Physical Non-inertial Poser (PNP): Modeling Non-inertial Effects in Sparse-inertial Human Motion Capture

TL;DR

This paper introduces a physics-informed neural network approach for non-inertial motion capture, explicitly modeling fictitious forces in the root frame to improve accuracy and robustness in human motion estimation.

Contribution

It models non-inertial effects in inertial motion capture using a physics-based estimator and synthetic data generation, enhancing motion capture accuracy and robustness.

Findings

Improved motion capture accuracy with non-inertial modeling.

Synthetic data generation enables effective training and calibration.

Enhanced robustness to calibration errors and hardware variations.

Abstract

Existing inertial motion capture techniques use the human root coordinate frame to estimate local poses and treat it as an inertial frame by default. We argue that when the root has linear acceleration or rotation, the root frame should be considered non-inertial theoretically. In this paper, we model the fictitious forces that are non-neglectable in a non-inertial frame by an auto-regressive estimator delicately designed following physics. With the fictitious forces, the force-related IMU measurement (accelerations) can be correctly compensated in the non-inertial frame and thus Newton's laws of motion are satisfied. In this case, the relationship between the accelerations and body motions is deterministic and learnable, and we train a neural network to model it for better motion capture. Furthermore, to train the neural network with synthetic data, we develop an IMU synthesis by simulation strategy to better model the noise model of IMU hardware and allow parameter tuning to fit different hardware. This strategy not only establishes the network training with synthetic data but also enables calibration error modeling to handle bad motion capture calibration, increasing the robustness of the system. Code is available at https://xinyu-yi.github.io/PNP/.