Object detection and segmentation can be facilitated by the availability of a reference object. However, accounting for possible transformations between the different object views, as part of the segmentation process, remains a challenge. Recent works address this problem by using comprehensive training data. Other approaches are applicable only to limited object classes or can only accommodate similarity transformations. We suggest a novel variational approach to prior-based segmentation, which accounts for planar projective transformation, using a single reference object. The prior shape is registered concurrently with the segmentation process, without point correspondence. The algorithm detects the object of interest and correctly extracts its boundaries. The homography between the two object views is accurately recovered as well. Extending the Chan-Vese level set framework, we propose a region-based segmentation functional that includes explicit representation of the projective homography between the prior shape and the shape to segment. The formulation is derived from two-view geometry. Segmentation of a variety of objects is demonstrated and the recovered transformation is verified.
Prior-based segmentation by projective registration and level sets
Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 ; 1 ; 204-211 Vol. 1
2005-01-01
735979 byte
Conference paper
Electronic Resource
English
Prior-Based Segmentation by Projective Registration and Level Sets
British Library Conference Proceedings | 2005
|Level set based shape prior segmentation
IEEE | 2005
|Document Registration Using Projective Geometry
British Library Conference Proceedings | 1995
|Document registration using projective geometry
IEEE | 1995
|Prior-based Segmentation and Shape Registration in the Presence of Perspective Distortion
British Library Online Contents | 2007
|