Arcanjo, Bruno and Ferrarini, Bruno and Fasli, Maria and Milford, Michael and McDonald-Maier, Klaus D and Ehsan, Shoaib (2024) Aggregating Multiple Bio-Inspired Image Region Classifiers for Effective and Lightweight Visual Place Recognition. IEEE Robotics and Automation Letters, 9 (4). pp. 3315-3322. DOI https://doi.org/10.1109/lra.2024.3367275
Arcanjo, Bruno and Ferrarini, Bruno and Fasli, Maria and Milford, Michael and McDonald-Maier, Klaus D and Ehsan, Shoaib (2024) Aggregating Multiple Bio-Inspired Image Region Classifiers for Effective and Lightweight Visual Place Recognition. IEEE Robotics and Automation Letters, 9 (4). pp. 3315-3322. DOI https://doi.org/10.1109/lra.2024.3367275
Arcanjo, Bruno and Ferrarini, Bruno and Fasli, Maria and Milford, Michael and McDonald-Maier, Klaus D and Ehsan, Shoaib (2024) Aggregating Multiple Bio-Inspired Image Region Classifiers for Effective and Lightweight Visual Place Recognition. IEEE Robotics and Automation Letters, 9 (4). pp. 3315-3322. DOI https://doi.org/10.1109/lra.2024.3367275
Abstract
Visual place recognition (VPR) enables autonomous systems to localize themselves within an environment using image information. While VPR techniques built upon a Convolutional Neural Network (CNN) backbone dominate state-of-the-art VPR performance, their high computational requirements make them unsuitable for platforms equipped with low-end hardware. Recently, a lightweight VPR system based on multiple bio-inspired classifiers, dubbed DrosoNets, has been proposed, achieving great computational efficiency at the cost of reduced absolute place retrieval performance. In this letter, we propose a novel multi-DrosoNet localization system, dubbed RegionDrosoNet, with significantly improved VPR performance, while preserving a low-computational profile. Our approach relies on specializing distinct groups of DrosoNets on differently sliced partitions of the original images, increasing model differentiation. Furthermore, we introduce a novel voting module to combine the outputs of all DrosoNets into the final place prediction which considers multiple top reference candidates from each DrosoNet. RegionDrosoNet outperforms other lightweight VPR techniques when dealing with both appearance changes and viewpoint variations. Moreover, it competes with computationally expensive methods on some benchmark datasets at a small fraction of their online inference time.
Item Type: | Article |
---|---|
Uncontrolled Keywords: | Vision-based navigation; localization; bioinspired robot learning |
Divisions: | Faculty of Science and Health Faculty of Science and Health > Computer Science and Electronic Engineering, School of |
SWORD Depositor: | Unnamed user with email elements@essex.ac.uk |
Depositing User: | Unnamed user with email elements@essex.ac.uk |
Date Deposited: | 20 Mar 2024 15:25 |
Last Modified: | 16 May 2024 22:15 |
URI: | http://repository.essex.ac.uk/id/eprint/37857 |
Available files
Filename: Aggregating_Multiple_Bio-Inspired_Image_Region_Classifiers_For_Effective_And_Lightweight_Visual_Place_Recognition.pdf
Licence: Creative Commons: Attribution 4.0