Authors:
Ketut Fundana
1
;
Niels Chr. Overgaard
1
;
Anders Heyden
1
;
David Gustavsson
2
and
Mads Nielsen
2
Affiliations:
1
Applied Mathematics Group, School of Technology and Society, Malmö University, Sweden
;
2
DIKU, Copenhagen University, Denmark
Keyword(s):
Segmentation, occlusion, image sequences, variational active contour, variational contour matching.
Related
Ontology
Subjects/Areas/Topics:
Applications
;
Computer Vision, Visualization and Computer Graphics
;
Image and Video Analysis
;
Image Registration
;
Pattern Recognition
;
Segmentation and Grouping
;
Software Engineering
;
Surface Geometry and Shape
;
Video Analysis
Abstract:
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 group of transformations and to allow moderate deformation in the shape of the contour. The segmentation method is then coupled with a novel variational contour matching formulation between two consecutive contours which gives a mapping of the intensities from the interior of the previous contour to the next. With this information occlusions can be detected and located using deviations from predicted intensities and the missing intensities in the occluded regions can be reconstructed. After reconstructing the occluded regions in the novel image, the segmentation can then be improved. Experimental results on synthetic and real im
age sequences are shown.
(More)