Introduction

This is the website for our paper " Skeleton-aware Graph-based Adversarial Networks for Human Pose Estimation from Sparse IMUs "

Recently, sparse-inertial human pose estimation (SI-HPE) with only a few IMUs has shown great potential in various fields. The most advanced work in this area achieved fairish results using only six IMUs. However, there are still two major issues that remain to be addressed. First, existing methods typically treat SI-HPE as a temporal sequential learning problem and often ignore the important spatial prior of skeletal topology. Second, their results show poor generalization, varying significantly across different datasets, which can be attributed to overfitting caused by fine-tuning on data with insufficient diversity. To address these issues, we propose ``Graph-based Adversarial Inertial Poser (GAIP)'', which tracks body movements using sparse data from six IMUs. To make full use of the spatial prior, we design a multi-stage pose regressor with graph convolution to explicitly learn the skeletal topology. A joint position loss is also introduced to implicitly mine spatial information. To enhance the generalization ability, we propose supervising the pose regression with an adversarial loss from a discriminator, bringing the ability of adversarial networks to learn implicit constraints into full play. Additionally, we construct a real dataset that includes hip support movements and a synthetic dataset containing various motion categories to enrich the diversity of inertial data for SI-HPE. Extensive experiments show that GAIP yields results with more precise limb movement amplitude and relative joint positions, and its outputs are with smaller joint angle and position errors than the state-of-the-art counterparts.

Source Codes

Get the code

Use git to clone the repository:

    git clone git@github.com:ST-ern/Ka_GAIP.git

Demo Video

The following is a demo video of our GAIP's huamn pose evaluation on different datasets.

The following ia a demo video of our recording example.

Last update: Aug. 22, 2023