Evaluation of Pattern Recognition Methods for Head Gesture-Based Interface of a Virtual Reality Helmet Equipped with a Single IMU Sensor.

Marcin Piekarczyk,Tomasz Hachaj

doi:10.3390/s19245408

Abstract

The motivation of this paper is to examine the effectiveness of state-of-the-art and newly proposed motion capture pattern recognition methods in the task of head gesture classifications. The head gestures are designed for a user interface that utilizes a virtual reality helmet equipped with an internal measurement unit (IMU) sensor that has 6-axis accelerometer and gyroscope. We will validate a classifier that uses Principal Components Analysis (PCA)-based features with various numbers of dimensions, a two-stage PCA-based method, a feedforward artificial neural network, and random forest. Moreover, we will also propose a Dynamic Time Warping (DTW) classifier trained with extension of DTW Barycenter Averaging (DBA) algorithm that utilizes quaternion averaging and a bagged variation of previous method (DTWb) that utilizes many DTW classifiers that perform voting. The evaluation has been performed on 975 head gesture recordings in seven classes acquired from 12 persons. The highest value of recognition rate in a leave-one-out test has been obtained for DTWb and it equals 0.975 (0.026 better than the best of state-of-the-art methods to which we have compared our approach). Among the most important applications of the proposed method is improving life quality for people who are disabled below the neck by supporting, for example, an assistive autonomous power chair with a head gesture interface or remote controlled interfaces in robotics.

Highlights

Virtual reality helmet (VRH) is a head-mounted device that allows a user to interact with a three-dimensional virtual reality environment by displaying stereovision images
Those methods utilize various classifiers depending on motions features selection, for example Dynamic Time Warping (DTW), Hidden Markov Models (HMM) or when features are derived after processing original motion capture data nearest neighbor classifier (NN), support vector machine (SVM) or neural network [12,13]
The recognition rate is defined as number of correctly classified objects of that class divided by all objects of that class, the error rate equals 1− recognition rate

Summary

Introduction

Virtual reality helmet (VRH) is a head-mounted device that allows a user to interact with a three-dimensional virtual reality environment by displaying stereovision images. VRH analyses user’s head position and adjusts the virtual camera position in the virtual reality world in order to enhance the immersive experience. Virtual reality systems might contain several types of user interface depending on the application of such solution. It can be either full-body motion capture (MoCap), both visual and sensor-based, hand gestures-based interface supported by various handled devices, gaze-based interface or head motion interface ( called head gestures interface). The last type of interface might be used without any additional handled devices and motion acquisition systems beside internal measurement unit (IMU). Gaze gestures are a promising input technology for wearable devices, especially in smart glasses form because gaze gesturing is unobtrusive and leaves the hands free for other tasks [1,2]

Methods

Results

Discussion

Conclusion