2008 IEEE Conference on Computer Vision and Pattern Recognition
Download PDF

Abstract

In the last decade, graph-cut optimization has been popular for a variety of pixel labeling problems. Typically graph-cut methods are used to incorporate a smoothness prior on a labeling. Recently several methods incorporated ordering constraints on labels for the application of object segmentation. An example of an ordering constraint is prohibiting a pixel with a “car wheel” label to be above a pixel with a “car roof” label. We observe that the commonly used graph-cut based α-expansion is more likely to get stuck in a local minimum when ordering constraints are used. For certain models with ordering constraints, we develop new graph-cut moves which we call order-preserving moves. Order-preserving moves act on all labels, unlike α-expansion. Although the global minimum is still not guaranteed, optimization with order-preserving moves performs significantly better than α-expansion. We evaluate order-preserving moves for the geometric class scene labeling (introduced by Hoiem et al.) where the goal is to assign each pixel a label such as “sky”, “groun”, etc., so ordering constraints arise naturally. In addition, we use order-preserving moves for certain simple shape priors in graphcut segmentation, which is a novel contribution in itself.
Like what you’re reading?
Already a member?Sign In
Member Price
$11
Non-Member Price
$21
Add to CartSign In
Get this article FREE with a new membership!

Related Articles