4D reconstruction of construction photographs

Simple item page
dc.contributor.authorMillar Usiskin, Josh
dc.contributor.examiningcommitteeMeek, Dereck (Computer Science) Diamond, Jeff (Electrical & Computer Engineering)en_US
dc.contributor.supervisorWalton, Desmond (Computer Science) Irani, Pourang (Computer Science)en_US
dc.date.accessioned2013-08-22T13:44:06Z
dc.date.available2013-08-22T13:44:06Z
dc.date.issued2013-08-22
dc.degree.disciplineComputer Scienceen_US
dc.degree.levelMaster of Science (M.Sc.)en_US
dc.description.abstractRecent research has enabled reconstruction of a scene from multiple images. These algorithms rely on assumptions that the scene does not change drastically from one photo to the next. Construction photographs, in particular, pose challenges for the existing algorithms. I propose a novel image-based reconstruction algorithm that overcomes these limitations and reconstructs a 4D indoor Manhattan model using construction photographs. Finally, I present a novel user interface that combines image-based rendering and intuitive 4D navigation controls to observe and explore the resulting reconstruction.en_US
dc.description.noteOctober 2013en_US
dc.identifier.urihttp://hdl.handle.net/1993/22057
dc.language.isoengen_US
dc.rightsopen accessen_US
dc.subjectreconstructionen_US
dc.subject4Den_US
dc.subject3Den_US
dc.subjectManhattanen_US
dc.subjectindooren_US
dc.subjectcomputer visionen_US
dc.subjectspatiotemporalen_US
dc.subjectvisualizationen_US
dc.title4D reconstruction of construction photographsen_US
dc.typemaster thesisen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
millar_usiskin_josh.pdf
Size:
7.89 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
2.25 KB
Format:
Item-specific license agreed to upon submission
Description:
Download
Collections
FGS - Electronic Theses and Practica