HuGaDB: Human Gait Database for Activity Recognition from Wearable\n Inertial Sensor Networks

Abstract

This paper presents a human gait data collection for analysis and activity\nrecognition consisting of continues recordings of combined activities, such as\nwalking, running, taking stairs up and down, sitting down, and so on; and the\ndata recorded are segmented and annotated. Data were collected from a body\nsensor network consisting of six wearable inertial sensors (accelerometer and\ngyroscope) located on the right and left thighs, shins, and feet. Additionally,\ntwo electromyography sensors were used on the quadriceps (front thigh) to\nmeasure muscle activity. This database can be used not only for activity\nrecognition but also for studying how activities are performed and how the\nparts of the legs move relative to each other. Therefore, the data can be used\n(a) to perform health-care-related studies, such as in walking rehabilitation\nor Parkinson's disease recognition, (b) in virtual reality and gaming for\nsimulating humanoid motion, or (c) for humanoid robotics to model humanoid\nwalking. This dataset is the first of its kind which provides data about human\ngait in great detail. The database is available free of charge\nhttps://github.com/romanchereshnev/HuGaDB.\n