View invariant gesture recognition using the CSEMSwissRanger SR-2 camera

Michael Boelstoft Holte, Thomas B. Moeslund, Preben Fihl

Research output: Contribution to journalJournal articleResearchpeer-review

16 Citations (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%.
Original languageEnglish
JournalInternational Journal of Intelligent Systems Technologies and Applications
Volume5
Issue number3/4
Pages (from-to)295-303
Number of pages13
ISSN1740-8865
DOIs
Publication statusPublished - 2008

Fingerprint

Dive into the research topics of 'View invariant gesture recognition using the CSEMSwissRanger SR-2 camera'. Together they form a unique fingerprint.

Cite this