The framework of the context-based reasoning components of the Gruff (Generic Recognition Using Form and Function) system will be presented. This is a genericobject recognition system which reasons about and generates plans for understanding 3-D scenes of objects. The recognition system considers the shape-suggested functionality of observed shapes by labeling the 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 objects such as chairs or tables can be used to infer the existence of scene concepts such as "office" or "meeting room space."

Please join us beforehand in the Math Lab for Pizza!!!!
North Science 111
11:50-12:08