eprintid: 1350009
rev_number: 31
eprint_status: archive
userid: 608
dir: disk0/01/35/00/09
datestamp: 2012-06-28 18:46:27
lastmod: 2021-11-15 01:55:15
status_changed: 2012-06-28 18:46:27
type: proceedings_section
metadata_visibility: show
item_issues_count: 0
creators_name: Campbell, NDF
creators_name: Vogiatzis, G
creators_name: Hernández, C
creators_name: Cipolla, R
title: Automatic Object Segmentation from Calibrated Images
ispublished: pub
divisions: UCL
divisions: B04
divisions: C05
divisions: F48
note: “© 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.”
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.
date: 2011-11
publisher: IEEE
official_url: http://dx.doi.org/10.1109/CVMP.2011.21
vfaculties: VENG
oa_status: green
full_text_type: other
language: eng
primo: open
primo_central: open_green
verified: verified_manual
elements_source: Manually entered
elements_id: 416404
doi: 10.1109/CVMP.2011.21
isbn_13: 9781467301176 
lyricists_name: Campbell, Neill
lyricists_id: NCAMP92
full_text_status: public
place_of_pub: USA
pagerange: 126-137
event_title: 2011 Conference for Visual Media Production 
event_location: London, UK
book_title: CVMP 2011: The Eighth European Conference on Visual Media Production
citation:        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   
 
document_url: https://discovery.ucl.ac.uk/id/eprint/1350009/1/campbell_cvmp11_auto_obj_seg.pdf