Vision based interface system for hands free control of an intelligent wheelchair

Abstract

Background: Due to the shift of the age structure in today's populations, the necessities for developing the devices or technologies to support them have been increasing. Traditionally, the wheelchair, including powered and manual ones, is the most popular and important rehabilitation/ assistive device for the disabled and the elderly. However, it is still highly restricted especially for severely disabled. As a solution to this, the Intelligent Wheelchairs (IWs) have received considerable attention as mobility aids. The purpose of this work is to develop the IW interface for providing more convenient and efficient interface to the people the disability in their limbs.

Evaluating the performance of a face movement based wheelchair control interface in an indoor environment

“…Apart from using these singlemodality human bio-signals, computer vision information, speech information and multi-modality signals have been studied and applied as wheelchair control interface. Ju and Shin et al introduced a vision based intelligent wheelchair system developed for people with quadriplegic in [9]. Li and Tan [10] proposed a bimodal wheelchair control approach by integrating vision and speech signals.…”

Multi-modality — EMG and Visual Based Hands-Free Control of an Intelligent Wheelchair

“…With the recent advancement of machine and computing ability, many HMIs have been developed from computer vision information [11], speech information and multi-modality phenomenon. Ju and Shin et al introduce a vision-based intelligent wheelchair system developed for people with quadriplegic [6]. Li and Tan [7] propose a bimodal wheelchair control approach by integrating vision and speech controls.…”

Vision-Based Interfaces Applied to Assistive Robots

“…This approach is widely used [6][7][8] due to its instrumentation simplicity, its low cost and its noninvasive nature.…”

“…For this reason they are used as assistive robots, attracting the attention of many research groups around the world. Some authors focus their attention on the human-machine interface, proposing alternatives to the control input such as electromyography (EMG) [2,3], bioimpedance [4], BrainComputer Interface (BCI) [5], face detection [6][7][8], or hybrid approaches [9,10]. Others propose different control strategies in order to ensure velocity control, safety and robustness.…”

“…Furthermore, this system is not suitable for patients with severe brain and spinal injuries who do not have recognizable speech and haptic sensing abilities. The already-cited interface based on head gestures [8] integrates the Adaboost face detection algorithm and Camshift object tracking algorithm. The control architecture has two control modes: intelligent control and manual control.…”