Physical Inertial Poser (PIP): Physics-aware Real-time Human Motion Tracking from Sparse Inertial Sensors
Authors:
Top Cited Papers
- 1 June 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 13157-13168
Abstract
Motion capture from sparse inertial sensors has shown great potential compared to image-based approaches since occlusions do not lead to a reduced tracking quality and the recording space is not restricted to be within the viewing frustum of the camera. However, capturing the motion and global position only from a sparse set of inertial sensors is inherently ambiguous and challenging. In consequence, recent state-of-the-art methods can barely handle very long period motions, and unrealistic artifacts are common due to the unawareness of physical constraints. To this end, we present the first method which combines a neural kinematics estimator and a physics-aware motion optimizer to track body motions with only 6 inertial sensors. The kinematics module first regresses the motion status as a reference, and then the physics module refines the motion to satisfy the physical constraints. Experiments demonstrate a clear improvement over the state of the art in terms of capture accuracy, temporal stability, and physical correctness.Keywords
All Related Versions
Funding Information
- Beijing Natural Science Foundation (JQ19015)
- NSFC (61727808,62021002)
- National Key R&D Program of China (2018YFA0704000)
- Tsinghua University
- Beijing Municipal Education Commission
- ERC (770784)
This publication has 76 references indexed in Scilit:
- Real-time Physics-based Motion Capture with Sparse Sensors2016
- Human Pose Estimation from Video and IMUsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- SMPLACM Transactions on Graphics, 2015
- Motion reconstruction using very few accelerometers and ground contactsGraphical Models, 2015
- Human motion tracking control with strict contact force constraints for floating-base humanoid robots2013
- Video-based 3D motion capture through biped controlACM Transactions on Graphics, 2012
- Motion reconstruction using sparse accelerometer dataACM Transactions on Graphics, 2011
- Discriminative Human Full-Body Pose Estimation from Wearable Inertial Sensor Data2009
- ZERO-MOMENT POINT — THIRTY FIVE YEARS OF ITS LIFEInternational Journal of Humanoid Robotics, 2004
- Bidirectional recurrent neural networksIEEE Transactions on Signal Processing, 1997