Pose Estimation from Electromyographical Data using Convolutional Neural Networks

This work demonstrates the effectiveness of Convolutional Neural Networks in the task of pose estimation from Electromyographical (EMG) data. The Ninapro DB5 dataset was used to train the model to predict the hand pose from EMG data. The models predict the hand pose with an error rate of 4.6% for the EMG model, and 3.6% when accelerometry data is included. This shows that hand pose can be effectively estimated from EMG data, which can be enhanced with accelerometry data.

[1]  Clément Gosselin,et al.  Deep Learning for Electromyographic Hand Gesture Signal Classification by Leveraging Transfer Learning , 2018, ArXiv.

[2]  Christian Szegedy,et al.  DeepPose: Human Pose Estimation via Deep Neural Networks , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Luca Benini,et al.  A Versatile Embedded Platform for EMG Acquisition and Gesture Recognition , 2015, IEEE Transactions on Biomedical Circuits and Systems.

[4]  Clément Gosselin,et al.  Deep Learning for Electromyographic Hand Gesture Signal Classification Using Transfer Learning , 2018, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[5]  Angkoon Phinyomark,et al.  EMG feature evaluation for improving myoelectric pattern recognition robustness , 2013, Expert Syst. Appl..

[6]  Jia Deng,et al.  Stacked Hourglass Networks for Human Pose Estimation , 2016, ECCV.

[7]  Manfredo Atzori,et al.  Comparison of six electromyography acquisition setups on hand movement classification tasks , 2017, PloS one.

[8]  Purushothaman Geethanjali,et al.  Myoelectric control of prosthetic hands: state-of-the-art review , 2016, Medical devices.

[9]  F. G. Pérez.  Orthopedic physical assessment , 2003 .

[10]  Ye Wang,et al.  Translating sEMG signals to continuous hand poses using recurrent neural networks , 2018, 2018 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI).

[11]  Robert D. Lipschutz,et al.  Targeted muscle reinnervation for real-time myoelectric control of multifunction artificial arms. , 2009, JAMA.

[12]  Xu Zhang,et al.  Random Forest-Based Recognition of Isolated Sign Language Subwords Using Data from Accelerometers and Surface Electromyographic Sensors , 2016, Sensors.