Point-based medialness for movement computing

We introduce the idea of using a perception-based medial point description of a biological form (such as a 2D profile of a moving animal) as a basis for movement computing which delivers computational schemes to automatically annotate movement and be capable of producing meaningful qualitative descriptions. We distinguish interior from exterior shape representation. Interior medialness is used to characterise deformations from straightness, corners and necks, while exterior medialness identifies the main concavities and inlands which are useful to verify parts extent and reason about articulation and movement. We define an interior dominant point as a well localised peak value in medialness representation, while an exterior dominant point is evaluated by identifying a region of concavity sub-tended by a minimum angular support. Furthermore, significant convex points are extracted from the object's form to further characterise the elongation of parts. We propose that our evaluated feature points are sufficiently representative, as a basis for shape characterisation, to address many of the goals of movement computing.