A Monocular Indoor Localiser Based on an Extended Kalman Filter and Edge Images from a Convolutional Neural Network

Unicomb, J; Ranasinghe, R; Dantanarayana, L; Dissanayake, G

A Monocular Indoor Localiser Based on an Extended Kalman Filter and Edge Images from a Convolutional Neural Network

Unicomb, J Ranasinghe, R

Dantanarayana, L

Dissanayake, G

Permalink

Publication Type:: Conference Proceeding
Citation:: IEEE International Conference on Intelligent Robots and Systems, 2018, pp. 6335 - 6340
Issue Date:: 2018-12-27

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Accepted Manuscript versionAdobe PDF (4.01 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Unicomb, J	en_US
dc.contributor.author	Ranasinghe, R https://orcid.org/0000-0002-3785-3723	en_US
dc.contributor.author	Dantanarayana, L https://orcid.org/0000-0002-8887-329X	en_US
dc.contributor.author	Dissanayake, G https://orcid.org/0000-0002-7992-0680	en_US
dc.date.available	2020-10-01T19:04:36Z
dc.date.issued	2018-12-27	en_US
dc.identifier.citation	IEEE International Conference on Intelligent Robots and Systems, 2018, pp. 6335 - 6340	en_US
dc.identifier.isbn	9781538680940	en_US
dc.identifier.issn	2153-0858	en_US
dc.identifier.uri	http://hdl.handle.net/10453/128212
dc.description.abstract	© 2018 IEEE. The main contribution of this paper is an extended Kalman filter (EKF)based algorithm for estimating the 6 DOF pose of a camera using monocular images of an indoor environment. In contrast to popular visual simultaneous localisation and mapping algorithms, the technique proposed relies on a pre-built map represented as an unsigned distance function of the ground plane edges. Images from the camera are processed using a Convolutional Neural Network (CNN)to extract a ground plane edge image. Pixels that belong to these edges are used in the observation equation of the EKF to estimate the camera location. Use of the CNN makes it possible to extract ground plane edges under significant changes to scene illumination. The EKF framework lends itself to use of a suitable motion model, fusing information from any other sensors such as wheel encoders or inertial measurement units, if available, and rejecting spurious observations. A series of experiments are presented to demonstrate the effectiveness of the proposed technique.	en_US
dc.relation.ispartof	IEEE International Conference on Intelligent Robots and Systems	en_US
dc.relation.isbasedon	10.1109/IROS.2018.8594337	en_US
dc.rights	info:eu-repo/semantics/openAccess
dc.title	A Monocular Indoor Localiser Based on an Extended Kalman Filter and Edge Images from a Convolutional Neural Network	en_US
dc.type	Conference Proceeding
utslib.for	0801 Artificial Intelligence and Image Processing	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Mechanical and Mechatronic Engineering
pubs.organisational-group	/University of Technology Sydney/Strength - CAS - Centre for Autonomous Systems
utslib.copyright.status	open_access	*
pubs.publication-status	Published	en_US

Abstract:

© 2018 IEEE. The main contribution of this paper is an extended Kalman filter (EKF)based algorithm for estimating the 6 DOF pose of a camera using monocular images of an indoor environment. In contrast to popular visual simultaneous localisation and mapping algorithms, the technique proposed relies on a pre-built map represented as an unsigned distance function of the ground plane edges. Images from the camera are processed using a Convolutional Neural Network (CNN)to extract a ground plane edge image. Pixels that belong to these edges are used in the observation equation of the EKF to estimate the camera location. Use of the CNN makes it possible to extract ground plane edges under significant changes to scene illumination. The EKF framework lends itself to use of a suitable motion model, fusing information from any other sensors such as wheel encoders or inertial measurement units, if available, and rejecting spurious observations. A series of experiments are presented to demonstrate the effectiveness of the proposed technique.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/128212