Home / Issues / 4.2007 / Tracking of industrial objects by using CAD models
Document Actions

Citation and metadata

Back to the article.

Recommended citation

Harald Wuest, and Didier Stricker, Tracking of industrial objects by using CAD models. JVRB - Journal of Virtual Reality and Broadcasting, 4(2007), no. 1. (urn:nbn:de:0009-6-11595)

Download Citation

Endnote

%0 Journal Article
%T Tracking of industrial objects by using CAD models
%A Wuest, Harald
%A Stricker, Didier
%J JVRB - Journal of Virtual Reality and Broadcasting
%D 2007
%V 4(2007)
%N 1
%@ 1860-2037
%F wuest2007
%X In this paper we present a model-based approach for real-time camera pose estimation in industrial scenarios. The line model which is used for tracking is generated by rendering a polygonal model and extracting contours out of the rendered scene. By un-projecting a point on the contour with the depth value stored in the z-buffer, the 3D coordinates of the contour can be calculated. For establishing 2D/3D correspondences the 3D control points on the contour are projected into the image and a perpendicular search for gradient maxima for every point on the contour is performed. Multiple hypotheses of 2D image points corresponding to a 3D control point make the pose estimation robust against ambiguous edges in the image.
%L 004
%K Augmented Reality
%K CAD model
%K Line Tracking
%K Tracking
%R 10.20385/1860-2037/4.2007.1
%U http://nbn-resolving.de/urn:nbn:de:0009-6-11595
%U http://dx.doi.org/10.20385/1860-2037/4.2007.1
Download

Bibtex

@Article{wuest2007,
  author = 	"Wuest, Harald
		and Stricker, Didier",
  title = 	"Tracking of industrial objects by using CAD models",
  journal = 	"JVRB - Journal of Virtual Reality and Broadcasting",
  year = 	"2007",
  volume = 	"4(2007)",
  number = 	"1",
  keywords = 	"Augmented Reality; CAD model; Line Tracking; Tracking",
  abstract = 	"In this paper we present a model-based approach for real-time camera pose estimation in industrial scenarios. The line model which is used for tracking is generated by rendering a polygonal model and extracting contours out of the rendered scene. By un-projecting a point on the contour with the depth value stored in the z-buffer, the 3D coordinates of the contour can be calculated. For establishing 2D/3D correspondences the 3D control points on the contour are projected into the image and a perpendicular search for gradient maxima for every point on the contour is performed. Multiple hypotheses of 2D image points corresponding to a 3D control point make the pose estimation robust against ambiguous edges in the image.",
  issn = 	"1860-2037",
  doi = 	"10.20385/1860-2037/4.2007.1",
  url = 	"http://nbn-resolving.de/urn:nbn:de:0009-6-11595"
}
Download

RIS

TY  - JOUR
AU  - Wuest, Harald
AU  - Stricker, Didier
PY  - 2007
DA  - 2007//
TI  - Tracking of industrial objects by using CAD models
JO  - JVRB - Journal of Virtual Reality and Broadcasting
VL  - 4(2007)
IS  - 1
KW  - Augmented Reality
KW  - CAD model
KW  - Line Tracking
KW  - Tracking
AB  - In this paper we present a model-based approach for real-time camera pose estimation in industrial scenarios. The line model which is used for tracking is generated by rendering a polygonal model and extracting contours out of the rendered scene. By un-projecting a point on the contour with the depth value stored in the z-buffer, the 3D coordinates of the contour can be calculated. For establishing 2D/3D correspondences the 3D control points on the contour are projected into the image and a perpendicular search for gradient maxima for every point on the contour is performed. Multiple hypotheses of 2D image points corresponding to a 3D control point make the pose estimation robust against ambiguous edges in the image.
SN  - 1860-2037
UR  - http://nbn-resolving.de/urn:nbn:de:0009-6-11595
DO  - 10.20385/1860-2037/4.2007.1
ID  - wuest2007
ER  -
Download

Wordbib

<?xml version="1.0" encoding="UTF-8"?>
<b:Sources SelectedStyle="" xmlns:b="http://schemas.openxmlformats.org/officeDocument/2006/bibliography"  xmlns="http://schemas.openxmlformats.org/officeDocument/2006/bibliography" >
<b:Source>
<b:Tag>wuest2007</b:Tag>
<b:SourceType>ArticleInAPeriodical</b:SourceType>
<b:Year>2007</b:Year>
<b:PeriodicalTitle>JVRB - Journal of Virtual Reality and Broadcasting</b:PeriodicalTitle>
<b:Volume>4(2007)</b:Volume>
<b:Issue>1</b:Issue>
<b:Url>http://nbn-resolving.de/urn:nbn:de:0009-6-11595</b:Url>
<b:Url>http://dx.doi.org/10.20385/1860-2037/4.2007.1</b:Url>
<b:Author>
<b:Author><b:NameList>
<b:Person><b:Last>Wuest</b:Last><b:First>Harald</b:First></b:Person>
<b:Person><b:Last>Stricker</b:Last><b:First>Didier</b:First></b:Person>
</b:NameList></b:Author>
</b:Author>
<b:Title>Tracking of industrial objects by using CAD models</b:Title>
<b:Comments>In this paper we present a model-based approach for real-time camera pose estimation in industrial scenarios. The line model which is used for tracking is generated by rendering a polygonal model and extracting contours out of the rendered scene. By un-projecting a point on the contour with the depth value stored in the z-buffer, the 3D coordinates of the contour can be calculated. For establishing 2D/3D correspondences the 3D control points on the contour are projected into the image and a perpendicular search for gradient maxima for every point on the contour is performed. Multiple hypotheses of 2D image points corresponding to a 3D control point make the pose estimation robust against ambiguous edges in the image.</b:Comments>
</b:Source>
</b:Sources>
Download

ISI

PT Journal
AU Wuest, H
   Stricker, D
TI Tracking of industrial objects by using CAD models
SO JVRB - Journal of Virtual Reality and Broadcasting
PY 2007
VL 4(2007)
IS 1
DI 10.20385/1860-2037/4.2007.1
DE Augmented Reality; CAD model; Line Tracking; Tracking
AB In this paper we present a model-based approach for real-time camera pose estimation in industrial scenarios. The line model which is used for tracking is generated by rendering a polygonal model and extracting contours out of the rendered scene. By un-projecting a point on the contour with the depth value stored in the z-buffer, the 3D coordinates of the contour can be calculated. For establishing 2D/3D correspondences the 3D control points on the contour are projected into the image and a perpendicular search for gradient maxima for every point on the contour is performed. Multiple hypotheses of 2D image points corresponding to a 3D control point make the pose estimation robust against ambiguous edges in the image.
ER
Download

Mods

<mods>
  <titleInfo>
    <title>Tracking of industrial objects by using CAD models</title>
  </titleInfo>
  <name type="personal">
    <namePart type="family">Wuest</namePart>
    <namePart type="given">Harald</namePart>
  </name>
  <name type="personal">
    <namePart type="family">Stricker</namePart>
    <namePart type="given">Didier</namePart>
  </name>
  <abstract>In this paper we present a model-based approach for real-time camera pose estimation in industrial scenarios. The line model which is used for tracking is generated by rendering a polygonal model and extracting contours out of the rendered scene. By un-projecting a point on the contour with the depth value stored in the z-buffer, the 3D coordinates of the contour can be calculated. For establishing 2D/3D correspondences the 3D control points on the contour are projected into the image and a perpendicular search for gradient maxima for every point on the contour is performed. Multiple hypotheses of 2D image points corresponding to a 3D control point make the pose estimation robust against ambiguous edges in the image.</abstract>
  <subject>
    <topic>Augmented Reality</topic>
    <topic>CAD model</topic>
    <topic>Line Tracking</topic>
    <topic>Tracking</topic>
  </subject>
  <classification authority="ddc">004</classification>
  <relatedItem type="host">
    <genre authority="marcgt">periodical</genre>
    <genre>academic journal</genre>
    <titleInfo>
      <title>JVRB - Journal of Virtual Reality and Broadcasting</title>
    </titleInfo>
    <part>
      <detail type="volume">
        <number>4(2007)</number>
      </detail>
      <detail type="issue">
        <number>1</number>
      </detail>
      <date>2007</date>
    </part>
  </relatedItem>
  <identifier type="issn">1860-2037</identifier>
  <identifier type="urn">urn:nbn:de:0009-6-11595</identifier>
  <identifier type="doi">10.20385/1860-2037/4.2007.1</identifier>
  <identifier type="uri">http://nbn-resolving.de/urn:nbn:de:0009-6-11595</identifier>
  <identifier type="citekey">wuest2007</identifier>
</mods>
Download

Full Metadata

Bibliographic Citation JVRB, 4(2007), no. 1.
Title

Tracking of industrial objects by using CAD models (eng)
Author Harald Wuest, Didier Stricker
Language eng
Abstract In this paper we present a model-based approach for real-time camera pose estimation in industrial scenarios. The line model which is used for tracking is generated by rendering a polygonal model and extracting contours out of the rendered scene. By un-projecting a point on the contour with the depth value stored in the z-buffer, the 3D coordinates of the contour can be calculated. For establishing 2D/3D correspondences the 3D control points on the contour are projected into the image and a perpendicular search for gradient maxima for every point on the contour is performed. Multiple hypotheses of 2D image points corresponding to a 3D control point make the pose estimation robust against ambiguous edges in the image.
Subject Augmented Reality, CAD model, Line Tracking, Tracking
Classified Subjects
swd
  • 4715802-5, Augmented Reality
  • 4311226-2, Tracking
DDC 004
Rights DPPL
URN: urn:nbn:de:0009-6-11595
DOI https://doi.org/10.20385/1860-2037/4.2007.1
Language
  1. Deutsch
  2. English
Navigation