Intelligent Data Fusion for Wide-Area Assessment of UXO Contamination. SERDP Project MM-1510. 2006 Annual Report
Abstract
Intelligent data fusion techniques are being developed and optimized for use in enhancing wide-area assessment UXO remediation efforts. A data fusion framework will be created to provide a cohesive data management and decision-making utility that will capture all available data and more efficiently direct the expenditure of time, labor, and resources. The objectives of the first year are to determine the feasibility of feature selection methods for data fusion. The first year of project MM-1510 successfully demonstrated the feasibility of feature extraction from wide-area assessment survey data. In contrast to the individual data sources, feature extraction yielded enhanced data for the Pueblo PBR #2 that was well-suited for data fusion. Preliminary combination of feature maps from the various data sources yielded a map for the Pueblo site that was more accurate than any one data source alone. Probability densities were generated from the feature maps and make possible the combination of estimates of data quality, UXO-related features, non-UXO backgrounds, and correlations among the data sets in a Bayesian-based approach to data fusion.
Document Details
- Document Type
- Technical Report
- Publication Date
- Apr 20, 2007
- Accession Number
- ADA467324
Entities
People
- Christian Minor
- Kevin Johnson
- Susan L. Rose-Pehrsson
- Verner Guthrie
Organizations
- United States Naval Research Laboratory