Visual odometry in dynamic environments with geometric multi-layer optimisation

Show simple item record

dc.contributor.author Geng, H en
dc.contributor.author Chien, HJ en
dc.contributor.author Nicolescu, Radu en
dc.contributor.author Klette, R en
dc.coverage.spatial Hobart, Australia en
dc.date.accessioned 2017-07-31T05:04:19Z en
dc.date.issued 2016 en
dc.identifier.citation AI 2016: Advances in Artificial Intelligence, Hobart, Australia, 05 Dec 2016 - 08 Dec 2016. Lecture Notes in Computer Science: AI 2016: Advances in Artificial Intelligence:. Springer Verlag. 9992: 183-190. 2016 en
dc.identifier.isbn 9783319501260 en
dc.identifier.issn 0302-9743 en
dc.identifier.uri http://hdl.handle.net/2292/34633 en
dc.description.abstract This paper presents a novel approach for optimising visual odometry results in a dynamic outdoor environment. Egomotion estimation is still considered to be one of the more difficult tasks in computer vision because of its continued computation pipeline: every phase of visual odometry can be a source of noise or errors, and influence future results. Also, tracking features in a dynamic environment is very challenging. Since feature tracking can only match two features in integer coordinates, there will be a data loss at sub-pixel level. In this paper we introduce a weighting scheme that measures the geometric relations between different layers: We divide tracked features into three groups based on geometric constrains; each group is recognised as being a “layer”. Each layer has a weight which depends on the distribution of the grouped features on the 2D image and the actual position in 3D scene coordinates. This geometric multi-layer approach can effectively remove all the dynamic features in the scene, and provide more reliable feature tracking results. Moreover, we propose a 3-state Kalman filter optimisation approach. Our method follows the traditional process of visual odometry algorithms by focusing on motion estimation between pairs of two consecutive frames. Experiments and evaluations are carried out for trajectory estimation. We use the provided ground truth of the KITTI data-sets to analyse mean rotation and translation errors over distance. en
dc.publisher Springer Verlag en
dc.relation.ispartof AI 2016: Advances in Artificial Intelligence en
dc.relation.ispartofseries Lecture Notes in Computer Science: AI 2016: Advances in Artificial Intelligence: en
dc.rights Items in ResearchSpace are protected by copyright, with all rights reserved, unless otherwise indicated. Previously published items are made available in accordance with the copyright policy of the publisher. en
dc.rights.uri https://researchspace.auckland.ac.nz/docs/uoa-docs/rights.htm en
dc.title Visual odometry in dynamic environments with geometric multi-layer optimisation en
dc.type Conference Item en
dc.identifier.doi 10.1007/978-3-319-50127-7_15 en
pubs.begin-page 183 en
pubs.volume 9992 en
dc.rights.holder Copyright: Springer Verlag en
pubs.end-page 190 en
pubs.finish-date 2016-12-08 en
pubs.publication-status Published en
pubs.start-date 2016-12-05 en
dc.rights.accessrights http://purl.org/eprint/accessRights/RestrictedAccess en
pubs.subtype Proceedings en
pubs.elements-id 606292 en
pubs.org-id Science en
pubs.org-id School of Computer Science en
dc.identifier.eissn 1611-3349 en
pubs.record-created-at-source-date 2017-07-31 en


Files in this item

There are no files associated with this item.

Find Full text

This item appears in the following Collection(s)

Show simple item record

Share

Search ResearchSpace


Browse

Statistics