Intelligent Data Fusion for Wide-Area Assessment of UXO Contamination
Abstract
Intelligent data fusion techniques are being developed and optimized for use in enhancing wide-area assessment (WAA) for UXO remediation efforts. This report describes the investigations in the second year of project MM-1510 that focused on data fusion. A generalized method for processing input data feature streams from UXO WAA surveys was developed. The method requires the generation of a corresponding geo-referenced feature intensity map and the specification of a functional relationship between the feature's intensity and the hypotheses supported by the presence or absence of that feature. The method accommodates diverse feature sets and widely varying evidential relationships as potential inputs for data fusion. Three data fusion theories were investigated: heuristic, Bayesian theoretic and Dempster-Shafer theoretic approaches. Two prototype data fusion frameworks were developed and evaluated with feature sets for the Pueblo and Kirtland sites. Preliminary results obtained with a prototype Dempster-Shafer based data fusion framework agreed well with the limited ground truth data available at the Pueblo site.
Document Details
- Document Type
- Technical Report
- Publication Date
- Feb 29, 2008
- Accession Number
- ADA478542
Entities
People
- Christian Minor
- Kevin Johnson
- Susan L. Rose-Pehrsson
- Verner Guthrie
Organizations
- United States Naval Research Laboratory