IMUOptimize: A Data-Driven Approach to Optimal IMU Placement for Human Pose Estimation with Transformer Architecture

TL;DR

This paper introduces a data-driven method using transformer architecture to optimize IMU placement for human pose estimation, achieving superior accuracy with fewer sensors and demonstrating the effectiveness of transformer models over traditional RNNs.

Contribution

It proposes a novel data-driven IMU placement strategy combined with a transformer-based model for improved human pose estimation from IMU data.

Findings

Transformer models outperform biRNNs in pose reconstruction.

Optimal IMU placement enhances accuracy with fewer sensors.

24 IMU locations with transformers match 6 IMU biRNN performance.

Abstract

This paper presents a novel approach for predicting human poses using IMU data, diverging from previous studies such as DIP-IMU, IMUPoser, and TransPose, which use up to 6 IMUs in conjunction with bidirectional RNNs. We introduce two main innovations: a data-driven strategy for optimal IMU placement and a transformer-based model architecture for time series analysis. Our findings indicate that our approach not only outperforms traditional 6 IMU-based biRNN models but also that the transformer architecture significantly enhances pose reconstruction from data obtained from 24 IMU locations, with equivalent performance to biRNNs when using only 6 IMUs. The enhanced accuracy provided by our optimally chosen locations, when coupled with the parallelizability and performance of transformers, provides significant improvements to the field of IMU-based pose estimation.