Improved Bag-of-Words Image Retrieval with Geometric Constraints for Ground Texture Localization

TL;DR

This paper introduces an enhanced bag-of-words image retrieval system utilizing geometric constraints, significantly improving ground texture localization accuracy and loop closure detection in SLAM applications.

Contribution

The paper presents a novel BoW approach with AKM vocabulary, soft assignment, and geometric constraints tailored for ground texture localization, offering high-accuracy and high-speed variants.

Findings

Higher accuracy in global localization

Improved precision and recall in loop closure detection

Effective replacement for existing BoW systems

Abstract

Ground texture localization using a downward-facing camera offers a low-cost, high-precision localization solution that is robust to dynamic environments and requires no environmental modification. We present a significantly improved bag-of-words (BoW) image retrieval system for ground texture localization, achieving substantially higher accuracy for global localization and higher precision and recall for loop closure detection in SLAM. Our approach leverages an approximate $k$-means (AKM) vocabulary with soft assignment, and exploits the consistent orientation and constant scale constraints inherent to ground texture localization. Identifying the different needs of global localization vs. loop closure detection for SLAM, we present both high-accuracy and high-speed versions of our algorithm. We test the effect of each of our proposed improvements through an ablation study and demonstrate our method's effectiveness for both global localization and loop closure detection. With numerous ground texture localization systems already using BoW, our method can readily replace other generic BoW systems in their pipeline and immediately improve their results.