<?xml version="1.0" encoding="UTF-8"?><?xml-stylesheet type="text/xsl" href="static/style.xsl"?><OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd"><responseDate>2026-11-21T03:45:46Z</responseDate><request verb="GetRecord" identifier="oai:macsphere.mcmaster.ca:11375/18248" metadataPrefix="dim">https://prod-ms-be.lib.mcmaster.ca/server/oai/request</request><GetRecord><record><header><identifier>oai:macsphere.mcmaster.ca:11375/18248</identifier><datestamp>2026-09-24T20:50:01Z</datestamp><setSpec>com_11375_271</setSpec><setSpec>col_11375_272</setSpec></header><metadata><dim:dim xmlns:dim="http://www.dspace.org/xmlns/dspace/dim" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:doc="http://www.lyncode.com/xoai" xsi:schemaLocation="http://www.dspace.org/xmlns/dspace/dim http://www.dspace.org/schema/dim.xsd">
   <dim:field mdschema="dc" element="contributor" qualifier="advisor">Shirani, Shahram</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="author">Lengyel, Robert</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="department" lang="en_US">Electrical and Computer Engineering</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2015-09-25T19:11:51Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="available">2015-09-25T19:11:51Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2015-11</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">http://hdl.handle.net/11375/18248</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">https://doi.org/10.71548/15904</dim:field>
   <dim:field mdschema="dc" element="description" lang="en_US">This work focuses on the high frequency restoration of video sequences captured by a hybrid camera, using key-frames as high frequency samples. The proposed method outlines a hierarchy to the super-resolution process, and is aimed at maximizing both speed and performance. Additionally, an advanced image processing simulator (EngineX) was developed to fine tune the algorithm.</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract" lang="en_US">Super-resolution algorithms are designed to enhance the detail level of a&#xd;
particular image or video sequence. However, it is very difficult to achieve in&#xd;
practice due to the problem being ill-posed, and often requires regularization&#xd;
based on assumptions about texture or edges. The process can be aided using&#xd;
high-resolution key-frames such as those generated from a hybrid camera. A&#xd;
hybrid camera is capable of capturing footage in multiple spatial and temporal&#xd;
resolutions. The typical output consists of a high resolution stream captured at&#xd;
low frame rate, and a low resolution stream captured at a high frame rate.&#xd;
Key-frame based super-resolution algorithms exploit the spatial and temporal&#xd;
correlation between the high resolution and low resolution streams to&#xd;
reconstruct a high resolution and high frame rate output stream.&#xd;
&#xd;
The proposed algorithm outlines a hierarchy to the super-resolution process,&#xd;
combining several different classical and novel methods. A residue formulation&#xd;
decides which pixels are required to be further reconstructed if a particular&#xd;
hierarchy stage fails to provide the expected results when compared to the low&#xd;
resolution prior. The hierarchy includes the optical flow based estimation which&#xd;
warps high frequency information from adjacent key-frames to the current frame.&#xd;
Specialized candidate pixel selection reduces the total number of pixels&#xd;
considered in the NLM stage. Occlusion is handled by a final fallback stage in&#xd;
the hierarchy. Additionally, the running time for a CIF sequence of 30 frames&#xd;
has been significantly reduced to within 3 minutes by identifying which pixels&#xd;
require reconstruction with a particular method.&#xd;
&#xd;
A custom simulation environment implements the proposed method as well as many&#xd;
common image processing algorithms. EngineX provides a graphical interface where&#xd;
video sequences and image processing methods can be manipulated and combined.&#xd;
The framework allows for advanced features such as multithreading, parameter&#xd;
sweeping, and block level abstraction which aided the development of the&#xd;
proposed super-resolution algorithm. Both speed and performance were fine tuned&#xd;
using the simulator which is the key to its improved quality over other traditional&#xd;
super-resolution schemes.</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="degreetype" lang="en_US">Thesis</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="degree" lang="en_US">Master of Applied Science (MASc)</dim:field>
   <dim:field mdschema="dc" element="language" qualifier="iso" lang="en_US">en</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Video Super-resolution</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Hybrid Cameras</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">High Frequency Restoration</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">EngineX Simulator</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Key-frame</dim:field>
   <dim:field mdschema="dc" element="title" lang="en_US">Key-Frame Based Video Super-Resolution for Hybrid Cameras</dim:field>
   <dim:field mdschema="dc" element="type" lang="en_US">Thesis</dim:field>
   <dim:field mdschema="others" element="access-status">open.access</dim:field>
</dim:dim></metadata></record></GetRecord></OAI-PMH>