USA As Represented by Secretary of the Navy

John A Antoniades

Peter J Palmadesso

Jeffrey H Bowles

Mark M Baumback

Daniel G Haas

John M Grossman

John Fisher

John M Grossmann

A method for defining targets in hyperspectral image data of a scene, has the steps: (1) identifying a target within the scene; (2) fitting a plurality of conjoined hyperplanes about the target in the scene; and (3) fitting a shape to the identified target by shrinkwrapping the hyperplanes about the target by translating and rotating the hyperplanes until a specified fit parameter is satisfied.

Hyperspectral visualization extensible workbench

The Intelligent Hypersensor Processing System (IHPS) is a system for the rapid detection of small, weak, or hidden objects, substances, or patterns embedded in complex backgrounds, providing fast adaptive processing for demixing and recognizing patterns or signatures in data provided by certain types of &ldquo;hypersensors&rdquo;. SERENE introduces an improved noise reduction algorithm useful on systems which use hypersensors such as IHPS, or other systems which use sensors which are hyper or multi spectral. The SERENE technique may be employed through out the Learning Module Processor pipelining and further processes the data stream to filter intrinsic and extrinsic noise, and minimize exemplar noise effects in the exemplar set. This system represents an alternative to prior systems for hidden object detection by solving the problems encountered when attempting to detect hidden objects/targets in dynamic scenarios at real-time.

System for eliminating or reducing exemplar effects in multispectral or hyperspectral sensors

The Compression of Hyperdata with ORASIS Multisegment Pattern Sets, (CHOMPS), system is a collection of algorithms designed to optimize the efficiency of multi spectral data processing systems. The CHOMPS system employs two types of algorithms, Focus searching algorithms and Compression Packaging algorithms. The Focus algorithms employed by CHOMPS reduce the computational burden of the prescreening process by reducing the number of comparisons necessary to determine whether or not data is redundant, by selecting only those exemplars which are likely to result in the exclusion of the incoming sensor data for the prescreener comparisons. The Compression Packaging algorithms employed by CHOMPS, compress the volume of the data necessary to describe what the sensor samples. In the preferred embodiment these algorithms employ the Prescreener, the Demixer Pipeline and the Adaptive Learning Module Pipeline to construct a compressed data set. The compression is realized by constructing the data set from the exemplars defined in the prescreening operation and expressing those exemplars in wavespace with the necessary scene mapping data, or further processing the exemplars through the adaptive learning pipeline and expressing the exemplars in terms of endmembers, to facilitate the efficient storage, download and the later reconstruction of the complete data set with minimal deterioration of signal information.

Compression of hyperdata with ORASIS multisegment pattern sets (CHOMPS)

The Intelligent Hypersensor Processing System (IHPS) is a system for the rapid detection of small, weak, or hidden objects, substances, or patterns embedded in complex backgrounds. providing fast adaptive processing for demixing and recognizing patterns or signatures in data provided by certain types of 'hypersensors'. This system represents an alternative to prior systems for hidden object detection by solving the problems encountered when attempting to detect hidden objects/targets in dynamic scenarios at real-time. IHPS accomplishes this by forming, a series of pattern vectors through the concatenation of the outputs of multiple sensors. Each sensor measures a different attribute of the system being observed, and has a consistent relationship to all the other sensors. The data stream form the sensors is entered into a processing system which employs a parallel-pipeline architecture. The data stream is simultaneously sent to two separate processor pipes. The first is the Demixer Module, which decomposes each pattern vector into a convex combination of a set of fundamental patterns which are the constituents of the mixture. The decomposition is accomplished using projection operations called `Filter Vectors` generated by the Adaptive Learning Module. The signature pattern of a weak constituent or unresolved small target is separated from background patterns which may hide the target pattern in the unmixed data. A prior knowledge about the signatures of known targets can be used and approximate signatures of unknown constituents are determined automatically. Information detailing the composition of the demixed data patterns is sent to the Display/Output Module along with information about the fundamental patterns and Filter Vectors.

Growing community of inventors

Fulton, MD, United States of America

John A Antoniades