Abstract
dc:description.abstractThe field of computer vision has numerous applications of the real-world to pixel coordinate conversion. Related fields of machine learning, artificial intelligence, virtual reality, and augmented reality share similar benefits. My contribution involves assessing the accuracy of multiple coordinate conversion methods through experimentation. The Focal Length Calibration method allows for manual calibration using the scale factor. I have concluded that manual camera calibration causes the greatest improvements to accuracy when the method focuses on every point in the image. Methods that localize accuracy still increase accuracy, but not to the same degree.
Degree
thesis:*- Name thesis:degree_name
- Master of Science, Computer Science (M.S.C.S.)
- Level thesis:degree_level
- Thesis (open access)
- Discipline thesis:degree_discipline
- Department of Computer Science
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Imudia, Noredia O
- Contributors dc:contributor
-
- Ryan Florin
- Weitian Tong
- Andrew Allen
Subjects
dc:subject × 7Rights
- Licence dc:rights.license
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://digitalcommons.georgiasouthern.edu/etd/3004