ConvSequential-SLAM: A Sequence-based, Training-less Visual Place Recognition Technique for Changing Environments

TL;DR

ConvSequential-SLAM is a trainingless visual place recognition method that combines SeqSLAM and CoHOG techniques, utilizing sequence information and regional convolutional matching to achieve robust performance in changing environments.

Contribution

It introduces a novel handcrafted VPR approach that blends existing techniques to improve robustness against appearance and viewpoint changes without training.

Findings

Achieves state-of-the-art performance on public datasets.

Effectively handles appearance and viewpoint variations.

Provides insights into sequence length optimization.

Abstract

Visual Place Recognition (VPR) is the ability to correctly recall a previously visited place under changing viewpoints and appearances. A large number of handcrafted and deep-learning-based VPR techniques exist, where the former suffer from appearance changes and the latter have significant computational needs. In this paper, we present a new handcrafted VPR technique that achieves state-of-the-art place matching performance under challenging conditions. Our technique combines the best of 2 existing trainingless VPR techniques, SeqSLAM and CoHOG, which are each robust to conditional and viewpoint changes, respectively. This blend, namely ConvSequential-SLAM, utilises sequential information and block-normalisation to handle appearance changes, while using regional-convolutional matching to achieve viewpoint-invariance. We analyse content-overlap in-between query frames to find a minimum sequence length, while also re-using the image entropy information for environment-based sequence length tuning. State-of-the-art performance is reported in contrast to 8 contemporary VPR techniques on 4 public datasets. Qualitative insights and an ablation study on sequence length are also provided.