Hyperspectral Anomaly Detection: Comparative Evaluation in Scenes with Diverse Complexity

Abstract

Anomaly detection (AD) in hyperspectral data has received a lot of attention for various applications. The aim of anomaly detection is to detect pixels in the hyperspectral data cube whose spectra differ significantly from the background spectra. Many anomaly detectors have been proposed in the literature. They differ in the way the background is characterized and in the method used for determining the difference between the current pixel and the background. The most well-known anomaly detector is the RX detector that calculates the Mahalanobis distance between the pixel under test (PUT) and the background. Global RX characterizes the background of the complete scene by a single multivariate normal probability density function. In many cases, this model is not appropriate for describing the background. For that reason a variety of other anomaly detection methods have been developed. This paper examines three classes of anomaly detectors: subspace methods, local methods, and segmentation-based methods. Representative examples of each class are chosen and applied on a set of hyperspectral data with diverse complexity. The results are evaluated and compared.

Análisis espectral de materiales geológicos en la Cordillera Volcánica Central de Costa Rica y su relación con la detección remota de anomalías

“…Se han contrastado las anomalías obtenidas por RX con las calculadas mediante DAFT como variante de Projection Pursuit (Malpica et al, 2008), mediante un método SSRX basado en subespacios hiperespectrales (Borghys et al 2012) y mediante ortoproyección subespacial -OSPRX (Chang, 2005).…”

Visualization Techniques for Surveillance: Visualizing What Cannot Be Seen and Hiding What Should Not Be Seen

“…In order to do that, we need to find a mathematical measure of uncommonness (abnormality) in an image and assign this uncommonness to the brightness of each pixel. Many such measures have been developed during the last 30 years; an overview is given by Borghys et al 52 In our example, figure 14 shows that there are apparently differences in spectral signature that are not visible; some dark green pixels are very uncommon, other dark green pixels are very common, even if the colors are very similar to the human eye. The left picture shows a magnified part of the image in figure 13 whereas the right picture shows what it looks like when each pixel in the left image is colored according to how uncommon that particular signature ("color") is.…”

A New Algorithm for the On-Board Compression of Hyperspectral Images

“…After doing so, all the reconstructed images as well as the original images (without applying any transformation) have been processed using the well known Orthogonal Subspace Projection Reed-Xiaoli (OSPRX) detector for identifying the anomalous pixels. The OSPRX algorithm is one of the commonly used detectors for anomaly detection applications and provides good detection results [30][31][32].…”