Increasing temporal, structural, and spectral resolution in images using exemplar-based priors

Simple item page
dc.contributor.advisorVeeraraghavan, Ashoken_US
dc.contributor.committeeMemberBaraniuk, Richard G.en_US
dc.contributor.committeeMemberKelly, Kevin F.en_US
dc.creatorHolloway, Jasonen_US
dc.date.accessioned2013-09-16T15:13:54Zen_US
dc.date.accessioned2013-09-16T15:14:17Zen_US
dc.date.available2013-09-16T15:13:54Zen_US
dc.date.available2013-09-16T15:14:17Zen_US
dc.date.created2013-05en_US
dc.date.issued2013-09-16en_US
dc.date.submittedMay 2013en_US
dc.date.updated2013-09-16T15:14:18Zen_US
dc.description.abstractIn the past decade, camera manufacturers have offered smaller form factors, smaller pixel sizes (leading to higher resolution images), and faster processing chips to increase the performance of consumer cameras. However, these conventional approaches have failed to capitalize on the spatio-temporal redundancy inherent in images, nor have they adequately provided a solution for finding $3$D point correspondences for cameras sampling different bands of the visible spectrum. In this thesis, we pose the following question---given the repetitious nature of image patches, and appropriate camera architectures, can statistical models be used to increase temporal, structural, or spectral resolution? While many techniques have been suggested to tackle individual aspects of this question, the proposed solutions either require prohibitively expensive hardware modifications and/or require overly simplistic assumptions about the geometry of the scene. We propose a two-stage solution to facilitate image reconstruction; 1) design a linear camera system that optically encodes scene information and 2) recover full scene information using prior models learned from statistics of natural images. By leveraging the tendency of small regions to repeat throughout an image or video, we are able to learn prior models from patches pulled from exemplar images. The quality of this approach will be demonstrated for two application domains, using low-speed video cameras for high-speed video acquisition and multi-spectral fusion using an array of cameras. We also investigate a conventional approach for finding 3D correspondence that enables a generalized assorted array of cameras to operate in multiple modalities, including multi-spectral, high dynamic range, and polarization imaging of dynamic scenes.en_US
dc.format.mimetypeapplication/pdfen_US
dc.identifier.citationHolloway, Jason. "Increasing temporal, structural, and spectral resolution in images using exemplar-based priors." (2013) Master’s Thesis, Rice University. <a href="https://hdl.handle.net/1911/71966">https://hdl.handle.net/1911/71966</a>.en_US
dc.identifier.slug123456789/ETD-2013-05-518en_US
dc.identifier.urihttps://hdl.handle.net/1911/71966en_US
dc.language.isoengen_US
dc.rightsCopyright is held by the author, unless otherwise indicated. Permission to reuse, publish, or reproduce the work beyond the bounds of fair use or other exemptions to copyright law must be obtained from the copyright holder.en_US
dc.subjectHigh speed videoen_US
dc.subjectCompressive sensingen_US
dc.subjectFlutter shutter video cameraen_US
dc.subjectFSVCen_US
dc.subjectMultispectral imagingen_US
dc.subjectCamera arrayen_US
dc.subject3D stereoen_US
dc.subjectCross-channel point correspondenceen_US
dc.subjectHDR imagingen_US
dc.subjectGeneralized assorted camerasen_US
dc.subjectGACen_US
dc.titleIncreasing temporal, structural, and spectral resolution in images using exemplar-based priorsen_US
dc.typeThesisen_US
dc.type.materialTexten_US
thesis.degree.departmentElectrical and Computer Engineeringen_US
thesis.degree.disciplineEngineeringen_US
thesis.degree.grantorRice Universityen_US
thesis.degree.levelMastersen_US
thesis.degree.nameMaster of Scienceen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
HOLLOWAY-THESIS.pdf
Size:
31.81 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.61 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Rice University Theses and Dissertations
ECE Theses and Dissertations