Research Repository

CAMAL: Context-Aware Multi-scale Attention framework for Lightweight Visual Place Recognition

Khaliq, Ahmad and Ehsan, Shoaib and Milford, Michael and McDonald-Maier, Klaus (2019) CAMAL: Context-Aware Multi-scale Attention framework for Lightweight Visual Place Recognition. Working Paper. arXiv. (Unpublished)

[img]
Preview
Text
1909.08153v1.pdf

Download (2MB) | Preview

Abstract

In the last few years, Deep Convolutional Neural Networks (D-CNNs) have shown state-of-the-art performances for Visual Place Recognition (VPR). Their prestigious generalization power has played a vital role in identifying persistent image regions under changing conditions and viewpoints. However, against the computation intensive D-CNNs based VPR algorithms, lightweight VPR techniques are preferred for resource-constraints mobile robots. This paper presents a lightweight CNN-based VPR technique that captures multi-layer context-aware attentions robust under changing environment and viewpoints. Evaluation of challenging benchmark datasets reveals better performance at low memory and resources utilization over state-of-the-art contemporary VPR methodologies.

Item Type: Monograph (Working Paper)
Additional Information: Submitted in ICRA 2020
Uncontrolled Keywords: cs.CV, cs.CV
Divisions: Faculty of Science and Health > Computer Science and Electronic Engineering, School of
Depositing User: Elements
Date Deposited: 22 May 2020 15:36
Last Modified: 22 May 2020 16:15
URI: http://repository.essex.ac.uk/id/eprint/27583

Actions (login required)

View Item View Item