Video Stabilization for Robot Eye Using IMU-Aided Feature Tracker

In this paper, new video stabilization system is presented for robot eye. This system is biologically inspired by the human vestibulo-ocular reflex. Feature tracker with inertial sensor is proposed to estimate the motion more accurately and fast. The rotational motion measured by the inertial sensor is incorporated into the KLT tracker in order to predict a position of feature in current frame. This IMU-aided tracker improves a success rate and reduces an iteration number in tracking feature. Also, a Kalman filter is applied to remove unwanted camera motion. The experimental results show that the proposed video stabilization system has the characteristics of the high speed and accuracy in various conditions.