Multiwave: Doppler Effect Based Gesture Recognition In Multiple Dimensions
Keywords
3D interaction; Doppler Effect; Gesture recognition; User studies
Abstract
We constructed an acoustic, gesture-based recognition system called Multiwave, which leverages the Doppler Effect to translate multidimensional movements into user interface commands. Our system only requires the use of two speakers and a microphone to be operational. Since these components are already built in to most end user systems, our design makes gesture-based input more accessible to a wider range of end users. By generating a known high frequency tone from multiple speakers and detecting movement using changes in the sound waves, we are able to calculate a Euclidean representation of hand velocity that is then used for more natural gesture recognition and thus, more meaningful interaction mappings. We present the results of a user study of Multiwave to evaluate recognition rates for different gestures and report accuracy rates comparable to or better than the current state of the art. We also report subjective user feedback and some lessons learned from our system that provide additional insight for future applications of multidimensional gesture recognition.
Publication Date
5-7-2016
Publication Title
Conference on Human Factors in Computing Systems - Proceedings
Volume
07-12-May-2016
Number of Pages
1729-1736
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1145/2851581.2892286
Copyright Status
Unknown
Socpus ID
85014689698 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/85014689698
STARS Citation
Pittman, Corey; Brooks, Conner; Wisniewski, Pamela; and Laviola, Joseph J., "Multiwave: Doppler Effect Based Gesture Recognition In Multiple Dimensions" (2016). Scopus Export 2015-2019. 4296.
https://stars.library.ucf.edu/scopus2015/4296