Temporal Clustering of Motion Capture Data with Optimal Partitioning

Temporal Clustering of Motion Capture Data with Optimal Partitioning

Abstract

Motion capture data can be characterized as a series of multi-dimensional spatio-temporal data, which is recorded by tracking the number of key points in space over time with a 3-dimensioanl representation. Such complex characteristics make the processing of motion capture data a non-trivial task. Hence, techniques that can provide an approximated, less complicated representation of such data are highly desirable. In this paper, we propose a novel technique that uses temporal clustering to generate an approximate representation of motion capture data. First, we segment the motion in the time domain with an optimal partition algorithm so that the within-segment sum of squared error (WSSSE) is minimized. Then, we represent the motion capture data as the averages taken over all the segments, resulting in a representation of much lower complexity. Experimental results suggest that comparing with the state-of-the-art methods, our proposed representation technique can better approximate the motion capture data.

Publication

Yang Yang, Huiwen Bian, Hubert P. H. Shum, Nauman Aslam and Lanling Zeng,
"Temporal Clustering of Motion Capture Data with Optimal Partitioning",
Proceedings of the 2016 International Conference on Virtual-Reality Continuum and its Applications in Industry (VRCAI)

Downloads

YouTube

References

BibTeX

@inproceedings{yang16temporal,
 author={Yang, Yang and Bian, Huiwen and Shum, Hubert P. H. and Aslam, Nauman and Zeng, Lanling},
 booktitle={Proceedings of the 2016 International Conference on Virtual-Reality Continuum and its Applications in Industry},
 series={VRCAI '16},
 title={Temporal Clustering of Motion Capture Data with Optimal Partitioning},
 year={2016},
 month={Dec},
 pages={479--482},
 numpages={4},
 doi={10.1145/3013971.3014019},
 isbn={978-1-4503-4692-4},
 publisher={ACM},
 Address={New York, NY, USA},
 location={Zhuhai, China},
}

EndNote/RefMan

TY  - CONF
AU  - Yang, Yang
AU  - Bian, Huiwen
AU  - Shum, Hubert P. H.
AU  - Aslam, Nauman
AU  - Zeng, Lanling
T2  - Proceedings of the 2016 International Conference on Virtual-Reality Continuum and its Applications in Industry
TI  - Temporal Clustering of Motion Capture Data with Optimal Partitioning
PY  - 2016
Y1  - Dec 2016
SP  - 479
EP  - 482
DO  - 10.1145/3013971.3014019
SN  - 978-1-4503-4692-4
PB  - ACM
ER  - 

Plain Text

Yang Yang, Huiwen Bian, Hubert P. H. Shum, Nauman Aslam and Lanling Zeng, "Temporal Clustering of Motion Capture Data with Optimal Partitioning," in VRCAI '16: Proceedings of the 2016 International Conference on Virtual-Reality Continuum and its Applications in Industry, pp. 479-482, Zhuhai, China, ACM, Dec 2016.

Similar Research

 

         

Last update: 14/01/2019