Gait feature extraction from foot video using image processing

Abstract

In recent years, Japan's declining birth rate and aging population have become serious problems. Under such circumstances, there is a concern about the shortage of caregivers in elderly care facilities, especially when looking after residents. Therefore, the introduction of camera-based monitoring systems in elderly care facilities could help reduce the burden on caregivers. However, caregivers may feel averse to being captured by surveillance cameras, so there is an issue of privacy. Our proposed solution to this problem is a camera-based monitoring system that focuses only on the feet of pedestrians. In this study, the foot video is compressed into a single feature image. This image is converted to an image called Flat Feet Image. Flat Feet Image and foot videos were used to extract gait features such as step length and gait velocity. Cross-validation with a support vector machine using the obtained gait features achieved an 87% accuracy.