足元動画像からの歩行特徴抽出手法の検討

抄録

In recent years, the number of young people is decreasing and the number of elderly people is increasing in Japan. Therefore, one of the concerns is the declining working population. In nursing care facilities for the elderly, introducing a monitoring system using cameras is thought to help reduce the burden on caregivers. However, there is the issue of privacy. Here we proposed a camera-based monitoring system that only shows the feet of pedestrians. The purpose of this research is to extract gait features from video images in which only the pedestrian’s feet are visible by image processing. This system could extract the foot during standing as a binary image and it found to extract heel and toe of foot during standing with high accuracy.