|PROPOSAL NUMBER:||05-II S7.01-8496|
|PHASE-I CONTRACT NUMBER:||NNC06CB48C|
|SUBTOPIC TITLE:||Geospatial Data Analysis Processing and Visualization Technologies|
|PROPOSAL TITLE:||Automated Feature Extraction from Hyperspectral Imagery|
SMALL BUSINESS CONCERN
(Firm Name, Mail Address, City/State/Zip, Phone)
VISUAL LEARNING SYSTEMS, INC.
1719 Dearborn Avenue
Missoula, MT 59801-2391
PRINCIPAL INVESTIGATOR/PROJECT MANAGER
(Name, E-mail, Mail Address, City/State/Zip, Phone)
1280 S. 3rd Street West, #2
Missoula, MT 59801-2391
TECHNICAL ABSTRACT (Limit 2000 characters, approximately 200 words)
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.
POTENTIAL NASA COMMERCIAL APPLICATIONS (Limit 1500 characters, approximately 150 words)
NASA has a significant requirement for detailed, accurate and timely information from orbital systems to understand the earth, its environment and the changes that are ongoing. The proposer's current products Feature Analyst and LIDAR Analyst provide automated techniques for creating and building valuable information about the earth from orbital and airborne sensors; however, such sensors are growing more sophisticated, such as hyperspectral sensors, which requires new and innovative software tools. The proposed Hyperspectral Toolkit compliments the existing proposer's current products to precisely meet NASA's pressing need. The proposed system from Phase II is a perfect fit for NASA because (a) it provides a solution to a pressing need (HSI exploitation techniques), (b) it is easy to learn and use, (c) it provides automated solutions to currently time-consuming tasks, (d) it provides accurate information, and (e) it fits in and enhances the current NASA systems and workflow (ArcGIS and ERDAS IMAGINE).
POTENTIAL NON-NASA COMMERCIAL APPLICATIONS (Limit 1500 characters, approximately 150 words)
The proposed technology will greatly simplify the application of hyperspectral image processing and feature extraction for a wide variety earth imagery applications including: 1. Forestry and Environmental solutions to support timber management applications, wildfire modeling, and land-use analysis. The US Forest Service has already purchased a site license of Feature Analyst and their use of hyperspectral data increases. 2. Civil Government applications for such activities as pervious-impervious surface mapping, creation and maintenance of GIS data layers for roads and structures, identification of urban green space. 3. Homeland Security solutions for the creation and maintenance of GIS data layers. The newly created Department of Homeland Security has a budget of over $30 billion to include spending on the identification and mapping of high-value assets (pipelines, power plants, etc), monitoring of borders, and development of 3D urban models for preparing disaster and emergency services. 4. Defense and Intelligence agencies, such as the NGA and all branches of the military use Feature Analyst in their production and need better techniques for handling HSI data. 5. Over 100 universities currently use Feature Analyst and are large consumers of HSI.
|NASA's technology taxonomy has been developed by the SBIR-STTR program to disseminate awareness of proposed and awarded R/R&D in the agency. It is a listing of over 100 technologies, sorted into broad categories, of interest to NASA.|
TECHNOLOGY TAXONOMY MAPPING
Autonomous Reasoning/Artificial Intelligence
Data Acquisition and End-to-End-Management
Database Development and Interfacing