Multi-view Pose Fusion for Occlusion-Aware 3D Human Pose Estimation

TL;DR

This paper introduces a multi-view fusion method for robust 3D human pose estimation that effectively handles occlusions in human-robot collaboration scenarios, outperforming existing techniques.

Contribution

The paper proposes a novel multi-view fusion approach using monocular 3D skeletons and reprojection error optimization with limb symmetry constraints for improved occlusion robustness.

Findings

Outperforms state-of-the-art multi-view pose estimation methods.

Shows superior performance on occluded scenarios with synthetic and real data.

Demonstrates effectiveness in real human-robot collaboration environments.

Abstract

Robust 3D human pose estimation is crucial to ensure safe and effective human-robot collaboration. Accurate human perception,however, is particularly challenging in these scenarios due to strong occlusions and limited camera viewpoints. Current 3D human pose estimation approaches are rather vulnerable in such conditions. In this work we present a novel approach for robust 3D human pose estimation in the context of human-robot collaboration. Instead of relying on noisy 2D features triangulation, we perform multi-view fusion on 3D skeletons provided by absolute monocular methods. Accurate 3D pose estimation is then obtained via reprojection error optimization, introducing limbs length symmetry constraints. We evaluate our approach on the public dataset Human3.6M and on a novel version Human3.6M-Occluded, derived adding synthetic occlusions on the camera views with the purpose of testing pose estimation algorithms under severe occlusions. We further validate our method on real human-robot collaboration workcells, in which we strongly surpass current 3D human pose estimation methods. Our approach outperforms state-of-the-art multi-view human pose estimation techniques and demonstrates superior capabilities in handling challenging scenarios with strong occlusions, representing a reliable and effective solution for real human-robot collaboration setups.