Learning 3D joint constraints from vision-based motion capture datasets

• Published in: IPSJ transactions on computer vision and applications Vol. 11; no. 1; pp. 1 - 9
• Main Authors: Murthy, Pramod, Butt, Hammad T., Hiremath, Sandesh, Khoshhal, Alireza, Stricker, Didier
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 25-06-2019; Springer Nature B.V
• Subjects: Artificial Intelligence; Computer Imaging; Computer Science; Datasets; Discriminators; Express Paper; Human motion; Image Processing and Computer Vision; Motion capture; Neural networks; Parameterization; Pattern Recognition and Graphics; Robotics and Automation; Synthesis; Three dimensional motion; User Interfaces and Human Computer Interaction; Vision; Joint constraint; Motion capture; Human pose estimation
• ISSN: 1882-6695; 1882-6695
• DOI: 10.1186/s41074-019-0057-z

Realistic estimation and synthesis of articulated human motion must satisfy anatomical constraints on joint angles. A data-driven approach is used to learn human joint limits from 3D motion capture datasets. We represent joint constraints with a new formulation (
s
1
,
s
2
,
τ
) using swing-twist representation in exponential maps form. Our parameterization is applied on Human3.6M dataset to create the lookup-map for each joint. These maps enable us to generate ‘synthetic’ datasets in entire joint rotation space of a given joint. A set of neural network discriminators is then trained with synthetic datasets to learn valid/invalid joint rotations. The discriminators achieve accuracy of [94.4−99.4
%
] for different joints. We validate precision-accuracy trade-off of discriminators and qualitatively evaluate classified poses with an interactive tool. The learned discriminators can be used as ‘priors’ for human pose estimation and motion synthesis.