Masters Thesis Defense for Joshua Dowdy
01/24/18 at 8:30 AM
January 8, 2018
Faculty, graduate and undergraduate students,
You are cordially invited to my Masters thesis defense.
Title: Signal Processing and Machine Learning for Explosive Hazard Detection Using Synthetic Aperture Acoustic and High Resolution Voxel Radar
When: Wednesday, January 24, 2018 at 8:30 AM
Where: Simrall Hall, Room 228 (Conference Room)
Candidate: Joshua L. Dowdy
Degree: Masters, Electrical and Computer Engineering
Committee:
Dr. John E. Ball
(Major Professor)
Dr. Derek T. Anderson
(Co-major Professor)
Dr. Nicolas H. Younan
(Committee Member)
Abstract:
Different signal processing techniques for synthetic aperture acoustic (SAA) and high-resolution voxel radar (HRVR) sensing modalities for side-attack explosive ballistic (SAEB) detection are proposed in this thesis. The sensing modalities were vehicle mounted and the data used was collected at an army test site. More specifically, the use of a frequency azimuthal (fraz) feature for SAA and the fusion of a matched filter (MF) and size contrast filter (SCF) for HRVR was explored. For SAA, the focus was to find a signature in the target’s response that would vary as the vehicle’s view on the target changed. In particular, three different methods to extract the fraz feature were investigated and involved one method being performed in the time domain and the other two being performed on the SAA beamfored imagery. For the HRVR, the focus was put on finding objects that were both anomalous (SCF) and target-like (MF). The idea for this was that if an object in the scene was anomalous to the scene and appeared to be target-like, there is a high chance that the object of interest is a target. The results in both cases are obtained using receiver operating characteristic (ROC) curves and both show encouraging results.
Cheers,
Josh Dowdy