Design of an Antagonistic Exercise Support System Using a Depth Image Sensor (original) (raw)

Proceedings of the 10th EAI International Conference on Pervasive Computing Technologies for Healthcare, 2016

Abstract

Dementia is one of the main reasons for elderly people becoming dependent on care. In addition to lifestyle improvements, it is thought that cognitive function exercises and motor function exercises are also effective for the prevention of dementia. Antagonistic exercise, which involves performing different movements with the upper and lower limbs on the left and right sides, is a form of exercise that uses cognitive and motor functions at the same time. Preventive care specialists that can lead this sort of exercise are few in number compared with elderly people, and are under a heavy burden. Therefore, there is a need for an exercise support system that can reduce the burden on specialists. On the other hand, the Kinect has become popular as a low-cost device that can acquire human actions. The Kinect uses a depth image sensor to obtain precise measurements of human joint movements, and can thus be used to recognize antagonistic exercises. In this study we designed and implemented an antagonistic exercise support system using a Kinect. To recognize exercises, data representing the positions of the person's joints as acquired from the depth sensor is used to evaluate the performance of exercises and provide real-time feedback. This system uses audiovisual displays to explain to elderly people how to perform the exercises, and displays model images to promote the exercises. We have also prepared four types of rhythm game where people can perform exercises in time with music. We performed recognition accuracy tests with young and elderly test subjects.

Susumu Shibusawa hasn't uploaded this paper.

Let Susumu know you want this paper to be uploaded.

Ask for this paper to be uploaded.