameter estimation algorithm for learning this model from sample data, and then deploy this for modeling textures, including natural (i.e. optical) and SAR images. Our simulation results demonstrate how, for each case, we obtain improved performance over the CG model; thus indicating the versatility of the MCG model in accurately modeling various natural phenomena of interest.

Of recent interest in automatic target recognition (ATR) is the problem of combining the merits of multiple classifiers. This is commonly done by “fusing” the soft-outputs of several classifiers into making a single decision. We observe that the improvement in recognition rates afforded by these approaches is due to the complementary yet correlated information captured by different features/signal representations that these individual classifiers employ. We present the use of probabilistic graphical models in modeling and capturing feature dependencies that are crucial for target classification. In particular, we develop a two-stage target recognition framework that combines the merits of distinct and sparse signal representations with discriminatively learnt graphical models. The first stage designs multiple projections yielding M >; 1 sparse representations, while the second stage models each individual representation using graphs and combines these initially disjoint and simple graphical models into a thicker probabilistic graphical model. Experimental results show that our approach outperforms state-of-the art target classification techniques in terms of recognition rates. The use of graphical models is particularly meritorious when feature dimensionality is high and training is limited - a commonly observed constraint in synthetic aperture radar (SAR) imagery based target recognition.

We extend our previous work on Multilinear Independent Component Analysis (MICA) by introducing a Fast-MICA algorithm that demonstrates the same improvement over classical ICA as the original MICA algorithm [1] while improving the computational speed by two polynomial orders of magnitude. Apart for enabling a faster determination of the multilinear structure of image patch probability density, this new approach opens up, for the first time, the possibility of computing a novel non-stationarity index based on the relative change in mutual information. We demonstrate the performance of our Fast-MICA algorithm together with an illustration of our novel non-stationarity index.

We present information-theoretic underpinnings of a computation theory of low-level visual fixations in natural images. In continuation of our prior work on optimal contrast-based fixations [1], we develop an optimum texture- based fixation selection algorithm based on a recent theory of non-stationarity measurement in natural images [2]. Thereafter we propose a simple coupling of the optimal texture-based and contrast-based fixation features to produce a new algorithm called CONTEXT, which exhibits robust performance for fixation selection in natural images. The performance of the fixation algorithms are evaluated for natural images by comparison to randomized fixation strategies via actual human fixations performed on the images. The fixation patterns obtained outperform randomized, GAFFE-based [3], and Itti [4] fixation strategies in terms of matching human fixation patterns. These results also demonstrate the important role that contrast and textural information play in low-level visual processes in the Human Visual System (HVS).

We refine the classical independent component analysis (ICA) decomposition using a multilinear expansion of the probability density function of the source statistics. In particular, we introduce a specific nonlinear system that allows us to elegantly capture the statistical dependences between the responses of the multilinear ICA (MICA) filters. The resulting multilinear probability density is analytically tractable and does not require Monte Carlo simulations to estimate the model parameters. We demonstrate the MICA model on natural image textures and envision that the new model will prove useful for analyzing nonstationarity natural images using natural scene statistics models.

We refine the classical independent component analysis (ICA) decomposition using a multilinear expansion of the probability density function of the source statistics. In particular, to model the source statistics of natural image textures, we introduce a specific non-linear system that allows us to elegantly capture the statistical dependences between the responses of the multilinear ICA (MICA) filters. The resulting multilinear probability density is analytically tractable and does not require Monte Carlo simulations to estimate the model parameters. We demonstrate the success of the MICA model on natural textures and discuss applications to non-stationarity detection and natural scene statistics (NSS) modeling.

We present a novel approach for non-stationarity detection in natural images by exploiting the prior knowledge of the independent component structure of scene statistics. Our proposed non-stationarity index is conceptually simple and is intertwined with the probabilistic structure of the image segment being analyzed. It shows consistently good results when applied to natural scenes and, we expect, will find useful applications in computer vision algorithms in as much as the detection of statistically non-stationary locations in images can be an important preliminary step toward the understanding of scene content and in the guiding of visual fixations.

In this paper we address the problem of visual surveillance, which we define as the problem of optimally extracting information from the visual scene with a fixating, foveated imaging system. We are explicitly concerned with eye/camera movement strategies that result in maximizing information extraction from the visual field. Here we demonstrate how a novel characterization of the contrast statistics of natural images can be used for selecting fixation points that minimize the total contrast uncertainty (entropy) of natural images. We demonstrate the performance of the algorithm and compare its performance to ground truth methods. The results show that our algorithm performs favorably in terms of both efficiency and its ability to find salient features in the image.

We develop theorems that place limits on the point-wise approximation of the responses of filters, both linear shift invariant (LSI) and linear shift variant (LSV), to input signals and images that are LSV in the following sense: they can be expressed as the outputs of systems with LSV impulse responses, where the shift variance is with respect to the filter scale of a single-prototype fillter. The approximations take the form of LSI approximations to the responses. We develop tight bounds on the approximation errors expressed in terms of filter durations and derivative (Sobolev) norms. Finally, we find application of the developed theory to defoveation of images, deblurring of shift-variant blurs, and shift-variant edge detection.