Omni

Figure 1: Reconstructing the subject's full-body pose is important to create immersive experiences in AR/VR. While external cameras limit the capture space and head-worn cameras can suffer from heavy self-occlusions in top-down views (A), our method reconstructs the body pose from electromagnetic (EM) field-based sensing (B). We leverage a customized system consisting of up to 12 wireless sensors measuring their 6D pose relative to a body-worn source. We adopt learned gradient descent (LGD) [53] to estimate SMPL pose and shape from as little as 6 EM sensors (C) tested on a newly captured dataset.

show abstract

Effects of Sensor Resolution and Localization Rate on the Performance of a Myokinetic Control Interface

Masiero

Sinibaldi

Clemente

et al. 2021

IEEE Sensors J.

View full text Add to dashboard Cite

Magnetic tracking systems have been widely investigated in biomedical engineering due to the transparency of the human body to static magnetic fields. We recently proposed a novel human-machine interface for prosthetic application, namely the myokinetic interface. This controls multi-articulated prostheses by tracking magnets implanted in the residual muscles of individuals with amputation. Previous studies in this area focused solely on the choice and tuning of the localization algorithm. Here, we addressed the role of the intrinsic properties of the sensors, by analysing their effects on the tracking accuracy and on the computation time of the localization algorithm, through experimentally-verified computer simulations. We observed that the tracking accuracy is primarily affected by the localization rate, which is directly related to the sampling frequency of the sensors, and less significantly affected by the sensor resolution. The computation time, instead, proved positively correlated to the number of MMs, and negatively correlated with the localization rate. Our results may contribute to the development of novel human-machine interfaces for prosthetic limbs and could be extended to a broad range of applications involving magnetic tracking.

show abstract

Omni

Cited by 14 publications

References 50 publications

Creative Design of Gaussian Sensor System with Encoding and Decoding

Creative Design of Gaussian Sensor System with Encoding and Decoding

EM-POSE: 3D Human Pose Estimation from Sparse Electromagnetic Trackers

Effects of Sensor Resolution and Localization Rate on the Performance of a Myokinetic Control Interface

Contact Info

Product

Resources

About