PGD-VIO: An Accurate Plane-Aided Visual-Inertial Odometry with Graph-Based Drift Suppression

TL;DR

This paper introduces PGD-VIO, a visual-inertial odometry system that integrates point and plane features with a graph-based drift suppression method, significantly improving localization accuracy in man-made environments.

Contribution

The paper presents a novel VIO approach combining point and plane features within an EKF framework and introduces a graph-based drift detection strategy for long-term navigation.

Findings

Outperforms state-of-the-art methods in localization accuracy

Generates a compact, consistent plane map

Eliminates need for global bundle adjustment and loop closing

Abstract

Generally, high-level features provide more geometrical information compared to point features, which can be exploited to further constrain motions. Planes are commonplace in man-made environments, offering an active means to reduce drift, due to their extensive spatial and temporal observability. To make full use of planar information, we propose a novel visual-inertial odometry (VIO) using an RGBD camera and an inertial measurement unit (IMU), effectively integrating point and plane features in an extended Kalman filter (EKF) framework. Depth information of point features is leveraged to improve the accuracy of point triangulation, while plane features serve as direct observations added into the state vector. Notably, to benefit long-term navigation,a novel graph-based drift detection strategy is proposed to search overlapping and identical structures in the plane map so that the cumulative drift is suppressed subsequently. The experimental results on two public datasets demonstrate that our system outperforms state-of-the-art methods in localization accuracy and meanwhile generates a compact and consistent plane map, free of expensive global bundle adjustment and loop closing techniques.