<?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>μ-MAR: Multiplane 3D Marker based Registration for depth-sensing cameras</dc:title>
<dc:creator>Saval-Calvo, Marcelo</dc:creator>
<dc:creator>Azorin-Lopez, Jorge</dc:creator>
<dc:creator>Fuster-Guilló, Andrés</dc:creator>
<dc:creator>Mora, Higinio</dc:creator>
<dc:contributor>Universidad de Alicante. Departamento de Tecnología Informática y Computación</dc:contributor>
<dc:contributor>Informática Industrial y Redes de Computadores</dc:contributor>
<dc:subject>RGB-D sensor</dc:subject>
<dc:subject>Registration</dc:subject>
<dc:subject>Model-based</dc:subject>
<dc:subject>Multiplane</dc:subject>
<dc:subject>Object reconstruction</dc:subject>
<dc:subject>Arquitectura y Tecnología de Computadores</dc:subject>
<dc:description>Many applications including object reconstruction, robot guidance, and. scene mapping require the registration of multiple views from a scene to generate a complete geometric and appearance model of it. In real situations, transformations between views are unknown and it is necessary to apply expert inference to estimate them. In the last few years, the emergence of low-cost depth-sensing cameras has strengthened the research on this topic, motivating a plethora of new applications. Although they have enough resolution and accuracy for many applications, some situations may not be solved with general state-of-the-art registration methods due to the signal-to-noise ratio (SNR) and the resolution of the data provided. The problem of working with low SNR data, in general terms, may appear in any 3D system, then it is necessary to propose novel solutions in this aspect. In this paper, we propose a method, μ-MAR, able to both coarse and fine register sets of 3D points provided by low-cost depth-sensing cameras, despite it is not restricted to these sensors, into a common coordinate system. The method is able to overcome the noisy data problem by means of using a model-based solution of multiplane registration. Specifically, it iteratively registers 3D markers composed by multiple planes extracted from points of multiple views of the scene. As the markers and the object of interest are static in the scenario, the transformations obtained for the markers are applied to the object in order to reconstruct it. Experiments have been performed using synthetic and real data. The synthetic data allows a qualitative and quantitative evaluation by means of visual inspection and Hausdorff distance respectively. The real data experiments show the performance of the proposal using data acquired by a Primesense Carmine RGB-D sensor. The method has been compared to several state-of-the-art methods. The results show the good performance of the μ-MAR to register objects with high accuracy in presence of noisy data outperforming the existing methods.</dc:description>
<dc:description>This work has been supported by grant University of Alicante projects GRE11-01 and grant Valencian Government GV/2013/005.</dc:description>
<dc:date>2015-09-21T08:59:50Z</dc:date>
<dc:date>2015-09-21T08:59:50Z</dc:date>
<dc:date>2015-12-15</dc:date>
<dc:type>info:eu-repo/semantics/article</dc:type>
<dc:identifier>Expert Systems with Applications. 2015, 42(23): 9353-9365. doi:10.1016/j.eswa.2015.08.011</dc:identifier>
<dc:identifier>0957-4174 (Print)</dc:identifier>
<dc:identifier>1873-6793 (Online)</dc:identifier>
<dc:identifier>http://hdl.handle.net/10045/49529</dc:identifier>
<dc:identifier>10.1016/j.eswa.2015.08.011</dc:identifier>
<dc:identifier>A7758346</dc:identifier>
<dc:language>eng</dc:language>
<dc:relation>http://dx.doi.org/10.1016/j.eswa.2015.08.011</dc:relation>
<dc:rights>© 2015 Elsevier Ltd.</dc:rights>
<dc:rights>info:eu-repo/semantics/openAccess</dc:rights>
<dc:publisher>Elsevier</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">2015-09-21T08:59:50Z</dcterms:created>
</d:DIDLInfo>
<d:Item id="hdl_10045_49529">
<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:10045/49529</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>μ-MAR: Multiplane 3D Marker based Registration for depth-sensing cameras</dc:title>
<dc:creator>Saval-Calvo, Marcelo</dc:creator>
<dc:creator>Azorin-Lopez, Jorge</dc:creator>
<dc:creator>Fuster-Guilló, Andrés</dc:creator>
<dc:creator>Mora, Higinio</dc:creator>
<dc:contributor>Universidad de Alicante. Departamento de Tecnología Informática y Computación</dc:contributor>
<dc:subject>RGB-D sensor</dc:subject>
<dc:subject>Registration</dc:subject>
<dc:subject>Model-based</dc:subject>
<dc:subject>Multiplane</dc:subject>
<dc:subject>Object reconstruction</dc:subject>
<dc:description>Many applications including object reconstruction, robot guidance, and. scene mapping require the registration of multiple views from a scene to generate a complete geometric and appearance model of it. In real situations, transformations between views are unknown and it is necessary to apply expert inference to estimate them. In the last few years, the emergence of low-cost depth-sensing cameras has strengthened the research on this topic, motivating a plethora of new applications. Although they have enough resolution and accuracy for many applications, some situations may not be solved with general state-of-the-art registration methods due to the signal-to-noise ratio (SNR) and the resolution of the data provided. The problem of working with low SNR data, in general terms, may appear in any 3D system, then it is necessary to propose novel solutions in this aspect. In this paper, we propose a method, μ-MAR, able to both coarse and fine register sets of 3D points provided by low-cost depth-sensing cameras, despite it is not restricted to these sensors, into a common coordinate system. The method is able to overcome the noisy data problem by means of using a model-based solution of multiplane registration. Specifically, it iteratively registers 3D markers composed by multiple planes extracted from points of multiple views of the scene. As the markers and the object of interest are static in the scenario, the transformations obtained for the markers are applied to the object in order to reconstruct it. Experiments have been performed using synthetic and real data. The synthetic data allows a qualitative and quantitative evaluation by means of visual inspection and Hausdorff distance respectively. The real data experiments show the performance of the proposal using data acquired by a Primesense Carmine RGB-D sensor. The method has been compared to several state-of-the-art methods. The results show the good performance of the μ-MAR to register objects with high accuracy in presence of noisy data outperforming the existing methods.</dc:description>
<dc:date>2015-09-21T08:59:50Z</dc:date>
<dc:date>2015-09-21T08:59:50Z</dc:date>
<dc:date>2015-12-15</dc:date>
<dc:type>info:eu-repo/semantics/article</dc:type>
<dc:identifier>Expert Systems with Applications. 2015, 42(23): 9353-9365. doi:10.1016/j.eswa.2015.08.011</dc:identifier>
<dc:identifier>0957-4174 (Print)</dc:identifier>
<dc:identifier>1873-6793 (Online)</dc:identifier>
<dc:identifier>http://hdl.handle.net/10045/49529</dc:identifier>
<dc:identifier>10.1016/j.eswa.2015.08.011</dc:identifier>
<dc:identifier>A7758346</dc:identifier>
<dc:relation>http://dx.doi.org/10.1016/j.eswa.2015.08.011</dc:relation>
<dc:rights>info:eu-repo/semantics/openAccess</dc:rights>
<dc:rights>© 2015 Elsevier Ltd.</dc:rights>
<dc:publisher>Elsevier</dc:publisher>
</oai_dc:dc>
</d:Statement>
</d:Descriptor>
<d:Component id="10045_49529_1">
</d:Component>
<d:Component id="10045_49529_2">
</d:Component>
</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" lang="es" mdschema="dc">Informática Industrial y Redes de Computadores</dim:field>
<dim:field element="contributor" mdschema="dc" qualifier="author">Saval-Calvo, Marcelo</dim:field>
<dim:field element="contributor" mdschema="dc" qualifier="author">Azorin-Lopez, Jorge</dim:field>
<dim:field element="contributor" mdschema="dc" qualifier="author">Fuster-Guilló, Andrés</dim:field>
<dim:field element="contributor" mdschema="dc" qualifier="author">Mora, Higinio</dim:field>
<dim:field element="contributor" lang="es" mdschema="dc" qualifier="other">Universidad de Alicante. Departamento de Tecnología Informática y Computación</dim:field>
<dim:field element="date" mdschema="dc" qualifier="accessioned">2015-09-21T08:59:50Z</dim:field>
<dim:field element="date" mdschema="dc" qualifier="available">2015-09-21T08:59:50Z</dim:field>
<dim:field element="date" mdschema="dc" qualifier="issued">2015-12-15</dim:field>
<dim:field element="identifier" lang="es" mdschema="dc" qualifier="citation">Expert Systems with Applications. 2015, 42(23): 9353-9365. doi:10.1016/j.eswa.2015.08.011</dim:field>
<dim:field element="identifier" mdschema="dc" qualifier="issn">0957-4174 (Print)</dim:field>
<dim:field element="identifier" mdschema="dc" qualifier="issn">1873-6793 (Online)</dim:field>
<dim:field element="identifier" mdschema="dc" qualifier="uri">http://hdl.handle.net/10045/49529</dim:field>
<dim:field element="identifier" mdschema="dc" qualifier="doi">10.1016/j.eswa.2015.08.011</dim:field>
<dim:field element="identifier" mdschema="dc" qualifier="cvID">A7758346</dim:field>
<dim:field element="description" lang="es" mdschema="dc" qualifier="abstract">Many applications including object reconstruction, robot guidance, and. scene mapping require the registration of multiple views from a scene to generate a complete geometric and appearance model of it. In real situations, transformations between views are unknown and it is necessary to apply expert inference to estimate them. In the last few years, the emergence of low-cost depth-sensing cameras has strengthened the research on this topic, motivating a plethora of new applications. Although they have enough resolution and accuracy for many applications, some situations may not be solved with general state-of-the-art registration methods due to the signal-to-noise ratio (SNR) and the resolution of the data provided. The problem of working with low SNR data, in general terms, may appear in any 3D system, then it is necessary to propose novel solutions in this aspect. In this paper, we propose a method, μ-MAR, able to both coarse and fine register sets of 3D points provided by low-cost depth-sensing cameras, despite it is not restricted to these sensors, into a common coordinate system. The method is able to overcome the noisy data problem by means of using a model-based solution of multiplane registration. Specifically, it iteratively registers 3D markers composed by multiple planes extracted from points of multiple views of the scene. As the markers and the object of interest are static in the scenario, the transformations obtained for the markers are applied to the object in order to reconstruct it. Experiments have been performed using synthetic and real data. The synthetic data allows a qualitative and quantitative evaluation by means of visual inspection and Hausdorff distance respectively. The real data experiments show the performance of the proposal using data acquired by a Primesense Carmine RGB-D sensor. The method has been compared to several state-of-the-art methods. The results show the good performance of the μ-MAR to register objects with high accuracy in presence of noisy data outperforming the existing methods.</dim:field>
<dim:field element="description" lang="en" mdschema="dc" qualifier="provenance">Submitted by JORGE AZORIN LOPEZ (jazorin@ua.es) on 2015-09-21T08:30:05Z No. of bitstreams: 1 ESWA-Review1.pdf: 3145728 bytes, checksum: b887963ae416737f764f5f2481b73cae (MD5)</dim:field>
<dim:field element="description" lang="en" mdschema="dc" qualifier="provenance">Approved for entry into archive by Javier Gómez Castaño (javier.gomez@ua.es) on 2015-09-21T08:59:21Z (GMT) No. of bitstreams: 1 ESWA-Review1.pdf: 3145728 bytes, checksum: b887963ae416737f764f5f2481b73cae (MD5)</dim:field>
<dim:field element="description" lang="en" mdschema="dc" qualifier="provenance">Made available in DSpace on 2015-09-21T08:59:50Z (GMT). No. of bitstreams: 1 ESWA-Review1.pdf: 3145728 bytes, checksum: b887963ae416737f764f5f2481b73cae (MD5) Previous issue date: 2015-12-15</dim:field>
<dim:field element="description" lang="es" mdschema="dc" qualifier="sponsorship">This work has been supported by grant University of Alicante projects GRE11-01 and grant Valencian Government GV/2013/005.</dim:field>
<dim:field element="language" lang="es" mdschema="dc">eng</dim:field>
<dim:field element="publisher" lang="es" mdschema="dc">Elsevier</dim:field>
<dim:field element="rights" lang="es" mdschema="dc">© 2015 Elsevier Ltd.</dim:field>
<dim:field element="rights" lang="es" mdschema="dc" qualifier="accessRights">info:eu-repo/semantics/openAccess</dim:field>
<dim:field element="subject" lang="es" mdschema="dc">RGB-D sensor</dim:field>
<dim:field element="subject" lang="es" mdschema="dc">Registration</dim:field>
<dim:field element="subject" lang="es" mdschema="dc">Model-based</dim:field>
<dim:field element="subject" lang="es" mdschema="dc">Multiplane</dim:field>
<dim:field element="subject" lang="es" mdschema="dc">Object reconstruction</dim:field>
<dim:field element="subject" lang="es" mdschema="dc" qualifier="other">Arquitectura y Tecnología de Computadores</dim:field>
<dim:field element="title" lang="es" mdschema="dc">μ-MAR: Multiplane 3D Marker based Registration for depth-sensing cameras</dim:field>
<dim:field element="type" lang="es" mdschema="dc">info:eu-repo/semantics/article</dim:field>
<dim:field element="peerreviewed" lang="es" mdschema="dc">si</dim:field>
<dim:field element="relation" lang="es" mdschema="dc" qualifier="publisherversion">http://dx.doi.org/10.1016/j.eswa.2015.08.011</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>μ-MAR: Multiplane 3D Marker based Registration for depth-sensing cameras</title>
<creator>Saval-Calvo, Marcelo</creator>
<creator>Azorin-Lopez, Jorge</creator>
<creator>Fuster-Guilló, Andrés</creator>
<creator>Mora, Higinio</creator>
<contributor>Universidad de Alicante. Departamento de Tecnología Informática y Computación</contributor>
<subject>RGB-D sensor</subject>
<subject>Registration</subject>
<subject>Model-based</subject>
<subject>Multiplane</subject>
<subject>Object reconstruction</subject>
<description>Many applications including object reconstruction, robot guidance, and. scene mapping require the registration of multiple views from a scene to generate a complete geometric and appearance model of it. In real situations, transformations between views are unknown and it is necessary to apply expert inference to estimate them. In the last few years, the emergence of low-cost depth-sensing cameras has strengthened the research on this topic, motivating a plethora of new applications. Although they have enough resolution and accuracy for many applications, some situations may not be solved with general state-of-the-art registration methods due to the signal-to-noise ratio (SNR) and the resolution of the data provided. The problem of working with low SNR data, in general terms, may appear in any 3D system, then it is necessary to propose novel solutions in this aspect. In this paper, we propose a method, μ-MAR, able to both coarse and fine register sets of 3D points provided by low-cost depth-sensing cameras, despite it is not restricted to these sensors, into a common coordinate system. The method is able to overcome the noisy data problem by means of using a model-based solution of multiplane registration. Specifically, it iteratively registers 3D markers composed by multiple planes extracted from points of multiple views of the scene. As the markers and the object of interest are static in the scenario, the transformations obtained for the markers are applied to the object in order to reconstruct it. Experiments have been performed using synthetic and real data. The synthetic data allows a qualitative and quantitative evaluation by means of visual inspection and Hausdorff distance respectively. The real data experiments show the performance of the proposal using data acquired by a Primesense Carmine RGB-D sensor. The method has been compared to several state-of-the-art methods. The results show the good performance of the μ-MAR to register objects with high accuracy in presence of noisy data outperforming the existing methods.</description>
<date>2015-09-21</date>
<date>2015-09-21</date>
<date>2015-12-15</date>
<type>info:eu-repo/semantics/article</type>
<identifier>Expert Systems with Applications. 2015, 42(23): 9353-9365. doi:10.1016/j.eswa.2015.08.011</identifier>
<identifier>0957-4174 (Print)</identifier>
<identifier>1873-6793 (Online)</identifier>
<identifier>http://hdl.handle.net/10045/49529</identifier>
<identifier>10.1016/j.eswa.2015.08.011</identifier>
<identifier>A7758346</identifier>
<relation>http://dx.doi.org/10.1016/j.eswa.2015.08.011</relation>
<rights>info:eu-repo/semantics/openAccess</rights>
<rights>© 2015 Elsevier Ltd.</rights>
<publisher>Elsevier</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">Saval-Calvo, Marcelo</subfield>
<subfield code="e">author</subfield>
</datafield>
<datafield ind1=" " ind2=" " tag="720">
<subfield code="a">Azorin-Lopez, Jorge</subfield>
<subfield code="e">author</subfield>
</datafield>
<datafield ind1=" " ind2=" " tag="720">
<subfield code="a">Fuster-Guilló, Andrés</subfield>
<subfield code="e">author</subfield>
</datafield>
<datafield ind1=" " ind2=" " tag="720">
<subfield code="a">Mora, Higinio</subfield>
<subfield code="e">author</subfield>
</datafield>
<datafield ind1=" " ind2=" " tag="260">
<subfield code="c">2015-12-15</subfield>
</datafield>
<datafield ind1=" " ind2=" " tag="520">
<subfield code="a">Many applications including object reconstruction, robot guidance, and. scene mapping require the registration of multiple views from a scene to generate a complete geometric and appearance model of it. In real situations, transformations between views are unknown and it is necessary to apply expert inference to estimate them. In the last few years, the emergence of low-cost depth-sensing cameras has strengthened the research on this topic, motivating a plethora of new applications. Although they have enough resolution and accuracy for many applications, some situations may not be solved with general state-of-the-art registration methods due to the signal-to-noise ratio (SNR) and the resolution of the data provided. The problem of working with low SNR data, in general terms, may appear in any 3D system, then it is necessary to propose novel solutions in this aspect. In this paper, we propose a method, μ-MAR, able to both coarse and fine register sets of 3D points provided by low-cost depth-sensing cameras, despite it is not restricted to these sensors, into a common coordinate system. The method is able to overcome the noisy data problem by means of using a model-based solution of multiplane registration. Specifically, it iteratively registers 3D markers composed by multiple planes extracted from points of multiple views of the scene. As the markers and the object of interest are static in the scenario, the transformations obtained for the markers are applied to the object in order to reconstruct it. Experiments have been performed using synthetic and real data. The synthetic data allows a qualitative and quantitative evaluation by means of visual inspection and Hausdorff distance respectively. The real data experiments show the performance of the proposal using data acquired by a Primesense Carmine RGB-D sensor. The method has been compared to several state-of-the-art methods. The results show the good performance of the μ-MAR to register objects with high accuracy in presence of noisy data outperforming the existing methods.</subfield>
</datafield>
<datafield ind1="8" ind2=" " tag="024">
<subfield code="a">Expert Systems with Applications. 2015, 42(23): 9353-9365. doi:10.1016/j.eswa.2015.08.011</subfield>
</datafield>
<datafield ind1="8" ind2=" " tag="024">
<subfield code="a">0957-4174 (Print)</subfield>
</datafield>
<datafield ind1="8" ind2=" " tag="024">
<subfield code="a">1873-6793 (Online)</subfield>
</datafield>
<datafield ind1="8" ind2=" " tag="024">
<subfield code="a">http://hdl.handle.net/10045/49529</subfield>
</datafield>
<datafield ind1="8" ind2=" " tag="024">
<subfield code="a">10.1016/j.eswa.2015.08.011</subfield>
</datafield>
<datafield ind1="8" ind2=" " tag="024">
<subfield code="a">A7758346</subfield>
</datafield>
<datafield ind1=" " ind2=" " tag="653">
<subfield code="a">RGB-D sensor</subfield>
</datafield>
<datafield ind1=" " ind2=" " tag="653">
<subfield code="a">Registration</subfield>
</datafield>
<datafield ind1=" " ind2=" " tag="653">
<subfield code="a">Model-based</subfield>
</datafield>
<datafield ind1=" " ind2=" " tag="653">
<subfield code="a">Multiplane</subfield>
</datafield>
<datafield ind1=" " ind2=" " tag="653">
<subfield code="a">Object reconstruction</subfield>
</datafield>
<datafield ind1="0" ind2="0" tag="245">
<subfield code="a">μ-MAR: Multiplane 3D Marker based Registration for depth-sensing cameras</subfield>
</datafield>
</record>
<?xml version="1.0" encoding="UTF-8" ?>
<mets ID=" DSpace_ITEM_10045-49529" OBJID=" hdl:10045/49529" 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="2022-10-31T20:23:35Z">
<agent ROLE="CUSTODIAN" TYPE="ORGANIZATION">
<name>RUA</name>
</agent>
</metsHdr>
<dmdSec ID="DMD_10045_49529">
<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>Saval-Calvo, Marcelo</mods:namePart>
</mods:name>
<mods:name>
<mods:role>
<mods:roleTerm type="text">author</mods:roleTerm>
</mods:role>
<mods:namePart>Azorin-Lopez, Jorge</mods:namePart>
</mods:name>
<mods:name>
<mods:role>
<mods:roleTerm type="text">author</mods:roleTerm>
</mods:role>
<mods:namePart>Fuster-Guilló, Andrés</mods:namePart>
</mods:name>
<mods:name>
<mods:role>
<mods:roleTerm type="text">author</mods:roleTerm>
</mods:role>
<mods:namePart>Mora, Higinio</mods:namePart>
</mods:name>
<mods:name>
<mods:role>
<mods:roleTerm type="text">other</mods:roleTerm>
</mods:role>
<mods:namePart>Universidad de Alicante. Departamento de Tecnología Informática y Computación</mods:namePart>
</mods:name>
<mods:extension>
<mods:dateAccessioned encoding="iso8601">2015-09-21T08:59:50Z</mods:dateAccessioned>
</mods:extension>
<mods:extension>
<mods:dateAvailable encoding="iso8601">2015-09-21T08:59:50Z</mods:dateAvailable>
</mods:extension>
<mods:originInfo>
<mods:dateIssued encoding="iso8601">2015-12-15</mods:dateIssued>
</mods:originInfo>
<mods:identifier type="citation">Expert Systems with Applications. 2015, 42(23): 9353-9365. doi:10.1016/j.eswa.2015.08.011</mods:identifier>
<mods:identifier type="issn">0957-4174 (Print)</mods:identifier>
<mods:identifier type="uri">http://hdl.handle.net/10045/49529</mods:identifier>
<mods:identifier type="doi">10.1016/j.eswa.2015.08.011</mods:identifier>
<mods:identifier type="cvID">A7758346</mods:identifier>
<mods:abstract>Many applications including object reconstruction, robot guidance, and. scene mapping require the registration of multiple views from a scene to generate a complete geometric and appearance model of it. In real situations, transformations between views are unknown and it is necessary to apply expert inference to estimate them. In the last few years, the emergence of low-cost depth-sensing cameras has strengthened the research on this topic, motivating a plethora of new applications. Although they have enough resolution and accuracy for many applications, some situations may not be solved with general state-of-the-art registration methods due to the signal-to-noise ratio (SNR) and the resolution of the data provided. The problem of working with low SNR data, in general terms, may appear in any 3D system, then it is necessary to propose novel solutions in this aspect. In this paper, we propose a method, μ-MAR, able to both coarse and fine register sets of 3D points provided by low-cost depth-sensing cameras, despite it is not restricted to these sensors, into a common coordinate system. The method is able to overcome the noisy data problem by means of using a model-based solution of multiplane registration. Specifically, it iteratively registers 3D markers composed by multiple planes extracted from points of multiple views of the scene. As the markers and the object of interest are static in the scenario, the transformations obtained for the markers are applied to the object in order to reconstruct it. Experiments have been performed using synthetic and real data. The synthetic data allows a qualitative and quantitative evaluation by means of visual inspection and Hausdorff distance respectively. The real data experiments show the performance of the proposal using data acquired by a Primesense Carmine RGB-D sensor. The method has been compared to several state-of-the-art methods. The results show the good performance of the μ-MAR to register objects with high accuracy in presence of noisy data outperforming the existing methods.</mods:abstract>
<mods:language>
</mods:language>
<mods:accessCondition type="useAndReproduction">© 2015 Elsevier Ltd.</mods:accessCondition>
<mods:subject>
<mods:topic>RGB-D sensor</mods:topic>
</mods:subject>
<mods:subject>
<mods:topic>Registration</mods:topic>
</mods:subject>
<mods:subject>
<mods:topic>Model-based</mods:topic>
</mods:subject>
<mods:subject>
<mods:topic>Multiplane</mods:topic>
</mods:subject>
<mods:subject>
<mods:topic>Object reconstruction</mods:topic>
</mods:subject>
<mods:titleInfo>
<mods:title>μ-MAR: Multiplane 3D Marker based Registration for depth-sensing cameras</mods:title>
</mods:titleInfo>
<mods:genre>info:eu-repo/semantics/article</mods:genre>
</mods:mods>
</xmlData>
</mdWrap>
</dmdSec>
<amdSec ID="FO_10045_49529_1">
<techMD ID="TECH_O_10045_49529_1">
<mdWrap MDTYPE="PREMIS">
<xmlData schemaLocation="http://www.loc.gov/standards/premis http://www.loc.gov/standards/premis/PREMIS-v1-0.xsd">
<premis:premis>
<premis:object>
<premis:objectIdentifier>
<premis:objectIdentifierType>URL</premis:objectIdentifierType>
<premis:objectIdentifierValue>http://rua.ua.es/dspace/bitstream/10045/49529/1/2015_Saval_etal_ESWA_final.pdf</premis:objectIdentifierValue>
</premis:objectIdentifier>
<premis:objectCategory>File</premis:objectCategory>
<premis:objectCharacteristics>
<premis:fixity>
<premis:messageDigestAlgorithm>MD5</premis:messageDigestAlgorithm>
<premis:messageDigest>b3e80db442c26c3d6fe7c2342948cb95</premis:messageDigest>
</premis:fixity>
<premis:size>5646252</premis:size>
<premis:format>
<premis:formatDesignation>
<premis:formatName>application/pdf</premis:formatName>
</premis:formatDesignation>
</premis:format>
</premis:objectCharacteristics>
<premis:originalName>2015_Saval_etal_ESWA_final.pdf</premis:originalName>
</premis:object>
</premis:premis>
</xmlData>
</mdWrap>
</techMD>
</amdSec>
<amdSec ID="FO_10045_49529_2">
<techMD ID="TECH_O_10045_49529_2">
<mdWrap MDTYPE="PREMIS">
<xmlData schemaLocation="http://www.loc.gov/standards/premis http://www.loc.gov/standards/premis/PREMIS-v1-0.xsd">
<premis:premis>
<premis:object>
<premis:objectIdentifier>
<premis:objectIdentifierType>URL</premis:objectIdentifierType>
<premis:objectIdentifierValue>http://rua.ua.es/dspace/bitstream/10045/49529/2/2015_Saval_etal_ESWA_preprint.pdf</premis:objectIdentifierValue>
</premis:objectIdentifier>
<premis:objectCategory>File</premis:objectCategory>
<premis:objectCharacteristics>
<premis:fixity>
<premis:messageDigestAlgorithm>MD5</premis:messageDigestAlgorithm>
<premis:messageDigest>01ba647e300977fd1d2011e50011a81c</premis:messageDigest>
</premis:fixity>
<premis:size>1625114</premis:size>
<premis:format>
<premis:formatDesignation>
<premis:formatName>application/pdf</premis:formatName>
</premis:formatDesignation>
</premis:format>
</premis:objectCharacteristics>
<premis:originalName>2015_Saval_etal_ESWA_preprint.pdf</premis:originalName>
</premis:object>
</premis:premis>
</xmlData>
</mdWrap>
</techMD>
</amdSec>
<amdSec ID="FT_10045_49529_3">
<techMD ID="TECH_T_10045_49529_3">
<mdWrap MDTYPE="PREMIS">
<xmlData schemaLocation="http://www.loc.gov/standards/premis http://www.loc.gov/standards/premis/PREMIS-v1-0.xsd">
<premis:premis>
<premis:object>
<premis:objectIdentifier>
<premis:objectIdentifierType>URL</premis:objectIdentifierType>
<premis:objectIdentifierValue>http://rua.ua.es/dspace/bitstream/10045/49529/3/2015_Saval_etal_ESWA_final.pdf.txt</premis:objectIdentifierValue>
</premis:objectIdentifier>
<premis:objectCategory>File</premis:objectCategory>
<premis:objectCharacteristics>
<premis:fixity>
<premis:messageDigestAlgorithm>MD5</premis:messageDigestAlgorithm>
<premis:messageDigest>9fbc6788c1d31c99e9864ebde84360cc</premis:messageDigest>
</premis:fixity>
<premis:size>67309</premis:size>
<premis:format>
<premis:formatDesignation>
<premis:formatName>text/plain</premis:formatName>
</premis:formatDesignation>
</premis:format>
</premis:objectCharacteristics>
<premis:originalName>2015_Saval_etal_ESWA_final.pdf.txt</premis:originalName>
</premis:object>
</premis:premis>
</xmlData>
</mdWrap>
</techMD>
</amdSec>
<amdSec ID="FT_10045_49529_5">
<techMD ID="TECH_T_10045_49529_5">
<mdWrap MDTYPE="PREMIS">
<xmlData schemaLocation="http://www.loc.gov/standards/premis http://www.loc.gov/standards/premis/PREMIS-v1-0.xsd">
<premis:premis>
<premis:object>
<premis:objectIdentifier>
<premis:objectIdentifierType>URL</premis:objectIdentifierType>
<premis:objectIdentifierValue>http://rua.ua.es/dspace/bitstream/10045/49529/5/2015_Saval_etal_ESWA_preprint.pdf.txt</premis:objectIdentifierValue>
</premis:objectIdentifier>
<premis:objectCategory>File</premis:objectCategory>
<premis:objectCharacteristics>
<premis:fixity>
<premis:messageDigestAlgorithm>MD5</premis:messageDigestAlgorithm>
<premis:messageDigest>2ec89411d9f14fa37e82181bbcabf9ea</premis:messageDigest>
</premis:fixity>
<premis:size>65707</premis:size>
<premis:format>
<premis:formatDesignation>
<premis:formatName>text/plain</premis:formatName>
</premis:formatDesignation>
</premis:format>
</premis:objectCharacteristics>
<premis:originalName>2015_Saval_etal_ESWA_preprint.pdf.txt</premis:originalName>
</premis:object>
</premis:premis>
</xmlData>
</mdWrap>
</techMD>
</amdSec>
<fileSec>
<fileGrp USE="ORIGINAL">
<file ADMID="FO_10045_49529_1" CHECKSUM="b3e80db442c26c3d6fe7c2342948cb95" CHECKSUMTYPE="MD5" GROUPID="GROUP_BITSTREAM_10045_49529_1" ID="BITSTREAM_ORIGINAL_10045_49529_1" MIMETYPE="application/pdf" SEQ="1" SIZE="5646252">
</file>
<file ADMID="FO_10045_49529_2" CHECKSUM="01ba647e300977fd1d2011e50011a81c" CHECKSUMTYPE="MD5" GROUPID="GROUP_BITSTREAM_10045_49529_2" ID="BITSTREAM_ORIGINAL_10045_49529_2" MIMETYPE="application/pdf" SEQ="2" SIZE="1625114">
</file>
</fileGrp>
<fileGrp USE="TEXT">
<file ADMID="FT_10045_49529_3" CHECKSUM="9fbc6788c1d31c99e9864ebde84360cc" CHECKSUMTYPE="MD5" GROUPID="GROUP_BITSTREAM_10045_49529_3" ID="BITSTREAM_TEXT_10045_49529_3" MIMETYPE="text/plain" SEQ="3" SIZE="67309">
</file>
<file ADMID="FT_10045_49529_5" CHECKSUM="2ec89411d9f14fa37e82181bbcabf9ea" CHECKSUMTYPE="MD5" GROUPID="GROUP_BITSTREAM_10045_49529_5" ID="BITSTREAM_TEXT_10045_49529_5" MIMETYPE="text/plain" SEQ="5" SIZE="65707">
</file>
</fileGrp>
</fileSec>
<structMap LABEL="DSpace Object" TYPE="LOGICAL">
<div ADMID="DMD_10045_49529" TYPE="DSpace Object Contents">
<div TYPE="DSpace BITSTREAM">
</div>
<div TYPE="DSpace BITSTREAM">
</div>
</div>
</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>Saval-Calvo, Marcelo</mods:namePart>
</mods:name>
<mods:name>
<mods:namePart>Azorin-Lopez, Jorge</mods:namePart>
</mods:name>
<mods:name>
<mods:namePart>Fuster-Guilló, Andrés</mods:namePart>
</mods:name>
<mods:name>
<mods:namePart>Mora, Higinio</mods:namePart>
</mods:name>
<mods:extension>
<mods:dateAvailable encoding="iso8601">2015-09-21T08:59:50Z</mods:dateAvailable>
</mods:extension>
<mods:extension>
<mods:dateAccessioned encoding="iso8601">2015-09-21T08:59:50Z</mods:dateAccessioned>
</mods:extension>
<mods:originInfo>
<mods:dateIssued encoding="iso8601">2015-12-15</mods:dateIssued>
</mods:originInfo>
<mods:identifier type="citation">Expert Systems with Applications. 2015, 42(23): 9353-9365. doi:10.1016/j.eswa.2015.08.011</mods:identifier>
<mods:identifier type="issn">0957-4174 (Print)</mods:identifier>
<mods:identifier type="issn">1873-6793 (Online)</mods:identifier>
<mods:identifier type="uri">http://hdl.handle.net/10045/49529</mods:identifier>
<mods:identifier type="doi">10.1016/j.eswa.2015.08.011</mods:identifier>
<mods:identifier type="cvID">A7758346</mods:identifier>
<mods:abstract>Many applications including object reconstruction, robot guidance, and. scene mapping require the registration of multiple views from a scene to generate a complete geometric and appearance model of it. In real situations, transformations between views are unknown and it is necessary to apply expert inference to estimate them. In the last few years, the emergence of low-cost depth-sensing cameras has strengthened the research on this topic, motivating a plethora of new applications. Although they have enough resolution and accuracy for many applications, some situations may not be solved with general state-of-the-art registration methods due to the signal-to-noise ratio (SNR) and the resolution of the data provided. The problem of working with low SNR data, in general terms, may appear in any 3D system, then it is necessary to propose novel solutions in this aspect. In this paper, we propose a method, μ-MAR, able to both coarse and fine register sets of 3D points provided by low-cost depth-sensing cameras, despite it is not restricted to these sensors, into a common coordinate system. The method is able to overcome the noisy data problem by means of using a model-based solution of multiplane registration. Specifically, it iteratively registers 3D markers composed by multiple planes extracted from points of multiple views of the scene. As the markers and the object of interest are static in the scenario, the transformations obtained for the markers are applied to the object in order to reconstruct it. Experiments have been performed using synthetic and real data. The synthetic data allows a qualitative and quantitative evaluation by means of visual inspection and Hausdorff distance respectively. The real data experiments show the performance of the proposal using data acquired by a Primesense Carmine RGB-D sensor. The method has been compared to several state-of-the-art methods. The results show the good performance of the μ-MAR to register objects with high accuracy in presence of noisy data outperforming the existing methods.</mods:abstract>
<mods:accessCondition type="useAndReproduction">info:eu-repo/semantics/openAccess</mods:accessCondition>
<mods:accessCondition type="useAndReproduction">© 2015 Elsevier Ltd.</mods:accessCondition>
<mods:subject>
<mods:topic>RGB-D sensor</mods:topic>
</mods:subject>
<mods:subject>
<mods:topic>Registration</mods:topic>
</mods:subject>
<mods:subject>
<mods:topic>Model-based</mods:topic>
</mods:subject>
<mods:subject>
<mods:topic>Multiplane</mods:topic>
</mods:subject>
<mods:subject>
<mods:topic>Object reconstruction</mods:topic>
</mods:subject>
<mods:titleInfo>
<mods:title>μ-MAR: Multiplane 3D Marker based Registration for depth-sensing cameras</mods:title>
</mods:titleInfo>
<mods:genre>info:eu-repo/semantics/article</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/10045/49529/ore.xml</atom:id>
<atom:published>2015-09-21T08:59:50Z</atom:published>
<atom:updated>2015-09-21T08:59:50Z</atom:updated>
<atom:source>
<atom:generator>RUA</atom:generator>
</atom:source>
<atom:title>μ-MAR: Multiplane 3D Marker based Registration for depth-sensing cameras</atom:title>
<atom:author>
<atom:name>Saval-Calvo, Marcelo</atom:name>
</atom:author>
<atom:author>
<atom:name>Azorin-Lopez, Jorge</atom:name>
</atom:author>
<atom:author>
<atom:name>Fuster-Guilló, Andrés</atom:name>
</atom:author>
<atom:author>
<atom:name>Mora, Higinio</atom:name>
</atom:author>
<oreatom:triples>
<rdf:Description about="http://hdl.handle.net/10045/49529/ore.xml#atom">
<dcterms:modified>2015-09-21T08:59:50Z</dcterms:modified>
</rdf:Description>
<rdf:Description about="http://rua.ua.es/dspace/bitstream/10045/49529/3/2015_Saval_etal_ESWA_final.pdf.txt">
<dcterms:description>TEXT</dcterms:description>
</rdf:Description>
<rdf:Description about="http://rua.ua.es/dspace/bitstream/10045/49529/5/2015_Saval_etal_ESWA_preprint.pdf.txt">
<dcterms:description>TEXT</dcterms:description>
</rdf:Description>
<rdf:Description about="http://rua.ua.es/dspace/bitstream/10045/49529/4/2015_Saval_etal_ESWA_final.pdf.jpg">
<dcterms:description>THUMBNAIL</dcterms:description>
</rdf:Description>
<rdf:Description about="http://rua.ua.es/dspace/bitstream/10045/49529/6/2015_Saval_etal_ESWA_preprint.pdf.jpg">
<dcterms:description>THUMBNAIL</dcterms:description>
</rdf:Description>
<rdf:Description about="http://rua.ua.es/dspace/bitstream/10045/49529/1/2015_Saval_etal_ESWA_final.pdf">
<dcterms:description>ORIGINAL</dcterms:description>
</rdf:Description>
<rdf:Description about="http://rua.ua.es/dspace/bitstream/10045/49529/2/2015_Saval_etal_ESWA_preprint.pdf">
<dcterms:description>ORIGINAL</dcterms:description>
</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>μ-MAR: Multiplane 3D Marker based Registration for depth-sensing cameras</dc:title>
<dc:creator>Saval-Calvo, Marcelo</dc:creator>
<dc:creator>Azorin-Lopez, Jorge</dc:creator>
<dc:creator>Fuster-Guilló, Andrés</dc:creator>
<dc:creator>Mora, Higinio</dc:creator>
<dc:contributor>Universidad de Alicante. Departamento de Tecnología Informática y Computación</dc:contributor>
<dc:subject>RGB-D sensor</dc:subject>
<dc:subject>Registration</dc:subject>
<dc:subject>Model-based</dc:subject>
<dc:subject>Multiplane</dc:subject>
<dc:subject>Object reconstruction</dc:subject>
<dcterms:abstract>Many applications including object reconstruction, robot guidance, and. scene mapping require the registration of multiple views from a scene to generate a complete geometric and appearance model of it. In real situations, transformations between views are unknown and it is necessary to apply expert inference to estimate them. In the last few years, the emergence of low-cost depth-sensing cameras has strengthened the research on this topic, motivating a plethora of new applications. Although they have enough resolution and accuracy for many applications, some situations may not be solved with general state-of-the-art registration methods due to the signal-to-noise ratio (SNR) and the resolution of the data provided. The problem of working with low SNR data, in general terms, may appear in any 3D system, then it is necessary to propose novel solutions in this aspect. In this paper, we propose a method, μ-MAR, able to both coarse and fine register sets of 3D points provided by low-cost depth-sensing cameras, despite it is not restricted to these sensors, into a common coordinate system. The method is able to overcome the noisy data problem by means of using a model-based solution of multiplane registration. Specifically, it iteratively registers 3D markers composed by multiple planes extracted from points of multiple views of the scene. As the markers and the object of interest are static in the scenario, the transformations obtained for the markers are applied to the object in order to reconstruct it. Experiments have been performed using synthetic and real data. The synthetic data allows a qualitative and quantitative evaluation by means of visual inspection and Hausdorff distance respectively. The real data experiments show the performance of the proposal using data acquired by a Primesense Carmine RGB-D sensor. The method has been compared to several state-of-the-art methods. The results show the good performance of the μ-MAR to register objects with high accuracy in presence of noisy data outperforming the existing methods.</dcterms:abstract>
<dcterms:dateAccepted>2015-09-21T08:59:50Z</dcterms:dateAccepted>
<dcterms:available>2015-09-21T08:59:50Z</dcterms:available>
<dcterms:created>2015-09-21T08:59:50Z</dcterms:created>
<dcterms:issued>2015-12-15</dcterms:issued>
<dc:type>info:eu-repo/semantics/article</dc:type>
<dc:identifier>Expert Systems with Applications. 2015, 42(23): 9353-9365. doi:10.1016/j.eswa.2015.08.011</dc:identifier>
<dc:identifier>0957-4174 (Print)</dc:identifier>
<dc:identifier>1873-6793 (Online)</dc:identifier>
<dc:identifier>http://hdl.handle.net/10045/49529</dc:identifier>
<dc:identifier>10.1016/j.eswa.2015.08.011</dc:identifier>
<dc:identifier>A7758346</dc:identifier>
<dc:relation>http://dx.doi.org/10.1016/j.eswa.2015.08.011</dc:relation>
<dc:rights>info:eu-repo/semantics/openAccess</dc:rights>
<dc:rights>© 2015 Elsevier Ltd.</dc:rights>
<dc:publisher>Elsevier</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:rua.ua.es:10045/49529">
<dc:title>μ-MAR: Multiplane 3D Marker based Registration for depth-sensing cameras</dc:title>
<dc:creator>Saval-Calvo, Marcelo</dc:creator>
<dc:creator>Azorin-Lopez, Jorge</dc:creator>
<dc:creator>Fuster-Guilló, Andrés</dc:creator>
<dc:creator>Mora, Higinio</dc:creator>
<dc:contributor>Universidad de Alicante. Departamento de Tecnología Informática y Computación</dc:contributor>
<dc:subject>RGB-D sensor</dc:subject>
<dc:subject>Registration</dc:subject>
<dc:subject>Model-based</dc:subject>
<dc:subject>Multiplane</dc:subject>
<dc:subject>Object reconstruction</dc:subject>
<dc:description>Many applications including object reconstruction, robot guidance, and. scene mapping require the registration of multiple views from a scene to generate a complete geometric and appearance model of it. In real situations, transformations between views are unknown and it is necessary to apply expert inference to estimate them. In the last few years, the emergence of low-cost depth-sensing cameras has strengthened the research on this topic, motivating a plethora of new applications. Although they have enough resolution and accuracy for many applications, some situations may not be solved with general state-of-the-art registration methods due to the signal-to-noise ratio (SNR) and the resolution of the data provided. The problem of working with low SNR data, in general terms, may appear in any 3D system, then it is necessary to propose novel solutions in this aspect. In this paper, we propose a method, μ-MAR, able to both coarse and fine register sets of 3D points provided by low-cost depth-sensing cameras, despite it is not restricted to these sensors, into a common coordinate system. The method is able to overcome the noisy data problem by means of using a model-based solution of multiplane registration. Specifically, it iteratively registers 3D markers composed by multiple planes extracted from points of multiple views of the scene. As the markers and the object of interest are static in the scenario, the transformations obtained for the markers are applied to the object in order to reconstruct it. Experiments have been performed using synthetic and real data. The synthetic data allows a qualitative and quantitative evaluation by means of visual inspection and Hausdorff distance respectively. The real data experiments show the performance of the proposal using data acquired by a Primesense Carmine RGB-D sensor. The method has been compared to several state-of-the-art methods. The results show the good performance of the μ-MAR to register objects with high accuracy in presence of noisy data outperforming the existing methods.</dc:description>
<dc:date>2015-09-21T08:59:50Z</dc:date>
<dc:date>2015-09-21T08:59:50Z</dc:date>
<dc:date>2015-12-15</dc:date>
<dc:type>info:eu-repo/semantics/article</dc:type>
<dc:identifier>Expert Systems with Applications. 2015, 42(23): 9353-9365. doi:10.1016/j.eswa.2015.08.011</dc:identifier>
<dc:identifier>0957-4174 (Print)</dc:identifier>
<dc:identifier>1873-6793 (Online)</dc:identifier>
<dc:identifier>http://hdl.handle.net/10045/49529</dc:identifier>
<dc:identifier>10.1016/j.eswa.2015.08.011</dc:identifier>
<dc:identifier>A7758346</dc:identifier>
<dc:relation>http://dx.doi.org/10.1016/j.eswa.2015.08.011</dc:relation>
<dc:rights>info:eu-repo/semantics/openAccess</dc:rights>
<dc:rights>© 2015 Elsevier Ltd.</dc:rights>
<dc:publisher>Elsevier</dc:publisher>
<dc:peerreviewed>si</dc:peerreviewed>
</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="es">
<field name="value">Informática Industrial y Redes de Computadores</field>
</element>
<element name="author">
<element name="none">
<field name="value">Saval-Calvo, Marcelo</field>
<field name="value">Azorin-Lopez, Jorge</field>
<field name="value">Fuster-Guilló, Andrés</field>
<field name="value">Mora, Higinio</field>
</element>
</element>
<element name="other">
<element name="es">
<field name="value">Universidad de Alicante. Departamento de Tecnología Informática y Computación</field>
</element>
</element>
</element>
<element name="date">
<element name="accessioned">
<element name="none">
<field name="value">2015-09-21T08:59:50Z</field>
</element>
</element>
<element name="available">
<element name="none">
<field name="value">2015-09-21T08:59:50Z</field>
</element>
</element>
<element name="issued">
<element name="none">
<field name="value">2015-12-15</field>
</element>
</element>
</element>
<element name="identifier">
<element name="citation">
<element name="es">
<field name="value">Expert Systems with Applications. 2015, 42(23): 9353-9365. doi:10.1016/j.eswa.2015.08.011</field>
</element>
</element>
<element name="issn">
<element name="none">
<field name="value">0957-4174 (Print)</field>
<field name="value">1873-6793 (Online)</field>
</element>
</element>
<element name="uri">
<element name="none">
<field name="value">http://hdl.handle.net/10045/49529</field>
</element>
</element>
<element name="doi">
<element name="none">
<field name="value">10.1016/j.eswa.2015.08.011</field>
</element>
</element>
<element name="cvID">
<element name="none">
<field name="value">A7758346</field>
</element>
</element>
</element>
<element name="description">
<element name="abstract">
<element name="es">
<field name="value">Many applications including object reconstruction, robot guidance, and. scene mapping require the registration of multiple views from a scene to generate a complete geometric and appearance model of it. In real situations, transformations between views are unknown and it is necessary to apply expert inference to estimate them. In the last few years, the emergence of low-cost depth-sensing cameras has strengthened the research on this topic, motivating a plethora of new applications. Although they have enough resolution and accuracy for many applications, some situations may not be solved with general state-of-the-art registration methods due to the signal-to-noise ratio (SNR) and the resolution of the data provided. The problem of working with low SNR data, in general terms, may appear in any 3D system, then it is necessary to propose novel solutions in this aspect. In this paper, we propose a method, μ-MAR, able to both coarse and fine register sets of 3D points provided by low-cost depth-sensing cameras, despite it is not restricted to these sensors, into a common coordinate system. The method is able to overcome the noisy data problem by means of using a model-based solution of multiplane registration. Specifically, it iteratively registers 3D markers composed by multiple planes extracted from points of multiple views of the scene. As the markers and the object of interest are static in the scenario, the transformations obtained for the markers are applied to the object in order to reconstruct it. Experiments have been performed using synthetic and real data. The synthetic data allows a qualitative and quantitative evaluation by means of visual inspection and Hausdorff distance respectively. The real data experiments show the performance of the proposal using data acquired by a Primesense Carmine RGB-D sensor. The method has been compared to several state-of-the-art methods. The results show the good performance of the μ-MAR to register objects with high accuracy in presence of noisy data outperforming the existing methods.</field>
</element>
</element>
<element name="provenance">
<element name="en">
<field name="value">Submitted by JORGE AZORIN LOPEZ (jazorin@ua.es) on 2015-09-21T08:30:05Z No. of bitstreams: 1 ESWA-Review1.pdf: 3145728 bytes, checksum: b887963ae416737f764f5f2481b73cae (MD5)</field>
<field name="value">Approved for entry into archive by Javier Gómez Castaño (javier.gomez@ua.es) on 2015-09-21T08:59:21Z (GMT) No. of bitstreams: 1 ESWA-Review1.pdf: 3145728 bytes, checksum: b887963ae416737f764f5f2481b73cae (MD5)</field>
<field name="value">Made available in DSpace on 2015-09-21T08:59:50Z (GMT). No. of bitstreams: 1 ESWA-Review1.pdf: 3145728 bytes, checksum: b887963ae416737f764f5f2481b73cae (MD5) Previous issue date: 2015-12-15</field>
</element>
</element>
<element name="sponsorship">
<element name="es">
<field name="value">This work has been supported by grant University of Alicante projects GRE11-01 and grant Valencian Government GV/2013/005.</field>
</element>
</element>
</element>
<element name="language">
<element name="es">
<field name="value">eng</field>
</element>
</element>
<element name="publisher">
<element name="es">
<field name="value">Elsevier</field>
</element>
</element>
<element name="rights">
<element name="es">
<field name="value">© 2015 Elsevier Ltd.</field>
</element>
<element name="accessRights">
<element name="es">
<field name="value">info:eu-repo/semantics/openAccess</field>
</element>
</element>
</element>
<element name="subject">
<element name="es">
<field name="value">RGB-D sensor</field>
<field name="value">Registration</field>
<field name="value">Model-based</field>
<field name="value">Multiplane</field>
<field name="value">Object reconstruction</field>
</element>
<element name="other">
<element name="es">
<field name="value">Arquitectura y Tecnología de Computadores</field>
</element>
</element>
</element>
<element name="title">
<element name="es">
<field name="value">μ-MAR: Multiplane 3D Marker based Registration for depth-sensing cameras</field>
</element>
</element>
<element name="type">
<element name="es">
<field name="value">info:eu-repo/semantics/article</field>
</element>
</element>
<element name="peerreviewed">
<element name="es">
<field name="value">si</field>
</element>
</element>
<element name="relation">
<element name="publisherversion">
<element name="es">
<field name="value">http://dx.doi.org/10.1016/j.eswa.2015.08.011</field>
</element>
</element>
</element>
</element>
<element name="bundles">
<element name="bundle">
<field name="name">TEXT</field>
<element name="bitstreams">
<element name="bitstream">
<field name="name">2015_Saval_etal_ESWA_final.pdf.txt</field>
<field name="originalName">2015_Saval_etal_ESWA_final.pdf.txt</field>
<field name="description">Extracted text</field>
<field name="format">text/plain</field>
<field name="size">67309</field>
<field name="url">http://rua.ua.es/dspace/bitstream/10045/49529/3/2015_Saval_etal_ESWA_final.pdf.txt</field>
<field name="checksum">9fbc6788c1d31c99e9864ebde84360cc</field>
<field name="checksumAlgorithm">MD5</field>
<field name="sid">3</field>
</element>
<element name="bitstream">
<field name="name">2015_Saval_etal_ESWA_preprint.pdf.txt</field>
<field name="originalName">2015_Saval_etal_ESWA_preprint.pdf.txt</field>
<field name="description">Extracted text</field>
<field name="format">text/plain</field>
<field name="size">65707</field>
<field name="url">http://rua.ua.es/dspace/bitstream/10045/49529/5/2015_Saval_etal_ESWA_preprint.pdf.txt</field>
<field name="checksum">2ec89411d9f14fa37e82181bbcabf9ea</field>
<field name="checksumAlgorithm">MD5</field>
<field name="sid">5</field>
</element>
</element>
</element>
<element name="bundle">
<field name="name">THUMBNAIL</field>
<element name="bitstreams">
<element name="bitstream">
<field name="name">2015_Saval_etal_ESWA_final.pdf.jpg</field>
<field name="originalName">2015_Saval_etal_ESWA_final.pdf.jpg</field>
<field name="description">IM Thumbnail</field>
<field name="format">image/jpeg</field>
<field name="size">5173</field>
<field name="url">http://rua.ua.es/dspace/bitstream/10045/49529/4/2015_Saval_etal_ESWA_final.pdf.jpg</field>
<field name="checksum">6aafe5bab6b63d73099aed60d604515e</field>
<field name="checksumAlgorithm">MD5</field>
<field name="sid">4</field>
</element>
<element name="bitstream">
<field name="name">2015_Saval_etal_ESWA_preprint.pdf.jpg</field>
<field name="originalName">2015_Saval_etal_ESWA_preprint.pdf.jpg</field>
<field name="description">IM Thumbnail</field>
<field name="format">image/jpeg</field>
<field name="size">4438</field>
<field name="url">http://rua.ua.es/dspace/bitstream/10045/49529/6/2015_Saval_etal_ESWA_preprint.pdf.jpg</field>
<field name="checksum">66bdf67b54379238d31069440ade6636</field>
<field name="checksumAlgorithm">MD5</field>
<field name="sid">6</field>
</element>
</element>
</element>
<element name="bundle">
<field name="name">ORIGINAL</field>
<element name="bitstreams">
<element name="bitstream">
<field name="name">2015_Saval_etal_ESWA_final.pdf</field>
<field name="originalName">2015_Saval_etal_ESWA_final.pdf</field>
<field name="description">Versión final (acceso restringido)</field>
<field name="format">application/pdf</field>
<field name="size">5646252</field>
<field name="url">http://rua.ua.es/dspace/bitstream/10045/49529/1/2015_Saval_etal_ESWA_final.pdf</field>
<field name="checksum">b3e80db442c26c3d6fe7c2342948cb95</field>
<field name="checksumAlgorithm">MD5</field>
<field name="sid">1</field>
</element>
<element name="bitstream">
<field name="name">2015_Saval_etal_ESWA_preprint.pdf</field>
<field name="originalName">2015_Saval_etal_ESWA_preprint.pdf</field>
<field name="description">Preprint (acceso abierto)</field>
<field name="format">application/pdf</field>
<field name="size">1625114</field>
<field name="url">http://rua.ua.es/dspace/bitstream/10045/49529/2/2015_Saval_etal_ESWA_preprint.pdf</field>
<field name="checksum">01ba647e300977fd1d2011e50011a81c</field>
<field name="checksumAlgorithm">MD5</field>
<field name="sid">2</field>
</element>
</element>
</element>
</element>
<element name="others">
<field name="handle">10045/49529</field>
<field name="identifier">oai:rua.ua.es:10045/49529</field>
<field name="lastModifyDate">2016-11-09 11:47:32.279</field>
</element>
<element name="repository">
<field name="name">RUA</field>
<field name="mail">dspace@ua.es</field>
</element>
</metadata>