loading
Documents

Research.Publish.Connect.

Paper

Authors: Rafael Rego Drumond 1 ; Bruno A. Dorta Marques 2 ; Cristina Nader Vasconcelos 2 and Esteban Clua 2

Affiliations: 1 University of Hildesheim, Germany ; 2 Universidade Federal Fluminense, Brazil

ISBN: 978-989-758-287-5

Keyword(s): Motion Classifier, IMU Device, Deep Learning, Recurrent Neural Networks, Sparse Data, Machine Learning.

Related Ontology Subjects/Areas/Topics: Advanced User Interfaces ; Animation and Simulation ; Animation from Motion Capture ; Computer Vision, Visualization and Computer Graphics ; Interactive Environments

Abstract: Games and other applications are exploring many different modes of interaction in order to create intuitive interfaces, such as touch screens, motion controllers, recognition of gesture or body movements among many others. In that direction, human motion is being captured by different sensors, such as accelerometers, gyroscopes, heat sensors and cameras. However, there is still room for investigation the analysis of motion data captured from low-cost sensors. This article explores the extent to which a full body motion classification can be achieved by observing only sparse data captured by two separate inherent wereable measurement unit (IMU) sensors. For that, we developed a novel Recurrent Neural Network topology based on Long Short-Term Memory cells (LSTMs) that are able to classify motions sequences of different sizes. Using cross-validation tests, our model achieves an overall accuracy of 96% which is quite significant considering that the raw data used was obtained usi ng only 2 simple and accessible IMU sensors capturing arms movements. We also built and made public a motion database constructed by capturing sparse data from 11 actors performing five different actions. For comparison with existent methods, other deep learning approaches for sequence evaluation (more specifically, based on convolutional neural networks), were adapted to our problem and evaluated. (More)

PDF ImageFull Text

Download
Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 54.159.51.118

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Rego Drumond R., Dorta Marques B., Nader Vasconcelos C. and Clua E. (2018). PEEK - An LSTM Recurrent Network for Motion Classification from Sparse Data.In Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 1: GRAPP, ISBN 978-989-758-287-5, pages 215-222. DOI: 10.5220/0006585202150222

@conference{grapp18,
author={Rafael Rego Drumond and Bruno A. Dorta Marques and Cristina Nader Vasconcelos and Esteban Clua},
title={PEEK - An LSTM Recurrent Network for Motion Classification from Sparse Data},
booktitle={Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 1: GRAPP,},
year={2018},
pages={215-222},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006585202150222},
isbn={978-989-758-287-5},
}

TY - CONF

JO - Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 1: GRAPP,
TI - PEEK - An LSTM Recurrent Network for Motion Classification from Sparse Data
SN - 978-989-758-287-5
AU - Rego Drumond R.
AU - Dorta Marques B.
AU - Nader Vasconcelos C.
AU - Clua E.
PY - 2018
SP - 215
EP - 222
DO - 10.5220/0006585202150222

Login or register to post comments.

Comments on this Paper: Be the first to review this paper.