Efficient collision detection between 2D polygons

Abstract

Collision detection between moving objects is an open question which raises major problems concerning its algorithmic complexity. In this paper we present a polygon collision detection algorithm which uses polygon decomposition through triangle coverings and polygon influence areas (implemented by signs of barycentric coordinates). By using influence areas and the temporal and spatial coherence property, the amount of time needed to detect a collision between objects is reduced. By means of these techniques, a valid representation for any kind of polygon is obtained, whether concave or convex, manifold or non-manifold, with or without holes, as well as a collision detection algorithm for this type of figures. This detection algorithm has been compared with the well-known PIVOT2D [Hof01] one and better results have been achieved in most situations. This improvement together with its possible extension to 3D makes it an attractive method because pre-processing of the polygons is no longer necessary. Besides, since this method uses sign operations, it proves to be a simple, more efficient and robust method.