VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimator

VINS-Mono: надежный и универсальный моноокулярный визуально-инерциальный оцениватель состояния
Tong Qin, Peiliang Li, Shaojie Shen
2018-07-27

VINS-Monoloop detectionmonocular visual-inertial odometrypose graph optimizationpreintegrated IMU measurements
One camera and one low-cost inertial measurement unit (IMU) form a monocular visual-inertial system (VINS), which is the minimum sensor suite (in size, weight, and power) for the metric six degrees-of-freedom (DOF) state estimation. In this paper, we present VINS-Mono: a robust and versatile monocular visual-inertial state estimator. Our approach starts with a robust procedure for estimator initialization. A tightly coupled, nonlinear optimization-based method is used to obtain highly accurate visual-inertial odometry by fusing preintegrated IMU measurements and feature observations. A loop detection module, in combination with our tightly coupled formulation, enables relocalization with minimum computation. We additionally perform 4-DOF pose graph optimization to enforce the global consistency. Furthermore, the proposed system can reuse a map by saving and loading it in an efficient way. The current and previous maps can be merged together by the global pose graph optimization. We validate the performance of our system on public datasets and real-world experiments and compare against other state-of-the-art algorithms. We also perform an onboard closed-loop autonomous flight on the microaerial-vehicle platform and port the algorithm to an iOS-based demonstration. We highlight that the proposed work is a reliable, complete, and versatile system that is applicable for different applications that require high accuracy in localization. We open source our implementations for both PCs (https://github.com/HKUST-Aerial-Robotics/VINS-Mono) and iOS mobile devices (https://github.com/HKUST-Aerial-Robotics/VINS-Mobile).
1
Implementations for PC and iOS platforms were released as open source, supporting broad practical deployment.
2
Loop detection enables computationally efficient relocalization, while 4-DOF pose-graph optimization maintains global consistency.
3
The system combines robust initialization with tightly coupled nonlinear optimization, fusing preintegrated IMU measurements and visual features for accurate visual-inertial odometry.
4
The system was validated on public datasets, real-world experiments, onboard autonomous microaerial-vehicle flight, and an iOS demonstration, with comparisons against state-of-the-art methods.
5
VINS-Mono provides metric six-degree-of-freedom state estimation using only one camera and a low-cost IMU.
6
VINS-Mono supports efficient map saving, loading, and merging through global pose-graph optimization.

Monocular visual-inertial state estimation system (VINS-Mono) using one camera and one IMU

robust and versatile state-estimation performance, including visual-inertial odometry accuracy, initialization, relocalization, global consistency, and map reuse

Publication Details
Publication Date
2018-07-27
Journal
Publisher
ISSN
Cited by
4836
Access Type
Author Information
Authors
Tong Qin
Peiliang Li
Shaojie Shen
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%