Visual Place Recognition with Probabilistic Vertex Voting

TL;DR

This paper introduces a probabilistic scoring method for visual place recognition that improves accuracy and efficiency by leveraging descriptor voting and binomial distribution modeling, enabling high-precision loop closure detection.

Contribution

It presents a novel probabilistic voting framework for visual place recognition that eliminates heuristic parameters and enhances accuracy and efficiency in both 2D-2D and 2D-3D matching scenarios.

Findings

Achieves state-of-the-art results on challenging datasets.

Maintains high accuracy with low-dimensional descriptors.

Enables efficient online operation with fast nearest neighbor retrieval.

Abstract

We propose a novel scoring concept for visual place recognition based on nearest neighbor descriptor voting and demonstrate how the algorithm naturally emerges from the problem formulation. Based on the observation that the number of votes for matching places can be evaluated using a binomial distribution model, loop closures can be detected with high precision. By casting the problem into a probabilistic framework, we not only remove the need for commonly employed heuristic parameters but also provide a powerful score to classify matching and non-matching places. We present methods for both a 2D-2D pose-graph vertex matching and a 2D-3D landmark matching based on the above scoring. The approach maintains accuracy while being efficient enough for online application through the use of compact (low dimensional) descriptors and fast nearest neighbor retrieval techniques. The proposed methods are evaluated on several challenging datasets in varied environments, showing state-of-the-art results with high precision and high recall.