University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Scalable object instance recognition based on keygraph matching

Dazzi, Estephan, de Campos, Teofilo, Hilton, Adrian and Cesar Jr., Roberto M. (2017) Scalable object instance recognition based on keygraph matching Pattern Recognition Letters.

[img] Text
Scalable object instance recognition based on keygraph matching.pdf - Accepted version Manuscript
Restricted to Repository staff only until 1 November 2018.

Download (2MB)

Abstract

We propose a generalisation of the local feature matching framework, where keypoints are replaced by k-keygraphs, i.e., isomorphic directed attributed graphs of cardinality k whose vertices are keypoints. Keygraphs have structural and topological properties which are discriminative and efficient to compute, based on graph edge length and orientation as well as vertex scale and orientation. Keypoint matching is performed based on descriptor similarity. Next, 2-keygraphs are calculated; as a result, the number of incorrect keypoint matches reduced in 75% (while the correct keypoint matches were preserved). Then, 3-keygraphs are calculated, followed by 4-keygraphs; this yielded a significant reduction of 99% in the number of remaining incorrect keypoint matches. The stage that finds 2-keygraphs has a computational cost equal to a small fraction of the cost of the keypoint matching stage, while the stages that find 3-keygraphs or 4-keygraphs have a negligible cost. In the final stage, RANSAC finds object poses represented as affine transformations mapping images. Our experiments concern large-scale object instance recognition subject to occlusion, background clutter and appearance changes. By using 4-keygraphs, RANSAC needed 1% of the iterations in comparison with 2-keygraphs or simple keypoints. As a result, using 4-keygraphs provided a better efficiency as well as allowed a larger number of initial keypoints matches to be established, which increased performance.

Item Type: Article
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :
NameEmailORCID
Dazzi, EstephanUNSPECIFIEDUNSPECIFIED
de Campos, TeofiloUNSPECIFIEDUNSPECIFIED
Hilton, AdrianA.Hilton@surrey.ac.ukUNSPECIFIED
Cesar Jr., Roberto M.UNSPECIFIEDUNSPECIFIED
Date : 2 November 2017
Identification Number : 10.1016/j.patrec.2017.10.038
Copyright Disclaimer : © 2017 Published by Elsevier B.V
Uncontrolled Keywords : Local invariant features; Semi-local graph matching; Graph topological properties
Depositing User : Clive Harris
Date Deposited : 23 Jan 2018 08:37
Last Modified : 23 Jan 2018 08:37
URI: http://epubs.surrey.ac.uk/id/eprint/845661

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800