Inference and Visualization of Spatial Relations

We present an approach to spatial inference which is based on the procedural semantics of spatial relations. In contrast to qualitative reasoning, we do not use discrete symbolic models. Instead, relations between pairs of objects are represented by parameterized homogeneous transformation matrices with numerical constraints. A textual description of a spatial scene is transformed into a graph with objects and annotated local reference systems as nodes and relations as arcs. Inference is realized by multiplication of transformation matrices, constraint propagation and verification. Constraints consisting of equations and inequations containing trigonometric functions can be solved using machine learning techniques. By assigning values to the parameters and using heuristics for the placement of objects, a visualization of the described spatial layout can be generated from the graph.

• Type: Conference
• Year: 2000
• Where: SPATIALCOGNITION
• Authors: Sylvia Wiebrock, Lars Wittenburg, Ute Schmid, Fritz Wysotzki
• Keywords: Information Management, Spatial, Spatial Inference, SPATIALCOGNITION 2000, Transformation Matrices