3D Gesture recognition: an evaluation of user and system performance

Michael Wright, Chun-Jung Lin, Eamonn O'Neill, Darren Cosker, Peter Johnson

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

13 Citations (Scopus)
105 Downloads (Pure)

Abstract

We report a series of empirical studies investigating gesture as an interaction technique in pervasive computing. In our first study, participants generated gestures for given tasks and from these we identified archetypal common gestures. Furthermore, we discovered that many of these user-generated gestures were performed in 3D. We implemented a computer vision based 3D gesture recognition system and applied it in a further study in which participants used the common gestures generated in the first study. We investigated the trade off between system performance and human performance and preferences, deriving design recommendations. We achieved 84% recognition accuracy by our prototype 3D gesture recognition system after tuning it through the use of simple heuristics. The most popular gestures from Study 1 were regarded by participants in Study 2 as best matching the task they represented, and they produced the fewest recall errors.
Original languageEnglish
Title of host publicationPervasive Computing - 9th International Conference, Pervasive 2011, San Francisco, USA, June 12-15, 2011. Proceedings
EditorsK Lyons, J Hightower, E M Huang
Place of PublicationBerlin
PublisherSpringer
Pages294-313
Number of pages20
ISBN (Electronic)9783642217265
ISBN (Print)9783642217258
DOIs
Publication statusPublished - 2011
Event9th International Conference on Pervasive Computing, Pervasive 2011, June 12, 2011 - June 15, 2011 - San Francisco, CA, USA United States
Duration: 1 Jun 2011 → …

Publication series

NameLecture Notes in Computer Science
Volume6696
ISSN (Print)0302-9743

Conference

Conference9th International Conference on Pervasive Computing, Pervasive 2011, June 12, 2011 - June 15, 2011
CountryUSA United States
CitySan Francisco, CA
Period1/06/11 → …

Fingerprint

Gesture recognition
Ubiquitous computing
Computer vision
Tuning

Cite this

Wright, M., Lin, C-J., O'Neill, E., Cosker, D., & Johnson, P. (2011). 3D Gesture recognition: an evaluation of user and system performance. In K. Lyons, J. Hightower, & E. M. Huang (Eds.), Pervasive Computing - 9th International Conference, Pervasive 2011, San Francisco, USA, June 12-15, 2011. Proceedings (pp. 294-313). (Lecture Notes in Computer Science; Vol. 6696). Berlin: Springer. https://doi.org/10.1007/978-3-642-21726-5_19

3D Gesture recognition: an evaluation of user and system performance. / Wright, Michael; Lin, Chun-Jung; O'Neill, Eamonn; Cosker, Darren; Johnson, Peter.

Pervasive Computing - 9th International Conference, Pervasive 2011, San Francisco, USA, June 12-15, 2011. Proceedings. ed. / K Lyons; J Hightower; E M Huang. Berlin : Springer, 2011. p. 294-313 (Lecture Notes in Computer Science; Vol. 6696).

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

Wright, M, Lin, C-J, O'Neill, E, Cosker, D & Johnson, P 2011, 3D Gesture recognition: an evaluation of user and system performance. in K Lyons, J Hightower & EM Huang (eds), Pervasive Computing - 9th International Conference, Pervasive 2011, San Francisco, USA, June 12-15, 2011. Proceedings. Lecture Notes in Computer Science, vol. 6696, Springer, Berlin, pp. 294-313, 9th International Conference on Pervasive Computing, Pervasive 2011, June 12, 2011 - June 15, 2011, San Francisco, CA, USA United States, 1/06/11. https://doi.org/10.1007/978-3-642-21726-5_19
Wright M, Lin C-J, O'Neill E, Cosker D, Johnson P. 3D Gesture recognition: an evaluation of user and system performance. In Lyons K, Hightower J, Huang EM, editors, Pervasive Computing - 9th International Conference, Pervasive 2011, San Francisco, USA, June 12-15, 2011. Proceedings. Berlin: Springer. 2011. p. 294-313. (Lecture Notes in Computer Science). https://doi.org/10.1007/978-3-642-21726-5_19
Wright, Michael ; Lin, Chun-Jung ; O'Neill, Eamonn ; Cosker, Darren ; Johnson, Peter. / 3D Gesture recognition: an evaluation of user and system performance. Pervasive Computing - 9th International Conference, Pervasive 2011, San Francisco, USA, June 12-15, 2011. Proceedings. editor / K Lyons ; J Hightower ; E M Huang. Berlin : Springer, 2011. pp. 294-313 (Lecture Notes in Computer Science).
@inproceedings{23fbc32a8faa4cfab8fd7847a21d4397,
title = "3D Gesture recognition: an evaluation of user and system performance",
abstract = "We report a series of empirical studies investigating gesture as an interaction technique in pervasive computing. In our first study, participants generated gestures for given tasks and from these we identified archetypal common gestures. Furthermore, we discovered that many of these user-generated gestures were performed in 3D. We implemented a computer vision based 3D gesture recognition system and applied it in a further study in which participants used the common gestures generated in the first study. We investigated the trade off between system performance and human performance and preferences, deriving design recommendations. We achieved 84{\%} recognition accuracy by our prototype 3D gesture recognition system after tuning it through the use of simple heuristics. The most popular gestures from Study 1 were regarded by participants in Study 2 as best matching the task they represented, and they produced the fewest recall errors.",
author = "Michael Wright and Chun-Jung Lin and Eamonn O'Neill and Darren Cosker and Peter Johnson",
note = "Conference paper from the 9th International Conference on Pervasive Computing, Pervasive 2011. 12-15 June 2011. San Francisco, CA, United States.",
year = "2011",
doi = "10.1007/978-3-642-21726-5_19",
language = "English",
isbn = "9783642217258",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "294--313",
editor = "K Lyons and J Hightower and Huang, {E M}",
booktitle = "Pervasive Computing - 9th International Conference, Pervasive 2011, San Francisco, USA, June 12-15, 2011. Proceedings",

}

TY - GEN

T1 - 3D Gesture recognition: an evaluation of user and system performance

AU - Wright, Michael

AU - Lin, Chun-Jung

AU - O'Neill, Eamonn

AU - Cosker, Darren

AU - Johnson, Peter

N1 - Conference paper from the 9th International Conference on Pervasive Computing, Pervasive 2011. 12-15 June 2011. San Francisco, CA, United States.

PY - 2011

Y1 - 2011

N2 - We report a series of empirical studies investigating gesture as an interaction technique in pervasive computing. In our first study, participants generated gestures for given tasks and from these we identified archetypal common gestures. Furthermore, we discovered that many of these user-generated gestures were performed in 3D. We implemented a computer vision based 3D gesture recognition system and applied it in a further study in which participants used the common gestures generated in the first study. We investigated the trade off between system performance and human performance and preferences, deriving design recommendations. We achieved 84% recognition accuracy by our prototype 3D gesture recognition system after tuning it through the use of simple heuristics. The most popular gestures from Study 1 were regarded by participants in Study 2 as best matching the task they represented, and they produced the fewest recall errors.

AB - We report a series of empirical studies investigating gesture as an interaction technique in pervasive computing. In our first study, participants generated gestures for given tasks and from these we identified archetypal common gestures. Furthermore, we discovered that many of these user-generated gestures were performed in 3D. We implemented a computer vision based 3D gesture recognition system and applied it in a further study in which participants used the common gestures generated in the first study. We investigated the trade off between system performance and human performance and preferences, deriving design recommendations. We achieved 84% recognition accuracy by our prototype 3D gesture recognition system after tuning it through the use of simple heuristics. The most popular gestures from Study 1 were regarded by participants in Study 2 as best matching the task they represented, and they produced the fewest recall errors.

UR - http://www.scopus.com/inward/record.url?scp=79958828841&partnerID=8YFLogxK

UR - http://dx.doi.org/10.1007/978-3-642-21726-5_19

U2 - 10.1007/978-3-642-21726-5_19

DO - 10.1007/978-3-642-21726-5_19

M3 - Conference contribution

SN - 9783642217258

T3 - Lecture Notes in Computer Science

SP - 294

EP - 313

BT - Pervasive Computing - 9th International Conference, Pervasive 2011, San Francisco, USA, June 12-15, 2011. Proceedings

A2 - Lyons, K

A2 - Hightower, J

A2 - Huang, E M

PB - Springer

CY - Berlin

ER -