Gesture detection in low-quality video

Myung Cheol Roh; Seong Whan Lee

doi:10.1109/ICPR.2006.607

Gesture detection in low-quality video

Myung Cheol Roh, Seong Whan Lee

Department of Artificial Intelligence

Research output: Contribution to journal › Conference article › peer-review

1 Citation (Scopus)

Abstract

The spotting and recognition of the human gestures is a key task in automating the analysis of the video material and human-robot interaction. Specially, applying this technology to low-resolution video has many potential applications. The human area is small with respect to input video frames in broadcast sports video, surveillance video, etc. However, this condition makes the spotting certain gesture in a video sequence a challenging task, especially if there is large camera motion. To overcome the problems, we propose a posture matching method based on curvature scale space templates of the human silhouette. We also propose a new recognition method which is robust to noisy sequences of data.

Original language	English
Article number	1699959
Pages (from-to)	791-794
Number of pages	4
Journal	Proceedings - International Conference on Pattern Recognition
Volume	4
DOIs	https://doi.org/10.1109/ICPR.2006.607
Publication status	Published - 2006
Event	18th International Conference on Pattern Recognition, ICPR 2006 - Hong Kong, China Duration: 2006 Aug 20 → 2006 Aug 24

ASJC Scopus subject areas

Computer Vision and Pattern Recognition

Access to Document

10.1109/ICPR.2006.607

Cite this

@article{8c980870f0fe49dbb068686221d61572,

title = "Gesture detection in low-quality video",

abstract = "The spotting and recognition of the human gestures is a key task in automating the analysis of the video material and human-robot interaction. Specially, applying this technology to low-resolution video has many potential applications. The human area is small with respect to input video frames in broadcast sports video, surveillance video, etc. However, this condition makes the spotting certain gesture in a video sequence a challenging task, especially if there is large camera motion. To overcome the problems, we propose a posture matching method based on curvature scale space templates of the human silhouette. We also propose a new recognition method which is robust to noisy sequences of data.",

author = "Roh, {Myung Cheol} and Lee, {Seong Whan}",

year = "2006",

doi = "10.1109/ICPR.2006.607",

language = "English",

volume = "4",

pages = "791--794",

journal = "Proceedings - International Conference on Pattern Recognition",

issn = "1051-4651",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "18th International Conference on Pattern Recognition, ICPR 2006 ; Conference date: 20-08-2006 Through 24-08-2006",

}

TY - JOUR

T1 - Gesture detection in low-quality video

AU - Roh, Myung Cheol

AU - Lee, Seong Whan

PY - 2006

Y1 - 2006

N2 - The spotting and recognition of the human gestures is a key task in automating the analysis of the video material and human-robot interaction. Specially, applying this technology to low-resolution video has many potential applications. The human area is small with respect to input video frames in broadcast sports video, surveillance video, etc. However, this condition makes the spotting certain gesture in a video sequence a challenging task, especially if there is large camera motion. To overcome the problems, we propose a posture matching method based on curvature scale space templates of the human silhouette. We also propose a new recognition method which is robust to noisy sequences of data.

AB - The spotting and recognition of the human gestures is a key task in automating the analysis of the video material and human-robot interaction. Specially, applying this technology to low-resolution video has many potential applications. The human area is small with respect to input video frames in broadcast sports video, surveillance video, etc. However, this condition makes the spotting certain gesture in a video sequence a challenging task, especially if there is large camera motion. To overcome the problems, we propose a posture matching method based on curvature scale space templates of the human silhouette. We also propose a new recognition method which is robust to noisy sequences of data.

UR - http://www.scopus.com/inward/record.url?scp=34147132213&partnerID=8YFLogxK

U2 - 10.1109/ICPR.2006.607

DO - 10.1109/ICPR.2006.607

M3 - Conference article

AN - SCOPUS:34147132213

SN - 1051-4651

VL - 4

SP - 791

EP - 794

JO - Proceedings - International Conference on Pattern Recognition

JF - Proceedings - International Conference on Pattern Recognition

M1 - 1699959

T2 - 18th International Conference on Pattern Recognition, ICPR 2006

Y2 - 20 August 2006 through 24 August 2006

ER -

Gesture detection in low-quality video

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this