The Probabilistic Normal Epipolar Constraint for Frame-To-Frame Rotation Optimization under Uncertain Feature Positions

TL;DR

This paper introduces the probabilistic normal epipolar constraint (PNEC), a new method that accounts for feature uncertainty to improve relative rotation estimation in camera pose problems, demonstrating superior accuracy over existing methods.

Contribution

The paper presents PNEC, a novel probabilistic formulation that incorporates feature uncertainties into the epipolar constraint, enhancing rotation estimation accuracy in real-time applications.

Findings

PNEC outperforms NEC and other algorithms on synthetic data.

PNEC improves rotation estimates in monocular odometry on KITTI dataset.

The method maintains real-time performance while increasing accuracy.

Abstract

The estimation of the relative pose of two camera views is a fundamental problem in computer vision. Kneip et al. proposed to solve this problem by introducing the normal epipolar constraint (NEC). However, their approach does not take into account uncertainties, so that the accuracy of the estimated relative pose is highly dependent on accurate feature positions in the target frame. In this work, we introduce the probabilistic normal epipolar constraint (PNEC) that overcomes this limitation by accounting for anisotropic and inhomogeneous uncertainties in the feature positions. To this end, we propose a novel objective function, along with an efficient optimization scheme that effectively minimizes our objective while maintaining real-time performance. In experiments on synthetic data, we demonstrate that the novel PNEC yields more accurate rotation estimates than the original NEC and several popular relative rotation estimation algorithms. Furthermore, we integrate the proposed method into a state-of-the-art monocular rotation-only odometry system and achieve consistently improved results for the real-world KITTI dataset.