Hand gesture and on-body touch recognition by active acoustic sensing throughout the human body

Tomohiro Yokota; Tomoko Hashida

doi:10.1145/2984751.2985721

Hand gesture and on-body touch recognition by active acoustic sensing throughout the human body

Tomohiro Yokota, Tomoko Hashida

School of Fundamental Science and Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

7 Citations (Scopus)

Abstract

In this paper, we present a novel acoustic sensing technique that recognizes two convenient input actions: hand gestures and on-body touch. We achieved them by observing the fre-quency spectrum of the wave propagated in the body, around the periphery of the wrist. Our approach can recognize hand gestures and on-body touch concurrently in real-time and is expected to obtain rich input variations by combining them. We conducted a user study that showed classification accu-racy of 97%, 96%, and 97% for hand gestures, touches on the forearm, and touches on the back of the hand.

Original language	English
Title of host publication	UIST 2016 Adjunct - Proceedings of the 29th Annual Symposium on User Interface Software and Technology
Publisher	Association for Computing Machinery, Inc
Pages	113-115
Number of pages	3
ISBN (Electronic)	9781450345316
DOIs	https://doi.org/10.1145/2984751.2985721
Publication status	Published - 2016 Oct 16
Event	29th Annual Symposium on User Interface Software and Technology, UIST 2016 - Tokyo, Japan Duration: 2016 Oct 16 → 2016 Oct 19

Publication series

Name	UIST 2016 Adjunct - Proceedings of the 29th Annual Symposium on User Interface Software and Technology

Other

Other	29th Annual Symposium on User Interface Software and Technology, UIST 2016
Country/Territory	Japan
City	Tokyo
Period	16/10/16 → 16/10/19

Keywords

Acoustic sensing
Combined input
Hand gestures
Machine learning
On-body touch

ASJC Scopus subject areas

Software
Human-Computer Interaction

Access to Document

10.1145/2984751.2985721

Cite this

Yokota, T., & Hashida, T. (2016). Hand gesture and on-body touch recognition by active acoustic sensing throughout the human body. In UIST 2016 Adjunct - Proceedings of the 29th Annual Symposium on User Interface Software and Technology (pp. 113-115). (UIST 2016 Adjunct - Proceedings of the 29th Annual Symposium on User Interface Software and Technology). Association for Computing Machinery, Inc. https://doi.org/10.1145/2984751.2985721

Hand gesture and on-body touch recognition by active acoustic sensing throughout the human body. / Yokota, Tomohiro; Hashida, Tomoko.

UIST 2016 Adjunct - Proceedings of the 29th Annual Symposium on User Interface Software and Technology. Association for Computing Machinery, Inc, 2016. p. 113-115 (UIST 2016 Adjunct - Proceedings of the 29th Annual Symposium on User Interface Software and Technology).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Yokota, T & Hashida, T 2016, Hand gesture and on-body touch recognition by active acoustic sensing throughout the human body. in UIST 2016 Adjunct - Proceedings of the 29th Annual Symposium on User Interface Software and Technology. UIST 2016 Adjunct - Proceedings of the 29th Annual Symposium on User Interface Software and Technology, Association for Computing Machinery, Inc, pp. 113-115, 29th Annual Symposium on User Interface Software and Technology, UIST 2016, Tokyo, Japan, 16/10/16. https://doi.org/10.1145/2984751.2985721

Yokota T, Hashida T. Hand gesture and on-body touch recognition by active acoustic sensing throughout the human body. In UIST 2016 Adjunct - Proceedings of the 29th Annual Symposium on User Interface Software and Technology. Association for Computing Machinery, Inc. 2016. p. 113-115. (UIST 2016 Adjunct - Proceedings of the 29th Annual Symposium on User Interface Software and Technology). doi: 10.1145/2984751.2985721

Yokota, Tomohiro ; Hashida, Tomoko. / Hand gesture and on-body touch recognition by active acoustic sensing throughout the human body. UIST 2016 Adjunct - Proceedings of the 29th Annual Symposium on User Interface Software and Technology. Association for Computing Machinery, Inc, 2016. pp. 113-115 (UIST 2016 Adjunct - Proceedings of the 29th Annual Symposium on User Interface Software and Technology).

@inproceedings{f976fc1bdede4c76befe4033f8399fb1,

title = "Hand gesture and on-body touch recognition by active acoustic sensing throughout the human body",

abstract = "In this paper, we present a novel acoustic sensing technique that recognizes two convenient input actions: hand gestures and on-body touch. We achieved them by observing the fre-quency spectrum of the wave propagated in the body, around the periphery of the wrist. Our approach can recognize hand gestures and on-body touch concurrently in real-time and is expected to obtain rich input variations by combining them. We conducted a user study that showed classification accu-racy of 97%, 96%, and 97% for hand gestures, touches on the forearm, and touches on the back of the hand.",

keywords = "Acoustic sensing, Combined input, Hand gestures, Machine learning, On-body touch",

author = "Tomohiro Yokota and Tomoko Hashida",

note = "Publisher Copyright: {\textcopyright} 2016 Copyright held by the author/owner(s). Copyright: Copyright 2017 Elsevier B.V., All rights reserved.; 29th Annual Symposium on User Interface Software and Technology, UIST 2016 ; Conference date: 16-10-2016 Through 19-10-2016",

year = "2016",

month = oct,

day = "16",

doi = "10.1145/2984751.2985721",

language = "English",

series = "UIST 2016 Adjunct - Proceedings of the 29th Annual Symposium on User Interface Software and Technology",

publisher = "Association for Computing Machinery, Inc",

pages = "113--115",

booktitle = "UIST 2016 Adjunct - Proceedings of the 29th Annual Symposium on User Interface Software and Technology",

}

TY - GEN

T1 - Hand gesture and on-body touch recognition by active acoustic sensing throughout the human body

AU - Yokota, Tomohiro

AU - Hashida, Tomoko

PY - 2016/10/16

Y1 - 2016/10/16

N2 - In this paper, we present a novel acoustic sensing technique that recognizes two convenient input actions: hand gestures and on-body touch. We achieved them by observing the fre-quency spectrum of the wave propagated in the body, around the periphery of the wrist. Our approach can recognize hand gestures and on-body touch concurrently in real-time and is expected to obtain rich input variations by combining them. We conducted a user study that showed classification accu-racy of 97%, 96%, and 97% for hand gestures, touches on the forearm, and touches on the back of the hand.

AB - In this paper, we present a novel acoustic sensing technique that recognizes two convenient input actions: hand gestures and on-body touch. We achieved them by observing the fre-quency spectrum of the wave propagated in the body, around the periphery of the wrist. Our approach can recognize hand gestures and on-body touch concurrently in real-time and is expected to obtain rich input variations by combining them. We conducted a user study that showed classification accu-racy of 97%, 96%, and 97% for hand gestures, touches on the forearm, and touches on the back of the hand.

KW - Acoustic sensing

KW - Combined input

KW - Hand gestures

KW - Machine learning

KW - On-body touch

UR - http://www.scopus.com/inward/record.url?scp=84995579308&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84995579308&partnerID=8YFLogxK

U2 - 10.1145/2984751.2985721

DO - 10.1145/2984751.2985721

M3 - Conference contribution

AN - SCOPUS:84995579308

T3 - UIST 2016 Adjunct - Proceedings of the 29th Annual Symposium on User Interface Software and Technology

SP - 113

EP - 115

BT - UIST 2016 Adjunct - Proceedings of the 29th Annual Symposium on User Interface Software and Technology

PB - Association for Computing Machinery, Inc

T2 - 29th Annual Symposium on User Interface Software and Technology, UIST 2016

Y2 - 16 October 2016 through 19 October 2016

ER -

Hand gesture and on-body touch recognition by active acoustic sensing throughout the human body

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this