The Community for Technology Leaders
Ninth IEEE International Symposium on Wearable Computers (ISWC'05) (2005)
Osaka, Japan
Oct. 18, 2005 to Oct. 21, 2005
ISBN: 0-7695-2419-2
pp: 152-159
Georg Ogris , Institute for Computer Systems and Networks, UMIT Innsbruck, Austria
Thomas Stiefmeier , Wearable Computing Lab, ETH Z?urich, Switzerland
Holger Junker , Wearable Computing Lab, ETH Z?urich, Switzerland
Paul Lukowicz , Wearable Computing Lab, ETH Z?urich, Switzerland
Gerhard Tr?oster , Wearable Computing Lab, ETH Z?urich, Switzerland
ABSTRACT
<p>The paper demonstrates how ultrasonic hand tracking can be used to improve the performance of a wearable, accelerometer and gyroscope based activity recognition system. Specifically we target the recognition of manipulative gestures of the type found in assembly and maintenance tasks. We discuss how relevant information can be extracted from the ultrasonic signal despite problems with low sampling rate, occlusions and reflections that occur in this type of application. We then introduce several methods of fusing the ultrasound and motion sensor information. We evaluate our methods on an experimental data set that contains 21 different actions performed repeatedly by three different subjects during simulated bike repair. Due to the complexity of the recognition tasks with many similar and vaguely defined actions and person independent training both the ultrasound and motion sensors perform poorly on their own. However with our fusion methods recognition rates well over 90% can be achieved for most activities. In extreme case recognition rates go up from just over 50% for separate classifications to nearly 89% with our fusion methods.</p>
INDEX TERMS
null
CITATION

P. Lukowicz, T. Stiefmeier, G. Tr?oster, H. Junker and G. Ogris, "Using Ultrasonic Hand Tracking to Augment Motion Analysis Based Recognition of Manipulative Gestures," Ninth IEEE International Symposium on Wearable Computers (ISWC'05)(ISWC), Osaka, Japan, 2005, pp. 152-159.
doi:10.1109/ISWC.2005.54
96 ms
(Ver 3.3 (11022016))