MLINE-VINS: Robust Monocular Visual-Inertial SLAM With Flow Manhattan and Line Features

2025-03-03

AI Summary

Monocular visual-inertial odometry (VIO) suffers from unstable line-feature tracking in structured environments and difficulty in maintaining consistent Manhattan-frame alignment and optimization. To address these challenges, we propose MLINE-VINS—a robust visual-inertial SLAM system integrating line features with the Manhattan-world assumption. Its key contributions are: (1) a novel geometric line optical flow algorithm enabling detection- and descriptor-free, continuous tracking of variable-length line segments; (2) an online Manhattan-frame tracking-and-detection module coupled with a dynamic alignment mechanism to the VIO coordinate frame; and (3) a tightly coupled backend jointly optimizing Manhattan-frame consistency and global structural constraints. Extensive experiments on multiple public and custom datasets demonstrate that MLINE-VINS significantly improves pose estimation accuracy and long-trajectory robustness, outperforming state-of-the-art monocular VIO methods in comprehensive evaluations.

Technology Category

• Computer Vision: Motion & Tracking
• Intelligent Robots: State Estimation
• Machine Learning: Multi-instance/Multi-view Learning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

In this paper we introduce MLINE-VINS, a novel monocular visual-inertial odometry (VIO) system that leverages line features and Manhattan Word assumption. Specifically, for line matching process, we propose a novel geometric line optical flow algorithm that efficiently tracks line features with varying lengths, whitch is do not require detections and descriptors in every frame. To address the instability of Manhattan estimation from line features, we propose a tracking-by-detection module that consistently tracks and optimizes Manhattan framse in consecutive images. By aligning the Manhattan World with the VIO world frame, the tracking could restart using the latest pose from back-end, simplifying the coordinate transformations within the system. Furthermore, we implement a mechanism to validate Manhattan frames and a novel global structural constraints back-end optimization. Extensive experiments results on vairous datasets, including benchmark and self-collected datasets, show that the proposed approach outperforms existing methods in terms of accuracy and long-range robustness. The source code of our method is available at: https://github.com/LiHaoy-ux/MLINE-VINS.

Problem

• Enhances monocular visual-inertial SLAM with line features and Manhattan World assumption.
• Improves line feature tracking using a novel geometric line optical flow algorithm.
• Stabilizes Manhattan frame estimation with a tracking-by-detection module and global optimization.

Innovation

• Geometric line optical flow for feature tracking
• Tracking-by-detection for Manhattan frame optimization
• Global structural constraints in back-end optimization