Faster Deep Inertial Pose Estimation with Six Inertial Sensors
Open Access
Abstract
We propose a novel pose estimation method that can predict the full-body pose from six inertial sensors worn by the user. This method solves problems encountered in vision, such as occlusion or expensive deployment. We address several complex challenges. First, we use the SRU network structure instead of the bidirectional RNN structure used in previous work to reduce the computational effort of the model without losing its accuracy. Second, our model does not require joint position supervision to achieve the best results of the previous work. Finally, since sensor data tend to be noisy, we use SmoothLoss to reduce the impact of inertial sensors on pose estimation. The faster deep inertial poser model proposed in this paper can perform online inference at 90 FPS on the CPU. We reduce the impact of each error by more than 10% and increased the inference speed by 250% compared to the previous state of the art.Keywords
Funding Information
- Fundamental Research Funds for the Central Universities, China (XDJK2020B029)
- Major Transverse Project, China (SWU41015718, SWU2071095)
This publication has 22 references indexed in Scilit:
- 3D Human Pose Estimation in Video With Temporal Convolutions and Semi-Supervised Training2019
- Deep Autoencoder for Combined Human Pose Estimation and Body Model Upscaling2018
- Fusing Visual and Inertial Sensors with Semantics for 3D Human Pose EstimationInternational Journal of Computer Vision, 2018
- Motion database of disguised and non-disguised team handball penalty throws by novice and expert performersData in Brief, 2017
- Sparse Inertial Poser: Automatic 3D Human Pose Estimation from Sparse IMUsComputer Graphics Forum, 2017
- SMPLACM Transactions on Graphics, 2015
- Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural EnvironmentsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- HumanEva: Synchronized Video and Motion Capture Dataset and Baseline Algorithm for Evaluation of Articulated Human MotionInternational Journal of Computer Vision, 2009
- Bidirectional recurrent neural networksIEEE Transactions on Signal Processing, 1997
- Long Short-Term MemoryNeural Computation, 1997