<?xml version="1.0" encoding="UTF-8" ?>
<oai_dc:dc schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
<dc:title>6DoF : Registration of Range Data [lecture 1]</dc:title>
<dc:creator>Birk, Andreas Johannes</dc:creator>
<dc:subject>Visualització tridimensional (Informàtica) -- Congressos</dc:subject>
<dc:subject>Three-dimensional display systems -- Congresses</dc:subject>
<dc:subject>Robots mòbils -- Sistemes de control -- Congressos</dc:subject>
<dc:subject>Mobile robots -- Control systems -- Congresses</dc:subject>
<dc:description>Registration deals with the problem of aligning sensor readings taken at two different poses, i.e., in the case of 3D range data to determine the 6 degree‐of‐freedom (DoF) spatial transformation that properlyco‐aligns corresponding regions of the data. 6‐DoF registration is hence a core element in 3D perception and world‐modeling, for example for the matching of templates from an object database to a scene or for the integration of multiple scans taken at different poses into a global 3D map. The lecture presents well‐known state of the art methods like the Iterative Closest Point (ICP) algorithm and its variants, and visual methods using interest points, e.g., the Harris corner detector, plus descriptors, e.g., the Scale Invariant Feature Transform (SIFT), in combination with the Random Sampling Consensus (RANSAC) algorithm. Furthermore, novel 6‐DoF registration methods are presented that unlike classical methods like ICP do not use local features. Instead they are based on the postulate that it is beneficial to employ large dominant structures in the data for registration. The first method is Spectral Registration withMultilayer Resampling (SRMR). It is based on decoupling 3D rotation from 3D translation by a corresponding resampling process of the spectral magnitude of a 3D Fast Fourier Transform (FFT) calculation on discretized 3D range data. The registration of all 6‐DoF is then subsequently carried out with spectral registrations in 1D, 2D and 3D using Phase Only Matched Filtering (POMF). The second method is Plane‐based Registration, which features an efficient algorithm to simultaneously determine optimal correspondences and rigid transforms between two sets of planes fitted into range data. It is shown for both methods that they work under very partial overlap between the scans, with very noisy sensor data, and even under the presence of large occlusions. It is also shown for the Plane‐based. Registration that it not only works in indoor environments but also in unstructured scenarios including even hilly landscapes</dc:description>
<dc:date>2012-05-08</dc:date>
<dc:date>2015-06-03T03:26:15Z</dc:date>
<dc:date>2015-06-03T03:26:15Z</dc:date>
<dc:date>2015-06-03T03:26:15Z</dc:date>
<dc:type>info:eu-repo/semantics/lecture</dc:type>
<dc:identifier>Birk, A.J. (2011). 6DoF : Registration of Range Data [lecture 1]. A 'Sessions professors visitants màster Vibot'. Girona: Universitat. [Consulta: 15 maig 2011]. Disponible a: http://hdl.handle.net/10256.1/2536</dc:identifier>
<dc:identifier>http://hdl.handle.net/10256.1/2536</dc:identifier>
<dc:language>eng</dc:language>
<dc:relation>Sessions professors visitants màster Vibot</dc:relation>
<dc:rights>Aquest document està subjecte a una llicència Creative Commons: Reconeixement – No comercial – Compartir igual (by-nc-sa)</dc:rights>
<dc:rights><a href="http://creativecommons.org/licenses/by-nc-sa/3.0/es/deed.ca">http://creativecommons.org/licenses/by-nc-sa/3.0/es/deed.ca</a></dc:rights>
<dc:format>video/H263</dc:format>
<dc:format>audio/mpeg</dc:format>
<dc:publisher>Universitat de Girona. Escola Politècnica Superior</dc:publisher>
</oai_dc:dc>
<?xml version="1.0" encoding="UTF-8" ?>
<d:DIDL schemaLocation="urn:mpeg:mpeg21:2002:02-DIDL-NS http://standards.iso.org/ittf/PubliclyAvailableStandards/MPEG-21_schema_files/did/didl.xsd">
<d:DIDLInfo>
<dcterms:created schemaLocation="http://purl.org/dc/terms/ http://dublincore.org/schemas/xmls/qdc/dcterms.xsd">2015-06-03T03:26:15Z</dcterms:created>
</d:DIDLInfo>
<d:Item id="hdl_10503_31302">
<d:Descriptor>
<d:Statement mimeType="application/xml; charset=utf-8">
<dii:Identifier schemaLocation="urn:mpeg:mpeg21:2002:01-DII-NS http://standards.iso.org/ittf/PubliclyAvailableStandards/MPEG-21_schema_files/dii/dii.xsd">urn:hdl:10503/31302</dii:Identifier>
</d:Statement>
</d:Descriptor>
<d:Descriptor>
<d:Statement mimeType="application/xml; charset=utf-8">
<oai_dc:dc schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
<dc:title>6DoF : Registration of Range Data [lecture 1]</dc:title>
<dc:creator>Birk, Andreas Johannes</dc:creator>
<dc:subject>Visualització tridimensional (Informàtica) -- Congressos</dc:subject>
<dc:subject>Three-dimensional display systems -- Congresses</dc:subject>
<dc:subject>Robots mòbils -- Sistemes de control -- Congressos</dc:subject>
<dc:subject>Mobile robots -- Control systems -- Congresses</dc:subject>
<dc:description>Registration deals with the problem of aligning sensor readings taken at two different poses, i.e., in the case of 3D range data to determine the 6 degree‐of‐freedom (DoF) spatial transformation that properlyco‐aligns corresponding regions of the data. 6‐DoF registration is hence a core element in 3D perception and world‐modeling, for example for the matching of templates from an object database to a scene or for the integration of multiple scans taken at different poses into a global 3D map. The lecture presents well‐known state of the art methods like the Iterative Closest Point (ICP) algorithm and its variants, and visual methods using interest points, e.g., the Harris corner detector, plus descriptors, e.g., the Scale Invariant Feature Transform (SIFT), in combination with the Random Sampling Consensus (RANSAC) algorithm. Furthermore, novel 6‐DoF registration methods are presented that unlike classical methods like ICP do not use local features. Instead they are based on the postulate that it is beneficial to employ large dominant structures in the data for registration. The first method is Spectral Registration withMultilayer Resampling (SRMR). It is based on decoupling 3D rotation from 3D translation by a corresponding resampling process of the spectral magnitude of a 3D Fast Fourier Transform (FFT) calculation on discretized 3D range data. The registration of all 6‐DoF is then subsequently carried out with spectral registrations in 1D, 2D and 3D using Phase Only Matched Filtering (POMF). The second method is Plane‐based Registration, which features an efficient algorithm to simultaneously determine optimal correspondences and rigid transforms between two sets of planes fitted into range data. It is shown for both methods that they work under very partial overlap between the scans, with very noisy sensor data, and even under the presence of large occlusions. It is also shown for the Plane‐based. Registration that it not only works in indoor environments but also in unstructured scenarios including even hilly landscapes</dc:description>
<dc:date>2015-06-03T03:26:15Z</dc:date>
<dc:date>2015-06-03T03:26:15Z</dc:date>
<dc:date>2015-06-03T03:26:15Z</dc:date>
<dc:type>info:eu-repo/semantics/lecture</dc:type>
<dc:identifier>Birk, A.J. (2011). 6DoF : Registration of Range Data [lecture 1]. A 'Sessions professors visitants màster Vibot'. Girona: Universitat. [Consulta: 15 maig 2011]. Disponible a: http://hdl.handle.net/10256.1/2536</dc:identifier>
<dc:identifier>http://hdl.handle.net/10256.1/2536</dc:identifier>
<dc:language>eng</dc:language>
<dc:relation>Sessions professors visitants màster Vibot</dc:relation>
<dc:rights>Aquest document està subjecte a una llicència Creative Commons: Reconeixement – No comercial – Compartir igual (by-nc-sa)</dc:rights>
<dc:rights><a href="http://creativecommons.org/licenses/by-nc-sa/3.0/es/deed.ca">http://creativecommons.org/licenses/by-nc-sa/3.0/es/deed.ca</a></dc:rights>
<dc:publisher>Universitat de Girona. Escola Politècnica Superior</dc:publisher>
</oai_dc:dc>
</d:Statement>
</d:Descriptor>
</d:Item>
</d:DIDL>
<?xml version="1.0" encoding="UTF-8" ?>
<dim:dim schemaLocation="http://www.dspace.org/xmlns/dspace/dim http://www.dspace.org/schema/dim.xsd">
<dim:field element="contributor" mdschema="dc" qualifier="author">Birk, Andreas Johannes</dim:field>
<dim:field element="date" mdschema="dc">2012-05-08</dim:field>
<dim:field element="date" mdschema="dc" qualifier="accessioned">2015-06-03T03:26:15Z</dim:field>
<dim:field element="date" mdschema="dc" qualifier="available">2015-06-03T03:26:15Z</dim:field>
<dim:field element="date" mdschema="dc" qualifier="issued">2015-06-03T03:26:15Z</dim:field>
<dim:field element="identifier" mdschema="dc" qualifier="citation">Birk, A.J. (2011). 6DoF : Registration of Range Data [lecture 1]. A 'Sessions professors visitants màster Vibot'. Girona: Universitat. [Consulta: 15 maig 2011]. Disponible a: http://hdl.handle.net/10256.1/2536</dim:field>
<dim:field element="identifier" mdschema="dc" qualifier="uri">http://hdl.handle.net/10256.1/2536</dim:field>
<dim:field element="description" mdschema="dc" qualifier="abstract">Registration deals with the problem of aligning sensor readings taken at two different poses, i.e., in the case of 3D range data to determine the 6 degree‐of‐freedom (DoF) spatial transformation that properlyco‐aligns corresponding regions of the data. 6‐DoF registration is hence a core element in 3D perception and world‐modeling, for example for the matching of templates from an object database to a scene or for the integration of multiple scans taken at different poses into a global 3D map. The lecture presents well‐known state of the art methods like the Iterative Closest Point (ICP) algorithm and its variants, and visual methods using interest points, e.g., the Harris corner detector, plus descriptors, e.g., the Scale Invariant Feature Transform (SIFT), in combination with the Random Sampling Consensus (RANSAC) algorithm. Furthermore, novel 6‐DoF registration methods are presented that unlike classical methods like ICP do not use local features. Instead they are based on the postulate that it is beneficial to employ large dominant structures in the data for registration. The first method is Spectral Registration withMultilayer Resampling (SRMR). It is based on decoupling 3D rotation from 3D translation by a corresponding resampling process of the spectral magnitude of a 3D Fast Fourier Transform (FFT) calculation on discretized 3D range data. The registration of all 6‐DoF is then subsequently carried out with spectral registrations in 1D, 2D and 3D using Phase Only Matched Filtering (POMF). The second method is Plane‐based Registration, which features an efficient algorithm to simultaneously determine optimal correspondences and rigid transforms between two sets of planes fitted into range data. It is shown for both methods that they work under very partial overlap between the scans, with very noisy sensor data, and even under the presence of large occlusions. It is also shown for the Plane‐based. Registration that it not only works in indoor environments but also in unstructured scenarios including even hilly landscapes</dim:field>
<dim:field element="description" lang="en" mdschema="dc" qualifier="provenance">Made available in DSpace on 2015-06-03T03:26:15Z (GMT). No. of bitstreams: 0</dim:field>
<dim:field element="format" mdschema="dc">video/H263</dim:field>
<dim:field element="format" mdschema="dc">audio/mpeg</dim:field>
<dim:field element="language" mdschema="dc" qualifier="iso">eng</dim:field>
<dim:field element="publisher" mdschema="dc">Universitat de Girona. Escola Politècnica Superior</dim:field>
<dim:field element="relation" mdschema="dc">Sessions professors visitants màster Vibot</dim:field>
<dim:field element="rights" mdschema="dc">Aquest document està subjecte a una llicència Creative Commons: Reconeixement – No comercial – Compartir igual (by-nc-sa)</dim:field>
<dim:field element="rights" mdschema="dc"><a href="http://creativecommons.org/licenses/by-nc-sa/3.0/es/deed.ca">http://creativecommons.org/licenses/by-nc-sa/3.0/es/deed.ca</a></dim:field>
<dim:field element="subject" mdschema="dc">Visualització tridimensional (Informàtica) -- Congressos</dim:field>
<dim:field element="subject" mdschema="dc">Three-dimensional display systems -- Congresses</dim:field>
<dim:field element="subject" mdschema="dc">Robots mòbils -- Sistemes de control -- Congressos</dim:field>
<dim:field element="subject" mdschema="dc">Mobile robots -- Control systems -- Congresses</dim:field>
<dim:field element="title" mdschema="dc">6DoF : Registration of Range Data [lecture 1]</dim:field>
<dim:field element="type" mdschema="dc">info:eu-repo/semantics/lecture</dim:field>
</dim:dim>
<?xml version="1.0" encoding="UTF-8" ?>
<thesis schemaLocation="http://www.ndltd.org/standards/metadata/etdms/1.0/ http://www.ndltd.org/standards/metadata/etdms/1.0/etdms.xsd">
<title>6DoF : Registration of Range Data [lecture 1]</title>
<creator>Birk, Andreas Johannes</creator>
<subject>Visualització tridimensional (Informàtica) -- Congressos</subject>
<subject>Three-dimensional display systems -- Congresses</subject>
<subject>Robots mòbils -- Sistemes de control -- Congressos</subject>
<subject>Mobile robots -- Control systems -- Congresses</subject>
<description>Registration deals with the problem of aligning sensor readings taken at two different poses, i.e., in the case of 3D range data to determine the 6 degree‐of‐freedom (DoF) spatial transformation that properlyco‐aligns corresponding regions of the data. 6‐DoF registration is hence a core element in 3D perception and world‐modeling, for example for the matching of templates from an object database to a scene or for the integration of multiple scans taken at different poses into a global 3D map. The lecture presents well‐known state of the art methods like the Iterative Closest Point (ICP) algorithm and its variants, and visual methods using interest points, e.g., the Harris corner detector, plus descriptors, e.g., the Scale Invariant Feature Transform (SIFT), in combination with the Random Sampling Consensus (RANSAC) algorithm. Furthermore, novel 6‐DoF registration methods are presented that unlike classical methods like ICP do not use local features. Instead they are based on the postulate that it is beneficial to employ large dominant structures in the data for registration. The first method is Spectral Registration withMultilayer Resampling (SRMR). It is based on decoupling 3D rotation from 3D translation by a corresponding resampling process of the spectral magnitude of a 3D Fast Fourier Transform (FFT) calculation on discretized 3D range data. The registration of all 6‐DoF is then subsequently carried out with spectral registrations in 1D, 2D and 3D using Phase Only Matched Filtering (POMF). The second method is Plane‐based Registration, which features an efficient algorithm to simultaneously determine optimal correspondences and rigid transforms between two sets of planes fitted into range data. It is shown for both methods that they work under very partial overlap between the scans, with very noisy sensor data, and even under the presence of large occlusions. It is also shown for the Plane‐based. Registration that it not only works in indoor environments but also in unstructured scenarios including even hilly landscapes</description>
<date>2015-06-03</date>
<date>2015-06-03</date>
<date>2015-06-03</date>
<type>info:eu-repo/semantics/lecture</type>
<identifier>Birk, A.J. (2011). 6DoF : Registration of Range Data [lecture 1]. A 'Sessions professors visitants màster Vibot'. Girona: Universitat. [Consulta: 15 maig 2011]. Disponible a: http://hdl.handle.net/10256.1/2536</identifier>
<identifier>http://hdl.handle.net/10256.1/2536</identifier>
<language>eng</language>
<relation>Sessions professors visitants màster Vibot</relation>
<rights>Aquest document està subjecte a una llicència Creative Commons: Reconeixement – No comercial – Compartir igual (by-nc-sa)</rights>
<rights><a href="http://creativecommons.org/licenses/by-nc-sa/3.0/es/deed.ca">http://creativecommons.org/licenses/by-nc-sa/3.0/es/deed.ca</a></rights>
<publisher>Universitat de Girona. Escola Politècnica Superior</publisher>
</thesis>
<?xml version="1.0" encoding="UTF-8" ?>
<record schemaLocation="http://www.loc.gov/MARC21/slim http://www.loc.gov/standards/marcxml/schema/MARC21slim.xsd">
<leader>00925njm 22002777a 4500</leader>
<datafield ind1=" " ind2=" " tag="042">
<subfield code="a">dc</subfield>
</datafield>
<datafield ind1=" " ind2=" " tag="720">
<subfield code="a">Birk, Andreas Johannes</subfield>
<subfield code="e">author</subfield>
</datafield>
<datafield ind1=" " ind2=" " tag="260">
<subfield code="c">2015-06-03T03:26:15Z</subfield>
</datafield>
<datafield ind1=" " ind2=" " tag="520">
<subfield code="a">Registration deals with the problem of aligning sensor readings taken at two different poses, i.e., in the case of 3D range data to determine the 6 degree‐of‐freedom (DoF) spatial transformation that properlyco‐aligns corresponding regions of the data. 6‐DoF registration is hence a core element in 3D perception and world‐modeling, for example for the matching of templates from an object database to a scene or for the integration of multiple scans taken at different poses into a global 3D map. The lecture presents well‐known state of the art methods like the Iterative Closest Point (ICP) algorithm and its variants, and visual methods using interest points, e.g., the Harris corner detector, plus descriptors, e.g., the Scale Invariant Feature Transform (SIFT), in combination with the Random Sampling Consensus (RANSAC) algorithm. Furthermore, novel 6‐DoF registration methods are presented that unlike classical methods like ICP do not use local features. Instead they are based on the postulate that it is beneficial to employ large dominant structures in the data for registration. The first method is Spectral Registration withMultilayer Resampling (SRMR). It is based on decoupling 3D rotation from 3D translation by a corresponding resampling process of the spectral magnitude of a 3D Fast Fourier Transform (FFT) calculation on discretized 3D range data. The registration of all 6‐DoF is then subsequently carried out with spectral registrations in 1D, 2D and 3D using Phase Only Matched Filtering (POMF). The second method is Plane‐based Registration, which features an efficient algorithm to simultaneously determine optimal correspondences and rigid transforms between two sets of planes fitted into range data. It is shown for both methods that they work under very partial overlap between the scans, with very noisy sensor data, and even under the presence of large occlusions. It is also shown for the Plane‐based. Registration that it not only works in indoor environments but also in unstructured scenarios including even hilly landscapes</subfield>
</datafield>
<datafield ind1="8" ind2=" " tag="024">
<subfield code="a">Birk, A.J. (2011). 6DoF : Registration of Range Data [lecture 1]. A 'Sessions professors visitants màster Vibot'. Girona: Universitat. [Consulta: 15 maig 2011]. Disponible a: http://hdl.handle.net/10256.1/2536</subfield>
</datafield>
<datafield ind1="8" ind2=" " tag="024">
<subfield code="a">http://hdl.handle.net/10256.1/2536</subfield>
</datafield>
<datafield ind1=" " ind2=" " tag="653">
<subfield code="a">Visualització tridimensional (Informàtica) -- Congressos</subfield>
</datafield>
<datafield ind1=" " ind2=" " tag="653">
<subfield code="a">Three-dimensional display systems -- Congresses</subfield>
</datafield>
<datafield ind1=" " ind2=" " tag="653">
<subfield code="a">Robots mòbils -- Sistemes de control -- Congressos</subfield>
</datafield>
<datafield ind1=" " ind2=" " tag="653">
<subfield code="a">Mobile robots -- Control systems -- Congresses</subfield>
</datafield>
<datafield ind1="0" ind2="0" tag="245">
<subfield code="a">6DoF : Registration of Range Data [lecture 1]</subfield>
</datafield>
</record>
<?xml version="1.0" encoding="UTF-8" ?>
<mets ID=" DSpace_ITEM_10503-31302" OBJID=" hdl:10503/31302" PROFILE="DSpace METS SIP Profile 1.0" TYPE="DSpace ITEM" schemaLocation="http://www.loc.gov/METS/ http://www.loc.gov/standards/mets/mets.xsd">
<metsHdr CREATEDATE="2016-01-04T20:04:07Z">
<agent ROLE="CUSTODIAN" TYPE="ORGANIZATION">
<name>MDX (Materials Docents en Xarxa)</name>
</agent>
</metsHdr>
<dmdSec ID="DMD_10503_31302">
<mdWrap MDTYPE="MODS">
<xmlData schemaLocation="http://www.loc.gov/mods/v3 http://www.loc.gov/standards/mods/v3/mods-3-1.xsd">
<mods:mods schemaLocation="http://www.loc.gov/mods/v3 http://www.loc.gov/standards/mods/v3/mods-3-1.xsd">
<mods:name>
<mods:role>
<mods:roleTerm type="text">author</mods:roleTerm>
</mods:role>
<mods:namePart>Birk, Andreas Johannes</mods:namePart>
</mods:name>
<mods:extension>
<mods:dateAccessioned encoding="iso8601">2015-06-03T03:26:15Z</mods:dateAccessioned>
</mods:extension>
<mods:extension>
<mods:dateAvailable encoding="iso8601">2015-06-03T03:26:15Z</mods:dateAvailable>
</mods:extension>
<mods:originInfo>
<mods:dateIssued encoding="iso8601">2015-06-03T03:26:15Z</mods:dateIssued>
</mods:originInfo>
<mods:identifier type="citation">Birk, A.J. (2011). 6DoF : Registration of Range Data [lecture 1]. A 'Sessions professors visitants màster Vibot'. Girona: Universitat. [Consulta: 15 maig 2011]. Disponible a: http://hdl.handle.net/10256.1/2536</mods:identifier>
<mods:identifier type="uri">http://hdl.handle.net/10256.1/2536</mods:identifier>
<mods:abstract>Registration deals with the problem of aligning sensor readings taken at two different poses, i.e., in the case of 3D range data to determine the 6 degree‐of‐freedom (DoF) spatial transformation that properlyco‐aligns corresponding regions of the data. 6‐DoF registration is hence a core element in 3D perception and world‐modeling, for example for the matching of templates from an object database to a scene or for the integration of multiple scans taken at different poses into a global 3D map. The lecture presents well‐known state of the art methods like the Iterative Closest Point (ICP) algorithm and its variants, and visual methods using interest points, e.g., the Harris corner detector, plus descriptors, e.g., the Scale Invariant Feature Transform (SIFT), in combination with the Random Sampling Consensus (RANSAC) algorithm. Furthermore, novel 6‐DoF registration methods are presented that unlike classical methods like ICP do not use local features. Instead they are based on the postulate that it is beneficial to employ large dominant structures in the data for registration. The first method is Spectral Registration withMultilayer Resampling (SRMR). It is based on decoupling 3D rotation from 3D translation by a corresponding resampling process of the spectral magnitude of a 3D Fast Fourier Transform (FFT) calculation on discretized 3D range data. The registration of all 6‐DoF is then subsequently carried out with spectral registrations in 1D, 2D and 3D using Phase Only Matched Filtering (POMF). The second method is Plane‐based Registration, which features an efficient algorithm to simultaneously determine optimal correspondences and rigid transforms between two sets of planes fitted into range data. It is shown for both methods that they work under very partial overlap between the scans, with very noisy sensor data, and even under the presence of large occlusions. It is also shown for the Plane‐based. Registration that it not only works in indoor environments but also in unstructured scenarios including even hilly landscapes</mods:abstract>
<mods:language>
<mods:languageTerm authority="rfc3066">eng</mods:languageTerm>
</mods:language>
<mods:accessCondition type="useAndReproduction">Aquest document està subjecte a una llicència Creative Commons: Reconeixement – No comercial – Compartir igual (by-nc-sa)</mods:accessCondition>
<mods:subject>
<mods:topic>Visualització tridimensional (Informàtica) -- Congressos</mods:topic>
</mods:subject>
<mods:subject>
<mods:topic>Three-dimensional display systems -- Congresses</mods:topic>
</mods:subject>
<mods:subject>
<mods:topic>Robots mòbils -- Sistemes de control -- Congressos</mods:topic>
</mods:subject>
<mods:subject>
<mods:topic>Mobile robots -- Control systems -- Congresses</mods:topic>
</mods:subject>
<mods:titleInfo>
<mods:title>6DoF : Registration of Range Data [lecture 1]</mods:title>
</mods:titleInfo>
<mods:genre>info:eu-repo/semantics/lecture</mods:genre>
</mods:mods>
</xmlData>
</mdWrap>
</dmdSec>
<structMap LABEL="DSpace Object" TYPE="LOGICAL">
</structMap>
</mets>
<?xml version="1.0" encoding="UTF-8" ?>
<mods:mods schemaLocation="http://www.loc.gov/mods/v3 http://www.loc.gov/standards/mods/v3/mods-3-1.xsd">
<mods:name>
<mods:namePart>Birk, Andreas Johannes</mods:namePart>
</mods:name>
<mods:extension>
<mods:dateAvailable encoding="iso8601">2015-06-03T03:26:15Z</mods:dateAvailable>
</mods:extension>
<mods:extension>
<mods:dateAccessioned encoding="iso8601">2015-06-03T03:26:15Z</mods:dateAccessioned>
</mods:extension>
<mods:originInfo>
<mods:dateIssued encoding="iso8601">2015-06-03T03:26:15Z</mods:dateIssued>
</mods:originInfo>
<mods:identifier type="citation">Birk, A.J. (2011). 6DoF : Registration of Range Data [lecture 1]. A 'Sessions professors visitants màster Vibot'. Girona: Universitat. [Consulta: 15 maig 2011]. Disponible a: http://hdl.handle.net/10256.1/2536</mods:identifier>
<mods:identifier type="uri">http://hdl.handle.net/10256.1/2536</mods:identifier>
<mods:abstract>Registration deals with the problem of aligning sensor readings taken at two different poses, i.e., in the case of 3D range data to determine the 6 degree‐of‐freedom (DoF) spatial transformation that properlyco‐aligns corresponding regions of the data. 6‐DoF registration is hence a core element in 3D perception and world‐modeling, for example for the matching of templates from an object database to a scene or for the integration of multiple scans taken at different poses into a global 3D map. The lecture presents well‐known state of the art methods like the Iterative Closest Point (ICP) algorithm and its variants, and visual methods using interest points, e.g., the Harris corner detector, plus descriptors, e.g., the Scale Invariant Feature Transform (SIFT), in combination with the Random Sampling Consensus (RANSAC) algorithm. Furthermore, novel 6‐DoF registration methods are presented that unlike classical methods like ICP do not use local features. Instead they are based on the postulate that it is beneficial to employ large dominant structures in the data for registration. The first method is Spectral Registration withMultilayer Resampling (SRMR). It is based on decoupling 3D rotation from 3D translation by a corresponding resampling process of the spectral magnitude of a 3D Fast Fourier Transform (FFT) calculation on discretized 3D range data. The registration of all 6‐DoF is then subsequently carried out with spectral registrations in 1D, 2D and 3D using Phase Only Matched Filtering (POMF). The second method is Plane‐based Registration, which features an efficient algorithm to simultaneously determine optimal correspondences and rigid transforms between two sets of planes fitted into range data. It is shown for both methods that they work under very partial overlap between the scans, with very noisy sensor data, and even under the presence of large occlusions. It is also shown for the Plane‐based. Registration that it not only works in indoor environments but also in unstructured scenarios including even hilly landscapes</mods:abstract>
<mods:language>
<mods:languageTerm>eng</mods:languageTerm>
</mods:language>
<mods:accessCondition type="useAndReproduction">Aquest document està subjecte a una llicència Creative Commons: Reconeixement – No comercial – Compartir igual (by-nc-sa)</mods:accessCondition>
<mods:accessCondition type="useAndReproduction"><a href="http://creativecommons.org/licenses/by-nc-sa/3.0/es/deed.ca">http://creativecommons.org/licenses/by-nc-sa/3.0/es/deed.ca</a></mods:accessCondition>
<mods:subject>
<mods:topic>Visualització tridimensional (Informàtica) -- Congressos</mods:topic>
</mods:subject>
<mods:subject>
<mods:topic>Three-dimensional display systems -- Congresses</mods:topic>
</mods:subject>
<mods:subject>
<mods:topic>Robots mòbils -- Sistemes de control -- Congressos</mods:topic>
</mods:subject>
<mods:subject>
<mods:topic>Mobile robots -- Control systems -- Congresses</mods:topic>
</mods:subject>
<mods:titleInfo>
<mods:title>6DoF : Registration of Range Data [lecture 1]</mods:title>
</mods:titleInfo>
<mods:genre>info:eu-repo/semantics/lecture</mods:genre>
</mods:mods>
<?xml version="1.0" encoding="UTF-8" ?>
<atom:entry schemaLocation="http://www.w3.org/2005/Atom http://www.kbcafe.com/rss/atom.xsd.xml">
<atom:id>http://hdl.handle.net/10256.1/2536/ore.xml</atom:id>
<atom:published>2015-06-03T03:26:15Z</atom:published>
<atom:updated>2015-06-03T03:26:15Z</atom:updated>
<atom:source>
<atom:generator>MDX (Materials Docents en Xarxa)</atom:generator>
</atom:source>
<atom:title>6DoF : Registration of Range Data [lecture 1]</atom:title>
<atom:author>
<atom:name>Birk, Andreas Johannes</atom:name>
</atom:author>
<oreatom:triples>
<rdf:Description about="http://hdl.handle.net/10256.1/2536/ore.xml#atom">
<dcterms:modified>2015-06-03T03:26:15Z</dcterms:modified>
</rdf:Description>
</oreatom:triples>
</atom:entry>
<?xml version="1.0" encoding="UTF-8" ?>
<qdc:qualifieddc schemaLocation="http://purl.org/dc/elements/1.1/ http://dublincore.org/schemas/xmls/qdc/2006/01/06/dc.xsd http://purl.org/dc/terms/ http://dublincore.org/schemas/xmls/qdc/2006/01/06/dcterms.xsd http://dspace.org/qualifieddc/ http://www.ukoln.ac.uk/metadata/dcmi/xmlschema/qualifieddc.xsd">
<dc:title>6DoF : Registration of Range Data [lecture 1]</dc:title>
<dc:subject>Visualització tridimensional (Informàtica) -- Congressos</dc:subject>
<dc:subject>Three-dimensional display systems -- Congresses</dc:subject>
<dc:subject>Robots mòbils -- Sistemes de control -- Congressos</dc:subject>
<dc:subject>Mobile robots -- Control systems -- Congresses</dc:subject>
<dcterms:abstract>Registration deals with the problem of aligning sensor readings taken at two different poses, i.e., in the case of 3D range data to determine the 6 degree‐of‐freedom (DoF) spatial transformation that properlyco‐aligns corresponding regions of the data. 6‐DoF registration is hence a core element in 3D perception and world‐modeling, for example for the matching of templates from an object database to a scene or for the integration of multiple scans taken at different poses into a global 3D map. The lecture presents well‐known state of the art methods like the Iterative Closest Point (ICP) algorithm and its variants, and visual methods using interest points, e.g., the Harris corner detector, plus descriptors, e.g., the Scale Invariant Feature Transform (SIFT), in combination with the Random Sampling Consensus (RANSAC) algorithm. Furthermore, novel 6‐DoF registration methods are presented that unlike classical methods like ICP do not use local features. Instead they are based on the postulate that it is beneficial to employ large dominant structures in the data for registration. The first method is Spectral Registration withMultilayer Resampling (SRMR). It is based on decoupling 3D rotation from 3D translation by a corresponding resampling process of the spectral magnitude of a 3D Fast Fourier Transform (FFT) calculation on discretized 3D range data. The registration of all 6‐DoF is then subsequently carried out with spectral registrations in 1D, 2D and 3D using Phase Only Matched Filtering (POMF). The second method is Plane‐based Registration, which features an efficient algorithm to simultaneously determine optimal correspondences and rigid transforms between two sets of planes fitted into range data. It is shown for both methods that they work under very partial overlap between the scans, with very noisy sensor data, and even under the presence of large occlusions. It is also shown for the Plane‐based. Registration that it not only works in indoor environments but also in unstructured scenarios including even hilly landscapes</dcterms:abstract>
<dcterms:dateAccepted>2015-06-03T03:26:15Z</dcterms:dateAccepted>
<dcterms:available>2015-06-03T03:26:15Z</dcterms:available>
<dcterms:created>2015-06-03T03:26:15Z</dcterms:created>
<dcterms:issued>2015-06-03T03:26:15Z</dcterms:issued>
<dc:type>info:eu-repo/semantics/lecture</dc:type>
<dc:identifier>Birk, A.J. (2011). 6DoF : Registration of Range Data [lecture 1]. A 'Sessions professors visitants màster Vibot'. Girona: Universitat. [Consulta: 15 maig 2011]. Disponible a: http://hdl.handle.net/10256.1/2536</dc:identifier>
<dc:identifier>http://hdl.handle.net/10256.1/2536</dc:identifier>
<dc:language>eng</dc:language>
<dc:relation>Sessions professors visitants màster Vibot</dc:relation>
<dc:rights>Aquest document està subjecte a una llicència Creative Commons: Reconeixement – No comercial – Compartir igual (by-nc-sa)</dc:rights>
<dc:rights><a href="http://creativecommons.org/licenses/by-nc-sa/3.0/es/deed.ca">http://creativecommons.org/licenses/by-nc-sa/3.0/es/deed.ca</a></dc:rights>
<dc:publisher>Universitat de Girona. Escola Politècnica Superior</dc:publisher>
</qdc:qualifieddc>
<?xml version="1.0" encoding="UTF-8" ?>
<rdf:RDF schemaLocation="http://www.openarchives.org/OAI/2.0/rdf/ http://www.openarchives.org/OAI/2.0/rdf.xsd">
<ow:Publication about="oai:mdx.cat:10503/31302">
<dc:title>6DoF : Registration of Range Data [lecture 1]</dc:title>
<dc:creator>Birk, Andreas Johannes</dc:creator>
<dc:subject>Visualització tridimensional (Informàtica) -- Congressos</dc:subject>
<dc:subject>Three-dimensional display systems -- Congresses</dc:subject>
<dc:subject>Robots mòbils -- Sistemes de control -- Congressos</dc:subject>
<dc:subject>Mobile robots -- Control systems -- Congresses</dc:subject>
<dc:description>Registration deals with the problem of aligning sensor readings taken at two different poses, i.e., in the case of 3D range data to determine the 6 degree‐of‐freedom (DoF) spatial transformation that properlyco‐aligns corresponding regions of the data. 6‐DoF registration is hence a core element in 3D perception and world‐modeling, for example for the matching of templates from an object database to a scene or for the integration of multiple scans taken at different poses into a global 3D map. The lecture presents well‐known state of the art methods like the Iterative Closest Point (ICP) algorithm and its variants, and visual methods using interest points, e.g., the Harris corner detector, plus descriptors, e.g., the Scale Invariant Feature Transform (SIFT), in combination with the Random Sampling Consensus (RANSAC) algorithm. Furthermore, novel 6‐DoF registration methods are presented that unlike classical methods like ICP do not use local features. Instead they are based on the postulate that it is beneficial to employ large dominant structures in the data for registration. The first method is Spectral Registration withMultilayer Resampling (SRMR). It is based on decoupling 3D rotation from 3D translation by a corresponding resampling process of the spectral magnitude of a 3D Fast Fourier Transform (FFT) calculation on discretized 3D range data. The registration of all 6‐DoF is then subsequently carried out with spectral registrations in 1D, 2D and 3D using Phase Only Matched Filtering (POMF). The second method is Plane‐based Registration, which features an efficient algorithm to simultaneously determine optimal correspondences and rigid transforms between two sets of planes fitted into range data. It is shown for both methods that they work under very partial overlap between the scans, with very noisy sensor data, and even under the presence of large occlusions. It is also shown for the Plane‐based. Registration that it not only works in indoor environments but also in unstructured scenarios including even hilly landscapes</dc:description>
<dc:date>2015-06-03T03:26:15Z</dc:date>
<dc:date>2015-06-03T03:26:15Z</dc:date>
<dc:date>2015-06-03T03:26:15Z</dc:date>
<dc:type>info:eu-repo/semantics/lecture</dc:type>
<dc:identifier>Birk, A.J. (2011). 6DoF : Registration of Range Data [lecture 1]. A 'Sessions professors visitants màster Vibot'. Girona: Universitat. [Consulta: 15 maig 2011]. Disponible a: http://hdl.handle.net/10256.1/2536</dc:identifier>
<dc:identifier>http://hdl.handle.net/10256.1/2536</dc:identifier>
<dc:language>eng</dc:language>
<dc:relation>Sessions professors visitants màster Vibot</dc:relation>
<dc:rights>Aquest document està subjecte a una llicència Creative Commons: Reconeixement – No comercial – Compartir igual (by-nc-sa)</dc:rights>
<dc:rights><a href="http://creativecommons.org/licenses/by-nc-sa/3.0/es/deed.ca">http://creativecommons.org/licenses/by-nc-sa/3.0/es/deed.ca</a></dc:rights>
<dc:publisher>Universitat de Girona. Escola Politècnica Superior</dc:publisher>
</ow:Publication>
</rdf:RDF>
<?xml version="1.0" encoding="UTF-8" ?>
<metadata schemaLocation="http://www.lyncode.com/xoai http://www.lyncode.com/xsd/xoai.xsd">
<element name="dc">
<element name="contributor">
<element name="author">
<element name="none">
<field name="value">Birk, Andreas Johannes</field>
</element>
</element>
</element>
<element name="date">
<element name="none">
<field name="value">2012-05-08</field>
</element>
<element name="accessioned">
<element name="none">
<field name="value">2015-06-03T03:26:15Z</field>
</element>
</element>
<element name="available">
<element name="none">
<field name="value">2015-06-03T03:26:15Z</field>
</element>
</element>
<element name="issued">
<element name="none">
<field name="value">2015-06-03T03:26:15Z</field>
</element>
</element>
</element>
<element name="identifier">
<element name="citation">
<element name="none">
<field name="value">Birk, A.J. (2011). 6DoF : Registration of Range Data [lecture 1]. A 'Sessions professors visitants màster Vibot'. Girona: Universitat. [Consulta: 15 maig 2011]. Disponible a: http://hdl.handle.net/10256.1/2536</field>
</element>
</element>
<element name="uri">
<element name="none">
<field name="value">http://hdl.handle.net/10256.1/2536</field>
</element>
</element>
</element>
<element name="description">
<element name="abstract">
<element name="none">
<field name="value">Registration deals with the problem of aligning sensor readings taken at two different poses, i.e., in the case of 3D range data to determine the 6 degree‐of‐freedom (DoF) spatial transformation that properlyco‐aligns corresponding regions of the data. 6‐DoF registration is hence a core element in 3D perception and world‐modeling, for example for the matching of templates from an object database to a scene or for the integration of multiple scans taken at different poses into a global 3D map. The lecture presents well‐known state of the art methods like the Iterative Closest Point (ICP) algorithm and its variants, and visual methods using interest points, e.g., the Harris corner detector, plus descriptors, e.g., the Scale Invariant Feature Transform (SIFT), in combination with the Random Sampling Consensus (RANSAC) algorithm. Furthermore, novel 6‐DoF registration methods are presented that unlike classical methods like ICP do not use local features. Instead they are based on the postulate that it is beneficial to employ large dominant structures in the data for registration. The first method is Spectral Registration withMultilayer Resampling (SRMR). It is based on decoupling 3D rotation from 3D translation by a corresponding resampling process of the spectral magnitude of a 3D Fast Fourier Transform (FFT) calculation on discretized 3D range data. The registration of all 6‐DoF is then subsequently carried out with spectral registrations in 1D, 2D and 3D using Phase Only Matched Filtering (POMF). The second method is Plane‐based Registration, which features an efficient algorithm to simultaneously determine optimal correspondences and rigid transforms between two sets of planes fitted into range data. It is shown for both methods that they work under very partial overlap between the scans, with very noisy sensor data, and even under the presence of large occlusions. It is also shown for the Plane‐based. Registration that it not only works in indoor environments but also in unstructured scenarios including even hilly landscapes</field>
</element>
</element>
<element name="provenance">
<element name="en">
<field name="value">Made available in DSpace on 2015-06-03T03:26:15Z (GMT). No. of bitstreams: 0</field>
</element>
</element>
</element>
<element name="format">
<element name="none">
<field name="value">video/H263</field>
<field name="value">audio/mpeg</field>
</element>
</element>
<element name="language">
<element name="iso">
<element name="none">
<field name="value">eng</field>
</element>
</element>
</element>
<element name="publisher">
<element name="none">
<field name="value">Universitat de Girona. Escola Politècnica Superior</field>
</element>
</element>
<element name="relation">
<element name="none">
<field name="value">Sessions professors visitants màster Vibot</field>
</element>
</element>
<element name="rights">
<element name="none">
<field name="value">Aquest document està subjecte a una llicència Creative Commons: Reconeixement – No comercial – Compartir igual (by-nc-sa)</field>
<field name="value"><a href="http://creativecommons.org/licenses/by-nc-sa/3.0/es/deed.ca">http://creativecommons.org/licenses/by-nc-sa/3.0/es/deed.ca</a></field>
</element>
</element>
<element name="subject">
<element name="none">
<field name="value">Visualització tridimensional (Informàtica) -- Congressos</field>
<field name="value">Three-dimensional display systems -- Congresses</field>
<field name="value">Robots mòbils -- Sistemes de control -- Congressos</field>
<field name="value">Mobile robots -- Control systems -- Congresses</field>
</element>
</element>
<element name="title">
<element name="none">
<field name="value">6DoF : Registration of Range Data [lecture 1]</field>
</element>
</element>
<element name="type">
<element name="none">
<field name="value">info:eu-repo/semantics/lecture</field>
</element>
</element>
</element>
<element name="others">
<field name="handle">10503/31302</field>
<field name="identifier">oai:mdx.cat:10503/31302</field>
<field name="lastModifyDate">2015-06-03 05:26:15.741</field>
</element>
<element name="repository">
<field name="name">MDX (Materials Docents en Xarxa)</field>
<field name="mail">mdx@csuc.cat</field>
</element>
</metadata>