Matching and Interpretation of Planar Motion Using Tensor Voting

An ellipse that is rotating within an image can be interpreted in different ways under different conditions. We are interested in the 'thin vs. fat ellipse' phenomenon; a thin rotating ellipse is perceived as undergoing rigid rotation, while a fat one is perceived as undergoing nonrigid deformation. Our computational model tries to emulate human perception using the tensor voting framework. The original 4-D tensor voting formalism is found not sufficient to solve this problem, and we augment it here to explicitly handle rotation and deformation.