Combining Acceleration and Gyroscope Data for Motion Gesture Recognition using Classifiers with Dimensionality Constraints

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Authors

  • Sven Kratz
  • Michael Rohs
  • Georg Essl

External Research Organisations

  • University of Michigan
  • FXPAL
View graph of relations

Details

Original languageEnglish
Title of host publicationIUI '13
Subtitle of host publicationProceedings of the 2013 international conference on Intelligent user interfaces
Pages173-177
Number of pages5
ISBN (electronic)9781450319652
Publication statusPublished - 19 Mar 2013
Event18th International Conference on Intelligent User Interfaces, IUI 2013 - Santa Monica, CA, United States
Duration: 19 Mar 201322 Mar 2013

Abstract

Motivated by the addition of gyroscopes to a large number of new smart phones, we study the effects of combining ac-celerometer and gyroscope data on the recognition rate of motion gesture recognizers with dimensionality constraints. Using a large data set of motion gestures we analyze results for the following algorithms: Protractor3D, Dynamic Time Warping (DTW) and Regularized Logistic Regression (LR). We chose to study these algorithms because they are relatively easy to implement, thus well suited for rapid prototyping or early deployment during prototyping stages. For use in our analysis, we contribute a method to extend Protractor3D to work with the 6D data obtained by combining accelerometer and gyroscope data. Our results show that combining accelerometer and gyroscope data is beneficial also for algorithms with dimensionality constraints and improves the gesture recognition rate on our data set by up to 4%.

Keywords

    Accelerometer, Gesture recognition, Gyroscope, Mobile, Motion gestures, Sensor fusion

ASJC Scopus subject areas

Cite this

Combining Acceleration and Gyroscope Data for Motion Gesture Recognition using Classifiers with Dimensionality Constraints. / Kratz, Sven; Rohs, Michael; Essl, Georg.
IUI '13: Proceedings of the 2013 international conference on Intelligent user interfaces. 2013. p. 173-177.

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Kratz, S, Rohs, M & Essl, G 2013, Combining Acceleration and Gyroscope Data for Motion Gesture Recognition using Classifiers with Dimensionality Constraints. in IUI '13: Proceedings of the 2013 international conference on Intelligent user interfaces. pp. 173-177, 18th International Conference on Intelligent User Interfaces, IUI 2013, Santa Monica, CA, United States, 19 Mar 2013. https://doi.org/10.1145/2449396.2449419
Kratz, S., Rohs, M., & Essl, G. (2013). Combining Acceleration and Gyroscope Data for Motion Gesture Recognition using Classifiers with Dimensionality Constraints. In IUI '13: Proceedings of the 2013 international conference on Intelligent user interfaces (pp. 173-177) https://doi.org/10.1145/2449396.2449419
Kratz S, Rohs M, Essl G. Combining Acceleration and Gyroscope Data for Motion Gesture Recognition using Classifiers with Dimensionality Constraints. In IUI '13: Proceedings of the 2013 international conference on Intelligent user interfaces. 2013. p. 173-177 doi: 10.1145/2449396.2449419
Kratz, Sven ; Rohs, Michael ; Essl, Georg. / Combining Acceleration and Gyroscope Data for Motion Gesture Recognition using Classifiers with Dimensionality Constraints. IUI '13: Proceedings of the 2013 international conference on Intelligent user interfaces. 2013. pp. 173-177
Download
@inproceedings{3cc6bd634abe49d6bf8a84fbd346c238,
title = "Combining Acceleration and Gyroscope Data for Motion Gesture Recognition using Classifiers with Dimensionality Constraints",
abstract = "Motivated by the addition of gyroscopes to a large number of new smart phones, we study the effects of combining ac-celerometer and gyroscope data on the recognition rate of motion gesture recognizers with dimensionality constraints. Using a large data set of motion gestures we analyze results for the following algorithms: Protractor3D, Dynamic Time Warping (DTW) and Regularized Logistic Regression (LR). We chose to study these algorithms because they are relatively easy to implement, thus well suited for rapid prototyping or early deployment during prototyping stages. For use in our analysis, we contribute a method to extend Protractor3D to work with the 6D data obtained by combining accelerometer and gyroscope data. Our results show that combining accelerometer and gyroscope data is beneficial also for algorithms with dimensionality constraints and improves the gesture recognition rate on our data set by up to 4%.",
keywords = "Accelerometer, Gesture recognition, Gyroscope, Mobile, Motion gestures, Sensor fusion",
author = "Sven Kratz and Michael Rohs and Georg Essl",
note = "Copyright: Copyright 2013 Elsevier B.V., All rights reserved.; 18th International Conference on Intelligent User Interfaces, IUI 2013 ; Conference date: 19-03-2013 Through 22-03-2013",
year = "2013",
month = mar,
day = "19",
doi = "10.1145/2449396.2449419",
language = "English",
pages = "173--177",
booktitle = "IUI '13",

}

Download

TY - GEN

T1 - Combining Acceleration and Gyroscope Data for Motion Gesture Recognition using Classifiers with Dimensionality Constraints

AU - Kratz, Sven

AU - Rohs, Michael

AU - Essl, Georg

N1 - Copyright: Copyright 2013 Elsevier B.V., All rights reserved.

PY - 2013/3/19

Y1 - 2013/3/19

N2 - Motivated by the addition of gyroscopes to a large number of new smart phones, we study the effects of combining ac-celerometer and gyroscope data on the recognition rate of motion gesture recognizers with dimensionality constraints. Using a large data set of motion gestures we analyze results for the following algorithms: Protractor3D, Dynamic Time Warping (DTW) and Regularized Logistic Regression (LR). We chose to study these algorithms because they are relatively easy to implement, thus well suited for rapid prototyping or early deployment during prototyping stages. For use in our analysis, we contribute a method to extend Protractor3D to work with the 6D data obtained by combining accelerometer and gyroscope data. Our results show that combining accelerometer and gyroscope data is beneficial also for algorithms with dimensionality constraints and improves the gesture recognition rate on our data set by up to 4%.

AB - Motivated by the addition of gyroscopes to a large number of new smart phones, we study the effects of combining ac-celerometer and gyroscope data on the recognition rate of motion gesture recognizers with dimensionality constraints. Using a large data set of motion gestures we analyze results for the following algorithms: Protractor3D, Dynamic Time Warping (DTW) and Regularized Logistic Regression (LR). We chose to study these algorithms because they are relatively easy to implement, thus well suited for rapid prototyping or early deployment during prototyping stages. For use in our analysis, we contribute a method to extend Protractor3D to work with the 6D data obtained by combining accelerometer and gyroscope data. Our results show that combining accelerometer and gyroscope data is beneficial also for algorithms with dimensionality constraints and improves the gesture recognition rate on our data set by up to 4%.

KW - Accelerometer

KW - Gesture recognition

KW - Gyroscope

KW - Mobile

KW - Motion gestures

KW - Sensor fusion

UR - http://www.scopus.com/inward/record.url?scp=84875847396&partnerID=8YFLogxK

U2 - 10.1145/2449396.2449419

DO - 10.1145/2449396.2449419

M3 - Conference contribution

AN - SCOPUS:84875847396

SP - 173

EP - 177

BT - IUI '13

T2 - 18th International Conference on Intelligent User Interfaces, IUI 2013

Y2 - 19 March 2013 through 22 March 2013

ER -