Bag-of-Word-Groups (BoWG): A Robust and Efficient Loop Closure Detection Method Under Perceptual Aliasing

TL;DR

The paper introduces BoWG, a novel loop closure detection method for SLAM that leverages word groups and temporal consistency to improve robustness and efficiency in perceptually aliased environments.

Contribution

BoWG's main innovation is the use of spatially co-occurring word groups and adaptive temporal similarity, enhancing loop closure detection in challenging environments.

Findings

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

Achieves 16 ms processing time per image on large datasets.

Demonstrates robustness in perceptually aliased environments.

Abstract

Loop closure is critical in Simultaneous Localization and Mapping (SLAM) systems to reduce accumulative drift and ensure global mapping consistency. However, conventional methods struggle in perceptually aliased environments, such as narrow pipes, due to vector quantization, feature sparsity, and repetitive textures, while existing solutions often incur high computational costs. This paper presents Bag-of-Word-Groups (BoWG), a novel loop closure detection method that achieves superior precision-recall, robustness, and computational efficiency. The core innovation lies in the introduction of word groups, which captures the spatial co-occurrence and proximity of visual words to construct an online dictionary. Additionally, drawing inspiration from probabilistic transition models, we incorporate temporal consistency directly into similarity computation with an adaptive scheme, substantially improving precision-recall performance. The method is further strengthened by a feature distribution analysis module and dedicated post-verification mechanisms. To evaluate the effectiveness of our method, we conduct experiments on both public datasets and a confined-pipe dataset we constructed. Results demonstrate that BoWG surpasses state-of-the-art methods, including both traditional and learning-based approaches, in terms of precision-recall and computational efficiency. Our approach also exhibits excellent scalability, achieving an average processing time of 16 ms per image across 17,565 images in the Bicocca25b dataset.