Spatio-temporal video segmentation with shape growth or shrinkage constraint (ATTENTION en salle de réunion, aile Turing)
vendredi 6 décembre 2013, 14h00 - 15h00
We will present a new framework for joint segmentation of monotonously growing or shrinking shapes in a time series of extremely noisy images, in a low computational time. We consider the image sequences, where both foreground and background intensity distributions can vary significantly over time, foreground can be heavily occluded or undistinguishable from a part of the background, and data for some pixels can be missing. The task of segmenting the image time series is expressed as an optimization problem using the spatio-temporal graph of pixels, in which we are able to impose the constraint of shape growth or of shrinkage by introducing monodirectional infinite links connecting pixels at the same spatial locations in successive image frames. The globally-optimal solution is computed with a graph cut.
The performance of the proposed framework will be validated on three applications: segmentation of melting sea ice floes and of growing burned areas from time series of 2D satellite images, and segmentation of a growing brain tumor from sequences of 3D medical scans. In the latter application, we impose an additional inter-sequences inclusion constraint by adding directed infinite links between pixels of dependent image structures. We will demonstrate that the new method is robust to important noise and low contrast, and it copes well with missing data. It shows linear complexity in practice, so that globally optimal shape-consistent segmentations of image time series are obtained in a matter of seconds.