Work

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

Year: 2025

Type: article

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.

Source: IEEE Robotics and Automation Letters

DOI: 10.1109/lra.2025.3544522

Authors: Changshi Mu, Daquan Feng, Qi Zheng, Yuan Zhuang

Institutions: Shenzhen University, Wuhan University, State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing

Language: English

Topic: Robotics and Sensor-Based Localization

Subfield: Aerospace Engineering

Field: Engineering

Domain: Physical Sciences

Open Access status: green

Funder: National Outstanding Youth Science Fund Project of National Natural Science Foundation of China

Award: G2469021360