<?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>83LX3pFwXQZeBBx/fLgjb</identifier>
		<repository>dpi.inpe.br/banon/1999/01.13.18.50</repository>
		<lastupdate>1999:01.18.02.00.00 sid.inpe.br/banon/2001/03.30.15.38 administrator</lastupdate>
		<metadatarepository>sid.inpe.br/banon/2001/03.30.15.53.55</metadatarepository>
		<metadatalastupdate>2022:06.14.00.16.31 sid.inpe.br/banon/2001/03.30.15.38 administrator {D 1998}</metadatalastupdate>
		<citationkey>Gonzalo-TasisFina:1998:ToCoRe</citationkey>
		<title>Towards a coarse real-time stereo fusion based on triple junctions</title>
		<year>1998</year>
		<numberoffiles>1</numberoffiles>
		<size>67 KiB</size>
		<author>Gonzalo-Tasis, Margarita,</author>
		<author>Finat, Javier,</author>
		<editor>Costa, L. da F,</editor>
		<editor>Camara, G.,</editor>
		<conferencename>International Symposium on Computer Graphics, Image Processing and Vision, 11 (SIBGRAPI)</conferencename>
		<conferencelocation>Rio de Janeiro, RJ, Brazil</conferencelocation>
		<date>20-23 Oct. 1998</date>
		<publisher>Sociedade Brasileira de Computação</publisher>
		<publisheraddress>Porto Alegre</publisheraddress>
		<booktitle>Proceedings</booktitle>
		<tertiarytype>Full Paper</tertiarytype>
		<organization>SBC - Sociedade Brasileira de Computação</organization>
		<transferableflag>1</transferableflag>
		<keywords>computer graphics, image processing, stereo vision processamento de imagem, visiom estereo</keywords>
		<abstract>In this paper we develop a hybrid method to establish the correspondence between common triple junctions appearing in two views of the same scene taken by an uncalibrated bicameral heading with known disparity between both cameras and under constant illumination conditions. After a segmentation process, we get a set of edges. Beginning from theses edges, we extract different types of junctions (uparrow, T, L or Y). These geometric features are robust even when the noise arising from the real s cenes appears. We provide a very fast process of comparison between these points placed at a similar depth in real scenes. Next, we apply a labeling relaxation procedure to determine possible homologues between two images. Decision criteria are based on probabilistic methods, allowing us an easy extension under uncertainty conditions or under incomplete information due to partial occlusions or noise.</abstract>
		<targetfile>sse012.pdf</targetfile>
		<usergroup>administrator</usergroup>
		<visibility>shown</visibility>
		<nexthigherunit>8JMKD3MGPEW34M/46RGNB8</nexthigherunit>
		<nexthigherunit>8JMKD3MGPEW34M/4742MCS</nexthigherunit>
		<citingitemlist>sid.inpe.br/sibgrapi/2022/05.08.04.49 5</citingitemlist>
		<hostcollection>sid.inpe.br/banon/2001/03.30.15.38</hostcollection>
		<notes>The conference was held in Rio de Janeiro, RJ, Brazil, from October 20 to 23.</notes>
		<lasthostcollection>sid.inpe.br/banon/2001/03.30.15.38</lasthostcollection>
		<url>http://sibgrapi.sid.inpe.br/rep-/dpi.inpe.br/banon/1999/01.13.18.50</url>
	</metadata>
</metadatalist>