Sciweavers

Share
ICCV
2007
IEEE

Learning to Find Object Boundaries Using Motion Cues

9 years 7 months ago
Learning to Find Object Boundaries Using Motion Cues
While great strides have been made in detecting and localizing specific objects in natural images, the bottom-up segmentation of unknown, generic objects remains a difficult challenge. We believe that occlusion can provide a strong cue for object segmentation and "pop-out", but detecting an object's occlusion boundaries using appearance alone is a difficult problem in itself. If the camera or the scene is moving, however, that motion provides an additional powerful indicator of occlusion. Thus, we use standard appearance cues (e.g. brightness/color gradient) in addition to motion cues that capture subtle differences in the relative surface motion (i.e. parallax) on either side of an occlusion boundary. We describe a learned local classifier and global inference approach which provide a framework for combining and reasoning about these appearance and motion cues to estimate which region boundaries of an initial over-segmentation correspond to object/occlusion boundaries ...
Andrew N. Stein, Derek Hoiem, Martial Hebert
Added 14 Oct 2009
Updated 30 Oct 2009
Type Conference
Year 2007
Where ICCV
Authors Andrew N. Stein, Derek Hoiem, Martial Hebert
Comments (0)
books