Research Repository

A Holistic Visual Place Recognition Approach Using Lightweight CNNs for Significant ViewPoint and Appearance Changes

Khaliq, Ahmad and Ehsan, Shoaib and Chen, Zetao and Milford, Michael and McDonald-Maier, Klaus (2020) 'A Holistic Visual Place Recognition Approach Using Lightweight CNNs for Significant ViewPoint and Appearance Changes.' IEEE Transactions on Robotics, 36 (2). pp. 561-569. ISSN 1552-3098

[img]
Preview
Text
08944012.pdf - Published Version
Available under License Creative Commons Attribution.

Download (5MB) | Preview

Abstract

This article presents a lightweight visual place recognition approach, capable of achieving high performance with low computational cost, and feasible for mobile robotics under significant viewpoint and appearance changes. Results on several benchmark datasets confirm an average boost of 13% in accuracy, and 12x average speedup relative to state-of-the-art methods.

Item Type: Article
Additional Information: Conditionally Accepted as short paper at IEEE Transactions on Robotics (T-RO)
Uncontrolled Keywords: Convolutional neural network (CNN); feature encoding; robot localization; vector of locally aggregated descriptors (VLADs); visual place recognition (VPR)
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: 31 Jan 2020 14:57
Last Modified: 15 Jan 2022 01:26
URI: http://repository.essex.ac.uk/id/eprint/26329

Actions (login required)

View Item View Item