Theses and Dissertations
ORCID
https://orcid.org/0009-0005-9116-2981
Advisor
Lee, Seunghan
Committee Member
Wang, Haifeng
Committee Member
Tajik, Nazanin
Committee Member
Piper, Adam
Committee Member
Driouche, Bouteina
Date of Degree
12-12-2025
Original embargo terms
Embargo 2 years
Document Type
Dissertation - Open Access
Major
Industrial and Systems Engineering
Degree Name
Doctor of Philosophy (Ph.D.)
College
James Worth Bagley College of Engineering
Department
Department of Industrial and Systems Engineering
Abstract
Since their initial use by John Johnson at the U.S. Army Night Vision Laboratory (later renamed the U.S. Army Night Vision and Electronic Sensors Directorate, NVESD) for target identification, recognition, and prediction, Electro-Optical and Infrared (EO/IR) sensors have become widely employed in surveillance, intelligence gathering, geospatial monitoring, and military operations. With a projected market valuation of $12.9 billion by 2031, EO/IR sensors play a crucial role in addressing global military challenges and advancing Unmanned Aerial Vehicles (UAVs). This is particularly evident in the commercial and civilian UAV sectors, where Beyond Visual Line of Sight (BVLOS) research has become essential. To support these advancements, the Federal Aviation Administration (FAA) is actively funding research aimed at enabling BVLOS flight for commercial and civilian applications. The objective of this research is to enhance EO/IR sensor data analytics by employing Dynamic Time Warping (DTW)-based approaches. Specifically, this research (1) Evaluates EO/IR sensor data and assesses decluttering techniques (2) Compares and contrasts various time series and sensor trajectory classification techniques (3) simulates sensor signals (4) utilizes machine learning methods for sensor classification.
Sponsorship (Optional)
Waggoner Engineering Inc. and FAA ASSURE A57
Recommended Citation
Ajayi, Asishana Bamidele, "Advanced EO/IR sensor data analysis: DTW-based methods for track simulation, clutter reduction, and classification" (2025). Theses and Dissertations. 6743.
https://scholarsjunction.msstate.edu/td/6743
