MonoSLAM: Robust Monocular SLAM with Global Structure Optimization

2025-03-12

AI Summary

Monocular visual SLAM suffers from pose drift and mapping failure in low-texture environments due to insufficient feature points. To address this, this paper proposes a robust monocular SLAM framework integrating points, lines, and vanishing points. We introduce a novel line-based vanishing point estimation method and, for the first time, construct a weighted global primitive model across non-overlapping multi-frame regions. Furthermore, we formulate a joint multi-frame reprojection error optimization framework where points, lines, and vanishing points serve as geometric observations, optimized collaboratively via nonlinear least squares. Extensive evaluations on standard benchmarks—including TUM RGB-D and ICL-NUIM—demonstrate that our approach reduces absolute trajectory error (ATE) by 32.7% on average in texture-poor scenes, outperforming state-of-the-art methods such as ORB-SLAM2 and LSD-SLAM. The framework achieves both high accuracy and strong robustness under challenging low-texture conditions.

Technology Category

• Computer Vision: Motion & Tracking
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Learning with Manifolds

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

This paper presents a robust monocular visual SLAM system that simultaneously utilizes point, line, and vanishing point features for accurate camera pose estimation and mapping. To address the critical challenge of achieving reliable localization in low-texture environments, where traditional point-based systems often fail due to insufficient visual features, we introduce a novel approach leveraging Global Primitives structural information to improve the system's robustness and accuracy performance. Our key innovation lies in constructing vanishing points from line features and proposing a weighted fusion strategy to build Global Primitives in the world coordinate system. This strategy associates multiple frames with non-overlapping regions and formulates a multi-frame reprojection error optimization, significantly improving tracking accuracy in texture-scarce scenarios. Evaluations on various datasets show that our system outperforms state-of-the-art methods in trajectory precision, particularly in challenging environments.

Problem

• Improves camera pose estimation in low-texture environments
• Enhances SLAM robustness using point, line, and vanishing point features
• Optimizes global structure for better tracking in texture-scarce scenarios

Innovation

• Uses point, line, vanishing point features
• Leverages Global Primitives structural information
• Proposes weighted fusion strategy for accuracy