Home / Issues / 7.2010 / Registration of Sub-Sequence and Multi-Camera Reconstructions for Camera Motion Estimation
Document Actions

Citation and metadata

Back to the article.

Recommended citation

Thorsten Thormählen, Nils Hasler, Michael Wand, and Hans-Peter Seidel, Registration of Sub-Sequence and Multi-Camera Reconstructions for Camera Motion Estimation. JVRB - Journal of Virtual Reality and Broadcasting, 7(2010), no. 2. (urn:nbn:de:0009-6-24379)

Download Citation

Endnote

%0 Journal Article
%T Registration of Sub-Sequence and Multi-Camera Reconstructions for Camera Motion Estimation
%A Thormählen, Thorsten
%A Hasler, Nils
%A Wand, Michael
%A Seidel, Hans-Peter
%J JVRB - Journal of Virtual Reality and Broadcasting
%D 2010
%V 7(2010)
%N 2
%@ 1860-2037
%F thormählen2010
%X This paper presents different application scenarios for which the registration of sub-sequence reconstructions or multi-camera reconstructions is essential for successful camera motion estimation and 3D reconstruction from video. The registration is achieved by merging unconnected feature point tracks between the reconstructions. One application is drift removal for sequential camera motion estimation of long sequences. The state-of-the-art in drift removal is to apply a RANSAC approach to find unconnected feature point tracks. In this paper an alternative spectral algorithm for pairwise matching of unconnected feature point tracks is used. It is then shown that the algorithms can be combined and applied to novel scenarios where independent camera motion estimations must be registered into a common global coordinate system. In the first scenario multiple moving cameras, which capture the same scene simultaneously, are registered. A second new scenario occurs in situations where the tracking of feature points during sequential camera motion estimation fails completely, e.g., due to large occluding objects in the foreground, and the unconnected tracks of the independent reconstructions must be merged. In the third scenario image sequences of the same scene, which are captured under different illuminations, are registered. Several experiments with challenging real video sequences demonstrate that the presented techniques work in practice.
%L 004
%K camera motion estimation
%K drift removal
%K multi-camera registration
%K structure-from-motion
%R 10.20385/1860-2037/7.2010.2
%U http://nbn-resolving.de/urn:nbn:de:0009-6-24379
%U http://dx.doi.org/10.20385/1860-2037/7.2010.2
Download

Bibtex

@Article{thormählen2010,
  author = 	"Thorm{\"a}hlen, Thorsten
		and Hasler, Nils
		and Wand, Michael
		and Seidel, Hans-Peter",
  title = 	"Registration of Sub-Sequence and Multi-Camera Reconstructions for Camera Motion Estimation",
  journal = 	"JVRB - Journal of Virtual Reality and Broadcasting",
  year = 	"2010",
  volume = 	"7(2010)",
  number = 	"2",
  keywords = 	"camera motion estimation; drift removal; multi-camera registration; structure-from-motion",
  abstract = 	"This paper presents different application scenarios for which the registration of sub-sequence reconstructions or multi-camera reconstructions is essential for successful camera motion estimation and 3D reconstruction from video. The registration is achieved by merging unconnected feature point tracks between the reconstructions. One application is drift removal for sequential camera motion estimation of long sequences. The state-of-the-art in drift removal is to apply a RANSAC approach to find unconnected feature point tracks. In this paper an alternative spectral algorithm for pairwise matching of unconnected feature point tracks is used. It is then shown that the algorithms can be combined and applied to novel scenarios where independent camera motion estimations must be registered into a common global coordinate system. In the first scenario multiple moving cameras, which capture the same scene simultaneously, are registered. A second new scenario occurs in situations where the tracking of feature points during sequential camera motion estimation fails completely, e.g., due to large occluding objects in the foreground, and the unconnected tracks of the independent reconstructions must be merged. In the third scenario image sequences of the same scene, which are captured under different illuminations, are registered. Several experiments with challenging real video sequences demonstrate that the presented techniques work in practice.",
  issn = 	"1860-2037",
  doi = 	"10.20385/1860-2037/7.2010.2",
  url = 	"http://nbn-resolving.de/urn:nbn:de:0009-6-24379"
}
Download

RIS

TY  - JOUR
AU  - Thormählen, Thorsten
AU  - Hasler, Nils
AU  - Wand, Michael
AU  - Seidel, Hans-Peter
PY  - 2010
DA  - 2010//
TI  - Registration of Sub-Sequence and Multi-Camera Reconstructions for Camera Motion Estimation
JO  - JVRB - Journal of Virtual Reality and Broadcasting
VL  - 7(2010)
IS  - 2
KW  - camera motion estimation
KW  - drift removal
KW  - multi-camera registration
KW  - structure-from-motion
AB  - This paper presents different application scenarios for which the registration of sub-sequence reconstructions or multi-camera reconstructions is essential for successful camera motion estimation and 3D reconstruction from video. The registration is achieved by merging unconnected feature point tracks between the reconstructions. One application is drift removal for sequential camera motion estimation of long sequences. The state-of-the-art in drift removal is to apply a RANSAC approach to find unconnected feature point tracks. In this paper an alternative spectral algorithm for pairwise matching of unconnected feature point tracks is used. It is then shown that the algorithms can be combined and applied to novel scenarios where independent camera motion estimations must be registered into a common global coordinate system. In the first scenario multiple moving cameras, which capture the same scene simultaneously, are registered. A second new scenario occurs in situations where the tracking of feature points during sequential camera motion estimation fails completely, e.g., due to large occluding objects in the foreground, and the unconnected tracks of the independent reconstructions must be merged. In the third scenario image sequences of the same scene, which are captured under different illuminations, are registered. Several experiments with challenging real video sequences demonstrate that the presented techniques work in practice.
SN  - 1860-2037
UR  - http://nbn-resolving.de/urn:nbn:de:0009-6-24379
DO  - 10.20385/1860-2037/7.2010.2
ID  - thormählen2010
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>thormählen2010</b:Tag>
<b:SourceType>ArticleInAPeriodical</b:SourceType>
<b:Year>2010</b:Year>
<b:PeriodicalTitle>JVRB - Journal of Virtual Reality and Broadcasting</b:PeriodicalTitle>
<b:Volume>7(2010)</b:Volume>
<b:Issue>2</b:Issue>
<b:Url>http://nbn-resolving.de/urn:nbn:de:0009-6-24379</b:Url>
<b:Url>http://dx.doi.org/10.20385/1860-2037/7.2010.2</b:Url>
<b:Author>
<b:Author><b:NameList>
<b:Person><b:Last>Thormählen</b:Last><b:First>Thorsten</b:First></b:Person>
<b:Person><b:Last>Hasler</b:Last><b:First>Nils</b:First></b:Person>
<b:Person><b:Last>Wand</b:Last><b:First>Michael</b:First></b:Person>
<b:Person><b:Last>Seidel</b:Last><b:First>Hans-Peter</b:First></b:Person>
</b:NameList></b:Author>
</b:Author>
<b:Title>Registration of Sub-Sequence and Multi-Camera Reconstructions for Camera Motion Estimation</b:Title>
<b:Comments>This paper presents different application scenarios for which the registration of sub-sequence reconstructions or multi-camera reconstructions is essential for successful camera motion estimation and 3D reconstruction from video. The registration is achieved by merging unconnected feature point tracks between the reconstructions. One application is drift removal for sequential camera motion estimation of long sequences. The state-of-the-art in drift removal is to apply a RANSAC approach to find unconnected feature point tracks. In this paper an alternative spectral algorithm for pairwise matching of unconnected feature point tracks is used. It is then shown that the algorithms can be combined and applied to novel scenarios where independent camera motion estimations must be registered into a common global coordinate system. In the first scenario multiple moving cameras, which capture the same scene simultaneously, are registered. A second new scenario occurs in situations where the tracking of feature points during sequential camera motion estimation fails completely, e.g., due to large occluding objects in the foreground, and the unconnected tracks of the independent reconstructions must be merged. In the third scenario image sequences of the same scene, which are captured under different illuminations, are registered. Several experiments with challenging real video sequences demonstrate that the presented techniques work in practice.</b:Comments>
</b:Source>
</b:Sources>
Download

ISI

PT Journal
AU Thormählen, T
   Hasler, N
   Wand, M
   Seidel, H
TI Registration of Sub-Sequence and Multi-Camera Reconstructions for Camera Motion Estimation
SO JVRB - Journal of Virtual Reality and Broadcasting
PY 2010
VL 7(2010)
IS 2
DI 10.20385/1860-2037/7.2010.2
DE camera motion estimation; drift removal; multi-camera registration; structure-from-motion
AB This paper presents different application scenarios for which the registration of sub-sequence reconstructions or multi-camera reconstructions is essential for successful camera motion estimation and 3D reconstruction from video. The registration is achieved by merging unconnected feature point tracks between the reconstructions. One application is drift removal for sequential camera motion estimation of long sequences. The state-of-the-art in drift removal is to apply a RANSAC approach to find unconnected feature point tracks. In this paper an alternative spectral algorithm for pairwise matching of unconnected feature point tracks is used. It is then shown that the algorithms can be combined and applied to novel scenarios where independent camera motion estimations must be registered into a common global coordinate system. In the first scenario multiple moving cameras, which capture the same scene simultaneously, are registered. A second new scenario occurs in situations where the tracking of feature points during sequential camera motion estimation fails completely, e.g., due to large occluding objects in the foreground, and the unconnected tracks of the independent reconstructions must be merged. In the third scenario image sequences of the same scene, which are captured under different illuminations, are registered. Several experiments with challenging real video sequences demonstrate that the presented techniques work in practice.
ER
Download

Mods

<mods>
  <titleInfo>
    <title>Registration of Sub-Sequence and Multi-Camera Reconstructions for Camera Motion Estimation</title>
  </titleInfo>
  <name type="personal">
    <namePart type="family">Thormählen</namePart>
    <namePart type="given">Thorsten</namePart>
  </name>
  <name type="personal">
    <namePart type="family">Hasler</namePart>
    <namePart type="given">Nils</namePart>
  </name>
  <name type="personal">
    <namePart type="family">Wand</namePart>
    <namePart type="given">Michael</namePart>
  </name>
  <name type="personal">
    <namePart type="family">Seidel</namePart>
    <namePart type="given">Hans-Peter</namePart>
  </name>
  <abstract>This paper presents different application scenarios for which the registration of sub-sequence reconstructions or multi-camera reconstructions is essential for successful camera motion estimation and 3D reconstruction from video. The registration is achieved by merging unconnected feature point tracks between the reconstructions. One application is drift removal for sequential camera motion estimation of long sequences. The state-of-the-art in drift removal is to apply a RANSAC approach to find unconnected feature point tracks. In this paper an alternative spectral algorithm for pairwise matching of unconnected feature point tracks is used. It is then shown that the algorithms can be combined and applied to novel scenarios where independent camera motion estimations must be registered into a common global coordinate system. In the first scenario multiple moving cameras, which capture the same scene simultaneously, are registered. A second new scenario occurs in situations where the tracking of feature points during sequential camera motion estimation fails completely, e.g., due to large occluding objects in the foreground, and the unconnected tracks of the independent reconstructions must be merged. In the third scenario image sequences of the same scene, which are captured under different illuminations, are registered. Several experiments with challenging real video sequences demonstrate that the presented techniques work in practice.</abstract>
  <subject>
    <topic>camera motion estimation</topic>
    <topic>drift removal</topic>
    <topic>multi-camera registration</topic>
    <topic>structure-from-motion</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>7(2010)</number>
      </detail>
      <detail type="issue">
        <number>2</number>
      </detail>
      <date>2010</date>
    </part>
  </relatedItem>
  <identifier type="issn">1860-2037</identifier>
  <identifier type="urn">urn:nbn:de:0009-6-24379</identifier>
  <identifier type="doi">10.20385/1860-2037/7.2010.2</identifier>
  <identifier type="uri">http://nbn-resolving.de/urn:nbn:de:0009-6-24379</identifier>
  <identifier type="citekey">thormählen2010</identifier>
</mods>
Download

Full Metadata

Bibliographic Citation JVRB, 7(2010), no. 2.
Title

Registration of Sub-Sequence and Multi-Camera Reconstructions for Camera Motion Estimation (eng)
Author Thorsten Thormählen, Nils Hasler, Michael Wand, Hans-Peter Seidel
Language eng
Abstract This paper presents different application scenarios for which the registration of sub-sequence reconstructions or multi-camera reconstructions is essential for successful camera motion estimation and 3D reconstruction from video. The registration is achieved by merging unconnected feature point tracks between the reconstructions. One application is drift removal for sequential camera motion estimation of long sequences. The state-of-the-art in drift removal is to apply a RANSAC approach to find unconnected feature point tracks. In this paper an alternative spectral algorithm for pairwise matching of unconnected feature point tracks is used. It is then shown that the algorithms can be combined and applied to novel scenarios where independent camera motion estimations must be registered into a common global coordinate system. In the first scenario multiple moving cameras, which capture the same scene simultaneously, are registered. A second new scenario occurs in situations where the tracking of feature points during sequential camera motion estimation fails completely, e.g., due to large occluding objects in the foreground, and the unconnected tracks of the independent reconstructions must be merged. In the third scenario image sequences of the same scene, which are captured under different illuminations, are registered. Several experiments with challenging real video sequences demonstrate that the presented techniques work in practice.
Subject camera motion estimation, drift removal, multi-camera registration, structure-from-motion
Classified Subjects
swd
  • 4366655-3, Kamera
  • 4154362-2, Kamera / Film
  • 4006311-2, Bewegung
DDC 004
Rights DPPL
URN: urn:nbn:de:0009-6-24379
DOI https://doi.org/10.20385/1860-2037/7.2010.2