DocumentCode :
594689
Title :
Unsupervised motion pattern learning for motion segmentation
Author :
Weber, Matthias ; Bleser, Gabriele ; Liwicki, Marcus ; Stricker, Didier
Author_Institution :
German Res. Center for AI (DFKI GmbH), Kaiserslautern, Germany
fYear :
2012
fDate :
11-15 Nov. 2012
Firstpage :
202
Lastpage :
205
Abstract :
This paper proposes a novel method for automated generation of motion segmentation models for full body motion monitoring. The method generates, in an un-supervised manner, a motion template for a dynamic warping approach from a short training sequence, i.e., from very few data. Therefore it first automatically detects motif candidates, i.e. the recurring patterns in the training sequence. Then it uses the detected motifs to construct the model. This novel method is able to automatically find motifs in a multivariate time series and generate a model which is capable of segmenting the series in a real-time system. The technology is evaluated in the context of a personalized virtual rehabilitation trainer application during a clinical study. The novel motion capturing dataset is publicly available.
Keywords :
gait analysis; image motion analysis; image segmentation; object detection; patient monitoring; patient rehabilitation; time series; unsupervised learning; automatically motif candidate detection; body motion monitoring; dynamic warping approach; motion segmentation model; motion template; multivariate time series; personalized virtual rehabilitation; real-time system; recurring pattern; training sequence; unsupervised motion pattern learning; Biological system modeling; Hidden Markov models; Joints; Monitoring; Motion segmentation; Time series analysis; Training;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Pattern Recognition (ICPR), 2012 21st International Conference on
Conference_Location :
Tsukuba
ISSN :
1051-4651
Print_ISBN :
978-1-4673-2216-4
Type :
conf
Filename :
6460107
Link To Document :
بازگشت