Title :
EMG and visual based HMI for hands-free control of an intelligent wheelchair
Author :
Wei, Lai ; Hu, Huosheng
Author_Institution :
Sch. of Comput. Sci. & Electron. Eng., Univ. of Essex, Colchester, UK
Abstract :
This paper presents a new human-machine interaction (HMI) method designed for hands-free control of electric wheelchairs. Both forehead electromyography (EMG) signals and color face image information is jointly used to identify winking and jaw clenching movements. Five winking and jaw clenching movement patterns are selected and classified, mapping into five control commands to drive a simulated wheelchair in an office environment. Six subjects participated in the experiments and the result shows that this new control method can work well and reliably.
Keywords :
electric vehicles; electromyography; face recognition; human computer interaction; image classification; image colour analysis; medical image processing; wheelchairs; EMG signals; HMI; color face image information; electromyography; hands-free control; human-machine interaction; intelligent wheelchair; Electromyography; Face; Feature extraction; Humans; Muscles; Training; Wheelchairs; Adaboost; Boosting; EMG; Eye Close Detection; Face Detection; Haar Features; SVMs; Wheelchair Controller;
Conference_Titel :
Intelligent Control and Automation (WCICA), 2010 8th World Congress on
Conference_Location :
Jinan
Print_ISBN :
978-1-4244-6712-9
DOI :
10.1109/WCICA.2010.5554766