Open AccessHuman motion capture data recovery using trajectory‐based matrix completion
Author(s) -
Tan CheenHau,
Hou JunHui,
Chau LapPui
Publication year - 2013
Publication title -
electronics letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.375
H-Index - 146
eISSN - 1350-911X
pISSN - 0013-5194
DOI - 10.1049/el.2013.0442
Subject(s) - motion capture , matrix completion , trajectory , motion (physics) , computer science , representation (politics) , matrix (chemical analysis) , missing data , reliability (semiconductor) , artificial intelligence , sequence (biology) , computer vision , matrix representation , algorithm , machine learning , materials science , composite material , quantum mechanics , gaussian , physics , astronomy , law , chemistry , genetics , biology , power (physics) , political science , organic chemistry , politics , group (periodic table)
Matrix completion has previously been used as a method to recover missing data in a mocap sequence. Improvments to this scheme by structuring motion capture data into an alternative representation for matrix completion are proposed. This representation takes advantage of the properties of mocap data and matrix completion to improve the reliability of matrix completion. Experiments show that the proposed motion capture data recovery method performs significantly better for nearly all tested motion sequences and amounts of missing data.