Exploiting temporal stability and low-rank structure for motion capture data refinement

Authors: Feng, Y., Xiao, J., Zhuang, Y., Yang, X., Zhang, J.J. and Song, R.

Journal: Information Sciences

Volume: 277

Pages: 777-793

ISSN: 0020-0255

DOI: 10.1016/j.ins.2014.03.013

Abstract:

Inspired by the development of the matrix completion theories and algorithms, a low-rank based motion capture (mocap) data refinement method has been developed, which has achieved encouraging results. However, it does not guarantee a stable outcome if we only consider the low-rank property of the motion data. To solve this problem, we propose to exploit the temporal stability of human motion and convert the mocap data refinement problem into a robust matrix completion problem, where both the low-rank structure and temporal stability properties of the mocap data as well as the noise effect are considered. An efficient optimization method derived from the augmented Lagrange multiplier algorithm is presented to solve the proposed model. Besides, a trust data detection method is also introduced to improve the degree of automation for processing the entire set of the data and boost the performance. Extensive experiments and comparisons with other methods demonstrate the effectiveness of our approaches on both predicting missing data and de-noising. © 2014 Elsevier Inc. All rights reserved.

https://eprints.bournemouth.ac.uk/21397/

Source: Scopus

Preferred by: Jian Jun Zhang

Exploiting temporal stability and low-rank structure for motion capture data refinement

Authors: Feng, Y., Xiao, J., Zhuang, Y., Yang, X., Zhang, J.J. and Song, R.

Journal: INFORMATION SCIENCES

Volume: 277

Pages: 777-793

eISSN: 1872-6291

ISSN: 0020-0255

DOI: 10.1016/j.ins.2014.03.013

https://eprints.bournemouth.ac.uk/21397/

Source: Web of Science (Lite)

Exploiting temporal stability and low-rank structure for motion capture data refinement

Authors: Feng, Y., Xiao, J., Zhuang, Y., Song, R., Yang, X. and Zhang, J.J.

Journal: Information Sciences

Volume: 277

Pages: 777-793

ISSN: 0020-0255

DOI: 10.1016/j.ins.2014.03.013

Abstract:

Inspired by the development of the matrix completion theories and algorithms, a low-rank based motion capture (mocap) data refinement method has been developed, which has achieved encouraging results. However, it does not guarantee a stable outcome if we only consider the low-rank property of the motion data. To solve this problem, we propose to exploit the temporal stability of human motion and convert the mocap data refinement problem into a robust matrix completion problem, where both the low-rank structure and temporal stability properties of the mocap data as well as the noise effect are considered. An efficient optimization method derived from the augmented Lagrange multiplier algorithm is presented to solve the proposed model. Besides, a trust data detection method is also introduced to improve the degree of automation for processing the entire set of the data and boost the performance. Extensive experiments and comparisons with other methods demonstrate the effectiveness of our approaches on both predicting missing data and de-noising. © 2014 Elsevier Inc. All rights reserved.

https://eprints.bournemouth.ac.uk/21397/

Source: Manual

Preferred by: Xiaosong Yang

Exploiting temporal stability and low-rank structure for motion capture data refinement

Authors: Feng, Y., Xiao, J., Zhuang, Y., Song, R., Yang, X. and Zhang, J.J.

Journal: Information Sciences

Volume: 277

Pages: 777-793

ISSN: 0020-0255

Abstract:

Inspired by the development of the matrix completion theories and algorithms, a low-rank based motion capture (mocap) data refinement method has been developed, which has achieved encouraging results. However, it does not guarantee a stable outcome if we only consider the low-rank property of the motion data. To solve this problem, we propose to exploit the temporal stability of human motion and convert the mocap data refinement problem into a robust matrix completion problem, where both the low-rank structure and temporal stability properties of the mocap data as well as the noise effect are considered. An efficient optimization method derived from the augmented Lagrange multiplier algorithm is presented to solve the proposed model. Besides, a trust data detection method is also introduced to improve the degree of automation for processing the entire set of the data and boost the performance. Extensive experiments and comparisons with other methods demonstrate the effectiveness of our approaches on both predicting missing data and de-noising. © 2014 Elsevier Inc. All rights reserved.

https://eprints.bournemouth.ac.uk/21397/

Source: BURO EPrints