Submitted by kyoungmu on 2010, February 2 - 03:53.61 views | 0 comments | 7 votes
pdf

Partially Occluded Object-Specific Segmentation in View-Based Recognition

  • Partially Occluded Object-Specific Segmentation in View-Based Recognition
Gallery
cv.snu.ac.kr
We present a novel object-specific segmentation method which can be used in view-based object recognition systems. Previous object segmentation approaches generate inexact results especially in partially occluded and cluttered environment because their top-down strategies fail to explain the details of various specific objects. On the contrary, our segmentation method efficiently exploits the information of the matched model views in view-based recognition because the aligned model view to the input image can serve as the best top-down cue for object segmentation. In this paper, we cast the problem of partially occluded object segmentation as that of labelling displacement and foreground status simultaneously for each pixel between the aligned model view and an input image. The problem is formulated by a maximum a posteriori Markov random field (MAP-MRF) model which minimizes a particular energy function. Our method overcomes complex occlusion and clutter and provides accurate segmentation boundaries by combining a bottom-up segmentation cue together. We demonstrate the efficiency and robustness of it by experimental results on various objects under occluded and cluttered environments.
Minsu Cho, Kyoung Mu Lee
CVPR - 2007
IEEE

Traffic Map
  • Delicious
  • Digg
  • Facebook
  • Google
  • Yahoo
Keywords computer vision | CVPR 2007 | occlusion | segmentation | View-based recognition |
Category Computer Science | Engineering |


Added 02 Feb 2010
Updated 02 Feb 2010
Type Conference
Year 2007
Where CVPR
Authors Minsu Cho (Seoul National University), Kyoung Mu Lee (Seoul National University)

Discussion Board (0)