Movement science needs different pose tracking algorithms

TL;DR

This paper argues that current pose tracking algorithms are inadequate for movement science needs, highlighting the importance of precise 3D movement data and proposing changes to improve their utility in scientific applications.

Contribution

The paper identifies the limitations of existing pose tracking algorithms for movement science and discusses necessary modifications to better serve scientific research needs.

Findings

Current algorithms use noisy ground truth data

Metrics do not prioritize relevant movement variables

Changes are needed for pose tracking to be scientifically useful

Abstract

Over the last decade, computer science has made progress towards extracting body pose from single camera photographs or videos. This promises to enable movement science to detect disease, quantify movement performance, and take the science out of the lab into the real world. However, current pose tracking algorithms fall short of the needs of movement science; the types of movement data that matter are poorly estimated. For instance, the metrics currently used for evaluating pose tracking algorithms use noisy hand-labeled ground truth data and do not prioritize precision of relevant variables like three-dimensional position, velocity, acceleration, and forces which are crucial for movement science. Here, we introduce the scientific disciplines that use movement data, the types of data they need, and discuss the changes needed to make pose tracking truly transformative for movement science.