View invariant gesture recognition using the CSEMSwissRanger SR-2 camera

Michael Boelstoft Holte; Thomas B. Moeslund; Preben Fihl

doi:10.1504/IJISTA.2008.021292

View invariant gesture recognition using the CSEMSwissRanger SR-2 camera

Michael Boelstoft Holte, Thomas B. Moeslund, Preben Fihl

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › peer review

16 Citationer (Scopus)

Abstract

This paper introduces the use of range information acquired by a CSEM SwissRanger SR-2 camera for view invariant recognition of one and two arms gestures. The range data enables motion detection and 3D representation of gestures. Motion is detected by double difference range images and filtered by a hysteresis bandpass filter. Gestures are represented by concatenating harmonic shape contexts over time. This representation allows for a view invariant matching of the gestures. The system is trained on gestures from one viewpoint and evaluated on gestures from other viewpoints. The results show a recognition rate of 93.75%.

Originalsprog	Engelsk
Tidsskrift	International Journal of Intelligent Systems Technologies and Applications
Vol/bind	5
Udgave nummer	3/4
Sider (fra-til)	295-303
Antal sider	13
ISSN	1740-8865
DOI	https://doi.org/10.1504/IJISTA.2008.021292
Status	Udgivet - 2008

Adgang til dokumentet

10.1504/IJISTA.2008.021292

AUB Link

Søg efter materialet i Aalborg Universitetsbiblioteks søgemaskine

Citationsformater

@article{b1405050af6611dda82d000ea68e967b,

title = "View invariant gesture recognition using the CSEMSwissRanger SR-2 camera",

abstract = "This paper introduces the use of range information acquired by a CSEM SwissRanger SR-2 camera for view invariant recognition of one and two arms gestures. The range data enables motion detection and 3D representation of gestures. Motion is detected by double difference range images and filtered by a hysteresis bandpass filter. Gestures are represented by concatenating harmonic shape contexts over time. This representation allows for a view invariant matching of the gestures. The system is trained on gestures from one viewpoint and evaluated on gestures from other viewpoints. The results show a recognition rate of 93.75%.",

author = "Holte, {Michael Boelstoft} and Moeslund, {Thomas B.} and Preben Fihl",

year = "2008",

doi = "10.1504/IJISTA.2008.021292",

language = "English",

volume = "5",

pages = "295--303",

journal = "International Journal of Intelligent Systems Technologies and Applications",

issn = "1740-8865",

publisher = "Inderscience Publishers",

number = "3/4",

}

TY - JOUR

T1 - View invariant gesture recognition using the CSEMSwissRanger SR-2 camera

AU - Holte, Michael Boelstoft

AU - Moeslund, Thomas B.

AU - Fihl, Preben

PY - 2008

Y1 - 2008

N2 - This paper introduces the use of range information acquired by a CSEM SwissRanger SR-2 camera for view invariant recognition of one and two arms gestures. The range data enables motion detection and 3D representation of gestures. Motion is detected by double difference range images and filtered by a hysteresis bandpass filter. Gestures are represented by concatenating harmonic shape contexts over time. This representation allows for a view invariant matching of the gestures. The system is trained on gestures from one viewpoint and evaluated on gestures from other viewpoints. The results show a recognition rate of 93.75%.

AB - This paper introduces the use of range information acquired by a CSEM SwissRanger SR-2 camera for view invariant recognition of one and two arms gestures. The range data enables motion detection and 3D representation of gestures. Motion is detected by double difference range images and filtered by a hysteresis bandpass filter. Gestures are represented by concatenating harmonic shape contexts over time. This representation allows for a view invariant matching of the gestures. The system is trained on gestures from one viewpoint and evaluated on gestures from other viewpoints. The results show a recognition rate of 93.75%.

U2 - 10.1504/IJISTA.2008.021292

DO - 10.1504/IJISTA.2008.021292

M3 - Journal article

SN - 1740-8865

VL - 5

SP - 295

EP - 303

JO - International Journal of Intelligent Systems Technologies and Applications

JF - International Journal of Intelligent Systems Technologies and Applications

IS - 3/4

ER -

View invariant gesture recognition using the CSEMSwissRanger SR-2 camera

Abstract

Adgang til dokumentet

AUB Link

Fingeraftryk

Citationsformater