Human Pose Estimation from Sparse Inertial Measurements through Recurrent Graph Convolution

07/23/2021
by   Patrik Puchert, et al.
0

We propose the adjacency adaptive graph convolutional long-short term memory network (AAGC-LSTM) for human pose estimation from sparse inertial measurements, obtained from only 6 measurement units. The AAGC-LSTM combines both spatial and temporal dependency in a single network operation. This is made possible by equipping graph convolutions with adjacency adaptivity, which also allows for learning unknown dependencies of the human body joints. To further boost accuracy, we propose longitudinal loss weighting to consider natural movement patterns, as well as body-aware contralateral data augmentation. By combining these contributions, we are able to utilize the inherent graph nature of the human body, and can thus outperform the state of the art for human pose estimation from sparse inertial measurements.

READ FULL TEXT

page 1

page 7

research
05/21/2021

3D Human Pose Regression using Graph Convolutional Network

3D human pose estimation is a difficult task, due to challenges such as ...
research
03/23/2017

Sparse Inertial Poser: Automatic 3D Human Pose Estimation from Sparse IMUs

We address the problem of making human motion capture in the wild more p...
research
08/29/2023

Spatio-temporal MLP-graph network for 3D human pose estimation

Graph convolutional networks and their variants have shown significant p...
research
10/10/2018

Deep Inertial Poser: Learning to Reconstruct Human Pose from Sparse Inertial Measurements in Real Time

We demonstrate a novel deep neural network capable of reconstructing hum...
research
05/09/2023

Regular Splitting Graph Network for 3D Human Pose Estimation

In human pose estimation methods based on graph convolutional architectu...
research
08/06/2017

Long Short-Term Memory Kalman Filters:Recurrent Neural Estimators for Pose Regularization

One-shot pose estimation for tasks such as body joint localization, came...
research
05/05/2022

Koopman pose predictions for temporally consistent human walking estimations

We tackle the problem of tracking the human lower body as an initial ste...

Please sign up or login with your details

Forgot password? Click here to reset