University of Surrey

Test tubes in the lab Research in the ATI Dance Research

A Saliency-based Framework for 2D-3D Registration

Brown, M, Guillemaut, Jean-Yves and Windridge, D (2015) A Saliency-based Framework for 2D-3D Registration In: 2014 International Conference on Computer Vision Theory and Applications (VISAPP), 5-8 Jan. 2014, Lisbon, Portugal.

BrownVISAPP2014_camera_ready.pdf - Accepted version Manuscript
Available under License : See the attached licence file.

Download (1MB) | Preview
Text (licence)
Available under License : See the attached licence file.

Download (33kB) | Preview


Here we propose a saliency-based filtering approach to the problem of registering an untextured 3D object to a single monocular image. The principle of saliency can be applied to a range of modalities and domains to find intrinsically descriptive entities from amongst detected entities, making it a rigorous approach to multi-modal registration. We build on the Kadir-Brady saliency framework due to its principled information-theoretic approach which enables us to naturally extend it to the 3D domain. The salient points from each domain are initially aligned using the SoftPosit algorithm. This is subsequently refined by aligning the silhouette with contours extracted from the image. Whereas other point based registration algorithms focus on corners or straight lines, our saliency-based approach is more general as it is more widely applicable e.g. to curved surfaces where a corner detector would fail. We compare our salient point detector to the Harris corner and SIFT keypoint detectors and show it generally achieves superior registration accuracy

Item Type: Conference or Workshop Item (Conference Paper)
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering > Centre for Vision Speech and Signal Processing
Authors :
Brown, M
Windridge, D
Date : 12 October 2015
Copyright Disclaimer : © 2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Uncontrolled Keywords : pose estimation, registration, saliency
Depositing User : Symplectic Elements
Date Deposited : 28 Mar 2017 13:14
Last Modified : 19 Dec 2019 00:29

Actions (login required)

View Item View Item


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