Contour Fragment Grouping and Shared, Simple Occluders

Bounding contours of physical objects are often fragmented by other occluding objects. Long-distance perceptual grouping seeks to join fragments belonging to the same object. Approaches to grouping based on invariants assume objects are in restricted classes, while those based on minimal energy continuations assume a shape for the missing contours and require this shape to drive the grouping process. While these assumptions may be appropriate for certain speci c tasks or when contour gaps are small, in general occlusion can give rise to large gaps, and thus long-distance contour fragment grouping is a di erent type of perceptual organization problem. We propose the long-distance principle that those fragments should be grouped whose fragmentation could have arisen from a shared, simple occluder. The gap skeleton is introduced as a representation of this virtual occluder, and an algorithm for computing it is given. Finally, we show that a view of the virtual occluder as a disc can be interpreted as an equivalence class of curves interpolating the fragment endpoints. 1 Figure 1: Di erent distance scales for contour fragmentation. (left) The bounding contour of a camel is broken by a foreground palm tree. (center) Curve fragments remaining after depth separation using T-junctions. This is long-scale fragmentation. (right)Magni cation of rear leg. Observe slight contour gaps can be caused by sensor noise. This is short-scale fragmentation. The techniques developed in this paper are for long-scale fragmentation.