Accurate and Robust Scale Recovery for Monocular Visual Odometry Based on Plane Geometry
This addresses scale recovery for applications like self-driving cars where loop closure is unreliable, though it is incremental by building on prior environment-based methods.
The paper tackles scale ambiguity in monocular visual odometry by developing a light-weight framework that uses ground plane geometry to recover scale, achieving state-of-the-art translation accuracy on the KITTI dataset with a 20Hz frequency.
Scale ambiguity is a fundamental problem in monocular visual odometry. Typical solutions include loop closure detection and environment information mining. For applications like self-driving cars, loop closure is not always available, hence mining prior knowledge from the environment becomes a more promising approach. In this paper, with the assumption of a constant height of the camera above the ground, we develop a light-weight scale recovery framework leveraging an accurate and robust estimation of the ground plane. The framework includes a ground point extraction algorithm for selecting high-quality points on the ground plane, and a ground point aggregation algorithm for joining the extracted ground points in a local sliding window. Based on the aggregated data, the scale is finally recovered by solving a least-squares problem using a RANSAC-based optimizer. Sufficient data and robust optimizer enable a highly accurate scale recovery. Experiments on the KITTI dataset show that the proposed framework can achieve state-of-the-art accuracy in terms of translation errors, while maintaining competitive performance on the rotation error. Due to the light-weight design, our framework also demonstrates a high frequency of 20Hz on the dataset.