Exploiting context in function-based reasoning

This paper presents the framework of the new context-based reasoning components of the GRUFF (Generic Recognition Using Form and Function) system. This is a generic object recognition system which reasons about and generates plans for understanding 3-D scenes of objects. A range image is generated from a stereo image pair and is provided as input to a multi-stage recognition system. A 3-D model of the scene, extracted from the range image, is processed to identify evidence of potential functionality directed by contextual cues. This recognition process considers the shape-suggested functionality by applying concepts of physics and causation to label an object's potential functionality. The methodology for context-based reasoning relies on determining the significance of the accumulated functional evidence derived from the scene. For example, functional evidence for a chair or multiple chairs along with a table, in set configurations, is used to infer the existence of scene concepts such as "office" or "meeting room space." Results of this work are presented for scene understanding derived from both simulated and real sensors positioned in typical office and meeting room environments.