Scaled Monocular SLAM for Walking People

In this paper we present a full-scaled real-time monocular SLAM using only a wearable camera. Assuming that the per-son is walking, the perception of the head oscillatory motion in the initial visual odometry estimate allows for the com-putation of a dynamic scale factor for static windows of N camera poses. Improving on this method we introduce a con-sistency test to detect non-walking situations and propose a sliding window approach to reduce the delay in the update of the scaled trajectory. We evaluate our approach experimen-tally on a unscaled visual odometry estimate obtained with a wearable camera along a path of 886 m. The results show a significant improvement respect to the initial unscaled esti-mate with a mean relative error of 0.91 % over the total trajec-tory length. Author Keywords monocular SLAM, visual odometry, wearable vision