AddBiomechanics Dataset: Capturing the Physics of Human Motion at Scale

TL;DR

The AddBiomechanics Dataset provides a large-scale, high-quality collection of human motion and force data to facilitate research in human dynamics and physics estimation from pose data.

Contribution

This paper introduces the first large-scale dataset with detailed human motion and force data, along with analytical methods and benchmarks for estimating human dynamics.

Findings

Over 70 hours of motion and force data collected from 273 subjects

Benchmark results for human dynamics estimation established

Novel analytical methods for dataset construction proposed

Abstract

While reconstructing human poses in 3D from inexpensive sensors has advanced significantly in recent years, quantifying the dynamics of human motion, including the muscle-generated joint torques and external forces, remains a challenge. Prior attempts to estimate physics from reconstructed human poses have been hampered by a lack of datasets with high-quality pose and force data for a variety of movements. We present the AddBiomechanics Dataset 1.0, which includes physically accurate human dynamics of 273 human subjects, over 70 hours of motion and force plate data, totaling more than 24 million frames. To construct this dataset, novel analytical methods were required, which are also reported here. We propose a benchmark for estimating human dynamics from motion using this dataset, and present several baseline results. The AddBiomechanics Dataset is publicly available at https://addbiomechanics.org/download_data.html.