Optic Flow Statistics and Intrinsic Dimensionality
Sinan Kalkan, Dirk Calow, Michael Felsberg, Florentin Wörgötter, Markus Lappe, Norbert Krüger · 2004
Different kinds of visual sub-structures can be distinguished by the intrinsic dimensionality of the local signals. The concept of intrinsic dimensionality has been mostly exercised using discrete formulations. A recent work (Kruger and Felsberg, 2003; Felsberg and Kruger, 2003) introduced a continuous definition and showed that the inherent structure of the intrinsic dimensionality has essentially the form of a triangle. The current study work analyzes the distribution of signals according to the continuous interpretation of intrinsic dimensionality and the relation to orientation and optic flow features of image patches. Among other things, we give a quantitative interpretation of the distribution of signals according to their intrinsic dimensionality that reveals specific patterns associated to established sub-structures in computer vision. Furthermore, we link quantitative and qualitative properties of the distribution of optic-flow error estimates to these patterns.