Stroke patients usually have difficulties to conduct rehabilitation training themselves, due to no rehabilitation evaluation in time and dependence on doctors. In order to solve this problem, this paper proposes a motion rehabilitation and evaluation system based on the Kinect gesture measuring technology combining VR technology as well as traditional method of stroke rehabilitation. Real-time rehabilitation motion feedback is achieved by using Kinect motion capturing, customized skeleton modeling, and virtual characters constructed in Unity3D. The jitter problem of virtual characters following motion using Kinect is solved. Fidelity and interactivity of virtual rehabilitation training is improved. Our experiment validated the feasibility of this system preliminarily.
With an ageing population problem increasingly prominent, the number of hemiplegia patients is growing caused by stroke, which has a high morbidity and high mortality rate . Stroke can lead to the dysfunction of the brain central nervous, often characterized by language, cognitive or motor dysfunction , . The medical rehabilitation mechanism of stroke is based on neural plasticity theory and the theory of mirror neurons .
Source: A motion rehabilitation self-training and evaluation system using Kinect – IEEE Xplore Document