Home / Issues / 13.2016 / Presenting a Holistic Framework for Scalable, Marker-less Motion Capturing: Skeletal Tracking Performance Analysis, Sensor Fusion Algorithms and Usage in Automotive Industry
Document Actions

Citation and metadata

Back to the article.

Recommended citation

Michael M. Otto, Philipp Agethen, Florian Geiselhart, Michael Rietzler, Felix Gaisbauer, and Enrico Rukzio, Presenting a Holistic Framework for Scalable, Marker-less Motion Capturing: Skeletal Tracking Performance Analysis, Sensor Fusion Algorithms and Usage in Automotive Industry. Journal of Virtual Reality and Broadcasting, 13(2016), no. 3. (urn:nbn:de:0009-6-44811)

Download Citation

Endnote

%0 Journal Article
%T Presenting a Holistic Framework for Scalable, Marker-less Motion Capturing: Skeletal Tracking Performance Analysis, Sensor Fusion Algorithms and Usage in Automotive Industry
%A Otto, Michael M.
%A Agethen, Philipp
%A Geiselhart, Florian
%A Rietzler, Michael
%A Gaisbauer, Felix
%A Rukzio, Enrico
%J Journal of Virtual Reality and Broadcasting
%D 2017
%V 13(2016)
%N 3
%@ 1860-2037
%F otto2017
%X Even though there is promising technological progress, input is currently still one of virtual reality's biggest issues. Off-the-shelf depth cameras have the potential to resolve these tracking problems. These sensors have become common in several application areas due to their availability and affordability. However, various applications in industry and research still require large-scale tracking systems e.g. for interaction with virtual environments. As single depth-cameras have limited performance in this context, we propose a novel set of methods for multiple depth-camera registration and heuristic-based sensor fusion using skeletal tracking. An in-depth accuracy analysis of Kinect v2 skeletal tracking is presented in which a robot moves a mannequin for accurate, reproducible motion paths. Based on the results of this evaluation, a distributed and service-oriented marker-less tracking system consisting of multiple Kinect v2 sensors is developed for real-time interaction with virtual environments. Evaluation shows that this approach helps in increasing tracking areas, resolving occlusions and improving human posture analysis. Additionally, an advanced error prediction model is proposed to further improve skeletal tracking results. The overall system is evaluated by using it for realistic ergonomic assessments in automotive production verification workshops. It is shown that performance and applicability of the system is suitable for the use in automotive industry and may replace conventional high-end marker-based systems partially in this domain.
%L 004
%K full-body motion capture
%K markerless
%K scalable
%K skeletal tracking
%R 10.20385/1860-2037/13.2016.3
%U http://nbn-resolving.de/urn:nbn:de:0009-6-44811
%U http://dx.doi.org/10.20385/1860-2037/13.2016.3
Download

Bibtex

@Article{otto2017,
  author = 	"Otto, Michael M.
		and Agethen, Philipp
		and Geiselhart, Florian
		and Rietzler, Michael
		and Gaisbauer, Felix
		and Rukzio, Enrico",
  title = 	"Presenting a Holistic Framework for Scalable, Marker-less Motion Capturing: Skeletal Tracking Performance Analysis, Sensor Fusion Algorithms and Usage in Automotive Industry",
  journal = 	"Journal of Virtual Reality and Broadcasting",
  year = 	"2017",
  volume = 	"13(2016)",
  number = 	"3",
  keywords = 	"full-body motion capture; markerless; scalable; skeletal tracking",
  abstract = 	"Even though there is promising technological progress, input is currently still one of virtual reality's biggest issues. Off-the-shelf depth cameras have the potential to resolve these tracking problems. These sensors have become common in several application areas due to their availability and affordability. However, various applications in industry and research still require large-scale tracking systems e.g. for interaction with virtual environments. As single depth-cameras have limited performance in this context, we propose a novel set of methods for multiple depth-camera registration and heuristic-based sensor fusion using skeletal tracking. An in-depth accuracy analysis of Kinect v2 skeletal tracking is presented in which a robot moves a mannequin for accurate, reproducible motion paths. Based on the results of this evaluation, a distributed and service-oriented marker-less tracking system consisting of multiple Kinect v2 sensors is developed for real-time interaction with virtual environments. Evaluation shows that this approach helps in increasing tracking areas, resolving occlusions and improving human posture analysis. Additionally, an advanced error prediction model is proposed to further improve skeletal tracking results. The overall system is evaluated by using it for realistic ergonomic assessments in automotive production verification workshops. It is shown that performance and applicability of the system is suitable for the use in automotive industry and may replace conventional high-end marker-based systems partially in this domain.",
  issn = 	"1860-2037",
  doi = 	"10.20385/1860-2037/13.2016.3",
  url = 	"http://nbn-resolving.de/urn:nbn:de:0009-6-44811"
}
Download

RIS

TY  - JOUR
AU  - Otto, Michael M.
AU  - Agethen, Philipp
AU  - Geiselhart, Florian
AU  - Rietzler, Michael
AU  - Gaisbauer, Felix
AU  - Rukzio, Enrico
PY  - 2017
DA  - 2017//
TI  - Presenting a Holistic Framework for Scalable, Marker-less Motion Capturing: Skeletal Tracking Performance Analysis, Sensor Fusion Algorithms and Usage in Automotive Industry
JO  - Journal of Virtual Reality and Broadcasting
VL  - 13(2016)
IS  - 3
KW  - full-body motion capture
KW  - markerless
KW  - scalable
KW  - skeletal tracking
AB  - Even though there is promising technological progress, input is currently still one of virtual reality's biggest issues. Off-the-shelf depth cameras have the potential to resolve these tracking problems. These sensors have become common in several application areas due to their availability and affordability. However, various applications in industry and research still require large-scale tracking systems e.g. for interaction with virtual environments. As single depth-cameras have limited performance in this context, we propose a novel set of methods for multiple depth-camera registration and heuristic-based sensor fusion using skeletal tracking. An in-depth accuracy analysis of Kinect v2 skeletal tracking is presented in which a robot moves a mannequin for accurate, reproducible motion paths. Based on the results of this evaluation, a distributed and service-oriented marker-less tracking system consisting of multiple Kinect v2 sensors is developed for real-time interaction with virtual environments. Evaluation shows that this approach helps in increasing tracking areas, resolving occlusions and improving human posture analysis. Additionally, an advanced error prediction model is proposed to further improve skeletal tracking results. The overall system is evaluated by using it for realistic ergonomic assessments in automotive production verification workshops. It is shown that performance and applicability of the system is suitable for the use in automotive industry and may replace conventional high-end marker-based systems partially in this domain.
SN  - 1860-2037
UR  - http://nbn-resolving.de/urn:nbn:de:0009-6-44811
DO  - 10.20385/1860-2037/13.2016.3
ID  - otto2017
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>otto2017</b:Tag>
<b:SourceType>ArticleInAPeriodical</b:SourceType>
<b:Year>2017</b:Year>
<b:PeriodicalTitle>Journal of Virtual Reality and Broadcasting</b:PeriodicalTitle>
<b:Volume>13(2016)</b:Volume>
<b:Issue>3</b:Issue>
<b:Url>http://nbn-resolving.de/urn:nbn:de:0009-6-44811</b:Url>
<b:Url>http://dx.doi.org/10.20385/1860-2037/13.2016.3</b:Url>
<b:Author>
<b:Author><b:NameList>
<b:Person><b:Last>Otto</b:Last><b:First>Michael M.</b:First></b:Person>
<b:Person><b:Last>Agethen</b:Last><b:First>Philipp</b:First></b:Person>
<b:Person><b:Last>Geiselhart</b:Last><b:First>Florian</b:First></b:Person>
<b:Person><b:Last>Rietzler</b:Last><b:First>Michael</b:First></b:Person>
<b:Person><b:Last>Gaisbauer</b:Last><b:First>Felix</b:First></b:Person>
<b:Person><b:Last>Rukzio</b:Last><b:First>Enrico</b:First></b:Person>
</b:NameList></b:Author>
</b:Author>
<b:Title>Presenting a Holistic Framework for Scalable, Marker-less Motion Capturing: Skeletal Tracking Performance Analysis, Sensor Fusion Algorithms and Usage in Automotive Industry</b:Title>
<b:Comments>Even though there is promising technological progress, input is currently still one of virtual reality&apos;s biggest issues. Off-the-shelf depth cameras have the potential to resolve these tracking problems. These sensors have become common in several application areas due to their availability and affordability. However, various applications in industry and research still require large-scale tracking systems e.g. for interaction with virtual environments. As single depth-cameras have limited performance in this context, we propose a novel set of methods for multiple depth-camera registration and heuristic-based sensor fusion using skeletal tracking. An in-depth accuracy analysis of Kinect v2 skeletal tracking is presented in which a robot moves a mannequin for accurate, reproducible motion paths. Based on the results of this evaluation, a distributed and service-oriented marker-less tracking system consisting of multiple Kinect v2 sensors is developed for real-time interaction with virtual environments. Evaluation shows that this approach helps in increasing tracking areas, resolving occlusions and improving human posture analysis. Additionally, an advanced error prediction model is proposed to further improve skeletal tracking results. The overall system is evaluated by using it for realistic ergonomic assessments in automotive production verification workshops. It is shown that performance and applicability of the system is suitable for the use in automotive industry and may replace conventional high-end marker-based systems partially in this domain.</b:Comments>
</b:Source>
</b:Sources>
Download

ISI

PT Journal
AU Otto, M
   Agethen, P
   Geiselhart, F
   Rietzler, M
   Gaisbauer, F
   Rukzio, E
TI Presenting a Holistic Framework for Scalable, Marker-less Motion Capturing: Skeletal Tracking Performance Analysis, Sensor Fusion Algorithms and Usage in Automotive Industry
SO Journal of Virtual Reality and Broadcasting
PY 2017
VL 13(2016)
IS 3
DI 10.20385/1860-2037/13.2016.3
DE full-body motion capture; markerless; scalable; skeletal tracking
AB Even though there is promising technological progress, input is currently still one of virtual reality's biggest issues. Off-the-shelf depth cameras have the potential to resolve these tracking problems. These sensors have become common in several application areas due to their availability and affordability. However, various applications in industry and research still require large-scale tracking systems e.g. for interaction with virtual environments. As single depth-cameras have limited performance in this context, we propose a novel set of methods for multiple depth-camera registration and heuristic-based sensor fusion using skeletal tracking. An in-depth accuracy analysis of Kinect v2 skeletal tracking is presented in which a robot moves a mannequin for accurate, reproducible motion paths. Based on the results of this evaluation, a distributed and service-oriented marker-less tracking system consisting of multiple Kinect v2 sensors is developed for real-time interaction with virtual environments. Evaluation shows that this approach helps in increasing tracking areas, resolving occlusions and improving human posture analysis. Additionally, an advanced error prediction model is proposed to further improve skeletal tracking results. The overall system is evaluated by using it for realistic ergonomic assessments in automotive production verification workshops. It is shown that performance and applicability of the system is suitable for the use in automotive industry and may replace conventional high-end marker-based systems partially in this domain.
ER
Download

Mods

<mods>
  <titleInfo>
    <title>Presenting a Holistic Framework for Scalable, Marker-less Motion Capturing: Skeletal Tracking Performance Analysis, Sensor Fusion Algorithms and Usage in Automotive Industry</title>
  </titleInfo>
  <name type="personal">
    <namePart type="family">Otto</namePart>
    <namePart type="given">Michael M.</namePart>
  </name>
  <name type="personal">
    <namePart type="family">Agethen</namePart>
    <namePart type="given">Philipp</namePart>
  </name>
  <name type="personal">
    <namePart type="family">Geiselhart</namePart>
    <namePart type="given">Florian</namePart>
  </name>
  <name type="personal">
    <namePart type="family">Rietzler</namePart>
    <namePart type="given">Michael</namePart>
  </name>
  <name type="personal">
    <namePart type="family">Gaisbauer</namePart>
    <namePart type="given">Felix</namePart>
  </name>
  <name type="personal">
    <namePart type="family">Rukzio</namePart>
    <namePart type="given">Enrico</namePart>
  </name>
  <abstract>Even though there is promising technological progress, input is currently still one of virtual reality's biggest issues. Off-the-shelf depth cameras have the potential to resolve these tracking problems. These sensors have become common in several application areas due to their availability and affordability. However, various applications in industry and research still require large-scale tracking systems e.g. for interaction with virtual environments. As single depth-cameras have limited performance in this context, we propose a novel set of methods for multiple depth-camera registration and heuristic-based sensor fusion using skeletal tracking. An in-depth accuracy analysis of Kinect v2 skeletal tracking is presented in which a robot moves a mannequin for accurate, reproducible motion paths. Based on the results of this evaluation, a distributed and service-oriented marker-less tracking system consisting of multiple Kinect v2 sensors is developed for real-time interaction with virtual environments. Evaluation shows that this approach helps in increasing tracking areas, resolving occlusions and improving human posture analysis. Additionally, an advanced error prediction model is proposed to further improve skeletal tracking results. The overall system is evaluated by using it for realistic ergonomic assessments in automotive production verification workshops. It is shown that performance and applicability of the system is suitable for the use in automotive industry and may replace conventional high-end marker-based systems partially in this domain.</abstract>
  <subject>
    <topic>full-body motion capture</topic>
    <topic>markerless</topic>
    <topic>scalable</topic>
    <topic>skeletal tracking</topic>
  </subject>
  <classification authority="ddc">004</classification>
  <relatedItem type="host">
    <genre authority="marcgt">periodical</genre>
    <genre>academic journal</genre>
    <titleInfo>
      <title>Journal of Virtual Reality and Broadcasting</title>
    </titleInfo>
    <part>
      <detail type="volume">
        <number>13(2016)</number>
      </detail>
      <detail type="issue">
        <number>3</number>
      </detail>
      <date>2017</date>
    </part>
  </relatedItem>
  <identifier type="issn">1860-2037</identifier>
  <identifier type="urn">urn:nbn:de:0009-6-44811</identifier>
  <identifier type="doi">10.20385/1860-2037/13.2016.3</identifier>
  <identifier type="uri">http://nbn-resolving.de/urn:nbn:de:0009-6-44811</identifier>
  <identifier type="citekey">otto2017</identifier>
</mods>
Download

Full Metadata

Bibliographic Citation JVRB, 13(2016), no. 3.
Title

Presenting a Holistic Framework for Scalable, Marker-less Motion Capturing: Skeletal Tracking Performance Analysis, Sensor Fusion Algorithms and Usage in Automotive Industry (eng)
Author Michael M. Otto, Philipp Agethen, Florian Geiselhart, Michael Rietzler, Felix Gaisbauer, Enrico Rukzio
Language eng
Abstract Even though there is promising technological progress, input is currently still one of virtual reality's biggest issues. Off-the-shelf depth cameras have the potential to resolve these tracking problems. These sensors have become common in several application areas due to their availability and affordability. However, various applications in industry and research still require large-scale tracking systems e.g. for interaction with virtual environments. As single depth-cameras have limited performance in this context, we propose a novel set of methods for multiple depth-camera registration and heuristic-based sensor fusion using skeletal tracking. An in-depth accuracy analysis of Kinect v2 skeletal tracking is presented in which a robot moves a mannequin for accurate, reproducible motion paths. Based on the results of this evaluation, a distributed and service-oriented marker-less tracking system consisting of multiple Kinect v2 sensors is developed for real-time interaction with virtual environments. Evaluation shows that this approach helps in increasing tracking areas, resolving occlusions and improving human posture analysis. Additionally, an advanced error prediction model is proposed to further improve skeletal tracking results. The overall system is evaluated by using it for realistic ergonomic assessments in automotive production verification workshops. It is shown that performance and applicability of the system is suitable for the use in automotive industry and may replace conventional high-end marker-based systems partially in this domain.
Subject full-body motion capture, markerless, scalable, skeletal tracking
Classified Subjects
swd
  • 4311226-2, Tracking
  • 4546181-8, Motion Capturing
  • 4032690-1, Kraftfahrzeugindustrie
DDC 004
Rights DPPL
URN: urn:nbn:de:0009-6-44811
DOI https://doi.org/10.20385/1860-2037/13.2016.3