"Land mine detection using metal detector (MD) and ground penetrating radar (GPR) sensors in hand-held units is a difficult problem. Detection difficulties arise for several reasons, including the varying composition and type of metal in land mines and the time-varying nature of backgrounds, among others. This research explores spatially distributed MD features for differentiating land mine signatures from backgrounds. The spatially distributed features involve correlating sequences of MD energy values with six weighted density distribution functions. These features are evaluated using a standard back propagation neural network on real data sets containing more than 2,300 mine encounters of different size, shape, content and metal composition that are measured under different soil conditions. The effectiveness of these features to detect landmines of varying metal composition and type is investigated. Also, experimental results are presented from statistical analysis for feature assessment"--Abstract, page iii.
Stanley, R. Joe
Miller, Ann K.
Dagli, Cihan H., 1949-
Electrical and Computer Engineering
M.S. in Electrical Engineering
University of Missouri--Rolla
viii, 38 pages
© 2002 Satish Chandra Somanchi, All rights reserved.
Thesis - Restricted Access
Land mines -- Detection
Mines (Military explosives) -- Detection
Print OCLC #
Link to Catalog Record
Electronic access to the full-text of this document is restricted to Missouri S&T users. Otherwise, request this publication directly from Missouri S&T Library or contact your local library.http://merlin.lib.umsystem.edu/record=b4967899~S5
Somanchi, Satish, "The application of weighted density distribution functions to landmine detection using hand-held units" (2002). Masters Theses. 2222.
Share My Thesis If you are the author of this work and would like to grant permission to make it openly accessible to all, please click the button above.