[Paper Review] TransPose: Real-time 3D Human Translation and Pose Estimation with Six Inertial Sensors

Xinyu Yi, Yuxiao Zhou+1 more|arXiv (Cornell University)|May 10, 2021

Human Pose and Action Recognition44 references52 citations

TL;DR

TransPose uses six IMUs to achieve real-time 3D human pose estimation and global translation at over 90 fps by a multi-stage pose pipeline and a fusion-based global translation estimator.

ABSTRACT

Motion capture is facing some new possibilities brought by the inertial sensing technologies which do not suffer from occlusion or wide-range recordings as vision-based solutions do. However, as the recorded signals are sparse and quite noisy, online performance and global translation estimation turn out to be two key difficulties. In this paper, we present TransPose, a DNN-based approach to perform full motion capture (with both global translations and body poses) from only 6 Inertial Measurement Units (IMUs) at over 90 fps. For body pose estimation, we propose a multi-stage network that estimates leaf-to-full joint positions as intermediate results. This design makes the pose estimation much easier, and thus achieves both better accuracy and lower computation cost. For global translation estimation, we propose a supporting-foot-based method and an RNN-based method to robustly solve for the global translations with a confidence-based fusion technique. Quantitative and qualitative comparisons show that our method outperforms the state-of-the-art learning- and optimization-based methods with a large margin in both accuracy and efficiency. As a purely inertial sensor-based approach, our method is not limited by environmental settings (e.g., fixed cameras), making the capture free from common difficulties such as wide-range motion space and strong occlusion.

Motivation & Objective

• Address the under-constrained problem of full motion capture from only six IMUs by leveraging temporal information and pose priors.
• Enable real-time (over 90 fps) estimation of both body pose and global translation without cameras or external sensors.
• Improve accuracy and efficiency over prior DIP/SIP methods by decomposing pose estimation into intermediate joint-position tasks.
• Propose a robust, fusion-based approach to estimate global translations in real time from sparse inertial data.

Proposed method

• A three-stage pose estimation pipeline that first predicts leaf joint positions (Pose-S1), then completes all joint positions (Pose-S2), and finally regresses joint rotations (Pose-S3) using bi-directional RNNs with LSTM cells.
• Leaf joints are used as intermediate representations to leverage the human kinematic hierarchy and temporal information.
• Global translation estimation is done via two parallel branches: a foot-ground contact-based velocity estimate (Trans-B1) and a root-velocity RNN (Trans-B2), fused according to foot contact probability.
• The foot-ground contact network uses leaf joint positions and IMU data to infer which foot is on the ground and computes root velocity from forward kinematics of the supporting foot.
• Trans-B2 predicts the root velocity in the root’s coordinate frame with an RNN, then converts to world space using the root rotation; a fusion rule combines v_f and v_e based on foot contact probability.
• The system uses the SMPL skeleton, with leg lengths measured in advance or defaulted to the mean SMPL, and synthesizes training data from DIP-IMU, TotalCapture, and AMASS with noise and augmentation.

Experimental results

Research questions

• RQ1 Can real-time full-motion capture, including global translation, be achieved from only six IMUs at high frame rates without environmental constraints?
• RQ2 Does a multi-stage pose estimation approach with intermediate joint-position representations improve accuracy and efficiency over direct pose regression from IMU data?
• RQ3 Can a fusion-based translation estimation strategy leveraging foot-ground contact and learned root velocity robustly estimate global movement in diverse motions?
• RQ4 How do synthetic data and motion history modeling impact generalization across datasets like DIP-IMU, TotalCapture, and AMASS?

Key findings

• The approach achieves real-time motion capture with global translation estimation using only 6 IMUs at over 90 fps.
• A three-stage pose estimation design (leaf joints → all joints → rotations) yields higher accuracy and lower computation than direct rotation prediction.
• A hybrid translation estimator combining foot-ground contact-based velocity and root-velocity regression improves robustness across walking, running, and jumping.
• The method outperforms prior works DIP and SIP in both qualitative and quantitative evaluations on public datasets, with improved accuracy and efficiency.
• The system remains purely inertial, avoiding occlusion and environmental limitations inherent to vision-based mocap.