Towards Accurate Loop Closure Detection in Semantic SLAM with 3D Semantic Covisibility Graphs

TL;DR

This paper presents SmSLAM+LCD, a novel approach integrating high-level 3D semantic data with low-level features to improve loop closure detection accuracy and reduce drift in semantic SLAM systems.

Contribution

It introduces a new method that combines 3D semantic covisibility graphs with traditional features for more accurate loop closure detection in SLAM.

Findings

Improved loop closure detection accuracy demonstrated.

Effective reduction of SLAM drift shown in tests.

Enhanced robustness over conventional methods.

Abstract

Loop closure is necessary for correcting errors accumulated in simultaneous localization and mapping (SLAM) in unknown environments. However, conventional loop closure methods based on low-level geometric or image features may cause high ambiguity by not distinguishing similar scenarios. Thus, incorrect loop closures can occur. Though semantic 2D image information is considered in some literature to detect loop closures, there is little work that compares 3D scenes as an integral part of a semantic SLAM system. This paper introduces an approach, called SmSLAM+LCD, integrated into a semantic SLAM system to combine high-level 3D semantic information and low-level feature information to conduct accurate loop closure detection and effective drift reduction. The effectiveness of our approach is demonstrated in testing results.