A stretch-sensing soft glove for interactive hand pose estimation

Oliver Glauser, Shihao Wu, Daniele Panozzo, Otmar Hilliges, Olga Sorkine-Hornung

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

Abstract

We present a stretch-sensing soft glove to interactively capture full hand poses with high accuracy and without requiring an external optical setup. Our device can be fabricated with simple tools available in most fabrication labs. The pose is reconstructed from a capacitive sensor array embedded in the glove. We propose a data representation that allows deep neural networks to exploit the spatial layout of the sensor itself. The network is trained only once, using an inexpensive off-the-shelf hand pose reconstruction system to gather the training data. The per-user calibration is then performed on-the-fly using only the glove.

Original languageEnglish (US)
Title of host publicationACM SIGGRAPH 2019 Emerging Technologies, SIGGRAPH 2019
PublisherAssociation for Computing Machinery, Inc
ISBN (Electronic)9781450363082
DOIs
StatePublished - Jul 28 2019
EventACM SIGGRAPH 2019 Emerging Technologies - International Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 2019 - Los Angeles, United States
Duration: Jul 28 2019 → …

Publication series

NameACM SIGGRAPH 2019 Emerging Technologies, SIGGRAPH 2019

Conference

ConferenceACM SIGGRAPH 2019 Emerging Technologies - International Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 2019
CountryUnited States
CityLos Angeles
Period7/28/19 → …

Fingerprint

Capacitive sensors
Sensor arrays
Calibration
Fabrication
Sensors
Deep neural networks

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Human-Computer Interaction

Cite this

Glauser, O., Wu, S., Panozzo, D., Hilliges, O., & Sorkine-Hornung, O. (2019). A stretch-sensing soft glove for interactive hand pose estimation. In ACM SIGGRAPH 2019 Emerging Technologies, SIGGRAPH 2019 (ACM SIGGRAPH 2019 Emerging Technologies, SIGGRAPH 2019). Association for Computing Machinery, Inc. https://doi.org/10.1145/3305367.3327975

A stretch-sensing soft glove for interactive hand pose estimation. / Glauser, Oliver; Wu, Shihao; Panozzo, Daniele; Hilliges, Otmar; Sorkine-Hornung, Olga.

ACM SIGGRAPH 2019 Emerging Technologies, SIGGRAPH 2019. Association for Computing Machinery, Inc, 2019. (ACM SIGGRAPH 2019 Emerging Technologies, SIGGRAPH 2019).

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

Glauser, O, Wu, S, Panozzo, D, Hilliges, O & Sorkine-Hornung, O 2019, A stretch-sensing soft glove for interactive hand pose estimation. in ACM SIGGRAPH 2019 Emerging Technologies, SIGGRAPH 2019. ACM SIGGRAPH 2019 Emerging Technologies, SIGGRAPH 2019, Association for Computing Machinery, Inc, ACM SIGGRAPH 2019 Emerging Technologies - International Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 2019, Los Angeles, United States, 7/28/19. https://doi.org/10.1145/3305367.3327975
Glauser O, Wu S, Panozzo D, Hilliges O, Sorkine-Hornung O. A stretch-sensing soft glove for interactive hand pose estimation. In ACM SIGGRAPH 2019 Emerging Technologies, SIGGRAPH 2019. Association for Computing Machinery, Inc. 2019. (ACM SIGGRAPH 2019 Emerging Technologies, SIGGRAPH 2019). https://doi.org/10.1145/3305367.3327975
Glauser, Oliver ; Wu, Shihao ; Panozzo, Daniele ; Hilliges, Otmar ; Sorkine-Hornung, Olga. / A stretch-sensing soft glove for interactive hand pose estimation. ACM SIGGRAPH 2019 Emerging Technologies, SIGGRAPH 2019. Association for Computing Machinery, Inc, 2019. (ACM SIGGRAPH 2019 Emerging Technologies, SIGGRAPH 2019).
@inproceedings{f40e8322151c46e2b163b9d1fe65b956,
title = "A stretch-sensing soft glove for interactive hand pose estimation",
abstract = "We present a stretch-sensing soft glove to interactively capture full hand poses with high accuracy and without requiring an external optical setup. Our device can be fabricated with simple tools available in most fabrication labs. The pose is reconstructed from a capacitive sensor array embedded in the glove. We propose a data representation that allows deep neural networks to exploit the spatial layout of the sensor itself. The network is trained only once, using an inexpensive off-the-shelf hand pose reconstruction system to gather the training data. The per-user calibration is then performed on-the-fly using only the glove.",
author = "Oliver Glauser and Shihao Wu and Daniele Panozzo and Otmar Hilliges and Olga Sorkine-Hornung",
year = "2019",
month = "7",
day = "28",
doi = "10.1145/3305367.3327975",
language = "English (US)",
series = "ACM SIGGRAPH 2019 Emerging Technologies, SIGGRAPH 2019",
publisher = "Association for Computing Machinery, Inc",
booktitle = "ACM SIGGRAPH 2019 Emerging Technologies, SIGGRAPH 2019",

}

TY - GEN

T1 - A stretch-sensing soft glove for interactive hand pose estimation

AU - Glauser, Oliver

AU - Wu, Shihao

AU - Panozzo, Daniele

AU - Hilliges, Otmar

AU - Sorkine-Hornung, Olga

PY - 2019/7/28

Y1 - 2019/7/28

N2 - We present a stretch-sensing soft glove to interactively capture full hand poses with high accuracy and without requiring an external optical setup. Our device can be fabricated with simple tools available in most fabrication labs. The pose is reconstructed from a capacitive sensor array embedded in the glove. We propose a data representation that allows deep neural networks to exploit the spatial layout of the sensor itself. The network is trained only once, using an inexpensive off-the-shelf hand pose reconstruction system to gather the training data. The per-user calibration is then performed on-the-fly using only the glove.

AB - We present a stretch-sensing soft glove to interactively capture full hand poses with high accuracy and without requiring an external optical setup. Our device can be fabricated with simple tools available in most fabrication labs. The pose is reconstructed from a capacitive sensor array embedded in the glove. We propose a data representation that allows deep neural networks to exploit the spatial layout of the sensor itself. The network is trained only once, using an inexpensive off-the-shelf hand pose reconstruction system to gather the training data. The per-user calibration is then performed on-the-fly using only the glove.

UR - http://www.scopus.com/inward/record.url?scp=85071278584&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85071278584&partnerID=8YFLogxK

U2 - 10.1145/3305367.3327975

DO - 10.1145/3305367.3327975

M3 - Conference contribution

AN - SCOPUS:85071278584

T3 - ACM SIGGRAPH 2019 Emerging Technologies, SIGGRAPH 2019

BT - ACM SIGGRAPH 2019 Emerging Technologies, SIGGRAPH 2019

PB - Association for Computing Machinery, Inc

ER -