Automatic object segmentation from calibrated images

Neill D.F. Campbell, George Vogiatzis, Carlos Hernández, Roberto Cipolla

Research output: Chapter in Book/Published conference outputConference publication


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.
Original languageEnglish
Title of host publication2011 Conference for Visual Media Production (CVMP)
Number of pages12
ISBN (Print)978-1-4673-0117-6
Publication statusPublished - 2011
Event2011 Conference for Visual Media Production - London, United Kingdom
Duration: 16 Nov 201117 Nov 2011


Conference2011 Conference for Visual Media Production
Abbreviated titleCVMP 2011
Country/TerritoryUnited Kingdom


  • multi view
  • foreground segmentation


Dive into the research topics of 'Automatic object segmentation from calibrated images'. Together they form a unique fingerprint.

Cite this