Real-time gesture recognition with minimal training requirements and on-line learning

Stjepan Rajko; Gang Qian; Todd Ingalls; Jodi James

doi:10.1109/CVPR.2007.383330

Real-time gesture recognition with minimal training requirements and on-line learning

Stjepan Rajko, Gang Qian, Todd Ingalls, Jodi James

Arts, Media and Engineering, School of (AME)

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

41 Scopus citations

Abstract

In this paper, we introduce the semantic network model (SNM), a generalization of the hidden Markov model (HMM) that uses factorization of state transition probabilities to reduce training requirements, increase the efficiency of gesture recognition and on-line learning, and allow more precision in gesture modeling. We demonstrate the advantages both formally and experimentally, using examples such as full-body multimodal gesture recognition via optical motion capture and a pressure sensitive floor, as well as mouse / pen gesture recognition. Our results show that our algorithm performs much better than the traditional approach in situations where training samples are limited and/or the precision of the gesture model is high.

Original language	English (US)
Title of host publication	2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR'07
DOIs	https://doi.org/10.1109/CVPR.2007.383330
State	Published - Oct 11 2007
Event	2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR'07 - Minneapolis, MN, United States Duration: Jun 17 2007 → Jun 22 2007

Publication series

Name	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

Other

Other	2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR'07
Country/Territory	United States
City	Minneapolis, MN
Period	6/17/07 → 6/22/07

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition

Access to Document

10.1109/CVPR.2007.383330

Cite this

Rajko, S., Qian, G., Ingalls, T., & James, J. (2007). Real-time gesture recognition with minimal training requirements and on-line learning. In 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR'07 Article 4270328 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). https://doi.org/10.1109/CVPR.2007.383330

Real-time gesture recognition with minimal training requirements and on-line learning. / Rajko, Stjepan; Qian, Gang; Ingalls, Todd et al.
2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR'07. 2007. 4270328 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Rajko, S, Qian, G, Ingalls, T & James, J 2007, Real-time gesture recognition with minimal training requirements and on-line learning. in 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR'07., 4270328, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR'07, Minneapolis, MN, United States, 6/17/07. https://doi.org/10.1109/CVPR.2007.383330

@inproceedings{48156d23c1754b17a88b8cd08c1d04f4,

title = "Real-time gesture recognition with minimal training requirements and on-line learning",

abstract = "In this paper, we introduce the semantic network model (SNM), a generalization of the hidden Markov model (HMM) that uses factorization of state transition probabilities to reduce training requirements, increase the efficiency of gesture recognition and on-line learning, and allow more precision in gesture modeling. We demonstrate the advantages both formally and experimentally, using examples such as full-body multimodal gesture recognition via optical motion capture and a pressure sensitive floor, as well as mouse / pen gesture recognition. Our results show that our algorithm performs much better than the traditional approach in situations where training samples are limited and/or the precision of the gesture model is high.",

author = "Stjepan Rajko and Gang Qian and Todd Ingalls and Jodi James",

year = "2007",

month = oct,

day = "11",

doi = "10.1109/CVPR.2007.383330",

language = "English (US)",

isbn = "1424411807",

series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

booktitle = "2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR'07",

note = "2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR'07 ; Conference date: 17-06-2007 Through 22-06-2007",

}

TY - GEN

T1 - Real-time gesture recognition with minimal training requirements and on-line learning

AU - Rajko, Stjepan

AU - Qian, Gang

AU - Ingalls, Todd

AU - James, Jodi

PY - 2007/10/11

Y1 - 2007/10/11

N2 - In this paper, we introduce the semantic network model (SNM), a generalization of the hidden Markov model (HMM) that uses factorization of state transition probabilities to reduce training requirements, increase the efficiency of gesture recognition and on-line learning, and allow more precision in gesture modeling. We demonstrate the advantages both formally and experimentally, using examples such as full-body multimodal gesture recognition via optical motion capture and a pressure sensitive floor, as well as mouse / pen gesture recognition. Our results show that our algorithm performs much better than the traditional approach in situations where training samples are limited and/or the precision of the gesture model is high.

AB - In this paper, we introduce the semantic network model (SNM), a generalization of the hidden Markov model (HMM) that uses factorization of state transition probabilities to reduce training requirements, increase the efficiency of gesture recognition and on-line learning, and allow more precision in gesture modeling. We demonstrate the advantages both formally and experimentally, using examples such as full-body multimodal gesture recognition via optical motion capture and a pressure sensitive floor, as well as mouse / pen gesture recognition. Our results show that our algorithm performs much better than the traditional approach in situations where training samples are limited and/or the precision of the gesture model is high.

UR - http://www.scopus.com/inward/record.url?scp=34948815099&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34948815099&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2007.383330

DO - 10.1109/CVPR.2007.383330

M3 - Conference contribution

SN - 1424411807

SN - 9781424411801

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

BT - 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR'07

T2 - 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR'07

Y2 - 17 June 2007 through 22 June 2007

ER -

Real-time gesture recognition with minimal training requirements and on-line learning

Abstract

Publication series

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this