Haarlet-based hand gesture recognition for 3D interaction

Michael Van den Bergh, Frédéric Bosché, E Koller-Meier, Luc Van Gool

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper presents a system to manipulate 3D objectsor navigate through 3D models by detecting the gesturesand the movements of the hands of a user in front of a cameramounted on top of a screen. This paper more particularlyintroduces an improved skin color segmentation algorithmwhich combines an online and an offline model; anda Haarlet-based hand gesture recognition system, wherethe Haarlets are trained based on Average NeighborhoodMargin Maximization (ANMM). The result is a real-timemarker-less interaction system which is applied to two applications,one for manipulating 3D objects, and the otherfor navigating through a 3D model.
Original languageEnglish
Title of host publication2009 Workshop on Applications of Computer Vision (WACV)
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
ISBN (Print)978-1-4244-5497-6
DOIs
Publication statusPublished - 2 Feb 2010
Event2009 Workshop on Applications of Computer Vision - Snowbird, United States
Duration: 7 Dec 20098 Dec 2009

Workshop

Workshop2009 Workshop on Applications of Computer Vision
Abbreviated titleWACV
Country/TerritoryUnited States
CitySnowbird
Period7/12/098/12/09

Fingerprint

Dive into the research topics of 'Haarlet-based hand gesture recognition for 3D interaction'. Together they form a unique fingerprint.

Cite this