Gesture Recognition based on Long-Short Term Memory Cells using Smartphone IMUs

TL;DR

This paper presents a gesture recognition system using LSTM neural networks on smartphone IMU data, achieving classification of ten gestures based on accelerometer and gyroscope signals.

Contribution

The study introduces an LSTM-based approach for gesture recognition utilizing smartphone IMU data, with experiments on sensor selection and model performance analysis.

Findings

LSTM models effectively classify gestures from IMU data.

Sensor selection impacts recognition accuracy.

Proposed methods outperform baseline approaches.

Abstract

Over the last few decades, Smartphone technology has seen significant improvements. Enhancements specific to built-in Inertial Measurement Units (IMUs) and other dedicated sensors of the smartphones(which are often available as default) such as- Accelerometer, Gyroscope, Magnetometer, Fingerprint reader, Proximity and Ambient light sensors have made devices smarter and the interaction seamless. Gesture recognition using these smart phones have been experimented with many techniques. In this solution, a Recurrent Neural Network (RNN) approach, LSTM (Long-Short Term Memory Cells) has been used to classify ten different gestures based on data from Accelerometer and Gyroscope. Selection of sensor data (Accelerometer and Gyroscope) was based on the ones that provided maximum information regarding the movement and orientation of the phone. Various models were experimented in this project, the results of which are presented in the later sections. Furthermore, the properties and characteristics of the collected data were studied and a set of improvements have been suggested in the future work section.