Probabilistic Egomotion for Stereo Visual Odometry

We present a novel approach of probabilistic egomotion methods for Stereo Visual Odometry using vehicles equipped with calibrated stereo cameras. We combine a dense probabilistic 5D egomotion estimation method with a sparse keypoint based stereo approach to provide high quality estimates of vehicle’s angular and linear velocities. To validate our approach, we perform two sets of experiments with a well known benchmarking dataset. First, we assess the quality of the raw velocity estimates in comparison to classical pose estimation algorithms. Second, we cascade our method’s instantaneous velocity estimates with an Extended Kalman Filter and compare its performance results with a well known open source stereo Visual Odometry library. The presented results compare favorably with state-of-the-art approaches, mainly in the estimation of the angular velocities, where significant improvements are achieved.