UCL logo

UCL Discovery

UCL home » Library Services » Electronic resources » UCL Discovery

Automatic Object Segmentation from Calibrated Images

Campbell, NDF; Vogiatzis, G; Hernández, C; Cipolla, R; (2011) Automatic Object Segmentation from Calibrated Images. In: CVMP 2011: The Eighth European Conference on Visual Media Production. (pp. pp. 126-137). IEEE: USA. Green open access

[img]PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
13Mb

Abstract

This paper addresses the problem of automatically obtaining the object/background segmentation of a rigid 3D object observed in a set of images that have been calibrated for camera pose and intrinsics. Such segmentations can be used to obtain a shape representation of a potentially texture-less object by computing a visual hull. We propose an automatic approach where the object to be segmented is identified by the pose of the cameras instead of user input such as 2D bounding rectangles or brush-strokes. The key behind our method is a pairwise MRF framework that combines (a) foreground/background appearance models, (b) epipolar constraints and (c) weak stereo correspondence into a single segmentation cost function that can be efficiently solved by Graph-cuts. The segmentation thus obtained is further improved using silhouette coherency and then used to update the foreground/background appearance models which are fed into the next Graph-cut computation. These two steps are iterated until segmentation convergences. Our method can automatically provide a 3D surface representation even in texture-less scenes where MVS methods might fail. Furthermore, it confers improved performance in images where the object is not readily separable from the background in colour space, an area that previous segmentation approaches have found challenging.

Type:Proceedings paper
Title:Automatic Object Segmentation from Calibrated Images
Event:2011 Conference for Visual Media Production
Location:London, UK
ISBN-13:9781467301176
Open access status:An open access version is available from UCL Discovery
DOI:10.1109/CVMP.2011.21
Publisher version:http://dx.doi.org/10.1109/CVMP.2011.21
Language:English
Additional information:“© 2011 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.”
UCL classification:UCL > School of BEAMS > Faculty of Engineering Science > Computer Science

View download statistics for this item

Archive Staff Only: edit this record