Stefania Matteoli

A tutorial overview of anomaly detection in hyperspectral images

In this paper, a tutorial overview on anomaly detection for hyperspectral electro-optical systems is presented. This tutorial is focused on those techniques that aim to detect small man-made anomalies typically found in defense and surveillance applications. Since a variety of methods have been proposed for detecting such targets, this tutorial places emphasis on the techniques that are either mathematically more tractable or easier to interpret physically. These methods are not only more suitable for a tutorial publication, but also an essential to a study of anomaly detection. Previous surveys on this subject have focused mainly on anomaly detectors developed in a statistical framework and have been based on well-known background statistical models. However, the most recent research trends seem to move away from the statistical framework and to focus more on deterministic and geometric concepts. This work also takes into consideration these latest trends, providing a wide theoretical review without disregarding practical recommendations about algorithm implementation. The main open research topics are addressed as well, the foremost being algorithm optimization, which is required for embodying anomaly detectors in real-time systems.

An Overview of Background Modeling for Detection of Targets and Anomalies in Hyperspectral Remotely Sensed Imagery

This paper reviews well-known classic algorithms and more recent experimental approaches for distinguishing the weak signal of a target (either known or anomalous) from the cluttered background of a hyperspectral image. Making this distinction requires characterization of the targets and characterization of the backgrounds, and our emphasis in this review is on the backgrounds. We describe a variety of background modeling strategies-Gaussian and non-Gaussian, global and local, generative and discriminative, parametric and nonparametric, spectral and spatio-spectral-in the context of how they relate to the target and anomaly detection problems. We discuss the major issues addressed by these algorithms, and some of the tradeoffs made in choosing an effective algorithm for a given detection application. We identify connections among these algorithms and point out directions where innovative modeling strategies may be developed into detection algorithms that are more sensitive and reliable.

An Automatic Approach to Adaptive Local Background Estimation and Suppression in Hyperspectral Target Detection

This paper deals with subspace-based target detection in hyperspectral images. Specifically, it focuses on a general detection scheme where, first, background is suppressed through orthogonal-subspace projection and then target detection is accomplished. An adequate estimation of the background subspace is essential to a successful outcome. The background subspace has been typically estimated globally. However, global approaches may be ineffective for small-target-detection applications since they tend to overestimate the background interference affecting a given target. This may result in a low target residual energy after background suppression that is detrimental to detection performance. In this paper, we propose a novel and fully automatic algorithm for local background-subspace estimation (LBSE). Local background has typically a lower inherent complexity than that of global background. By estimating the background subspace over a local neighborhood of the test pixel, the resulting background-subspace dimension is expected to be low, thus resulting in a higher target residual energy after suppression which benefits the detection performance. Specifically, the proposed LBSE acts on a per-pixel basis, thus adaptively tailoring the estimated basis to the local complexity of background. Both simulated and real hyperspectral data are employed to investigate the detection-performance improvements offered by LBSE with respect to both global and local methodologies previously presented.

Improved estimation of local background covariance matrix for anomaly detection in hyperspectral images

Anomaly detection in hyperspectral images has proven valuable in many applications, such as hazardous material and mine detection. The benchmark anomaly detector is the Reed-Xiaoli (RX) detector, which is based on the local multivariate normality of background. The RX algorithm, along with its many modified versions, has been widely explored, and the main concerns identified are related to local background covariance matrix estimation. The small sample size, local background nonhomogeneity, and the presence of target pixels within the estimation window are factors that can deeply affect local background covariance matrix estimation. These critical aspects may occur together in the same operational scenario, and they may strongly impair the detection performance. However, due to their intrinsic difference, these aspects have been typically discussed within different frameworks, disregarding the possible existing connections while developing different approaches to solution. We investigate these critical aspects, along with their impact on the detection process, from an operational detection perspective. The approaches to solution are critically analyzed, discussing possible links and connections. Real hyperspectral data are employed for assessing if the algorithms, designed ad hoc to solve a specific problem, can either handle more complex situations, or bring about further complications.

Models and Methods for Automated Background Density Estimation in Hyperspectral Anomaly Detection

Anomaly detection (AD) in remotely sensed hyperspectral images has been proven to be valuable in many applications. In this paper, we propose a scheme for detecting global anomalies in which a likelihood ratio test-based decision rule is applied in conjunction with automated data-driven estimation of the background probability density function (PDF). Specifically, the use of both semiparametric (finite mixtures) and nonparametric (Parzen windows) models is investigated for background PDF estimation. Although such approaches are well known in multivariate data analysis, they have been very seldom applied to estimate the hyperspectral image background PDF, mostly due to the difficulty of reliably learning the model parameters without operator intervention. In this paper, semi and nonparametric estimators have been successfully employed to estimate the image background PDF with the aim of detecting global anomalies in a scene benefiting from the application of ad hoc Bayesian learning strategies. Two real hyperspectral images have been used to experimentally evaluate the ability of the proposed AD scheme resulting from the application of different global background PDF models and learning methods.

Operational and Performance Considerations of Radiative-Transfer Modeling in Hyperspectral Target Detection

Accounting for radiative transfer within the atmosphere is usually necessary to accomplish target detection in airborne/satellite hyperspectral images. In this paper, two methods of accounting for the illumination and atmospheric effects-atmospheric compensation (AC) and forward modeling (FM)-are investigated in their application to target detection. Specifically, several crucial aspects are examined, such as the processing required, the computational complexity, and the flexibility accorded to an imperfect knowledge of acquisition conditions. Real ground-truthed hyperspectral data are employed in order to evaluate the operational applicability of such approaches in a target-detection scenario, as well as their impact on the processing-chain computational complexity. Results indicate that AC is recommended when accurate knowledge of the acquisition conditions is available, and the image has relatively uniform illumination and nonshadowed targets. Conversely, FM is preferred if scene conditions are not well known and when the targets may be subject to varying illumination conditions, including shadowing.

Hyperspectral Anomaly Detection With Kurtosis-Driven Local Covariance Matrix Corruption Mitigation

Local background covariance matrix corruption due to outliers in the sample data may be one of the major causes that limit detection performance of those algorithms that detect local anomalies in hyperspectral images on the basis of the Mahalanobis distance. In this letter, an original detection scheme is presented that efficiently embeds covariance corruption mitigation. A kurtosis-based binary hypothesis test is first applied to each pixel to quickly determine the presence of outliers in the local neighborhood. Rejection of the null hypothesis triggers application of a robust-to-outlier covariance estimation technique. Results on real data exhibit good detection performance and robustness to outliers. Contrary to previous works, this is achieved without an unnecessary increase of the procedural complexity.

Development of algorithms and products for supporting the Italian hyperspectral PRISMA mission: The SAP4PRISMA project

The SAP4PRISMA is a four year research project which aims at developing algorithms and products for the future PRISMA mission. The project started on May 2010 and is now entering his full activities as the ”PRISMA like” data set has been defined and the test areas were selected. The paper describes the main project objectives and the activities realized in the first 9 months of the project.

Robust hyperspectral image segmentation based on a non-Gaussian model

Spectra collected by hyperspectral sensors over samples of the same material are not deterministic quantities. Their inherent spectral variability can be accounted for by making use of suitable statistical models. Within this framework, the Gaussian Mixture Model (GMM) is one of the most widely adopted models for modeling hyperspectral data. Unfortunately, the GMM has been shown not to be sufficiently adequate to represent the statistical behavior of real hyperspectral data, especially for the tails of the distributions. The class of elliptically contoured distributions, which accommodates longer tails, promises to better match the spectral distribution of hyperspectral data.

Fully Unsupervised Learning of Gaussian Mixtures for Anomaly Detection in Hyperspectral Imagery

This paper proposes a fully unsupervised anomaly detection strategy in hyperspectral imagery based on mixture learning. Anomaly detection is conducted by adopting a Gaussian Mixture Model (GMM) to describe the statistics of the background in hyperspectral data. One of the key tasks in the application of mixture models is the specification in advance of the number of GMM components, the determination of which is essential and strongly affects detection performance. In this work, GMM parameters estimation was performed through a variation of the well-known Expectation Maximization (EM) algorithm that was developed within a Bayesian framework. Specifically, the adopted mixture learning technique incorporates a built-in mechanism for automatically assessing the number of components during the parameter estimation procedure. Then, Generalized Likelihood Ratio Test (GLRT) is considered for detecting anomalies. Real hyperspectral imagery acquired by an airborne sensor is used for experimental evaluation of the proposed anomaly detection strategy.