Collective Classification in Semantic Mapping with a Probabilistic Description Logic.
Fabiano Rogério Corrêa, Fábio Gagliardi Cozman, Jun Okamoto · 2011
Abstract. Sensor data classification is very dependent on which fea-tures represent primitives. We consider line segments extracted from laser points as primitives, and focus on their collective classification into door or wall objects, so as to build semantic maps. Because features may have non-trivial characteristics, and sensor primitives may be inter-related in complex ways, we represent features of spatial relationships using a prob-abilistic description logic. 1