Pose2sim: An end-to-end workflow for 3D markerless sports kinematics—Part 1: Robustness

David Pagnon, Mathieu Domalain, Lionel Reveret

Research output: Contribution to journalArticlepeer-review

32 Citations (SciVal)

Abstract

Being able to capture relevant information about elite athletes’ movement “in the wild” is challenging, especially because reference marker-based approaches hinder natural movement and are highly sensitive to environmental conditions. We propose Pose2Sim, a markerless kinematics workflow that uses OpenPose 2D pose detections from multiple views as inputs, identifies the person of interest, robustly triangulates joint coordinates from calibrated cameras, and feeds those to a 3D inverse kinematic full-body OpenSim model in order to compute biomechanically congruent joint angles. We assessed the robustness of this workflow when facing simulated challenging conditions: (Im) degrades image quality (11-pixel Gaussian blur and 0.5 gamma compression); (4c) uses few cameras (4 vs. 8); and (Cal) introduces calibration errors (1 cm vs. perfect calibration). Three physical activities were investigated: walking, running, and cycling. When averaged over all joint angles, stride-to-stride standard deviations lay between 1.7 and 3.2 for all conditions and tasks, and mean absolute errors (compared to the reference condition—Ref) ranged between 0.35 and 1.6. For walking, errors in the sagittal plane were: 1.5, 0.90, 0.19 for (Im), (4c), and (Cal), respectively. In conclusion, Pose2Sim provides a simple and robust markerless kinematics analysis from a network of calibrated cameras.

Original languageEnglish
Article number6530
JournalSensors
Volume21
Issue number19
Early online date30 Sept 2021
DOIs
Publication statusPublished - 1 Oct 2021

Bibliographical note

Funding Information:
Funding: This research has received funding from CNRS (Doctoral Thesis 2019), ANR Equipex PIA 2011 (project Kinovis), and ANR PPR STHP 2020 (project PerfAnalytics, ANR 20-STHP-0003).

Funding

Funding: This research has received funding from CNRS (Doctoral Thesis 2019), ANR Equipex PIA 2011 (project Kinovis), and ANR PPR STHP 2020 (project PerfAnalytics, ANR 20-STHP-0003).

Keywords

  • Computer vision
  • Deep learning
  • Kinematics
  • Markerless motion capture
  • Openpose
  • Opensim
  • Robustness
  • Sports performance analysis

ASJC Scopus subject areas

  • Analytical Chemistry
  • Information Systems
  • Atomic and Molecular Physics, and Optics
  • Biochemistry
  • Instrumentation
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Pose2sim: An end-to-end workflow for 3D markerless sports kinematics—Part 1: Robustness'. Together they form a unique fingerprint.

Cite this