David Gustavsson

Learn More
In this paper we propose a method for variational segmenta-tion and contour matching of non-rigid objects in image sequences which can deal with the occlusions. The method is based on a region-based active contour model of the Chan-Vese, augmented with a frame-to-frame interaction term which uses the segmentation result from the previous frame as a shape(More)
We address the problem of nonrigid object segmentation in image sequences in the presence of occlusions. The proposed variational segmentation method is based on a region-based active contour of the Chan-Vese model augmented with a frame-to-frame interaction term as a shape prior. The interaction term is constructed to be pose-invariant by minimizing over a(More)
  • 1