Categorization of Transparent-Motion Patterns Using the Projective Plane

Based on a new framework for the description of N transparent motions we categorize different types of transparent-motion patterns. Confidence measures for the presence of all these classes of patterns are defined in terms of the ranks of the generalized structure tensor. To resolve the correspondence between the ranks of the tensors and the motion patterns, we introduce the projective plane as a new way of describing motion patterns. Transparent motions can occur in video sequences and are relevant for problems in human and computer vision. We show a few examples for how our framework can be applied to describe the perception of multiple-motion patterns and predict a new illusion.