Accession Number : AD1037127


Title :   Advanced EMI Models and Classification Algorithms: The Next Level of Sophistication to Improve Discrimination of Challenging Targets


Descriptive Note : Technical Report,06 Apr 2012,30 Apr 2017


Corporate Author : Dartmouth College Hanover United States


Personal Author(s) : Shubitidze,Fridon ; Fernandez,Juan P ; Barrowes,Benjamin ; George,Dave ; Stienhurst,Daniel ; Bell,Thomas


Full Text : https://apps.dtic.mil/dtic/tr/fulltext/u2/1037127.pdf


Report Date : 01 Jan 2017


Pagination or Media Count : 116


Abstract : This project yields combined software/hardware approaches for enhancing the detection and classification of small and/or deep targets at live UXO sites. Advanced EMI models were adapted to existing hardware, hardware electronics were modified to increase EMI responsesfrom buried targets, and modified hardware/software performance was evaluated using test-stand and blind data sets. The combinedapproach detected and classified all shallow targets and also managed to detect and classify small targets buried as deep as 20 times thetarget diameter. The high-power transmitter system developed here has been implemented in the Geometrics mini MetalMapper, acommercially available version of the 2 2 TEMTADS.


Descriptors :   target detection , target classification , schematic diagrams , magnetic dipoles , inverse problems , electromagnetic induction sensors , uxo detection , detectors , electromagnetic induction , pattern recognition , munitions , electrical properties , magnetic fields , warning systems , digital data , classification , algorithms , TARGET DISCRIMINATION


Subject Categories : Target Direction, Range and Position Finding
      Numerical Mathematics


Distribution Statement : APPROVED FOR PUBLIC RELEASE