# MRS-VPR: a multi-resolution sampling based global visual place recognition method

## TL;DR

MRS-VPR introduces a multi-resolution, sampling-based approach for visual place recognition that enhances efficiency and accuracy in long-term navigation, especially with smaller test sequences, by employing a coarse-to-fine search and particle filtering.

## Contribution

The paper presents a novel multi-resolution sampling method with a coarse-to-fine search and particle filter scheme, improving upon SeqSLAM for long-term visual place recognition.

## Key findings

- Significantly faster matching than SeqSLAM.
- Maintains high accuracy in locating short trajectories.
- Performs better with smaller test sequences.

## Abstract

Place recognition and loop closure detection are challenging for long-term visual navigation tasks. SeqSLAM is considered to be one of the most successful approaches to achieving long-term localization under varying environmental conditions and changing viewpoints. It depends on a brute-force, time-consuming sequential matching method. We propose MRS-VPR, a multi-resolution, sampling-based place recognition method, which can significantly improve the matching efficiency and accuracy in sequential matching. The novelty of this method lies in the coarse-to-fine searching pipeline and a particle filter-based global sampling scheme, that can balance the matching efficiency and accuracy in the long-term navigation task. Moreover, our model works much better than SeqSLAM when the testing sequence has a much smaller scale than the reference sequence. Our experiments demonstrate that the proposed method is efficient in locating short temporary trajectories within long-term reference ones without losing accuracy compared to SeqSLAM.