Interactive Object Segmentation in Video
by Fitting Splines to Graph Cuts

Iddo Drori    Tommer Leyvand     Daniel Cohen-Or    Hezy Yeshurun

ACM SIGGRAPH 2004 - Poster Session



Object segmentation in image sequences is one of the fundamental problems in computer vision and graphics. This problem is usually addressed either by discrete representations which are currently manifested by graph partitioning techniques, or by continuous methods typically referred to as active contours. In this work we take a unified approach by fitting splines to graph cuts. The strengths of this approach stem from the dual discrete and continuous representations and from allowing the user to refine the result of the cut by fitting a new spline to it and modifying its points.

PDF (670KB)

Some results:

Fish Sequence:

The user specified rough outline spline and the result of our iterative graph-cut (in red).

The spline fitting for the discrete graph-cut data.

Apple QuickTime video (31MB)

Red-Mini Sequence*:


* Images from "The Bourne Identity (2002)",©Universal Studios

Back to my homepage