<mods:mods xmlns:mods="http://www.loc.gov/mods/v3" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" ID="etd1119" xsi:schemaLocation="http://www.loc.gov/mods/v3 http://www.loc.gov/standards/mods/v3/mods-3-2.xsd">
	<mods:titleInfo>
		<mods:title>Physically Plausible Human Pose and Control Estimation from Video</mods:title>
	</mods:titleInfo><mods:name type="personal">
		<mods:namePart>Vondrak, Marek </mods:namePart>
	<mods:role>
		<mods:roleTerm type="text">creator</mods:roleTerm>
	</mods:role>
	</mods:name>
<mods:originInfo>
	<mods:copyrightDate>2013</mods:copyrightDate>
</mods:originInfo>
<mods:physicalDescription>
        <mods:extent>20, 229 p.</mods:extent>
        <mods:digitalOrigin>born digital</mods:digitalOrigin>
</mods:physicalDescription>
<mods:note>Thesis (Ph.D. -- Brown University (2013)</mods:note>
<mods:name type="personal">
<mods:namePart>Jenkins, Odest</mods:namePart>
<mods:role>
<mods:roleTerm type="text">Director</mods:roleTerm>
</mods:role>
</mods:name>

<mods:name type="personal">
<mods:namePart>Sigal, Leonid</mods:namePart>
<mods:role>
<mods:roleTerm type="text">Reader</mods:roleTerm>
</mods:role>
</mods:name>

<mods:name type="personal">
<mods:namePart>Hodgins, Jessica</mods:namePart>
<mods:role>
<mods:roleTerm type="text">Reader</mods:roleTerm>
</mods:role>
</mods:name>

<mods:name type="personal">
<mods:namePart>Fleet, David</mods:namePart>
<mods:role>
<mods:roleTerm type="text">Reader</mods:roleTerm>
</mods:role>
</mods:name>

<mods:name type="personal">
<mods:namePart>Hays, James</mods:namePart>
<mods:role>
<mods:roleTerm type="text">Reader</mods:roleTerm>
</mods:role>
</mods:name>
<mods:name type="corporate">
		<mods:namePart>Brown University. Computer Science</mods:namePart>
		<mods:role>
			<mods:roleTerm type="text">sponsor</mods:roleTerm>
		</mods:role>
		</mods:name>
	<mods:genre authority="aat">theses</mods:genre>
	<mods:abstract>We propose a new paradigm for vision-based human motion capture. This paradigm 

extends the traditional capture of poses by providing guarantees of physical 

plausibility for the motion reconstructions and mechanisms for adaptation of 

the estimated motions to new environments. We achieve these benefits by 

estimating control programs for simulated physics-based characters from 

(potentially monocular) images. The control programs encode motions implicitly, 

based on their ``underlying physical principles'' and reconstruct the motions 

through simulation. Feedback within the control allows application of the 

principles in modified environments, providing an ability to adapt the motion 

to external events and perturbations. We explore two control models:  

trajectory control and state-space control. The trajectory control model 

encodes the desired behavior of the character as a sequence of per-frame target 

poses tracked by the controller. We can recover this sequence incrementally and 

produce pose estimates that do not suffer from common visual artifacts.  

However, the inference process is prone to overfitting. To address this 

limitation, we then explore a more compact model that is less sensitive to the 

quality of observations. State-space controllers allow concise representation 

of motion dynamics through a sparse set of target poses and control parameters, 

in essence allowing a key-frame-like representation of the original motion. We 

represent state-space controllers using state machines that characterize the 

character behavior in terms of motion phases (states) and physical events that 

cause the phases to switch (transitions, e.g., a foot contact).  Parameters of 

the controller encode the control programs that reproduce the individual phases 

in simulation. Because this control representation is sparse, we are able to 

integrate information locally from multiple (tens of) image frames in 

inference, inducing smoothness in the resulting motion, resolving some of the 

ambiguities that arise in monocular video-based capture and enabling inference 

with weak likelihoods. We demonstrate our approach by capturing sequences of 

walking, jumping, and gymnastics. We evaluate our methods quantitatively and 

qualitatively and illustrate that we can produce motion interpretations that go 

beyond state-of-the-art in pose tracking and are physically plausible.  </mods:abstract>

    <mods:subject>
        <mods:topic>motion capture</mods:topic>
    </mods:subject>

    <mods:subject>
        <mods:topic>control</mods:topic>
    </mods:subject>

    <mods:subject>
        <mods:topic>physics-based characters</mods:topic>
    </mods:subject>

    <mods:subject>
        <mods:topic>physical simulation</mods:topic>
    </mods:subject>

    <mods:subject>
        <mods:topic>controller estimation</mods:topic>
    </mods:subject>

    <mods:subject>
        <mods:topic>optimal control</mods:topic>
    </mods:subject>

	<mods:subject xmlns:xlink="http://www.w3.org/1999/xlink" authority="FAST" authorityURI="http://id.worldcat.org/fast" valueURI="http://id.worldcat.org/fast/872687"><mods:topic>Computer vision</mods:topic></mods:subject><mods:recordInfo>
		<mods:recordContentSource authority="marcorg">RPB</mods:recordContentSource>
		<mods:recordCreationDate encoding="iso8601">20131219</mods:recordCreationDate>        
	</mods:recordInfo>
<mods:language xmlns:xlink="http://www.w3.org/1999/xlink"><mods:languageTerm type="code" authority="iso639-2b">eng</mods:languageTerm><mods:languageTerm type="text">English</mods:languageTerm></mods:language><mods:identifier xmlns:xlink="http://www.w3.org/1999/xlink" type="doi">10.7301/Z0XP737C</mods:identifier><mods:accessCondition xmlns:xlink="http://www.w3.org/1999/xlink" type="rights statement" xlink:href="http://rightsstatements.org/vocab/InC/1.0/">In Copyright</mods:accessCondition><mods:accessCondition type="restriction on access">Collection is open for research.</mods:accessCondition><mods:typeOfResource xmlns:xlink="http://www.w3.org/1999/xlink" authority="primo">dissertations</mods:typeOfResource></mods:mods>