SemanticTopoLoop: Semantic Loop Closure With 3D Topological Graph Based on Quadric-Level Object Map

TL;DR

This paper introduces a novel semantic loop closure approach in SLAM that leverages 3D topological graphs of objects, improving accuracy and robustness over traditional appearance-based methods.

Contribution

It proposes a new object-level data association method and a semantic loop closure technique based on quadric-level object map topology, enhancing SLAM performance.

Findings

Outperforms state-of-the-art methods in precision and recall

Demonstrates robustness in diverse real-world scenarios

Improves localization accuracy significantly

Abstract

Loop closure, as one of the crucial components in SLAM, plays an essential role in correcting the accumulated errors. Traditional appearance-based methods, such as bag-of-words models, are often limited by local 2D features and the volume of training data, making them less versatile and robust in real-world scenarios, leading to missed detections or false positives detections in loop closure. To address these issues, we first propose a object-level data association method based on multi-level verification, which can associate 2D semantic features of current frame with 3D objects landmarks of map. Next, taking advantage of these association relations, we introduce a semantic loop closure method based on quadric-level object map topology, which represents scenes through the topological graph of objects and achieves accurate loop closure at a wide field of view by comparing differences in the topological graphs. Finally, we integrate these two methods into a complete object-aware SLAM system. Qualitative experiments and ablation studies demonstrate the effectiveness and robustness of the proposed object-level data association algorithm. Quantitative experiments show that our semantic loop closure method outperforms existing state-of-the-art methods in terms of precision, recall and localization accuracy metrics.