This is the latest version of this eprint.
Ozdemir, A. orcid.org/0000-0003-0014-4699, Scerri, M. orcid.org/0000-0001-5740-037X, Barron, A.B. orcid.org/0000-0002-8135-6628 et al. (4 more authors) (2022) EchoVPR: Echo state networks for visual place recognition. IEEE Robotics and Automation Letters, 7 (2). pp. 4520-4527. ISSN 2377-3766
Abstract
Recognising previously visited locations is an important, but unsolved, task in autonomous navigation. Current visual place recognition (VPR) benchmarks typically challenge models to recover the position of a query image (or images) from sequential datasets that include both spatial and temporal components. Recently, Echo State Network (ESN) varieties have proven particularly powerful at solving machine learning tasks that require spatio-temporal modelling. These networks are simple, yet powerful neural architectures that - exhibiting memory over multiple time-scales and non-linear high-dimensional representations - can discover temporal relations in the data while still maintaining linearity in the learning time. In this letter, we present a series of ESNs and analyse their applicability to the VPR problem. We report that the addition of ESNs to pre-processed convolutional neural networks led to a dramatic boost in performance in comparison to non-recurrent networks in five out of six standard benchmarks (GardensPoint, SPEDTest, ESSEX3IN1, Oxford RobotCar, and Nordland), demonstrating that ESNs are able to capture the temporal structure inherent in VPR problems. Moreover, we show that models that include ESNs can outperform class-leading VPR models which also exploit the sequential dynamics of the data. Finally, our results demonstrate that ESNs improve generalisation abilities, robustness, and accuracy further supporting their suitability to VPR applications.
Metadata
Item Type: | Article |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works. Reproduced in accordance with the publisher's self-archiving policy. |
Keywords: | Reservoirs; Computational modeling; Training; Task analysis; Visualization; Benchmark testing; Image recognition |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield) |
Funding Information: | Funder Grant number ENGINEERING AND PHYSICAL SCIENCE RESEARCH COUNCIL EP/P006094/1 ENGINEERING AND PHYSICAL SCIENCE RESEARCH COUNCIL EP/S009647/1 ENGINEERING AND PHYSICAL SCIENCE RESEARCH COUNCIL EP/S030964/1 ENGINEERING AND PHYSICAL SCIENCE RESEARCH COUNCIL EP/V006339/1 |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 05 Jun 2023 12:00 |
Last Modified: | 05 Jan 2024 15:30 |
Status: | Published |
Publisher: | Institute of Electrical and Electronics Engineers (IEEE) |
Refereed: | Yes |
Identification Number: | 10.1109/lra.2022.3150505 |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:199933 |
Available Versions of this Item
-
EchoVPR: Echo state networks for visual place recognition. (deposited 05 Jan 2024 15:30)
- EchoVPR: Echo state networks for visual place recognition. (deposited 05 Jun 2023 12:00) [Currently Displayed]