View Invariant Gesture Recognition using 3D Motion Primitives

Research output: Contribution to journalConference article in JournalResearchpeer-review

21 Citations (Scopus)

Abstract

This paper presents a method for automatic recognition of human gestures. The method works with 3D image data from a range camera to achieve invariance to viewpoint. The recognition is based solely on motion from characteristic instances of the gestures. These instances are denoted 3D motion primitives. The method extracts 3D motion from range images and represent the motion from each input frame in a view invariant manner using harmonic shape context. The harmonic shape context is classified as a 3D motion primitive. A sequence of input frames results in a set of primitives that are classified as a gesture using a probabilistic edit distance method. The system has been trained on frontal images (0deg camera rotation) and tested on 240 video sequences from 0deg and 45deg. An overall recognition rate of 82.9% is achieved. The recognition rate is independent of the viewpoint which shows that the method is indeed view invariant.
Original languageEnglish
JournalProceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing
Pages (from-to)797-800
ISSN1520-6149
DOIs
Publication statusPublished - 2008
EventIEEE International Conference on Acoustics, Speech, and Signal Processing - Las Vegas, United States
Duration: 31 Mar 20084 Apr 2008

Conference

ConferenceIEEE International Conference on Acoustics, Speech, and Signal Processing
CountryUnited States
CityLas Vegas
Period31/03/200804/04/2008

Cite this

@inproceedings{738ed5c06ad211dd92a2000ea68e967b,
title = "View Invariant Gesture Recognition using 3D Motion Primitives",
abstract = "This paper presents a method for automatic recognition of human gestures. The method works with 3D image data from a range camera to achieve invariance to viewpoint. The recognition is based solely on motion from characteristic instances of the gestures. These instances are denoted 3D motion primitives. The method extracts 3D motion from range images and represent the motion from each input frame in a view invariant manner using harmonic shape context. The harmonic shape context is classified as a 3D motion primitive. A sequence of input frames results in a set of primitives that are classified as a gesture using a probabilistic edit distance method. The system has been trained on frontal images (0deg camera rotation) and tested on 240 video sequences from 0deg and 45deg. An overall recognition rate of 82.9{\%} is achieved. The recognition rate is independent of the viewpoint which shows that the method is indeed view invariant.",
author = "Holte, {Michael Boelstoft} and Moeslund, {Thomas B.}",
year = "2008",
doi = "10.1109/ICASSP.2008.4517730",
language = "English",
pages = "797--800",
journal = "I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings",
issn = "1520-6149",
publisher = "IEEE Signal Processing Society",

}

TY - GEN

T1 - View Invariant Gesture Recognition using 3D Motion Primitives

AU - Holte, Michael Boelstoft

AU - Moeslund, Thomas B.

PY - 2008

Y1 - 2008

N2 - This paper presents a method for automatic recognition of human gestures. The method works with 3D image data from a range camera to achieve invariance to viewpoint. The recognition is based solely on motion from characteristic instances of the gestures. These instances are denoted 3D motion primitives. The method extracts 3D motion from range images and represent the motion from each input frame in a view invariant manner using harmonic shape context. The harmonic shape context is classified as a 3D motion primitive. A sequence of input frames results in a set of primitives that are classified as a gesture using a probabilistic edit distance method. The system has been trained on frontal images (0deg camera rotation) and tested on 240 video sequences from 0deg and 45deg. An overall recognition rate of 82.9% is achieved. The recognition rate is independent of the viewpoint which shows that the method is indeed view invariant.

AB - This paper presents a method for automatic recognition of human gestures. The method works with 3D image data from a range camera to achieve invariance to viewpoint. The recognition is based solely on motion from characteristic instances of the gestures. These instances are denoted 3D motion primitives. The method extracts 3D motion from range images and represent the motion from each input frame in a view invariant manner using harmonic shape context. The harmonic shape context is classified as a 3D motion primitive. A sequence of input frames results in a set of primitives that are classified as a gesture using a probabilistic edit distance method. The system has been trained on frontal images (0deg camera rotation) and tested on 240 video sequences from 0deg and 45deg. An overall recognition rate of 82.9% is achieved. The recognition rate is independent of the viewpoint which shows that the method is indeed view invariant.

U2 - 10.1109/ICASSP.2008.4517730

DO - 10.1109/ICASSP.2008.4517730

M3 - Conference article in Journal

SP - 797

EP - 800

JO - I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings

JF - I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings

SN - 1520-6149

ER -