Date of Award
3-2022
Document Type
Thesis
Degree Name
Master of Science in Electrical Engineering
Department
Department of Electrical and Computer Engineering
First Advisor
Robert C. Leishman, PhD
Abstract
Aircraft visual inspection, which is essential to daily maintenance of an aircraft, is expensive and time-consuming to perform. Augmenting trained maintenance technicians with automated UAVs to collect and analyze images for aircraft inspection is an active research topic and a potential application of CNNs. Training datasets for niche research topics such as aircraft visual inspection are small and challenging to produce, and the manual process of labeling these datasets often produces subjective annotations. Recently, researchers have produced several successful applications of artificially generated datasets with domain randomization for training CNNs for real-world computer vision problems. The research outlined herein builds upon this idea to create an artificial data generation pipeline inside Blender and generate an artificial dataset to train an instance-segmentation CNN model for car damage detection. This research then evaluates the real-world performance of several models, each pre-trained on the COCO dataset and fine-tuned on custom generated artificial dataset.
AFIT Designator
AFIT-ENG-MS-20-M-028
DTIC Accession Number
AD1173295
Recommended Citation
Gaul, Nathan J., "Automated Aircraft Visual Inspection with Artificial Data Generation Enabled Deep Learning" (2022). Theses and Dissertations. 5367.
https://scholar.afit.edu/etd/5367