ConvSequential-SLAM

A Sequence-Based, Training-Less Visual Place Recognition Technique for Changing Environments

Journal article (2021)

Authors

Mihnea Alexandru Tomita University of Essex
M. Zaffar Intelligent Vehicles - Mechanical, Maritime and Materials Engineering
Michael J. Milford Queensland University of Technology
Klaus D. McDonald-Maier University of Essex
Shoaib Ehsan University of Essex
Research Group
Intelligent Vehicles (Mechanical, Maritime and Materials Engineering) (TU Delft)
Copyright: © 2021 Mihnea Alexandru Tomia, M. Zaffar, Michael J. Milford, Klaus D. McDonald-Maier, Shoaib Ehsan
DOI: https://doi.org/10.1109/ACCESS.2021.3107778
More Info
expand_more

Published Date

2021

Language

English

Faculty

Mechanical, Maritime and Materials Engineering

Department

Cognitive Robotics

Research Group

Intelligent Vehicles

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, namely ConvSequential-SLAM, that achieves state-of-the-art place matching performance under challenging conditions. We utilise 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 9 contemporary VPR techniques on 4 public datasets. Qualitative insights and an ablation study on sequence length are also provided.