Improved Trajectory Reconstruction for Markerless Pose Estimation

TL;DR

This paper improves markerless pose estimation accuracy by evaluating keypoint detectors and reconstruction algorithms, demonstrating that a top-down detector and implicit function reconstruction yield smooth, anatomically plausible trajectories with minimal noise, aiding gait analysis.

Contribution

It introduces an optimized approach combining a top-down keypoint detector and implicit function reconstruction for more accurate markerless pose estimation.

Findings

Achieved only 8mm noise in step width estimates compared to GaitRite.

Using a top-down detector improves keypoint detection accuracy.

Implicit function reconstruction produces smooth, anatomically plausible trajectories.

Abstract

Markerless pose estimation allows reconstructing human movement from multiple synchronized and calibrated views, and has the potential to make movement analysis easy and quick, including gait analysis. This could enable much more frequent and quantitative characterization of gait impairments, allowing better monitoring of outcomes and responses to interventions. However, the impact of different keypoint detectors and reconstruction algorithms on markerless pose estimation accuracy has not been thoroughly evaluated. We tested these algorithmic choices on data acquired from a multicamera system from a heterogeneous sample of 25 individuals seen in a rehabilitation hospital. We found that using a top-down keypoint detector and reconstructing trajectories with an implicit function enabled accurate, smooth and anatomically plausible trajectories, with a noise in the step width estimates compared to a GaitRite walkway of only 8mm.