Gesture-Controlled User Input to Complete Questionnaires on Wrist-Worn Watches

Authors:
Oliver Amft;Roman Amstutz;Asim Smailagic;Dan Siewiorek;Gerhard Tröster
Affiliations:
Wearable Computing Lab., ETH Zurich, Zurich, Switzerland CH-8092 and Signal Processing Systems, TU Einhoven, Einhoven, The Netherlands 5600 MB;Wearable Computing Lab., ETH Zurich, Zurich, Switzerland CH-8092 and Carnegie Mellon University, Pittsburgh, USA PA 15213;Carnegie Mellon University, Pittsburgh, USA PA 15213;Carnegie Mellon University, Pittsburgh, USA PA 15213;Wearable Computing Lab., ETH Zurich, Zurich, Switzerland CH-8092
Venue:
Proceedings of the 13th International Conference on Human-Computer Interaction. Part II: Novel Interaction Methods and Techniques
Year:
2009

Citing 9
Cited 2

Gesture spotting from continuous hand motion

Pattern Recognition Letters
Recognition of Visual Activities and Interactions by Stochastic Parsing

IEEE Transactions on Pattern Analysis and Machine Intelligence
An HMM-Based Approach for Gesture Segmentation and Recognition

ICPR '00 Proceedings of the International Conference on Pattern Recognition - Volume 3
Loser: a dog named spot

IEEE Spectrum
Documenting Motion Sequences with a Personalized Annotation System

IEEE MultiMedia
eWatch: A Wearable Sensor and Notification Platform

BSN '06 Proceedings of the International Workshop on Wearable and Implantable Body Sensor Networks
Gesture spotting with body-worn inertial sensors to detect user activities

Pattern Recognition
Gesture recognition with a Wii controller

Proceedings of the 2nd international conference on Tangible and embedded interaction
Gesture Recognition: A Survey

IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews

Promesses et contraintes de la joaillerie numérique interactive: un aperçu de l'état de l'art

23rd French Speaking Conference on Human-Computer Interaction
Airwriting: a wearable handwriting recognition system

Personal and Ubiquitous Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

The aim of this work was to investigate arm gestures as an alternative input modality for wrist-worn watches. In particular we implemented a gesture recognition system and questionnaire interface into a watch prototype. We analyzed the wearer's effort and learning performance to use the gesture interface and compared their performance to a classical button-based solution. Moreover we evaluated the system performance to spot wearer gestures and the system responsiveness. Our wearer study showed that the watch achieved a recognition accuracy of more than 90%. Completion times showed a clear decrease from 3 min in the first repetition to 1 min, 49 sec in the last one. Similarly, variance of completion times between wearers decreased during repetitions. Completion time using the button interface was 36 sec. Ratings of physical and concentration effort decreased during the study. Our results confirm that wearer training state is rather reflected in completion time than recognition performance.