Dual-Hierarchy Graph Method for Object Indexing and Recognition

摘要

UMD built an innovative general purpose, inherently robust system for object representation and recognition. The system is model-based and knowledge-based, unlike most of the current methods which rely on generic statistical inference. This knowledge is intrinsic to the objects themselves, based on geometric and semantic relations among objects. Therefor the system is insensitive to external interferences such as viewpoint changes (pose, scale etc.), illumination changes, occlusion, shadows, sensor noise etc. It also handles variability in the object itself, e.g. articulation or camouflage. All available models are represented in one graph consisting of two independent but interlocking hierarchies. One of these intrinsic hierarchies is a 'Level of Abstraction (LOA) hierarchy, going up from specific to generic objects. The other is based on parts of the object.