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