This project addresses the problem of gait estimation using visual and inertial data, as well as data-driven models of human motion. In particular, a batch lease squares (BLS) algorithm is presented that fuses data from a minimal set of sensors [two inertial measurement units (IMUs), on each foot, and the Google Glass's IMU-camera pair] along with stochastic constraints corresponding to the different walking phases, to estimate the person's head and feet poses. Subsequently, gait models are used to generate an animation of the lower-limbs' and trunk's motion. Experimental results against the VICON motion capture system demonstrate the accuracy of the proposed minimalistic, in terms of sensors, approach for determining a person's motion.
