Loosely-Coupled Semi-Direct Monocular SLAM

TL;DR

This paper introduces a semi-direct monocular SLAM system that combines direct and feature-based methods through multi-level optimization, achieving real-time performance and improved accuracy.

Contribution

It presents a novel loosely-coupled framework that integrates direct odometry with feature-based SLAM using three parallel optimization levels.

Findings

Outperforms state-of-the-art monocular SLAM in accuracy

Operates in real-time with limited feature-based computations

Demonstrates robustness across benchmark datasets

Abstract

We propose a novel semi-direct approach for monocular simultaneous localization and mapping (SLAM) that combines the complementary strengths of direct and feature-based methods. The proposed pipeline loosely couples direct odometry and feature-based SLAM to perform three levels of parallel optimizations: (1) photometric bundle adjustment (BA) that jointly optimizes the local structure and motion, (2) geometric BA that refines keyframe poses and associated feature map points, and (3) pose graph optimization to achieve global map consistency in the presence of loop closures. This is achieved in real-time by limiting the feature-based operations to marginalized keyframes from the direct odometry module. Exhaustive evaluation on two benchmark datasets demonstrates that our system outperforms the state-of-the-art monocular odometry and SLAM systems in terms of overall accuracy and robustness.