Automated Feature Extraction from Hyperspectral Imagery

Award Information
Agency:
National Aeronautics and Space Administration
Branch:
N/A
Amount:
$600,000.00
Award Year:
2007
Program:
SBIR
Phase:
Phase II
Contract:
NNS07AA10C
Agency Tracking Number:
054506
Solicitation Year:
2005
Solicitation Topic Code:
S7.01
Solicitation Number:
N/A
Small Business Information
Visual Learning Systems, Inc.
1719 Dearborn Avenue, Missoula, MT, 59801-2391
Hubzone Owned:
N
Socially and Economically Disadvantaged:
N
Woman Owned:
N
Duns:
150373442
Principal Investigator
 Stuart Blundell
 Principal Investigator
 (406) 829-1384
 sblundell@vls-inc.com
Business Contact
 James Blundell
Title: CEO
Phone: (406) 829-1384
Email: sblundell@vls-inc.com
Research Institution
N/A
Abstract
The proposed activities will result in the development of a novel hyperspectral feature-extraction toolkit that will provide a simple, automated, and accurate approach to materials classification from hyperspectral imagery (HSI). The proposed toolkit will be built as an extension to the state-of-the-art technology in automated feature extraction (AFE), the Feature Analyst software suite, which was developed by the proposing company. Feature Analyst uses, along with spectral information, feature characteristics such as spatial association, size, shape, texture, pattern, and shadow in its generic AFE process. Incorporating the best AFE approach (Feature Analyst) with the best HSI techniques promises to greatly increase the usefulness and applicability of HSI. While current HSI techniques, such as spectral end-member classification, can provide effective materials classification, these methods are slow (or manual), cumbersome, complex for analysts, and are limited to materials classification only. Feature Analyst, on the other hand, has a simple workflow of (a) an analyst providing a few examples, and (b) an advanced software agent classifying the rest of the imagery. This simple yet powerful approach will become the new paradigm for HSI materials classification since Phase I experiments show it is (a) accurate, (b) simple, (c) advanced, and (d) exists as workflow extension to market leading products. The deliverables of this proposal will allow HSI products to be fully exploited for the first time by a wide range of users.

* information listed above is at the time of submission.

Agency Micro-sites

US Flag An Official Website of the United States Government