Date Approved
2-3-2025
Embargo Period
3-24-2025
Document Type
Thesis
Degree Name
Master of Science (M.S.)
Department
Electrical and Computer Engineering
College
Henry M. Rowan College of Engineering
Advisor
George Lecakes, PhD
Committee Member 1
Nidhal Bouaynaya, PhD
Committee Member 2
Amanda Almon, MFA, CMI
Keywords
Drones;Object Detection;Synthetic Data;Virtual Reality
Disciplines
Computer Engineering | Engineering
Abstract
The widespread use of unmanned aerial vehicles (UAVs) across civilian and military applications has necessitated the advancement of real-time drone detection and tracking capabilities. Machine Learning (ML) addresses these requirements, however, to train a robust and generalizable model requires large and diverse video datasets. Curating these real-world datasets is often time-consuming and cost-prohibitive. Here, we present DyViR, a real-time customizable rendering application capable of automatically generating highly realistic synthetic, multi-modal video of aerial objects, digital environments, and automatic generation and labeling of bounding boxes. Synthetic data, coupled with real-world training sets, augment the ML training process, leading to increased performance and detection accuracy. DyViR is designed to enable non-technical users to generate datasets containing 47 different aerial objects, 4 flight patterns, and 8 environments. To verify the benefits of using synthetic data to augment existing real-world datasets, the YOLOv7-tiny model was employed to evaluate a fully real-world dataset and one augmented with synthetically generated data from DyViR, resulting in a 60.4% increase in mean average precision. This research demonstrates the potential of synthetic datasets, especially when it would be impossible or cost-prohibitive to obtain, opening the door to broader applications where data acquisition is challenging.
Recommended Citation
Williams, Garrett, "GENERATING REAL-TIME SYNTHETIC DATASETS TO IMPROVE AERIAL OBJECT DETECTION" (2025). Theses and Dissertations. 3326.
https://rdw.rowan.edu/etd/3326
