Hand gesture segmentation in uncontrolled environments with partition matrix and a spotting scheme based on hidden conditional random fields

Yi Yao; Chang Tsun Li

doi:10.1109/ACPR.2013.153

Hand gesture segmentation in uncontrolled environments with partition matrix and a spotting scheme based on hidden conditional random fields

Yi Yao, Chang Tsun Li

Computing and Mathematics

Research output: Book chapter/Published conference paper › Conference paper › peer-review

5 Citations (Scopus)

Abstract

Hand gesture segmentation is the task of interpreting and spotting meaningful hand gestures from continuous hand gesture sequences with non-sign transitional hand movements. In real world scenarios, challenges from the unconstrained environments can largely affect the performance of gesture segmentation. In this paper, we propose a gesture spotting scheme which can detect and monitor all eligible hand candidates in the scene, and evaluate their movement trajectories with a novel method called Partition Matrix based on Hidden Conditional Random Fields. Our experimental results demonstrate that the proposed method can spot meaningful hand gestures from continuous gesture stream with 2-4 people randomly moving around in an uncontrolled background.

Original language	English
Title of host publication	Proceedings of 2013 2nd IAPR Asian Conference on Pattern Recognition (ACPR 2013)
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	842-846
Number of pages	5
DOIs	https://doi.org/10.1109/ACPR.2013.153
Publication status	Published - 2013
Event	2013 2nd IAPR Asian Conference on Pattern Recognition (ACPR 2013) - Loisir Hotel & SPA Tower Naha, Naha, Okinawa, Japan Duration: 05 Nov 2013 → 08 Nov 2013 http://www.am.sanken.osaka-u.ac.jp/ACPR2013/

Conference

Conference	2013 2nd IAPR Asian Conference on Pattern Recognition (ACPR 2013)
Country	Japan
City	Naha, Okinawa
Period	05/11/13 → 08/11/13
Internet address	http://www.am.sanken.osaka-u.ac.jp/ACPR2013/

Access to Document

10.1109/ACPR.2013.153

Fingerprint Dive into the research topics of 'Hand gesture segmentation in uncontrolled environments with partition matrix and a spotting scheme based on hidden conditional random fields'. Together they form a unique fingerprint.

Cite this

Yao, Y., & Li, C. T. (2013). Hand gesture segmentation in uncontrolled environments with partition matrix and a spotting scheme based on hidden conditional random fields. In Proceedings of 2013 2nd IAPR Asian Conference on Pattern Recognition (ACPR 2013) (pp. 842-846). [6778449] IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ACPR.2013.153

@inproceedings{2d13a8853066497f87ad4c8c1e6f6152,

title = "Hand gesture segmentation in uncontrolled environments with partition matrix and a spotting scheme based on hidden conditional random fields",

abstract = "Hand gesture segmentation is the task of interpreting and spotting meaningful hand gestures from continuous hand gesture sequences with non-sign transitional hand movements. In real world scenarios, challenges from the unconstrained environments can largely affect the performance of gesture segmentation. In this paper, we propose a gesture spotting scheme which can detect and monitor all eligible hand candidates in the scene, and evaluate their movement trajectories with a novel method called Partition Matrix based on Hidden Conditional Random Fields. Our experimental results demonstrate that the proposed method can spot meaningful hand gestures from continuous gesture stream with 2-4 people randomly moving around in an uncontrolled background.",

keywords = "Hand gesture spotting, Hidden Conditional Random Fields, Uncontrolled environments",

author = "Yi Yao and Li, {Chang Tsun}",

year = "2013",

doi = "10.1109/ACPR.2013.153",

language = "English",

pages = "842--846",

booktitle = "Proceedings of 2013 2nd IAPR Asian Conference on Pattern Recognition (ACPR 2013)",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States",

note = "2013 2nd IAPR Asian Conference on Pattern Recognition (ACPR 2013) ; Conference date: 05-11-2013 Through 08-11-2013",

url = "http://www.am.sanken.osaka-u.ac.jp/ACPR2013/",

}

Yao, Y & Li, CT 2013, Hand gesture segmentation in uncontrolled environments with partition matrix and a spotting scheme based on hidden conditional random fields. in Proceedings of 2013 2nd IAPR Asian Conference on Pattern Recognition (ACPR 2013)., 6778449, IEEE, Institute of Electrical and Electronics Engineers, pp. 842-846, 2013 2nd IAPR Asian Conference on Pattern Recognition (ACPR 2013), Naha, Okinawa, Japan, 05/11/13. https://doi.org/10.1109/ACPR.2013.153

Hand gesture segmentation in uncontrolled environments with partition matrix and a spotting scheme based on hidden conditional random fields. / Yao, Yi; Li, Chang Tsun.

Proceedings of 2013 2nd IAPR Asian Conference on Pattern Recognition (ACPR 2013). IEEE, Institute of Electrical and Electronics Engineers, 2013. p. 842-846 6778449.

Research output: Book chapter/Published conference paper › Conference paper › peer-review

TY - GEN

T1 - Hand gesture segmentation in uncontrolled environments with partition matrix and a spotting scheme based on hidden conditional random fields

AU - Yao, Yi

AU - Li, Chang Tsun

PY - 2013

Y1 - 2013

N2 - Hand gesture segmentation is the task of interpreting and spotting meaningful hand gestures from continuous hand gesture sequences with non-sign transitional hand movements. In real world scenarios, challenges from the unconstrained environments can largely affect the performance of gesture segmentation. In this paper, we propose a gesture spotting scheme which can detect and monitor all eligible hand candidates in the scene, and evaluate their movement trajectories with a novel method called Partition Matrix based on Hidden Conditional Random Fields. Our experimental results demonstrate that the proposed method can spot meaningful hand gestures from continuous gesture stream with 2-4 people randomly moving around in an uncontrolled background.

AB - Hand gesture segmentation is the task of interpreting and spotting meaningful hand gestures from continuous hand gesture sequences with non-sign transitional hand movements. In real world scenarios, challenges from the unconstrained environments can largely affect the performance of gesture segmentation. In this paper, we propose a gesture spotting scheme which can detect and monitor all eligible hand candidates in the scene, and evaluate their movement trajectories with a novel method called Partition Matrix based on Hidden Conditional Random Fields. Our experimental results demonstrate that the proposed method can spot meaningful hand gestures from continuous gesture stream with 2-4 people randomly moving around in an uncontrolled background.

KW - Hand gesture spotting

KW - Hidden Conditional Random Fields

KW - Uncontrolled environments

UR - http://www.scopus.com/inward/record.url?scp=84899070341&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84899070341&partnerID=8YFLogxK

U2 - 10.1109/ACPR.2013.153

DO - 10.1109/ACPR.2013.153

M3 - Conference paper

AN - SCOPUS:84899070341

SP - 842

EP - 846

BT - Proceedings of 2013 2nd IAPR Asian Conference on Pattern Recognition (ACPR 2013)

PB - IEEE, Institute of Electrical and Electronics Engineers

T2 - 2013 2nd IAPR Asian Conference on Pattern Recognition (ACPR 2013)

Y2 - 5 November 2013 through 8 November 2013

ER -