Research Repository

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

Tomia, Mihnea-Alexandru and Zaffar, Mubariz and Milford, Michael J and McDonald-Maier, Klaus D and Ehsan, Shoaib (2021) 'ConvSequential-SLAM: A Sequence-Based, Training-Less Visual Place Recognition Technique for Changing Environments.' IEEE Access, 9. pp. 118673-118683. ISSN 2169-3536

ConvSequential-SLAM_A_Sequence-Based_Training-Less_Visual_Place_Recognition_Technique_for_Changing_Environments.pdf - Published Version
Available under License Creative Commons Attribution.

Download (2MB) | Preview


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.

Item Type: Article
Uncontrolled Keywords: SLAM; sequence-based filtering; visual localization; visual place recognition
Divisions: Faculty of Science and Health
Faculty of Science and Health > Computer Science and Electronic Engineering, School of
SWORD Depositor: Elements
Depositing User: Elements
Date Deposited: 24 Jun 2022 11:14
Last Modified: 24 Jun 2022 11:15

Actions (login required)

View Item View Item