GeoS: Geodesic Image Segmentation

This paper presents GeoS, a new algorithm for the efficient segmentation of n-dimensional image and video data. The segmentation problem is cast as approximate energy minimization in a conditional random field. A new, parallel filtering operator built upon efficient geodesic distance computation is used to propose a set of spatially smooth, contrast-sensitive segmentation hypotheses. An economical search algorithm finds the solution with minimum energy within a sensible and highly restricted subset of all possible labellings. Advantages include: i) computational efficiency with high segmentation accuracy; ii) the ability to estimate an approximation to the posterior over segmentations; iii) the ability to handle generally complex energy models. Comparison with max-flow indicates up to 60 times greater computational efficiency as well as greater memory efficiency. GeoS is validated quantitatively and qualitatively by thorough comparative experiments on existing and novel ground-truth da...

• Type: Conference
• Year: 2008
• Where: ECCV
• Authors: Antonio Criminisi, Toby Sharp, Andrew Blake
• Keywords: Automatic Segmentation, Computer Vision, Contrast-sensitive Segmentation Hypotheses, ECCV 2008, Efficient Segmentation, Greater Computational Efficiency, Segmentation Problem