Date of Award
3-2021
Document Type
Thesis
Degree Name
Master of Science
Department
Department of Electrical and Computer Engineering
First Advisor
Scott L. Nykl, PhD
Abstract
Remotely Piloted Aircraft (RPA) are currently unable to refuel mid-air due to the large communication delays between their operators and the aircraft. AAR seeks to address this problem by reducing the communication delay to a fast line-of-sight signal between the tanker and the RPA. Current proposals for AAR utilize stereo cameras to estimate where the receiving aircraft is relative to the tanker, but require accurate calibrations for accurate location estimates of the receiver. This paper improves the accuracy of this calibration by improving three components of it: increasing the quantity of intrinsic calibration data with CNN preprocessing, improving the quality of the intrinsic calibration data through a novel linear regression filter, and reducing the epipolar error of the stereo calibration with optical flow for feature matching and alignment. A combination of all three approaches resulted in significant epipolar error improvements over OpenCV's stereo calibration while also providing significant precision improvements.
AFIT Designator
AFIT-ENG-MS-21-M-056
DTIC Accession Number
AD1132785
Recommended Citation
Larson, Joshua D., "Stereo Camera Calibrations with Optical Flow" (2021). Theses and Dissertations. 4903.
https://scholar.afit.edu/etd/4903