Automated Feature Extraction from Hyperspectral Imagery
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.
Small Business Information at Submission:
Visual Learning Systems, Inc.
1719 Dearborn Avenue Missoula, MT 59801
Number of Employees: