Context-dependent feature selection for landmine detection with ground-penetrating radar
Published
Conference Paper
We present a novel method for improving landmine detection with ground-penetrating radar (GPR) by utilizing a priori knowledge of environmental conditions to facilitate algorithm training. The goal of Context-Dependent Feature Selection (CDFS) is to mitigate performance degradation caused by environmental factors. CDFS operates on GPR data by first identifying its environmental context, and then fuses the decisions of several classifiers trained on context-dependent subsets of features. CDFS was evaluated on GPR data collected at severaldistinct sites under a variety of weather conditions. Results show that using prior environmental knowledge in this fashion has the potential to improve landmine detection. © 2009 SPIE.
Full Text
Duke Authors
Cited Authors
- Ratto, CR; Torrione, PA; Collins, LM
Published Date
- September 8, 2009
Published In
Volume / Issue
- 7303 /
International Standard Serial Number (ISSN)
- 0277-786X
International Standard Book Number 13 (ISBN-13)
- 9780819475695
Digital Object Identifier (DOI)
- 10.1117/12.817946
Citation Source
- Scopus