<?xml version="1.0" encoding="ISO-8859-1"?>
<metadatalist>
	<metadata ReferenceType="Conference Proceedings">
		<site>sibgrapi.sid.inpe.br 802</site>
		<holdercode>{ibi 8JMKD3MGPEW34M/46T9EHH}</holdercode>
		<identifier>8JMKD3MGPBW34M/3JUHHEB</identifier>
		<repository>sid.inpe.br/sibgrapi/2015/07.31.17.03</repository>
		<lastupdate>2015:07.31.17.03.32 sid.inpe.br/banon/2001/03.30.15.38 acsantossouza@gmail.com</lastupdate>
		<metadatarepository>sid.inpe.br/sibgrapi/2015/07.31.17.03.32</metadatarepository>
		<metadatalastupdate>2022:05.18.22.21.01 sid.inpe.br/banon/2001/03.30.15.38 administrator {D 2015}</metadatalastupdate>
		<citationkey>SouzaApol:2015:AdApRe</citationkey>
		<title>An Adaptive Approach to Real-Time 3D Non-Rigid Registration</title>
		<format>On-line</format>
		<year>2015</year>
		<secondarytype>Doctoral Work</secondarytype>
		<numberoffiles>1</numberoffiles>
		<size>2949 KiB</size>
		<author>Souza, Antonio Carlos dos Santos,</author>
		<author>Apolinário Júnior, Antônio Lopes,</author>
		<affiliation>Federal Institute of Bahia</affiliation>
		<affiliation>Federal University of Bahia</affiliation>
		<editor>Segundo, Maurício Pamplona,</editor>
		<editor>Faria, Fabio Augusto,</editor>
		<e-mailaddress>acsantossouza@gmail.com</e-mailaddress>
		<conferencename>Conference on Graphics, Patterns and Images, 28 (SIBGRAPI)</conferencename>
		<conferencelocation>Salvador, BA, Brazil</conferencelocation>
		<date>26-29 Aug. 2015</date>
		<publisher>Sociedade Brasileira de Computação</publisher>
		<publisheraddress>Porto Alegre</publisheraddress>
		<booktitle>Proceedings</booktitle>
		<tertiarytype>Master's or Doctoral Work</tertiarytype>
		<transferableflag>1</transferableflag>
		<keywords>adaptive algorithms, augmented reality, non-rigid registration.</keywords>
		<abstract>3D non-rigid registration is fundamental for tracking or reconstruction of 3D deformable shapes. Fast methods for 3D non-rigid registration are particularly interesting for markerless augmented reality applications, in which the object being used as a natural marker may undergo a non-rigid user interaction. Here, we present a multi-frame adaptive algorithm for 3D non-rigid registration implemented on GPU where the 3D data is captured from an RGB-D camera. In this work, adaptivity is used in three stages of the process. First, to guide the distribution of regions of influence based on the deformation intensity on some region of the shape. Second, during the selection of constraints, where the sampling done over the object for the optimization is based on the current deformation. Third, to apply the algorithm in a multi-frame manner only when the rigid tracking error is above a pre-defined threshold. The results obtained show that the proposed algorithm is capable to achieve real-time performance with an approach as accurate as the ones proposed in the literature.</abstract>
		<language>en</language>
		<targetfile>PhdSIBGRAPI2015.pdf</targetfile>
		<usergroup>acsantossouza@gmail.com</usergroup>
		<visibility>shown</visibility>
		<documentstage>not transferred</documentstage>
		<mirrorrepository>sid.inpe.br/banon/2001/03.30.15.38.24</mirrorrepository>
		<nexthigherunit>8JMKD3MGPBW34M/3K24PF8</nexthigherunit>
		<citingitemlist>sid.inpe.br/sibgrapi/2015/08.03.22.49 11</citingitemlist>
		<hostcollection>sid.inpe.br/banon/2001/03.30.15.38</hostcollection>
		<agreement>agreement.html .htaccess .htaccess2</agreement>
		<lasthostcollection>sid.inpe.br/banon/2001/03.30.15.38</lasthostcollection>
		<url>http://sibgrapi.sid.inpe.br/rep-/sid.inpe.br/sibgrapi/2015/07.31.17.03</url>
	</metadata>
</metadatalist>