Identifying motion capture tracking markers with self-organizing maps

Matthias Weber, Hani Ben Amor, Thomas Alexander

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

Motion Capture (MoCap) describes methods and technologies for the detection and measurement of human motion in all its intricacies. Most systems use markers to track points on a body. Especially with natural human motion data captured with passive systems (to not hinder the participant) deficiencies like low accuracy of tracked points or even occluded markers might occur. Additionally, such MoCap data is often unlabeled. In consequence, the system does not provide information about which body landmarks the points belong to. Self-organizing neural networks, especially selforganizing maps (SOMs), are capable of dealing with such problems. This work describes a method to model, initialize and train such SOMs to track and label potentially noisy motion capture data.

Original languageEnglish (US)
Title of host publicationProceedings - IEEE Virtual Reality
Pages297-298
Number of pages2
DOIs
StatePublished - 2008
Externally publishedYes
EventIEEE Virtual Reality 2008, VR - Reno, NV, United States
Duration: Mar 8 2008Mar 12 2008

Other

OtherIEEE Virtual Reality 2008, VR
CountryUnited States
CityReno, NV
Period3/8/083/12/08

Fingerprint

Self organizing maps
Data acquisition
Labels
Neural networks

Keywords

  • Connectionism and neural nets
  • H. 1.2 [models and principles]: User/machine systems
  • Human information processing; 1.2.6 [artificial intelligence]: Learning

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Weber, M., Ben Amor, H., & Alexander, T. (2008). Identifying motion capture tracking markers with self-organizing maps. In Proceedings - IEEE Virtual Reality (pp. 297-298). [4480809] https://doi.org/10.1109/VR.2008.4480809

Identifying motion capture tracking markers with self-organizing maps. / Weber, Matthias; Ben Amor, Hani; Alexander, Thomas.

Proceedings - IEEE Virtual Reality. 2008. p. 297-298 4480809.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Weber, M, Ben Amor, H & Alexander, T 2008, Identifying motion capture tracking markers with self-organizing maps. in Proceedings - IEEE Virtual Reality., 4480809, pp. 297-298, IEEE Virtual Reality 2008, VR, Reno, NV, United States, 3/8/08. https://doi.org/10.1109/VR.2008.4480809
Weber M, Ben Amor H, Alexander T. Identifying motion capture tracking markers with self-organizing maps. In Proceedings - IEEE Virtual Reality. 2008. p. 297-298. 4480809 https://doi.org/10.1109/VR.2008.4480809
Weber, Matthias ; Ben Amor, Hani ; Alexander, Thomas. / Identifying motion capture tracking markers with self-organizing maps. Proceedings - IEEE Virtual Reality. 2008. pp. 297-298
@inproceedings{2251c4780f88409fa7c2c56ac596dbfd,
title = "Identifying motion capture tracking markers with self-organizing maps",
abstract = "Motion Capture (MoCap) describes methods and technologies for the detection and measurement of human motion in all its intricacies. Most systems use markers to track points on a body. Especially with natural human motion data captured with passive systems (to not hinder the participant) deficiencies like low accuracy of tracked points or even occluded markers might occur. Additionally, such MoCap data is often unlabeled. In consequence, the system does not provide information about which body landmarks the points belong to. Self-organizing neural networks, especially selforganizing maps (SOMs), are capable of dealing with such problems. This work describes a method to model, initialize and train such SOMs to track and label potentially noisy motion capture data.",
keywords = "Connectionism and neural nets, H. 1.2 [models and principles]: User/machine systems, Human information processing; 1.2.6 [artificial intelligence]: Learning",
author = "Matthias Weber and {Ben Amor}, Hani and Thomas Alexander",
year = "2008",
doi = "10.1109/VR.2008.4480809",
language = "English (US)",
isbn = "9781424419715",
pages = "297--298",
booktitle = "Proceedings - IEEE Virtual Reality",

}

TY - GEN

T1 - Identifying motion capture tracking markers with self-organizing maps

AU - Weber, Matthias

AU - Ben Amor, Hani

AU - Alexander, Thomas

PY - 2008

Y1 - 2008

N2 - Motion Capture (MoCap) describes methods and technologies for the detection and measurement of human motion in all its intricacies. Most systems use markers to track points on a body. Especially with natural human motion data captured with passive systems (to not hinder the participant) deficiencies like low accuracy of tracked points or even occluded markers might occur. Additionally, such MoCap data is often unlabeled. In consequence, the system does not provide information about which body landmarks the points belong to. Self-organizing neural networks, especially selforganizing maps (SOMs), are capable of dealing with such problems. This work describes a method to model, initialize and train such SOMs to track and label potentially noisy motion capture data.

AB - Motion Capture (MoCap) describes methods and technologies for the detection and measurement of human motion in all its intricacies. Most systems use markers to track points on a body. Especially with natural human motion data captured with passive systems (to not hinder the participant) deficiencies like low accuracy of tracked points or even occluded markers might occur. Additionally, such MoCap data is often unlabeled. In consequence, the system does not provide information about which body landmarks the points belong to. Self-organizing neural networks, especially selforganizing maps (SOMs), are capable of dealing with such problems. This work describes a method to model, initialize and train such SOMs to track and label potentially noisy motion capture data.

KW - Connectionism and neural nets

KW - H. 1.2 [models and principles]: User/machine systems

KW - Human information processing; 1.2.6 [artificial intelligence]: Learning

UR - http://www.scopus.com/inward/record.url?scp=50249144686&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=50249144686&partnerID=8YFLogxK

U2 - 10.1109/VR.2008.4480809

DO - 10.1109/VR.2008.4480809

M3 - Conference contribution

SN - 9781424419715

SP - 297

EP - 298

BT - Proceedings - IEEE Virtual Reality

ER -