SUPER: Seated Upper Body Pose Estimation using mmWave Radars

TL;DR

This paper introduces SUPER, a novel mmWave radar-based framework for accurately estimating seated upper body poses, demonstrating significant improvements over existing methods and potential applications in human-machine interaction and safety.

Contribution

The paper presents a new radar data fusion algorithm and a lightweight neural network for high-precision seated upper body pose estimation using dual-mmWave radars.

Findings

SUPER outperforms baseline by 30-184% in accuracy.

Effective in diverse motion sequences and subjects.

Useful for hand-object interaction tasks.

Abstract

In industrial countries, adults spend a considerable amount of time sedentary each day at work, driving and during activities of daily living. Characterizing the seated upper body human poses using mmWave radars is an important, yet under-studied topic with many applications in human-machine interaction, transportation and road safety. In this work, we devise SUPER, a framework for seated upper body human pose estimation that utilizes dual-mmWave radars in close proximity. A novel masking algorithm is proposed to coherently fuse data from the radars to generate intensity and Doppler point clouds with complementary information for high-motion but small radar cross section areas (e.g., upper extremities) and low-motion but large RCS areas (e.g. torso). A lightweight neural network extracts both global and local features of upper body and output pose parameters for the Skinned Multi-Person Linear (SMPL) model. Extensive leave-one-subject-out experiments on various motion sequences from multiple subjects show that SUPER outperforms a state-of-the-art baseline method by 30 -- 184%. We also demonstrate its utility in a simple downstream task for hand-object interaction.