TY - JOUR

T1 - Learning inverse dynamics for human locomotion analysis

AU - Zell, Petrissa

AU - Rosenhahn, Bodo

PY - 2019/12/23

Y1 - 2019/12/23

N2 - In this work, learning-based inverse dynamics algorithms are proposed for the analysis of human motion. Immeasurable joint torques and exterior contact forces are directly estimated from motions by machine learning techniques including deep neural networks, random forests and Ridge regression. A multistage subclass approach is introduced. The method recovers occluded motion data and generates meaningful features, as well as gait phase labels to restrict and facilitate the regression of forces and moments. In contrast to the state-of-the-art inverse dynamics optimization, the learning-based methods are independent of ground reaction force measurements and the global position and orientation of the human body. These properties make the application to reconstructed poses from videos or inertial measurements possible, creating fast and simple access to the underlying dynamics of recorded human motions. The performance of the proposed methods is evaluated on a self-recorded data set including walking and running motions and on a publicly available gait data set by Fukuchi et al. (PeerJ 6:e4640, 2018). Furthermore, the applicability to reconstructed gait sequences taken from the well-known CMU database (Human motion capture database, 2014. http://mocap.cs.cmu.edu/) is investigated. Finally, the method is tested as a tool to detect abnormal torque distributions in gait, based on a reconstructed 3D motion of a limping subject.

AB - In this work, learning-based inverse dynamics algorithms are proposed for the analysis of human motion. Immeasurable joint torques and exterior contact forces are directly estimated from motions by machine learning techniques including deep neural networks, random forests and Ridge regression. A multistage subclass approach is introduced. The method recovers occluded motion data and generates meaningful features, as well as gait phase labels to restrict and facilitate the regression of forces and moments. In contrast to the state-of-the-art inverse dynamics optimization, the learning-based methods are independent of ground reaction force measurements and the global position and orientation of the human body. These properties make the application to reconstructed poses from videos or inertial measurements possible, creating fast and simple access to the underlying dynamics of recorded human motions. The performance of the proposed methods is evaluated on a self-recorded data set including walking and running motions and on a publicly available gait data set by Fukuchi et al. (PeerJ 6:e4640, 2018). Furthermore, the applicability to reconstructed gait sequences taken from the well-known CMU database (Human motion capture database, 2014. http://mocap.cs.cmu.edu/) is investigated. Finally, the method is tested as a tool to detect abnormal torque distributions in gait, based on a reconstructed 3D motion of a limping subject.

KW - Deep neural networks

KW - Gait phase detection

KW - Human locomotion

KW - Inverse dynamics

UR - http://www.scopus.com/inward/record.url?scp=85077148319&partnerID=8YFLogxK

U2 - 10.1007/s00521-019-04658-z

DO - 10.1007/s00521-019-04658-z

M3 - Article

AN - SCOPUS:85077148319

VL - 32

SP - 11729

EP - 11743

JO - Neural Computing and Applications

JF - Neural Computing and Applications

SN - 0941-0643

IS - 15

ER -