Non-iterative planar visual odometry using a monocular camera

This paper presents a visual odometry system for ground vehicles using a single downward-facing camera. Our method calculates the motion from a monocular camera without using any probabilistic (non-deterministic) or iterative routines neither for motion estimation nor for outliers rejection. Accordingly, the proposed method improves the accuracy, the certainty, and the speed of the algorithm. Our method is validated for real data sets and shows competitive accuracy and robustness with a loop closure error reaching as low as 1.25% for a run of 460 meters.