Position stabilisation and lag reduction with Gaussian processes in sensor fusion system for user performance improvement

Feng, S., Murray-Smith, R. and Ramsay, A. (2017) Position stabilisation and lag reduction with Gaussian processes in sensor fusion system for user performance improvement. International Journal of Machine Learning and Cybernetics, 8(4), pp. 1167-1184. (doi: 10.1007/s13042-015-0488-5)

[img]
Preview
Text
114818.pdf - Published Version

1MB

Abstract

In this paper we present a novel Gaussian Process (GP) prior model-based sensor fusion approach to dealing with position uncertainty and lag in a system composed of an external position sensing device (Kinect) and inertial sensors embedded in a mobile device for user performance improvement. To test the approach, we conducted two experiments: (1) GPs sensor fusion simulation. Experimental results show that the novel GP sensor fusion helps improve the accuracy of position estimation, and reduce the lag (0.11 s). (2) User study on a trajectory-based target acquisition task in a spatially aware display application. We implemented the real-time sensor fusion system by augmenting the Kinect with a Nokia N9. In the trajectory-based interaction experiment, each user performed target selection tasks following a trajectory in (a) the Kinect system and (b) the sensor fusion system. In comparison with the Kinect time-delay system, our system enables the user to perform the task easier and faster. The MSE of target selection was reduced by 38.3 % and the average task completion time was reduced by 26.7 %.

Item Type:Articles
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:Murray-Smith, Professor Roderick and Feng, Mr Shimin and Ramsay, Mr Andrew
Authors: Feng, S., Murray-Smith, R., and Ramsay, A.
College/School:College of Science and Engineering > School of Computing Science
Journal Name:International Journal of Machine Learning and Cybernetics
Publisher:Springer
ISSN:1868-8071
ISSN (Online):1868-808X
Published Online:11 January 2016

University Staff: Request a correction | Enlighten Editors: Update this record