A Robust and Efficient Visual-Inertial Initialization with Probabilistic Normal Epipolar Constraint

TL;DR

This paper introduces a robust visual-inertial initialization method that uses probabilistic normal epipolar constraints and fuses IMU and visual data to improve accuracy and efficiency in pose estimation, especially in challenging scenes.

Contribution

It extends the rotation-translation-decoupled framework with new uncertainty parameters and optimization modules, incorporating probabilistic normal epipolar constraints for better initialization.

Findings

Reduces gyroscope bias and rotation errors by 16% and 4% on EuRoC dataset.

Decreases gravity error by 29% on EuRoC dataset.

Lowers gravity and scale errors by 14.2% and 5.7% on TUM dataset.

Abstract

Accurate and robust initialization is essential for Visual-Inertial Odometry (VIO), as poor initialization can severely degrade pose accuracy. During initialization, it is crucial to estimate parameters such as accelerometer bias, gyroscope bias, initial velocity, gravity, etc. Most existing VIO initialization methods adopt Structure from Motion (SfM) to solve for gyroscope bias. However, SfM is not stable and efficient enough in fast-motion or degenerate scenes. To overcome these limitations, we extended the rotation-translation-decoupled framework by adding new uncertainty parameters and optimization modules. First, we adopt a gyroscope bias estimator that incorporates probabilistic normal epipolar constraints. Second, we fuse IMU and visual measurements to solve for velocity, gravity, and scale efficiently. Finally, we design an additional refinement module that effectively reduces gravity and scale errors. Extensive EuRoC dataset tests show that our method reduces gyroscope bias and rotation errors by 16\% and 4\% on average, and gravity error by 29\% on average. On the TUM dataset, our method reduces the gravity error and scale error by 14.2\% and 5.7\% on average respectively. The source code is available at https://github.com/MUCS714/DRT-PNEC.git