Human Behavior Recognition Using Foot Pressure Sensing Shoes

Abstract

To recognize human behavior in unlimited environments, sensing shoes for measuring foot pressure distribution were developed. Seven pressure sensors were installed on an insole, and a measurement module was embedded in the shoe. An analysis for discriminating the user's movements from the foot pressure distribution was examined, considering the movements, walking, running, standing, sitting, going upstairs and downstairs, and cycling. These seven actions were discriminated using feature quantities such as the average, standard deviation, maximum, and difference deviation extracted from the data of three sensors by discriminant analysis. The evaluation results showed highly accurate behavior recognition based on foot pressure at some points. In addition, by canonical discriminant analysis, six discriminant functions which classify the seven actions with an accuracy of 100% were derived by using feature quantities extracted from five sensors. The results confirmed that discriminant analysis can be used for automatically recognizing human behaviors based on foot pressure data.

Keywords

• human behavior recognition
• foot pressure
• discriminant analysis
• feature quantity
• wearable sensors