<?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>2026-11-22T17:05:06Z</responseDate><request verb="GetRecord" identifier="oai:uwspace.uwaterloo.ca:10012/6346" metadataPrefix="dim">https://dspacemainprd01.lib.uwaterloo.ca/server/oai/request</request><GetRecord><record><header><identifier>oai:uwspace.uwaterloo.ca:10012/6346</identifier><datestamp>2017-03-21T14:30:24Z</datestamp><setSpec>com_10012_9900</setSpec><setSpec>com_10012_1</setSpec><setSpec>col_10012_9914</setSpec><setSpec>col_10012_6</setSpec></header><metadata><dim:dim xmlns:dim="http://www.dspace.org/xmlns/dspace/dim" xmlns:doc="http://www.lyncode.com/xoai" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.dspace.org/xmlns/dspace/dim http://www.dspace.org/schema/dim.xsd">
   <dim:field mdschema="dc" element="contributor" qualifier="author" authority="33f12861-5e9c-465e-bc09-46d5699bc241" confidence="600">Shabani, Hossein</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2011-10-03T19:04:01Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="available">2014-04-02T05:00:09Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2011-10-03T19:04:01Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="submitted">2011</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">http://hdl.handle.net/10012/6346</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract" lang="en">The automatic recognition of human actions in video is of great interest in many applications&#xd;
such as automated surveillance, content-based video summarization, video search, and indexing.&#xd;
The problem is challenging due to a wide range of variations among the motion pattern of a given&#xd;
action such as walking across different subjects and the low variations among similar motions&#xd;
such as running and jogging.&#xd;
This thesis has three contributions in a discriminative bottom-up framework to improve the&#xd;
multi-resolution analysis of the motion patterns in video for better recognition of human actions.&#xd;
The first contribution of this thesis is the introduction of a novel approach for a robust local&#xd;
motion feature detection in video. To this end, four different multi-resolution temporally&#xd;
causal and asymmetric filters of log Gaussian, scale-derivative Gaussian, Poisson, and asymmetric&#xd;
sinc are introduced. The performance of these filters is compared with the widely used&#xd;
multi-resolution Gabor filter in a common framework for detection of local salient motions. The&#xd;
features obtained from the asymmetric filtering are more precise and more robust under geometric&#xd;
deformations such as view change or affine transformations. Moreover, they provide higher&#xd;
classification accuracy when they are used with a standard bag-of-words representation of actions&#xd;
and a single discriminative classifier. The experimental results show that the asymmetric&#xd;
sinc performs the best. The Poisson and the scale-derivative Gaussian perform better than log&#xd;
Gaussian and that better than the symmetric temporal Gabor filter.&#xd;
The second contribution of this thesis is the introduction of an efficient action representation.&#xd;
The observation is that the salient features at different spatial and temporal scales characterize&#xd;
different motion information. A multi-resolution analysis of the motion characteristic should be&#xd;
representative of different actions. A multi-resolution action signature provides a more discriminative&#xd;
video representation.&#xd;
The third contribution of this thesis is on the classification of different human actions. To this&#xd;
end, an ensemble of classifiers in a multiple classifier systems (MCS) framework with a parallel&#xd;
topology is utilized. This framework can fully benefit from the multi-resolution characteristics&#xd;
of the motion patterns in the human actions. The classification combination concept of the MCS&#xd;
has been then extended to address two problems in the configuration setting of a recognition&#xd;
framework, namely the choice of distance metric for comparing the action representations and&#xd;
the size of the codebook by which an action is represented. This implication of MCS at multiple&#xd;
stages of the recognition pipeline provides a multi-stage MCS framework which outperforms the&#xd;
existing methods which use a single classifier.&#xd;
Based on the experimental results of the local feature detection and the action classification,&#xd;
the multi-stage MCS framework, which uses the multi-scale features obtained from the temporal&#xd;
asymmetric sinc filtering, is recommended for the task of human action recognition in video.</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="embargoterms" lang="en">1 year</dim:field>
   <dim:field mdschema="dc" element="language" qualifier="iso" lang="en">en</dim:field>
   <dim:field mdschema="dc" element="publisher" lang="en">University of Waterloo</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">motion analysis</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">action classification</dim:field>
   <dim:field mdschema="dc" element="subject" qualifier="program" lang="en">System Design Engineering</dim:field>
   <dim:field mdschema="dc" element="title" lang="en">Improved Multi-resolution Analysis of the Motion Patterns in Video for Human Action Classification</dim:field>
   <dim:field mdschema="dc" element="type" lang="en">Doctoral Thesis</dim:field>
   <dim:field mdschema="dc" element="pending" lang="en">true</dim:field>
   <dim:field mdschema="uws-etd" element="degree" qualifier="department" lang="en">Systems Design Engineering</dim:field>
   <dim:field mdschema="uws-etd" element="degree" lang="en">Doctor of Philosophy</dim:field>
   <dim:field mdschema="uws" element="typeOfResource" lang="en">Text</dim:field>
   <dim:field mdschema="uws" element="peerReviewStatus" lang="en">Unreviewed</dim:field>
   <dim:field mdschema="uws" element="scholarLevel" lang="en">Graduate</dim:field>
   <dim:field mdschema="others" element="access-status">open.access</dim:field>
</dim:dim>
</metadata></record></GetRecord></OAI-PMH>