Static and dynamic hand-gesture recognition for augmented reality applications

Authors:
Stefan Reifinger;Frank Wallhoff;Markus Ablassmeier;Tony Poitschke;Gerhard Rigoll
Affiliations:
Technische Universität München, Institute for Man Machine Communication, Munich, Germany;Technische Universität München, Institute for Man Machine Communication, Munich, Germany;Technische Universität München, Institute for Man Machine Communication, Munich, Germany;Technische Universität München, Institute for Man Machine Communication, Munich, Germany;Technische Universität München, Institute for Man Machine Communication, Munich, Germany
Venue:
HCI'07 Proceedings of the 12th international conference on Human-computer interaction: intelligent multimodal interaction environments
Year:
2007

Citing 2
Cited 7

Mutual disambiguation of 3D multimodal interaction in augmented and virtual reality

Proceedings of the 5th international conference on Multimodal interfaces
FingARtips: gesture based direct manipulation in Augmented Reality

Proceedings of the 2nd international conference on Computer graphics and interactive techniques in Australasia and South East Asia

Real-time framework for multimodal human-robot interaction

HSI'09 Proceedings of the 2nd conference on Human System Interactions
Multimodal data communication for human-robot interactions

ICME'09 Proceedings of the 2009 IEEE international conference on Multimedia and Expo
On the use of graph parsing for recognition of isolated hand postures of Polish Sign Language

Pattern Recognition
A gestural approach to presentation exploiting motion capture metaphors

Proceedings of the International Working Conference on Advanced Visual Interfaces
Free-hands interaction in augmented reality

Proceedings of the 1st symposium on Spatial user interaction
A survey on ontologies for human behavior recognition

ACM Computing Surveys (CSUR)
One-shot learning gesture recognition from RGB-D data using bag of features

The Journal of Machine Learning Research

Quantified Score

Hi-index	0.00

Visualization

Abstract

This contribution presents our approach for an instrumented automatic gesture recognition system for use in Augmented Reality, which is able to differentiate static and dynamic gestures. Basing on an infrared tracking system, infrared targets mounted at the users thumbs and index fingers are used to retrieve information about position and orientation of each finger. Our system receives this information and extracts static gestures by distance classifiers and dynamic gestures by statistical models. The concluded gesture is provided to any connected application. We introduce a small demonstration as basis for a short evaluation. In this we compare interaction in a real environment, Augmented Reality with a mouse/keyboard, and our gesture recognition system concerning properties, such as task execution time or intuitiveness of interaction. The results show that tasks executed by interaction with our gesture recognition system are faster than using the mouse/keyboard. However, this enhancement entails a slightly lowered wearing comfort.