Beyond ANN: Exploiting Structural Knowledge for Efficient Place Recognition

TL;DR

This paper introduces a fast, sequence-based place recognition method that efficiently identifies matching images in large databases, outperforming existing approaches in speed and accuracy while enabling online application.

Contribution

A novel sequence-based approach that exploits intra-database similarities for efficient, online place recognition without sacrificing performance.

Findings

Outperforms two state-of-the-art methods in multiple datasets

Reduces the number of image comparisons needed

Effective relocalization from sequence losses

Abstract

Visual place recognition is the task of recognizing same places of query images in a set of database images, despite potential condition changes due to time of day, weather or seasons. It is important for loop closure detection in SLAM and candidate selection for global localization. Many approaches in the literature perform computationally inefficient full image comparisons between queries and all database images. There is still a lack of suited methods for efficient place recognition that allow a fast, sparse comparison of only the most promising image pairs without any loss in performance. While this is partially given by ANN-based methods, they trade speed for precision and additional memory consumption, and many cannot find arbitrary numbers of matching database images in case of loops in the database. In this paper, we propose a novel fast sequence-based method for efficient place recognition that can be applied online. It uses relocalization to recover from sequence losses, and exploits usually available but often unused intra-database similarities for a potential detection of all matching database images for each query in case of loops or stops in the database. We performed extensive experimental evaluations over five datasets and 21 sequence combinations, and show that our method outperforms two state-of-the-art approaches and even full image comparisons in many cases, while providing a good tradeoff between performance and percentage of evaluated image pairs. Source code for Matlab will be provided with publication of this paper.