Combining Feature-Based and Direct Methods for Semi-dense Real-Time Stereo Visual Odometry

Visual motion estimation is challenging, due to high data rates, fast camera motions, featureless or repetitive environments, uneven lighting, and many other issues. In this work, we propose a two-layer approach for visual odometry with stereo cameras, which runs in real-time and combines feature-based matching with semi-dense direct image alignment. Our method initializes semi-dense depth estimation, which is computationally expensive, from motion that is tracked by a fast but robust feature point-based method. By that, we are not only able to efficiently estimate the pose of the camera with a high frame rate, but also to reconstruct the 3D structure of the environment at image gradients, which is useful, e.g., for mapping and obstacle avoidance. Experiments on datasets captured by a micro aerial vehicle (MAV) show that our approach is faster than state-of-the-art methods without losing accuracy. Moreover, our combined approach achieves promising results on the KITTI dataset, which is very challenging for direct methods, because of the low frame rate in conjunction with fast motion.