Fine Grained Group Gesture Detection Using Smartwatches

Abstract

People may perform synchronized activities in a group setting. It is helpful to provide notifications to users and also the group leader whether people are in sync. This work aims to provide this support via analyzing motion data collected from wearable devices. We collected experimental data from smart watches worn by people, applied signal processing algorithms in both time and frequency domains for identification of the fine-grained group gesture status. We further developed a prototype system consisting of a smart watch, a smartphone, and a server. Our simulation results and actual system implementation demonstrate the feasibility of our approaches.