Publication details

<< back
 

Gait Recognition Based on Normalized Walk Cycles

Basic information
Original title:Gait Recognition Based on Normalized Walk Cycles
Authors:Jan Sedmidubský, Jakub Valčík, Michal Balážia, Pavel Zezula
Further information
Citation:SEDMIDUBSKÝ, Jan, Jakub VALČÍK, Michal BALÁŽIA and Pavel ZEZULA. Gait Recognition Based on Normalized Walk Cycles. In Bebis, George and Boyle, Richard and Parvin, Bahram and Koracin, Darko and Fowlkes, Charless and Wang, Sen and Choi, Min-Hyung and Mantler, Stephan and Schulze, Jürgen and Acevedo, Daniel and Mueller, Klaus and Papka, Michael. Proceedings of 8th International Symposium on Visual Computing (ISVC 2012), LNCS 7432. Heidelberg: Springer-Verlag, 2012. p. 11-20, 10 pp. ISBN 978-3-642-33190-9. doi:10.1007/978-3-642-33191-6_2.Export BibTeX
@inproceedings{982503,
author = {Sedmidubský, Jan and Valčík, Jakub and Balážia, Michal and Zezula, Pavel},
address = {Heidelberg},
booktitle = {Proceedings of 8th International Symposium on Visual Computing (ISVC 2012), LNCS 7432},
doi = {http://dx.doi.org/10.1007/978-3-642-33191-6_2},
editor = {Bebis, George and Boyle, Richard and Parvin, Bahram and Koracin, Darko and Fowlkes, Charless and Wang, Sen and Choi, Min-Hyung and Mantler, Stephan and Schulze, Jürgen and Acevedo, Daniel and Mueller, Klaus and Papka, Michael},
keywords = {gait recognition; gait pattern; similarity of gait patterns},
howpublished = {tištěná verze "print"},
language = {eng},
location = {Heidelberg},
isbn = {978-3-642-33190-9},
pages = {11-20},
publisher = {Springer-Verlag},
title = {Gait Recognition Based on Normalized Walk Cycles},
year = {2012}
}
Original language:English
Field:Informatics
Type:Article in Proceedings
Keywords:gait recognition; gait pattern; similarity of gait patterns

We focus on recognizing persons according to the way they walk. Our approach considers a human movement as a set of trajectories formed by specific anatomical landmarks, such as hips, feet, shoulders, or hands. The trajectories are used for the extraction of distance-time dependency signals that express how a distance between a pair of specific landmarks on the human body changes in time as the person walks. The collection of such signals characterizes a gait pattern of person's walk. To determine the similarity of gait patterns, we propose several functions that compare various combinations of extracted signals. The gait patterns are compared on the level of individual walk cycles in order to increase the recognition effectiveness. The results evaluated on a 3D database of walking humans achieved the recognition rate up to 96%.

Related projects:

 
 
top