Continuous and Simultaneous Gesture and Posture Recognition for Commanding a Robotic Wheelchair; Towards Spotting the Signal Patterns

TL;DR

This paper presents a novel signal pattern recognition approach for continuous, simultaneous gesture and posture classification to control a robotic wheelchair, achieving high accuracy and eliminating manual training intervention.

Contribution

It introduces a new methodology combining subspace clustering and sparse representation for automatic training and real-time recognition of gestures and postures.

Findings

Achieved 100% recognition accuracy on streaming signals.

Eliminated human intervention in training data preparation.

Implemented a real-time control system for robotic wheelchair.

Abstract

Spotting signal patterns with varying lengths has been still an open problem in the literature. In this study, we describe a signal pattern recognition approach for continuous and simultaneous classification of a tracked hand's posture and gestures and map them to steering commands for control of a robotic wheelchair. The developed methodology not only affords 100\% recognition accuracy on a streaming signal for continuous recognition, but also brings about a new perspective for building a training dictionary which eliminates human intervention to spot the gesture or postures on a training signal. In the training phase we employ a state of art subspace clustering method to find the most representative state samples. The recognition and training framework reveal boundaries of the patterns on the streaming signal with a successive decision tree structure intrinsically. We make use of the Collaborative ans Block Sparse Representation based classification methods for continuous gesture and posture recognition.