Real-time Arm Skeleton Tracking using a Smartwatch


ArmTroi can achieve real-time 3D arm skeleton tracking using a smartwatch. The skeleton of each arm is determined from the locations of the elbow and wrist, whereas a smartwatch only senses a single point from the wrist. Result shows that the potential solution space is huge. This underconstrained nature fundamentally challenges the achievement of accurate and real-time arm skeleton tracking. In this study, we propose Hidden Markov Model (HMM) state reorganization and hierarchical search two methods to improve the heavyweight computation of the state-of-art arm tracking model [MobiSys'16] and achieve real-time tracking even on mobile phone.

Demo Video


Real-time Arm Skeleton Tracking and Gesture Inference Tolerant to Missing Wearable Sensors

Yang Liu, Zhenjiang Li, Zhidan Liu, Kaishun Wu

ACM MobiSys, 2019

[pdf] [slides] [source code]

Cite ArmTroi

title={Real-time arm skeleton tracking and gesture inference tolerant to missing wearable sensors},
author={Liu, Yang and Li, Zhenjiang and Liu, Zhidan and Wu, Kaishun},
booktitle={Proceedings of the 17th Annual International Conference on Mobile Systems, Applications, and Services},