Title of thesis: A PERFORMANCE CHARACTERIZATION OF KERNEL-BASED ALGORITHMS FOR ANOMALY DETECTION IN HYPERSPECTRAL IMAGERY Hirsh Goldberg Master of Science, 2007 Thesis directed by: Professor Rama Chellappa Department of Electrical Engineering This thesis provides a performance comparison of linear and nonlinear subspacebased anomaly detection algorithms. Using a dual-window technique to separat...

Over the past decade, airborne hyperspectral systems have shown remarkable performance in identifying and classifying a variety of ground objects, such as differentiating between minerals, vegetations, artificial materials, water, etc. Though the hyperspectral imaging market is still relatively small, yet it is steadily growing. Currently, most of the high performance systems are of the pushbro...

Band selection is a commonly used approach for dimensionality reduction in hyperspectral imagery. Affinity propagation (AP), a new clustering algorithm, is addressed in many fields, and it can be used for hyperspectral band selection. However, this algorithm cannot get a fixed number of exemplars during the message-passing procedure, which limits its uses to a great extent. This paper proposes ...

During a surgery, the inevitable presence of blood covering the surgical field demands efforts to keep the area as clean as possible. A new hyperspectral data processing method is being developed to deliver clearer images to the surgeon. The analysis of optical absorption properties of the blood and water indicates that, between the visible and near infrared spectral regions, some valuable info...

A novel approach using volumetric texture and reduced-spectral features is presented for hyperspectral image classification. Using this approach, the volumetric textural features were extracted by volumetric gray-level co-occurrence matrices (VGLCM). The spectral features were extracted by minimum estimated abundance covariance (MEAC) and linear prediction (LP)-based band selection, and a semi-...

In this paper we present the utilization of high-spectral resolution imagery for improving low-spectral resolution imagery. In our analysis, we assume that an acquisition of high spectral resolution images provides more accurate spectral predictions of low spectral resolution images than a direct acquisition of low spectral resolution images. We illustrate the advantages by focusing on a specif...

In recent years the use of remote sensing imagery to classify and map vegetation over different spatial scales has gained wide acceptance in the research community. Many national and regional datasets have been derived using remote sensing data. However, much of this research was undertaken using multispectral remote sensing datasets. With advances in remote sensing technologies, the use of hyp...

This paper evaluates the impact of removing random noise of radiance data using a spectral-spatial smoothing approach on data compression onboard a hyperspectral satellite. A datacube acquired using a Short Wave Infrared Full Spectrum Imager II for target detection application of hyperspectral data was tested. The impact was evaluated using both the statistical based measures and a remote sensi...

Anomaly detection has received considerable interest for hyperspectral data exploitation due to its high spectral resolution. A well-known algorithm for hyperspectral anomaly detection is the RX detector. A number of variations have been studied since then, including global and local versions for different type of anomalies. Aiming at a real-time requirement for practical applications, this pap...

This research work presents a supervised classification framework for hyperspectral data that takes into account both spectral and spatial information. Texture analysis is performed to model spatial characteristics that provides additional information, which is used along with rich spectral measurements for better classification of hyperspectral imagery. The moment invariants of an image can de...